diff options
| author |  Shawn O. Pearce <spearce@spearce.org> | 2007-01-14 02:44:18 -0500 |
|---|---|---|
| committer | Shawn O. Pearce <spearce@spearce.org> | 2007-01-14 02:44:18 -0500 |
| commit | 1fcdd62adf81a172f45c7c6a58177212d500b9d9 (patch) | |
| tree | 94acde078fd78c3d214fe09d45e85ed346a2f2d4 | |
| parent | Allow creating branches without committing in fast-import. (diff) | |
| parent | git-commit documentation: -a adds and also removes (diff) | |
| download | tgif-1fcdd62adf81a172f45c7c6a58177212d500b9d9.tar.xz | |
Merge branch 'master' into sp/fast-import
I'm bringing master in early so that the OBJ_OFS_DELTA implementation
is available as part of the topic. This way git-fast-import can
learn about this new slightly smaller and faster packfile format,
and can generate them directly rather than needing to have them be
repacked with git-pack-objects.
Due to the API changes in master during the period of development
of git-fast-import, a few minor tweaks to fast-import.c are needed
to produce a working merge. I've done them here as part of the
merge to ensure bisection always works.
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
404 files changed, 36654 insertions, 15208 deletions
diff --git a/.gitignore b/.gitignore index 8ddccd7dac..a9dc462cb5 100644 --- a/.gitignore +++ b/.gitignore @@ -2,13 +2,16 @@ GIT-CFLAGS GIT-VERSION-FILE git git-add +git-add--interactive git-am git-annotate git-apply git-applymbox git-applypatch git-archimport +git-archive git-bisect +git-blame git-branch git-cat-file git-check-ref-format @@ -37,8 +40,10 @@ git-fetch git-fetch-pack git-findtags git-fmt-merge-msg +git-for-each-ref git-format-patch git-fsck-objects +git-gc git-get-tar-commit-id git-grep git-hash-object @@ -46,6 +51,7 @@ git-http-fetch git-http-push git-imap-send git-index-pack +git-init git-init-db git-instaweb git-local-fetch @@ -59,10 +65,12 @@ git-mailsplit git-merge git-merge-base git-merge-index +git-merge-file git-merge-tree git-merge-octopus git-merge-one-file git-merge-ours +git-merge-recur git-merge-recursive git-merge-resolve git-merge-stupid @@ -72,6 +80,7 @@ git-name-rev git-mv git-pack-redundant git-pack-objects +git-pack-refs git-parse-remote git-patch-id git-peek-remote @@ -83,7 +92,9 @@ git-quiltimport git-read-tree git-rebase git-receive-pack +git-reflog git-relink +git-remote git-repack git-repo-config git-request-pull @@ -94,6 +105,7 @@ git-rev-list git-rev-parse git-revert git-rm +git-runstatus git-send-email git-send-pack git-sh-setup @@ -102,6 +114,7 @@ git-shortlog git-show git-show-branch git-show-index +git-show-ref git-ssh-fetch git-ssh-pull git-ssh-push @@ -118,8 +131,8 @@ git-unpack-objects git-update-index git-update-ref git-update-server-info +git-upload-archive git-upload-pack -git-upload-tar git-var git-verify-pack git-verify-tag @@ -140,9 +153,9 @@ git-core.spec *.py[co] config.mak autom4te.cache +config.cache config.log config.status config.mak.autogen config.mak.append configure -git-blame diff --git a/.mailmap b/.mailmap new file mode 100644 index 0000000000..2c658f42f5 --- /dev/null +++ b/.mailmap @@ -0,0 +1,37 @@ +# +# This list is used by git-shortlog to fix a few botched name translations +# in the git archive, either because the author's full name was messed up +# and/or not always written the same way, making contributions from the +# same person appearing not to be so. +# + +Aneesh Kumar K.V <aneesh.kumar@gmail.com> +Chris Shoemaker <c.shoemaker@cox.net> +Daniel Barkalow <barkalow@iabervon.org> +David KÃ¥gedal <davidk@lysator.liu.se> +Fredrik Kuivinen <freku045@student.liu.se> +H. Peter Anvin <hpa@bonde.sc.orionmulti.com> +H. Peter Anvin <hpa@tazenda.sc.orionmulti.com> +H. Peter Anvin <hpa@trantor.hos.anvin.org> +Horst H. von Brand <vonbrand@inf.utfsm.cl> +Joachim Berdal Haga <cjhaga@fys.uio.no> +Jon Loeliger <jdl@freescale.com> +Jon Seymour <jon@blackcubes.dyndns.org> +Karl Hasselström <kha@treskal.com> +Kent Engstrom <kent@lysator.liu.se> +Lars Doelle <lars.doelle@on-line.de> +Lars Doelle <lars.doelle@on-line ! de> +Lukas Sandström <lukass@etek.chalmers.se> +Martin Langhoff <martin@catalyst.net.nz> +Nguyá»…n Thái Ngá»c Duy <pclouds@gmail.com> +Ramsay Allan Jones <ramsay@ramsay1.demon.co.uk> +René Scharfe <rene.scharfe@lsrfire.ath.cx> +Robert Fitzsimons <robfitz@273k.net> +Santi Béjar <sbejar@gmail.com> +Sean Estabrooks <seanlkml@sympatico.ca> +Shawn O. Pearce <spearce@spearce.org> +Tony Luck <tony.luck@intel.com> +Ville Skyttä <scop@xemacs.org> +YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> +anonymous <linux@horizon.com> +anonymous <linux@horizon.net> diff --git a/Documentation/Makefile b/Documentation/Makefile index 0d9ffb4ad9..93c7024b48 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -32,6 +32,9 @@ man7dir=$(mandir)/man7 # DESTDIR= INSTALL?=install +DOC_REF = origin/man + +-include ../config.mak.autogen # # Please note that there is a minor bug in asciidoc. @@ -54,8 +57,8 @@ man7: $(DOC_MAN7) install: man $(INSTALL) -d -m755 $(DESTDIR)$(man1dir) $(DESTDIR)$(man7dir) - $(INSTALL) $(DOC_MAN1) $(DESTDIR)$(man1dir) - $(INSTALL) $(DOC_MAN7) $(DESTDIR)$(man7dir) + $(INSTALL) -m644 $(DOC_MAN1) $(DESTDIR)$(man1dir) + $(INSTALL) -m644 $(DOC_MAN7) $(DESTDIR)$(man7dir) # @@ -105,8 +108,11 @@ WEBDOC_DEST = /pub/software/scm/git/docs $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt rm -f $@+ $@ - sed -e '1,/^$$/d' $? | asciidoc -b xhtml11 - >$@+ + sed -e '1,/^$$/d' $< | asciidoc -b xhtml11 - >$@+ mv $@+ $@ install-webdoc : html sh ./install-webdoc.sh $(WEBDOC_DEST) + +quick-install: + sh ./install-doc-quick.sh $(DOC_REF) $(mandir) diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 90722c21fa..646b6e7331 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -101,8 +101,13 @@ send it "To:" the mailing list, and optionally "cc:" him. If it is trivially correct or after the list reached a consensus, send it "To:" the maintainer and optionally "cc:" the list. +Also note that your maintainer does not actively involve himself in +maintaining what are in contrib/ hierarchy. When you send fixes and +enhancements to them, do not forget to "cc: " the person who primarily +worked on that hierarchy in contrib/. -(6) Sign your work + +(4) Sign your work To improve tracking of who did what, we've borrowed the "sign-off" procedure from the Linux kernel project on patches @@ -144,6 +149,9 @@ then you just add a line saying Signed-off-by: Random J Developer <random@developer.example.org> +This line can be automatically added by git if you run the git-commit +command with the -s option. + Some people also put extra tags at the end. They'll just be ignored for now, but you can do this to mark internal company procedures or just point out some special detail about the sign-off. diff --git a/Documentation/asciidoc.conf b/Documentation/asciidoc.conf index 8196d787ab..44b1ce4c6b 100644 --- a/Documentation/asciidoc.conf +++ b/Documentation/asciidoc.conf @@ -11,6 +11,7 @@ caret=^ startsb=[ endsb=] +tilde=~ ifdef::backend-docbook[] [gitlink-inlinemacro] diff --git a/Documentation/callouts.xsl b/Documentation/callouts.xsl index ad03755d8f..6a361a2136 100644 --- a/Documentation/callouts.xsl +++ b/Documentation/callouts.xsl @@ -13,4 +13,18 @@ <xsl:apply-templates/> <xsl:text>.br </xsl:text> </xsl:template> + +<!-- sorry, this is not about callouts, but attempts to work around + spurious .sp at the tail of the line docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + </xsl:stylesheet> diff --git a/Documentation/config.txt b/Documentation/config.txt index ce722a2db0..f7dba8977f 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -31,6 +31,11 @@ Example external = "/usr/local/bin/gnu-diff -u" renames = true + [branch "devel"] + remote = origin + merge = refs/heads/devel + + Variables ~~~~~~~~~ @@ -71,12 +76,19 @@ core.preferSymlinkRefs:: expect HEAD to be a symbolic link. core.logAllRefUpdates:: - If true, `git-update-ref` will append a line to - "$GIT_DIR/logs/<ref>" listing the new SHA1 and the date/time - of the update. If the file does not exist it will be - created automatically. This information can be used to - determine what commit was the tip of a branch "2 days ago". - This value is false by default (no logging). + Updates to a ref <ref> is logged to the file + "$GIT_DIR/logs/<ref>", by appending the new and old + SHA1, the date/time and the reason of the update, but + only when the file exists. If this configuration + variable is set to true, missing "$GIT_DIR/logs/<ref>" + file is automatically created for branch heads. ++ +This information can be used to determine what commit +was the tip of a branch "2 days ago". ++ +This value is true by default in a repository that has +a working directory associated with it, and false by +default in a bare repository. core.repositoryFormatVersion:: Internal variable identifying the repository format and layout @@ -88,7 +100,7 @@ core.sharedRepository:: group-writable). When 'all' (or 'world' or 'everybody'), the repository will be readable by all users, additionally to being group-shareable. When 'umask' (or 'false'), git will use permissions - reported by umask(2). See gitlink:git-init-db[1]. False by default. + reported by umask(2). See gitlink:git-init[1]. False by default. core.warnAmbiguousRefs:: If true, git will warn you if the ref name you passed it is ambiguous @@ -106,6 +118,34 @@ core.legacyheaders:: database directly (where the "http://" and "rsync://" protocols count as direct access). +core.packedGitWindowSize:: + Number of bytes of a pack file to map into memory in a + single mapping operation. Larger window sizes may allow + your system to process a smaller number of large pack files + more quickly. Smaller window sizes will negatively affect + performance due to increased calls to the operating system's + memory manager, but may improve performance when accessing + a large number of large pack files. ++ +Default is 1 MiB if NO_MMAP was set at compile time, otherwise 32 +MiB on 32 bit platforms and 1 GiB on 64 bit platforms. This should +be reasonable for all users/operating systems. You probably do +not need to adjust this value. ++ +Common unit suffixes of 'k', 'm', or 'g' are supported. + +core.packedGitLimit:: + Maximum number of bytes to map simultaneously into memory + from pack files. If Git needs to access more than this many + bytes at once to complete an operation it will unmap existing + regions to reclaim virtual address space within the process. ++ +Default is 256 MiB on 32 bit platforms and 8 GiB on 64 bit platforms. +This should be reasonable for all users/operating systems, except on +the largest projects. You probably do not need to adjust this value. ++ +Common unit suffixes of 'k', 'm', or 'g' are supported. + alias.*:: Command aliases for the gitlink:git[1] command wrapper - e.g. after defining "alias.last = cat-file commit HEAD", the invocation @@ -119,25 +159,65 @@ apply.whitespace:: Tells `git-apply` how to handle whitespaces, in the same way as the '--whitespace' option. See gitlink:git-apply[1]. -pager.color:: - A boolean to enable/disable colored output when the pager is in - use (default is true). - -diff.color:: +branch.<name>.remote:: + When in branch <name>, it tells `git fetch` which remote to fetch. + If this option is not given, `git fetch` defaults to remote "origin". + +branch.<name>.merge:: + When in branch <name>, it tells `git fetch` the default refspec to + be marked for merging in FETCH_HEAD. The value has exactly to match + a remote part of one of the refspecs which are fetched from the remote + given by "branch.<name>.remote". + The merge information is used by `git pull` (which at first calls + `git fetch`) to lookup the default branch for merging. Without + this option, `git pull` defaults to merge the first refspec fetched. + Specify multiple values to get an octopus merge. + +color.branch:: + A boolean to enable/disable color in the output of + gitlink:git-branch[1]. May be set to `true` (or `always`), + `false` (or `never`) or `auto`, in which case colors are used + only when the output is to a terminal. Defaults to false. + +color.branch.<slot>:: + Use customized color for branch coloration. `<slot>` is one of + `current` (the current branch), `local` (a local branch), + `remote` (a tracking branch in refs/remotes/), `plain` (other + refs), or `reset` (the normal terminal color). The value for + these configuration variables can be one of: `normal`, `bold`, + `dim`, `ul`, `blink`, `reverse`, `reset`, `black`, `red`, + `green`, `yellow`, `blue`, `magenta`, `cyan`, or `white`. + +color.diff:: When true (or `always`), always use colors in patch. When false (or `never`), never. When set to `auto`, use colors only when the output is to the terminal. -diff.color.<slot>:: +color.diff.<slot>:: Use customized color for diff colorization. `<slot>` specifies which part of the patch to use the specified color, and is one of `plain` (context text), `meta` (metainformation), `frag` (hunk header), `old` (removed - lines), or `new` (added lines). The value for these - configuration variables can be one of: `normal`, `bold`, - `dim`, `ul`, `blink`, `reverse`, `reset`, `black`, - `red`, `green`, `yellow`, `blue`, `magenta`, `cyan`, or - `white`. + lines), or `new` (added lines). The values of these + variables may be specified as in color.branch.<slot>. + +color.pager:: + A boolean to enable/disable colored output when the pager is in + use (default is true). + +color.status:: + A boolean to enable/disable color in the output of + gitlink:git-status[1]. May be set to `true` (or `always`), + `false` (or `never`) or `auto`, in which case colors are used + only when the output is to a terminal. Defaults to false. + +color.status.<slot>:: + Use customized color for status colorization. `<slot>` is + one of `header` (the header text of the status message), + `added` or `updated` (files which are added but not committed), + `changed` (files which are changed but not added in the index), + or `untracked` (files which are not tracked by git). The values of + these variables may be specified as in color.branch.<slot>. diff.renameLimit:: The number of files to consider when performing the copy/rename @@ -152,6 +232,25 @@ format.headers:: Additional email headers to include in a patch to be submitted by mail. See gitlink:git-format-patch[1]. +gc.reflogexpire:: + `git reflog expire` removes reflog entries older than + this time; defaults to 90 days. + +gc.reflogexpireunreachable:: + `git reflog expire` removes reflog entries older than + this time and are not reachable from the current tip; + defaults to 30 days. + +gc.rerereresolved:: + Records of conflicted merge you resolved earlier are + kept for this many days when `git rerere gc` is run. + The default is 60 days. See gitlink:git-rerere[1]. + +gc.rerereunresolved:: + Records of conflicted merge you have not resolved are + kept for this many days when `git rerere gc` is run. + The default is 15 days. See gitlink:git-rerere[1]. + gitcvs.enabled:: Whether the cvs pserver interface is enabled for this repository. See gitlink:git-cvsserver[1]. @@ -195,6 +294,12 @@ http.lowSpeedLimit, http.lowSpeedTime:: Can be overridden by the 'GIT_HTTP_LOW_SPEED_LIMIT' and 'GIT_HTTP_LOW_SPEED_TIME' environment variables. +http.noEPSV:: + A boolean which disables using of EPSV ftp command by curl. + This can helpful with some "poor" ftp servers which doesn't + support EPSV mode. Can be overridden by the 'GIT_CURL_FTP_NO_EPSV' + environment variable. Default is false (curl will use EPSV). + i18n.commitEncoding:: Character encoding the commit messages are stored in; git itself does not care per se, but this information is necessary e.g. when @@ -202,6 +307,16 @@ i18n.commitEncoding:: browser (and possibly at other places in the future or in other porcelains). See e.g. gitlink:git-mailinfo[1]. Defaults to 'utf-8'. +i18n.logOutputEncoding:: + Character encoding the commit messages are converted to when + running `git-log` and friends. + +log.showroot:: + If true, the initial commit will be shown as a big creation event. + This is equivalent to a diff against an empty tree. + Tools like gitlink:git-log[1] or gitlink:git-whatchanged[1], which + normally hide the root commit will now show it. True by default. + merge.summary:: Whether to include summaries of merged commits in newly created merge commit messages. False by default. @@ -217,6 +332,22 @@ pull.octopus:: pull.twohead:: The default merge strategy to use when pulling a single branch. +remote.<name>.url:: + The URL of a remote repository. See gitlink:git-fetch[1] or + gitlink:git-push[1]. + +remote.<name>.fetch:: + The default set of "refspec" for gitlink:git-fetch[1]. See + gitlink:git-fetch[1]. + +remote.<name>.push:: + The default set of "refspec" for gitlink:git-push[1]. See + gitlink:git-push[1]. + +repack.usedeltabaseoffset:: + Allow gitlink:git-repack[1] to create packs that uses + delta-base offset. Defaults to false. + show.difftree:: The default gitlink:git-diff-tree[1] arguments to be used for gitlink:git-show[1]. @@ -253,3 +384,19 @@ whatchanged.difftree:: imap:: The configuration variables in the 'imap' section are described in gitlink:git-imap-send[1]. + +receive.unpackLimit:: + If the number of objects received in a push is below this + limit then the objects will be unpacked into loose object + files. However if the number of received objects equals or + exceeds this limit then the received pack will be stored as + a pack, after adding any missing delta bases. Storing the + pack from a push can make the push operation complete faster, + especially on slow filesystems. + +receive.denyNonFastForwards:: + If set to true, git-receive-pack will deny a ref update which is + not a fast forward. Use this to prevent such an update via a push, + even if that push is forced. This configuration variable is + set when initializing a shared repository. + diff --git a/Documentation/core-tutorial.txt b/Documentation/core-tutorial.txt index 1185897f70..0cd33fb5b7 100644 --- a/Documentation/core-tutorial.txt +++ b/Documentation/core-tutorial.txt @@ -46,18 +46,18 @@ to import into git. For our first example, we're going to start a totally new repository from scratch, with no pre-existing files, and we'll call it `git-tutorial`. To start up, create a subdirectory for it, change into that -subdirectory, and initialize the git infrastructure with `git-init-db`: +subdirectory, and initialize the git infrastructure with `git-init`: ------------------------------------------------ $ mkdir git-tutorial $ cd git-tutorial -$ git-init-db +$ git-init ------------------------------------------------ to which git will reply ---------------- -defaulting to local storage area +Initialized empty Git repository in .git/ ---------------- which is just git's way of saying that you haven't been doing anything @@ -336,17 +336,9 @@ $ commit=$(echo 'Initial commit' | git-commit-tree $tree) $ git-update-ref HEAD $commit ------------------------------------------------ -which will say: - ----------------- -Committing initial tree 8988da15d077d4829fc51d8544c097def6644dbb ----------------- - -just to warn you about the fact that it created a totally new commit -that is not related to anything else. Normally you do this only *once* -for a project ever, and all later commits will be parented on top of an -earlier commit, and you'll never see this "Committing initial tree" -message ever again. +In this case this creates a totally new commit that is not related to +anything else. Normally you do this only *once* for a project ever, and +all later commits will be parented on top of an earlier commit. Again, normally you'd never actually do this by hand. There is a helpful script called `git commit` that will do all of this for you. So @@ -1379,11 +1371,11 @@ $ mkdir my-git.git ------------ Then, make that directory into a git repository by running -`git init-db`, but this time, since its name is not the usual +`git init`, but this time, since its name is not the usual `.git`, we do things slightly differently: ------------ -$ GIT_DIR=my-git.git git-init-db +$ GIT_DIR=my-git.git git-init ------------ Make sure this directory is available for others you want your @@ -1519,7 +1511,7 @@ A recommended workflow for a "project lead" goes like this: + If other people are pulling from your repository over dumb transport protocols (HTTP), you need to keep this repository -'dumb transport friendly'. After `git init-db`, +'dumb transport friendly'. After `git init`, `$GIT_DIR/hooks/post-update` copied from the standard templates would contain a call to `git-update-server-info` but the `post-update` hook itself is disabled by default -- enable it @@ -1620,7 +1612,7 @@ suggested in the previous section may be new to you. You do not have to worry. git supports "shared public repository" style of cooperation you are probably more familiar with as well. -See link:cvs-migration.txt[git for CVS users] for the details. +See link:cvs-migration.html[git for CVS users] for the details. Bundling your work together --------------------------- diff --git a/Documentation/cvs-migration.txt b/Documentation/cvs-migration.txt index d2b0bd38de..775bf4266a 100644 --- a/Documentation/cvs-migration.txt +++ b/Documentation/cvs-migration.txt @@ -1,90 +1,87 @@ git for CVS users ================= -So you're a CVS user. That's OK, it's a treatable condition. The job of -this document is to put you on the road to recovery, by helping you -convert an existing cvs repository to git, and by showing you how to use a -git repository in a cvs-like fashion. +Git differs from CVS in that every working tree contains a repository with +a full copy of the project history, and no repository is inherently more +important than any other. However, you can emulate the CVS model by +designating a single shared repository which people can synchronize with; +this document explains how to do that. Some basic familiarity with git is required. This link:tutorial.html[tutorial introduction to git] should be sufficient. -First, note some ways that git differs from CVS: +Developing against a shared repository +-------------------------------------- - * Commits are atomic and project-wide, not per-file as in CVS. - - * Offline work is supported: you can make multiple commits locally, - then submit them when you're ready. - - * Branching is fast and easy. +Suppose a shared repository is set up in /pub/repo.git on the host +foo.com. Then as an individual committer you can clone the shared +repository over ssh with: - * Every working tree contains a repository with a full copy of the - project history, and no repository is inherently more important than - any other. However, you can emulate the CVS model by designating a - single shared repository which people can synchronize with; see below - for details. +------------------------------------------------ +$ git clone foo.com:/pub/repo.git/ my-project +$ cd my-project +------------------------------------------------ -Importing a CVS archive ------------------------ +and hack away. The equivalent of `cvs update` is -First, install version 2.1 or higher of cvsps from -link:http://www.cobite.com/cvsps/[http://www.cobite.com/cvsps/] and make -sure it is in your path. The magic command line is then +------------------------------------------------ +$ git pull origin +------------------------------------------------ -------------------------------------------- -$ git cvsimport -v -d <cvsroot> -C <destination> <module> -------------------------------------------- +which merges in any work that others might have done since the clone +operation. If there are uncommitted changes in your working tree, commit +them first before running git pull. -This puts a git archive of the named CVS module in the directory -<destination>, which will be created if necessary. The -v option makes -the conversion script very chatty. +[NOTE] +================================ +The `pull` command knows where to get updates from because of certain +configuration variables that were set by the first `git clone` +command; see `git repo-config -l` and the gitlink:git-repo-config[1] man +page for details. +================================ -The import checks out from CVS every revision of every file. Reportedly -cvsimport can average some twenty revisions per second, so for a -medium-sized project this should not take more than a couple of minutes. -Larger projects or remote repositories may take longer. +You can update the shared repository with your changes by first committing +your changes, and then using the gitlink:git-push[1] command: -The main trunk is stored in the git branch named `origin`, and additional -CVS branches are stored in git branches with the same names. The most -recent version of the main trunk is also left checked out on the `master` -branch, so you can start adding your own changes right away. +------------------------------------------------ +$ git push origin master +------------------------------------------------ -The import is incremental, so if you call it again next month it will -fetch any CVS updates that have been made in the meantime. For this to -work, you must not modify the imported branches; instead, create new -branches for your own changes, and merge in the imported branches as -necessary. +to "push" those commits to the shared repository. If someone else has +updated the repository more recently, `git push`, like `cvs commit`, will +complain, in which case you must pull any changes before attempting the +push again. -Development Models ------------------- +In the `git push` command above we specify the name of the remote branch +to update (`master`). If we leave that out, `git push` tries to update +any branches in the remote repository that have the same name as a branch +in the local repository. So the last `push` can be done with either of: -CVS users are accustomed to giving a group of developers commit access to -a common repository. In the next section we'll explain how to do this -with git. However, the distributed nature of git allows other development -models, and you may want to first consider whether one of them might be a -better fit for your project. +------------ +$ git push origin +$ git push foo.com:/pub/project.git/ +------------ -For example, you can choose a single person to maintain the project's -primary public repository. Other developers then clone this repository -and each work in their own clone. When they have a series of changes that -they're happy with, they ask the maintainer to pull from the branch -containing the changes. The maintainer reviews their changes and pulls -them into the primary repository, which other developers pull from as -necessary to stay coordinated. The Linux kernel and other projects use -variants of this model. +as long as the shared repository does not have any branches +other than `master`. -With a small group, developers may just pull changes from each other's -repositories without the need for a central maintainer. +Setting Up a Shared Repository +------------------------------ -Emulating the CVS Development Model ------------------------------------ +We assume you have already created a git repository for your project, +possibly created from scratch or from a tarball (see the +link:tutorial.html[tutorial]), or imported from an already existing CVS +repository (see the next section). -Start with an ordinary git working directory containing the project, and -remove the checked-out files, keeping just the bare .git directory: +Assume your existing repo is at /home/alice/myproject. Create a new "bare" +repository (a repository without a working tree) and fetch your project into +it: ------------------------------------------------ -$ mv project/.git /pub/repo.git -$ rm -r project/ +$ mkdir /pub/my-repo.git +$ cd /pub/my-repo.git +$ git --bare init --shared +$ git --bare fetch /home/alice/myproject master:master ------------------------------------------------ Next, give every team member read/write access to this repository. One @@ -97,208 +94,78 @@ Put all the committers in the same group, and make the repository writable by that group: ------------------------------------------------ -$ chgrp -R $group repo.git -$ find repo.git -mindepth 1 -type d |xargs chmod ug+rwx,g+s -$ GIT_DIR=repo.git git repo-config core.sharedrepository true +$ chgrp -R $group /pub/my-repo.git ------------------------------------------------ Make sure committers have a umask of at most 027, so that the directories they create are writable and searchable by other group members. -Suppose this repository is now set up in /pub/repo.git on the host -foo.com. Then as an individual committer you can clone the shared -repository: - ------------------------------------------------- -$ git clone foo.com:/pub/repo.git/ my-project -$ cd my-project ------------------------------------------------- - -and hack away. The equivalent of `cvs update` is - ------------------------------------------------- -$ git pull origin ------------------------------------------------- - -which merges in any work that others might have done since the clone -operation. - -[NOTE] -================================ -The first `git clone` places the following in the -`my-project/.git/remotes/origin` file, and that's why the previous step -and the next step both work. ------------- -URL: foo.com:/pub/project.git/ my-project -Pull: master:origin ------------- -================================ - -You can update the shared repository with your changes using: +Importing a CVS archive +----------------------- ------------------------------------------------- -$ git push origin master ------------------------------------------------- +First, install version 2.1 or higher of cvsps from +link:http://www.cobite.com/cvsps/[http://www.cobite.com/cvsps/] and make +sure it is in your path. Then cd to a checked out CVS working directory +of the project you are interested in and run gitlink:git-cvsimport[1]: -If someone else has updated the repository more recently, `git push`, like -`cvs commit`, will complain, in which case you must pull any changes -before attempting the push again. +------------------------------------------- +$ git cvsimport -C <destination> +------------------------------------------- -In the `git push` command above we specify the name of the remote branch -to update (`master`). If we leave that out, `git push` tries to update -any branches in the remote repository that have the same name as a branch -in the local repository. So the last `push` can be done with either of: +This puts a git archive of the named CVS module in the directory +<destination>, which will be created if necessary. ------------- -$ git push origin -$ git push repo.shared.xz:/pub/scm/project.git/ ------------- +The import checks out from CVS every revision of every file. Reportedly +cvsimport can average some twenty revisions per second, so for a +medium-sized project this should not take more than a couple of minutes. +Larger projects or remote repositories may take longer. -as long as the shared repository does not have any branches -other than `master`. +The main trunk is stored in the git branch named `origin`, and additional +CVS branches are stored in git branches with the same names. The most +recent version of the main trunk is also left checked out on the `master` +branch, so you can start adding your own changes right away. -[NOTE] -============ -Because of this behavior, if the shared repository and the developer's -repository both have branches named `origin`, then a push like the above -attempts to update the `origin` branch in the shared repository from the -developer's `origin` branch. The results may be unexpected, so it's -usually best to remove any branch named `origin` from the shared -repository. -============ +The import is incremental, so if you call it again next month it will +fetch any CVS updates that have been made in the meantime. For this to +work, you must not modify the imported branches; instead, create new +branches for your own changes, and merge in the imported branches as +necessary. Advanced Shared Repository Management ------------------------------------- Git allows you to specify scripts called "hooks" to be run at certain points. You can use these, for example, to send all commits to the shared -repository to a mailing list. See link:hooks.txt[Hooks used by git]. +repository to a mailing list. See link:hooks.html[Hooks used by git]. You can enforce finer grained permissions using update hooks. See link:howto/update-hook-example.txt[Controlling access to branches using update hooks]. -CVS annotate ------------- +Providing CVS Access to a git Repository +---------------------------------------- + +It is also possible to provide true CVS access to a git repository, so +that developers can still use CVS; see gitlink:git-cvsserver[1] for +details. + +Alternative Development Models +------------------------------ + +CVS users are accustomed to giving a group of developers commit access to +a common repository. As we've seen, this is also possible with git. +However, the distributed nature of git allows other development models, +and you may want to first consider whether one of them might be a better +fit for your project. + +For example, you can choose a single person to maintain the project's +primary public repository. Other developers then clone this repository +and each work in their own clone. When they have a series of changes that +they're happy with, they ask the maintainer to pull from the branch +containing the changes. The maintainer reviews their changes and pulls +them into the primary repository, which other developers pull from as +necessary to stay coordinated. The Linux kernel and other projects use +variants of this model. -So, something has gone wrong, and you don't know whom to blame, and -you're an ex-CVS user and used to do "cvs annotate" to see who caused -the breakage. You're looking for the "git annotate", and it's just -claiming not to find such a script. You're annoyed. - -Yes, that's right. Core git doesn't do "annotate", although it's -technically possible, and there are at least two specialized scripts out -there that can be used to get equivalent information (see the git -mailing list archives for details). - -git has a couple of alternatives, though, that you may find sufficient -or even superior depending on your use. One is called "git-whatchanged" -(for obvious reasons) and the other one is called "pickaxe" ("a tool for -the software archaeologist"). - -The "git-whatchanged" script is a truly trivial script that can give you -a good overview of what has changed in a file or a directory (or an -arbitrary list of files or directories). The "pickaxe" support is an -additional layer that can be used to further specify exactly what you're -looking for, if you already know the specific area that changed. - -Let's step back a bit and think about the reason why you would -want to do "cvs annotate a-file.c" to begin with. - -You would use "cvs annotate" on a file when you have trouble -with a function (or even a single "if" statement in a function) -that happens to be defined in the file, which does not do what -you want it to do. And you would want to find out why it was -written that way, because you are about to modify it to suit -your needs, and at the same time you do not want to break its -current callers. For that, you are trying to find out why the -original author did things that way in the original context. - -Many times, it may be enough to see the commit log messages of -commits that touch the file in question, possibly along with the -patches themselves, like this: - - $ git-whatchanged -p a-file.c - -This will show log messages and patches for each commit that -touches a-file. - -This, however, may not be very useful when this file has many -modifications that are not related to the piece of code you are -interested in. You would see many log messages and patches that -do not have anything to do with the piece of code you are -interested in. As an example, assuming that you have this piece -of code that you are interested in in the HEAD version: - - if (frotz) { - nitfol(); - } - -you would use git-rev-list and git-diff-tree like this: - - $ git-rev-list HEAD | - git-diff-tree --stdin -v -p -S'if (frotz) { - nitfol(); - }' - -We have already talked about the "\--stdin" form of git-diff-tree -command that reads the list of commits and compares each commit -with its parents (otherwise you should go back and read the tutorial). -The git-whatchanged command internally runs -the equivalent of the above command, and can be used like this: - - $ git-whatchanged -p -S'if (frotz) { - nitfol(); - }' - -When the -S option is used, git-diff-tree command outputs -differences between two commits only if one tree has the -specified string in a file and the corresponding file in the -other tree does not. The above example looks for a commit that -has the "if" statement in it in a file, but its parent commit -does not have it in the same shape in the corresponding file (or -the other way around, where the parent has it and the commit -does not), and the differences between them are shown, along -with the commit message (thanks to the -v flag). It does not -show anything for commits that do not touch this "if" statement. - -Also, in the original context, the same statement might have -appeared at first in a different file and later the file was -renamed to "a-file.c". CVS annotate would not help you to go -back across such a rename, but git would still help you in such -a situation. For that, you can give the -C flag to -git-diff-tree, like this: - - $ git-whatchanged -p -C -S'if (frotz) { - nitfol(); - }' - -When the -C flag is used, file renames and copies are followed. -So if the "if" statement in question happens to be in "a-file.c" -in the current HEAD commit, even if the file was originally -called "o-file.c" and then renamed in an earlier commit, or if -the file was created by copying an existing "o-file.c" in an -earlier commit, you will not lose track. If the "if" statement -did not change across such a rename or copy, then the commit that -does rename or copy would not show in the output, and if the -"if" statement was modified while the file was still called -"o-file.c", it would find the commit that changed the statement -when it was in "o-file.c". - -NOTE: The current version of "git-diff-tree -C" is not eager - enough to find copies, and it will miss the fact that a-file.c - was created by copying o-file.c unless o-file.c was somehow - changed in the same commit. - -You can use the --pickaxe-all flag in addition to the -S flag. -This causes the differences from all the files contained in -those two commits, not just the differences between the files -that contain this changed "if" statement: - - $ git-whatchanged -p -C -S'if (frotz) { - nitfol(); - }' --pickaxe-all - -NOTE: This option is called "--pickaxe-all" because -S - option is internally called "pickaxe", a tool for software - archaeologists. +With a small group, developers may just pull changes from each other's +repositories without the need for a central maintainer. diff --git a/Documentation/diff-format.txt b/Documentation/diff-format.txt index 617d8f526f..883c1bb0a6 100644 --- a/Documentation/diff-format.txt +++ b/Documentation/diff-format.txt @@ -65,62 +65,17 @@ Generating patches with -p When "git-diff-index", "git-diff-tree", or "git-diff-files" are run with a '-p' option, they do not produce the output described above; -instead they produce a patch file. +instead they produce a patch file. You can customize the creation +of such patches via the GIT_EXTERNAL_DIFF and the GIT_DIFF_OPTS +environment variables. -The patch generation can be customized at two levels. - -1. When the environment variable 'GIT_EXTERNAL_DIFF' is not set, - these commands internally invoke "diff" like this: - - diff -L a/<path> -L b/<path> -pu <old> <new> -+ -For added files, `/dev/null` is used for <old>. For removed -files, `/dev/null` is used for <new> -+ -The "diff" formatting options can be customized via the -environment variable 'GIT_DIFF_OPTS'. For example, if you -prefer context diff: - - GIT_DIFF_OPTS=-c git-diff-index -p HEAD - - -2. When the environment variable 'GIT_EXTERNAL_DIFF' is set, the - program named by it is called, instead of the diff invocation - described above. -+ -For a path that is added, removed, or modified, -'GIT_EXTERNAL_DIFF' is called with 7 parameters: - - path old-file old-hex old-mode new-file new-hex new-mode -+ -where: - - <old|new>-file:: are files GIT_EXTERNAL_DIFF can use to read the - contents of <old|new>, - <old|new>-hex:: are the 40-hexdigit SHA1 hashes, - <old|new>-mode:: are the octal representation of the file modes. - -+ -The file parameters can point at the user's working file -(e.g. `new-file` in "git-diff-files"), `/dev/null` (e.g. `old-file` -when a new file is added), or a temporary file (e.g. `old-file` in the -index). 'GIT_EXTERNAL_DIFF' should not worry about unlinking the -temporary file --- it is removed when 'GIT_EXTERNAL_DIFF' exits. - -For a path that is unmerged, 'GIT_EXTERNAL_DIFF' is called with 1 -parameter, <path>. - - -git specific extension to diff format -------------------------------------- - -What -p option produces is slightly different from the -traditional diff format. +What the -p option produces is slightly different from the traditional +diff format. 1. It is preceded with a "git diff" header, that looks like this: - diff --git a/file1 b/file2 + diff --git a/file1 b/file2 + The `a/` and `b/` filenames are the same unless rename/copy is involved. Especially, even for a creation or a deletion, @@ -144,8 +99,10 @@ the file that rename/copy produces, respectively. dissimilarity index <number> index <hash>..<hash> <mode> -3. TAB, LF, and backslash characters in pathnames are - represented as `\t`, `\n`, and `\\`, respectively. +3. TAB, LF, double quote and backslash characters in pathnames + are represented as `\t`, `\n`, `\"` and `\\`, respectively. + If there is need for such substitution then the whole + pathname is put in double quotes. combined diff format @@ -156,31 +113,91 @@ to produce 'combined diff', which looks like this: ------------ diff --combined describe.c -@@@ +98,7 @@@ - return (a_date > b_date) ? -1 : (a_date == b_date) ? 0 : 1; +index fabadb8,cc95eb0..4866510 +--- a/describe.c ++++ b/describe.c +@@@ -98,20 -98,12 +98,20 @@@ + return (a_date > b_date) ? -1 : (a_date == b_date) ? 0 : 1; } - + - static void describe(char *arg) -static void describe(struct commit *cmit, int last_one) ++static void describe(char *arg, int last_one) { - + unsigned char sha1[20]; - + struct commit *cmit; + + unsigned char sha1[20]; + + struct commit *cmit; + struct commit_list *list; + static int initialized = 0; + struct commit_name *n; + + + if (get_sha1(arg, sha1) < 0) + + usage(describe_usage); + + cmit = lookup_commit_reference(sha1); + + if (!cmit) + + usage(describe_usage); + + + if (!initialized) { + initialized = 1; + for_each_ref(get_name); ------------ +1. It is preceded with a "git diff" header, that looks like + this (when '-c' option is used): + + diff --combined file ++ +or like this (when '--cc' option is used): + + diff --c file + +2. It is followed by one or more extended header lines + (this example shows a merge with two parents): + + index <hash>,<hash>..<hash> + mode <mode>,<mode>..<mode> + new file mode <mode> + deleted file mode <mode>,<mode> ++ +The `mode <mode>,<mode>..<mode>` line appears only if at least one of +the <mode> is diferent from the rest. Extended headers with +information about detected contents movement (renames and +copying detection) are designed to work with diff of two +<tree-ish> and are not used by combined diff format. + +3. It is followed by two-line from-file/to-file header + + --- a/file + +++ b/file ++ +Similar to two-line header for traditional 'unified' diff +format, `/dev/null` is used to signal created or deleted +files. + +4. Chunk header format is modified to prevent people from + accidentally feeding it to `patch -p1`. Combined diff format + was created for review of merge commit changes, and was not + meant for apply. The change is similar to the change in the + extended 'index' header: + + @@@ <from-file-range> <from-file-range> <to-file-range> @@@ ++ +There are (number of parents + 1) `@` characters in the chunk +header for combined diff format. + Unlike the traditional 'unified' diff format, which shows two files A and B with a single column that has `-` (minus -- appears in A but removed in B), `+` (plus -- missing in A but -added to B), or ` ` (space -- unchanged) prefix, this format +added to B), or `" "` (space -- unchanged) prefix, this format compares two or more files file1, file2,... with one file X, and shows how X differs from each of fileN. One column for each of fileN is prepended to the output line to note how X's line is different from it. A `-` character in the column N means that the line appears in -fileN but it does not appear in the last file. A `+` character +fileN but it does not appear in the result. A `+` character in the column N means that the line appears in the last file, -and fileN does not have that line. +and fileN does not have that line (in other words, the line was +added, from the point of view of that parent). In the above example output, the function signature was changed from both files (hence two `-` removals from both file1 and diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt index b5d9763594..da1cc60e97 100644 --- a/Documentation/diff-options.txt +++ b/Documentation/diff-options.txt @@ -10,8 +10,23 @@ --patch-with-raw:: Synonym for "-p --raw". ---stat:: - Generate a diffstat. +--stat[=width[,name-width]]:: + Generate a diffstat. You can override the default + output width for 80-column terminal by "--stat=width". + The width of the filename part can be controlled by + giving another width to it separated by a comma. + +--numstat:: + Similar to \--stat, but shows number of added and + deleted lines in decimal notation and pathname without + abbreviation, to make it more machine friendly. For + binary files, outputs two `-` instead of saying + `0 0`. + +--shortstat:: + Output only the last line of the --stat format containing total + number of modified files, as well as number of added and deleted + lines. --summary:: Output a condensed summary of extended header information @@ -121,5 +136,21 @@ -a:: Shorthand for "--text". +--ignore-space-change:: + Ignore changes in amount of white space. This ignores white + space at line end, and consider all other sequences of one or + more white space characters to be equivalent. + +-b:: + Shorthand for "--ignore-space-change". + +--ignore-all-space:: + Ignore white space when comparing lines. This ignores + difference even if one line has white space where the other + line has none. + +-w:: + Shorthand for "--ignore-all-space". + For more detailed explanation on these common options, see also link:diffcore.html[diffcore documentation]. diff --git a/Documentation/everyday.txt b/Documentation/everyday.txt index b935c18088..4e83994c58 100644 --- a/Documentation/everyday.txt +++ b/Documentation/everyday.txt @@ -1,22 +1,7 @@ Everyday GIT With 20 Commands Or So =================================== -GIT suite has over 100 commands, and the manual page for each of -them discusses what the command does and how it is used in -detail, but until you know what command should be used in order -to achieve what you want to do, you cannot tell which manual -page to look at, and if you know that already you do not need -the manual. - -Does that mean you need to know all of them before you can use -git? Not at all. Depending on the role you play, the set of -commands you need to know is slightly different, but in any case -what you need to learn is far smaller than the full set of -commands to carry out your day-to-day work. This document is to -serve as a cheat-sheet and a set of pointers for people playing -various roles. - -<<Basic Repository>> commands are needed by people who has a +<<Basic Repository>> commands are needed by people who have a repository --- that is everybody, because every working tree of git is a repository. @@ -25,31 +10,33 @@ essential for anybody who makes a commit, even for somebody who works alone. If you work with other people, you will need commands listed in -<<Individual Developer (Participant)>> section as well. +the <<Individual Developer (Participant)>> section as well. -People who play <<Integrator>> role need to learn some more +People who play the <<Integrator>> role need to learn some more commands in addition to the above. <<Repository Administration>> commands are for system -administrators who are responsible to care and feed git -repositories to support developers. +administrators who are responsible for the care and feeding +of git repositories. Basic Repository[[Basic Repository]] ------------------------------------ -Everybody uses these commands to feed and care git repositories. +Everybody uses these commands to maintain git repositories. - * gitlink:git-init-db[1] or gitlink:git-clone[1] to create a + * gitlink:git-init[1] or gitlink:git-clone[1] to create a new repository. - * gitlink:git-fsck-objects[1] to validate the repository. + * gitlink:git-fsck-objects[1] to check the repository for errors. - * gitlink:git-prune[1] to garbage collect cruft in the - repository. + * gitlink:git-prune[1] to remove unused objects in the repository. * gitlink:git-repack[1] to pack loose objects for efficiency. + * gitlink:git-gc[1] to do common housekeeping tasks such as + repack and prune. + Examples ~~~~~~~~ @@ -57,19 +44,19 @@ Check health and remove cruft.:: + ------------ $ git fsck-objects <1> -$ git prune $ git count-objects <2> $ git repack <3> -$ git prune <4> +$ git gc <4> ------------ + -<1> running without "--full" is usually cheap and assures the +<1> running without `\--full` is usually cheap and assures the repository health reasonably well. <2> check how many loose objects there are and how much disk space is wasted by not repacking. -<3> without "-a" repacks incrementally. repacking every 4-5MB +<3> without `-a` repacks incrementally. repacking every 4-5MB of loose objects accumulation may be a good rule of thumb. -<4> after repack, prune removes the duplicate loose objects. +<4> it is easier to use `git gc` than individual housekeeping commands +such as `prune` and `repack`. This runs `repack -a -d`. Repack a small project into single pack.:: + @@ -78,8 +65,8 @@ $ git repack -a -d <1> $ git prune ------------ + -<1> pack all the objects reachable from the refs into one pack -and remove unneeded other packs +<1> pack all the objects reachable from the refs into one pack, +then remove the other packs. Individual Developer (Standalone)[[Individual Developer (Standalone)]] @@ -93,14 +80,10 @@ following commands. * gitlink:git-log[1] to see what happened. - * gitlink:git-whatchanged[1] to find out where things have - come from. - * gitlink:git-checkout[1] and gitlink:git-branch[1] to switch branches. - * gitlink:git-add[1] and gitlink:git-update-index[1] to manage - the index file. + * gitlink:git-add[1] to manage the index file. * gitlink:git-diff[1] and gitlink:git-status[1] to see what you are in the middle of doing. @@ -110,8 +93,7 @@ following commands. * gitlink:git-reset[1] and gitlink:git-checkout[1] (with pathname parameters) to undo changes. - * gitlink:git-pull[1] with "." as the remote to merge between - local branches. + * gitlink:git-merge[1] to merge between local branches. * gitlink:git-rebase[1] to maintain topic branches. @@ -120,12 +102,12 @@ following commands. Examples ~~~~~~~~ -Extract a tarball and create a working tree and a new repository to keep track of it.:: +Use a tarball as a starting point for a new repository.:: + ------------ $ tar zxf frotz.tar.gz $ cd frotz -$ git-init-db +$ git-init $ git add . <1> $ git commit -m 'import of frotz source tree.' $ git tag v2.43 <2> @@ -142,7 +124,7 @@ $ edit/compile/test $ git checkout -- curses/ux_audio_oss.c <2> $ git add curses/ux_audio_alsa.c <3> $ edit/compile/test -$ git diff <4> +$ git diff HEAD <4> $ git commit -a -s <5> $ edit/compile/test $ git reset --soft HEAD^ <6> @@ -150,15 +132,15 @@ $ edit/compile/test $ git diff ORIG_HEAD <7> $ git commit -a -c ORIG_HEAD <8> $ git checkout master <9> -$ git pull . alsa-audio <10> +$ git merge alsa-audio <10> $ git log --since='3 days ago' <11> $ git log v2.43.. curses/ <12> ------------ + <1> create a new topic branch. -<2> revert your botched changes in "curses/ux_audio_oss.c". +<2> revert your botched changes in `curses/ux_audio_oss.c`. <3> you need to tell git if you added a new file; removal and -modification will be caught if you do "commit -a" later. +modification will be caught if you do `git commit -a` later. <4> to see what changes you are committing. <5> commit everything as you have tested, with your sign-off. <6> take the last commit back, keeping what is in the working tree. @@ -166,11 +148,13 @@ modification will be caught if you do "commit -a" later. <8> redo the commit undone in the previous step, using the message you originally wrote. <9> switch to the master branch. -<10> merge a topic branch into your master branch +<10> merge a topic branch into your master branch. You can also use +`git pull . alsa-audio`, i.e. pull from the local repository. <11> review commit logs; other forms to limit output can be -combined and include --max-count=10 (show 10 commits), --until='2005-12-10'. -<12> view only the changes that touch what's in curses/ -directory, since v2.43 tag. +combined and include `\--max-count=10` (show 10 commits), +`\--until=2005-12-10`, etc. +<12> view only the changes that touch what's in `curses/` +directory, since `v2.43` tag. Individual Developer (Participant)[[Individual Developer (Participant)]] @@ -203,7 +187,7 @@ $ cd my2.6 $ edit/compile/test; git commit -a -s <1> $ git format-patch origin <2> $ git pull <3> -$ git whatchanged -p ORIG_HEAD.. arch/i386 include/asm-i386 <4> +$ git log -p ORIG_HEAD.. arch/i386 include/asm-i386 <4> $ git pull git://git.kernel.org/pub/.../jgarzik/libata-dev.git ALL <5> $ git reset --hard ORIG_HEAD <6> $ git prune <7> @@ -212,7 +196,7 @@ $ git fetch --tags <8> + <1> repeat as needed. <2> extract patches from your branch for e-mail submission. -<3> "pull" fetches from "origin" by default and merges into the +<3> `git pull` fetches from `origin` by default and merges into the current branch. <4> immediately after pulling, look at the changes done upstream since last time we checked, only in the @@ -220,37 +204,41 @@ area we are interested in. <5> fetch from a specific branch from a specific repository and merge. <6> revert the pull. <7> garbage collect leftover objects from reverted pull. -<8> from time to time, obtain official tags from the "origin" -and store them under .git/refs/tags/. +<8> from time to time, obtain official tags from the `origin` +and store them under `.git/refs/tags/`. Push into another repository.:: + ------------ -satellite$ git clone mothership:frotz/.git frotz <1> +satellite$ git clone mothership:frotz frotz <1> satellite$ cd frotz -satellite$ cat .git/remotes/origin <2> -URL: mothership:frotz/.git -Pull: master:origin -satellite$ echo 'Push: master:satellite' >>.git/remotes/origin <3> +satellite$ git repo-config --get-regexp '^(remote|branch)\.' <2> +remote.origin.url mothership:frotz +remote.origin.fetch refs/heads/*:refs/remotes/origin/* +branch.master.remote origin +branch.master.merge refs/heads/master +satellite$ git repo-config remote.origin.push \ + master:refs/remotes/satellite/master <3> satellite$ edit/compile/test/commit satellite$ git push origin <4> mothership$ cd frotz mothership$ git checkout master -mothership$ git pull . satellite <5> +mothership$ git merge satellite/master <5> ------------ + <1> mothership machine has a frotz repository under your home directory; clone from it to start a repository on the satellite machine. -<2> clone creates this file by default. It arranges "git pull" -to fetch and store the master branch head of mothership machine -to local "origin" branch. -<3> arrange "git push" to push local "master" branch to -"satellite" branch of the mothership machine. -<4> push will stash our work away on "satellite" branch on the -mothership machine. You could use this as a back-up method. +<2> clone sets these configuration variables by default. +It arranges `git pull` to fetch and store the branches of mothership +machine to local `remotes/origin/*` tracking branches. +<3> arrange `git push` to push local `master` branch to +`remotes/satellite/master` branch of the mothership machine. +<4> push will stash our work away on `remotes/satellite/master` +tracking branch on the mothership machine. You could use this as +a back-up method. <5> on mothership machine, merge the work done on the satellite machine into the master branch. @@ -266,7 +254,7 @@ $ git format-patch -k -m --stdout v2.6.14..private2.6.14 | + <1> create a private branch based on a well known (but somewhat behind) tag. -<2> forward port all changes in private2.6.14 branch to master branch +<2> forward port all changes in `private2.6.14` branch to `master` branch without a formal "merging". @@ -303,13 +291,13 @@ $ mailx <3> & s 2 3 4 5 ./+to-apply & s 7 8 ./+hold-linus & q -$ git checkout master +$ git checkout -b topic/one master $ git am -3 -i -s -u ./+to-apply <4> $ compile/test $ git checkout -b hold/linus && git am -3 -i -s -u ./+hold-linus <5> $ git checkout topic/one && git rebase master <6> -$ git checkout pu && git reset --hard master <7> -$ git pull . topic/one topic/two && git pull . hold/linus <8> +$ git checkout pu && git reset --hard next <7> +$ git merge topic/one topic/two && git merge hold/linus <8> $ git checkout maint $ git cherry-pick master~4 <9> $ compile/test @@ -326,29 +314,32 @@ they are. that are not quite ready. <4> apply them, interactively, with my sign-offs. <5> create topic branch as needed and apply, again with my -sign-offs. +sign-offs. <6> rebase internal topic branch that has not been merged to the master, nor exposed as a part of a stable branch. -<7> restart "pu" every time from the master. +<7> restart `pu` every time from the next. <8> and bundle topic branches still cooking. <9> backport a critical fix. <10> create a signed tag. <11> make sure I did not accidentally rewind master beyond what I -already pushed out. "ko" shorthand points at the repository I have +already pushed out. `ko` shorthand points at the repository I have at kernel.org, and looks like this: + ------------ $ cat .git/remotes/ko URL: kernel.org:/pub/scm/git/git.git Pull: master:refs/tags/ko-master +Pull: next:refs/tags/ko-next Pull: maint:refs/tags/ko-maint Push: master +Push: next Push: +pu Push: maint ------------ + -In the output from "git show-branch", "master" should have -everything "ko-master" has. +In the output from `git show-branch`, `master` should have +everything `ko-master` has, and `next` should have +everything `ko-next` has. <12> push out the bleeding edge. <13> push the tag out, too. @@ -372,12 +363,19 @@ example of managing a shared central repository. Examples ~~~~~~~~ +We assume the following in /etc/services:: ++ +------------ +$ grep 9418 /etc/services +git 9418/tcp # Git Version Control System +------------ + Run git-daemon to serve /pub/scm from inetd.:: + ------------ $ grep git /etc/inetd.conf git stream tcp nowait nobody \ - /usr/bin/git-daemon git-daemon --inetd --syslog --export-all /pub/scm + /usr/bin/git-daemon git-daemon --inetd --export-all /pub/scm ------------ + The actual configuration line should be on one line. @@ -397,7 +395,7 @@ service git wait = no user = nobody server = /usr/bin/git-daemon - server_args = --inetd --syslog --export-all --base-path=/pub/scm + server_args = --inetd --export-all --base-path=/pub/scm log_on_failure += USERID } ------------ @@ -418,7 +416,7 @@ $ grep git /etc/shells <2> ------------ + <1> log-in shell is set to /usr/bin/git-shell, which does not -allow anything but "git push" and "git pull". The users should +allow anything but `git push` and `git pull`. The users should get an ssh access to the machine. <2> in many distributions /etc/shells needs to list what is used as the login shell. diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt index 13f34d3ca2..5b4d184a73 100644 --- a/Documentation/fetch-options.txt +++ b/Documentation/fetch-options.txt @@ -36,6 +36,13 @@ -u, \--update-head-ok:: By default `git-fetch` refuses to update the head which corresponds to the current branch. This flag disables the - check. Note that fetching into the current branch will not - update the index and working directory, so use it with care. + check. This is purely for the internal use for `git-pull` + to communicate with `git-fetch`, and unless you are + implementing your own Porcelain you are not supposed to + use it. + +\--depth=<depth>:: + Deepen the history of a 'shallow' repository created by + `git clone` with `--depth=<depth>` option (see gitlink:git-clone[1]) + by the specified number of commits. diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 6342ea33e4..95bea66374 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -3,24 +3,45 @@ git-add(1) NAME ---- -git-add - Add files to the index file +git-add - Add file contents to the changeset to be committed next SYNOPSIS -------- -'git-add' [-n] [-v] [--] <file>... +'git-add' [-n] [-v] [-f] [--interactive] [--] <file>... DESCRIPTION ----------- -A simple wrapper for git-update-index to add files to the index, -for people used to do "cvs add". +All the changed file contents to be committed together in a single set +of changes must be "added" with the 'add' command before using the +'commit' command. This is not only for adding new files. Even modified +files must be added to the set of changes about to be committed. + +This command can be performed multiple times before a commit. The added +content corresponds to the state of specified file(s) at the time the +'add' command is used. This means the 'commit' command will not consider +subsequent changes to already added content if it is not added again before +the commit. + +The 'git status' command can be used to obtain a summary of what is included +for the next commit. + +This command can be used to add ignored files with `-f` (force) +option, but they have to be +explicitly and exactly specified from the command line. File globbing +and recursive behaviour do not add ignored files. + +Please see gitlink:git-commit[1] for alternative ways to add content to a +commit. -It only adds non-ignored files, to add ignored files use -"git update-index --add". OPTIONS ------- <file>...:: - Files to add to the index (see gitlink:git-ls-files[1]). + Files to add content from. Fileglobs (e.g. `*.c`) can + be given to add all matching files. Also a + leading directory name (e.g. `dir` to add `dir/file1` + and `dir/file2`) can be given to add all files in the + directory, recursively. -n:: Don't actually add the file(s), just show if they exist. @@ -28,33 +49,25 @@ OPTIONS -v:: Be verbose. +-f:: + Allow adding otherwise ignored files. + +\--interactive:: + Add modified contents in the working tree interactively to + the index. + \--:: This option can be used to separate command-line options from the list of files, (useful when filenames might be mistaken for command-line options). -DISCUSSION ----------- - -The list of <file> given to the command is fed to `git-ls-files` -command to list files that are not registered in the index and -are not ignored/excluded by `$GIT_DIR/info/exclude` file or -`.gitignore` file in each directory. This means two things: - -. You can put the name of a directory on the command line, and - the command will add all files in it and its subdirectories; - -. Giving the name of a file that is already in index does not - run `git-update-index` on that path. - - EXAMPLES -------- git-add Documentation/\\*.txt:: - Adds all `\*.txt` files that are not in the index under - `Documentation` directory and its subdirectories. + Adds content from all `\*.txt` files under `Documentation` + directory and its subdirectories. + Note that the asterisk `\*` is quoted from the shell in this example; this lets the command to include the files from @@ -62,15 +75,131 @@ subdirectories of `Documentation/` directory. git-add git-*.sh:: - Adds all git-*.sh scripts that are not in the index. + Considers adding content from all git-*.sh scripts. Because this example lets shell expand the asterisk (i.e. you are listing the files explicitly), it does not - add `subdir/git-foo.sh` to the index. + consider `subdir/git-foo.sh`. + +Interactive mode +---------------- +When the command enters the interactive mode, it shows the +output of the 'status' subcommand, and then goes into ints +interactive command loop. + +The command loop shows the list of subcommands available, and +gives a prompt "What now> ". In general, when the prompt ends +with a single '>', you can pick only one of the choices given +and type return, like this: + +------------ + *** Commands *** + 1: status 2: update 3: revert 4: add untracked + 5: patch 6: diff 7: quit 8: help + What now> 1 +------------ + +You also could say "s" or "sta" or "status" above as long as the +choice is unique. + +The main command loop has 6 subcommands (plus help and quit). + +status:: + + This shows the change between HEAD and index (i.e. what will be + committed if you say "git commit"), and between index and + working tree files (i.e. what you could stage further before + "git commit" using "git-add") for each path. A sample output + looks like this: ++ +------------ + staged unstaged path + 1: binary nothing foo.png + 2: +403/-35 +1/-1 git-add--interactive.perl +------------ ++ +It shows that foo.png has differences from HEAD (but that is +binary so line count cannot be shown) and there is no +difference between indexed copy and the working tree +version (if the working tree version were also different, +'binary' would have been shown in place of 'nothing'). The +other file, git-add--interactive.perl, has 403 lines added +and 35 lines deleted if you commit what is in the index, but +working tree file has further modifications (one addition and +one deletion). + +update:: + + This shows the status information and gives prompt + "Update>>". When the prompt ends with double '>>', you can + make more than one selection, concatenated with whitespace or + comma. Also you can say ranges. E.g. "2-5 7,9" to choose + 2,3,4,5,7,9 from the list. You can say '*' to choose + everything. ++ +What you chose are then highlighted with '*', +like this: ++ +------------ + staged unstaged path + 1: binary nothing foo.png +* 2: +403/-35 +1/-1 git-add--interactive.perl +------------ ++ +To remove selection, prefix the input with `-` +like this: ++ +------------ +Update>> -2 +------------ ++ +After making the selection, answer with an empty line to stage the +contents of working tree files for selected paths in the index. + +revert:: + + This has a very similar UI to 'update', and the staged + information for selected paths are reverted to that of the + HEAD version. Reverting new paths makes them untracked. + +add untracked:: + + This has a very similar UI to 'update' and + 'revert', and lets you add untracked paths to the index. + +patch:: + + This lets you choose one path out of 'status' like selection. + After choosing the path, it presents diff between the index + and the working tree file and asks you if you want to stage + the change of each hunk. You can say: + + y - add the change from that hunk to index + n - do not add the change from that hunk to index + a - add the change from that hunk and all the rest to index + d - do not the change from that hunk nor any of the rest to index + j - do not decide on this hunk now, and view the next + undecided hunk + J - do not decide on this hunk now, and view the next hunk + k - do not decide on this hunk now, and view the previous + undecided hunk + K - do not decide on this hunk now, and view the previous hunk ++ +After deciding the fate for all hunks, if there is any hunk +that was chosen, the index is updated with the selected hunks. + +diff:: + + This lets you review what will be committed (i.e. between + HEAD and index). + See Also -------- +gitlink:git-status[1] gitlink:git-rm[1] -gitlink:git-ls-files[1] +gitlink:git-mv[1] +gitlink:git-commit[1] +gitlink:git-update-index[1] Author ------ diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt index 910457d3b3..53e81cb103 100644 --- a/Documentation/git-am.txt +++ b/Documentation/git-am.txt @@ -9,7 +9,7 @@ git-am - Apply a series of patches in a mailbox SYNOPSIS -------- [verse] -'git-am' [--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] +'git-am' [--signoff] [--dotest=<dir>] [--utf8 | --no-utf8] [--binary] [--3way] [--interactive] [--whitespace=<option>] <mbox>... 'git-am' [--skip | --resolved] @@ -29,8 +29,21 @@ OPTIONS Instead of `.dotest` directory, use <dir> as a working area to store extracted patches. ---utf8, --keep:: - Pass `-u` and `-k` flags to `git-mailinfo` (see +--keep:: + Pass `-k` flag to `git-mailinfo` (see gitlink:git-mailinfo[1]). + +--utf8:: + Pass `-u` flag to `git-mailinfo` (see gitlink:git-mailinfo[1]). + The proposed commit log message taken from the e-mail + are re-coded into UTF-8 encoding (configuration variable + `i18n.commitencoding` can be used to specify project's + preferred encoding if it is not UTF-8). ++ +This was optional in prior versions of git, but now it is the +default. You could use `--no-utf8` to override this. + +--no-utf8:: + Do not pass `-u` flag to `git-mailinfo` (see gitlink:git-mailinfo[1]). --binary:: diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt index 2ff74949a7..33b93db508 100644 --- a/Documentation/git-apply.txt +++ b/Documentation/git-apply.txt @@ -10,9 +10,10 @@ SYNOPSIS -------- [verse] 'git-apply' [--stat] [--numstat] [--summary] [--check] [--index] [--apply] - [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] - [-CNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] - [<patch>...] + [--no-add] [--index-info] [--allow-binary-replacement | --binary] + [-R | --reverse] [--reject] [-z] [-pNUM] [-CNUM] [--inaccurate-eof] + [--whitespace=<nowarn|warn|error|error-all|strip>] [--exclude=PATH] + [--cached] [--verbose] [<patch>...] DESCRIPTION ----------- @@ -32,8 +33,9 @@ OPTIONS --numstat:: Similar to \--stat, but shows number of added and deleted lines in decimal notation and pathname without - abbreviation, to make it more machine friendly. Turns - off "apply". + abbreviation, to make it more machine friendly. For + binary files, outputs two `-` instead of saying + `0 0`. Turns off "apply". --summary:: Instead of applying the patch, output a condensed @@ -55,6 +57,11 @@ OPTIONS up-to-date, it is flagged as an error. This flag also causes the index file to be updated. +--cached:: + Apply a patch without touching the working tree. Instead, take the + cached data, apply the patch, and store the result in the index, + without using the working tree. This implies '--index'. + --index-info:: Newer git-diff output has embedded 'index information' for each blob to help identify the original version that @@ -62,6 +69,16 @@ OPTIONS the original version of the blob is available locally, outputs information about them to the standard output. +-R, --reverse:: + Apply the patch in reverse. + +--reject:: + For atomicity, gitlink:git-apply[1] by default fails the whole patch and + does not touch the working tree when some of the hunks + do not apply. This option makes it apply + the parts of the patch that are applicable, and leave the + rejected hunks in corresponding *.rej files. + -z:: When showing the index information, do not munge paths, but use NUL terminated machine readable format. Without @@ -79,9 +96,19 @@ OPTIONS context exist they all must match. By default no context is ever ignored. +--unidiff-zero:: + By default, gitlink:git-apply[1] expects that the patch being + applied is a unified diff with at least one line of context. + This provides good safety measures, but breaks down when + applying a diff generated with --unified=0. To bypass these + checks use '--unidiff-zero'. ++ +Note, for the reasons stated above usage of context-free patches are +discouraged. + --apply:: - If you use any of the options marked ``Turns off - "apply"'' above, git-apply reads and outputs the + If you use any of the options marked "Turns off + 'apply'" above, gitlink:git-apply[1] reads and outputs the information you asked without actually applying the patch. Give this flag after those flags to also apply the patch. @@ -93,16 +120,16 @@ OPTIONS the result with this option, which would apply the deletion part but not addition part. ---allow-binary-replacement:: - When applying a patch, which is a git-enhanced patch - that was prepared to record the pre- and post-image object - name in full, and the path being patched exactly matches - the object the patch applies to (i.e. "index" line's - pre-image object name is what is in the working tree), - and the post-image object is available in the object - database, use the post-image object as the patch - result. This allows binary files to be patched in a - very limited way. +--allow-binary-replacement, --binary:: + Historically we did not allow binary patch applied + without an explicit permission from the user, and this + flag was the way to do so. Currently we always allow binary + patch application, so this is a no-op. + +--exclude=<path-pattern>:: + Don't apply changes to files matching the given path pattern. This can + be useful when importing patchsets, where you want to exclude certain + files or directories. --whitespace=<option>:: When applying a patch, detect a new or modified line @@ -110,7 +137,7 @@ OPTIONS line that solely consists of whitespaces). By default, the command outputs warning messages and applies the patch. - When `git-apply` is used for statistics and not applying a + When gitlink:git-apply[1] is used for statistics and not applying a patch, it defaults to `nowarn`. You can use different `<option>` to control this behavior: @@ -124,6 +151,17 @@ OPTIONS * `strip` outputs warnings for a few such errors, strips out the trailing whitespaces and applies the patch. +--inaccurate-eof:: + Under certain circumstances, some versions of diff do not correctly + detect a missing new-line at the end of the file. As a result, patches + created by such diff programs do not record incomplete lines + correctly. This option adds support for applying such patches by + working around this bug. + +--verbose:: + Report progress to stderr. By default, only a message about the + current patch being applied will be printed. This option will cause + additional information to be reported. Configuration ------------- diff --git a/Documentation/git-applymbox.txt b/Documentation/git-applymbox.txt index f74c6a49b3..95dc65a583 100644 --- a/Documentation/git-applymbox.txt +++ b/Documentation/git-applymbox.txt @@ -42,13 +42,13 @@ OPTIONS and the current tree. -u:: - By default, the commit log message, author name and - author email are taken from the e-mail without any - charset conversion, after minimally decoding MIME - transfer encoding. This flag causes the resulting - commit to be encoded in utf-8 by transliterating them. - Note that the patch is always used as is without charset - conversion, even with this flag. + The commit log message, author name and author email are + taken from the e-mail, and after minimally decoding MIME + transfer encoding, re-coded in UTF-8 by transliterating + them. This used to be optional but now it is the default. ++ +Note that the patch is always used as-is without charset +conversion, even with this flag. -c .dotest/<num>:: When the patch contained in an e-mail does not cleanly diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt new file mode 100644 index 0000000000..031fcd5190 --- /dev/null +++ b/Documentation/git-archive.txt @@ -0,0 +1,113 @@ +git-archive(1) +============== + +NAME +---- +git-archive - Creates a archive of the files in the named tree + + +SYNOPSIS +-------- +'git-archive' --format=<fmt> [--list] [--prefix=<prefix>/] [<extra>] + [--remote=<repo>] <tree-ish> [path...] + +DESCRIPTION +----------- +Creates an archive of the specified format containing the tree +structure for the named tree. If <prefix> is specified it is +prepended to the filenames in the archive. + +'git-archive' behaves differently when given a tree ID versus when +given a commit ID or tag ID. In the first case the current time is +used as modification time of each file in the archive. In the latter +case the commit time as recorded in the referenced commit object is +used instead. Additionally the commit ID is stored in a global +extended pax header if the tar format is used; it can be extracted +using 'git-get-tar-commit-id'. In ZIP files it is stored as a file +comment. + +OPTIONS +------- + +--format=<fmt>:: + Format of the resulting archive: 'tar', 'zip'... + +--list:: + Show all available formats. + +--prefix=<prefix>/:: + Prepend <prefix>/ to each filename in the archive. + +<extra>:: + This can be any options that the archiver backend understand. + See next section. + +--remote=<repo>:: + Instead of making a tar archive from local repository, + retrieve a tar archive from a remote repository. + +<tree-ish>:: + The tree or commit to produce an archive for. + +path:: + If one or more paths are specified, include only these in the + archive, otherwise include all files and subdirectories. + +BACKEND EXTRA OPTIONS +--------------------- + +zip +~~~ +-0:: + Store the files instead of deflating them. +-9:: + Highest and slowest compression level. You can specify any + number from 1 to 9 to adjust compression speed and ratio. + + +CONFIGURATION +------------- +By default, file and directories modes are set to 0666 or 0777 in tar +archives. It is possible to change this by setting the "umask" variable +in the repository configuration as follows : + +[tar] + umask = 002 ;# group friendly + +The special umask value "user" indicates that the user's current umask +will be used instead. The default value remains 0, which means world +readable/writable files and directories. + +EXAMPLES +-------- +git archive --format=tar --prefix=junk/ HEAD | (cd /var/tmp/ && tar xf -):: + + Create a tar archive that contains the contents of the + latest commit on the current branch, and extracts it in + `/var/tmp/junk` directory. + +git archive --format=tar --prefix=git-1.4.0/ v1.4.0 | gzip >git-1.4.0.tar.gz:: + + Create a compressed tarball for v1.4.0 release. + +git archive --format=tar --prefix=git-1.4.0/ v1.4.0{caret}\{tree\} | gzip >git-1.4.0.tar.gz:: + + Create a compressed tarball for v1.4.0 release, but without a + global extended pax header. + +git archive --format=zip --prefix=git-docs/ HEAD:Documentation/ > git-1.4.0-docs.zip:: + + Put everything in the current head's Documentation/ directory + into 'git-1.4.0-docs.zip', with the prefix 'git-docs/'. + +Author +------ +Written by Franck Bui-Huu and Rene Scharfe. + +Documentation +-------------- +Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-blame.txt b/Documentation/git-blame.txt index bfed945914..bdfc666928 100644 --- a/Documentation/git-blame.txt +++ b/Documentation/git-blame.txt @@ -3,21 +3,45 @@ git-blame(1) NAME ---- -git-blame - Blame file lines on commits +git-blame - Show what revision and author last modified each line of a file SYNOPSIS -------- -git-blame file [options] file [revision] +[verse] +'git-blame' [-c] [-l] [-t] [-f] [-n] [-p] [-L n,m] [-S <revs-file>] + [-M] [-C] [-C] [--since=<date>] [<rev>] [--] <file> DESCRIPTION ----------- -Annotates each line in the given file with information from the commit -which introduced the line. Start annotation from the given revision. + +Annotates each line in the given file with information from the revision which +last modified the line. Optionally, start annotating from the given revision. + +Also it can limit the range of lines annotated. + +This report doesn't tell you anything about lines which have been deleted or +replaced; you need to use a tool such as gitlink:git-diff[1] or the "pickaxe" +interface briefly mentioned in the following paragraph. + +Apart from supporting file annotation, git also supports searching the +development history for when a code snippet occured in a change. This makes it +possible to track when a code snippet was added to a file, moved or copied +between files, and eventually deleted or replaced. It works by searching for +a text string in the diff. A small example: + +----------------------------------------------------------------------------- +$ git log --pretty=oneline -S'blame_usage' +5040f17eba15504bad66b14a645bddd9b015ebb7 blame -S <ancestry-file> +ea4c7f9bf69e781dd0cd88d2bccb2bf5cc15c9a7 git-blame: Make the output +----------------------------------------------------------------------------- OPTIONS ------- -c, --compatibility:: - Use the same output mode as git-annotate (Default: off). + Use the same output mode as gitlink:git-annotate[1] (Default: off). + +-L n,m:: + Annotate only the specified line range (lines count from 1). -l, --long:: Show long rev (Default: off). @@ -26,19 +50,118 @@ OPTIONS Show raw timestamp (Default: off). -S, --rev-file <revs-file>:: - Use revs from revs-file instead of calling git-rev-list. + Use revs from revs-file instead of calling gitlink:git-rev-list[1]. + +-f, --show-name:: + Show filename in the original commit. By default + filename is shown if there is any line that came from a + file with different name, due to rename detection. + +-n, --show-number:: + Show line number in the original commit (Default: off). + +-p, --porcelain:: + Show in a format designed for machine consumption. + +-M:: + Detect moving lines in the file as well. When a commit + moves a block of lines in a file (e.g. the original file + has A and then B, and the commit changes it to B and + then A), traditional 'blame' algorithm typically blames + the lines that were moved up (i.e. B) to the parent and + assigns blame to the lines that were moved down (i.e. A) + to the child commit. With this option, both groups of + lines are blamed on the parent. + +-C:: + In addition to `-M`, detect lines copied from other + files that were modified in the same commit. This is + useful when you reorganize your program and move code + around across files. When this option is given twice, + the command looks for copies from all other files in the + parent for the commit that creates the file in addition. -h, --help:: Show help message. +THE PORCELAIN FORMAT +-------------------- + +In this format, each line is output after a header; the +header at the minumum has the first line which has: + +- 40-byte SHA-1 of the commit the line is attributed to; +- the line number of the line in the original file; +- the line number of the line in the final file; +- on a line that starts a group of line from a different + commit than the previous one, the number of lines in this + group. On subsequent lines this field is absent. + +This header line is followed by the following information +at least once for each commit: + +- author name ("author"), email ("author-mail"), time + ("author-time"), and timezone ("author-tz"); similarly + for committer. +- filename in the commit the line is attributed to. +- the first line of the commit log message ("summary"). + +The contents of the actual line is output after the above +header, prefixed by a TAB. This is to allow adding more +header elements later. + + +SPECIFIYING RANGES +------------------ + +Unlike `git-blame` and `git-annotate` in older git, the extent +of annotation can be limited to both line ranges and revision +ranges. When you are interested in finding the origin for +ll. 40-60 for file `foo`, you can use `-L` option like this: + + git blame -L 40,60 foo + +Also you can use regular expression to specify the line range. + + git blame -L '/^sub hello {/,/^}$/' foo + +would limit the annotation to the body of `hello` subroutine. + +When you are not interested in changes older than the version +v2.6.18, or changes older than 3 weeks, you can use revision +range specifiers similar to `git-rev-list`: + + git blame v2.6.18.. -- foo + git blame --since=3.weeks -- foo + +When revision range specifiers are used to limit the annotation, +lines that have not changed since the range boundary (either the +commit v2.6.18 or the most recent commit that is more than 3 +weeks old in the above example) are blamed for that range +boundary commit. + +A particularly useful way is to see if an added file have lines +created by copy-and-paste from existing files. Sometimes this +indicates that the developer was being sloppy and did not +refactor the code properly. You can first find the commit that +introduced the file with: + + git log --diff-filter=A --pretty=short -- foo + +and then annotate the change between the commit and its +parents, using `commit{caret}!` notation: + + git blame -C -C -f $commit^! -- foo + + SEE ALSO -------- gitlink:git-annotate[1] AUTHOR ------ -Written by Fredrik Kuivinen <freku045@student.liu.se>. +Written by Junio C Hamano <junkio@cox.net> GIT --- diff --git a/Documentation/git-branch.txt b/Documentation/git-branch.txt index d43ef1dec4..e872fc89fc 100644 --- a/Documentation/git-branch.txt +++ b/Documentation/git-branch.txt @@ -8,23 +8,33 @@ git-branch - List, create, or delete branches. SYNOPSIS -------- [verse] -'git-branch' [-r] +'git-branch' [--color | --no-color] [-r | -a] [-v [--abbrev=<length>]] 'git-branch' [-l] [-f] <branchname> [<start-point>] -'git-branch' (-d | -D) <branchname>... +'git-branch' (-m | -M) [<oldbranch>] <newbranch> +'git-branch' (-d | -D) [-r] <branchname>... DESCRIPTION ----------- -With no arguments given (or just `-r`) a list of available branches +With no arguments given a list of existing branches will be shown, the current branch will be highlighted with an asterisk. +Option `-r` causes the remote-tracking branches to be listed, +and option `-a` shows both. In its second form, a new branch named <branchname> will be created. It will start out with a head equal to the one given as <start-point>. If no <start-point> is given, the branch will be created with a head equal to that of the currently checked out branch. +With a '-m' or '-M' option, <oldbranch> will be renamed to <newbranch>. +If <oldbranch> had a corresponding reflog, it is renamed to match +<newbranch>, and a reflog entry is created to remember the branch +renaming. If <newbranch> exists, -M must be used to force the rename +to happen. + With a `-d` or `-D` option, `<branchname>` will be deleted. You may specify more than one branch for deletion. If the branch currently -has a ref log then the ref log will also be deleted. +has a ref log then the ref log will also be deleted. Use -r together with -d +to delete remote-tracking branches. OPTIONS @@ -44,8 +54,31 @@ OPTIONS Force the creation of a new branch even if it means deleting a branch that already exists with the same name. +-m:: + Move/rename a branch and the corresponding reflog. + +-M:: + Move/rename a branch even if the new branchname already exists. + +--color:: + Color branches to highlight current, local, and remote branches. + +--no-color:: + Turn off branch colors, even when the configuration file gives the + default to color output. + -r:: - List only the "remote" branches. + List or delete (if used with -d) the remote-tracking branches. + +-a:: + List both remote-tracking branches and local branches. + +-v:: + Show sha1 and commit subjectline for each head. + +--abbrev=<length>:: + Alter minimum display length for sha1 in output listing, + default value is 7. <branchname>:: The name of the branch to create or delete. @@ -58,6 +91,12 @@ OPTIONS be given as a branch name, a commit-id, or a tag. If this option is omitted, the current branch is assumed. +<oldbranch>:: + The name of an existing branch to rename. + +<newbranch>:: + The new name for an existing branch. The same restrictions as for + <branchname> applies. Examples @@ -80,10 +119,12 @@ Delete unneeded branch:: ------------ $ git clone git://git.kernel.org/.../git.git my.git $ cd my.git -$ git branch -D todo <1> +$ git branch -d -r todo html man <1> +$ git branch -D test <2> ------------ + -<1> delete todo branch even if the "master" branch does not have all +<1> delete remote-tracking branches "todo", "html", "man" +<2> delete "test" branch even if the "master" branch does not have all commits from todo branch. diff --git a/Documentation/git-cherry-pick.txt b/Documentation/git-cherry-pick.txt index bfa950ca19..875edb6b9f 100644 --- a/Documentation/git-cherry-pick.txt +++ b/Documentation/git-cherry-pick.txt @@ -7,7 +7,7 @@ git-cherry-pick - Apply the change introduced by an existing commit SYNOPSIS -------- -'git-cherry-pick' [--edit] [-n] [-r] <commit> +'git-cherry-pick' [--edit] [-n] [-x] <commit> DESCRIPTION ----------- @@ -24,13 +24,22 @@ OPTIONS With this option, `git-cherry-pick` will let you edit the commit message prior committing. --r|--replay:: - Usually the command appends which commit was +-x:: + Cause the command to append which commit was cherry-picked after the original commit message when - making a commit. This option, '--replay', causes it to - use the original commit message intact. This is useful - when you are reordering the patches in your private tree - before publishing. + making a commit. Do not use this option if you are + cherry-picking from your private branch because the + information is useless to the recipient. If on the + other hand you are cherry-picking between two publicly + visible branches (e.g. backporting a fix to a + maintenance branch for an older release from a + development branch), adding this information can be + useful. + +-r|--replay:: + It used to be that the command defaulted to do `-x` + described above, and `-r` was to disable it. Now the + default is not to do `-x` so this option is a no-op. -n|--no-commit:: Usually the command automatically creates a commit with diff --git a/Documentation/git-cherry.txt b/Documentation/git-cherry.txt index 893baaa6f6..27b67b81a5 100644 --- a/Documentation/git-cherry.txt +++ b/Documentation/git-cherry.txt @@ -7,17 +7,33 @@ git-cherry - Find commits not merged upstream SYNOPSIS -------- -'git-cherry' [-v] <upstream> [<head>] +'git-cherry' [-v] <upstream> [<head>] [<limit>] DESCRIPTION ----------- The changeset (or "diff") of each commit between the fork-point and <head> is compared against each commit between the fork-point and <upstream>. -Every commit with a changeset that doesn't exist in the other branch -has its id (sha1) reported, prefixed by a symbol. Those existing only +Every commit that doesn't exist in the <upstream> branch +has its id (sha1) reported, prefixed by a symbol. The ones that have +equivalent change already in the <upstream> branch are prefixed with a minus (-) sign, and those -that only exist in the <head> branch are prefixed with a plus (+) symbol. +that only exist in the <head> branch are prefixed with a plus (+) symbol: + + __*__*__*__*__> <upstream> + / + fork-point + \__+__+__-__+__+__-__+__> <head> + + +If a <limit> has been given then the commits along the <head> branch up +to and including <limit> are not reported: + + __*__*__*__*__> <upstream> + / + fork-point + \__*__*__<limit>__-__+__> <head> + Because git-cherry compares the changeset rather than the commit id (sha1), you can use git-cherry to find out if a commit you made locally diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt index f973c64313..a78207461d 100644 --- a/Documentation/git-clone.txt +++ b/Documentation/git-clone.txt @@ -11,25 +11,25 @@ SYNOPSIS [verse] 'git-clone' [--template=<template_directory>] [-l [-s]] [-q] [-n] [--bare] [-o <name>] [-u <upload-pack>] [--reference <repository>] - [--use-separate-remote] <repository> [<directory>] + [--depth=<depth>] <repository> [<directory>] DESCRIPTION ----------- -Clones a repository into a newly created directory. All remote -branch heads are copied under `$GIT_DIR/refs/heads/`, except -that the remote `master` is also copied to `origin` branch. -In addition, `$GIT_DIR/remotes/origin` file is set up to have -this line: +Clones a repository into a newly created directory, creates +remote-tracking branches for each branch in the cloned repository +(visible using `git branch -r`), and creates and checks out an initial +branch equal to the cloned repository's currently active branch. - Pull: master:origin +After the clone, a plain `git fetch` without arguments will update +all the remote-tracking branches, and a `git pull` without +arguments will in addition merge the remote master branch into the +current master branch, if any. -This is to help the typical workflow of working off of the -remote `master` branch. Every time `git pull` without argument -is run, the progress on the remote `master` branch is tracked by -copying it into the local `origin` branch, and merged into the -branch you are currently working on. Remote branches other than -`master` are also added there to be tracked. +This default configuration is achieved by creating references to +the remote branch heads under `$GIT_DIR/refs/remotes/origin` and +by initializing `remote.origin.url` and `remote.origin.fetch` +configuration variables. OPTIONS @@ -71,16 +71,18 @@ OPTIONS Make a 'bare' GIT repository. That is, instead of creating `<directory>` and placing the administrative files in `<directory>/.git`, make the `<directory>` - itself the `$GIT_DIR`. This implies `-n` option. When - this option is used, neither the `origin` branch nor the - default `remotes/origin` file is created. - + itself the `$GIT_DIR`. This obviously implies the `-n` + because there is nowhere to check out the working tree. + Also the branch heads at the remote are copied directly + to corresponding local branch heads, without mapping + them to `refs/remotes/origin/`. When this option is + used, neither remote-tracking branches nor the related + configuration variables are created. + +--origin <name>:: -o <name>:: - Instead of using the branch name 'origin' to keep track - of the upstream repository, use <name> instead. Note - that the shorthand name stored in `remotes/origin` is - not affected, but the local branch name to pull the - remote `master` branch into is. + Instead of using the remote name 'origin' to keep track + of the upstream repository, use <name> instead. --upload-pack <upload-pack>:: -u <upload-pack>:: @@ -94,10 +96,14 @@ OPTIONS if unset the templates are taken from the installation defined default, typically `/usr/share/git-core/templates`. ---use-separate-remote:: - Save remotes heads under `$GIT_DIR/remotes/origin/` instead - of `$GIT_DIR/refs/heads/`. Only the master branch is saved - in the latter. +--depth=<depth>:: + Create a 'shallow' clone with a history truncated to the + specified number of revs. A shallow repository has + number of limitations (you cannot clone or fetch from + it, nor push from nor into it), but is adequate if you + want to only look at near the tip of a large project + with a long history, and would want to send in a fixes + as patches. <repository>:: The (possibly remote) repository to clone from. It can diff --git a/Documentation/git-commit-tree.txt b/Documentation/git-commit-tree.txt index 41d1a1c4b3..77ba96ed8a 100644 --- a/Documentation/git-commit-tree.txt +++ b/Documentation/git-commit-tree.txt @@ -81,6 +81,11 @@ Your parents must have hated you!:: Your sysadmin must hate you!:: The password(5) name field is longer than a giant static buffer. +Discussion +---------- + +include::i18n.txt[] + See Also -------- gitlink:git-write-tree[1] diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index 517a86b238..b4528d72ba 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -14,25 +14,42 @@ SYNOPSIS DESCRIPTION ----------- -Updates the index file for given paths, or all modified files if -'-a' is specified, and makes a commit object. The command specified -by either the VISUAL or EDITOR environment variables are used to edit -the commit log message. +Use 'git commit' when you want to record your changes into the repository +along with a log message describing what the commit is about. All changes +to be committed must be explicitly identified using one of the following +methods: -Several environment variable are used during commits. They are -documented in gitlink:git-commit-tree[1]. +1. by using gitlink:git-add[1] to incrementally "add" changes to the + next commit before using the 'commit' command (Note: even modified + files must be "added"); +2. by using gitlink:git-rm[1] to identify content removal for the next + commit, again before using the 'commit' command; + +3. by directly listing files containing changes to be committed as arguments + to the 'commit' command, in which cases only those files alone will be + considered for the commit; + +4. by using the -a switch with the 'commit' command to automatically "add" + changes from all known files i.e. files that have already been committed + before, and to automatically "rm" files that have been + removed from the working tree, and perform the actual commit. + +The gitlink:git-status[1] command can be used to obtain a +summary of what is included by any of the above for the next +commit by giving the same set of parameters you would give to +this command. + +If you make a commit and then found a mistake immediately after +that, you can recover from it with gitlink:git-reset[1]. -This command can run `commit-msg`, `pre-commit`, and -`post-commit` hooks. See link:hooks.html[hooks] for more -information. OPTIONS ------- -a|--all:: - Update all paths in the index file. This flag notices - files that have been modified and deleted, but new files - you have not told git about are not affected. + Tell the command to automatically stage files that have + been modified and deleted, but new files you have not + told git about are not affected. -c or -C <commit>:: Take existing commit object, and reuse the log message @@ -55,16 +72,9 @@ OPTIONS -s|--signoff:: Add Signed-off-by line at the end of the commit message. --v|--verify:: - Look for suspicious lines the commit introduces, and - abort committing if there is one. The definition of - 'suspicious lines' is currently the lines that has - trailing whitespaces, and the lines whose indentation - has a SP character immediately followed by a TAB - character. This is the default. - --n|--no-verify:: - The opposite of `--verify`. +--no-verify:: + This option bypasses the pre-commit hook. + See also link:hooks.html[hooks]. -e|--edit:: The message taken from file with `-F`, command line with @@ -95,69 +105,145 @@ but can be used to amend a merge commit. -- -i|--include:: - Instead of committing only the files specified on the - command line, update them in the index file and then - commit the whole index. This is the traditional - behavior. + Before making a commit out of staged contents so far, + stage the contents of paths given on the command line + as well. This is usually not what you want unless you + are concluding a conflicted merge. --o|--only:: - Commit only the files specified on the command line. - This format cannot be used during a merge, nor when the - index and the latest commit does not match on the - specified paths to avoid confusion. +-q|--quiet:: + Supress commit summary message. \--:: Do not interpret any more arguments as options. <file>...:: - Files to be committed. The meaning of these is - different between `--include` and `--only`. Without - either, it defaults `--only` semantics. + When files are given on the command line, the command + commits the contents of the named files, without + recording the changes already staged. The contents of + these files are also staged for the next commit on top + of what have been staged before. -If you make a commit and then found a mistake immediately after -that, you can recover from it with gitlink:git-reset[1]. - -Discussion +EXAMPLES +-------- +When recording your own work, the contents of modified files in +your working tree are temporarily stored to a staging area +called the "index" with gitlink:git-add[1]. Removal +of a file is staged with gitlink:git-rm[1]. After building the +state to be committed incrementally with these commands, `git +commit` (without any pathname parameter) is used to record what +has been staged so far. This is the most basic form of the +command. An example: + +------------ +$ edit hello.c +$ git rm goodbye.c +$ git add hello.c +$ git commit +------------ + +//////////// +We should fix 'git rm' to remove goodbye.c from both index and +working tree for the above example. +//////////// + +Instead of staging files after each individual change, you can +tell `git commit` to notice the changes to the files whose +contents are tracked in +your working tree and do corresponding `git add` and `git rm` +for you. That is, this example does the same as the earlier +example if there is no other change in your working tree: + +------------ +$ edit hello.c +$ rm goodbye.c +$ git commit -a +------------ + +The command `git commit -a` first looks at your working tree, +notices that you have modified hello.c and removed goodbye.c, +and performs necessary `git add` and `git rm` for you. + +After staging changes to many files, you can alter the order the +changes are recorded in, by giving pathnames to `git commit`. +When pathnames are given, the command makes a commit that +only records the changes made to the named paths: + +------------ +$ edit hello.c hello.h +$ git add hello.c hello.h +$ edit Makefile +$ git commit Makefile +------------ + +This makes a commit that records the modification to `Makefile`. +The changes staged for `hello.c` and `hello.h` are not included +in the resulting commit. However, their changes are not lost -- +they are still staged and merely held back. After the above +sequence, if you do: + +------------ +$ git commit +------------ + +this second commit would record the changes to `hello.c` and +`hello.h` as expected. + +After a merge (initiated by either gitlink:git-merge[1] or +gitlink:git-pull[1]) stops because of conflicts, cleanly merged +paths are already staged to be committed for you, and paths that +conflicted are left in unmerged state. You would have to first +check which paths are conflicting with gitlink:git-status[1] +and after fixing them manually in your working tree, you would +stage the result as usual with gitlink:git-add[1]: + +------------ +$ git status | grep unmerged +unmerged: hello.c +$ edit hello.c +$ git add hello.c +------------ + +After resolving conflicts and staging the result, `git ls-files -u` +would stop mentioning the conflicted path. When you are done, +run `git commit` to finally record the merge: + +------------ +$ git commit +------------ + +As with the case to record your own changes, you can use `-a` +option to save typing. One difference is that during a merge +resolution, you cannot use `git commit` with pathnames to +alter the order the changes are committed, because the merge +should be recorded as a single commit. In fact, the command +refuses to run when given pathnames (but see `-i` option). + + +DISCUSSION ---------- -`git commit` without _any_ parameter commits the tree structure -recorded by the current index file. This is a whole-tree commit -even the command is invoked from a subdirectory. - -`git commit --include paths...` is equivalent to - - git update-index --remove paths... - git commit - -That is, update the specified paths to the index and then commit -the whole tree. - -`git commit paths...` largely bypasses the index file and -commits only the changes made to the specified paths. It has -however several safety valves to prevent confusion. +include::i18n.txt[] -. It refuses to run during a merge (i.e. when - `$GIT_DIR/MERGE_HEAD` exists), and reminds trained git users - that the traditional semantics now needs -i flag. +ENVIRONMENT VARIABLES +--------------------- +The command specified by either the VISUAL or EDITOR environment +variables is used to edit the commit log message. -. It refuses to run if named `paths...` are different in HEAD - and the index (ditto about reminding). Added paths are OK. - This is because an earlier `git diff` (not `git diff HEAD`) - would have shown the differences since the last `git - update-index paths...` to the user, and an inexperienced user - may mistakenly think that the changes between the index and - the HEAD (i.e. earlier changes made before the last `git - update-index paths...` was done) are not being committed. - -. It reads HEAD commit into a temporary index file, updates the - specified `paths...` and makes a commit. At the same time, - the real index file is also updated with the same `paths...`. +HOOKS +----- +This command can run `commit-msg`, `pre-commit`, and +`post-commit` hooks. See link:hooks.html[hooks] for more +information. -`git commit --all` updates the index file with _all_ changes to -the working tree, and makes a whole-tree commit, regardless of -which subdirectory the command is invoked in. +SEE ALSO +-------- +gitlink:git-add[1], +gitlink:git-rm[1], +gitlink:git-mv[1], +gitlink:git-merge[1], +gitlink:git-commit-tree[1] Author ------ diff --git a/Documentation/git-count-objects.txt b/Documentation/git-count-objects.txt index 198ce77a8a..c59df6438c 100644 --- a/Documentation/git-count-objects.txt +++ b/Documentation/git-count-objects.txt @@ -20,8 +20,8 @@ OPTIONS -v:: In addition to the number of loose objects and disk space consumed, it reports the number of in-pack - objects, and number of objects that can be removed by - running `git-prune-packed`. + objects, number of packs, and number of objects that can be + removed by running `git-prune-packed`. Author diff --git a/Documentation/git-cvsimport.txt b/Documentation/git-cvsimport.txt index d21d66bfeb..5c402de267 100644 --- a/Documentation/git-cvsimport.txt +++ b/Documentation/git-cvsimport.txt @@ -90,7 +90,8 @@ If you need to pass multiple options, separate them with a comma. Print a short usage message and exit. -z <fuzz>:: - Pass the timestamp fuzz factor to cvsps. + Pass the timestamp fuzz factor to cvsps, in seconds. If unset, + cvsps defaults to 300s. -s <subst>:: Substitute the character "/" in branch names with <subst> @@ -99,6 +100,18 @@ If you need to pass multiple options, separate them with a comma. CVS by default uses the unix username when writing its commit logs. Using this option and an author-conv-file in this format + +-a:: + Import all commits, including recent ones. cvsimport by default + skips commits that have a timestamp less than 10 minutes ago. + +-S <regex>:: + Skip paths matching the regex. + +-L <limit>:: + Limit the number of commits imported. Workaround for cases where + cvsimport leaks memory. + + --------- exon=Andreas Ericsson <ae@op5.se> diff --git a/Documentation/git-daemon.txt b/Documentation/git-daemon.txt index 0f7d274eab..993adc7c5a 100644 --- a/Documentation/git-daemon.txt +++ b/Documentation/git-daemon.txt @@ -8,19 +8,21 @@ git-daemon - A really simple server for git repositories SYNOPSIS -------- [verse] -'git-daemon' [--verbose] [--syslog] [--inetd | --port=n] [--export-all] +'git-daemon' [--verbose] [--syslog] [--export-all] [--timeout=n] [--init-timeout=n] [--strict-paths] [--base-path=path] [--user-path | --user-path=path] - [--reuseaddr] [--detach] [--pid-file=file] [directory...] + [--interpolated-path=pathtemplate] + [--reuseaddr] [--detach] [--pid-file=file] + [--enable=service] [--disable=service] + [--allow-override=service] [--forbid-override=service] + [--inetd | [--listen=host_or_ipaddr] [--port=n] [--user=user [--group=group]] + [directory...] DESCRIPTION ----------- A really simple TCP git daemon that normally listens on port "DEFAULT_GIT_PORT" -aka 9418. It waits for a connection, and will just execute "git-upload-pack" -when it gets one. - -It's careful in that there's a magic request-line that gives the command and -what directory to upload, and it verifies that the directory is OK. +aka 9418. It waits for a connection asking for a service, and will serve +that service if it is enabled. It verifies that the directory has the magic file "git-daemon-export-ok", and it will refuse to export any git directory that hasn't explicitly been marked @@ -28,7 +30,14 @@ for export this way (unless the '--export-all' parameter is specified). If you pass some directory paths as 'git-daemon' arguments, you can further restrict the offers to a whitelist comprising of those. -This is ideally suited for read-only updates, i.e., pulling from git repositories. +By default, only `upload-pack` service is enabled, which serves +`git-fetch-pack` and `git-peek-remote` clients that are invoked +from `git-fetch`, `git-ls-remote`, and `git-clone`. + +This is ideally suited for read-only updates, i.e., pulling from +git repositories. + +An `upload-archive` also exists to serve `git-archive`. OPTIONS ------- @@ -45,6 +54,16 @@ OPTIONS 'git://example.com/hello.git', `git-daemon` will interpret the path as '/srv/git/hello.git'. +--interpolated-path=pathtemplate:: + To support virtual hosting, an interpolated path template can be + used to dynamically construct alternate paths. The template + supports %H for the target hostname as supplied by the client but + converted to all lowercase, %CH for the canonical hostname, + %IP for the server's IP address, %P for the port number, + and %D for the absolute path of the named repository. + After interpolation, the path is validated against the directory + whitelist. + --export-all:: Allow pulling from all directories that look like GIT repositories (have the 'objects' and 'refs' subdirectories), even if they @@ -52,9 +71,17 @@ OPTIONS --inetd:: Have the server run as an inetd service. Implies --syslog. + Incompatible with --port, --listen, --user and --group options. ---port:: - Listen on an alternative port. +--listen=host_or_ipaddr:: + Listen on an a specific IP address or hostname. IP addresses can + be either an IPv4 address or an IPV6 address if supported. If IPv6 + is not supported, then --listen=hostname is also not supported and + --listen must be given an IPv4 address. + Incompatible with '--inetd' option. + +--port=n:: + Listen on an alternative port. Incompatible with '--inetd' option. --init-timeout:: Timeout between the moment the connection is established and the @@ -93,11 +120,109 @@ OPTIONS --pid-file=file:: Save the process id in 'file'. +--user=user, --group=group:: + Change daemon's uid and gid before entering the service loop. + When only `--user` is given without `--group`, the + primary group ID for the user is used. The values of + the option are given to `getpwnam(3)` and `getgrnam(3)` + and numeric IDs are not supported. ++ +Giving these options is an error when used with `--inetd`; use +the facility of inet daemon to achieve the same before spawning +`git-daemon` if needed. + +--enable-service, --disable-service:: + Enable/disable the service site-wide per default. Note + that a service disabled site-wide can still be enabled + per repository if it is marked overridable and the + repository enables the service with an configuration + item. + +--allow-override, --forbid-override:: + Allow/forbid overriding the site-wide default with per + repository configuration. By default, all the services + are overridable. + <directory>:: A directory to add to the whitelist of allowed directories. Unless --strict-paths is specified this will also include subdirectories of each named directory. +SERVICES +-------- + +upload-pack:: + This serves `git-fetch-pack` and `git-peek-remote` + clients. It is enabled by default, but a repository can + disable it by setting `daemon.uploadpack` configuration + item to `false`. + +upload-archive:: + This serves `git-archive --remote`. + +EXAMPLES +-------- +We assume the following in /etc/services:: ++ +------------ +$ grep 9418 /etc/services +git 9418/tcp # Git Version Control System +------------ + +git-daemon as inetd server:: + To set up `git-daemon` as an inetd service that handles any + repository under the whitelisted set of directories, /pub/foo + and /pub/bar, place an entry like the following into + /etc/inetd all on one line: ++ +------------------------------------------------ + git stream tcp nowait nobody /usr/bin/git-daemon + git-daemon --inetd --verbose --export-all + /pub/foo /pub/bar +------------------------------------------------ + + +git-daemon as inetd server for virtual hosts:: + To set up `git-daemon` as an inetd service that handles + repositories for different virtual hosts, `www.example.com` + and `www.example.org`, place an entry like the following into + `/etc/inetd` all on one line: ++ +------------------------------------------------ + git stream tcp nowait nobody /usr/bin/git-daemon + git-daemon --inetd --verbose --export-all + --interpolated-path=/pub/%H%D + /pub/www.example.org/software + /pub/www.example.com/software + /software +------------------------------------------------ ++ +In this example, the root-level directory `/pub` will contain +a subdirectory for each virtual host name supported. +Further, both hosts advertise repositories simply as +`git://www.example.com/software/repo.git`. For pre-1.4.0 +clients, a symlink from `/software` into the appropriate +default repository could be made as well. + + +git-daemon as regular daemon for virtual hosts:: + To set up `git-daemon` as a regular, non-inetd service that + handles repositories for multiple virtual hosts based on + their IP addresses, start the daemon like this: ++ +------------------------------------------------ + git-daemon --verbose --export-all + --interpolated-path=/pub/%IP/%D + /pub/192.168.1.200/software + /pub/10.10.220.23/software +------------------------------------------------ ++ +In this example, the root-level directory `/pub` will contain +a subdirectory for each virtual host IP address supported. +Repositories can still be accessed by hostname though, assuming +they correspond to these IP addresses. + + Author ------ Written by Linus Torvalds <torvalds@osdl.org>, YOSHIFUJI Hideaki diff --git a/Documentation/git-diff-index.txt b/Documentation/git-diff-index.txt index 9cd43f105b..2df581c2c9 100644 --- a/Documentation/git-diff-index.txt +++ b/Documentation/git-diff-index.txt @@ -54,7 +54,7 @@ If '--cached' is specified, it allows you to ask: For example, let's say that you have worked on your working directory, updated some files in the index and are ready to commit. You want to see exactly -*what* you are going to commit is without having to write a new tree +*what* you are going to commit, without having to write a new tree object and compare it that way, and to do that, you just do git-diff-index --cached HEAD @@ -68,7 +68,7 @@ matches my working directory. But doing a "git-diff-index" does: -100644 blob 4161aecc6700a2eb579e842af0b7f22b98443f74 commit.c +100644 blob 4161aecc6700a2eb579e842af0b7f22b98443f74 git-commit.c -You can trivially see that the above is a rename. +You can see easily that the above is a rename. In fact, "git-diff-index --cached" *should* always be entirely equivalent to actually doing a "git-write-tree" and comparing that. Except this one is much diff --git a/Documentation/git-diff-tree.txt b/Documentation/git-diff-tree.txt index f7e8ff2968..5d6e9dc751 100644 --- a/Documentation/git-diff-tree.txt +++ b/Documentation/git-diff-tree.txt @@ -73,10 +73,7 @@ separated with a single space are given. This flag causes "git-diff-tree --stdin" to also show the commit message before the differences. ---pretty[=(raw|medium|short)]:: - This is used to control "pretty printing" format of the - commit message. Without "=<style>", it defaults to - medium. +include::pretty-formats.txt[] --no-commit-id:: git-diff-tree outputs a line with the commit ID when diff --git a/Documentation/git-diff.txt b/Documentation/git-diff.txt index 228c4d95bd..8977877b21 100644 --- a/Documentation/git-diff.txt +++ b/Documentation/git-diff.txt @@ -8,36 +8,54 @@ git-diff - Show changes between commits, commit and working tree, etc SYNOPSIS -------- -'git-diff' [ --diff-options ] <tree-ish>{0,2} [<path>...] +'git-diff' [ --diff-options ] <commit>{0,2} [--] [<path>...] DESCRIPTION ----------- Show changes between two trees, a tree and the working tree, a tree and the index file, or the index file and the working tree. -The combination of what is compared with what is determined by -the number of trees given to the command. -* When no <tree-ish> is given, the working tree and the index - file are compared, using `git-diff-files`. +'git-diff' [--options] [--] [<path>...]:: -* When one <tree-ish> is given, the working tree and the named - tree are compared, using `git-diff-index`. The option - `--cached` can be given to compare the index file and - the named tree. + This form is to view the changes you made relative to + the index (staging area for the next commit). In other + words, the differences are what you _could_ tell git to + further add to the index but you still haven't. You can + stage these changes by using gitlink:git-add[1]. + +'git-diff' [--options] --cached [<commit>] [--] [<path>...]:: + + This form is to view the changes you staged for the next + commit relative to the named <commit>. Typically you + would want comparison with the latest commit, so if you + do not give <commit>, it defaults to HEAD. + +'git-diff' [--options] <commit> [--] [<path>...]:: + + This form is to view the changes you have in your + working tree relative to the named <commit>. You can + use HEAD to compare it with the latest commit, or a + branch name to compare with the tip of a different + branch. + +'git-diff' [--options] <commit> <commit> [--] [<path>...]:: + + This form is to view the changes between two <commit>, + for example, tips of two branches. + +Just in case if you are doing something exotic, it should be +noted that all of the <commit> in the above description can be +any <tree-ish>. -* When two <tree-ish>s are given, these two trees are compared - using `git-diff-tree`. OPTIONS ------- ---diff-options:: - '--diff-options' are passed to the `git-diff-files`, - `git-diff-index`, and `git-diff-tree` commands. See the - documentation for these commands for description. +include::diff-options.txt[] <path>...:: - The <path> arguments are also passed to `git-diff-\*` - commands. + The <paths> parameters, when given, are used to limit + the diff to the named paths (you can give directory + names and get diff for all files under them). EXAMPLES @@ -51,7 +69,7 @@ $ git diff --cached <2> $ git diff HEAD <3> ------------ + -<1> changes in the working tree since your last git-update-index. +<1> changes in the working tree not yet staged for the next commit. <2> changes between the index and your last commit; what you would be committing if you run "git commit" without "-a" option. <3> changes in the working tree since your last commit; what you diff --git a/Documentation/git-fetch-pack.txt b/Documentation/git-fetch-pack.txt index bff9aa6939..3e6cd880b0 100644 --- a/Documentation/git-fetch-pack.txt +++ b/Documentation/git-fetch-pack.txt @@ -32,7 +32,8 @@ OPTIONS -k:: Do not invoke 'git-unpack-objects' on received data, but create a single packfile out of it instead, and store it - in the object database. + in the object database. If provided twice then the pack is + locked against repacking. --exec=<git-upload-pack>:: Use this to specify the path to 'git-upload-pack' on the diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt new file mode 100644 index 0000000000..2bf6aef735 --- /dev/null +++ b/Documentation/git-for-each-ref.txt @@ -0,0 +1,185 @@ +git-for-each-ref(1) +=================== + +NAME +---- +git-for-each-ref - Output information on each ref + +SYNOPSIS +-------- +'git-for-each-ref' [--count=<count>]\* [--shell|--perl|--python] [--sort=<key>]\* [--format=<format>] [<pattern>] + +DESCRIPTION +----------- + +Iterate over all refs that match `<pattern>` and show them +according to the given `<format>`, after sorting them according +to the given set of `<key>`. If `<max>` is given, stop after +showing that many refs. The interporated values in `<format>` +can optionally be quoted as string literals in the specified +host language allowing their direct evaluation in that language. + +OPTIONS +------- +<count>:: + By default the command shows all refs that match + `<pattern>`. This option makes it stop after showing + that many refs. + +<key>:: + A field name to sort on. Prefix `-` to sort in + descending order of the value. When unspecified, + `refname` is used. More than one sort keys can be + given. + +<format>:: + A string that interpolates `%(fieldname)` from the + object pointed at by a ref being shown. If `fieldname` + is prefixed with an asterisk (`*`) and the ref points + at a tag object, the value for the field in the object + tag refers is used. When unspecified, defaults to + `%(objectname) SPC %(objecttype) TAB %(refname)`. + It also interpolates `%%` to `%`, and `%xx` where `xx` + are hex digits interpolates to character with hex code + `xx`; for example `%00` interpolates to `\0` (NUL), + `%09` to `\t` (TAB) and `%0a` to `\n` (LF). + +<pattern>:: + If given, the name of the ref is matched against this + using fnmatch(3). Refs that do not match the pattern + are not shown. + +--shell, --perl, --python:: + If given, strings that substitute `%(fieldname)` + placeholders are quoted as string literals suitable for + the specified host language. This is meant to produce + a scriptlet that can directly be `eval`ed. + + +FIELD NAMES +----------- + +Various values from structured fields in referenced objects can +be used to interpolate into the resulting output, or as sort +keys. + +For all objects, the following names can be used: + +refname:: + The name of the ref (the part after $GIT_DIR/refs/). + +objecttype:: + The type of the object (`blob`, `tree`, `commit`, `tag`). + +objectsize:: + The size of the object (the same as `git-cat-file -s` reports). + +objectname:: + The object name (aka SHA-1). + +In addition to the above, for commit and tag objects, the header +field names (`tree`, `parent`, `object`, `type`, and `tag`) can +be used to specify the value in the header field. + +Fields that have name-email-date tuple as its value (`author`, +`committer`, and `tagger`) can be suffixed with `name`, `email`, +and `date` to extract the named component. + +The first line of the message in a commit and tag object is +`subject`, the remaining lines are `body`. The whole message +is `contents`. + +For sorting purposes, fields with numeric values sort in numeric +order (`objectsize`, `authordate`, `committerdate`, `taggerdate`). +All other fields are used to sort in their byte-value order. + +In any case, a field name that refers to a field inapplicable to +the object referred by the ref does not cause an error. It +returns an empty string instead. + + +EXAMPLES +-------- + +An example directly producing formatted text. Show the most recent +3 tagged commits:: + +------------ +#!/bin/sh + +git-for-each-ref --count=3 --sort='-*authordate' \ +--format='From: %(*authorname) %(*authoremail) +Subject: %(*subject) +Date: %(*authordate) +Ref: %(*refname) + +%(*body) +' 'refs/tags' +------------ + + +A simple example showing the use of shell eval on the output, +demonstrating the use of --shell. List the prefixes of all heads:: +------------ +#!/bin/sh + +git-for-each-ref --shell --format="ref=%(refname)" refs/heads | \ +while read entry +do + eval "$entry" + echo `dirname $ref` +done +------------ + + +A bit more elaborate report on tags, demonstrating that the format +may be an entire script:: +------------ +#!/bin/sh + +fmt=' + r=%(refname) + t=%(*objecttype) + T=${r#refs/tags/} + + o=%(*objectname) + n=%(*authorname) + e=%(*authoremail) + s=%(*subject) + d=%(*authordate) + b=%(*body) + + kind=Tag + if test "z$t" = z + then + # could be a lightweight tag + t=%(objecttype) + kind="Lightweight tag" + o=%(objectname) + n=%(authorname) + e=%(authoremail) + s=%(subject) + d=%(authordate) + b=%(body) + fi + echo "$kind $T points at a $t object $o" + if test "z$t" = zcommit + then + echo "The commit was authored by $n $e +at $d, and titled + + $s + +Its message reads as: +" + echo "$b" | sed -e "s/^/ /" + echo + fi +' + +eval=`git-for-each-ref --shell --format="$fmt" \ + --sort='*objecttype' \ + --sort=-taggerdate \ + refs/tags` +eval "$eval" +------------ diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt new file mode 100644 index 0000000000..73d78c15e8 --- /dev/null +++ b/Documentation/git-gc.txt @@ -0,0 +1,64 @@ +git-gc(1) +========= + +NAME +---- +git-gc - Cleanup unnecessary files and optimize the local repository + + +SYNOPSIS +-------- +'git-gc' + +DESCRIPTION +----------- +Runs a number of housekeeping tasks within the current repository, +such as compressing file revisions (to reduce disk space and increase +performance) and removing unreachable objects which may have been +created from prior invocations of gitlink:git-add[1]. + +Users are encouraged to run this task on a regular basis within +each repository to maintain good disk space utilization and good +operating performance. + +Configuration +------------- + +The optional configuration variable 'gc.reflogExpire' can be +set to indicate how long historical entries within each branch's +reflog should remain available in this repository. The setting is +expressed as a length of time, for example '90 days' or '3 months'. +It defaults to '90 days'. + +The optional configuration variable 'gc.reflogExpireUnreachable' +can be set to indicate how long historical reflog entries which +are not part of the current branch should remain available in +this repository. These types of entries are generally created as +a result of using `git commit \--amend` or `git rebase` and are the +commits prior to the amend or rebase occuring. Since these changes +are not part of the current project most users will want to expire +them sooner. This option defaults to '30 days'. + +The optional configuration variable 'gc.rerereresolved' indicates +how long records of conflicted merge you resolved earlier are +kept. This defaults to 60 days. + +The optional configuration variable 'gc.rerereunresolved' indicates +how long records of conflicted merge you have not resolved are +kept. This defaults to 15 days. + + +See Also +-------- +gitlink:git-prune[1] +gitlink:git-reflog[1] +gitlink:git-repack[1] +gitlink:git-rerere[1] + +Author +------ +Written by Shawn O. Pearce <spearce@spearce.org> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt index 7545dd9a3e..bfbece9864 100644 --- a/Documentation/git-grep.txt +++ b/Documentation/git-grep.txt @@ -11,10 +11,10 @@ SYNOPSIS [verse] 'git-grep' [--cached] [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp] - [-v | --invert-match] [--full-name] + [-v | --invert-match] [-h|-H] [--full-name] [-E | --extended-regexp] [-G | --basic-regexp] [-F | --fixed-strings] [-n] [-l | --files-with-matches] [-L | --files-without-match] - [-c | --count] + [-c | --count] [--all-match] [-A <post-context>] [-B <pre-context>] [-C <context>] [-f <file>] [-e] <pattern> [--and|--or|--not|(|)|-e <pattern>...] [<tree>...] @@ -47,6 +47,13 @@ OPTIONS -v | --invert-match:: Select non-matching lines. +-h | -H:: + By default, the command shows the filename for each + match. `-h` option is used to suppress this output. + `-H` is there for completeness and does not do anything + except it overrides `-h` given earlier on the command + line. + --full-name:: When run from a subdirectory, the command usually outputs paths relative to the current directory. This @@ -89,6 +96,11 @@ OPTIONS higher precedence than `--or`. `-e` has to be used for all patterns. +--all-match:: + When giving multiple pattern expressions combined with `--or`, + this flag is specified to limit the match to files that + have lines to match all of them. + `<tree>...`:: Search blobs in the trees for specified patterns. @@ -104,6 +116,10 @@ git grep -e \'#define\' --and \( -e MAX_PATH -e PATH_MAX \):: Looks for a line that has `#define` and either `MAX_PATH` or `PATH_MAX`. +git grep --all-match -e NODE -e Unexpected:: + Looks for a line that has `NODE` or `Unexpected` in + files that have lines that match both. + Author ------ Originally written by Linus Torvalds <torvalds@osdl.org>, later diff --git a/Documentation/git-http-push.txt b/Documentation/git-http-push.txt index 7e1f894a92..c2485c6e9c 100644 --- a/Documentation/git-http-push.txt +++ b/Documentation/git-http-push.txt @@ -34,7 +34,7 @@ OPTIONS Report the list of objects being walked locally and the list of objects successfully sent to the remote repository. -<ref>...: +<ref>...:: The remote refs to update. diff --git a/Documentation/git-index-pack.txt b/Documentation/git-index-pack.txt index 71ce557276..2229ee86b7 100644 --- a/Documentation/git-index-pack.txt +++ b/Documentation/git-index-pack.txt @@ -8,7 +8,8 @@ git-index-pack - Build pack index file for an existing packed archive SYNOPSIS -------- -'git-index-pack' [-o <index-file>] <pack-file> +'git-index-pack' [-v] [-o <index-file>] <pack-file> +'git-index-pack' --stdin [--fix-thin] [--keep] [-v] [-o <index-file>] [<pack-file>] DESCRIPTION @@ -21,6 +22,9 @@ objects/pack/ directory of a git repository. OPTIONS ------- +-v:: + Be verbose about what is going on, including progress status. + -o <index-file>:: Write the generated pack index into the specified file. Without this option the name of pack index @@ -29,6 +33,52 @@ OPTIONS fails if the name of packed archive does not end with .pack). +--stdin:: + When this flag is provided, the pack is read from stdin + instead and a copy is then written to <pack-file>. If + <pack-file> is not specified, the pack is written to + objects/pack/ directory of the current git repository with + a default name determined from the pack content. If + <pack-file> is not specified consider using --keep to + prevent a race condition between this process and + gitlink::git-repack[1] . + +--fix-thin:: + It is possible for gitlink:git-pack-objects[1] to build + "thin" pack, which records objects in deltified form based on + objects not included in the pack to reduce network traffic. + Those objects are expected to be present on the receiving end + and they must be included in the pack for that pack to be self + contained and indexable. Without this option any attempt to + index a thin pack will fail. This option only makes sense in + conjunction with --stdin. + +--keep:: + Before moving the index into its final destination + create an empty .keep file for the associated pack file. + This option is usually necessary with --stdin to prevent a + simultaneous gitlink:git-repack[1] process from deleting + the newly constructed pack and index before refs can be + updated to use objects contained in the pack. + +--keep='why':: + Like --keep create a .keep file before moving the index into + its final destination, but rather than creating an empty file + place 'why' followed by an LF into the .keep file. The 'why' + message can later be searched for within all .keep files to + locate any which have outlived their usefulness. + + +Note +---- + +Once the index has been created, the list of object names is sorted +and the SHA1 hash of that list is printed to stdout. If --stdin was +also used then this is prefixed by either "pack\t", or "keep\t" if a +new .keep file was successfully created. This is useful to remove a +.keep file used as a lock to prevent the race with gitlink:git-repack[1] +mentioned above. + Author ------ diff --git a/Documentation/git-init-db.txt b/Documentation/git-init-db.txt index 63cd5dab3f..5412135d76 100644 --- a/Documentation/git-init-db.txt +++ b/Documentation/git-init-db.txt @@ -11,91 +11,9 @@ SYNOPSIS 'git-init-db' [--template=<template_directory>] [--shared[=<permissions>]] -OPTIONS -------- - --- - ---template=<template_directory>:: - -Provide the directory from which templates will be used. The default template -directory is `/usr/share/git-core/templates`. - -When specified, `<template_directory>` is used as the source of the template -files rather than the default. The template files include some directory -structure, some suggested "exclude patterns", and copies of non-executing -"hook" files. The suggested patterns and hook files are all modifiable and -extensible. - ---shared[={false|true|umask|group|all|world|everybody}]:: - -Specify that the git repository is to be shared amongst several users. This -allows users belonging to the same group to push into that -repository. When specified, the config variable "core.sharedRepository" is -set so that files and directories under `$GIT_DIR` are created with the -requested permissions. When not specified, git will use permissions reported -by umask(2). - -The option can have the following values, defaulting to 'group' if no value -is given: - - - 'umask' (or 'false'): Use permissions reported by umask(2). The default, - when `--shared` is not specified. - - - 'group' (or 'true'): Make the repository group-writable, (and g+sx, since - the git group may be not the primary group of all users). - - - 'all' (or 'world' or 'everybody'): Same as 'group', but make the repository - readable by all users. - --- - - DESCRIPTION ----------- -This command creates an empty git repository - basically a `.git` directory -with subdirectories for `objects`, `refs/heads`, `refs/tags`, and -template files. -An initial `HEAD` file that references the HEAD of the master branch -is also created. - -If the `$GIT_DIR` environment variable is set then it specifies a path -to use instead of `./.git` for the base of the repository. - -If the object storage directory is specified via the `$GIT_OBJECT_DIRECTORY` -environment variable then the sha1 directories are created underneath - -otherwise the default `$GIT_DIR/objects` directory is used. - -Running `git-init-db` in an existing repository is safe. It will not overwrite -things that are already there. The primary reason for rerunning `git-init-db` -is to pick up newly added templates. - - - -EXAMPLES --------- - -Start a new git repository for an existing code base:: -+ ----------------- -$ cd /path/to/my/codebase -$ git-init-db <1> -$ git-add . <2> ----------------- -+ -<1> prepare /path/to/my/codebase/.git directory -<2> add all existing file to the index - - -Author ------- -Written by Linus Torvalds <torvalds@osdl.org> - -Documentation --------------- -Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. -GIT ---- -Part of the gitlink:git[7] suite +This is a synonym for gitlink:git-init[1]. Please refer to the +documentation of that command. diff --git a/Documentation/git-init.txt b/Documentation/git-init.txt new file mode 100644 index 0000000000..596b567c90 --- /dev/null +++ b/Documentation/git-init.txt @@ -0,0 +1,111 @@ +git-init(1) +=========== + +NAME +---- +git-init - Creates an empty git repository + + +SYNOPSIS +-------- +'git-init' [--template=<template_directory>] [--shared[=<permissions>]] + + +OPTIONS +------- + +-- + +--template=<template_directory>:: + +Provide the directory from which templates will be used. The default template +directory is `/usr/share/git-core/templates`. + +When specified, `<template_directory>` is used as the source of the template +files rather than the default. The template files include some directory +structure, some suggested "exclude patterns", and copies of non-executing +"hook" files. The suggested patterns and hook files are all modifiable and +extensible. + +--shared[={false|true|umask|group|all|world|everybody}]:: + +Specify that the git repository is to be shared amongst several users. This +allows users belonging to the same group to push into that +repository. When specified, the config variable "core.sharedRepository" is +set so that files and directories under `$GIT_DIR` are created with the +requested permissions. When not specified, git will use permissions reported +by umask(2). + +The option can have the following values, defaulting to 'group' if no value +is given: + + - 'umask' (or 'false'): Use permissions reported by umask(2). The default, + when `--shared` is not specified. + + - 'group' (or 'true'): Make the repository group-writable, (and g+sx, since + the git group may be not the primary group of all users). + + - 'all' (or 'world' or 'everybody'): Same as 'group', but make the repository + readable by all users. + +By default, the configuration flag receive.denyNonFastforward is enabled +in shared repositories, so that you cannot force a non fast-forwarding push +into it. + +-- + + +DESCRIPTION +----------- +This command creates an empty git repository - basically a `.git` directory +with subdirectories for `objects`, `refs/heads`, `refs/tags`, and +template files. +An initial `HEAD` file that references the HEAD of the master branch +is also created. + +If the `$GIT_DIR` environment variable is set then it specifies a path +to use instead of `./.git` for the base of the repository. + +If the object storage directory is specified via the `$GIT_OBJECT_DIRECTORY` +environment variable then the sha1 directories are created underneath - +otherwise the default `$GIT_DIR/objects` directory is used. + +Running `git-init` in an existing repository is safe. It will not overwrite +things that are already there. The primary reason for rerunning `git-init` +is to pick up newly added templates. + +Note that `git-init` is the same as `git-init-db`. The command +was primarily meant to initialize the object database, but over +time it has become responsible for setting up the other aspects +of the repository, such as installing the default hooks and +setting the configuration variables. The old name is retained +for backward compatibility reasons. + + +EXAMPLES +-------- + +Start a new git repository for an existing code base:: ++ +---------------- +$ cd /path/to/my/codebase +$ git-init <1> +$ git-add . <2> +---------------- ++ +<1> prepare /path/to/my/codebase/.git directory +<2> add all existing file to the index + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index c9ffff734c..e9f746bbd4 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -24,14 +24,16 @@ This manual page describes only the most frequently used options. OPTIONS ------- ---pretty=<format>:: - Controls the way the commit log is formatted. + +include::pretty-formats.txt[] --max-count=<n>:: Limits the number of commits to show. <since>..<until>:: - Show only commits between the named two commits. + Show only commits between the named two commits. When + either <since> or <until> is omitted, it defaults to + `HEAD`, i.e. the tip of the current branch. -p:: Show the change the commit introduces in a patch form. @@ -63,6 +65,12 @@ git log -r --name-status release..test:: in the "release" branch, along with the list of paths each commit modifies. +Discussion +---------- + +include::i18n.txt[] + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-ls-remote.txt b/Documentation/git-ls-remote.txt index ae4c1a250e..c8a4c5a4d9 100644 --- a/Documentation/git-ls-remote.txt +++ b/Documentation/git-ls-remote.txt @@ -3,16 +3,19 @@ git-ls-remote(1) NAME ---- -git-ls-remote - Look at references other repository has +git-ls-remote - List references in a remote repository SYNOPSIS -------- -'git-ls-remote' [--heads] [--tags] <repository> <refs>... +[verse] +'git-ls-remote' [--heads] [--tags] [-u <exec> | --upload-pack <exec>] + <repository> <refs>... DESCRIPTION ----------- -Displays the references other repository has. +Displays references available in a remote repository along with the associated +commit IDs. OPTIONS @@ -23,9 +26,16 @@ OPTIONS both, references stored in refs/heads and refs/tags are displayed. +-u <exec>, --upload-pack=<exec>:: + Specify the full path of gitlink:git-upload-pack[1] on the remote + host. This allows listing references from repositories accessed via + SSH and where the SSH deamon does not use the PATH configured by the + user. Also see the '--exec' option for gitlink:git-peek-remote[1]. + <repository>:: Location of the repository. The shorthand defined in - $GIT_DIR/branches/ can be used. + $GIT_DIR/branches/ can be used. Use "." (dot) to list references in + the local repository. <refs>...:: When unspecified, all references, after filtering done diff --git a/Documentation/git-mailinfo.txt b/Documentation/git-mailinfo.txt index ea0a06557f..5088bbea84 100644 --- a/Documentation/git-mailinfo.txt +++ b/Documentation/git-mailinfo.txt @@ -33,15 +33,13 @@ OPTIONS format-patch --mbox' output. -u:: - By default, the commit log message, author name and - author email are taken from the e-mail without any - charset conversion, after minimally decoding MIME - transfer encoding. This flag causes the resulting - commit to be encoded in the encoding specified by - i18n.commitencoding configuration (defaults to utf-8) by - transliterating them. - Note that the patch is always used as is without charset - conversion, even with this flag. + The commit log message, author name and author email are + taken from the e-mail, and after minimally decoding MIME + transfer encoding, re-coded in UTF-8 by transliterating + them. This used to be optional but now it is the default. ++ +Note that the patch is always used as-is without charset +conversion, even with this flag. --encoding=<encoding>:: Similar to -u but if the local convention is different diff --git a/Documentation/git-merge-file.txt b/Documentation/git-merge-file.txt new file mode 100644 index 0000000000..29d3faa556 --- /dev/null +++ b/Documentation/git-merge-file.txt @@ -0,0 +1,92 @@ +git-merge-file(1) +================= + +NAME +---- +git-merge-file - three-way file merge + + +SYNOPSIS +-------- +[verse] +'git-merge-file' [-L <current-name> [-L <base-name> [-L <other-name>]]] + [-p|--stdout] [-q|--quiet] <current-file> <base-file> <other-file> + + +DESCRIPTION +----------- +git-file-merge incorporates all changes that lead from the `<base-file>` +to `<other-file>` into `<current-file>`. The result ordinarily goes into +`<current-file>`. git-merge-file is useful for combining separate changes +to an original. Suppose `<base-file>` is the original, and both +`<current-file>` and `<other-file>` are modifications of `<base-file>`. +Then git-merge-file combines both changes. + +A conflict occurs if both `<current-file>` and `<other-file>` have changes +in a common segment of lines. If a conflict is found, git-merge-file +normally outputs a warning and brackets the conflict with <<<<<<< and +>>>>>>> lines. A typical conflict will look like this: + + <<<<<<< A + lines in file A + ======= + lines in file B + >>>>>>> B + +If there are conflicts, the user should edit the result and delete one of +the alternatives. + +The exit value of this program is negative on error, and the number of +conflicts otherwise. If the merge was clean, the exit value is 0. + +git-merge-file is designed to be a minimal clone of RCS merge, that is, it +implements all of RCS merge's functionality which is needed by +gitlink:git[1]. + + +OPTIONS +------- + +-L <label>:: + This option may be given up to three times, and + specifies labels to be used in place of the + corresponding file names in conflict reports. That is, + `git-merge-file -L x -L y -L z a b c` generates output that + looks like it came from files x, y and z instead of + from files a, b and c. + +-p:: + Send results to standard output instead of overwriting + `<current-file>`. + +-q:: + Quiet; do not warn about conflicts. + + +EXAMPLES +-------- + +git merge-file README.my README README.upstream:: + + combines the changes of README.my and README.upstream since README, + tries to merge them and writes the result into README.my. + +git merge-file -L a -L b -L c tmp/a123 tmp/b234 tmp/c345:: + + merges tmp/a123 and tmp/c345 with the base tmp/b234, but uses labels + `a` and `c` instead of `tmp/a123` and `tmp/c345`. + + +Author +------ +Written by Johannes Schindelin <johannes.schindelin@gmx.de> + + +Documentation +-------------- +Documentation by Johannes Schindelin and the git-list <git@vger.kernel.org>, +with parts copied from the original documentation of RCS merge. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-merge-index.txt b/Documentation/git-merge-index.txt index 6cd0601082..0cf505ea84 100644 --- a/Documentation/git-merge-index.txt +++ b/Documentation/git-merge-index.txt @@ -40,8 +40,8 @@ If "git-merge-index" is called with multiple <file>s (or -a) then it processes them in turn only stopping if merge returns a non-zero exit code. -Typically this is run with the a script calling the merge command from -the RCS package. +Typically this is run with the a script calling git's imitation of +the merge command from the RCS package. A sample script called "git-merge-one-file" is included in the distribution. diff --git a/Documentation/git-merge.txt b/Documentation/git-merge.txt index bebf30ad3d..0f79665ea6 100644 --- a/Documentation/git-merge.txt +++ b/Documentation/git-merge.txt @@ -8,12 +8,13 @@ git-merge - Grand Unified Merge Driver SYNOPSIS -------- -'git-merge' [-n] [--no-commit] [-s <strategy>]... <msg> <head> <remote> <remote>... - +[verse] +'git-merge' [-n] [--no-commit] [--squash] [-s <strategy>]... + -m=<msg> <remote> <remote>... DESCRIPTION ----------- -This is the top-level user interface to the merge machinery +This is the top-level interface to the merge machinery which drives multiple merge strategy scripts. @@ -27,10 +28,11 @@ include::merge-options.txt[] to give a good default for automated `git-merge` invocations. <head>:: - our branch head commit. + Our branch head commit. This has to be `HEAD`, so new + syntax does not require it <remote>:: - other branch head merged into our branch. You need at + Other branch head merged into our branch. You need at least one <remote>. Specifying more than one <remote> obviously means you are trying an Octopus. diff --git a/Documentation/git-p4import.txt b/Documentation/git-p4import.txt index ee9e8fa909..6edb9f12b8 100644 --- a/Documentation/git-p4import.txt +++ b/Documentation/git-p4import.txt @@ -93,7 +93,7 @@ perforce branch into a branch named "jammy", like so: ------------ $ mkdir -p /home/sean/import/jam $ cd /home/sean/import/jam -$ git init-db +$ git init $ git p4import //public/jam jammy ------------ diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 4991f88c92..fdc6f97289 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -9,9 +9,9 @@ git-pack-objects - Create a packed archive of objects SYNOPSIS -------- [verse] -'git-pack-objects' [-q] [--no-reuse-delta] [--non-empty] - [--local] [--incremental] [--window=N] [--depth=N] - {--stdout | base-name} < object-list +'git-pack-objects' [-q] [--no-reuse-delta] [--delta-base-offset] [--non-empty] + [--local] [--incremental] [--window=N] [--depth=N] [--all-progress] + [--revs [--unpacked | --all]*] [--stdout | base-name] < object-list DESCRIPTION @@ -47,17 +47,34 @@ base-name:: <base-name> to determine the name of the created file. When this option is used, the two files are written in <base-name>-<SHA1>.{pack,idx} files. <SHA1> is a hash - of object names (currently in random order so it does - not have any useful meaning) to make the resulting - filename reasonably unique, and written to the standard + of the sorted object names to make the resulting filename + based on the pack content, and written to the standard output of the command. --stdout:: Write the pack contents (what would have been written to .pack file) out to the standard output. ---window and --depth:: - These two options affects how the objects contained in +--revs:: + Read the revision arguments from the standard input, instead of + individual object names. The revision arguments are processed + the same way as gitlink:git-rev-list[1] with `--objects` flag + uses its `commit` arguments to build the list of objects it + outputs. The objects on the resulting list are packed. + +--unpacked:: + This implies `--revs`. When processing the list of + revision arguments read from the standard input, limit + the objects packed to those that are not already packed. + +--all:: + This implies `--revs`. In addition to the list of + revision arguments read from the standard input, pretend + as if all refs under `$GIT_DIR/refs` are specified to be + included. + +--window=[N], --depth=[N]:: + These two options affect how the objects contained in the pack are stored using delta compression. The objects are first internally sorted by type, size and optionally names and compared against the other objects @@ -66,6 +83,7 @@ base-name:: it too deep affects the performance on the unpacker side, because delta data needs to be applied that many times to get to the necessary object. + The default value for both --window and --depth is 10. --incremental:: This flag causes an object already in a pack ignored @@ -81,6 +99,23 @@ base-name:: Only create a packed archive if it would contain at least one object. +--progress:: + Progress status is reported on the standard error stream + by default when it is attached to a terminal, unless -q + is specified. This flag forces progress status even if + the standard error stream is not directed to a terminal. + +--all-progress:: + When --stdout is specified then progress report is + displayed during the object count and deltification phases + but inhibited during the write-out phase. The reason is + that in some cases the output stream is directly linked + to another command which may wish to display progress + status of its own as it processes incoming pack data. + This flag is like --progress except that it forces progress + report for the write-out phase as well even if --stdout is + used. + -q:: This flag makes the command not to report its progress on the standard error stream. @@ -92,6 +127,17 @@ base-name:: This flag tells the command not to reuse existing deltas but compute them from scratch. +--delta-base-offset:: + A packed archive can express base object of a delta as + either 20-byte object name or as an offset in the + stream, but older version of git does not understand the + latter. By default, git-pack-objects only uses the + former format for better compatibility. This option + allows the command to use the latter format for + compactness. Depending on the average delta chain + length, this option typically shrinks the resulting + packfile by 3-5 per-cent. + Author ------ @@ -103,6 +149,7 @@ Documentation by Junio C Hamano See Also -------- +gitlink:git-rev-list[1] gitlink:git-repack[1] gitlink:git-prune-packed[1] diff --git a/Documentation/git-pack-refs.txt b/Documentation/git-pack-refs.txt new file mode 100644 index 0000000000..464269fbb9 --- /dev/null +++ b/Documentation/git-pack-refs.txt @@ -0,0 +1,55 @@ +git-pack-refs(1) +================ + +NAME +---- +git-pack-refs - Pack heads and tags for efficient repository access + +SYNOPSIS +-------- +'git-pack-refs' [--all] [--no-prune] + +DESCRIPTION +----------- + +Traditionally, tips of branches and tags (collectively known as +'refs') were stored one file per ref under `$GIT_DIR/refs` +directory. While many branch tips tend to be updated often, +most tags and some branch tips are never updated. When a +repository has hundreds or thousands of tags, this +one-file-per-ref format both wastes storage and hurts +performance. + +This command is used to solve the storage and performance +problem by stashing the refs in a single file, +`$GIT_DIR/packed-refs`. When a ref is missing from the +traditional `$GIT_DIR/refs` hierarchy, it is looked up in this +file and used if found. + +Subsequent updates to branches always creates new file under +`$GIT_DIR/refs` hierarchy. + +OPTIONS +------- + +\--all:: + +The command by default packs all tags and leaves branch tips +alone. This is because branches are expected to be actively +developed and packing their tips does not help performance. +This option causes branch tips to be packed as well. Useful for +a repository with many branches of historical interests. + +\--no-prune:: + +The command usually removes loose refs under `$GIT_DIR/refs` +hierarchy after packing them. This option tells it not to. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-prune-packed.txt b/Documentation/git-prune-packed.txt index 234882685d..a79193fb00 100644 --- a/Documentation/git-prune-packed.txt +++ b/Documentation/git-prune-packed.txt @@ -9,7 +9,7 @@ residing in a pack file. SYNOPSIS -------- -'git-prune-packed' [-n] +'git-prune-packed' [-n] [-q] DESCRIPTION @@ -32,6 +32,9 @@ OPTIONS Don't actually remove any objects, only show those that would have been removed. +-q:: + Squelch the progress indicator. + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-pull.txt b/Documentation/git-pull.txt index 51577fcbe6..13be992006 100644 --- a/Documentation/git-pull.txt +++ b/Documentation/git-pull.txt @@ -3,7 +3,7 @@ git-pull(1) NAME ---- -git-pull - Pull and merge from another repository +git-pull - Pull and merge from another repository or a local branch SYNOPSIS @@ -37,17 +37,27 @@ EXAMPLES -------- git pull, git pull origin:: - Fetch the default head from the repository you cloned - from and merge it into your current branch. - -git pull -s ours . obsolete:: - Merge local branch `obsolete` into the current branch, - using `ours` merge strategy. + Update the remote-tracking branches for the repository + you cloned from, then merge one of them into your + current branch. Normally the branch merged in is + the HEAD of the remote repository, but the choice is + determined by the branch.<name>.remote and + branch.<name>.merge options; see gitlink:git-repo-config[1] + for details. + +git pull origin next:: + Merge into the current branch the remote branch `next`; + leaves a copy of `next` temporarily in FETCH_HEAD, but + does not update any remote-tracking branches. git pull . fixes enhancements:: Bundle local branch `fixes` and `enhancements` on top of the current branch, making an Octopus merge. +git pull -s ours . obsolete:: + Merge local branch `obsolete` into the current branch, + using `ours` merge strategy. + git pull --no-commit . maint:: Merge local branch `maint` into the current branch, but do not make a commit automatically. This can be used @@ -61,48 +71,19 @@ release/version name would be acceptable. Command line pull of multiple branches from one repository:: + ------------------------------------------------ -$ cat .git/remotes/origin -URL: git://git.kernel.org/pub/scm/git/git.git -Pull: master:origin - $ git checkout master -$ git fetch origin master:origin +pu:pu maint:maint -$ git pull . origin +$ git fetch origin +pu:pu maint:tmp +$ git pull . tmp ------------------------------------------------ + -Here, a typical `.git/remotes/origin` file from a -`git-clone` operation is used in combination with -command line options to `git-fetch` to first update -multiple branches of the local repository and then -to merge the remote `origin` branch into the local -`master` branch. The local `pu` branch is updated -even if it does not result in a fast forward update. -Here, the pull can obtain its objects from the local -repository using `.`, as the previous `git-fetch` is -known to have already obtained and made available -all the necessary objects. - - -Pull of multiple branches from one repository using `.git/remotes` file:: +This updates (or creates, as necessary) branches `pu` and `tmp` +in the local repository by fetching from the branches +(respectively) `pu` and `maint` from the remote repository. + ------------------------------------------------- -$ cat .git/remotes/origin -URL: git://git.kernel.org/pub/scm/git/git.git -Pull: master:origin -Pull: +pu:pu -Pull: maint:maint - -$ git checkout master -$ git pull origin ------------------------------------------------- +The `pu` branch will be updated even if it is does not +fast-forward; the others will not be. + -Here, a typical `.git/remotes/origin` file from a -`git-clone` operation has been hand-modified to include -the branch-mapping of additional remote and local -heads directly. A single `git-pull` operation while -in the `master` branch will fetch multiple heads and -merge the remote `origin` head into the current, -local `master` branch. +The final command then merges the newly fetched `tmp` into master. If you tried a pull which resulted in a complex conflicts and @@ -112,7 +93,7 @@ gitlink:git-reset[1]. SEE ALSO -------- -gitlink:git-fetch[1], gitlink:git-merge[1] +gitlink:git-fetch[1], gitlink:git-merge[1], gitlink:git-repo-config[1] Author diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index d4ae99fa53..197f4b512f 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -49,12 +49,14 @@ corresponding remotes file---see below), then all the refs that exist both on the local side and on the remote side are updated. + -Some short-cut notations are also supported. +`tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`. + -* `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`. -* A parameter <ref> without a colon is equivalent to - <ref>`:`<ref>, hence updates <ref> in the destination from <ref> - in the source. +A parameter <ref> without a colon is equivalent to +<ref>`:`<ref>, hence updates <ref> in the destination from <ref> +in the source. ++ +Pushing an empty <src> allows you to delete the <dst> ref from +the remote repository. \--all:: Instead of naming each ref to push, specifies that all @@ -75,7 +77,8 @@ include::urls.txt[] Author ------ -Written by Junio C Hamano <junkio@cox.net> +Written by Junio C Hamano <junkio@cox.net>, later rewritten in C +by Linus Torvalds <torvalds@osdl.org> Documentation -------------- diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt index 11bd9c0adc..0ff2890c7f 100644 --- a/Documentation/git-read-tree.txt +++ b/Documentation/git-read-tree.txt @@ -8,7 +8,7 @@ git-read-tree - Reads tree information into the index SYNOPSIS -------- -'git-read-tree' (<tree-ish> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) +'git-read-tree' (<tree-ish> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] [--exclude-per-directory=<gitignore>] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) DESCRIPTION @@ -71,6 +71,20 @@ OPTIONS directory. Note that the `<prefix>/` value must end with a slash. +--exclude-per-directory=<gitignore>:: + When running the command with `-u` and `-m` options, the + merge result may need to overwrite paths that are not + tracked in the current branch. The command usually + refuses to proceed with the merge to avoid losing such a + path. However this safety valve sometimes gets in the + way. For example, it often happens that the other + branch added a file that used to be a generated file in + your branch, and the safety valve triggers when you try + to switch to that branch after you ran `make` but before + running `make clean` to remove the generated file. This + option tells the command to read per-directory exclude + file (usually '.gitignore') and allows such an untracked + but explicitly ignored file to be overwritten. <tree-ish#>:: The id of the tree object(s) to be read/merged. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 9d7bcaa38c..03e867a403 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -7,7 +7,7 @@ git-rebase - Rebase local commits to a new head SYNOPSIS -------- -'git-rebase' [--merge] [--onto <newbase>] <upstream> [<branch>] +'git-rebase' [-v] [--merge] [--onto <newbase>] <upstream> [<branch>] 'git-rebase' --continue | --skip | --abort @@ -51,20 +51,69 @@ would be: D---E---F---G master ------------ -While, starting from the same point, the result of either of the following -commands: +The latter form is just a short-hand of `git checkout topic` +followed by `git rebase master`. - git-rebase --onto master~1 master - git-rebase --onto master~1 master topic +Here is how you would transplant a topic branch based on one +branch to another, to pretend that you forked the topic branch +from the latter branch, using `rebase --onto`. -would be: +First let's assume your 'topic' is based on branch 'next'. +For example feature developed in 'topic' depends on some +functionality which is found in 'next'. ------------ - A'--B'--C' topic - / - D---E---F---G master + o---o---o---o---o master + \ + o---o---o---o---o next + \ + o---o---o topic +------------ + +We would want to make 'topic' forked from branch 'master', +for example because the functionality 'topic' branch depend on +got merged into more stable 'master' branch, like this: + +------------ + o---o---o---o---o master + | \ + | o'--o'--o' topic + \ + o---o---o---o---o next +------------ + +We can get this using the following command: + + git-rebase --onto master next topic + + +Another example of --onto option is to rebase part of a +branch. If we have the following situation: + +------------ + H---I---J topicB + / + E---F---G topicA + / + A---B---C---D master ------------ +then the command + + git-rebase --onto master topicA topicB + +would result in: + +------------ + H'--I'--J' topicB + / + | E---F---G topicA + |/ + A---B---C---D master +------------ + +This is useful when topicB does not depend on topicA. + In case of conflict, git-rebase will stop at the first problematic commit and leave conflict markers in the tree. You can use git diff to locate the markers (<<<<<<) and make edits to resolve the conflict. For each @@ -121,6 +170,9 @@ OPTIONS is used instead (`git-merge-recursive` when merging a single head, `git-merge-octopus` otherwise). This implies --merge. +-v, \--verbose:: + Display a diffstat of what changed upstream since the last rebase. + include::merge-strategies.txt[] NOTES diff --git a/Documentation/git-receive-pack.txt b/Documentation/git-receive-pack.txt index f9457d45ed..0dfadc2a32 100644 --- a/Documentation/git-receive-pack.txt +++ b/Documentation/git-receive-pack.txt @@ -73,6 +73,8 @@ packed and is served via a dumb transport. There are other real-world examples of using update and post-update hooks found in the Documentation/howto directory. +git-receive-pack honours the receive.denyNonFastforwards flag, which +tells it if updates to a ref should be denied if they are not fast-forwards. OPTIONS ------- diff --git a/Documentation/git-reflog.txt b/Documentation/git-reflog.txt new file mode 100644 index 0000000000..55a24d3266 --- /dev/null +++ b/Documentation/git-reflog.txt @@ -0,0 +1,59 @@ +git-reflog(1) +============= + +NAME +---- +git-reflog - Manage reflog information + + +SYNOPSIS +-------- +[verse] +'git-reflog' expire [--dry-run] + [--expire=<time>] [--expire-unreachable=<time>] [--all] <refs>... + + +DESCRIPTION +----------- + +Reflog is a mechanism to record when the tip of branches are +updated. This command is to manage the information recorded in it. + +The subcommand "expire" is used to prune older reflog entries. +Entries older than `expire` time, or entries older than +`expire-unreachable` time and are not reachable from the current +tip, are removed from the reflog. This is typically not used +directly by the end users -- instead, see gitlink:git-gc[1]. + + + +OPTIONS +------- + +--expire=<time>:: + Entries older than this time are pruned. Without the + option it is taken from configuration `gc.reflogExpire`, + which in turn defaults to 90 days. + +--expire-unreachable=<time>:: + Entries older than this time and are not reachable from + the current tip of the branch are pruned. Without the + option it is taken from configuration + `gc.reflogExpireUnreachable`, which in turn defaults to + 30 days. + +--all:: + Instead of listing <refs> explicitly, prune all refs. + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-remote.txt b/Documentation/git-remote.txt new file mode 100644 index 0000000000..5b93a8c8be --- /dev/null +++ b/Documentation/git-remote.txt @@ -0,0 +1,76 @@ +git-remote(1) +============ + +NAME +---- +git-remote - manage set of tracked repositories + + +SYNOPSIS +-------- +[verse] +'git-remote' +'git-remote' add <name> <url> +'git-remote' show <name> + +DESCRIPTION +----------- + +Manage the set of repositories ("remotes") whose branches you track. + +With no arguments, shows a list of existing remotes. + +In the second form, adds a remote named <name> for the repository at +<url>. The command `git fetch <name>` can then be used to create and +update remote-tracking branches <name>/<branch>. + +In the third form, gives some information about the remote <name>. + +The remote configuration is achieved using the `remote.origin.url` and +`remote.origin.fetch` configuration variables. (See +gitlink:git-repo-config[1]). + +Examples +-------- + +Add a new remote, fetch, and check out a branch from it: + +------------ +$ git remote +origin +$ git branch -r +origin/master +$ git remote add linux-nfs git://linux-nfs.org/pub/nfs-2.6.git +$ git remote +linux-nfs +origin +$ git fetch +* refs/remotes/linux-nfs/master: storing branch 'master' ... + commit: bf81b46 +$ git branch -r +origin/master +linux-nfs/master +$ git checkout -b nfs linux-nfs/master +... +------------ + +See Also +-------- +gitlink:git-fetch[1] +gitlink:git-branch[1] +gitlink:git-repo-config[1] + +Author +------ +Written by Junio Hamano + + +Documentation +-------------- +Documentation by J. Bruce Fields and the git-list <git@vger.kernel.org>. + + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 951622774a..0fa47e3b01 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -9,7 +9,7 @@ objects into pack files. SYNOPSIS -------- -'git-repack' [-a] [-d] [-f] [-l] [-n] [-q] +'git-repack' [-a] [-d] [-f] [-l] [-n] [-q] [--window=N] [--depth=N] DESCRIPTION ----------- @@ -56,6 +56,31 @@ OPTIONS Do not update the server information with `git update-server-info`. +--window=[N], --depth=[N]:: + These two options affect how the objects contained in the pack are + stored using delta compression. The objects are first internally + sorted by type, size and optionally names and compared against the + other objects within `--window` to see if using delta compression saves + space. `--depth` limits the maximum delta depth; making it too deep + affects the performance on the unpacker side, because delta data needs + to be applied that many times to get to the necessary object. + The default value for both --window and --depth is 10. + + +Configuration +------------- + +When configuration variable `repack.UseDeltaBaseOffset` is set +for the repository, the command passes `--delta-base-offset` +option to `git-pack-objects`; this typically results in slightly +smaller packs, but the generated packs are incompatible with +versions of git older than (and including) v1.4.3; do not set +the variable in a repository that older version of git needs to +be able to read (this includes repositories from which packs can +be copied out over http or rsync, and people who obtained packs +that way can try to use older git with it). + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-repo-config.txt b/Documentation/git-repo-config.txt index b03d66f61c..c55a8ba0dc 100644 --- a/Documentation/git-repo-config.txt +++ b/Documentation/git-repo-config.txt @@ -3,19 +3,20 @@ git-repo-config(1) NAME ---- -git-repo-config - Get and set options in .git/config +git-repo-config - Get and set repository or global options. SYNOPSIS -------- [verse] -'git-repo-config' [type] name [value [value_regex]] -'git-repo-config' [type] --replace-all name [value [value_regex]] -'git-repo-config' [type] --get name [value_regex] -'git-repo-config' [type] --get-all name [value_regex] -'git-repo-config' [type] --unset name [value_regex] -'git-repo-config' [type] --unset-all name [value_regex] -'git-repo-config' -l | --list +'git-repo-config' [--global] [type] name [value [value_regex]] +'git-repo-config' [--global] [type] --add name value +'git-repo-config' [--global] [type] --replace-all name [value [value_regex]] +'git-repo-config' [--global] [type] --get name [value_regex] +'git-repo-config' [--global] [type] --get-all name [value_regex] +'git-repo-config' [--global] [type] --unset name [value_regex] +'git-repo-config' [--global] [type] --unset-all name [value_regex] +'git-repo-config' [--global] -l | --list DESCRIPTION ----------- @@ -23,7 +24,8 @@ You can query/set/replace/unset options with this command. The name is actually the section and the key separated by a dot, and the value will be escaped. -If you want to set/unset an option which can occur on multiple +Multiple lines can be added to an option by using the '--add' option. +If you want to update or unset an option which can occur on multiple lines, a POSIX regexp `value_regex` needs to be given. Only the existing values that match the regexp are updated or unset. If you want to handle the lines that do *not* match the regex, just @@ -41,8 +43,9 @@ This command will fail if: . Can not write to .git/config, . no section was provided, . the section or key is invalid, -. you try to unset an option which does not exist, or -. you try to unset/set an option for which multiple lines match. +. you try to unset an option which does not exist, +. you try to unset/set an option for which multiple lines match, or +. you use --global option without $HOME being properly set. OPTIONS @@ -52,9 +55,14 @@ OPTIONS Default behavior is to replace at most one line. This replaces all lines matching the key (and optionally the value_regex). +--add:: + Adds a new line to the option without altering any existing + values. This is the same as providing '^$' as the value_regex. + --get:: Get the value for a given key (optionally filtered by a regex - matching the value). + matching the value). Returns error code 1 if the key was not + found and error code 2 if multiple key values were found. --get-all:: Like get, but does not fail if the number of values for the key @@ -63,14 +71,26 @@ OPTIONS --get-regexp:: Like --get-all, but interprets the name as a regular expression. +--global:: + Use global ~/.gitconfig file rather than the repository .git/config. + --unset:: - Remove the line matching the key from .git/config. + Remove the line matching the key from config file. --unset-all:: - Remove all matching lines from .git/config. + Remove all matching lines from config file. -l, --list:: - List all variables set in .git/config. + List all variables set in config file. + +--bool:: + git-repo-config will ensure that the output is "true" or "false" + +--int:: + git-repo-config will ensure that the output is a simple + decimal number. An optional value suffix of 'k', 'm', or 'g' + in the config file will cause the value to be multiplied + by 1024, 1048576, or 1073741824 prior to output. ENVIRONMENT @@ -78,6 +98,7 @@ ENVIRONMENT GIT_CONFIG:: Take the configuration from the given file instead of .git/config. + Using the "--global" option forces this to ~/.gitconfig. GIT_CONFIG_LOCAL:: Currently the same as $GIT_CONFIG; when Git will support global @@ -182,6 +203,12 @@ To actually match only values with an exclamation mark, you have to % git repo-config section.key value '[!]' ------------ +To add a new proxy, without altering any of the existing ones, use + +------------ +% git repo-config core.gitproxy '"proxy" for example.com' +------------ + include::config.txt[] diff --git a/Documentation/git-rerere.txt b/Documentation/git-rerere.txt index 8b6b651237..b57a72bdd7 100644 --- a/Documentation/git-rerere.txt +++ b/Documentation/git-rerere.txt @@ -7,8 +7,7 @@ git-rerere - Reuse recorded resolve SYNOPSIS -------- -'git-rerere' - +'git-rerere' [clear|diff|status|gc] DESCRIPTION ----------- @@ -27,6 +26,42 @@ results and applying the previously recorded hand resolution. You need to create `$GIT_DIR/rr-cache` directory to enable this command. + +COMMANDS +-------- + +Normally, git-rerere is run without arguments or user-intervention. +However, it has several commands that allow it to interact with +its working state. + +'clear':: + +This resets the metadata used by rerere if a merge resolution is to be +is aborted. Calling gitlink:git-am[1] --skip or gitlink:git-rebase[1] +[--skip|--abort] will automatcally invoke this command. + +'diff':: + +This displays diffs for the current state of the resolution. It is +useful for tracking what has changed while the user is resolving +conflicts. Additional arguments are passed directly to the system +diff(1) command installed in PATH. + +'status':: + +Like diff, but this only prints the filenames that will be tracked +for resolutions. + +'gc':: + +This command is used to prune records of conflicted merge that +occurred long time ago. By default, conflicts older than 15 +days that you have not recorded their resolution, and conflicts +older than 60 days, are pruned. These are controlled with +`gc.rerereunresolved` and `gc.rerereresolved` configuration +variables. + + DISCUSSION ---------- diff --git a/Documentation/git-reset.txt b/Documentation/git-reset.txt index 73a0ffc410..4f424782eb 100644 --- a/Documentation/git-reset.txt +++ b/Documentation/git-reset.txt @@ -7,7 +7,9 @@ git-reset - Reset current HEAD to the specified state SYNOPSIS -------- -'git-reset' [--mixed | --soft | --hard] [<commit-ish>] +[verse] +'git-reset' [--mixed | --soft | --hard] [<commit>] +'git-reset' [--mixed] <commit> [--] <paths>... DESCRIPTION ----------- @@ -21,6 +23,10 @@ the undo in the history. If you want to undo a commit other than the latest on a branch, gitlink:git-revert[1] is your friend. +The second form with 'paths' is used to revert selected paths in +the index from a given commit, without moving HEAD. + + OPTIONS ------- --mixed:: @@ -31,15 +37,15 @@ OPTIONS --soft:: Does not touch the index file nor the working tree at all, but requires them to be in a good order. This leaves all your changed - files "Updated but not checked in", as gitlink:git-status[1] would + files "Added but not yet committed", as gitlink:git-status[1] would put it. --hard:: Matches the working tree and index to that of the tree being switched to. Any changes to tracked files in the working tree - since <commit-ish> are lost. + since <commit> are lost. -<commit-ish>:: +<commit>:: Commit to make the current HEAD. Examples diff --git a/Documentation/git-rev-list.txt b/Documentation/git-rev-list.txt index dd9fff16d3..86c94e7dfd 100644 --- a/Documentation/git-rev-list.txt +++ b/Documentation/git-rev-list.txt @@ -10,6 +10,7 @@ SYNOPSIS -------- [verse] 'git-rev-list' [ \--max-count=number ] + [ \--skip=number ] [ \--max-age=timestamp ] [ \--min-age=timestamp ] [ \--sparse ] @@ -17,8 +18,11 @@ SYNOPSIS [ \--remove-empty ] [ \--not ] [ \--all ] + [ \--stdin ] [ \--topo-order ] [ \--parents ] + [ \--encoding[=<encoding>] ] + [ \--(author|committer|grep)=<pattern> ] [ [\--objects | \--objects-edge] [ \--unpacked ] ] [ \--pretty | \--header ] [ \--bisect ] @@ -27,116 +31,258 @@ SYNOPSIS DESCRIPTION ----------- + Lists commit objects in reverse chronological order starting at the given commit(s), taking ancestry relationship into account. This is useful to produce human-readable log output. -Commits which are stated with a preceding '{caret}' cause listing to stop at -that point. Their parents are implied. "git-rev-list foo bar {caret}baz" thus +Commits which are stated with a preceding '{caret}' cause listing to +stop at that point. Their parents are implied. Thus the following +command: + +----------------------------------------------------------------------- + $ git-rev-list foo bar ^baz +----------------------------------------------------------------------- + means "list all the commits which are included in 'foo' and 'bar', but not in 'baz'". -A special notation <commit1>..<commit2> can be used as a -short-hand for {caret}<commit1> <commit2>. +A special notation "'<commit1>'..'<commit2>'" can be used as a +short-hand for "{caret}'<commit1>' '<commit2>'". For example, either of +the following may be used interchangeably: -Another special notation is <commit1>...<commit2> which is useful for -merges. The resulting set of commits is the symmetric difference +----------------------------------------------------------------------- + $ git-rev-list origin..HEAD + $ git-rev-list HEAD ^origin +----------------------------------------------------------------------- + +Another special notation is "'<commit1>'...'<commit2>'" which is useful +for merges. The resulting set of commits is the symmetric difference between the two operands. The following two commands are equivalent: ------------- -$ git-rev-list A B --not $(git-merge-base --all A B) -$ git-rev-list A...B ------------- +----------------------------------------------------------------------- + $ git-rev-list A B --not $(git-merge-base --all A B) + $ git-rev-list A...B +----------------------------------------------------------------------- + +gitlink:git-rev-list[1] is a very essential git program, since it +provides the ability to build and traverse commit ancestry graphs. For +this reason, it has a lot of different options that enables it to be +used by commands as different as gitlink:git-bisect[1] and +gitlink:git-repack[1]. OPTIONS ------- ---pretty:: - Print the contents of the commit changesets in human-readable form. + +Commit Formatting +~~~~~~~~~~~~~~~~~ + +Using these options, gitlink:git-rev-list[1] will act similar to the +more specialized family of commit log tools: gitlink:git-log[1], +gitlink:git-show[1], and gitlink:git-whatchanged[1] + +include::pretty-formats.txt[] + +--relative-date:: + + Show dates relative to the current time, e.g. "2 hours ago". + Only takes effect for dates shown in human-readable format, such + as when using "--pretty". --header:: - Print the contents of the commit in raw-format; each - record is separated with a NUL character. + + Print the contents of the commit in raw-format; each record is + separated with a NUL character. --parents:: + Print the parents of the commit. ---objects:: - Print the object IDs of any object referenced by the listed commits. - 'git-rev-list --objects foo ^bar' thus means "send me all object IDs - which I need to download if I have the commit object 'bar', but - not 'foo'". +Diff Formatting +~~~~~~~~~~~~~~~ ---objects-edge:: - Similar to `--objects`, but also print the IDs of - excluded commits prefixed with a `-` character. This is - used by `git-pack-objects` to build 'thin' pack, which - records objects in deltified form based on objects - contained in these excluded commits to reduce network - traffic. +Below are listed options that control the formatting of diff output. +Some of them are specific to gitlink:git-rev-list[1], however other diff +options may be given. See gitlink:git-diff-files[1] for more options. ---unpacked:: - Only useful with `--objects`; print the object IDs that - are not in packs. +-c:: + + This flag changes the way a merge commit is displayed. It shows + the differences from each of the parents to the merge result + simultaneously instead of showing pairwise diff between a parent + and the result one at a time. Furthermore, it lists only files + which were modified from all parents. + +--cc:: + + This flag implies the '-c' options and further compresses the + patch output by omitting hunks that show differences from only + one parent, or show the same change from all but one parent for + an Octopus merge. + +-r:: + + Show recursive diffs. + +-t:: + + Show the tree objects in the diff output. This implies '-r'. + +Commit Limiting +~~~~~~~~~~~~~~~ + +Besides specifying a range of commits that should be listed using the +special notations explained in the description, additional commit +limiting may be applied. + +-- + +-n 'number', --max-count='number':: ---bisect:: - Limit output to the one commit object which is roughly halfway - between the included and excluded commits. Thus, if 'git-rev-list - --bisect foo {caret}bar {caret}baz' outputs 'midpoint', the output - of 'git-rev-list foo {caret}midpoint' and 'git-rev-list midpoint - {caret}bar {caret}baz' would be of roughly the same length. - Finding the change - which introduces a regression is thus reduced to a binary search: - repeatedly generate and test new 'midpoint's until the commit chain - is of length one. - ---max-count:: Limit the number of commits output. ---max-age=timestamp, --min-age=timestamp:: +--skip='number':: + + Skip 'number' commits before starting to show the commit output. + +--since='date', --after='date':: + + Show commits more recent than a specific date. + +--until='date', --before='date':: + + Show commits older than a specific date. + +--max-age='timestamp', --min-age='timestamp':: + Limit the commits output to specified time range. ---sparse:: - When optional paths are given, the command outputs only - the commits that changes at least one of them, and also - ignores merges that do not touch the given paths. This - flag makes the command output all eligible commits - (still subject to count and age limitation), but apply - merge simplification nevertheless. +--author='pattern', --committer='pattern':: + + Limit the commits output to ones with author/committer + header lines that match the specified pattern. + +--grep='pattern':: + + Limit the commits output to ones with log message that + matches the specified pattern. --remove-empty:: + Stop when a given path disappears from the tree. --no-merges:: + Do not print commits with more than one parent. --not:: - Reverses the meaning of the '{caret}' prefix (or lack - thereof) for all following revision specifiers, up to - the next `--not`. + + Reverses the meaning of the '{caret}' prefix (or lack thereof) + for all following revision specifiers, up to the next '--not'. --all:: - Pretend as if all the refs in `$GIT_DIR/refs/` are - listed on the command line as <commit>. ---topo-order:: - By default, the commits are shown in reverse - chronological order. This option makes them appear in - topological order (i.e. descendant commits are shown - before their parents). + Pretend as if all the refs in `$GIT_DIR/refs/` are listed on the + command line as '<commit>'. + +--stdin:: + + In addition to the '<commit>' listed on the command + line, read them from the standard input. --merge:: + After a failed merge, show refs that touch files having a conflict and don't exist on all heads to merge. +--boundary:: + + Output uninteresting commits at the boundary, which are usually + not shown. + +--dense, --sparse:: + +When optional paths are given, the default behaviour ('--dense') is to +only output commits that changes at least one of them, and also ignore +merges that do not touch the given paths. + +Use the '--sparse' flag to makes the command output all eligible commits +(still subject to count and age limitation), but apply merge +simplification nevertheless. + +--bisect:: + +Limit output to the one commit object which is roughly halfway between +the included and excluded commits. Thus, if + +----------------------------------------------------------------------- + $ git-rev-list --bisect foo ^bar ^baz +----------------------------------------------------------------------- + +outputs 'midpoint', the output of the two commands + +----------------------------------------------------------------------- + $ git-rev-list foo ^midpoint + $ git-rev-list midpoint ^bar ^baz +----------------------------------------------------------------------- + +would be of roughly the same length. Finding the change which +introduces a regression is thus reduced to a binary search: repeatedly +generate and test new 'midpoint's until the commit chain is of length +one. + +-- + +Commit Ordering +~~~~~~~~~~~~~~~ + +By default, the commits are shown in reverse chronological order. + +--topo-order:: + + This option makes them appear in topological order (i.e. + descendant commits are shown before their parents). + +--date-order:: + + This option is similar to '--topo-order' in the sense that no + parent comes before all of its children, but otherwise things + are still ordered in the commit timestamp order. + +Object Traversal +~~~~~~~~~~~~~~~~ + +These options are mostly targeted for packing of git repositories. + +--objects:: + + Print the object IDs of any object referenced by the listed + commits. 'git-rev-list --objects foo ^bar' thus means "send me + all object IDs which I need to download if I have the commit + object 'bar', but not 'foo'". + +--objects-edge:: + + Similar to '--objects', but also print the IDs of excluded + commits prefixed with a "-" character. This is used by + gitlink:git-pack-objects[1] to build "thin" pack, which records + objects in deltified form based on objects contained in these + excluded commits to reduce network traffic. + +--unpacked:: + + Only useful with '--objects'; print the object IDs that are not + in packs. + Author ------ Written by Linus Torvalds <torvalds@osdl.org> Documentation -------------- -Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. +Documentation by David Greaves, Junio C Hamano, Jonas Fonseca +and the git-list <git@vger.kernel.org>. GIT --- Part of the gitlink:git[7] suite - diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index b761b4b965..4eaf5a0d1e 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -111,7 +111,9 @@ SPECIFYING REVISIONS A revision parameter typically, but not necessarily, names a commit object. They use what is called an 'extended SHA1' -syntax. +syntax. Here are various ways to spell object names. The +ones listed near the end of this list are to name trees and +blobs contained in a commit. * The full SHA1 object name (40-byte hexadecimal string), or a substring of such that is unique within the repository. @@ -119,12 +121,31 @@ syntax. name the same commit object if there are no other object in your repository whose object name starts with dae86e. +* An output from `git-describe`; i.e. a closest tag, followed by a + dash, a `g`, and an abbreviated object name. + * A symbolic ref name. E.g. 'master' typically means the commit object referenced by $GIT_DIR/refs/heads/master. If you happen to have both heads/master and tags/master, you can explicitly say 'heads/master' to tell git which one you mean. + When ambiguous, a `<name>` is disambiguated by taking the + first match in the following rules: + + . if `$GIT_DIR/<name>` exists, that is what you mean (this is usually + useful only for `HEAD`, `FETCH_HEAD` and `MERGE_HEAD`); + + . otherwise, `$GIT_DIR/refs/<name>` if exists; + + . otherwise, `$GIT_DIR/refs/tags/<name>` if exists; + + . otherwise, `$GIT_DIR/refs/heads/<name>` if exists; -* A suffix '@' followed by a date specification enclosed in a brace + . otherwise, `$GIT_DIR/refs/remotes/<name>` if exists; + + . otherwise, `$GIT_DIR/refs/remotes/<name>/HEAD` if exists. + +* A ref followed by the suffix '@' with a date specification + enclosed in a brace pair (e.g. '\{yesterday\}', '\{1 month 2 weeks 3 days 1 hour 1 second ago\}' or '\{1979-02-26 18:30:00\}') to specify the value of the ref at a prior point in time. This suffix may only be @@ -138,11 +159,12 @@ syntax. 'rev{caret}0' means the commit itself and is used when 'rev' is the object name of a tag object that refers to a commit object. -* A suffix '~<n>' to a revision parameter means the commit +* A suffix '{tilde}<n>' to a revision parameter means the commit object that is the <n>th generation grand-parent of the named commit object, following only the first parent. I.e. rev~3 is - equivalent to rev{caret}{caret}{caret} which is equivalent to\ - rev{caret}1{caret}1{caret}1. + equivalent to rev{caret}{caret}{caret} which is equivalent to + rev{caret}1{caret}1{caret}1. See below for a illustration of + the usage of this form. * A suffix '{caret}' followed by an object type name enclosed in brace pair (e.g. `v0.99.8{caret}\{commit\}`) means the object @@ -156,6 +178,15 @@ syntax. and dereference the tag recursively until a non-tag object is found. +* A suffix ':' followed by a path; this names the blob or tree + at the given path in the tree-ish object named by the part + before the colon. + +* A colon, optionally followed by a stage number (0 to 3) and a + colon, followed by a path; this names a blob object in the + index at the given path. Missing stage number (and the colon + that follows it) names an stage 0 entry. + Here is an illustration, by Jon Loeliger. Both node B and C are a commit parents of commit node A. Parent commits are ordered left-to-right. @@ -208,14 +239,21 @@ of `r1` and `r2` and is defined as It it the set of commits that are reachable from either one of `r1` or `r2` but not from both. -Here are a few examples: +Two other shorthands for naming a set that is formed by a commit +and its parent commits exists. `r1{caret}@` notation means all +parents of `r1`. `r1{caret}!` includes commit `r1` but excludes +its all parents. + +Here are a handful examples: D A B D D F A B C D F - ^A G B D + ^A G B D ^A F B C F G...I C D F G I - ^B G I C D F G I + ^B G I C D F G I + F^@ A B C + F^! H D F H Author ------ diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt index 66fc478f57..3a8f279e1a 100644 --- a/Documentation/git-rm.txt +++ b/Documentation/git-rm.txt @@ -7,51 +7,54 @@ git-rm - Remove files from the working tree and from the index SYNOPSIS -------- -'git-rm' [-f] [-n] [-v] [--] <file>... +'git-rm' [-f] [-n] [-r] [--cached] [--] <file>... DESCRIPTION ----------- -A convenience wrapper for git-update-index --remove. For those coming -from cvs, git-rm provides an operation similar to "cvs rm" or "cvs -remove". +Remove files from the working tree and from the index. The +files have to be identical to the tip of the branch, and no +updates to its contents must have been placed in the staging +area (aka index). OPTIONS ------- <file>...:: - Files to remove from the index and optionally, from the - working tree as well. + Files to remove. Fileglobs (e.g. `*.c`) can be given to + remove all matching files. Also a leading directory name + (e.g. `dir` to add `dir/file1` and `dir/file2`) can be + given to remove all files in the directory, recursively, + but this requires `-r` option to be given for safety. -f:: - Remove files from the working tree as well as from the index. + Override the up-to-date check. -n:: Don't actually remove the file(s), just show if they exist in the index. --v:: - Be verbose. +-r:: + Allow recursive removal when a leading directory name is + given. \--:: This option can be used to separate command-line options from the list of files, (useful when filenames might be mistaken for command-line options). +\--cached:: + This option can be used to tell the command to remove + the paths only from the index, leaving working tree + files. + DISCUSSION ---------- -The list of <file> given to the command is fed to `git-ls-files` -command to list files that are registered in the index and -are not ignored/excluded by `$GIT_DIR/info/exclude` file or -`.gitignore` file in each directory. This means two things: - -. You can put the name of a directory on the command line, and the - command will remove all files in it and its subdirectories (the - directories themselves are never removed from the working tree); - -. Giving the name of a file that is not in the index does not - remove that file. +The list of <file> given to the command can be exact pathnames, +file glob patterns, or leading directory name. The command +removes only the paths that is known to git. Giving the name of +a file that you have not told git about does not remove that file. EXAMPLES @@ -69,10 +72,10 @@ subdirectories of `Documentation/` directory. git-rm -f git-*.sh:: Remove all git-*.sh scripts that are in the index. The files - are removed from the index, and (because of the -f option), - from the working tree as well. Because this example lets the - shell expand the asterisk (i.e. you are listing the files - explicitly), it does not remove `subdir/git-foo.sh`. + are removed from the index, and from the working + tree. Because this example lets the shell expand the + asterisk (i.e. you are listing the files explicitly), it + does not remove `subdir/git-foo.sh`. See Also -------- diff --git a/Documentation/git-runstatus.txt b/Documentation/git-runstatus.txt new file mode 100644 index 0000000000..89d7b92731 --- /dev/null +++ b/Documentation/git-runstatus.txt @@ -0,0 +1,69 @@ +git-runstatus(1) +================ + +NAME +---- +git-runstatus - A helper for git-status and git-commit + + +SYNOPSIS +-------- +'git-runstatus' [--color|--nocolor] [--amend] [--verbose] [--untracked] + + +DESCRIPTION +----------- +Examines paths in the working tree that has changes unrecorded +to the index file, and changes between the index file and the +current HEAD commit. The former paths are what you _could_ +commit by running 'git-update-index' before running 'git +commit', and the latter paths are what you _would_ commit by +running 'git commit'. + +If there is no path that is different between the index file and +the current HEAD commit, the command exits with non-zero status. + +Note that this is _not_ the user level command you would want to +run from the command line. Use 'git-status' instead. + + +OPTIONS +------- +--color:: + Show colored status, highlighting modified file names. + +--nocolor:: + Turn off coloring. + +--amend:: + Show status based on HEAD^1, not HEAD, i.e. show what + 'git-commit --amend' would do. + +--verbose:: + Show unified diff of all file changes. + +--untracked:: + Show files in untracked directories, too. Without this + option only its name and a trailing slash are displayed + for each untracked directory. + + +OUTPUT +------ +The output from this command is designed to be used as a commit +template comments, and all the output lines are prefixed with '#'. + + +Author +------ +Originally written by Linus Torvalds <torvalds@osdl.org> as part +of git-commit, and later rewritten in C by Jeff King. + +Documentation +-------------- +Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-send-email.txt b/Documentation/git-send-email.txt index 481b3f50e3..4c8d907bd5 100644 --- a/Documentation/git-send-email.txt +++ b/Documentation/git-send-email.txt @@ -66,8 +66,13 @@ The options available are: all that is output. --smtp-server:: - If set, specifies the outgoing SMTP server to use. Defaults to - localhost. + If set, specifies the outgoing SMTP server to use. A full + pathname of a sendmail-like program can be specified instead; + the program must support the `-i` option. Default value can + be specified by the 'sendemail.smtpserver' configuration + option; the built-in default is `/usr/sbin/sendmail` or + `/usr/lib/sendmail` if such program is available, or + `localhost` otherwise. --subject:: Specify the initial subject of the email thread. diff --git a/Documentation/git-send-pack.txt b/Documentation/git-send-pack.txt index 9e67f17302..5376f68548 100644 --- a/Documentation/git-send-pack.txt +++ b/Documentation/git-send-pack.txt @@ -43,7 +43,7 @@ OPTIONS <directory>:: The repository to update. -<ref>...: +<ref>...:: The remote refs to update. diff --git a/Documentation/git-shortlog.txt b/Documentation/git-shortlog.txt index 7486ebe785..95fa9010c1 100644 --- a/Documentation/git-shortlog.txt +++ b/Documentation/git-shortlog.txt @@ -7,16 +7,30 @@ git-shortlog - Summarize 'git log' output SYNOPSIS -------- -git-log --pretty=short | 'git-shortlog' +git-log --pretty=short | 'git-shortlog' [-h] [-n] [-s] +git-shortlog [-n|--number] [-s|--summary] [<committish>...] DESCRIPTION ----------- Summarizes 'git log' output in a format suitable for inclusion -in release announcements. Each commit will be grouped by author +in release announcements. Each commit will be grouped by author and the first line of the commit message will be shown. Additionally, "[PATCH]" will be stripped from the commit description. +OPTIONS +------- + +-h:: + Print a short usage message and exit. + +-n:: + Sort output according to the number of commits per author instead + of author alphabetic order. + +-s:: + Supress commit description and provide a commit count summary only. + FILES ----- '.mailmap':: diff --git a/Documentation/git-show-branch.txt b/Documentation/git-show-branch.txt index a2445a48fc..912e15bcba 100644 --- a/Documentation/git-show-branch.txt +++ b/Documentation/git-show-branch.txt @@ -8,9 +8,10 @@ git-show-branch - Show branches and their commits SYNOPSIS -------- [verse] -'git-show-branch' [--all] [--heads] [--tags] [--topo-order] [--current] +'git-show-branch' [--all] [--remotes] [--topo-order] [--current] [--more=<n> | --list | --independent | --merge-base] - [--no-name | --sha1-name] [<rev> | <glob>]... + [--no-name | --sha1-name] [--topics] [<rev> | <glob>]... +'git-show-branch' --reflog[=<n>] <ref> DESCRIPTION ----------- @@ -37,9 +38,11 @@ OPTIONS branches under $GIT_DIR/refs/heads/topic, giving `topic/*` would show all of them. ---all --heads --tags:: - Show all refs under $GIT_DIR/refs, $GIT_DIR/refs/heads, - and $GIT_DIR/refs/tags, respectively. +-r|--remotes:: + Show the remote-tracking branches. + +-a|--all:: + Show both remote-tracking branches and local branches. --current:: With this option, the command includes the current @@ -86,6 +89,18 @@ OPTIONS of "master"), name them with the unique prefix of their object names. +--topics:: + Shows only commits that are NOT on the first branch given. + This helps track topic branches by hiding any commit that + is already in the main line of development. When given + "git show-branch --topics master topic1 topic2", this + will show the revisions given by "git rev-list {caret}master + topic1 topic2" + +--reflog[=<n>] <ref>:: + Shows <n> most recent ref-log entries for the given ref. + + Note that --more, --list, --independent and --merge-base options are mutually exclusive. diff --git a/Documentation/git-show-ref.txt b/Documentation/git-show-ref.txt new file mode 100644 index 0000000000..5973a82517 --- /dev/null +++ b/Documentation/git-show-ref.txt @@ -0,0 +1,156 @@ +git-show-ref(1) +=============== + +NAME +---- +git-show-ref - List references in a local repository + +SYNOPSIS +-------- +[verse] +'git-show-ref' [-q|--quiet] [--verify] [-h|--head] [-d|--dereference] + [-s|--hash] [--abbrev] [--tags] [--heads] [--] <pattern>... + +DESCRIPTION +----------- + +Displays references available in a local repository along with the associated +commit IDs. Results can be filtered using a pattern and tags can be +dereferenced into object IDs. Additionally, it can be used to test whether a +particular ref exists. + +Use of this utility is encouraged in favor of directly accessing files under +in the `.git` directory. + +OPTIONS +------- + +-h, --head:: + + Show the HEAD reference. + +--tags, --heads:: + + Limit to only "refs/heads" and "refs/tags", respectively. These + options are not mutually exclusive; when given both, references stored + in "refs/heads" and "refs/tags" are displayed. + +-d, --dereference:: + + Dereference tags into object IDs as well. They will be shown with "^{}" + appended. + +-s, --hash:: + + Only show the SHA1 hash, not the reference name. When also using + --dereference the dereferenced tag will still be shown after the SHA1. + +--verify:: + + Enable stricter reference checking by requiring an exact ref path. + Aside from returning an error code of 1, it will also print an error + message if '--quiet' was not specified. + +--abbrev, --abbrev=len:: + + Abbreviate the object name. When using `--hash`, you do + not have to say `--hash --abbrev`; `--hash=len` would do. + +-q, --quiet:: + + Do not print any results to stdout. When combined with '--verify' this + can be used to silently check if a reference exists. + +<pattern>:: + + Show references matching one or more patterns. + +OUTPUT +------ + +The output is in the format: '<SHA-1 ID>' '<space>' '<reference name>'. + +----------------------------------------------------------------------------- +$ git show-ref --head --dereference +832e76a9899f560a90ffd62ae2ce83bbeff58f54 HEAD +832e76a9899f560a90ffd62ae2ce83bbeff58f54 refs/heads/master +832e76a9899f560a90ffd62ae2ce83bbeff58f54 refs/heads/origin +3521017556c5de4159da4615a39fa4d5d2c279b5 refs/tags/v0.99.9c +6ddc0964034342519a87fe013781abf31c6db6ad refs/tags/v0.99.9c^{} +055e4ae3ae6eb344cbabf2a5256a49ea66040131 refs/tags/v1.0rc4 +423325a2d24638ddcc82ce47be5e40be550f4507 refs/tags/v1.0rc4^{} +... +----------------------------------------------------------------------------- + +When using --hash (and not --dereference) the output format is: '<SHA-1 ID>' + +----------------------------------------------------------------------------- +$ git show-ref --heads --hash +2e3ba0114a1f52b47df29743d6915d056be13278 +185008ae97960c8d551adcd9e23565194651b5d1 +03adf42c988195b50e1a1935ba5fcbc39b2b029b +... +----------------------------------------------------------------------------- + +EXAMPLE +------- + +To show all references called "master", whether tags or heads or anything +else, and regardless of how deep in the reference naming hierarchy they are, +use: + +----------------------------------------------------------------------------- + git show-ref master +----------------------------------------------------------------------------- + +This will show "refs/heads/master" but also "refs/remote/other-repo/master", +if such references exists. + +When using the '--verify' flag, the command requires an exact path: + +----------------------------------------------------------------------------- + git show-ref --verify refs/heads/master +----------------------------------------------------------------------------- + +will only match the exact branch called "master". + +If nothing matches, gitlink:git-show-ref[1] will return an error code of 1, +and in the case of verification, it will show an error message. + +For scripting, you can ask it to be quiet with the "--quiet" flag, which +allows you to do things like + +----------------------------------------------------------------------------- + git-show-ref --quiet --verify -- "refs/heads/$headname" || + echo "$headname is not a valid branch" +----------------------------------------------------------------------------- + +to check whether a particular branch exists or not (notice how we don't +actually want to show any results, and we want to use the full refname for it +in order to not trigger the problem with ambiguous partial matches). + +To show only tags, or only proper branch heads, use "--tags" and/or "--heads" +respectively (using both means that it shows tags and heads, but not other +random references under the refs/ subdirectory). + +To do automatic tag object dereferencing, use the "-d" or "--dereference" +flag, so you can do + +----------------------------------------------------------------------------- + git show-ref --tags --dereference +----------------------------------------------------------------------------- + +to get a listing of all tags together with what they dereference. + +SEE ALSO +-------- +gitlink:git-ls-remote[1], gitlink:git-peek-remote[1] + +AUTHORS +------- +Written by Linus Torvalds <torvalds@osdl.org>. +Man page by Jonas Fonseca <fonseca@diku.dk>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-show.txt b/Documentation/git-show.txt index 2b4df3f96f..c210b9af6b 100644 --- a/Documentation/git-show.txt +++ b/Documentation/git-show.txt @@ -3,38 +3,68 @@ git-show(1) NAME ---- -git-show - Show one commit with difference it introduces +git-show - Show various types of objects SYNOPSIS -------- -'git-show' <option>... +'git-show' [options] <object>... DESCRIPTION ----------- -Shows commit log and textual diff for a single commit. The -command internally invokes 'git-rev-list' piped to -'git-diff-tree', and takes command line options for both of -these commands. It also presents the merge commit in a special -format as produced by 'git-diff-tree --cc'. +Shows one or more objects (blobs, trees, tags and commits). + +For commits it shows the log message and textual diff. It also +presents the merge commit in a special format as produced by +'git-diff-tree --cc'. + +For tags, it shows the tag message and the referenced objects. + +For trees, it shows the names (equivalent to gitlink:git-ls-tree[1] +with \--name-only). + +For plain blobs, it shows the plain contents. This manual page describes only the most frequently used options. OPTIONS ------- -<commitid>:: - ID of the commit to show. +<object>:: + The name of the object to show. + +include::pretty-formats.txt[] + + +EXAMPLES +-------- + +git show v1.0.0:: + Shows the tag `v1.0.0`, along with the object the tags + points at. + +git show v1.0.0^{tree}:: + Shows the tree pointed to by the tag `v1.0.0`. + +git show next~10:Documentation/README + Shows the contents of the file `Documentation/README` as + they were current in the 10th last commit of the branch + `next`. + +git show master:Makefile master:t/Makefile + Concatenates the contents of said Makefiles in the head + of the branch `master`. + +Discussion +---------- ---pretty=<format>:: - Controls the output format for the commit logs. - <format> can be one of 'raw', 'medium', 'short', 'full', - and 'oneline'. +include::i18n.txt[] Author ------ Written by Linus Torvalds <torvalds@osdl.org> and -Junio C Hamano <junkio@cox.net> +Junio C Hamano <junkio@cox.net>. Significantly enhanced by +Johannes Schindelin <Johannes.Schindelin@gmx.de>. Documentation diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt index 7d86809844..9ed721118b 100644 --- a/Documentation/git-svn.txt +++ b/Documentation/git-svn.txt @@ -3,7 +3,7 @@ git-svn(1) NAME ---- -git-svn - bidirectional operation between a single Subversion branch and git +git-svn - bidirectional operation between Subversion and git SYNOPSIS -------- @@ -11,49 +11,84 @@ SYNOPSIS DESCRIPTION ----------- -git-svn is a simple conduit for changesets between a single Subversion -branch and git. +git-svn is a simple conduit for changesets between Subversion and git. +It is not to be confused with gitlink:git-svnimport[1], which is +read-only and geared towards tracking multiple branches. -git-svn is not to be confused with git-svnimport. The were designed -with very different goals in mind. - -git-svn is designed for an individual developer who wants a +git-svn was originally designed for an individual developer who wants a bidirectional flow of changesets between a single branch in Subversion -and an arbitrary number of branches in git. git-svnimport is designed -for read-only operation on repositories that match a particular layout -(albeit the recommended one by SVN developers). - -For importing svn, git-svnimport is potentially more powerful when -operating on repositories organized under the recommended -trunk/branch/tags structure, and should be faster, too. +and an arbitrary number of branches in git. Since its inception, +git-svn has gained the ability to track multiple branches in a manner +similar to git-svnimport; but it cannot (yet) automatically detect new +branches and tags like git-svnimport does. -git-svn mostly ignores the very limited view of branching that -Subversion has. This allows git-svn to be much easier to use, -especially on repositories that are not organized in a manner that -git-svnimport is designed for. +git-svn is especially useful when it comes to tracking repositories +not organized in the way Subversion developers recommend (trunk, +branches, tags directories). COMMANDS -------- -init:: +-- + +'init':: Creates an empty git repository with additional metadata directories for git-svn. The Subversion URL must be specified - as a command-line argument. - -fetch:: - Fetch unfetched revisions from the Subversion URL we are - tracking. refs/remotes/git-svn will be updated to the - latest revision. - - Note: You should never attempt to modify the remotes/git-svn - branch outside of git-svn. Instead, create a branch from - remotes/git-svn and work on that branch. Use the 'commit' - command (see below) to write git commits back to - remotes/git-svn. - - See 'Additional Fetch Arguments' if you are interested in - manually joining branches on commit. - -commit:: + as a command-line argument. Optionally, the target directory + to operate on can be specified as a second argument. Normally + this command initializes the current directory. + +'fetch':: + +Fetch unfetched revisions from the Subversion URL we are +tracking. refs/remotes/git-svn will be updated to the +latest revision. + +Note: You should never attempt to modify the remotes/git-svn +branch outside of git-svn. Instead, create a branch from +remotes/git-svn and work on that branch. Use the 'dcommit' +command (see below) to write git commits back to +remotes/git-svn. + +See '<<fetch-args,Additional Fetch Arguments>>' if you are interested in +manually joining branches on commit. + +'dcommit':: + Commit each diff from a specified head directly to the SVN + repository, and then rebase or reset (depending on whether or + not there is a diff between SVN and head). This will create + a revision in SVN for each commit in git. + It is recommended that you run git-svn fetch and rebase (not + pull or merge) your commits against the latest changes in the + SVN repository. + An optional command-line argument may be specified as an + alternative to HEAD. + This is advantageous over 'set-tree' (below) because it produces + cleaner, more linear history. + +'log':: + This should make it easy to look up svn log messages when svn + users refer to -r/--revision numbers. + + The following features from `svn log' are supported: + + --revision=<n>[:<n>] - is supported, non-numeric args are not: + HEAD, NEXT, BASE, PREV, etc ... + -v/--verbose - it's not completely compatible with + the --verbose output in svn log, but + reasonably close. + --limit=<n> - is NOT the same as --max-count, + doesn't count merged/excluded commits + --incremental - supported + + New features: + + --show-commit - shows the git commit sha1, as well + --oneline - our version of --pretty=oneline + + Any other arguments are passed directly to `git log' + +'set-tree':: + You should consider using 'dcommit' instead of this command. Commit specified commit or tree objects to SVN. This relies on your imported fetch data being up-to-date. This makes absolutely no attempts to do patching when committing to SVN, it @@ -61,9 +96,9 @@ commit:: commit. All merging is assumed to have taken place independently of git-svn functions. -rebuild:: +'rebuild':: Not a part of daily usage, but this is a useful command if - you've just cloned a repository (using git-clone) that was + you've just cloned a repository (using gitlink:git-clone[1]) that was tracked with git-svn. Unfortunately, git-clone does not clone git-svn metadata and the svn working tree that git-svn uses for its operations. This rebuilds the metadata so git-svn can @@ -71,176 +106,344 @@ rebuild:: specified at the command-line if the directory/repository you're tracking has moved or changed protocols. -show-ignore:: +'show-ignore':: Recursively finds and lists the svn:ignore property on directories. The output is suitable for appending to the $GIT_DIR/info/exclude file. +'commit-diff':: + Commits the diff of two tree-ish arguments from the + command-line. This command is intended for interopability with + git-svnimport and does not rely on being inside an git-svn + init-ed repository. This command takes three arguments, (a) the + original tree to diff against, (b) the new tree result, (c) the + URL of the target Subversion repository. The final argument + (URL) may be omitted if you are working from a git-svn-aware + repository (that has been init-ed with git-svn). + The -r<revision> option is required for this. + +'graft-branches':: + This command attempts to detect merges/branches from already + imported history. Techniques used currently include regexes, + file copies, and tree-matches). This command generates (or + modifies) the $GIT_DIR/info/grafts file. This command is + considered experimental, and inherently flawed because + merge-tracking in SVN is inherently flawed and inconsistent + across different repositories. + +'multi-init':: + This command supports git-svnimport-like command-line syntax for + importing repositories that are layed out as recommended by the + SVN folks. This is a bit more tolerant than the git-svnimport + command-line syntax and doesn't require the user to figure out + where the repository URL ends and where the repository path + begins. + +-T<trunk_subdir>:: +--trunk=<trunk_subdir>:: +-t<tags_subdir>:: +--tags=<tags_subdir>:: +-b<branches_subdir>:: +--branches=<branches_subdir>:: + These are the command-line options for multi-init. Each of + these flags can point to a relative repository path + (--tags=project/tags') or a full url + (--tags=https://foo.org/project/tags) + +--prefix=<prefix> + This allows one to specify a prefix which is prepended to the + names of remotes. The prefix does not automatically include a + trailing slash, so be sure you include one in the argument if + that is what you want. This is useful if you wish to track + multiple projects that share a common repository. + +'multi-fetch':: + This runs fetch on all known SVN branches we're tracking. This + will NOT discover new branches (unlike git-svnimport), so + multi-init will need to be re-run (it's idempotent). + +-- + OPTIONS ------- +-- + +--shared:: +--template=<template_directory>:: + Only used with the 'init' command. + These are passed directly to gitlink:git-init[1]. + -r <ARG>:: --revision <ARG>:: - Only used with the 'fetch' command. - Takes any valid -r<argument> svn would accept and passes it - directly to svn. -r<ARG1>:<ARG2> ranges and "{" DATE "}" syntax - is also supported. This is passed directly to svn, see svn - documentation for more details. +Only used with the 'fetch' command. + +Takes any valid -r<argument> svn would accept and passes it +directly to svn. -r<ARG1>:<ARG2> ranges and "{" DATE "}" syntax +is also supported. This is passed directly to svn, see svn +documentation for more details. - This can allow you to make partial mirrors when running fetch. +This can allow you to make partial mirrors when running fetch. -:: --stdin:: - Only used with the 'commit' command. - Read a list of commits from stdin and commit them in reverse - order. Only the leading sha1 is read from each line, so - git-rev-list --pretty=oneline output can be used. +Only used with the 'set-tree' command. + +Read a list of commits from stdin and commit them in reverse +order. Only the leading sha1 is read from each line, so +git-rev-list --pretty=oneline output can be used. --rmdir:: - Only used with the 'commit' command. - Remove directories from the SVN tree if there are no files left - behind. SVN can version empty directories, and they are not - removed by default if there are no files left in them. git - cannot version empty directories. Enabling this flag will make - the commit to SVN act like git. +Only used with the 'dcommit', 'set-tree' and 'commit-diff' commands. + +Remove directories from the SVN tree if there are no files left +behind. SVN can version empty directories, and they are not +removed by default if there are no files left in them. git +cannot version empty directories. Enabling this flag will make +the commit to SVN act like git. - repo-config key: svn.rmdir +repo-config key: svn.rmdir -e:: --edit:: - Only used with the 'commit' command. - Edit the commit message before committing to SVN. This is off by - default for objects that are commits, and forced on when committing - tree objects. +Only used with the 'dcommit', 'set-tree' and 'commit-diff' commands. + +Edit the commit message before committing to SVN. This is off by +default for objects that are commits, and forced on when committing +tree objects. - repo-config key: svn.edit +repo-config key: svn.edit -l<num>:: --find-copies-harder:: - Both of these are only used with the 'commit' command. - They are both passed directly to git-diff-tree see - git-diff-tree(1) for more information. +Only used with the 'dcommit', 'set-tree' and 'commit-diff' commands. - repo-config key: svn.l - repo-config key: svn.findcopiesharder +They are both passed directly to git-diff-tree see +gitlink:git-diff-tree[1] for more information. + +[verse] +repo-config key: svn.l +repo-config key: svn.findcopiesharder -A<filename>:: --authors-file=<filename>:: - Syntax is compatible with the files used by git-svnimport and - git-cvsimport: +Syntax is compatible with the files used by git-svnimport and +git-cvsimport: ------------------------------------------------------------------------ -loginname = Joe User <user@example.com> + loginname = Joe User <user@example.com> ------------------------------------------------------------------------ - If this option is specified and git-svn encounters an SVN - committer name that does not exist in the authors-file, git-svn - will abort operation. The user will then have to add the - appropriate entry. Re-running the previous git-svn command - after the authors-file is modified should continue operation. +If this option is specified and git-svn encounters an SVN +committer name that does not exist in the authors-file, git-svn +will abort operation. The user will then have to add the +appropriate entry. Re-running the previous git-svn command +after the authors-file is modified should continue operation. + +repo-config key: svn.authorsfile + +-q:: +--quiet:: + Make git-svn less verbose. + +--repack[=<n>]:: +--repack-flags=<flags> + These should help keep disk usage sane for large fetches + with many revisions. + + --repack takes an optional argument for the number of revisions + to fetch before repacking. This defaults to repacking every + 1000 commits fetched if no argument is specified. + + --repack-flags are passed directly to gitlink:git-repack[1]. + +repo-config key: svn.repack +repo-config key: svn.repackflags - repo-config key: svn.authors-file +-m:: +--merge:: +-s<strategy>:: +--strategy=<strategy>:: + +These are only used with the 'dcommit' command. + +Passed directly to git-rebase when using 'dcommit' if a +'git-reset' cannot be used (see dcommit). + +-n:: +--dry-run:: + +This is only used with the 'dcommit' command. + +Print out the series of git arguments that would show +which diffs would be committed to SVN. + +-- ADVANCED OPTIONS ---------------- +-- + -b<refname>:: --branch <refname>:: - Used with 'fetch' or 'commit'. +Used with 'fetch', 'dcommit' or 'set-tree'. - This can be used to join arbitrary git branches to remotes/git-svn - on new commits where the tree object is equivalent. +This can be used to join arbitrary git branches to remotes/git-svn +on new commits where the tree object is equivalent. - When used with different GIT_SVN_ID values, tags and branches in - SVN can be tracked this way, as can some merges where the heads - end up having completely equivalent content. This can even be - used to track branches across multiple SVN _repositories_. +When used with different GIT_SVN_ID values, tags and branches in +SVN can be tracked this way, as can some merges where the heads +end up having completely equivalent content. This can even be +used to track branches across multiple SVN _repositories_. - This option may be specified multiple times, once for each - branch. +This option may be specified multiple times, once for each +branch. - repo-config key: svn.branch +repo-config key: svn.branch -i<GIT_SVN_ID>:: --id <GIT_SVN_ID>:: - This sets GIT_SVN_ID (instead of using the environment). See - the section on "Tracking Multiple Repositories or Branches" for - more information on using GIT_SVN_ID. + +This sets GIT_SVN_ID (instead of using the environment). See the +section on +'<<tracking-multiple-repos,Tracking Multiple Repositories or Branches>>' +for more information on using GIT_SVN_ID. + +--follow-parent:: + This is especially helpful when we're tracking a directory + that has been moved around within the repository, or if we + started tracking a branch and never tracked the trunk it was + descended from. + +repo-config key: svn.followparent + +--no-metadata:: + This gets rid of the git-svn-id: lines at the end of every commit. + + With this, you lose the ability to use the rebuild command. If + you ever lose your .git/svn/git-svn/.rev_db file, you won't be + able to fetch again, either. This is fine for one-shot imports. + + The 'git-svn log' command will not work on repositories using this, + either. + +repo-config key: svn.nometadata + +-- COMPATIBILITY OPTIONS --------------------- ---upgrade:: - Only used with the 'rebuild' command. +-- - Run this if you used an old version of git-svn that used - "git-svn-HEAD" instead of "remotes/git-svn" as the branch - for tracking the remote. +--upgrade:: +Only used with the 'rebuild' command. ---no-ignore-externals:: - Only used with the 'fetch' and 'rebuild' command. +Run this if you used an old version of git-svn that used +"git-svn-HEAD" instead of "remotes/git-svn" as the branch +for tracking the remote. - By default, git-svn passes --ignore-externals to svn to avoid - fetching svn:external trees into git. Pass this flag to enable - externals tracking directly via git. +--ignore-nodate:: +Only used with the 'fetch' command. - Versions of svn that do not support --ignore-externals are - automatically detected and this flag will be automatically - enabled for them. +By default git-svn will crash if it tries to import a revision +from SVN which has '(no date)' listed as the date of the revision. +This is repository corruption on SVN's part, plain and simple. +But sometimes you really need those revisions anyway. - Otherwise, do not enable this flag unless you know what you're - doing. +If supplied git-svn will convert '(no date)' entries to the UNIX +epoch (midnight on Jan. 1, 1970). Yes, that's probably very wrong. +SVN was very wrong. - repo-config key: svn.noignoreexternals +-- Basic Examples ~~~~~~~~~~~~~~ -Tracking and contributing to an Subversion managed-project: +Tracking and contributing to a the trunk of a Subversion-managed project: ------------------------------------------------------------------------ -# Initialize a tree (like git init-db): +# Initialize a repo (like git init): git-svn init http://svn.foo.org/project/trunk # Fetch remote revisions: git-svn fetch # Create your own branch to hack on: git checkout -b my-branch remotes/git-svn -# Commit only the git commits you want to SVN: - git-svn commit <tree-ish> [<tree-ish_2> ...] -# Commit all the git commits from my-branch that don't exist in SVN: - git-svn commit remotes/git-svn..my-branch -# Something is committed to SVN, pull the latest into your branch: - git-svn fetch && git pull . remotes/git-svn +# Do some work, and then commit your new changes to SVN, as well as +# automatically updating your working HEAD: + git-svn dcommit +# Something is committed to SVN, rebase the latest into your branch: + git-svn fetch && git rebase remotes/git-svn # Append svn:ignore settings to the default git exclude file: git-svn show-ignore >> .git/info/exclude ------------------------------------------------------------------------ +Tracking and contributing to an entire Subversion-managed project +(complete with a trunk, tags and branches): +See also: +'<<tracking-multiple-repos,Tracking Multiple Repositories or Branches>>' + +------------------------------------------------------------------------ +# Initialize a repo (like git init): + git-svn multi-init http://svn.foo.org/project \ + -T trunk -b branches -t tags +# Fetch remote revisions: + git-svn multi-fetch +# Create your own branch of trunk to hack on: + git checkout -b my-trunk remotes/trunk +# Do some work, and then commit your new changes to SVN, as well as +# automatically updating your working HEAD: + git-svn dcommit -i trunk +# Something has been committed to trunk, rebase the latest into your branch: + git-svn multi-fetch && git rebase remotes/trunk +# Append svn:ignore settings of trunk to the default git exclude file: + git-svn show-ignore -i trunk >> .git/info/exclude +# Check for new branches and tags (no arguments are needed): + git-svn multi-init +------------------------------------------------------------------------ + +REBASE VS. PULL/MERGE +--------------------- + +Originally, git-svn recommended that the remotes/git-svn branch be +pulled or merged from. This is because the author favored +'git-svn set-tree B' to commit a single head rather than the +'git-svn set-tree A..B' notation to commit multiple commits. + +If you use 'git-svn set-tree A..B' to commit several diffs and you do +not have the latest remotes/git-svn merged into my-branch, you should +use 'git rebase' to update your work branch instead of 'git pull' or +'git merge'. 'pull/merge' can cause non-linear history to be flattened +when committing into SVN, which can lead to merge commits reversing +previous commits in SVN. + DESIGN PHILOSOPHY ----------------- Merge tracking in Subversion is lacking and doing branched development -with Subversion is cumbersome as a result. git-svn completely forgoes -any automated merge/branch tracking on the Subversion side and leaves it -entirely up to the user on the git side. It's simply not worth it to do -a useful translation when the original signal is weak. +with Subversion is cumbersome as a result. git-svn does not do +automated merge/branch tracking by default and leaves it entirely up to +the user on the git side. +[[tracking-multiple-repos]] TRACKING MULTIPLE REPOSITORIES OR BRANCHES ------------------------------------------ -This is for advanced users, most users should ignore this section. - Because git-svn does not care about relationships between different branches or directories in a Subversion repository, git-svn has a simple hack to allow it to track an arbitrary number of related _or_ unrelated -SVN repositories via one git repository. Simply set the GIT_SVN_ID -environment variable to a name other other than "git-svn" (the default) -and git-svn will ignore the contents of the $GIT_DIR/git-svn directory -and instead do all of its work in $GIT_DIR/$GIT_SVN_ID for that -invocation. The interface branch will be remotes/$GIT_SVN_ID, instead of -remotes/git-svn. Any remotes/$GIT_SVN_ID branch should never be modified -by the user outside of git-svn commands. - +SVN repositories via one git repository. Simply use the --id/-i flag or +set the GIT_SVN_ID environment variable to a name other other than +"git-svn" (the default) and git-svn will ignore the contents of the +$GIT_DIR/svn/git-svn directory and instead do all of its work in +$GIT_DIR/svn/$GIT_SVN_ID for that invocation. The interface branch will +be remotes/$GIT_SVN_ID, instead of remotes/git-svn. Any +remotes/$GIT_SVN_ID branch should never be modified by the user outside +of git-svn commands. + +[[fetch-args]] ADDITIONAL FETCH ARGUMENTS -------------------------- This is for advanced users, most users should ignore this section. @@ -251,58 +454,33 @@ optionally be specified in the form of sha1 hex sums at the command-line. Unfetched SVN revisions may also be tied to particular git commits with the following syntax: +------------------------------------------------ svn_revision_number=git_commit_sha1 +------------------------------------------------ -This allows you to tie unfetched SVN revision 375 to your current HEAD:: +This allows you to tie unfetched SVN revision 375 to your current HEAD: - `git-svn fetch 375=$(git-rev-parse HEAD)` +------------------------------------------------ + git-svn fetch 375=$(git-rev-parse HEAD) +------------------------------------------------ -Advanced Example: Tracking a Reorganized Repository -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If you're tracking a directory that has moved, or otherwise been branched or tagged off of another directory in the repository and you -care about the full history of the project, then you can read this -section. - -This is how Yann Dirson tracked the trunk of the ufoai directory when -the /trunk directory of his repository was moved to /ufoai/trunk and -he needed to continue tracking /ufoai/trunk where /trunk left off. +care about the full history of the project, then you can use +the --follow-parent option. ------------------------------------------------------------------------- - # This log message shows when the repository was reorganized: - r166 | ydirson | 2006-03-02 01:36:55 +0100 (Thu, 02 Mar 2006) | 1 line - Changed paths: - D /trunk - A /ufoai/trunk (from /trunk:165) - - # First we start tracking the old revisions: - GIT_SVN_ID=git-oldsvn git-svn init \ - https://svn.sourceforge.net/svnroot/ufoai/trunk - GIT_SVN_ID=git-oldsvn git-svn fetch -r1:165 - - # And now, we continue tracking the new revisions: - GIT_SVN_ID=git-newsvn git-svn init \ - https://svn.sourceforge.net/svnroot/ufoai/ufoai/trunk - GIT_SVN_ID=git-newsvn git-svn fetch \ - 166=`git-rev-parse refs/remotes/git-oldsvn` ------------------------------------------------------------------------- +------------------------------------------------ + git-svn fetch --follow-parent +------------------------------------------------ BUGS ---- -If somebody commits a conflicting changeset to SVN at a bad moment -(right before you commit) causing a conflict and your commit to fail, -your svn working tree ($GIT_DIR/git-svn/tree) may be dirtied. The -easiest thing to do is probably just to rm -rf $GIT_DIR/git-svn/tree and -run 'rebuild'. We ignore all SVN properties except svn:executable. Too difficult to map them since we rely heavily on git write-tree being _exactly_ the same on both the SVN and git working trees and I prefer not to clutter working trees with metadata files. -svn:keywords can't be ignored in Subversion (at least I don't know of -a way to ignore them). - Renamed and copied directories are not detected by git and hence not tracked when committing to SVN. I do not plan on adding support for this as it's quite difficult and time-consuming to get working for all @@ -310,6 +488,10 @@ the possible corner cases (git doesn't do it, either). Renamed and copied files are fully supported if they're similar enough for git to detect them. +SEE ALSO +-------- +gitlink:git-rebase[1] + Author ------ Written by Eric Wong <normalperson@yhbt.net>. diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt index b1b87c2fcd..b166cf3327 100644 --- a/Documentation/git-svnimport.txt +++ b/Documentation/git-svnimport.txt @@ -15,6 +15,7 @@ SYNOPSIS [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] [ -s start_chg ] [ -m ] [ -r ] [ -M regex ] [ -I <ignorefile_name> ] [ -A <author_file> ] + [ -R <repack_each_revs>] [ -P <path_from_trunk> ] <SVN_repository_URL> [ <path> ] @@ -103,9 +104,25 @@ repository without -A. -l <max_rev>:: Specify a maximum revision number to pull. ++ +Formerly, this option controlled how many revisions to pull, +due to SVN memory leaks. (These have been worked around.) + +-R <repack_each_revs>:: + Specify how often git repository should be repacked. ++ +The default value is 1000. git-svnimport will do import in chunks of 1000 +revisions, after each chunk git repository will be repacked. To disable +this behavior specify some big value here which is mote than number of +revisions to import. - Formerly, this option controlled how many revisions to pull, - due to SVN memory leaks. (These have been worked around.) +-P <path_from_trunk>:: + Partial import of the SVN tree. ++ +By default, the whole tree on the SVN trunk (/trunk) is imported. +'-P my/proj' will import starting only from '/trunk/my/proj'. +This option is useful when you want to import one project from a +svn repo which hosts multiple projects under the same trunk. -v:: Verbosity: let 'svnimport' report what it is doing. diff --git a/Documentation/git-symbolic-ref.txt b/Documentation/git-symbolic-ref.txt index 68ac6a65df..4bc35a1d4b 100644 --- a/Documentation/git-symbolic-ref.txt +++ b/Documentation/git-symbolic-ref.txt @@ -19,29 +19,22 @@ argument to see on which branch your working tree is on. Give two arguments, create or update a symbolic ref <name> to point at the given branch <ref>. -Traditionally, `.git/HEAD` is a symlink pointing at -`refs/heads/master`. When we want to switch to another branch, -we did `ln -sf refs/heads/newbranch .git/HEAD`, and when we want +A symbolic ref is a regular file that stores a string that +begins with `ref: refs/`. For example, your `.git/HEAD` is +a regular file whose contents is `ref: refs/heads/master`. + +NOTES +----- +In the past, `.git/HEAD` was a symbolic link pointing at +`refs/heads/master`. When we wanted to switch to another branch, +we did `ln -sf refs/heads/newbranch .git/HEAD`, and when we wanted to find out which branch we are on, we did `readlink .git/HEAD`. This was fine, and internally that is what still happens by default, but on platforms that do not have working symlinks, or that do not have the `readlink(1)` command, this was a bit cumbersome. On some platforms, `ln -sf` does not even work as -advertised (horrors). - -A symbolic ref can be a regular file that stores a string that -begins with `ref: refs/`. For example, your `.git/HEAD` *can* -be a regular file whose contents is `ref: refs/heads/master`. -This can be used on a filesystem that does not support symbolic -links. Instead of doing `readlink .git/HEAD`, `git-symbolic-ref -HEAD` can be used to find out which branch we are on. To point -the HEAD to `newbranch`, instead of `ln -sf refs/heads/newbranch -.git/HEAD`, `git-symbolic-ref HEAD refs/heads/newbranch` can be -used. - -Currently, .git/HEAD uses a regular file symbolic ref on Cygwin, -and everywhere else it is implemented as a symlink. This can be -changed at compilation time. +advertised (horrors). Therefore symbolic links are now deprecated +and symbolic refs are used by default. Author ------ diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt index 45476c2e41..80bece0775 100644 --- a/Documentation/git-tag.txt +++ b/Documentation/git-tag.txt @@ -9,7 +9,8 @@ git-tag - Create a tag object signed with GPG SYNOPSIS -------- [verse] -'git-tag' [-a | -s | -u <key-id>] [-f | -d] [-m <msg>] <name> [<head>] +'git-tag' [-a | -s | -u <key-id>] [-f | -d | -v] [-m <msg> | -F <file>] + <name> [<head>] 'git-tag' -l [<pattern>] DESCRIPTION @@ -34,6 +35,8 @@ GnuPG key for signing. `-d <tag>` deletes the tag. +`-v <tag>` verifies the gpg signature of the tag. + `-l <pattern>` lists tags that match the given pattern (or all if no pattern is given). @@ -54,12 +57,18 @@ OPTIONS -d:: Delete an existing tag with the given name +-v:: + Verify the gpg signature of given the tag + -l <pattern>:: List tags that match the given pattern (or all if no pattern is given). -m <msg>:: Use the given tag message (instead of prompting) +-F <file>:: + Take the tag message from the given file. Use '-' to + read the message from the standard input. Author ------ diff --git a/Documentation/git-tar-tree.txt b/Documentation/git-tar-tree.txt index 1e1c7fa856..74a6fddd9a 100644 --- a/Documentation/git-tar-tree.txt +++ b/Documentation/git-tar-tree.txt @@ -12,6 +12,9 @@ SYNOPSIS DESCRIPTION ----------- +THIS COMMAND IS DEPRECATED. Use `git-archive` with `--format=tar` +option instead. + Creates a tar archive containing the tree structure for the named tree. When <base> is specified it is added as a leading path to the files in the generated tar archive. diff --git a/Documentation/git-unpack-objects.txt b/Documentation/git-unpack-objects.txt index c20b38b08a..ff6184b0f7 100644 --- a/Documentation/git-unpack-objects.txt +++ b/Documentation/git-unpack-objects.txt @@ -8,7 +8,7 @@ git-unpack-objects - Unpack objects from a packed archive SYNOPSIS -------- -'git-unpack-objects' [-n] [-q] <pack-file +'git-unpack-objects' [-n] [-q] [-r] <pack-file DESCRIPTION @@ -34,6 +34,12 @@ OPTIONS The command usually shows percentage progress. This flag suppresses it. +-r:: + When unpacking a corrupt packfile, the command dies at + the first corruption. This flag tells it to keep going + and make the best effort to recover as many objects as + possible. + Author ------ diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt index 3ae6e74573..0e0a3af1be 100644 --- a/Documentation/git-update-index.txt +++ b/Documentation/git-update-index.txt @@ -15,7 +15,7 @@ SYNOPSIS [--cacheinfo <mode> <object> <file>]\* [--chmod=(+|-)x] [--assume-unchanged | --no-assume-unchanged] - [--really-refresh] [--unresolve] [--again] + [--really-refresh] [--unresolve] [--again | -g] [--info-only] [--index-info] [-z] [--stdin] [--verbose] @@ -80,7 +80,7 @@ OPTIONS filesystem that has very slow lstat(2) system call (e.g. cifs). ---again:: +--again, -g:: Runs `git-update-index` itself on the paths whose index entries are different from those from the `HEAD` commit. @@ -216,8 +216,8 @@ $ git ls-files -s ------------ -Using "assume unchanged" bit ----------------------------- +Using ``assume unchanged'' bit +------------------------------ Many operations in git depend on your filesystem to have an efficient `lstat(2)` implementation, so that `st_mtime` diff --git a/Documentation/git-update-ref.txt b/Documentation/git-update-ref.txt index e062030e91..71bcb7954f 100644 --- a/Documentation/git-update-ref.txt +++ b/Documentation/git-update-ref.txt @@ -7,7 +7,7 @@ git-update-ref - update the object name stored in a ref safely SYNOPSIS -------- -'git-update-ref' [-m <reason>] <ref> <newvalue> [<oldvalue>] +'git-update-ref' [-m <reason>] (-d <ref> <oldvalue> | <ref> <newvalue> [<oldvalue>]) DESCRIPTION ----------- @@ -20,7 +20,9 @@ possibly dereferencing the symbolic refs, after verifying that the current value of the <ref> matches <oldvalue>. E.g. `git-update-ref refs/heads/master <newvalue> <oldvalue>` updates the master branch head to <newvalue> only if its current -value is <oldvalue>. +value is <oldvalue>. You can specify 40 "0" or an empty string +as <oldvalue> to make sure that the ref you are creating does +not exist. It also allows a "ref" file to be a symbolic pointer to another ref file by starting with the four-byte header sequence of @@ -49,6 +51,10 @@ for reading but not for writing (so we'll never write through a ref symlink to some other tree, if you have copied a whole archive by creating a symlink tree). +With `-d` flag, it deletes the named <ref> after verifying it +still contains <oldvalue>. + + Logging Updates --------------- If config parameter "core.logAllRefUpdates" is true or the file diff --git a/Documentation/git-upload-archive.txt b/Documentation/git-upload-archive.txt new file mode 100644 index 0000000000..388bb53d29 --- /dev/null +++ b/Documentation/git-upload-archive.txt @@ -0,0 +1,37 @@ +git-upload-archive(1) +==================== + +NAME +---- +git-upload-archive - Send archive + + +SYNOPSIS +-------- +'git-upload-archive' <directory> + +DESCRIPTION +----------- +Invoked by 'git-archive --remote' and sends a generated archive to the +other end over the git protocol. + +This command is usually not invoked directly by the end user. The UI +for the protocol is on the 'git-archive' side, and the program pair +is meant to be used to get an archive from a remote repository. + +OPTIONS +------- +<directory>:: + The repository to get a tar archive from. + +Author +------ +Written by Franck Bui-Huu. + +Documentation +-------------- +Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-upload-tar.txt b/Documentation/git-upload-tar.txt deleted file mode 100644 index 394af62015..0000000000 --- a/Documentation/git-upload-tar.txt +++ /dev/null @@ -1,39 +0,0 @@ -git-upload-tar(1) -================= - -NAME ----- -git-upload-tar - Send tar archive - - -SYNOPSIS --------- -'git-upload-tar' <directory> - -DESCRIPTION ------------ -Invoked by 'git-tar-tree --remote' and sends a generated tar archive -to the other end over the git protocol. - -This command is usually not invoked directly by the end user. -The UI for the protocol is on the 'git-tar-tree' side, and the -program pair is meant to be used to get a tar archive from a -remote repository. - - -OPTIONS -------- -<directory>:: - The repository to get a tar archive from. - -Author ------- -Written by Junio C Hamano <junio@kernel.org> - -Documentation --------------- -Documentation by Junio C Hamano. - -GIT ---- -Part of the gitlink:git[7] suite diff --git a/Documentation/git.txt b/Documentation/git.txt index 3de5fa9c82..f89d745efa 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -8,8 +8,9 @@ git - the stupid content tracker SYNOPSIS -------- +[verse] 'git' [--version] [--exec-path[=GIT_EXEC_PATH]] [-p|--paginate] - [--bare] [--git-dir=GIT_DIR] [--help] COMMAND [ARGS] + [--bare] [--git-dir=GIT_DIR] [--help] COMMAND [ARGS] DESCRIPTION ----------- @@ -71,186 +72,6 @@ GIT COMMANDS We divide git into high level ("porcelain") commands and low level ("plumbing") commands. -Low-level commands (plumbing) ------------------------------ - -Although git includes its -own porcelain layer, its low-level commands are sufficient to support -development of alternative porcelains. Developers of such porcelains -might start by reading about gitlink:git-update-index[1] and -gitlink:git-read-tree[1]. - -We divide the low-level commands into commands that manipulate objects (in -the repository, index, and working tree), commands that interrogate and -compare objects, and commands that move objects and references between -repositories. - -Manipulation commands -~~~~~~~~~~~~~~~~~~~~~ -gitlink:git-apply[1]:: - Reads a "diff -up1" or git generated patch file and - applies it to the working tree. - -gitlink:git-checkout-index[1]:: - Copy files from the index to the working tree. - -gitlink:git-commit-tree[1]:: - Creates a new commit object. - -gitlink:git-hash-object[1]:: - Computes the object ID from a file. - -gitlink:git-index-pack[1]:: - Build pack idx file for an existing packed archive. - -gitlink:git-init-db[1]:: - Creates an empty git object database, or reinitialize an - existing one. - -gitlink:git-merge-index[1]:: - Runs a merge for files needing merging. - -gitlink:git-mktag[1]:: - Creates a tag object. - -gitlink:git-mktree[1]:: - Build a tree-object from ls-tree formatted text. - -gitlink:git-pack-objects[1]:: - Creates a packed archive of objects. - -gitlink:git-prune-packed[1]:: - Remove extra objects that are already in pack files. - -gitlink:git-read-tree[1]:: - Reads tree information into the index. - -gitlink:git-repo-config[1]:: - Get and set options in .git/config. - -gitlink:git-unpack-objects[1]:: - Unpacks objects out of a packed archive. - -gitlink:git-update-index[1]:: - Registers files in the working tree to the index. - -gitlink:git-write-tree[1]:: - Creates a tree from the index. - - -Interrogation commands -~~~~~~~~~~~~~~~~~~~~~~ - -gitlink:git-cat-file[1]:: - Provide content or type/size information for repository objects. - -gitlink:git-describe[1]:: - Show the most recent tag that is reachable from a commit. - -gitlink:git-diff-index[1]:: - Compares content and mode of blobs between the index and repository. - -gitlink:git-diff-files[1]:: - Compares files in the working tree and the index. - -gitlink:git-diff-stages[1]:: - Compares two "merge stages" in the index. - -gitlink:git-diff-tree[1]:: - Compares the content and mode of blobs found via two tree objects. - -gitlink:git-fsck-objects[1]:: - Verifies the connectivity and validity of the objects in the database. - -gitlink:git-ls-files[1]:: - Information about files in the index and the working tree. - -gitlink:git-ls-tree[1]:: - Displays a tree object in human readable form. - -gitlink:git-merge-base[1]:: - Finds as good common ancestors as possible for a merge. - -gitlink:git-name-rev[1]:: - Find symbolic names for given revs. - -gitlink:git-pack-redundant[1]:: - Find redundant pack files. - -gitlink:git-rev-list[1]:: - Lists commit objects in reverse chronological order. - -gitlink:git-show-index[1]:: - Displays contents of a pack idx file. - -gitlink:git-tar-tree[1]:: - Creates a tar archive of the files in the named tree object. - -gitlink:git-unpack-file[1]:: - Creates a temporary file with a blob's contents. - -gitlink:git-var[1]:: - Displays a git logical variable. - -gitlink:git-verify-pack[1]:: - Validates packed git archive files. - -In general, the interrogate commands do not touch the files in -the working tree. - - -Synching repositories -~~~~~~~~~~~~~~~~~~~~~ - -gitlink:git-fetch-pack[1]:: - Updates from a remote repository (engine for ssh and - local transport). - -gitlink:git-http-fetch[1]:: - Downloads a remote git repository via HTTP by walking - commit chain. - -gitlink:git-local-fetch[1]:: - Duplicates another git repository on a local system by - walking commit chain. - -gitlink:git-peek-remote[1]:: - Lists references on a remote repository using - upload-pack protocol (engine for ssh and local - transport). - -gitlink:git-receive-pack[1]:: - Invoked by 'git-send-pack' to receive what is pushed to it. - -gitlink:git-send-pack[1]:: - Pushes to a remote repository, intelligently. - -gitlink:git-http-push[1]:: - Push missing objects using HTTP/DAV. - -gitlink:git-shell[1]:: - Restricted shell for GIT-only SSH access. - -gitlink:git-ssh-fetch[1]:: - Pulls from a remote repository over ssh connection by - walking commit chain. - -gitlink:git-ssh-upload[1]:: - Helper "server-side" program used by git-ssh-fetch. - -gitlink:git-update-server-info[1]:: - Updates auxiliary information on a dumb server to help - clients discover references and packs on it. - -gitlink:git-upload-pack[1]:: - Invoked by 'git-fetch-pack' to push - what are asked for. - -gitlink:git-upload-tar[1]:: - Invoked by 'git-tar-tree --remote' to return the tar - archive the other end asked for. - - High-level commands (porcelain) ------------------------------- @@ -269,6 +90,9 @@ gitlink:git-am[1]:: gitlink:git-applymbox[1]:: Apply patches from a mailbox, original version by Linus. +gitlink:git-archive[1]:: + Creates an archive of files from a named tree. + gitlink:git-bisect[1]:: Find the change that introduced a bug by binary search. @@ -302,6 +126,9 @@ gitlink:git-format-patch[1]:: gitlink:git-grep[1]:: Print lines matching a pattern. +gitlink:gitk[1]:: + The git repository browser. + gitlink:git-log[1]:: Shows commit logs. @@ -314,8 +141,11 @@ gitlink:git-merge[1]:: gitlink:git-mv[1]:: Move or rename a file, a directory, or a symlink. +gitlink:git-pack-refs[1]:: + Pack heads and tags for efficient repository access. + gitlink:git-pull[1]:: - Fetch from and merge with a remote repository. + Fetch from and merge with a remote repository or a local branch. gitlink:git-push[1]:: Update remote refs along with associated objects. @@ -382,6 +212,9 @@ gitlink:git-cvsexportcommit[1]:: gitlink:git-cvsserver[1]:: A CVS server emulator for git. +gitlink:git-gc[1]:: + Cleanup unnecessary files and optimize the local repository. + gitlink:git-lost-found[1]:: Recover lost refs that luckily have not yet been pruned. @@ -394,6 +227,9 @@ gitlink:git-prune[1]:: gitlink:git-quiltimport[1]:: Applies a quilt patchset onto the current branch. +gitlink:git-reflog[1]:: + Manage reflog information. + gitlink:git-relink[1]:: Hardlink common objects in local repositories. @@ -422,7 +258,7 @@ gitlink:git-annotate[1]:: Annotate file lines with commit info. gitlink:git-blame[1]:: - Blame file lines on commits. + Find out where each line in a file came from. gitlink:git-check-ref-format[1]:: Make sure ref name is well formed. @@ -472,6 +308,9 @@ gitlink:git-request-pull[1]:: gitlink:git-rev-parse[1]:: Pick out and massage parameters. +gitlink:git-runstatus[1]:: + A helper for git-status and git-commit. + gitlink:git-send-email[1]:: Send patch e-mails out of "format-patch --mbox" output. @@ -482,11 +321,192 @@ gitlink:git-stripspace[1]:: Filter out empty lines. -Commands not yet documented ---------------------------- +Low-level commands (plumbing) +----------------------------- -gitlink:gitk[1]:: - The gitk repository browser. +Although git includes its +own porcelain layer, its low-level commands are sufficient to support +development of alternative porcelains. Developers of such porcelains +might start by reading about gitlink:git-update-index[1] and +gitlink:git-read-tree[1]. + +We divide the low-level commands into commands that manipulate objects (in +the repository, index, and working tree), commands that interrogate and +compare objects, and commands that move objects and references between +repositories. + +Manipulation commands +~~~~~~~~~~~~~~~~~~~~~ +gitlink:git-apply[1]:: + Reads a "diff -up1" or git generated patch file and + applies it to the working tree. + +gitlink:git-checkout-index[1]:: + Copy files from the index to the working tree. + +gitlink:git-commit-tree[1]:: + Creates a new commit object. + +gitlink:git-hash-object[1]:: + Computes the object ID from a file. + +gitlink:git-index-pack[1]:: + Build pack idx file for an existing packed archive. + +gitlink:git-init[1]:: + Creates an empty git repository, or reinitialize an + existing one. + +gitlink:git-merge-file[1]:: + Runs a threeway merge. + +gitlink:git-merge-index[1]:: + Runs a merge for files needing merging. + +gitlink:git-mktag[1]:: + Creates a tag object. + +gitlink:git-mktree[1]:: + Build a tree-object from ls-tree formatted text. + +gitlink:git-pack-objects[1]:: + Creates a packed archive of objects. + +gitlink:git-prune-packed[1]:: + Remove extra objects that are already in pack files. + +gitlink:git-read-tree[1]:: + Reads tree information into the index. + +gitlink:git-repo-config[1]:: + Get and set options in .git/config. + +gitlink:git-unpack-objects[1]:: + Unpacks objects out of a packed archive. + +gitlink:git-update-index[1]:: + Registers files in the working tree to the index. + +gitlink:git-write-tree[1]:: + Creates a tree from the index. + + +Interrogation commands +~~~~~~~~~~~~~~~~~~~~~~ + +gitlink:git-cat-file[1]:: + Provide content or type/size information for repository objects. + +gitlink:git-describe[1]:: + Show the most recent tag that is reachable from a commit. + +gitlink:git-diff-index[1]:: + Compares content and mode of blobs between the index and repository. + +gitlink:git-diff-files[1]:: + Compares files in the working tree and the index. + +gitlink:git-diff-stages[1]:: + Compares two "merge stages" in the index. + +gitlink:git-diff-tree[1]:: + Compares the content and mode of blobs found via two tree objects. + +gitlink:git-for-each-ref[1]:: + Output information on each ref. + +gitlink:git-fsck-objects[1]:: + Verifies the connectivity and validity of the objects in the database. + +gitlink:git-ls-files[1]:: + Information about files in the index and the working tree. + +gitlink:git-ls-tree[1]:: + Displays a tree object in human readable form. + +gitlink:git-merge-base[1]:: + Finds as good common ancestors as possible for a merge. + +gitlink:git-name-rev[1]:: + Find symbolic names for given revs. + +gitlink:git-pack-redundant[1]:: + Find redundant pack files. + +gitlink:git-rev-list[1]:: + Lists commit objects in reverse chronological order. + +gitlink:git-show-index[1]:: + Displays contents of a pack idx file. + +gitlink:git-show-ref[1]:: + List references in a local repository. + +gitlink:git-tar-tree[1]:: + Creates a tar archive of the files in the named tree object. + +gitlink:git-unpack-file[1]:: + Creates a temporary file with a blob's contents. + +gitlink:git-var[1]:: + Displays a git logical variable. + +gitlink:git-verify-pack[1]:: + Validates packed git archive files. + +In general, the interrogate commands do not touch the files in +the working tree. + + +Synching repositories +~~~~~~~~~~~~~~~~~~~~~ + +gitlink:git-fetch-pack[1]:: + Updates from a remote repository (engine for ssh and + local transport). + +gitlink:git-http-fetch[1]:: + Downloads a remote git repository via HTTP by walking + commit chain. + +gitlink:git-local-fetch[1]:: + Duplicates another git repository on a local system by + walking commit chain. + +gitlink:git-peek-remote[1]:: + Lists references on a remote repository using + upload-pack protocol (engine for ssh and local + transport). + +gitlink:git-receive-pack[1]:: + Invoked by 'git-send-pack' to receive what is pushed to it. + +gitlink:git-send-pack[1]:: + Pushes to a remote repository, intelligently. + +gitlink:git-http-push[1]:: + Push missing objects using HTTP/DAV. + +gitlink:git-shell[1]:: + Restricted shell for GIT-only SSH access. + +gitlink:git-ssh-fetch[1]:: + Pulls from a remote repository over ssh connection by + walking commit chain. + +gitlink:git-ssh-upload[1]:: + Helper "server-side" program used by git-ssh-fetch. + +gitlink:git-update-server-info[1]:: + Updates auxiliary information on a dumb server to help + clients discover references and packs on it. + +gitlink:git-upload-archive[1]:: + Invoked by 'git-archive' to send a generated archive. + +gitlink:git-upload-pack[1]:: + Invoked by 'git-fetch-pack' to push + what are asked for. Configuration Mechanism @@ -563,6 +583,9 @@ HEAD:: a valid head 'name' (i.e. the contents of `$GIT_DIR/refs/heads/<head>`). +For a more complete list of ways to spell object names, see +"SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + File/Directory Structure ------------------------ @@ -625,11 +648,35 @@ git Commits git Diffs ~~~~~~~~~ 'GIT_DIFF_OPTS':: + Only valid setting is "--unified=??" or "-u??" to set the + number of context lines shown when a unified diff is created. + This takes precedence over any "-U" or "--unified" option + value passed on the git diff command line. + 'GIT_EXTERNAL_DIFF':: - see the "generating patches" section in : - gitlink:git-diff-index[1]; - gitlink:git-diff-files[1]; - gitlink:git-diff-tree[1] + When the environment variable 'GIT_EXTERNAL_DIFF' is set, the + program named by it is called, instead of the diff invocation + described above. For a path that is added, removed, or modified, + 'GIT_EXTERNAL_DIFF' is called with 7 parameters: + + path old-file old-hex old-mode new-file new-hex new-mode ++ +where: + + <old|new>-file:: are files GIT_EXTERNAL_DIFF can use to read the + contents of <old|new>, + <old|new>-hex:: are the 40-hexdigit SHA1 hashes, + <old|new>-mode:: are the octal representation of the file modes. + ++ +The file parameters can point at the user's working file +(e.g. `new-file` in "git-diff-files"), `/dev/null` (e.g. `old-file` +when a new file is added), or a temporary file (e.g. `old-file` in the +index). 'GIT_EXTERNAL_DIFF' should not worry about unlinking the +temporary file --- it is removed when 'GIT_EXTERNAL_DIFF' exits. ++ +For a path that is unmerged, 'GIT_EXTERNAL_DIFF' is called with 1 +parameter, <path>. other ~~~~~ @@ -637,9 +684,18 @@ other This environment variable overrides `$PAGER`. 'GIT_TRACE':: - If this variable is set git will print `trace:` messages on + If this variable is set to "1", "2" or "true" (comparison + is case insensitive), git will print `trace:` messages on stderr telling about alias expansion, built-in command execution and external command execution. + If this variable is set to an integer value greater than 1 + and lower than 10 (strictly) then git will interpret this + value as an open file descriptor and will try to write the + trace messages into this file descriptor. + Alternatively, if this variable is set to an absolute path + (starting with a '/' character), git will interpret this + as a file path and will try to write the trace messages + into it. Discussion[[Discussion]] ------------------------ diff --git a/Documentation/gitk.txt b/Documentation/gitk.txt index cb482bf98e..f1aeb07f64 100644 --- a/Documentation/gitk.txt +++ b/Documentation/gitk.txt @@ -3,26 +3,56 @@ gitk(1) NAME ---- -gitk - Some git command not yet documented. - +gitk - git repository browser SYNOPSIS -------- -'gitk' [ --option ] <args>... +'gitk' [<option>...] [<revs>] [--] [<path>...] DESCRIPTION ----------- -Does something not yet documented. +Displays changes in a repository or a selected set of commits. This includes +visualizing the commit graph, showing information related to each commit, and +the files in the trees of each revision. +Historically, gitk was the first repository browser. It's written in tcl/tk +and started off in a separate repository but was later merged into the main +git repository. OPTIONS ------- ---option:: - Some option not yet documented. +To control which revisions to shown, the command takes options applicable to +the gitlink:git-rev-list[1] command. This manual page describes only the most +frequently used options. + +-n <number>, --max-count=<number>:: + + Limits the number of commits to show. + +--since=<date>:: + + Show commits more recent than a specific date. + +--until=<date>:: + + Show commits older than a specific date. + +--all:: + + Show all branches. -<args>...:: - Some argument not yet documented. +<revs>:: + Limit the revisions to show. This can be either a single revision + meaning show from the given revision and back, or it can be a range in + the form "'<from>'..'<to>'" to show all revisions between '<from>' and + back to '<to>'. Note, more advanced revision selection can be applied. + +<path>:: + + Limit commits to the ones touching files in the given paths. Note, to + avoid ambiguity wrt. revision names use "--" to separate the paths + from any preceeding options. Examples -------- @@ -37,13 +67,32 @@ gitk --since="2 weeks ago" \-- gitk:: The "--" is necessary to avoid confusion with the *branch* named 'gitk' +gitk --max-count=100 --all -- Makefile:: + + Show at most 100 changes made to the file 'Makefile'. Instead of only + looking for changes in the current branch look in all branches. + +See Also +-------- +'qgit(1)':: + A repository browser written in C++ using Qt. + +'gitview(1)':: + A repository browser written in Python using Gtk. It's based on + 'bzrk(1)' and distributed in the contrib area of the git repository. + +'tig(1)':: + A minimal repository browser and git tool output highlighter written + in C using Ncurses. + Author ------ -Written by Paul Mackerras <paulus@samba.org> +Written by Paul Mackerras <paulus@samba.org>. Documentation -------------- -Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>. +Documentation by Junio C Hamano, Jonas Fonseca, and the git-list +<git@vger.kernel.org>. GIT --- diff --git a/Documentation/glossary.txt b/Documentation/glossary.txt index 14449ca8ba..bc917bbac3 100644 --- a/Documentation/glossary.txt +++ b/Documentation/glossary.txt @@ -179,7 +179,7 @@ object name:: character hexadecimal encoding of the hash of the object (possibly followed by a white space). -object type: +object type:: One of the identifiers "commit","tree","tag" and "blob" describing the type of an object. @@ -188,11 +188,12 @@ octopus:: predator. origin:: - The default upstream tracking branch. Most projects have at + The default upstream repository. Most projects have at least one upstream project which they track. By default 'origin' is used for that purpose. New upstream updates - will be fetched into this branch; you should never commit - to it yourself. + will be fetched into remote tracking branches named + origin/name-of-upstream-branch, which you can see using + "git branch -r". pack:: A set of objects which have been compressed into one file (to save @@ -234,8 +235,11 @@ push:: local head, the push fails. reachable:: - An object is reachable from a ref/commit/tree/tag, if there is a - chain leading from the latter to the former. + All of the ancestors of a given commit are said to be reachable from + that commit. More generally, one object is reachable from another if + we can reach the one from the other by a chain that follows tags to + whatever they tag, commits to their parents or trees, and trees to the + trees or blobs that they contain. rebase:: To clean a branch by starting from the head of the main line of @@ -255,7 +259,7 @@ refspec:: means "grab the master branch head from the $URL and store it as my origin branch head". And `git push $URL refs/heads/master:refs/heads/to-upstream` - means "publish my master branch head as to-upstream master head + means "publish my master branch head as to-upstream branch at $URL". See also gitlink:git-push[1] repository:: @@ -282,6 +286,13 @@ SCM:: SHA1:: Synonym for object name. +symref:: + Symbolic reference: instead of containing the SHA1 id itself, it + is of the format 'ref: refs/some/thing' and when referenced, it + recursively dereferences to this reference. 'HEAD' is a prime + example of a symref. Symbolic references are manipulated with + the gitlink:git-symbolic-ref[1] command. + topic branch:: A regular git branch that is used by a developer to identify a conceptual line of development. Since branches @@ -324,7 +335,7 @@ tag:: A tag is most typically used to mark a particular point in the commit ancestry chain. -unmerged index: +unmerged index:: An index which contains unmerged index entries. working tree:: diff --git a/Documentation/hooks.txt b/Documentation/hooks.txt index 898b4aaf80..e3b76f96eb 100644 --- a/Documentation/hooks.txt +++ b/Documentation/hooks.txt @@ -3,10 +3,9 @@ Hooks used by git Hooks are little scripts you can place in `$GIT_DIR/hooks` directory to trigger action at certain points. When -`git-init-db` is run, a handful example hooks are copied in the +`git-init` is run, a handful example hooks are copied in the `hooks` directory of the new repository, but by default they are -all disabled. To enable a hook, make it executable with `chmod -+x`. +all disabled. To enable a hook, make it executable with `chmod +x`. This document describes the currently defined hooks. @@ -16,16 +15,16 @@ applypatch-msg This hook is invoked by `git-applypatch` script, which is typically invoked by `git-applymbox`. It takes a single parameter, the name of the file that holds the proposed commit -log message. Exiting with non-zero status causes the -'git-applypatch' to abort before applying the patch. +log message. Exiting with non-zero status causes +`git-applypatch` to abort before applying the patch. The hook is allowed to edit the message file in place, and can be used to normalize the message into some project standard format (if the project has one). It can also be used to refuse the commit after inspecting the message file. -The default applypatch-msg hook, when enabled, runs the -commit-msg hook, if the latter is enabled. +The default 'applypatch-msg' hook, when enabled, runs the +'commit-msg' hook, if the latter is enabled. pre-applypatch -------------- @@ -39,8 +38,8 @@ after application of the patch not committed. It can be used to inspect the current working tree and refuse to make a commit if it does not pass certain test. -The default pre-applypatch hook, when enabled, runs the -pre-commit hook, if the latter is enabled. +The default 'pre-applypatch' hook, when enabled, runs the +'pre-commit' hook, if the latter is enabled. post-applypatch --------------- @@ -61,9 +60,9 @@ invoked before obtaining the proposed commit log message and making a commit. Exiting with non-zero status from this script causes the `git-commit` to abort. -The default pre-commit hook, when enabled, catches introduction +The default 'pre-commit' hook, when enabled, catches introduction of lines with trailing whitespaces and aborts the commit when -a such line is found. +such a line is found. commit-msg ---------- @@ -79,8 +78,8 @@ be used to normalize the message into some project standard format (if the project has one). It can also be used to refuse the commit after inspecting the message file. -The default commit-msg hook, when enabled, detects duplicate -Signed-off-by: lines, and aborts the commit when one is found. +The default 'commit-msg' hook, when enabled, detects duplicate +"Signed-off-by" lines, and aborts the commit if one is found. post-commit ----------- @@ -91,23 +90,24 @@ parameter, and is invoked after a commit is made. This hook is meant primarily for notification, and cannot affect the outcome of `git-commit`. -The default post-commit hook, when enabled, demonstrates how to +The default 'post-commit' hook, when enabled, demonstrates how to send out a commit notification e-mail. update ------ This hook is invoked by `git-receive-pack` on the remote repository, -which is happens when a `git push` is done on a local repository. +which happens when a `git push` is done on a local repository. Just before updating the ref on the remote repository, the update hook is invoked. Its exit status determines the success or failure of the ref update. The hook executes once for each ref to be updated, and takes three parameters: - - the name of the ref being updated, - - the old object name stored in the ref, - - and the new objectname to be stored in the ref. + + - the name of the ref being updated, + - the old object name stored in the ref, + - and the new objectname to be stored in the ref. A zero exit from the update hook allows the ref to be updated. Exiting with a non-zero status prevents `git-receive-pack` @@ -126,16 +126,16 @@ Another use suggested on the mailing list is to use this hook to implement access control which is finer grained than the one based on filesystem group. -The standard output of this hook is sent to /dev/null; if you -want to report something to the git-send-pack on the other end, -you can redirect your output to your stderr. +The standard output of this hook is sent to `stderr`, so if you +want to report something to the `git-send-pack` on the other end, +you can simply `echo` your messages. post-update ----------- This hook is invoked by `git-receive-pack` on the remote repository, -which is happens when a `git push` is done on a local repository. +which happens when a `git push` is done on a local repository. It executes on the remote repository once after all the refs have been updated. @@ -145,16 +145,16 @@ name of ref that was actually updated. This hook is meant primarily for notification, and cannot affect the outcome of `git-receive-pack`. -The post-update hook can tell what are the heads that were pushed, +The 'post-update' hook can tell what are the heads that were pushed, but it does not know what their original and updated values are, so it is a poor place to do log old..new. -The default post-update hook, when enabled, runs +When enabled, the default 'post-update' hook runs `git-update-server-info` to keep the information used by dumb -transports (e.g., http) up-to-date. If you are publishing -a git repository that is accessible via http, you should +transports (e.g., HTTP) up-to-date. If you are publishing +a git repository that is accessible via HTTP, you should probably enable this hook. -The standard output of this hook is sent to /dev/null; if you -want to report something to the git-send-pack on the other end, -you can redirect your output to your stderr. +The standard output of this hook is sent to `/dev/null`; if you +want to report something to the `git-send-pack` on the other end, +you can redirect your output to your `stderr`. diff --git a/Documentation/howto/setup-git-server-over-http.txt b/Documentation/howto/setup-git-server-over-http.txt index ba191569af..a202f3a460 100644 --- a/Documentation/howto/setup-git-server-over-http.txt +++ b/Documentation/howto/setup-git-server-over-http.txt @@ -70,7 +70,7 @@ DocumentRoot /where/ever/httpd.conf" to find your root: Initialize a bare repository $ cd my-new-repo.git - $ git --bare init-db + $ git --bare init Change the ownership to your web-server's credentials. Use "grep ^User diff --git a/Documentation/i18n.txt b/Documentation/i18n.txt new file mode 100644 index 0000000000..b4cbb3830e --- /dev/null +++ b/Documentation/i18n.txt @@ -0,0 +1,57 @@ +At the core level, git is character encoding agnostic. + + - The pathnames recorded in the index and in the tree objects + are treated as uninterpreted sequences of non-NUL bytes. + What readdir(2) returns are what are recorded and compared + with the data git keeps track of, which in turn are expected + to be what lstat(2) and creat(2) accepts. There is no such + thing as pathname encoding translation. + + - The contents of the blob objects are uninterpreted sequence + of bytes. There is no encoding translation at the core + level. + + - The commit log messages are uninterpreted sequence of non-NUL + bytes. + +Although we encourage that the commit log messages are encoded +in UTF-8, both the core and git Porcelain are designed not to +force UTF-8 on projects. If all participants of a particular +project find it more convenient to use legacy encodings, git +does not forbid it. However, there are a few things to keep in +mind. + +. `git-commit-tree` (hence, `git-commit` which uses it) issues + an warning if the commit log message given to it does not look + like a valid UTF-8 string, unless you explicitly say your + project uses a legacy encoding. The way to say this is to + have core.commitencoding in `.git/config` file, like this: ++ +------------ +[core] + commitencoding = ISO-8859-1 +------------ ++ +Commit objects created with the above setting record the value +of `core.commitencoding` in its `encoding` header. This is to +help other people who look at them later. Lack of this header +implies that the commit log message is encoded in UTF-8. + +. `git-log`, `git-show` and friends looks at the `encoding` + header of a commit object, and tries to re-code the log + message into UTF-8 unless otherwise specified. You can + specify the desired output encoding with + `core.logoutputencoding` in `.git/config` file, like this: ++ +------------ +[core] + logoutputencoding = ISO-8859-1 +------------ ++ +If you do not have this configuration variable, the value of +`core.commitencoding` is used instead. + +Note that we deliberately chose not to re-code the commit log +message when a commit is made to force UTF-8 at the commit +object level, because re-coding to UTF-8 is not necessarily a +reversible operation. diff --git a/Documentation/install-doc-quick.sh b/Documentation/install-doc-quick.sh new file mode 100755 index 0000000000..a64054948a --- /dev/null +++ b/Documentation/install-doc-quick.sh @@ -0,0 +1,31 @@ +#!/bin/sh +# This requires a branch named in $head +# (usually 'man' or 'html', provided by the git.git repository) +set -e +head="$1" +mandir="$2" +SUBDIRECTORY_OK=t +USAGE='<refname> <target directory>' +. git-sh-setup +export GIT_DIR + +test -z "$mandir" && usage +if ! git-rev-parse --verify "$head^0" >/dev/null; then + echo >&2 "head: $head does not exist in the current repository" + usage +fi + +GIT_INDEX_FILE=`pwd`/.quick-doc.index +export GIT_INDEX_FILE +rm -f "$GIT_INDEX_FILE" +git-read-tree $head +git-checkout-index -a -f --prefix="$mandir"/ + +if test -n "$GZ"; then + cd "$mandir" + for i in `git-ls-tree -r --name-only $head` + do + gzip < $i > $i.gz && rm $i + done +fi +rm -f "$GIT_INDEX_FILE" diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt new file mode 100644 index 0000000000..fb0b0b9582 --- /dev/null +++ b/Documentation/pretty-formats.txt @@ -0,0 +1,85 @@ +--pretty[='<format>']:: + + Pretty-prints the details of a commit. `--pretty` + without an explicit `=<format>` defaults to 'medium'. + If the commit is a merge, and if the pretty-format + is not 'oneline', 'email' or 'raw', an additional line is + inserted before the 'Author:' line. This line begins with + "Merge: " and the sha1s of ancestral commits are printed, + separated by spaces. Note that the listed commits may not + necessarily be the list of the *direct* parent commits if you + have limited your view of history: for example, if you are + only interested in changes related to a certain directory or + file. Here are some additional details for each format: + + * 'oneline' + + <sha1> <title line> ++ +This is designed to be as compact as possible. + + * 'short' + + commit <sha1> + Author: <author> + + <title line> + + * 'medium' + + commit <sha1> + Author: <author> + Date: <date> + + <title line> + + <full commit message> + + * 'full' + + commit <sha1> + Author: <author> + Commit: <committer> + + <title line> + + <full commit message> + + * 'fuller' + + commit <sha1> + Author: <author> + AuthorDate: <date & time> + Commit: <committer> + CommitDate: <date & time> + + <title line> + + <full commit message> + + + * 'email' + + From <sha1> <date> + From: <author> + Date: <date & time> + Subject: [PATCH] <title line> + + full commit message> + + + * 'raw' ++ +The 'raw' format shows the entire commit exactly as +stored in the commit object. Notably, the SHA1s are +displayed in full, regardless of whether --abbrev or +--no-abbrev are used, and 'parents' information show the +true parent commits, without taking grafts nor history +simplification into account. + +--encoding[=<encoding>]:: + The commit objects record the encoding used for the log message + in their encoding header; this option can be used to tell the + command to re-code the commit log message in the encoding + preferred by the user. For non plumbing commands this + defaults to UTF-8. diff --git a/Documentation/pull-fetch-param.txt b/Documentation/pull-fetch-param.txt index e852f41a32..8d4e950abc 100644 --- a/Documentation/pull-fetch-param.txt +++ b/Documentation/pull-fetch-param.txt @@ -39,10 +39,6 @@ checkout -b my-B remote-B`). Run `git fetch` to keep track of the progress of the remote side, and when you see something new on the remote branch, merge it into your development branch with `git pull . remote-B`, while you are on `my-B` branch. -The common `Pull: master:origin` mapping of a remote `master` -branch to a local `origin` branch, which is then merged to a -local development branch, again typically named `master`, is made -when you run `git clone` for you to follow this pattern. + [NOTE] There is a difference between listing multiple <refspec> diff --git a/Documentation/repository-layout.txt b/Documentation/repository-layout.txt index 275d18bb54..0fdd36614d 100644 --- a/Documentation/repository-layout.txt +++ b/Documentation/repository-layout.txt @@ -52,9 +52,20 @@ objects/info/packs:: by default. objects/info/alternates:: - This file records absolute filesystem paths of alternate - object stores that this object store borrows objects - from, one pathname per line. + This file records paths to alternate object stores that + this object store borrows objects from, one pathname per + line. Note that not only native Git tools use it locally, + but the HTTP fetcher also tries to use it remotely; this + will usually work if you have relative paths (relative + to the object database, not to the repository!) in your + alternates file, but it will not work if you use absolute + paths unless the absolute path in filesystem and web URL + is the same. See also 'objects/info/http-alternates'. + +objects/info/http-alternates:: + This file records URLs to alternate object stores that + this object store borrows objects from, to be used when + the repository is fetched over HTTP. refs:: References are stored in subdirectories of this @@ -70,12 +81,16 @@ refs/tags/`name`:: object, or a tag object that points at a commit object). HEAD:: - A symlink of the form `refs/heads/'name'` to point at - the current branch, if exists. It does not mean much if - the repository is not associated with any working tree + A symref (see glossary) to the `refs/heads/` namespace + describing the currently active branch. It does not mean + much if the repository is not associated with any working tree (i.e. a 'bare' repository), but a valid git repository - *must* have such a symlink here. It is legal if the - named branch 'name' does not (yet) exist. + *must* have the HEAD file; some porcelains may use it to + guess the designated "default" branch of the repository + (usually 'master'). It is legal if the named branch + 'name' does not (yet) exist. In some legacy setups, it is + a symbolic link instead of a symref that points at the current + branch. branches:: A slightly deprecated way to store shorthands to be used @@ -87,7 +102,7 @@ branches:: hooks:: Hooks are customization scripts used by various git commands. A handful of sample hooks are installed when - `git init-db` is run, but all of them are disabled by + `git init` is run, but all of them are disabled by default. To enable, they need to be made executable. Read link:hooks.html[hooks] for more details about each hook. diff --git a/Documentation/technical/racy-git.txt b/Documentation/technical/racy-git.txt index 7597d04142..5030d9f2f8 100644 --- a/Documentation/technical/racy-git.txt +++ b/Documentation/technical/racy-git.txt @@ -4,7 +4,7 @@ Use of index and Racy git problem Background ---------- -The index is one of the most important data structure in git. +The index is one of the most important data structures in git. It represents a virtual working tree state by recording list of paths and their object names and serves as a staging area to write out the next tree object to be committed. The state is @@ -16,7 +16,7 @@ virtual working tree state in the index and the files in the working tree. The most obvious case is when the user asks `git diff` (or its low level implementation, `git diff-files`) or `git-ls-files --modified`. In addition, git internally checks -if the files in the working tree is different from what are +if the files in the working tree are different from what are recorded in the index to avoid stomping on local changes in them during patch application, switching branches, and merging. @@ -24,9 +24,9 @@ In order to speed up this comparison between the files in the working tree and the index entries, the index entries record the information obtained from the filesystem via `lstat(2)` system call when they were last updated. When checking if they differ, -git first runs `lstat(2)` on the files and compare the result +git first runs `lstat(2)` on the files and compares the result with this information (this is what was originally done by the -`ce_match_stat()` function, which the current code does in +`ce_match_stat()` function, but the current code does it in `ce_match_stat_basic()` function). If some of these "cached stat information" fields do not match, git can tell that the files are modified without even looking at their contents. @@ -53,8 +53,9 @@ Racy git There is one slight problem with the optimization based on the cached stat information. Consider this sequence: + : modify 'foo' $ git update-index 'foo' - : modify 'foo' in-place without changing its size + : modify 'foo' again, in-place, without changing its size The first `update-index` computes the object name of the contents of file `foo` and updates the index entry for `foo` @@ -62,7 +63,8 @@ along with the `struct stat` information. If the modification that follows it happens very fast so that the file's `st_mtime` timestamp does not change, after this sequence, the cached stat information the index entry records still exactly match what you -can obtain from the filesystem, but the file `foo` is modified. +would see in the filesystem, even though the file `foo` is now +different. This way, git can incorrectly think files in the working tree are unmodified even though they actually are. This is called the "racy git" problem (discovered by Pasky), and the entries @@ -87,7 +89,7 @@ the stat information from updated paths, `st_mtime` timestamp of it is usually the same as or newer than any of the paths the index contains. And no matter how quick the modification that follows `git update-index foo` finishes, the resulting -`st_mtime` timestamp on `foo` cannot get the timestamp earlier +`st_mtime` timestamp on `foo` cannot get a value earlier than the index file. Therefore, index entries that can be racily clean are limited to the ones that have the same timestamp as the index file itself. @@ -111,7 +113,7 @@ value, and falsely clean entry `foo` would not be caught by the timestamp comparison check done with the former logic anymore. The latter makes sure that the cached stat information for `foo` would never match with the file in the working tree, so later -checks by `ce_match_stat_basic()` would report the index entry +checks by `ce_match_stat_basic()` would report that the index entry does not match the file and git does not have to fall back on more expensive `ce_modified_check_fs()`. @@ -155,17 +157,16 @@ of the cached stat information. Avoiding runtime penalty ------------------------ -In order to avoid the above runtime penalty, the recent "master" -branch (post 1.4.2) has a code that makes sure the index file -gets timestamp newer than the youngest files in the index when +In order to avoid the above runtime penalty, post 1.4.2 git used +to have a code that made sure the index file +got timestamp newer than the youngest files in the index when there are many young files with the same timestamp as the resulting index file would otherwise would have by waiting before finishing writing the index file out. -I suspect that in practice the situation where many paths in the -index are all racily clean is quite rare. The only code paths -that can record recent timestamp for large number of paths I -know of are: +I suspected that in practice the situation where many paths in the +index are all racily clean was quite rare. The only code paths +that can record recent timestamp for large number of paths are: . Initial `git add .` of a large project. @@ -188,6 +189,7 @@ youngest file in the working tree. This means that in these cases there actually will not be any racily clean entry in the resulting index. -So in summary I think we should not worry about avoiding the -runtime penalty and get rid of the "wait before finishing -writing" code out. +Based on this discussion, the current code does not use the +"workaround" to avoid the runtime penalty that does not exist in +practice anymore. This was done with commit 0fc82cff on Aug 15, +2006. diff --git a/Documentation/technical/send-pack-pipeline.txt b/Documentation/technical/send-pack-pipeline.txt new file mode 100644 index 0000000000..681efe4219 --- /dev/null +++ b/Documentation/technical/send-pack-pipeline.txt @@ -0,0 +1,63 @@ +git-send-pack +============= + +Overall operation +----------------- + +. Connects to the remote side and invokes git-receive-pack. + +. Learns what refs the remote has and what commit they point at. + Matches them to the refspecs we are pushing. + +. Checks if there are non-fast-forwards. Unlike fetch-pack, + the repository send-pack runs in is supposed to be a superset + of the recipient in fast-forward cases, so there is no need + for want/have exchanges, and fast-forward check can be done + locally. Tell the result to the other end. + +. Calls pack_objects() which generates a packfile and sends it + over to the other end. + +. If the remote side is new enough (v1.1.0 or later), wait for + the unpack and hook status from the other end. + +. Exit with appropriate error codes. + + +Pack_objects pipeline +--------------------- + +This function gets one file descriptor (`fd`) which is either a +socket (over the network) or a pipe (local). What's written to +this fd goes to git-receive-pack to be unpacked. + + send-pack ---> fd ---> receive-pack + +The function pack_objects creates a pipe and then forks. The +forked child execs pack-objects with --revs to receive revision +parameters from its standard input. This process will write the +packfile to the other end. + + send-pack + | + pack_objects() ---> fd ---> receive-pack + | ^ (pipe) + v | + (child) + +The child dup2's to arrange its standard output to go back to +the other end, and read its standard input to come from the +pipe. After that it exec's pack-objects. On the other hand, +the parent process, before starting to feed the child pipeline, +closes the reading side of the pipe and fd to receive-pack. + + send-pack + | + pack_objects(parent) + | + v [0] + pack-objects [0] ---> receive-pack + + +[jc: the pipeline was much more complex and needed documentation before + I understood an earlier bug, but now it is trivial and straightforward.] diff --git a/Documentation/tutorial-2.txt b/Documentation/tutorial-2.txt index 2f4fe1217a..f48894c9a2 100644 --- a/Documentation/tutorial-2.txt +++ b/Documentation/tutorial-2.txt @@ -17,18 +17,19 @@ Let's start a new project and create a small amount of history: ------------------------------------------------ $ mkdir test-project $ cd test-project -$ git init-db -defaulting to local storage area +$ git init +Initialized empty Git repository in .git/ $ echo 'hello world' > file.txt $ git add . $ git commit -a -m "initial commit" -Committing initial tree 92b8b694ffb1675e5975148e1121810081dbdffe +Created initial commit 54196cc2703dc165cbd373a65a4dcf22d50ae7f7 + create mode 100644 file.txt $ echo 'hello world!' >file.txt $ git commit -a -m "add emphasis" +Created commit c4d59f390b9cfd4318117afde11d601c1085f241 ------------------------------------------------ -What are the 40 digits of hex that git responded to the first commit -with? +What are the 40 digits of hex that git responded to the commit with? We saw in part one of the tutorial that commits have names like this. It turns out that every object in the git history is stored under @@ -38,13 +39,25 @@ the same data twice (since identical data is given an identical SHA1 name), and that the contents of a git object will never change (since that would change the object's name as well). +It is expected that the content of the commit object you created while +following the example above generates a different SHA1 hash than +the one shown above because the commit object records the time when +it was created and the name of the person performing the commit. + We can ask git about this particular object with the cat-file -command--just cut-and-paste from the reply to the initial commit, to -save yourself typing all 40 hex digits: +command. Don't copy the 40 hex digits from this example but use those +from your own version. Note that you can shorten it to only a few +characters to save yourself typing all 40 hex digits: ------------------------------------------------ -$ git cat-file -t 92b8b694ffb1675e5975148e1121810081dbdffe -tree +$ git-cat-file -t 54196cc2 +commit +$ git-cat-file commit 54196cc2 +tree 92b8b694ffb1675e5975148e1121810081dbdffe +author J. Bruce Fields <bfields@puzzle.fieldses.org> 1143414668 -0500 +committer J. Bruce Fields <bfields@puzzle.fieldses.org> 1143414668 -0500 + +initial commit ------------------------------------------------ A tree can refer to one or more "blob" objects, each corresponding to @@ -101,8 +114,7 @@ $ find .git/objects/ and the contents of these files is just the compressed data plus a header identifying their length and their type. The type is either a -blob, a tree, a commit, or a tag. We've seen a blob and a tree now, -so next we should look at a commit. +blob, a tree, a commit, or a tag. The simplest commit to find is the HEAD commit, which we can find from .git/HEAD: @@ -341,23 +353,23 @@ situation: ------------------------------------------------ $ git status # -# Updated but not checked in: +# Added but not yet committed: # (will commit) # # new file: closing.txt # # -# Changed but not updated: -# (use git-update-index to mark for commit) +# Changed but not added: +# (use "git add file1 file2" to include for commit) # # modified: file.txt # ------------------------------------------------ Since the current state of closing.txt is cached in the index file, -it is listed as "updated but not checked in". Since file.txt has +it is listed as "added but not yet committed". Since file.txt has changes in the working directory that aren't reflected in the index, -it is marked "changed but not updated". At this point, running "git +it is marked "changed but not added". At this point, running "git commit" would create a commit that added closing.txt (with its new contents), but that didn't modify file.txt. @@ -368,7 +380,7 @@ in the index file is identical to the one in the working directory. In addition to being the staging area for new commits, the index file is also populated from the object database when checking out a branch, and is used to hold the trees involved in a merge operation. -See the link:core-tutorial.txt[core tutorial] and the relevant man +See the link:core-tutorial.html[core tutorial] and the relevant man pages for details. What next? diff --git a/Documentation/tutorial.txt b/Documentation/tutorial.txt index 554ee0af91..d2bf0b905a 100644 --- a/Documentation/tutorial.txt +++ b/Documentation/tutorial.txt @@ -11,6 +11,18 @@ diff" with: $ man git-diff ------------------------------------------------ +It is a good idea to introduce yourself to git before doing any +operation. The easiest way to do so is: + +------------------------------------------------ +$ cat >~/.gitconfig <<\EOF +[user] + name = Your Name Comes Here + email = you@yourdomain.example.com +EOF +------------------------------------------------ + + Importing a new project ----------------------- @@ -20,18 +32,18 @@ can place it under git revision control as follows. ------------------------------------------------ $ tar xzf project.tar.gz $ cd project -$ git init-db +$ git init ------------------------------------------------ Git will reply ------------------------------------------------ -defaulting to local storage area +Initialized empty Git repository in .git/ ------------------------------------------------ You've now initialized the working directory--you may notice a new directory created, named ".git". Tell git that you want it to track -every file under the current directory with +every file under the current directory (note the '.') with: ------------------------------------------------ $ git add . @@ -40,42 +52,90 @@ $ git add . Finally, ------------------------------------------------ -$ git commit -a +$ git commit ------------------------------------------------ will prompt you for a commit message, then record the current state of all the files to the repository. +Making changes +-------------- + Try modifying some files, then run ------------------------------------------------ $ git diff ------------------------------------------------ -to review your changes. When you're done, +to review your changes. When you're done, tell git that you +want the updated contents of these files in the commit and then +make a commit, like this: + +------------------------------------------------ +$ git add file1 file2 file3 +$ git commit +------------------------------------------------ + +This will again prompt your for a message describing the change, and then +record the new versions of the files you listed. + +Alternatively, instead of running `git add` beforehand, you can use ------------------------------------------------ $ git commit -a ------------------------------------------------ -will again prompt your for a message describing the change, and then -record the new versions of the modified files. +which will automatically notice modified (but not new) files. A note on commit messages: Though not required, it's a good idea to begin the commit message with a single short (less than 50 character) line summarizing the change, followed by a blank line and then a more thorough description. Tools that turn commits into email, for -example, use the first line on the Subject line and the rest of the +example, use the first line on the Subject: line and the rest of the commit in the body. -To add a new file, first create the file, then ------------------------------------------------- -$ git add path/to/new/file ------------------------------------------------- +Git tracks content not files +---------------------------- + +With git you have to explicitly "add" all the changed _content_ you +want to commit together. This can be done in a few different ways: + +1) By using 'git add <file_spec>...' + + This can be performed multiple times before a commit. Note that this + is not only for adding new files. Even modified files must be + added to the set of changes about to be committed. The "git status" + command gives you a summary of what is included so far for the + next commit. When done you should use the 'git commit' command to + make it real. + + Note: don't forget to 'add' a file again if you modified it after the + first 'add' and before 'commit'. Otherwise only the previous added + state of that file will be committed. This is because git tracks + content, so what you're really 'add'ing to the commit is the *content* + of the file in the state it is in when you 'add' it. + +2) By using 'git commit -a' directly + + This is a quick way to automatically 'add' the content from all files + that were modified since the previous commit, and perform the actual + commit without having to separately 'add' them beforehand. This will + not add content from new files i.e. files that were never added before. + Those files still have to be added explicitly before performing a + commit. + +But here's a twist. If you do 'git commit <file1> <file2> ...' then only +the changes belonging to those explicitly specified files will be +committed, entirely bypassing the current "added" changes. Those "added" +changes will still remain available for a subsequent commit though. + +However, for normal usage you only have to remember 'git add' + 'git commit' +and/or 'git commit -a'. -then commit as usual. No special command is required when removing a -file; just remove it, then commit. + +Viewing the changelog +--------------------- At any point you can view the history of your changes using @@ -89,6 +149,13 @@ If you also want to see complete diffs at each step, use $ git log -p ------------------------------------------------ +Often the overview of the change is useful to get a feel of +each step + +------------------------------------------------ +$ git log --stat --summary +------------------------------------------------ + Managing branches ----------------- @@ -141,7 +208,7 @@ $ git commit -a ------------------------------------------------ at this point the two branches have diverged, with different changes -made in each. To merge the changes made in the two branches, run +made in each. To merge the changes made in experimental into master, run ------------------------------------------------ $ git pull . experimental @@ -169,6 +236,15 @@ $ gitk will show a nice graphical representation of the resulting history. +At this point you could delete the experimental branch with + +------------------------------------------------ +$ git branch -d experimental +------------------------------------------------ + +This command ensures that the changes in the experimental branch are +already in the current branch. + If you develop on a branch crazy-idea, then regret it, you can always delete the branch with @@ -209,29 +285,28 @@ at /home/bob/myrepo. She does this with: ------------------------------------------------ $ cd /home/alice/project -$ git pull /home/bob/myrepo +$ git pull /home/bob/myrepo master ------------------------------------------------ -This actually pulls changes from the branch in Bob's repository named -"master". Alice could request a different branch by adding the name -of the branch to the end of the git pull command line. +This merges the changes from Bob's "master" branch into Alice's +current branch. If Alice has made her own changes in the meantime, +then she may need to manually fix any conflicts. (Note that the +"master" argument in the above command is actually unnecessary, as it +is the default.) -This merges Bob's changes into her repository; "git log" will -now show the new commits. If Alice has made her own changes in the -meantime, then Bob's changes will be merged in, and she will need to -manually fix any conflicts. +The "pull" command thus performs two operations: it fetches changes +from a remote branch, then merges them into the current branch. -A more cautious Alice might wish to examine Bob's changes before -pulling them. She can do this by creating a temporary branch just -for the purpose of studying Bob's changes: +You can perform the first operation alone using the "git fetch" +command. For example, Alice could create a temporary branch just to +track Bob's changes, without merging them with her own, using: ------------------------------------- $ git fetch /home/bob/myrepo master:bob-incoming ------------------------------------- which fetches the changes from Bob's master branch into a new branch -named bob-incoming. (Unlike git pull, git fetch just fetches a copy -of Bob's line of development without doing any merging). Then +named bob-incoming. Then ------------------------------------- $ git log -p master..bob-incoming @@ -240,8 +315,8 @@ $ git log -p master..bob-incoming shows a list of all the changes that Bob made since he branched from Alice's master branch. -After examining those changes, and possibly fixing things, Alice can -pull the changes into her master branch: +After examining those changes, and possibly fixing things, Alice +could pull the changes into her master branch: ------------------------------------- $ git checkout master @@ -251,6 +326,18 @@ $ git pull . bob-incoming The last command is a pull from the "bob-incoming" branch in Alice's own repository. +Alice could also perform both steps at once with: + +------------------------------------- +$ git pull /home/bob/myrepo master:bob-incoming +------------------------------------- + +This is just like the "git pull /home/bob/myrepo master" that we saw +before, except that it also stores the unmerged changes from bob's +master branch in bob-incoming before merging them into Alice's +current branch. Note that git pull always merges into the current +branch, regardless of what else is given on the commandline. + Later, Bob can update his repo with Alice's latest changes using ------------------------------------- @@ -259,20 +346,25 @@ $ git pull Note that he doesn't need to give the path to Alice's repository; when Bob cloned Alice's repository, git stored the location of her -repository in the file .git/remotes/origin, and that location is used -as the default for pulls. - -Bob may also notice a branch in his repository that he didn't create: +repository in the repository configuration, and that location is +used for pulls: ------------------------------------- -$ git branch -* master - origin +$ git repo-config --get remote.origin.url +/home/bob/myrepo ------------------------------------- -The "origin" branch, which was created automatically by "git clone", -is a pristine copy of Alice's master branch; Bob should never commit -to it. +(The complete configuration created by git-clone is visible using +"git repo-config -l", and the gitlink:git-repo-config[1] man page +explains the meaning of each option.) + +Git also keeps a pristine copy of Alice's master branch under the +name "origin/master": + +------------------------------------- +$ git branch -r + origin/master +------------------------------------- If Bob later decides to work from a different host, he can still perform clones and pulls using the ssh protocol: @@ -312,7 +404,7 @@ commit. $ git show c82a22c39cbc32576f64f5c6b3f24b99ea8149c7 ------------------------------------- -But there other ways to refer to commits. You can use any initial +But there are other ways to refer to commits. You can use any initial part of the name that is long enough to uniquely identify the commit: ------------------------------------- @@ -322,8 +414,8 @@ $ git show HEAD # the tip of the current branch $ git show experimental # the tip of the "experimental" branch ------------------------------------- -Every commit has at least one "parent" commit, which points to the -previous state of the project: +Every commit usually has one "parent" commit +which points to the previous state of the project: ------------------------------------- $ git show HEAD^ # to see the parent of HEAD @@ -441,10 +533,10 @@ of the file: $ git diff v2.5:Makefile HEAD:Makefile.in ------------------------------------- -You can also use "git cat-file -p" to see any such file: +You can also use "git show" to see any such file: ------------------------------------- -$ git cat-file -p v2.5:Makefile +$ git show v2.5:Makefile ------------------------------------- Next Steps diff --git a/Documentation/urls.txt b/Documentation/urls.txt index 26ecba53fb..745f9677d0 100644 --- a/Documentation/urls.txt +++ b/Documentation/urls.txt @@ -40,10 +40,13 @@ In addition to the above, as a short-hand, the name of a file in `$GIT_DIR/remotes` directory can be given; the named file should be in the following format: +------------ URL: one of the above URL format Push: <refspec> Pull: <refspec> +------------ + Then such a short-hand is specified in place of <repository> without <refspec> parameters on the command line, <refspec> specified on `Push:` lines or `Pull:` @@ -51,6 +54,17 @@ lines are used for `git-push` and `git-fetch`/`git-pull`, respectively. Multiple `Push:` and `Pull:` lines may be specified for additional branch mappings. +Or, equivalently, in the `$GIT_DIR/config` (note the use +of `fetch` instead of `Pull:`): + +------------ + [remote "<remote>"] + url = <url> + push = <refspec> + fetch = <refspec> + +------------ + The name of a file in `$GIT_DIR/branches` directory can be specified as an older notation short-hand; the named file should contain a single line, a URL in one of the @@ -60,10 +74,15 @@ name of remote head (URL fragment notation). without the fragment is equivalent to have this in the corresponding file in the `$GIT_DIR/remotes/` directory. +------------ URL: <url> Pull: refs/heads/master:<remote> +------------ + while having `<url>#<head>` is equivalent to +------------ URL: <url> Pull: refs/heads/<head>:<remote> +------------ diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index 14923c973b..8502e4c5b2 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,7 +1,7 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v1.4.2.GIT +DEF_VER=v1.5.0-rc1.GIT LF=' ' @@ -38,6 +38,19 @@ Issues of note: has been actively developed since 1997, and people have moved over to graphical file managers. + - You can use git after building but without installing if you + wanted to. Various git commands need to find other git + commands and scripts to do their work, so you would need to + arrange a few environment variables to tell them that their + friends will be found in your built source area instead of at + their standard installation area. Something like this works + for me: + + GIT_EXEC_PATH=`pwd` + PATH=`pwd`:$PATH + GITPERLLIB=`pwd`/perl/blib/lib + export GIT_EXEC_PATH PATH GITPERLLIB + - Git is reasonably self-sufficient, but does depend on a few external programs and libraries: @@ -59,25 +72,6 @@ Issues of note: - expat library; git-http-push uses it for remote lock management over DAV. Similar to "curl" above, this is optional. - - "GNU diff" to generate patches. Of course, you don't _have_ to - generate patches if you don't want to, but let's face it, you'll - be wanting to. Or why did you get git in the first place? - - Non-GNU versions of the diff/patch programs don't generally support - the unified patch format (which is the one git uses), so you - really do want to get the GNU one. Trust me, you will want to - do that even if it wasn't for git. There's no point in living - in the dark ages any more. - - - "merge", the standard UNIX three-way merge program. It usually - comes with the "rcs" package on most Linux distributions, so if - you have a developer install you probably have it already, but a - "graphical user desktop" install might have left it out. - - You'll only need the merge program if you do development using - git, and if you only use git to track other peoples work you'll - never notice the lack of it. - - "wish", the Tcl/Tk windowing shell is used in gitk to show the history graphically @@ -86,9 +80,6 @@ Issues of note: - "perl" and POSIX-compliant shells are needed to use most of the barebone Porcelainish scripts. - - "python" 2.3 or more recent; if you have 2.3, you may need - to build with "make WITH_OWN_SUBPROCESS_PY=YesPlease". - - Some platform specific issues are dealt with Makefile rules, but depending on your specific installation, you may not have all the libraries/tools needed, or you may have @@ -104,7 +95,7 @@ Issues of note: repository itself. For example, you could: $ mkdir manual && cd manual - $ git init-db + $ git init $ git fetch-pack git://git.kernel.org/pub/scm/git/git.git man html | while read a b do @@ -1,11 +1,6 @@ # The default target of this Makefile is... -all: +all:: -# Define MOZILLA_SHA1 environment variable when running make to make use of -# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast -# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default -# choice) has very fast version optimized for i586. -# # Define NO_OPENSSL environment variable if you do not have OpenSSL. # This also implies MOZILLA_SHA1. # @@ -60,6 +55,11 @@ all: # Define ARM_SHA1 environment variable when running make to make use of # a bundled SHA1 routine optimized for ARM. # +# Define MOZILLA_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast +# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default +# choice) has very fast version optimized for i586. +# # Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin). # # Define NEEDS_LIBICONV if linking with libc is not enough (Darwin). @@ -69,7 +69,14 @@ all: # # Define NO_MMAP if you want to avoid mmap. # -# Define WITH_OWN_SUBPROCESS_PY if you want to use with python 2.3. +# Define NO_PREAD if you have a problem with pread() system call (e.g. +# cygwin.dll before v1.5.22). +# +# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is +# generally faster on your platform than accessing the working directory. +# +# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support +# the executable mode bit, but doesn't really do so. # # Define NO_IPV6 if you lack IPv6 support and getaddrinfo(). # @@ -78,23 +85,22 @@ all: # # Define NO_ICONV if your libc does not properly support iconv. # -# Define NO_ACCURATE_DIFF if your diff program at least sometimes misses -# a missing newline at the end of the file. -# -# Define NO_PYTHON if you want to lose all benefits of the recursive merge. +# Define NO_R_TO_GCC if your gcc does not like "-R/path/lib" that +# tells runtime paths to dynamic libraries; "-Wl,-rpath=/path/lib" +# is used instead. # -# Define COLLISION_CHECK below if you believe that SHA1's -# 1461501637330902918203684832716283019655932542976 hashes do not give you -# sufficient guarantee that no collisions between objects will ever happen. - # Define USE_NSEC below if you want git to care about sub-second file mtimes # and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and # it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely # randomly break unless your underlying filesystem supports those sub-second # times (my ext3 doesn't). - +# # Define USE_STDEV below if you want git to care about the underlying device # change being considered an inode change from the update-cache perspective. +# +# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's +# MakeMaker (e.g. using ActiveState under Cygwin). +# GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE @$(SHELL_PATH) ./GIT-VERSION-GEN @@ -118,7 +124,6 @@ prefix = $(HOME) bindir = $(prefix)/bin gitexecdir = $(bindir) template_dir = $(prefix)/share/git-core/templates/ -GIT_PYTHON_DIR = $(prefix)/share/git-core/python # DESTDIR= # default configuration for gitweb @@ -126,13 +131,18 @@ GITWEB_CONFIG = gitweb_config.perl GITWEB_HOME_LINK_STR = projects GITWEB_SITENAME = GITWEB_PROJECTROOT = /pub/git +GITWEB_EXPORT_OK = +GITWEB_STRICT_EXPORT = GITWEB_BASE_URL = GITWEB_LIST = GITWEB_HOMETEXT = indextext.html GITWEB_CSS = gitweb.css GITWEB_LOGO = git-logo.png +GITWEB_FAVICON = git-favicon.png +GITWEB_SITE_HEADER = +GITWEB_SITE_FOOTER = -export prefix bindir gitexecdir template_dir GIT_PYTHON_DIR +export prefix bindir gitexecdir template_dir CC = gcc AR = ar @@ -148,10 +158,16 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ ### --- END CONFIGURATION SECTION --- +# Those must not be GNU-specific; they are shared with perl/ which may +# be built by a different compiler. (Note that this is an artifact now +# but it still might be nice to keep that distinction.) +BASIC_CFLAGS = +BASIC_LDFLAGS = + SCRIPT_SH = \ - git-bisect.sh git-branch.sh git-checkout.sh \ - git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \ - git-fetch.sh \ + git-bisect.sh git-checkout.sh \ + git-clean.sh git-clone.sh git-commit.sh \ + git-fetch.sh git-gc.sh \ git-ls-remote.sh \ git-merge-one-file.sh git-parse-remote.sh \ git-pull.sh git-rebase.sh \ @@ -164,30 +180,23 @@ SCRIPT_SH = \ git-lost-found.sh git-quiltimport.sh SCRIPT_PERL = \ + git-add--interactive.perl \ git-archimport.perl git-cvsimport.perl git-relink.perl \ - git-shortlog.perl git-rerere.perl \ - git-annotate.perl git-cvsserver.perl \ + git-cvsserver.perl git-remote.perl \ git-svnimport.perl git-cvsexportcommit.perl \ git-send-email.perl git-svn.perl -SCRIPT_PYTHON = \ - git-merge-recursive.py - SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ $(patsubst %.perl,%,$(SCRIPT_PERL)) \ - $(patsubst %.py,%,$(SCRIPT_PYTHON)) \ git-cherry-pick git-status git-instaweb -# The ones that do not have to link with lcrypto, lz nor xdiff. -SIMPLE_PROGRAMS = \ - git-daemon$X - # ... and all the rest that could be moved out of bindir to gitexecdir PROGRAMS = \ git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \ git-hash-object$X git-index-pack$X git-local-fetch$X \ git-fast-import$X \ git-merge-base$X \ + git-daemon$X \ git-merge-index$X git-mktag$X git-mktree$X git-patch-id$X \ git-peek-remote$X git-receive-pack$X \ git-send-pack$X git-shell$X \ @@ -196,19 +205,21 @@ PROGRAMS = \ git-update-server-info$X \ git-upload-pack$X git-verify-pack$X \ git-pack-redundant$X git-var$X \ - git-describe$X git-merge-tree$X git-blame$X git-imap-send$X \ + git-merge-tree$X git-imap-send$X \ + git-merge-recursive$X \ $(EXTRA_PROGRAMS) # Empty... EXTRA_PROGRAMS = BUILT_INS = \ - git-format-patch$X git-show$X git-whatchanged$X \ - git-get-tar-commit-id$X \ + git-format-patch$X git-show$X git-whatchanged$X git-cherry$X \ + git-get-tar-commit-id$X git-init$X \ $(patsubst builtin-%.o,git-%$X,$(BUILTIN_OBJS)) # what 'all' will build and 'install' will install, in gitexecdir -ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) +ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) \ + git-merge-recur$X # Backward compatibility -- to be removed after 1.0 PROGRAMS += git-ssh-pull$X git-ssh-push$X @@ -220,21 +231,18 @@ endif ifndef PERL_PATH PERL_PATH = /usr/bin/perl endif -ifndef PYTHON_PATH - PYTHON_PATH = /usr/bin/python -endif -PYMODULES = \ - gitMergeCommon.py +export PERL_PATH LIB_FILE=libgit.a XDIFF_LIB=xdiff/lib.a LIB_H = \ - blob.h cache.h commit.h csum-file.h delta.h \ - diff.h object.h pack.h pkt-line.h quote.h refs.h \ + archive.h blob.h cache.h commit.h csum-file.h delta.h grep.h \ + diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h sideband.h \ run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \ - tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h + tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h \ + utf8.h DIFF_OBJS = \ diff.o diff-lib.o diffcore-break.o diffcore-order.o \ @@ -243,29 +251,39 @@ DIFF_OBJS = \ LIB_OBJS = \ blob.o commit.o connect.o csum-file.o cache-tree.o base85.o \ - date.o diff-delta.o entry.o exec_cmd.o ident.o lockfile.o \ - object.o pack-check.o patch-delta.o path.o pkt-line.o \ + date.o diff-delta.o entry.o exec_cmd.o ident.o \ + interpolate.o \ + lockfile.o \ + object.o pack-check.o patch-delta.o path.o pkt-line.o sideband.o \ + reachable.o \ quote.o read-cache.o refs.o run-command.o dir.o object-refs.o \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ - fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \ - write_or_die.o \ - alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) + revision.o pager.o tree-walk.o xdiff-interface.o \ + write_or_die.o trace.o list-objects.o grep.o \ + alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \ + color.o wt-status.o archive-zip.o archive-tar.o shallow.o utf8.o BUILTIN_OBJS = \ builtin-add.o \ + builtin-annotate.o \ builtin-apply.o \ + builtin-archive.o \ + builtin-blame.o \ + builtin-branch.o \ builtin-cat-file.o \ builtin-checkout-index.o \ builtin-check-ref-format.o \ builtin-commit-tree.o \ builtin-count-objects.o \ + builtin-describe.o \ builtin-diff.o \ builtin-diff-files.o \ builtin-diff-index.o \ builtin-diff-stages.o \ builtin-diff-tree.o \ builtin-fmt-merge-msg.o \ + builtin-for-each-ref.o \ builtin-grep.o \ builtin-init-db.o \ builtin-log.o \ @@ -273,6 +291,7 @@ BUILTIN_OBJS = \ builtin-ls-tree.o \ builtin-mailinfo.o \ builtin-mailsplit.o \ + builtin-merge-file.o \ builtin-mv.o \ builtin-name-rev.o \ builtin-pack-objects.o \ @@ -280,10 +299,14 @@ BUILTIN_OBJS = \ builtin-prune-packed.o \ builtin-push.o \ builtin-read-tree.o \ + builtin-reflog.o \ builtin-repo-config.o \ + builtin-rerere.o \ builtin-rev-list.o \ builtin-rev-parse.o \ builtin-rm.o \ + builtin-runstatus.o \ + builtin-shortlog.o \ builtin-show-branch.o \ builtin-stripspace.o \ builtin-symbolic-ref.o \ @@ -291,12 +314,14 @@ BUILTIN_OBJS = \ builtin-unpack-objects.o \ builtin-update-index.o \ builtin-update-ref.o \ - builtin-upload-tar.o \ + builtin-upload-archive.o \ builtin-verify-pack.o \ - builtin-write-tree.o + builtin-write-tree.o \ + builtin-show-ref.o \ + builtin-pack-refs.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) -LIBS = $(GITLIBS) -lz +EXTLIBS = -lz # # Platform specific tweaks @@ -316,18 +341,6 @@ ifeq ($(uname_S),Darwin) NEEDS_SSL_WITH_CRYPTO = YesPlease NEEDS_LIBICONV = YesPlease NO_STRLCPY = YesPlease - ifndef NO_FINK - ifeq ($(shell test -d /sw/lib && echo y),y) - ALL_CFLAGS += -I/sw/include - ALL_LDFLAGS += -L/sw/lib - endif - endif - ifndef NO_DARWIN_PORTS - ifeq ($(shell test -d /opt/local/lib && echo y),y) - ALL_CFLAGS += -I/opt/local/include - ALL_LDFLAGS += -L/opt/local/lib - endif - endif endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease @@ -347,7 +360,7 @@ ifeq ($(uname_S),SunOS) endif INSTALL = ginstall TAR = gtar - ALL_CFLAGS += -D__EXTENSIONS__ + BASIC_CFLAGS += -D__EXTENSIONS__ endif ifeq ($(uname_O),Cygwin) NO_D_TYPE_IN_DIRENT = YesPlease @@ -356,30 +369,33 @@ ifeq ($(uname_O),Cygwin) NO_SYMLINK_HEAD = YesPlease NEEDS_LIBICONV = YesPlease NO_C99_FORMAT = YesPlease + NO_FAST_WORKING_DIRECTORY = UnfortunatelyYes + NO_TRUSTABLE_FILEMODE = UnfortunatelyYes # There are conflicting reports about this. # On some boxes NO_MMAP is needed, and not so elsewhere. - # Try uncommenting this if you see things break -- YMMV. - # NO_MMAP = YesPlease + # Try commenting this out if you suspect MMAP is more efficient + NO_MMAP = YesPlease NO_IPV6 = YesPlease X = .exe endif ifeq ($(uname_S),FreeBSD) NEEDS_LIBICONV = YesPlease - ALL_CFLAGS += -I/usr/local/include - ALL_LDFLAGS += -L/usr/local/lib + BASIC_CFLAGS += -I/usr/local/include + BASIC_LDFLAGS += -L/usr/local/lib endif ifeq ($(uname_S),OpenBSD) NO_STRCASESTR = YesPlease NEEDS_LIBICONV = YesPlease - ALL_CFLAGS += -I/usr/local/include - ALL_LDFLAGS += -L/usr/local/lib + BASIC_CFLAGS += -I/usr/local/include + BASIC_LDFLAGS += -L/usr/local/lib endif ifeq ($(uname_S),NetBSD) ifeq ($(shell expr "$(uname_R)" : '[01]\.'),2) NEEDS_LIBICONV = YesPlease endif - ALL_CFLAGS += -I/usr/pkg/include - ALL_LDFLAGS += -L/usr/pkg/lib -Wl,-rpath,/usr/pkg/lib + BASIC_CFLAGS += -I/usr/pkg/include + BASIC_LDFLAGS += -L/usr/pkg/lib + ALL_LDFLAGS += -Wl,-rpath,/usr/pkg/lib endif ifeq ($(uname_S),AIX) NO_STRCASESTR=YesPlease @@ -393,9 +409,9 @@ ifeq ($(uname_S),IRIX64) NO_STRLCPY = YesPlease NO_SOCKADDR_STORAGE=YesPlease SHELL_PATH=/usr/gnu/bin/bash - ALL_CFLAGS += -DPATH_MAX=1024 + BASIC_CFLAGS += -DPATH_MAX=1024 # for now, build 32-bit version - ALL_LDFLAGS += -L/usr/lib32 + BASIC_LDFLAGS += -L/usr/lib32 endif ifneq (,$(findstring arm,$(uname_M))) ARM_SHA1 = YesPlease @@ -404,21 +420,34 @@ endif -include config.mak.autogen -include config.mak -ifdef WITH_OWN_SUBPROCESS_PY - PYMODULES += compat/subprocess.py -else - ifeq ($(NO_PYTHON),) - ifneq ($(shell $(PYTHON_PATH) -c 'import subprocess;print"OK"' 2>/dev/null),OK) - PYMODULES += compat/subprocess.py +ifeq ($(uname_S),Darwin) + ifndef NO_FINK + ifeq ($(shell test -d /sw/lib && echo y),y) + BASIC_CFLAGS += -I/sw/include + BASIC_LDFLAGS += -L/sw/lib + endif + endif + ifndef NO_DARWIN_PORTS + ifeq ($(shell test -d /opt/local/lib && echo y),y) + BASIC_CFLAGS += -I/opt/local/include + BASIC_LDFLAGS += -L/opt/local/lib endif endif endif +ifdef NO_R_TO_GCC_LINKER + # Some gcc does not accept and pass -R to the linker to specify + # the runtime dynamic library path. + CC_LD_DYNPATH = -Wl,-rpath= +else + CC_LD_DYNPATH = -R +endif + ifndef NO_CURL ifdef CURLDIR - # This is still problematic -- gcc does not always want -R. - ALL_CFLAGS += -I$(CURLDIR)/include - CURL_LIBCURL = -L$(CURLDIR)/lib -R$(CURLDIR)/lib -lcurl + # Try "-Wl,-rpath=$(CURLDIR)/lib" in such a case. + BASIC_CFLAGS += -I$(CURLDIR)/include + CURL_LIBCURL = -L$(CURLDIR)/lib $(CC_LD_DYNPATH)$(CURLDIR)/lib -lcurl else CURL_LIBCURL = -lcurl endif @@ -437,14 +466,13 @@ endif ifndef NO_OPENSSL OPENSSL_LIBSSL = -lssl ifdef OPENSSLDIR - # Again this may be problematic -- gcc does not always want -R. - ALL_CFLAGS += -I$(OPENSSLDIR)/include - OPENSSL_LINK = -L$(OPENSSLDIR)/lib -R$(OPENSSLDIR)/lib + BASIC_CFLAGS += -I$(OPENSSLDIR)/include + OPENSSL_LINK = -L$(OPENSSLDIR)/lib $(CC_LD_DYNPATH)$(OPENSSLDIR)/lib else OPENSSL_LINK = endif else - ALL_CFLAGS += -DNO_OPENSSL + BASIC_CFLAGS += -DNO_OPENSSL MOZILLA_SHA1 = 1 OPENSSL_LIBSSL = endif @@ -455,33 +483,30 @@ else endif ifdef NEEDS_LIBICONV ifdef ICONVDIR - # Again this may be problematic -- gcc does not always want -R. - ALL_CFLAGS += -I$(ICONVDIR)/include - ICONV_LINK = -L$(ICONVDIR)/lib -R$(ICONVDIR)/lib + BASIC_CFLAGS += -I$(ICONVDIR)/include + ICONV_LINK = -L$(ICONVDIR)/lib $(CC_LD_DYNPATH)$(ICONVDIR)/lib else ICONV_LINK = endif - LIBS += $(ICONV_LINK) -liconv + EXTLIBS += $(ICONV_LINK) -liconv endif ifdef NEEDS_SOCKET - LIBS += -lsocket - SIMPLE_LIB += -lsocket + EXTLIBS += -lsocket endif ifdef NEEDS_NSL - LIBS += -lnsl - SIMPLE_LIB += -lnsl + EXTLIBS += -lnsl endif ifdef NO_D_TYPE_IN_DIRENT - ALL_CFLAGS += -DNO_D_TYPE_IN_DIRENT + BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT endif ifdef NO_D_INO_IN_DIRENT - ALL_CFLAGS += -DNO_D_INO_IN_DIRENT + BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT endif ifdef NO_C99_FORMAT ALL_CFLAGS += -DNO_C99_FORMAT endif ifdef NO_SYMLINK_HEAD - ALL_CFLAGS += -DNO_SYMLINK_HEAD + BASIC_CFLAGS += -DNO_SYMLINK_HEAD endif ifdef NO_STRCASESTR COMPAT_CFLAGS += -DNO_STRCASESTR @@ -495,7 +520,7 @@ ifdef NO_SETENV COMPAT_CFLAGS += -DNO_SETENV COMPAT_OBJS += compat/setenv.o endif -ifdef NO_SETENV +ifdef NO_UNSETENV COMPAT_CFLAGS += -DNO_UNSETENV COMPAT_OBJS += compat/unsetenv.o endif @@ -503,22 +528,35 @@ ifdef NO_MMAP COMPAT_CFLAGS += -DNO_MMAP COMPAT_OBJS += compat/mmap.o endif +ifdef NO_PREAD + COMPAT_CFLAGS += -DNO_PREAD + COMPAT_OBJS += compat/pread.o +endif +ifdef NO_FAST_WORKING_DIRECTORY + BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY +endif +ifdef NO_TRUSTABLE_FILEMODE + BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE +endif ifdef NO_IPV6 - ALL_CFLAGS += -DNO_IPV6 + BASIC_CFLAGS += -DNO_IPV6 endif ifdef NO_SOCKADDR_STORAGE ifdef NO_IPV6 - ALL_CFLAGS += -Dsockaddr_storage=sockaddr_in + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in else - ALL_CFLAGS += -Dsockaddr_storage=sockaddr_in6 + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6 endif endif ifdef NO_INET_NTOP LIB_OBJS += compat/inet_ntop.o endif +ifdef NO_INET_PTON + LIB_OBJS += compat/inet_pton.o +endif ifdef NO_ICONV - ALL_CFLAGS += -DNO_ICONV + BASIC_CFLAGS += -DNO_ICONV endif ifdef PPC_SHA1 @@ -534,12 +572,12 @@ ifdef MOZILLA_SHA1 LIB_OBJS += mozilla-sha1/sha1.o else SHA1_HEADER = <openssl/sha.h> - LIBS += $(LIB_4_CRYPTO) + EXTLIBS += $(LIB_4_CRYPTO) endif endif endif -ifdef NO_ACCURATE_DIFF - ALL_CFLAGS += -DNO_ACCURATE_DIFF +ifdef NO_PERL_MAKEMAKER + export NO_PERL_MAKEMAKER endif # Shell quote (do not use $(call) to accommodate ancient setups); @@ -554,17 +592,27 @@ prefix_SQ = $(subst ','\'',$(prefix)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) -PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH)) -GIT_PYTHON_DIR_SQ = $(subst ','\'',$(GIT_PYTHON_DIR)) -ALL_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS) +LIBS = $(GITLIBS) $(EXTLIBS) + +BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS) LIB_OBJS += $(COMPAT_OBJS) + +ALL_CFLAGS += $(BASIC_CFLAGS) +ALL_LDFLAGS += $(BASIC_LDFLAGS) + export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir + + ### Build rules -all: $(ALL_PROGRAMS) $(BUILT_INS) git$X gitk gitweb/gitweb.cgi +all:: $(ALL_PROGRAMS) $(BUILT_INS) git$X gitk gitweb/gitweb.cgi +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) git$X)), rm -f '$p';) +endif -all: +all:: + $(MAKE) -C perl PERL_PATH='$(PERL_PATH_SQ)' prefix='$(prefix_SQ)' all $(MAKE) -C templates strip: $(PROGRAMS) git$X @@ -577,6 +625,9 @@ git$X: git.c common-cmds.h $(BUILTIN_OBJS) $(GITLIBS) GIT-CFLAGS help.o: common-cmds.h +git-merge-recur$X: git-merge-recursive$X + rm -f $@ && ln git-merge-recursive$X $@ + $(BUILT_INS): git$X rm -f $@ && ln git$X $@ @@ -590,25 +641,28 @@ $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ - -e 's/@@NO_PYTHON@@/$(NO_PYTHON)/g' \ $@.sh >$@+ chmod +x $@+ mv $@+ $@ -$(patsubst %.perl,%,$(SCRIPT_PERL)) : % : %.perl - rm -f $@ $@+ - sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \ - -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ - $@.perl >$@+ - chmod +x $@+ - mv $@+ $@ +$(patsubst %.perl,%,$(SCRIPT_PERL)): perl/perl.mak + +perl/perl.mak: GIT-CFLAGS + $(MAKE) -C perl PERL_PATH='$(PERL_PATH_SQ)' prefix='$(prefix_SQ)' $(@F) -$(patsubst %.py,%,$(SCRIPT_PYTHON)) : % : %.py GIT-CFLAGS +$(patsubst %.perl,%,$(SCRIPT_PERL)): % : %.perl rm -f $@ $@+ - sed -e '1s|#!.*python|#!$(PYTHON_PATH_SQ)|' \ - -e 's|@@GIT_PYTHON_PATH@@|$(GIT_PYTHON_DIR_SQ)|g' \ + INSTLIBDIR=`$(MAKE) -C perl -s --no-print-directory instlibdir` && \ + sed -e '1{' \ + -e ' s|#!.*perl|#!$(PERL_PATH_SQ)|' \ + -e ' h' \ + -e ' s=.*=use lib (split(/:/, $$ENV{GITPERLLIB} || "@@INSTLIBDIR@@"));=' \ + -e ' H' \ + -e ' x' \ + -e '}' \ + -e 's|@@INSTLIBDIR@@|'"$$INSTLIBDIR"'|g' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ - $@.py >$@+ + $@.perl >$@+ chmod +x $@+ mv $@+ $@ @@ -629,11 +683,16 @@ gitweb/gitweb.cgi: gitweb/gitweb.perl -e 's|++GITWEB_HOME_LINK_STR++|$(GITWEB_HOME_LINK_STR)|g' \ -e 's|++GITWEB_SITENAME++|$(GITWEB_SITENAME)|g' \ -e 's|++GITWEB_PROJECTROOT++|$(GITWEB_PROJECTROOT)|g' \ + -e 's|++GITWEB_EXPORT_OK++|$(GITWEB_EXPORT_OK)|g' \ + -e 's|++GITWEB_STRICT_EXPORT++|$(GITWEB_STRICT_EXPORT)|g' \ -e 's|++GITWEB_BASE_URL++|$(GITWEB_BASE_URL)|g' \ -e 's|++GITWEB_LIST++|$(GITWEB_LIST)|g' \ -e 's|++GITWEB_HOMETEXT++|$(GITWEB_HOMETEXT)|g' \ -e 's|++GITWEB_CSS++|$(GITWEB_CSS)|g' \ -e 's|++GITWEB_LOGO++|$(GITWEB_LOGO)|g' \ + -e 's|++GITWEB_FAVICON++|$(GITWEB_FAVICON)|g' \ + -e 's|++GITWEB_SITE_HEADER++|$(GITWEB_SITE_HEADER)|g' \ + -e 's|++GITWEB_SITE_FOOTER++|$(GITWEB_SITE_FOOTER)|g' \ $< >$@+ chmod +x $@+ mv $@+ $@ @@ -643,7 +702,6 @@ git-instaweb: git-instaweb.sh gitweb/gitweb.cgi gitweb/gitweb.css sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ - -e 's/@@NO_PYTHON@@/$(NO_PYTHON)/g' \ -e '/@@GITWEB_CGI@@/r gitweb/gitweb.cgi' \ -e '/@@GITWEB_CGI@@/d' \ -e '/@@GITWEB_CSS@@/r gitweb/gitweb.css' \ @@ -663,7 +721,6 @@ configure: configure.ac git$X git.spec \ $(patsubst %.sh,%,$(SCRIPT_SH)) \ $(patsubst %.perl,%,$(SCRIPT_PERL)) \ - $(patsubst %.py,%,$(SCRIPT_PYTHON)) \ : GIT-VERSION-FILE %.o: %.c GIT-CFLAGS @@ -687,11 +744,6 @@ endif git-%$X: %.o $(GITLIBS) $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) -$(SIMPLE_PROGRAMS) : $(LIB_FILE) -$(SIMPLE_PROGRAMS) : git-%$X : %.o - $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ - $(LIB_FILE) $(SIMPLE_LIB) - ssh-pull.o: ssh-fetch.c ssh-push.o: ssh-upload.c git-local-fetch$X: fetch.o @@ -718,12 +770,19 @@ $(DIFF_OBJS): diffcore.h $(LIB_FILE): $(LIB_OBJS) rm -f $@ && $(AR) rcs $@ $(LIB_OBJS) -XDIFF_OBJS=xdiff/xdiffi.o xdiff/xprepare.o xdiff/xutils.o xdiff/xemit.o +XDIFF_OBJS=xdiff/xdiffi.o xdiff/xprepare.o xdiff/xutils.o xdiff/xemit.o \ + xdiff/xmerge.o +$(XDIFF_OBJS): xdiff/xinclude.h xdiff/xmacros.h xdiff/xdiff.h xdiff/xtypes.h \ + xdiff/xutils.h xdiff/xprepare.h xdiff/xdiffi.h xdiff/xemit.h $(XDIFF_LIB): $(XDIFF_OBJS) rm -f $@ && $(AR) rcs $@ $(XDIFF_OBJS) +perl/Makefile: perl/Git.pm perl/Makefile.PL GIT-CFLAGS + (cd perl && $(PERL_PATH) Makefile.PL \ + PREFIX='$(prefix_SQ)') + doc: $(MAKE) -C Documentation all @@ -736,7 +795,7 @@ tags: find . -name '*.[hcS]' -print | xargs ctags -a ### Detect prefix changes -TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):$(GIT_PYTHON_DIR_SQ):\ +TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\ $(bindir_SQ):$(gitexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) GIT-CFLAGS: .FORCE-GIT-CFLAGS @@ -752,7 +811,6 @@ GIT-CFLAGS: .FORCE-GIT-CFLAGS # However, the environment gets quite big, and some programs have problems # with that. -export NO_PYTHON export NO_SVN_TESTS test: all @@ -761,8 +819,8 @@ test: all test-date$X: test-date.c date.o ctype.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) test-date.c date.o ctype.o -test-delta$X: test-delta.c diff-delta.o patch-delta.o - $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ +test-delta$X: test-delta.o diff-delta.o patch-delta.o $(GITLIBS) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS) $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) @@ -773,7 +831,7 @@ test-sha1$X: test-sha1.o $(GITLIBS) check-sha1:: test-sha1$X ./test-sha1.sh -check: +check: common-cmds.h for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done @@ -786,8 +844,7 @@ install: all $(INSTALL) $(ALL_PROGRAMS) '$(DESTDIR_SQ)$(gitexecdir_SQ)' $(INSTALL) git$X gitk '$(DESTDIR_SQ)$(bindir_SQ)' $(MAKE) -C templates DESTDIR='$(DESTDIR_SQ)' install - $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' - $(INSTALL) $(PYMODULES) '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' + $(MAKE) -C perl prefix='$(prefix_SQ)' install if test 'z$(bindir_SQ)' != 'z$(gitexecdir_SQ)'; \ then \ ln -f '$(DESTDIR_SQ)$(bindir_SQ)/git$X' \ @@ -796,10 +853,15 @@ install: all '$(DESTDIR_SQ)$(gitexecdir_SQ)/git$X'; \ fi $(foreach p,$(BUILT_INS), rm -f '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p' && ln '$(DESTDIR_SQ)$(gitexecdir_SQ)/git$X' '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p' ;) +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) git$X)), rm -f '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p';) +endif install-doc: $(MAKE) -C Documentation install +quick-install-doc: + $(MAKE) -C Documentation quick-install @@ -810,8 +872,9 @@ git.spec: git.spec.in mv $@+ $@ GIT_TARNAME=git-$(GIT_VERSION) -dist: git.spec git-tar-tree - ./git-tar-tree HEAD^{tree} $(GIT_TARNAME) > $(GIT_TARNAME).tar +dist: git.spec git-archive + ./git-archive --format=tar \ + --prefix=$(GIT_TARNAME)/ HEAD^{tree} > $(GIT_TARNAME).tar @mkdir -p $(GIT_TARNAME) @cp git.spec $(GIT_TARNAME) @echo $(GIT_VERSION) > $(GIT_TARNAME)/version @@ -856,7 +919,8 @@ clean: rm -f $(htmldocs).tar.gz $(manpages).tar.gz rm -f gitweb/gitweb.cgi $(MAKE) -C Documentation/ clean - $(MAKE) -C templates clean + $(MAKE) -C perl clean + $(MAKE) -C templates/ clean $(MAKE) -C t/ clean rm -f GIT-VERSION-FILE GIT-CFLAGS @@ -870,7 +934,7 @@ check-docs:: do \ case "$$v" in \ git-merge-octopus | git-merge-ours | git-merge-recursive | \ - git-merge-resolve | git-merge-stupid | \ + git-merge-resolve | git-merge-stupid | git-merge-recur | \ git-ssh-pull | git-ssh-push ) continue ;; \ esac ; \ test -f "Documentation/$$v.txt" || \ @@ -881,3 +945,8 @@ check-docs:: *) echo "no link: $$v";; \ esac ; \ done | sort + +### Make sure built-ins do not have dups and listed in git.c +# +check-builtins:: + ./check-builtins.sh diff --git a/archive-tar.c b/archive-tar.c new file mode 100644 index 0000000000..7d52a061f4 --- /dev/null +++ b/archive-tar.c @@ -0,0 +1,323 @@ +/* + * Copyright (c) 2005, 2006 Rene Scharfe + */ +#include "cache.h" +#include "commit.h" +#include "strbuf.h" +#include "tar.h" +#include "builtin.h" +#include "archive.h" + +#define RECORDSIZE (512) +#define BLOCKSIZE (RECORDSIZE * 20) + +static char block[BLOCKSIZE]; +static unsigned long offset; + +static time_t archive_time; +static int tar_umask = 002; +static int verbose; + +/* writes out the whole block, but only if it is full */ +static void write_if_needed(void) +{ + if (offset == BLOCKSIZE) { + write_or_die(1, block, BLOCKSIZE); + offset = 0; + } +} + +/* + * queues up writes, so that all our write(2) calls write exactly one + * full block; pads writes to RECORDSIZE + */ +static void write_blocked(const void *data, unsigned long size) +{ + const char *buf = data; + unsigned long tail; + + if (offset) { + unsigned long chunk = BLOCKSIZE - offset; + if (size < chunk) + chunk = size; + memcpy(block + offset, buf, chunk); + size -= chunk; + offset += chunk; + buf += chunk; + write_if_needed(); + } + while (size >= BLOCKSIZE) { + write_or_die(1, buf, BLOCKSIZE); + size -= BLOCKSIZE; + buf += BLOCKSIZE; + } + if (size) { + memcpy(block + offset, buf, size); + offset += size; + } + tail = offset % RECORDSIZE; + if (tail) { + memset(block + offset, 0, RECORDSIZE - tail); + offset += RECORDSIZE - tail; + } + write_if_needed(); +} + +/* + * The end of tar archives is marked by 2*512 nul bytes and after that + * follows the rest of the block (if any). + */ +static void write_trailer(void) +{ + int tail = BLOCKSIZE - offset; + memset(block + offset, 0, tail); + write_or_die(1, block, BLOCKSIZE); + if (tail < 2 * RECORDSIZE) { + memset(block, 0, offset); + write_or_die(1, block, BLOCKSIZE); + } +} + +static void strbuf_append_string(struct strbuf *sb, const char *s) +{ + int slen = strlen(s); + int total = sb->len + slen; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + memcpy(sb->buf + sb->len, s, slen); + sb->len = total; +} + +/* + * pax extended header records have the format "%u %s=%s\n". %u contains + * the size of the whole string (including the %u), the first %s is the + * keyword, the second one is the value. This function constructs such a + * string and appends it to a struct strbuf. + */ +static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, + const char *value, unsigned int valuelen) +{ + char *p; + int len, total, tmp; + + /* "%u %s=%s\n" */ + len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; + for (tmp = len; tmp > 9; tmp /= 10) + len++; + + total = sb->len + len; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + + p = sb->buf; + p += sprintf(p, "%u %s=", len, keyword); + memcpy(p, value, valuelen); + p += valuelen; + *p = '\n'; + sb->len = total; +} + +static unsigned int ustar_header_chksum(const struct ustar_header *header) +{ + char *p = (char *)header; + unsigned int chksum = 0; + while (p < header->chksum) + chksum += *p++; + chksum += sizeof(header->chksum) * ' '; + p += sizeof(header->chksum); + while (p < (char *)header + sizeof(struct ustar_header)) + chksum += *p++; + return chksum; +} + +static int get_path_prefix(const struct strbuf *path, int maxlen) +{ + int i = path->len; + if (i > maxlen) + i = maxlen; + do { + i--; + } while (i > 0 && path->buf[i] != '/'); + return i; +} + +static void write_entry(const unsigned char *sha1, struct strbuf *path, + unsigned int mode, void *buffer, unsigned long size) +{ + struct ustar_header header; + struct strbuf ext_header; + + memset(&header, 0, sizeof(header)); + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + + if (!sha1) { + *header.typeflag = TYPEFLAG_GLOBAL_HEADER; + mode = 0100666; + strcpy(header.name, "pax_global_header"); + } else if (!path) { + *header.typeflag = TYPEFLAG_EXT_HEADER; + mode = 0100666; + sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); + } else { + if (verbose) + fprintf(stderr, "%.*s\n", path->len, path->buf); + if (S_ISDIR(mode)) { + *header.typeflag = TYPEFLAG_DIR; + mode = (mode | 0777) & ~tar_umask; + } else if (S_ISLNK(mode)) { + *header.typeflag = TYPEFLAG_LNK; + mode |= 0777; + } else if (S_ISREG(mode)) { + *header.typeflag = TYPEFLAG_REG; + mode = (mode | ((mode & 0100) ? 0777 : 0666)) & ~tar_umask; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", + mode, sha1_to_hex(sha1)); + return; + } + if (path->len > sizeof(header.name)) { + int plen = get_path_prefix(path, sizeof(header.prefix)); + int rest = path->len - plen - 1; + if (plen > 0 && rest <= sizeof(header.name)) { + memcpy(header.prefix, path->buf, plen); + memcpy(header.name, path->buf + plen + 1, rest); + } else { + sprintf(header.name, "%s.data", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "path", + path->buf, path->len); + } + } else + memcpy(header.name, path->buf, path->len); + } + + if (S_ISLNK(mode) && buffer) { + if (size > sizeof(header.linkname)) { + sprintf(header.linkname, "see %s.paxheader", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "linkpath", + buffer, size); + } else + memcpy(header.linkname, buffer, size); + } + + sprintf(header.mode, "%07o", mode & 07777); + sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); + sprintf(header.mtime, "%011lo", archive_time); + + sprintf(header.uid, "%07o", 0); + sprintf(header.gid, "%07o", 0); + strlcpy(header.uname, "root", sizeof(header.uname)); + strlcpy(header.gname, "root", sizeof(header.gname)); + sprintf(header.devmajor, "%07o", 0); + sprintf(header.devminor, "%07o", 0); + + memcpy(header.magic, "ustar", 6); + memcpy(header.version, "00", 2); + + sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); + + if (ext_header.len > 0) { + write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); + } + write_blocked(&header, sizeof(header)); + if (S_ISREG(mode) && buffer && size > 0) + write_blocked(buffer, size); +} + +static void write_global_extended_header(const unsigned char *sha1) +{ + struct strbuf ext_header; + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); + write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); +} + +static int git_tar_config(const char *var, const char *value) +{ + if (!strcmp(var, "tar.umask")) { + if (!strcmp(value, "user")) { + tar_umask = umask(0); + umask(tar_umask); + } else { + tar_umask = git_config_int(var, value); + } + return 0; + } + return git_default_config(var, value); +} + +static int write_tar_entry(const unsigned char *sha1, + const char *base, int baselen, + const char *filename, unsigned mode, int stage) +{ + static struct strbuf path; + int filenamelen = strlen(filename); + void *buffer; + char type[20]; + unsigned long size; + + if (!path.alloc) { + path.buf = xmalloc(PATH_MAX); + path.alloc = PATH_MAX; + path.len = path.eof = 0; + } + if (path.alloc < baselen + filenamelen) { + free(path.buf); + path.buf = xmalloc(baselen + filenamelen); + path.alloc = baselen + filenamelen; + } + memcpy(path.buf, base, baselen); + memcpy(path.buf + baselen, filename, filenamelen); + path.len = baselen + filenamelen; + if (S_ISDIR(mode)) { + strbuf_append_string(&path, "/"); + buffer = NULL; + size = 0; + } else { + buffer = read_sha1_file(sha1, type, &size); + if (!buffer) + die("cannot read %s", sha1_to_hex(sha1)); + } + + write_entry(sha1, &path, mode, buffer, size); + free(buffer); + + return READ_TREE_RECURSIVE; +} + +int write_tar_archive(struct archiver_args *args) +{ + int plen = args->base ? strlen(args->base) : 0; + + git_config(git_tar_config); + + archive_time = args->time; + verbose = args->verbose; + + if (args->commit_sha1) + write_global_extended_header(args->commit_sha1); + + if (args->base && plen > 0 && args->base[plen - 1] == '/') { + char *base = xstrdup(args->base); + int baselen = strlen(base); + + while (baselen > 0 && base[baselen - 1] == '/') + base[--baselen] = '\0'; + write_tar_entry(args->tree->object.sha1, "", 0, base, 040777, 0); + free(base); + } + read_tree_recursive(args->tree, args->base, plen, 0, + args->pathspec, write_tar_entry); + write_trailer(); + + return 0; +} diff --git a/archive-zip.c b/archive-zip.c new file mode 100644 index 0000000000..f31b8ed823 --- /dev/null +++ b/archive-zip.c @@ -0,0 +1,349 @@ +/* + * Copyright (c) 2006 Rene Scharfe + */ +#include "cache.h" +#include "commit.h" +#include "blob.h" +#include "tree.h" +#include "quote.h" +#include "builtin.h" +#include "archive.h" + +static int verbose; +static int zip_date; +static int zip_time; + +static unsigned char *zip_dir; +static unsigned int zip_dir_size; + +static unsigned int zip_offset; +static unsigned int zip_dir_offset; +static unsigned int zip_dir_entries; + +#define ZIP_DIRECTORY_MIN_SIZE (1024 * 1024) + +struct zip_local_header { + unsigned char magic[4]; + unsigned char version[2]; + unsigned char flags[2]; + unsigned char compression_method[2]; + unsigned char mtime[2]; + unsigned char mdate[2]; + unsigned char crc32[4]; + unsigned char compressed_size[4]; + unsigned char size[4]; + unsigned char filename_length[2]; + unsigned char extra_length[2]; + unsigned char _end[1]; +}; + +struct zip_dir_header { + unsigned char magic[4]; + unsigned char creator_version[2]; + unsigned char version[2]; + unsigned char flags[2]; + unsigned char compression_method[2]; + unsigned char mtime[2]; + unsigned char mdate[2]; + unsigned char crc32[4]; + unsigned char compressed_size[4]; + unsigned char size[4]; + unsigned char filename_length[2]; + unsigned char extra_length[2]; + unsigned char comment_length[2]; + unsigned char disk[2]; + unsigned char attr1[2]; + unsigned char attr2[4]; + unsigned char offset[4]; + unsigned char _end[1]; +}; + +struct zip_dir_trailer { + unsigned char magic[4]; + unsigned char disk[2]; + unsigned char directory_start_disk[2]; + unsigned char entries_on_this_disk[2]; + unsigned char entries[2]; + unsigned char size[4]; + unsigned char offset[4]; + unsigned char comment_length[2]; + unsigned char _end[1]; +}; + +/* + * On ARM, padding is added at the end of the struct, so a simple + * sizeof(struct ...) reports two bytes more than the payload size + * we're interested in. + */ +#define ZIP_LOCAL_HEADER_SIZE offsetof(struct zip_local_header, _end) +#define ZIP_DIR_HEADER_SIZE offsetof(struct zip_dir_header, _end) +#define ZIP_DIR_TRAILER_SIZE offsetof(struct zip_dir_trailer, _end) + +static void copy_le16(unsigned char *dest, unsigned int n) +{ + dest[0] = 0xff & n; + dest[1] = 0xff & (n >> 010); +} + +static void copy_le32(unsigned char *dest, unsigned int n) +{ + dest[0] = 0xff & n; + dest[1] = 0xff & (n >> 010); + dest[2] = 0xff & (n >> 020); + dest[3] = 0xff & (n >> 030); +} + +static void *zlib_deflate(void *data, unsigned long size, + unsigned long *compressed_size) +{ + z_stream stream; + unsigned long maxsize; + void *buffer; + int result; + + memset(&stream, 0, sizeof(stream)); + deflateInit(&stream, zlib_compression_level); + maxsize = deflateBound(&stream, size); + buffer = xmalloc(maxsize); + + stream.next_in = data; + stream.avail_in = size; + stream.next_out = buffer; + stream.avail_out = maxsize; + + do { + result = deflate(&stream, Z_FINISH); + } while (result == Z_OK); + + if (result != Z_STREAM_END) { + free(buffer); + return NULL; + } + + deflateEnd(&stream); + *compressed_size = stream.total_out; + + return buffer; +} + +static char *construct_path(const char *base, int baselen, + const char *filename, int isdir, int *pathlen) +{ + int filenamelen = strlen(filename); + int len = baselen + filenamelen; + char *path, *p; + + if (isdir) + len++; + p = path = xmalloc(len + 1); + + memcpy(p, base, baselen); + p += baselen; + memcpy(p, filename, filenamelen); + p += filenamelen; + if (isdir) + *p++ = '/'; + *p = '\0'; + + *pathlen = len; + + return path; +} + +static int write_zip_entry(const unsigned char *sha1, + const char *base, int baselen, + const char *filename, unsigned mode, int stage) +{ + struct zip_local_header header; + struct zip_dir_header dirent; + unsigned long attr2; + unsigned long compressed_size; + unsigned long uncompressed_size; + unsigned long crc; + unsigned long direntsize; + unsigned long size; + int method; + int result = -1; + int pathlen; + unsigned char *out; + char *path; + char type[20]; + void *buffer = NULL; + void *deflated = NULL; + + crc = crc32(0, NULL, 0); + + path = construct_path(base, baselen, filename, S_ISDIR(mode), &pathlen); + if (verbose) + fprintf(stderr, "%s\n", path); + if (pathlen > 0xffff) { + error("path too long (%d chars, SHA1: %s): %s", pathlen, + sha1_to_hex(sha1), path); + goto out; + } + + if (S_ISDIR(mode)) { + method = 0; + attr2 = 16; + result = READ_TREE_RECURSIVE; + out = NULL; + uncompressed_size = 0; + compressed_size = 0; + } else if (S_ISREG(mode) || S_ISLNK(mode)) { + method = 0; + attr2 = S_ISLNK(mode) ? ((mode | 0777) << 16) : 0; + if (S_ISREG(mode) && zlib_compression_level != 0) + method = 8; + result = 0; + buffer = read_sha1_file(sha1, type, &size); + if (!buffer) + die("cannot read %s", sha1_to_hex(sha1)); + crc = crc32(crc, buffer, size); + out = buffer; + uncompressed_size = size; + compressed_size = size; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", mode, + sha1_to_hex(sha1)); + goto out; + } + + if (method == 8) { + deflated = zlib_deflate(buffer, size, &compressed_size); + if (deflated && compressed_size - 6 < size) { + /* ZLIB --> raw compressed data (see RFC 1950) */ + /* CMF and FLG ... */ + out = (unsigned char *)deflated + 2; + compressed_size -= 6; /* ... and ADLER32 */ + } else { + method = 0; + compressed_size = size; + } + } + + /* make sure we have enough free space in the dictionary */ + direntsize = ZIP_DIR_HEADER_SIZE + pathlen; + while (zip_dir_size < zip_dir_offset + direntsize) { + zip_dir_size += ZIP_DIRECTORY_MIN_SIZE; + zip_dir = xrealloc(zip_dir, zip_dir_size); + } + + copy_le32(dirent.magic, 0x02014b50); + copy_le16(dirent.creator_version, S_ISLNK(mode) ? 0x0317 : 0); + copy_le16(dirent.version, 10); + copy_le16(dirent.flags, 0); + copy_le16(dirent.compression_method, method); + copy_le16(dirent.mtime, zip_time); + copy_le16(dirent.mdate, zip_date); + copy_le32(dirent.crc32, crc); + copy_le32(dirent.compressed_size, compressed_size); + copy_le32(dirent.size, uncompressed_size); + copy_le16(dirent.filename_length, pathlen); + copy_le16(dirent.extra_length, 0); + copy_le16(dirent.comment_length, 0); + copy_le16(dirent.disk, 0); + copy_le16(dirent.attr1, 0); + copy_le32(dirent.attr2, attr2); + copy_le32(dirent.offset, zip_offset); + memcpy(zip_dir + zip_dir_offset, &dirent, ZIP_DIR_HEADER_SIZE); + zip_dir_offset += ZIP_DIR_HEADER_SIZE; + memcpy(zip_dir + zip_dir_offset, path, pathlen); + zip_dir_offset += pathlen; + zip_dir_entries++; + + copy_le32(header.magic, 0x04034b50); + copy_le16(header.version, 10); + copy_le16(header.flags, 0); + copy_le16(header.compression_method, method); + copy_le16(header.mtime, zip_time); + copy_le16(header.mdate, zip_date); + copy_le32(header.crc32, crc); + copy_le32(header.compressed_size, compressed_size); + copy_le32(header.size, uncompressed_size); + copy_le16(header.filename_length, pathlen); + copy_le16(header.extra_length, 0); + write_or_die(1, &header, ZIP_LOCAL_HEADER_SIZE); + zip_offset += ZIP_LOCAL_HEADER_SIZE; + write_or_die(1, path, pathlen); + zip_offset += pathlen; + if (compressed_size > 0) { + write_or_die(1, out, compressed_size); + zip_offset += compressed_size; + } + +out: + free(buffer); + free(deflated); + free(path); + + return result; +} + +static void write_zip_trailer(const unsigned char *sha1) +{ + struct zip_dir_trailer trailer; + + copy_le32(trailer.magic, 0x06054b50); + copy_le16(trailer.disk, 0); + copy_le16(trailer.directory_start_disk, 0); + copy_le16(trailer.entries_on_this_disk, zip_dir_entries); + copy_le16(trailer.entries, zip_dir_entries); + copy_le32(trailer.size, zip_dir_offset); + copy_le32(trailer.offset, zip_offset); + copy_le16(trailer.comment_length, sha1 ? 40 : 0); + + write_or_die(1, zip_dir, zip_dir_offset); + write_or_die(1, &trailer, ZIP_DIR_TRAILER_SIZE); + if (sha1) + write_or_die(1, sha1_to_hex(sha1), 40); +} + +static void dos_time(time_t *time, int *dos_date, int *dos_time) +{ + struct tm *t = localtime(time); + + *dos_date = t->tm_mday + (t->tm_mon + 1) * 32 + + (t->tm_year + 1900 - 1980) * 512; + *dos_time = t->tm_sec / 2 + t->tm_min * 32 + t->tm_hour * 2048; +} + +int write_zip_archive(struct archiver_args *args) +{ + int plen = strlen(args->base); + + dos_time(&args->time, &zip_date, &zip_time); + + zip_dir = xmalloc(ZIP_DIRECTORY_MIN_SIZE); + zip_dir_size = ZIP_DIRECTORY_MIN_SIZE; + verbose = args->verbose; + + if (args->base && plen > 0 && args->base[plen - 1] == '/') { + char *base = xstrdup(args->base); + int baselen = strlen(base); + + while (baselen > 0 && base[baselen - 1] == '/') + base[--baselen] = '\0'; + write_zip_entry(args->tree->object.sha1, "", 0, base, 040777, 0); + free(base); + } + read_tree_recursive(args->tree, args->base, plen, 0, + args->pathspec, write_zip_entry); + write_zip_trailer(args->commit_sha1); + + free(zip_dir); + + return 0; +} + +void *parse_extra_zip_args(int argc, const char **argv) +{ + for (; argc > 0; argc--, argv++) { + const char *arg = argv[0]; + + if (arg[0] == '-' && isdigit(arg[1]) && arg[2] == '\0') + zlib_compression_level = arg[1] - '0'; + else + die("Unknown argument for zip format: %s", arg); + } + return NULL; +} diff --git a/archive.h b/archive.h new file mode 100644 index 0000000000..6838dc788f --- /dev/null +++ b/archive.h @@ -0,0 +1,45 @@ +#ifndef ARCHIVE_H +#define ARCHIVE_H + +#define MAX_EXTRA_ARGS 32 +#define MAX_ARGS (MAX_EXTRA_ARGS + 32) + +struct archiver_args { + const char *base; + struct tree *tree; + const unsigned char *commit_sha1; + time_t time; + const char **pathspec; + unsigned int verbose : 1; + void *extra; +}; + +typedef int (*write_archive_fn_t)(struct archiver_args *); + +typedef void *(*parse_extra_args_fn_t)(int argc, const char **argv); + +struct archiver { + const char *name; + struct archiver_args args; + write_archive_fn_t write_archive; + parse_extra_args_fn_t parse_extra; +}; + +extern int parse_archive_args(int argc, + const char **argv, + struct archiver *ar); + +extern void parse_treeish_arg(const char **treeish, + struct archiver_args *ar_args, + const char *prefix); + +extern void parse_pathspec_arg(const char **pathspec, + struct archiver_args *args); +/* + * Archive-format specific backends. + */ +extern int write_tar_archive(struct archiver_args *); +extern int write_zip_archive(struct archiver_args *); +extern void *parse_extra_zip_args(int argc, const char **argv); + +#endif /* ARCHIVE_H */ diff --git a/blame.c b/blame.c deleted file mode 100644 index 8968046b00..0000000000 --- a/blame.c +++ /dev/null @@ -1,920 +0,0 @@ -/* - * Copyright (C) 2006, Fredrik Kuivinen <freku045@student.liu.se> - */ - -#include <assert.h> -#include <time.h> -#include <sys/time.h> -#include <math.h> - -#include "cache.h" -#include "refs.h" -#include "tag.h" -#include "commit.h" -#include "tree.h" -#include "blob.h" -#include "diff.h" -#include "diffcore.h" -#include "revision.h" -#include "xdiff-interface.h" - -#define DEBUG 0 - -static const char blame_usage[] = "git-blame [-c] [-l] [-t] [-S <revs-file>] [--] file [commit]\n" - " -c, --compatibility Use the same output mode as git-annotate (Default: off)\n" - " -l, --long Show long commit SHA1 (Default: off)\n" - " -t, --time Show raw timestamp (Default: off)\n" - " -S, --revs-file Use revisions from revs-file instead of calling git-rev-list\n" - " -h, --help This message"; - -static struct commit **blame_lines; -static int num_blame_lines; -static char* blame_contents; -static int blame_len; - -struct util_info { - int *line_map; - unsigned char sha1[20]; /* blob sha, not commit! */ - char *buf; - unsigned long size; - int num_lines; - const char* pathname; - - void* topo_data; -}; - -struct chunk { - int off1, len1; /* --- */ - int off2, len2; /* +++ */ -}; - -struct patch { - struct chunk *chunks; - int num; -}; - -static void get_blob(struct commit *commit); - -/* Only used for statistics */ -static int num_get_patch; -static int num_commits; -static int patch_time; - -struct blame_diff_state { - struct xdiff_emit_state xm; - struct patch *ret; -}; - -static void process_u0_diff(void *state_, char *line, unsigned long len) -{ - struct blame_diff_state *state = state_; - struct chunk *chunk; - - if (len < 4 || line[0] != '@' || line[1] != '@') - return; - - if (DEBUG) - printf("chunk line: %.*s", (int)len, line); - state->ret->num++; - state->ret->chunks = xrealloc(state->ret->chunks, - sizeof(struct chunk) * state->ret->num); - chunk = &state->ret->chunks[state->ret->num - 1]; - - assert(!strncmp(line, "@@ -", 4)); - - if (parse_hunk_header(line, len, - &chunk->off1, &chunk->len1, - &chunk->off2, &chunk->len2)) { - state->ret->num--; - return; - } - - if (chunk->len1 == 0) - chunk->off1++; - if (chunk->len2 == 0) - chunk->off2++; - - if (chunk->off1 > 0) - chunk->off1--; - if (chunk->off2 > 0) - chunk->off2--; - - assert(chunk->off1 >= 0); - assert(chunk->off2 >= 0); -} - -static struct patch *get_patch(struct commit *commit, struct commit *other) -{ - struct blame_diff_state state; - xpparam_t xpp; - xdemitconf_t xecfg; - mmfile_t file_c, file_o; - xdemitcb_t ecb; - struct util_info *info_c = (struct util_info *)commit->util; - struct util_info *info_o = (struct util_info *)other->util; - struct timeval tv_start, tv_end; - - get_blob(commit); - file_c.ptr = info_c->buf; - file_c.size = info_c->size; - - get_blob(other); - file_o.ptr = info_o->buf; - file_o.size = info_o->size; - - gettimeofday(&tv_start, NULL); - - xpp.flags = XDF_NEED_MINIMAL; - xecfg.ctxlen = 0; - xecfg.flags = 0; - ecb.outf = xdiff_outf; - ecb.priv = &state; - memset(&state, 0, sizeof(state)); - state.xm.consume = process_u0_diff; - state.ret = xmalloc(sizeof(struct patch)); - state.ret->chunks = NULL; - state.ret->num = 0; - - xdl_diff(&file_c, &file_o, &xpp, &xecfg, &ecb); - - gettimeofday(&tv_end, NULL); - patch_time += 1000000 * (tv_end.tv_sec - tv_start.tv_sec) + - tv_end.tv_usec - tv_start.tv_usec; - - num_get_patch++; - return state.ret; -} - -static void free_patch(struct patch *p) -{ - free(p->chunks); - free(p); -} - -static int get_blob_sha1_internal(const unsigned char *sha1, const char *base, - int baselen, const char *pathname, - unsigned mode, int stage); - -static unsigned char blob_sha1[20]; -static const char* blame_file; -static int get_blob_sha1(struct tree *t, const char *pathname, - unsigned char *sha1) -{ - int i; - const char *pathspec[2]; - blame_file = pathname; - pathspec[0] = pathname; - pathspec[1] = NULL; - hashclr(blob_sha1); - read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal); - - for (i = 0; i < 20; i++) { - if (blob_sha1[i] != 0) - break; - } - - if (i == 20) - return -1; - - hashcpy(sha1, blob_sha1); - return 0; -} - -static int get_blob_sha1_internal(const unsigned char *sha1, const char *base, - int baselen, const char *pathname, - unsigned mode, int stage) -{ - if (S_ISDIR(mode)) - return READ_TREE_RECURSIVE; - - if (strncmp(blame_file, base, baselen) || - strcmp(blame_file + baselen, pathname)) - return -1; - - hashcpy(blob_sha1, sha1); - return -1; -} - -static void get_blob(struct commit *commit) -{ - struct util_info *info = commit->util; - char type[20]; - - if (info->buf) - return; - - info->buf = read_sha1_file(info->sha1, type, &info->size); - - assert(!strcmp(type, blob_type)); -} - -/* For debugging only */ -static void print_patch(struct patch *p) -{ - int i; - printf("Num chunks: %d\n", p->num); - for (i = 0; i < p->num; i++) { - printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1, - p->chunks[i].off2, p->chunks[i].len2); - } -} - -#if DEBUG -/* For debugging only */ -static void print_map(struct commit *cmit, struct commit *other) -{ - struct util_info *util = cmit->util; - struct util_info *util2 = other->util; - - int i; - int max = - util->num_lines > - util2->num_lines ? util->num_lines : util2->num_lines; - int num; - - for (i = 0; i < max; i++) { - printf("i: %d ", i); - num = -1; - - if (i < util->num_lines) { - num = util->line_map[i]; - printf("%d\t", num); - } else - printf("\t"); - - if (i < util2->num_lines) { - int num2 = util2->line_map[i]; - printf("%d\t", num2); - if (num != -1 && num2 != num) - printf("---"); - } else - printf("\t"); - - printf("\n"); - } -} -#endif - -/* p is a patch from commit to other. */ -static void fill_line_map(struct commit *commit, struct commit *other, - struct patch *p) -{ - struct util_info *util = commit->util; - struct util_info *util2 = other->util; - int *map = util->line_map; - int *map2 = util2->line_map; - int cur_chunk = 0; - int i1, i2; - - if (p->num && DEBUG) - print_patch(p); - - if (DEBUG) - printf("num lines 1: %d num lines 2: %d\n", util->num_lines, - util2->num_lines); - - for (i1 = 0, i2 = 0; i1 < util->num_lines; i1++, i2++) { - struct chunk *chunk = NULL; - if (cur_chunk < p->num) - chunk = &p->chunks[cur_chunk]; - - if (chunk && chunk->off1 == i1) { - if (DEBUG && i2 != chunk->off2) - printf("i2: %d off2: %d\n", i2, chunk->off2); - - assert(i2 == chunk->off2); - - i1--; - i2--; - if (chunk->len1 > 0) - i1 += chunk->len1; - - if (chunk->len2 > 0) - i2 += chunk->len2; - - cur_chunk++; - } else { - if (i2 >= util2->num_lines) - break; - - if (map[i1] != map2[i2] && map[i1] != -1) { - if (DEBUG) - printf("map: i1: %d %d %p i2: %d %d %p\n", - i1, map[i1], - (void *) (i1 != -1 ? blame_lines[map[i1]] : NULL), - i2, map2[i2], - (void *) (i2 != -1 ? blame_lines[map2[i2]] : NULL)); - if (map2[i2] != -1 && - blame_lines[map[i1]] && - !blame_lines[map2[i2]]) - map[i1] = map2[i2]; - } - - if (map[i1] == -1 && map2[i2] != -1) - map[i1] = map2[i2]; - } - - if (DEBUG > 1) - printf("l1: %d l2: %d i1: %d i2: %d\n", - map[i1], map2[i2], i1, i2); - } -} - -static int map_line(struct commit *commit, int line) -{ - struct util_info *info = commit->util; - assert(line >= 0 && line < info->num_lines); - return info->line_map[line]; -} - -static struct util_info* get_util(struct commit *commit) -{ - struct util_info *util = commit->util; - - if (util) - return util; - - util = xmalloc(sizeof(struct util_info)); - util->buf = NULL; - util->size = 0; - util->line_map = NULL; - util->num_lines = -1; - util->pathname = NULL; - commit->util = util; - return util; -} - -static int fill_util_info(struct commit *commit) -{ - struct util_info *util = commit->util; - - assert(util); - assert(util->pathname); - - return !!get_blob_sha1(commit->tree, util->pathname, util->sha1); -} - -static void alloc_line_map(struct commit *commit) -{ - struct util_info *util = commit->util; - int i; - - if (util->line_map) - return; - - get_blob(commit); - - util->num_lines = 0; - for (i = 0; i < util->size; i++) { - if (util->buf[i] == '\n') - util->num_lines++; - } - if(util->buf[util->size - 1] != '\n') - util->num_lines++; - - util->line_map = xmalloc(sizeof(int) * util->num_lines); - - for (i = 0; i < util->num_lines; i++) - util->line_map[i] = -1; -} - -static void init_first_commit(struct commit* commit, const char* filename) -{ - struct util_info* util = commit->util; - int i; - - util->pathname = filename; - if (fill_util_info(commit)) - die("fill_util_info failed"); - - alloc_line_map(commit); - - util = commit->util; - - for (i = 0; i < util->num_lines; i++) - util->line_map[i] = i; -} - - -static void process_commits(struct rev_info *rev, const char *path, - struct commit** initial) -{ - int i; - struct util_info* util; - int lines_left; - int *blame_p; - int *new_lines; - int new_lines_len; - - struct commit* commit = get_revision(rev); - assert(commit); - init_first_commit(commit, path); - - util = commit->util; - num_blame_lines = util->num_lines; - blame_lines = xmalloc(sizeof(struct commit *) * num_blame_lines); - blame_contents = util->buf; - blame_len = util->size; - - for (i = 0; i < num_blame_lines; i++) - blame_lines[i] = NULL; - - lines_left = num_blame_lines; - blame_p = xmalloc(sizeof(int) * num_blame_lines); - new_lines = xmalloc(sizeof(int) * num_blame_lines); - do { - struct commit_list *parents; - int num_parents; - struct util_info *util; - - if (DEBUG) - printf("\nProcessing commit: %d %s\n", num_commits, - sha1_to_hex(commit->object.sha1)); - - if (lines_left == 0) - return; - - num_commits++; - memset(blame_p, 0, sizeof(int) * num_blame_lines); - new_lines_len = 0; - num_parents = 0; - for (parents = commit->parents; - parents != NULL; parents = parents->next) - num_parents++; - - if(num_parents == 0) - *initial = commit; - - if (fill_util_info(commit)) - continue; - - alloc_line_map(commit); - util = commit->util; - - for (parents = commit->parents; - parents != NULL; parents = parents->next) { - struct commit *parent = parents->item; - struct patch *patch; - - if (parse_commit(parent) < 0) - die("parse_commit error"); - - if (DEBUG) - printf("parent: %s\n", - sha1_to_hex(parent->object.sha1)); - - if (fill_util_info(parent)) { - num_parents--; - continue; - } - - patch = get_patch(parent, commit); - alloc_line_map(parent); - fill_line_map(parent, commit, patch); - - for (i = 0; i < patch->num; i++) { - int l; - for (l = 0; l < patch->chunks[i].len2; l++) { - int mapped_line = - map_line(commit, patch->chunks[i].off2 + l); - if (mapped_line != -1) { - blame_p[mapped_line]++; - if (blame_p[mapped_line] == num_parents) - new_lines[new_lines_len++] = mapped_line; - } - } - } - free_patch(patch); - } - - if (DEBUG) - printf("parents: %d\n", num_parents); - - for (i = 0; i < new_lines_len; i++) { - int mapped_line = new_lines[i]; - if (blame_lines[mapped_line] == NULL) { - blame_lines[mapped_line] = commit; - lines_left--; - if (DEBUG) - printf("blame: mapped: %d i: %d\n", - mapped_line, i); - } - } - } while ((commit = get_revision(rev)) != NULL); -} - - -static int compare_tree_path(struct rev_info* revs, - struct commit* c1, struct commit* c2) -{ - int ret; - const char* paths[2]; - struct util_info* util = c2->util; - paths[0] = util->pathname; - paths[1] = NULL; - - diff_tree_setup_paths(get_pathspec(revs->prefix, paths), - &revs->pruning); - ret = rev_compare_tree(revs, c1->tree, c2->tree); - diff_tree_release_paths(&revs->pruning); - return ret; -} - - -static int same_tree_as_empty_path(struct rev_info *revs, struct tree* t1, - const char* path) -{ - int ret; - const char* paths[2]; - paths[0] = path; - paths[1] = NULL; - - diff_tree_setup_paths(get_pathspec(revs->prefix, paths), - &revs->pruning); - ret = rev_same_tree_as_empty(revs, t1); - diff_tree_release_paths(&revs->pruning); - return ret; -} - -static const char* find_rename(struct commit* commit, struct commit* parent) -{ - struct util_info* cutil = commit->util; - struct diff_options diff_opts; - const char *paths[1]; - int i; - - if (DEBUG) { - printf("find_rename commit: %s ", - sha1_to_hex(commit->object.sha1)); - puts(sha1_to_hex(parent->object.sha1)); - } - - diff_setup(&diff_opts); - diff_opts.recursive = 1; - diff_opts.detect_rename = DIFF_DETECT_RENAME; - paths[0] = NULL; - diff_tree_setup_paths(paths, &diff_opts); - if (diff_setup_done(&diff_opts) < 0) - die("diff_setup_done failed"); - - diff_tree_sha1(commit->tree->object.sha1, parent->tree->object.sha1, - "", &diff_opts); - diffcore_std(&diff_opts); - - for (i = 0; i < diff_queued_diff.nr; i++) { - struct diff_filepair *p = diff_queued_diff.queue[i]; - - if (p->status == 'R' && !strcmp(p->one->path, cutil->pathname)) { - if (DEBUG) - printf("rename %s -> %s\n", p->one->path, p->two->path); - return p->two->path; - } - } - - return 0; -} - -static void simplify_commit(struct rev_info *revs, struct commit *commit) -{ - struct commit_list **pp, *parent; - - if (!commit->tree) - return; - - if (!commit->parents) { - struct util_info* util = commit->util; - if (!same_tree_as_empty_path(revs, commit->tree, - util->pathname)) - commit->object.flags |= TREECHANGE; - return; - } - - pp = &commit->parents; - while ((parent = *pp) != NULL) { - struct commit *p = parent->item; - - if (p->object.flags & UNINTERESTING) { - pp = &parent->next; - continue; - } - - parse_commit(p); - switch (compare_tree_path(revs, p, commit)) { - case REV_TREE_SAME: - parent->next = NULL; - commit->parents = parent; - get_util(p)->pathname = get_util(commit)->pathname; - return; - - case REV_TREE_NEW: - { - - struct util_info* util = commit->util; - if (revs->remove_empty_trees && - same_tree_as_empty_path(revs, p->tree, - util->pathname)) { - const char* new_name = find_rename(commit, p); - if (new_name) { - struct util_info* putil = get_util(p); - if (!putil->pathname) - putil->pathname = strdup(new_name); - } else { - *pp = parent->next; - continue; - } - } - } - - /* fallthrough */ - case REV_TREE_DIFFERENT: - pp = &parent->next; - if (!get_util(p)->pathname) - get_util(p)->pathname = - get_util(commit)->pathname; - continue; - } - die("bad tree compare for commit %s", - sha1_to_hex(commit->object.sha1)); - } - commit->object.flags |= TREECHANGE; -} - - -struct commit_info -{ - char* author; - char* author_mail; - unsigned long author_time; - char* author_tz; -}; - -static void get_commit_info(struct commit* commit, struct commit_info* ret) -{ - int len; - char* tmp; - static char author_buf[1024]; - - tmp = strstr(commit->buffer, "\nauthor ") + 8; - len = strchr(tmp, '\n') - tmp; - ret->author = author_buf; - memcpy(ret->author, tmp, len); - - tmp = ret->author; - tmp += len; - *tmp = 0; - while(*tmp != ' ') - tmp--; - ret->author_tz = tmp+1; - - *tmp = 0; - while(*tmp != ' ') - tmp--; - ret->author_time = strtoul(tmp, NULL, 10); - - *tmp = 0; - while(*tmp != ' ') - tmp--; - ret->author_mail = tmp + 1; - - *tmp = 0; -} - -static const char* format_time(unsigned long time, const char* tz_str, - int show_raw_time) -{ - static char time_buf[128]; - time_t t = time; - int minutes, tz; - struct tm *tm; - - if (show_raw_time) { - sprintf(time_buf, "%lu %s", time, tz_str); - return time_buf; - } - - tz = atoi(tz_str); - minutes = tz < 0 ? -tz : tz; - minutes = (minutes / 100)*60 + (minutes % 100); - minutes = tz < 0 ? -minutes : minutes; - t = time + minutes * 60; - tm = gmtime(&t); - - strftime(time_buf, sizeof(time_buf), "%Y-%m-%d %H:%M:%S ", tm); - strcat(time_buf, tz_str); - return time_buf; -} - -static void topo_setter(struct commit* c, void* data) -{ - struct util_info* util = c->util; - util->topo_data = data; -} - -static void* topo_getter(struct commit* c) -{ - struct util_info* util = c->util; - return util->topo_data; -} - -static int read_ancestry(const char *graft_file, - unsigned char **start_sha1) -{ - FILE *fp = fopen(graft_file, "r"); - char buf[1024]; - if (!fp) - return -1; - while (fgets(buf, sizeof(buf), fp)) { - /* The format is just "Commit Parent1 Parent2 ...\n" */ - int len = strlen(buf); - struct commit_graft *graft = read_graft_line(buf, len); - register_commit_graft(graft, 0); - if (!*start_sha1) - *start_sha1 = graft->sha1; - } - fclose(fp); - return 0; -} - -int main(int argc, const char **argv) -{ - int i; - struct commit *initial = NULL; - unsigned char sha1[20], *sha1_p = NULL; - - const char *filename = NULL, *commit = NULL; - char filename_buf[256]; - int sha1_len = 8; - int compatibility = 0; - int show_raw_time = 0; - int options = 1; - struct commit* start_commit; - - const char* args[10]; - struct rev_info rev; - - struct commit_info ci; - const char *buf; - int max_digits; - int longest_file, longest_author; - int found_rename; - - const char* prefix = setup_git_directory(); - git_config(git_default_config); - - for(i = 1; i < argc; i++) { - if(options) { - if(!strcmp(argv[i], "-h") || - !strcmp(argv[i], "--help")) - usage(blame_usage); - else if(!strcmp(argv[i], "-l") || - !strcmp(argv[i], "--long")) { - sha1_len = 40; - continue; - } else if(!strcmp(argv[i], "-c") || - !strcmp(argv[i], "--compatibility")) { - compatibility = 1; - continue; - } else if(!strcmp(argv[i], "-t") || - !strcmp(argv[i], "--time")) { - show_raw_time = 1; - continue; - } else if(!strcmp(argv[i], "-S")) { - if (i + 1 < argc && - !read_ancestry(argv[i + 1], &sha1_p)) { - compatibility = 1; - i++; - continue; - } - usage(blame_usage); - } else if(!strcmp(argv[i], "--")) { - options = 0; - continue; - } else if(argv[i][0] == '-') - usage(blame_usage); - else - options = 0; - } - - if(!options) { - if(!filename) - filename = argv[i]; - else if(!commit) - commit = argv[i]; - else - usage(blame_usage); - } - } - - if(!filename) - usage(blame_usage); - if (commit && sha1_p) - usage(blame_usage); - else if(!commit) - commit = "HEAD"; - - if(prefix) - sprintf(filename_buf, "%s%s", prefix, filename); - else - strcpy(filename_buf, filename); - filename = filename_buf; - - if (!sha1_p) { - if (get_sha1(commit, sha1)) - die("get_sha1 failed, commit '%s' not found", commit); - sha1_p = sha1; - } - start_commit = lookup_commit_reference(sha1_p); - get_util(start_commit)->pathname = filename; - if (fill_util_info(start_commit)) { - printf("%s not found in %s\n", filename, commit); - return 1; - } - - - init_revisions(&rev, setup_git_directory()); - rev.remove_empty_trees = 1; - rev.topo_order = 1; - rev.prune_fn = simplify_commit; - rev.topo_setter = topo_setter; - rev.topo_getter = topo_getter; - rev.parents = 1; - rev.limited = 1; - - commit_list_insert(start_commit, &rev.commits); - - args[0] = filename; - args[1] = NULL; - diff_tree_setup_paths(args, &rev.pruning); - prepare_revision_walk(&rev); - process_commits(&rev, filename, &initial); - - buf = blame_contents; - for (max_digits = 1, i = 10; i <= num_blame_lines + 1; max_digits++) - i *= 10; - - longest_file = 0; - longest_author = 0; - found_rename = 0; - for (i = 0; i < num_blame_lines; i++) { - struct commit *c = blame_lines[i]; - struct util_info* u; - if (!c) - c = initial; - u = c->util; - - if (!found_rename && strcmp(filename, u->pathname)) - found_rename = 1; - if (longest_file < strlen(u->pathname)) - longest_file = strlen(u->pathname); - get_commit_info(c, &ci); - if (longest_author < strlen(ci.author)) - longest_author = strlen(ci.author); - } - - for (i = 0; i < num_blame_lines; i++) { - struct commit *c = blame_lines[i]; - struct util_info* u; - - if (!c) - c = initial; - - u = c->util; - get_commit_info(c, &ci); - fwrite(sha1_to_hex(c->object.sha1), sha1_len, 1, stdout); - if(compatibility) { - printf("\t(%10s\t%10s\t%d)", ci.author, - format_time(ci.author_time, ci.author_tz, - show_raw_time), - i+1); - } else { - if (found_rename) - printf(" %-*.*s", longest_file, longest_file, - u->pathname); - printf(" (%-*.*s %10s %*d) ", - longest_author, longest_author, ci.author, - format_time(ci.author_time, ci.author_tz, - show_raw_time), - max_digits, i+1); - } - - if(i == num_blame_lines - 1) { - fwrite(buf, blame_len - (buf - blame_contents), - 1, stdout); - if(blame_contents[blame_len-1] != '\n') - putc('\n', stdout); - } else { - char* next_buf = strchr(buf, '\n') + 1; - fwrite(buf, next_buf - buf, 1, stdout); - buf = next_buf; - } - } - - if (DEBUG) { - printf("num get patch: %d\n", num_get_patch); - printf("num commits: %d\n", num_commits); - printf("patch time: %f\n", patch_time / 1000000.0); - printf("initial: %s\n", sha1_to_hex(initial->object.sha1)); - } - - return 0; -} @@ -1,6 +1,5 @@ #include "cache.h" #include "blob.h" -#include <stdlib.h> const char *blob_type = "blob"; diff --git a/builtin-add.c b/builtin-add.c index 0cb9c81200..e7a1b4d9ab 100644 --- a/builtin-add.c +++ b/builtin-add.c @@ -3,15 +3,14 @@ * * Copyright (C) 2006 Linus Torvalds */ -#include <fnmatch.h> - #include "cache.h" #include "builtin.h" #include "dir.h" +#include "exec_cmd.h" #include "cache-tree.h" static const char builtin_add_usage[] = -"git-add [-n] [-v] <filepattern>..."; +"git-add [-n] [-v] [-f] [--interactive] [--] <filepattern>..."; static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix) { @@ -27,11 +26,9 @@ static void prune_directory(struct dir_struct *dir, const char **pathspec, int p i = dir->nr; while (--i >= 0) { struct dir_entry *entry = *src++; - if (!match_pathspec(pathspec, entry->name, entry->len, prefix, seen)) { - free(entry); - continue; - } - *dst++ = entry; + if (match_pathspec(pathspec, entry->name, entry->len, + prefix, seen)) + *dst++ = entry; } dir->nr = dst - dir->entries; @@ -41,10 +38,20 @@ static void prune_directory(struct dir_struct *dir, const char **pathspec, int p if (seen[i]) continue; - /* Existing file? We must have ignored it */ match = pathspec[i]; - if (!match[0] || !lstat(match, &st)) + if (!match[0]) + continue; + + /* Existing file? We must have ignored it */ + if (!lstat(match, &st)) { + struct dir_entry *ent; + + ent = dir_add_name(dir, match, strlen(match)); + ent->ignored = 1; + if (S_ISDIR(st.st_mode)) + ent->ignored_dir = 1; continue; + } die("pathspec '%s' did not match any files", match); } } @@ -70,7 +77,6 @@ static void fill_directory(struct dir_struct *dir, const char **pathspec) base = ""; if (baselen) { char *common = xmalloc(baselen + 1); - common = xmalloc(baselen + 1); memcpy(common, *pathspec, baselen); common[baselen] = 0; path = base = common; @@ -84,20 +90,34 @@ static void fill_directory(struct dir_struct *dir, const char **pathspec) static struct lock_file lock_file; +static const char ignore_warning[] = +"The following paths are ignored by one of your .gitignore files:\n"; + int cmd_add(int argc, const char **argv, const char *prefix) { int i, newfd; - int verbose = 0, show_only = 0; + int verbose = 0, show_only = 0, ignored_too = 0; const char **pathspec; struct dir_struct dir; + int add_interactive = 0; + + for (i = 1; i < argc; i++) { + if (!strcmp("--interactive", argv[i])) + add_interactive++; + } + if (add_interactive) { + const char *args[] = { "add--interactive", NULL }; + + if (add_interactive != 1 || argc != 2) + die("add --interactive does not take any parameters"); + execv_git_cmd(args); + exit(1); + } git_config(git_default_config); newfd = hold_lock_file_for_update(&lock_file, get_index_file(), 1); - if (read_cache() < 0) - die("index file corrupt"); - for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -111,12 +131,21 @@ int cmd_add(int argc, const char **argv, const char *prefix) show_only = 1; continue; } + if (!strcmp(arg, "-f")) { + ignored_too = 1; + continue; + } if (!strcmp(arg, "-v")) { verbose = 1; continue; } usage(builtin_add_usage); } + if (argc <= i) { + fprintf(stderr, "Nothing specified, nothing added.\n"); + fprintf(stderr, "Maybe you wanted to say 'git add .'?\n"); + return 0; + } pathspec = get_pathspec(prefix, argv + i); fill_directory(&dir, pathspec); @@ -124,6 +153,8 @@ int cmd_add(int argc, const char **argv, const char *prefix) if (show_only) { const char *sep = "", *eof = ""; for (i = 0; i < dir.nr; i++) { + if (!ignored_too && dir.entries[i]->ignored) + continue; printf("%s%s", sep, dir.entries[i]->name); sep = " "; eof = "\n"; @@ -132,6 +163,30 @@ int cmd_add(int argc, const char **argv, const char *prefix) return 0; } + if (read_cache() < 0) + die("index file corrupt"); + + if (!ignored_too) { + int has_ignored = 0; + for (i = 0; i < dir.nr; i++) + if (dir.entries[i]->ignored) + has_ignored = 1; + if (has_ignored) { + fprintf(stderr, ignore_warning); + for (i = 0; i < dir.nr; i++) { + if (!dir.entries[i]->ignored) + continue; + fprintf(stderr, "%s", dir.entries[i]->name); + if (dir.entries[i]->ignored_dir) + fprintf(stderr, " (directory)"); + fputc('\n', stderr); + } + fprintf(stderr, + "Use -f if you really want to add them.\n"); + exit(1); + } + } + for (i = 0; i < dir.nr; i++) add_file_to_index(dir.entries[i]->name, verbose); diff --git a/builtin-annotate.c b/builtin-annotate.c new file mode 100644 index 0000000000..57c46840d5 --- /dev/null +++ b/builtin-annotate.c @@ -0,0 +1,25 @@ +/* + * "git annotate" builtin alias + * + * Copyright (C) 2006 Ryan Anderson + */ +#include "git-compat-util.h" +#include "builtin.h" + +int cmd_annotate(int argc, const char **argv, const char *prefix) +{ + const char **nargv; + int i; + nargv = xmalloc(sizeof(char *) * (argc + 2)); + + nargv[0] = "blame"; + nargv[1] = "-c"; + + for (i = 1; i < argc; i++) { + nargv[i+1] = argv[i]; + } + nargv[argc + 1] = NULL; + + return cmd_blame(argc + 1, nargv, prefix); +} + diff --git a/builtin-apply.c b/builtin-apply.c index 4f0eef0ac3..54fd2cb0c7 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -6,7 +6,6 @@ * This applies patches on top of some (arbitrary) version of the SCM. * */ -#include <fnmatch.h> #include "cache.h" #include "cache-tree.h" #include "quote.h" @@ -27,8 +26,8 @@ static const char *prefix; static int prefix_length = -1; static int newfd = -1; +static int unidiff_zero; static int p_value = 1; -static int allow_binary_replacement; static int check_index; static int write_index; static int cached; @@ -38,12 +37,14 @@ static int summary; static int check; static int apply = 1; static int apply_in_reverse; +static int apply_with_reject; +static int apply_verbosely; static int no_add; static int show_index_info; static int line_termination = '\n'; -static unsigned long p_context = -1; +static unsigned long p_context = ULONG_MAX; static const char apply_usage[] = -"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>..."; +"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [--reverse] [--reject] [--verbose] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>..."; static enum whitespace_eol { nowarn_whitespace, @@ -122,6 +123,7 @@ struct fragment { unsigned long newpos, newlines; const char *patch; int size; + int rejected; struct fragment *next; }; @@ -137,11 +139,15 @@ struct fragment { struct patch { char *new_name, *old_name, *def_name; unsigned int old_mode, new_mode; - int is_rename, is_copy, is_new, is_delete, is_binary; + int is_new, is_delete; /* -1 = unknown, 0 = false, 1 = true */ + int rejected; unsigned long deflate_origlen; int lines_added, lines_deleted; int score; - int inaccurate_eof:1; + unsigned int inaccurate_eof:1; + unsigned int is_binary:1; + unsigned int is_copy:1; + unsigned int is_rename:1; struct fragment *fragments; char *result; unsigned long resultsize; @@ -150,6 +156,24 @@ struct patch { struct patch *next; }; +static void say_patch_name(FILE *output, const char *pre, struct patch *patch, const char *post) +{ + fputs(pre, output); + if (patch->old_name && patch->new_name && + strcmp(patch->old_name, patch->new_name)) { + write_name_quoted(NULL, 0, patch->old_name, 1, output); + fputs(" => ", output); + write_name_quoted(NULL, 0, patch->new_name, 1, output); + } + else { + const char *n = patch->new_name; + if (!n) + n = patch->old_name; + write_name_quoted(NULL, 0, n, 1, output); + } + fputs(post, output); +} + #define CHUNKSIZE (8192) #define SLOP (16) @@ -338,7 +362,7 @@ static int gitdiff_hdrend(const char *line, struct patch *patch) static char *gitdiff_verify_name(const char *line, int isnull, char *orig_name, const char *oldnew) { if (!orig_name && !isnull) - return find_name(line, NULL, 1, 0); + return find_name(line, NULL, 1, TERM_TAB); if (orig_name) { int len; @@ -348,7 +372,7 @@ static char *gitdiff_verify_name(const char *line, int isnull, char *orig_name, len = strlen(name); if (isnull) die("git-apply: bad git-diff - expected /dev/null, got %s on line %d", name, linenr); - another = find_name(line, NULL, 1, 0); + another = find_name(line, NULL, 1, TERM_TAB); if (!another || memcmp(another, name, len)) die("git-apply: bad git-diff - inconsistent %s filename on line %d", oldnew, linenr); free(another); @@ -606,9 +630,7 @@ static char *git_header_name(char *line, int llen) * form. */ for (len = 0 ; ; len++) { - char c = name[len]; - - switch (c) { + switch (name[len]) { default: continue; case '\n': @@ -789,7 +811,8 @@ static int find_header(char *line, unsigned long size, int *hdrsize, struct patc struct fragment dummy; if (parse_fragment_header(line, len, &dummy) < 0) continue; - error("patch fragment without header at line %d: %.*s", linenr, (int)len-1, line); + die("patch fragment without header at line %d: %.*s", + linenr, (int)len-1, line); } if (size < len + 6) @@ -834,12 +857,54 @@ static int find_header(char *line, unsigned long size, int *hdrsize, struct patc return -1; } +static void check_whitespace(const char *line, int len) +{ + const char *err = "Adds trailing whitespace"; + int seen_space = 0; + int i; + + /* + * We know len is at least two, since we have a '+' and we + * checked that the last character was a '\n' before calling + * this function. That is, an addition of an empty line would + * check the '+' here. Sneaky... + */ + if (isspace(line[len-2])) + goto error; + + /* + * Make sure that there is no space followed by a tab in + * indentation. + */ + err = "Space in indent is followed by a tab"; + for (i = 1; i < len; i++) { + if (line[i] == '\t') { + if (seen_space) + goto error; + } + else if (line[i] == ' ') + seen_space = 1; + else + break; + } + return; + + error: + whitespace_error++; + if (squelch_whitespace_errors && + squelch_whitespace_errors < whitespace_error) + ; + else + fprintf(stderr, "%s.\n%s:%d:%.*s\n", + err, patch_input_file, linenr, len-2, line+1); +} + + /* - * Parse a unified diff. Note that this really needs - * to parse each fragment separately, since the only - * way to know the difference between a "---" that is - * part of a patch, and a "---" that starts the next - * patch is to look at the line counts.. + * Parse a unified diff. Note that this really needs to parse each + * fragment separately, since the only way to know the difference + * between a "---" that is part of a patch, and a "---" that starts + * the next patch is to look at the line counts.. */ static int parse_fragment(char *line, unsigned long size, struct patch *patch, struct fragment *fragment) { @@ -856,31 +921,14 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s leading = 0; trailing = 0; - if (patch->is_new < 0) { - patch->is_new = !oldlines; - if (!oldlines) - patch->old_name = NULL; - } - if (patch->is_delete < 0) { - patch->is_delete = !newlines; - if (!newlines) - patch->new_name = NULL; - } - - if (patch->is_new && oldlines) - return error("new file depends on old contents"); - if (patch->is_delete != !newlines) { - if (newlines) - return error("deleted file still has contents"); - fprintf(stderr, "** warning: file %s becomes empty but is not deleted\n", patch->new_name); - } - /* Parse the thing.. */ line += len; size -= len; linenr++; added = deleted = 0; - for (offset = len; size > 0; offset += len, size -= len, line += len, linenr++) { + for (offset = len; + 0 < size; + offset += len, size -= len, line += len, linenr++) { if (!oldlines && !newlines) break; len = linelen(line, size); @@ -889,6 +937,7 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s switch (*line) { default: return -1; + case '\n': /* newer GNU diff, an empty context line */ case ' ': oldlines--; newlines--; @@ -902,25 +951,8 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s trailing = 0; break; case '+': - /* - * We know len is at least two, since we have a '+' and - * we checked that the last character was a '\n' above. - * That is, an addition of an empty line would check - * the '+' here. Sneaky... - */ - if ((new_whitespace != nowarn_whitespace) && - isspace(line[len-2])) { - whitespace_error++; - if (squelch_whitespace_errors && - squelch_whitespace_errors < - whitespace_error) - ; - else { - fprintf(stderr, "Adds trailing whitespace.\n%s:%d:%.*s\n", - patch_input_file, - linenr, len-2, line+1); - } - } + if (new_whitespace != nowarn_whitespace) + check_whitespace(line, len); added++; newlines--; trailing = 0; @@ -953,12 +985,18 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s patch->lines_added += added; patch->lines_deleted += deleted; + + if (0 < patch->is_new && oldlines) + return error("new file depends on old contents"); + if (0 < patch->is_delete && newlines) + return error("deleted file still has contents"); return offset; } static int parse_single_patch(char *line, unsigned long size, struct patch *patch) { unsigned long offset = 0; + unsigned long oldlines = 0, newlines = 0, context = 0; struct fragment **fragp = &patch->fragments; while (size > 4 && !memcmp(line, "@@ -", 4)) { @@ -969,9 +1007,11 @@ static int parse_single_patch(char *line, unsigned long size, struct patch *patc len = parse_fragment(line, size, patch, fragment); if (len <= 0) die("corrupt patch at line %d", linenr); - fragment->patch = line; fragment->size = len; + oldlines += fragment->oldlines; + newlines += fragment->newlines; + context += fragment->leading + fragment->trailing; *fragp = fragment; fragp = &fragment->next; @@ -980,6 +1020,50 @@ static int parse_single_patch(char *line, unsigned long size, struct patch *patc line += len; size -= len; } + + /* + * If something was removed (i.e. we have old-lines) it cannot + * be creation, and if something was added it cannot be + * deletion. However, the reverse is not true; --unified=0 + * patches that only add are not necessarily creation even + * though they do not have any old lines, and ones that only + * delete are not necessarily deletion. + * + * Unfortunately, a real creation/deletion patch do _not_ have + * any context line by definition, so we cannot safely tell it + * apart with --unified=0 insanity. At least if the patch has + * more than one hunk it is not creation or deletion. + */ + if (patch->is_new < 0 && + (oldlines || (patch->fragments && patch->fragments->next))) + patch->is_new = 0; + if (patch->is_delete < 0 && + (newlines || (patch->fragments && patch->fragments->next))) + patch->is_delete = 0; + if (!unidiff_zero || context) { + /* If the user says the patch is not generated with + * --unified=0, or if we have seen context lines, + * then not having oldlines means the patch is creation, + * and not having newlines means the patch is deletion. + */ + if (patch->is_new < 0 && !oldlines) { + patch->is_new = 1; + patch->old_name = NULL; + } + if (patch->is_delete < 0 && !newlines) { + patch->is_delete = 1; + patch->new_name = NULL; + } + } + + if (0 < patch->is_new && oldlines) + die("new file %s depends on old contents", patch->new_name); + if (0 < patch->is_delete && newlines) + die("deleted file %s still has contents", patch->old_name); + if (!patch->is_delete && !newlines && context) + fprintf(stderr, "** warning: file %s becomes empty but " + "is not deleted\n", patch->new_name); + return offset; } @@ -1063,8 +1147,12 @@ static struct fragment *parse_binary_hunk(char **buf_p, llen = linelen(buffer, size); used += llen; linenr++; - if (llen == 1) + if (llen == 1) { + /* consume the blank line */ + buffer++; + size--; break; + } /* Minimum line is "A00000\n" which is 7-byte long, * and the line length must be multiple of 5 plus 2. */ @@ -1107,8 +1195,7 @@ static struct fragment *parse_binary_hunk(char **buf_p, return frag; corrupt: - if (data) - free(data); + free(data); *status_p = -1; error("corrupt binary patch at line %d: %.*s", linenr-1, llen-1, buffer); @@ -1205,14 +1292,12 @@ static int parse_chunk(char *buffer, unsigned long size, struct patch *patch) } } - /* Empty patch cannot be applied if: - * - it is a binary patch and we do not do binary_replace, or - * - text patch without metadata change + /* Empty patch cannot be applied if it is a text patch + * without metadata change. A binary patch appears + * empty to us here. */ if ((apply || check) && - (patch->is_binary - ? !allow_binary_replacement - : !metadata_changes(patch))) + (!patch->is_binary && !metadata_changes(patch))) die("patch with only garbage at line %d", linenr); } @@ -1305,8 +1390,7 @@ static void show_stats(struct patch *patch) printf(" %s%-*s |%5d %.*s%.*s\n", prefix, len, name, patch->lines_added + patch->lines_deleted, add, pluses, del, minuses); - if (qname) - free(qname); + free(qname); } static int read_old_data(struct stat *st, const char *path, void *buf, unsigned long size) @@ -1444,22 +1528,68 @@ static int apply_line(char *output, const char *patch, int plen) { /* plen is number of bytes to be copied from patch, * starting at patch+1 (patch[0] is '+'). Typically - * patch[plen] is '\n'. + * patch[plen] is '\n', unless this is the incomplete + * last line. */ + int i; int add_nl_to_tail = 0; - if ((new_whitespace == strip_whitespace) && - 1 < plen && isspace(patch[plen-1])) { + int fixed = 0; + int last_tab_in_indent = -1; + int last_space_in_indent = -1; + int need_fix_leading_space = 0; + char *buf; + + if ((new_whitespace != strip_whitespace) || !whitespace_error) { + memcpy(output, patch + 1, plen); + return plen; + } + + if (1 < plen && isspace(patch[plen-1])) { if (patch[plen] == '\n') add_nl_to_tail = 1; plen--; while (0 < plen && isspace(patch[plen])) plen--; - applied_after_stripping++; + fixed = 1; } - memcpy(output, patch + 1, plen); + + for (i = 1; i < plen; i++) { + char ch = patch[i]; + if (ch == '\t') { + last_tab_in_indent = i; + if (0 <= last_space_in_indent) + need_fix_leading_space = 1; + } + else if (ch == ' ') + last_space_in_indent = i; + else + break; + } + + buf = output; + if (need_fix_leading_space) { + /* between patch[1..last_tab_in_indent] strip the + * funny spaces, updating them to tab as needed. + */ + for (i = 1; i < last_tab_in_indent; i++, plen--) { + char ch = patch[i]; + if (ch != ' ') + *output++ = ch; + else if ((i % 8) == 0) + *output++ = '\t'; + } + fixed = 1; + i = last_tab_in_indent; + } + else + i = 1; + + memcpy(output, patch + i, plen); if (add_nl_to_tail) output[plen++] = '\n'; - return plen; + if (fixed) + applied_after_stripping++; + return output + plen - buf; } static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, int inaccurate_eof) @@ -1501,6 +1631,14 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i first = '-'; } switch (first) { + case '\n': + /* Newer GNU diff, empty context line */ + if (plen < 0) + /* ... followed by '\No newline'; nothing */ + break; + old[oldsize++] = '\n'; + new[newsize++] = '\n'; + break; case ' ': case '-': memcpy(old + oldsize, patch + 1, plen); @@ -1537,14 +1675,25 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i /* * If we don't have any leading/trailing data in the patch, * we want it to match at the beginning/end of the file. + * + * But that would break if the patch is generated with + * --unified=0; sane people wouldn't do that to cause us + * trouble, but we try to please not so sane ones as well. */ - match_beginning = !leading && (frag->oldpos == 1); - match_end = !trailing; + if (unidiff_zero) { + match_beginning = (!leading && !frag->oldpos); + match_end = 0; + } + else { + match_beginning = !leading && (frag->oldpos == 1); + match_end = !trailing; + } lines = 0; pos = frag->newpos; for (;;) { - offset = find_offset(buf, desc->size, oldlines, oldsize, pos, &lines); + offset = find_offset(buf, desc->size, + oldlines, oldsize, pos, &lines); if (match_end && offset + oldsize != desc->size) offset = -1; if (match_beginning && offset) @@ -1557,8 +1706,10 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i /* Warn if it was necessary to reduce the number * of context lines. */ - if ((leading != frag->leading) || (trailing != frag->trailing)) - fprintf(stderr, "Context reduced to (%ld/%ld) to apply fragment at %d\n", + if ((leading != frag->leading) || + (trailing != frag->trailing)) + fprintf(stderr, "Context reduced to (%ld/%ld)" + " to apply fragment at %d\n", leading, trailing, pos + lines); if (size > alloc) { @@ -1568,7 +1719,9 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i desc->buffer = buf; } desc->size = size; - memmove(buf + offset + newsize, buf + offset + oldsize, size - offset - newsize); + memmove(buf + offset + newsize, + buf + offset + oldsize, + size - offset - newsize); memcpy(buf + offset, newlines, newsize); offset = 0; @@ -1618,7 +1771,7 @@ static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch) "without the reverse hunk to '%s'", patch->new_name ? patch->new_name : patch->old_name); - fragment = fragment; + fragment = fragment->next; } data = (void*) fragment->patch; switch (fragment->binary_patch_method) { @@ -1646,13 +1799,6 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) { const char *name = patch->old_name ? patch->old_name : patch->new_name; unsigned char sha1[20]; - unsigned char hdr[50]; - int hdrlen; - - if (!allow_binary_replacement) - return error("cannot apply binary patch to '%s' " - "without --allow-binary-replacement", - name); /* For safety, we require patch index line to contain * full 40-byte textual SHA1 for old and new, at least for now. @@ -1668,8 +1814,7 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) /* See if the old one matches what the patch * applies to. */ - write_sha1_file_prepare(desc->buffer, desc->size, - blob_type, sha1, hdr, &hdrlen); + hash_sha1_file(desc->buffer, desc->size, blob_type, sha1); if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix)) return error("the patch applies to '%s' (%s), " "which does not match the " @@ -1714,10 +1859,9 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) name); /* verify that the result matches */ - write_sha1_file_prepare(desc->buffer, desc->size, blob_type, - sha1, hdr, &hdrlen); + hash_sha1_file(desc->buffer, desc->size, blob_type, sha1); if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix)) - return error("binary patch to '%s' creates incorrect result", name); + return error("binary patch to '%s' creates incorrect result (expecting %s, got %s)", name, patch->new_sha1_prefix, sha1_to_hex(sha1)); } return 0; @@ -1732,9 +1876,12 @@ static int apply_fragments(struct buffer_desc *desc, struct patch *patch) return apply_binary(desc, patch); while (frag) { - if (apply_one_fragment(desc, frag, patch->inaccurate_eof) < 0) - return error("patch failed: %s:%ld", - name, frag->oldpos); + if (apply_one_fragment(desc, frag, patch->inaccurate_eof)) { + error("patch failed: %s:%ld", name, frag->oldpos); + if (!apply_with_reject) + return -1; + frag->rejected = 1; + } frag = frag->next; } return 0; @@ -1770,8 +1917,9 @@ static int apply_data(struct patch *patch, struct stat *st, struct cache_entry * desc.size = size; desc.alloc = alloc; desc.buffer = buf; + if (apply_fragments(&desc, patch) < 0) - return -1; + return -1; /* note with --reject this succeeds. */ /* NUL terminate the result */ if (desc.alloc <= desc.size) @@ -1781,7 +1929,7 @@ static int apply_data(struct patch *patch, struct stat *st, struct cache_entry * patch->result = desc.buffer; patch->resultsize = desc.size; - if (patch->is_delete && patch->resultsize) + if (0 < patch->is_delete && patch->resultsize) return error("removal patch leaves file contents"); return 0; @@ -1796,6 +1944,7 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) struct cache_entry *ce = NULL; int ok_if_exists; + patch->rejected = 1; /* we will drop this after we succeed */ if (old_name) { int changed = 0; int stat_ret = 0; @@ -1852,7 +2001,7 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) old_name, st_mode, patch->old_mode); } - if (new_name && prev_patch && prev_patch->is_delete && + if (new_name && prev_patch && 0 < prev_patch->is_delete && !strcmp(prev_patch->old_name, new_name)) /* A type-change diff is always split into a patch to * delete old, immediately followed by a patch to @@ -1865,7 +2014,8 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) else ok_if_exists = 0; - if (new_name && (patch->is_new | patch->is_rename | patch->is_copy)) { + if (new_name && + ((0 < patch->is_new) | (0 < patch->is_rename) | patch->is_copy)) { if (check_index && cache_name_pos(new_name, strlen(new_name)) >= 0 && !ok_if_exists) @@ -1882,7 +2032,7 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) return error("%s: %s", new_name, strerror(errno)); } if (!patch->new_mode) { - if (patch->is_new) + if (0 < patch->is_new) patch->new_mode = S_IFREG | 0644; else patch->new_mode = patch->old_mode; @@ -1901,19 +2051,23 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) if (apply_data(patch, &st, ce) < 0) return error("%s: patch does not apply", name); + patch->rejected = 0; return 0; } static int check_patch_list(struct patch *patch) { struct patch *prev_patch = NULL; - int error = 0; + int err = 0; for (prev_patch = NULL; patch ; patch = patch->next) { - error |= check_patch(patch, prev_patch); + if (apply_verbosely) + say_patch_name(stderr, + "Checking patch ", patch, "...\n"); + err |= check_patch(patch, prev_patch); prev_patch = patch; } - return error; + return err; } static void show_index_list(struct patch *list) @@ -1929,7 +2083,7 @@ static void show_index_list(struct patch *list) const char *name; name = patch->old_name ? patch->old_name : patch->new_name; - if (patch->is_new) + if (0 < patch->is_new) sha1_ptr = null_sha1; else if (get_sha1(patch->old_sha1_prefix, sha1)) die("sha1 information is lacking or useless (%s).", @@ -1965,12 +2119,16 @@ static void numstat_patch_list(struct patch *patch) for ( ; patch; patch = patch->next) { const char *name; name = patch->new_name ? patch->new_name : patch->old_name; - printf("%d\t%d\t", patch->lines_added, patch->lines_deleted); + if (patch->is_binary) + printf("-\t-\t"); + else + printf("%d\t%d\t", + patch->lines_added, patch->lines_deleted); if (line_termination && quote_c_style(name, NULL, NULL, 0)) quote_c_style(name, NULL, stdout, 0); else fputs(name, stdout); - putchar('\n'); + putchar(line_termination); } } @@ -2081,8 +2239,19 @@ static void remove_file(struct patch *patch) die("unable to remove %s from index", patch->old_name); cache_tree_invalidate_path(active_cache_tree, patch->old_name); } - if (!cached) - unlink(patch->old_name); + if (!cached) { + if (!unlink(patch->old_name)) { + char *name = xstrdup(patch->old_name); + char *end = strrchr(name, '/'); + while (end) { + *end = 0; + if (rmdir(name)) + break; + end = strrchr(name, '/'); + } + free(name); + } + } } static void add_index_file(const char *path, unsigned mode, void *buf, unsigned long size) @@ -2219,23 +2388,99 @@ static void write_out_one_result(struct patch *patch, int phase) if (phase == 0) remove_file(patch); if (phase == 1) - create_file(patch); + create_file(patch); +} + +static int write_out_one_reject(struct patch *patch) +{ + FILE *rej; + char namebuf[PATH_MAX]; + struct fragment *frag; + int cnt = 0; + + for (cnt = 0, frag = patch->fragments; frag; frag = frag->next) { + if (!frag->rejected) + continue; + cnt++; + } + + if (!cnt) { + if (apply_verbosely) + say_patch_name(stderr, + "Applied patch ", patch, " cleanly.\n"); + return 0; + } + + /* This should not happen, because a removal patch that leaves + * contents are marked "rejected" at the patch level. + */ + if (!patch->new_name) + die("internal error"); + + /* Say this even without --verbose */ + say_patch_name(stderr, "Applying patch ", patch, " with"); + fprintf(stderr, " %d rejects...\n", cnt); + + cnt = strlen(patch->new_name); + if (ARRAY_SIZE(namebuf) <= cnt + 5) { + cnt = ARRAY_SIZE(namebuf) - 5; + fprintf(stderr, + "warning: truncating .rej filename to %.*s.rej", + cnt - 1, patch->new_name); + } + memcpy(namebuf, patch->new_name, cnt); + memcpy(namebuf + cnt, ".rej", 5); + + rej = fopen(namebuf, "w"); + if (!rej) + return error("cannot open %s: %s", namebuf, strerror(errno)); + + /* Normal git tools never deal with .rej, so do not pretend + * this is a git patch by saying --git nor give extended + * headers. While at it, maybe please "kompare" that wants + * the trailing TAB and some garbage at the end of line ;-). + */ + fprintf(rej, "diff a/%s b/%s\t(rejected hunks)\n", + patch->new_name, patch->new_name); + for (cnt = 1, frag = patch->fragments; + frag; + cnt++, frag = frag->next) { + if (!frag->rejected) { + fprintf(stderr, "Hunk #%d applied cleanly.\n", cnt); + continue; + } + fprintf(stderr, "Rejected hunk #%d.\n", cnt); + fprintf(rej, "%.*s", frag->size, frag->patch); + if (frag->patch[frag->size-1] != '\n') + fputc('\n', rej); + } + fclose(rej); + return -1; } -static void write_out_results(struct patch *list, int skipped_patch) +static int write_out_results(struct patch *list, int skipped_patch) { int phase; + int errs = 0; + struct patch *l; if (!list && !skipped_patch) - die("No changes"); + return error("No changes"); for (phase = 0; phase < 2; phase++) { - struct patch *l = list; + l = list; while (l) { - write_out_one_result(l, phase); + if (l->rejected) + errs = 1; + else { + write_out_one_result(l, phase); + if (phase == 1 && write_out_one_reject(l)) + errs = 1; + } l = l->next; } } + return errs; } static struct lock_file lock_file; @@ -2310,11 +2555,13 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) die("unable to read index file"); } - if ((check || apply) && check_patch_list(list) < 0) + if ((check || apply) && + check_patch_list(list) < 0 && + !apply_with_reject) exit(1); - if (apply) - write_out_results(list, skipped_patch); + if (apply && write_out_results(list, skipped_patch)) + exit(1); if (show_index_info) show_index_list(list); @@ -2335,7 +2582,7 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) static int git_apply_config(const char *var, const char *value) { if (!strcmp(var, "apply.whitespace")) { - apply_default_whitespace = strdup(value); + apply_default_whitespace = xstrdup(value); return 0; } return git_default_config(var, value); @@ -2347,6 +2594,7 @@ int cmd_apply(int argc, const char **argv, const char *prefix) int i; int read_stdin = 1; int inaccurate_eof = 0; + int errs = 0; const char *whitespace_option = NULL; @@ -2356,7 +2604,7 @@ int cmd_apply(int argc, const char **argv, const char *prefix) int fd; if (!strcmp(arg, "-")) { - apply_patch(0, "<stdin>", inaccurate_eof); + errs |= apply_patch(0, "<stdin>", inaccurate_eof); read_stdin = 0; continue; } @@ -2382,8 +2630,7 @@ int cmd_apply(int argc, const char **argv, const char *prefix) } if (!strcmp(arg, "--allow-binary-replacement") || !strcmp(arg, "--binary")) { - allow_binary_replacement = 1; - continue; + continue; /* now no-op */ } if (!strcmp(arg, "--numstat")) { apply = 0; @@ -2437,6 +2684,18 @@ int cmd_apply(int argc, const char **argv, const char *prefix) apply_in_reverse = 1; continue; } + if (!strcmp(arg, "--unidiff-zero")) { + unidiff_zero = 1; + continue; + } + if (!strcmp(arg, "--reject")) { + apply = apply_with_reject = apply_verbosely = 1; + continue; + } + if (!strcmp(arg, "--verbose")) { + apply_verbosely = 1; + continue; + } if (!strcmp(arg, "--inaccurate-eof")) { inaccurate_eof = 1; continue; @@ -2457,18 +2716,19 @@ int cmd_apply(int argc, const char **argv, const char *prefix) usage(apply_usage); read_stdin = 0; set_default_whitespace_mode(whitespace_option); - apply_patch(fd, arg, inaccurate_eof); + errs |= apply_patch(fd, arg, inaccurate_eof); close(fd); } set_default_whitespace_mode(whitespace_option); if (read_stdin) - apply_patch(0, "<stdin>", inaccurate_eof); + errs |= apply_patch(0, "<stdin>", inaccurate_eof); if (whitespace_error) { if (squelch_whitespace_errors && squelch_whitespace_errors < whitespace_error) { int squelched = whitespace_error - squelch_whitespace_errors; - fprintf(stderr, "warning: squelched %d whitespace error%s\n", + fprintf(stderr, "warning: squelched %d " + "whitespace error%s\n", squelched, squelched == 1 ? "" : "s"); } @@ -2496,5 +2756,5 @@ int cmd_apply(int argc, const char **argv, const char *prefix) die("Unable to write new index file"); } - return 0; + return !!errs; } diff --git a/builtin-archive.c b/builtin-archive.c new file mode 100644 index 0000000000..32737d3162 --- /dev/null +++ b/builtin-archive.c @@ -0,0 +1,262 @@ +/* + * Copyright (c) 2006 Franck Bui-Huu + * Copyright (c) 2006 Rene Scharfe + */ +#include "cache.h" +#include "builtin.h" +#include "archive.h" +#include "commit.h" +#include "tree-walk.h" +#include "exec_cmd.h" +#include "pkt-line.h" +#include "sideband.h" + +static const char archive_usage[] = \ +"git-archive --format=<fmt> [--prefix=<prefix>/] [--verbose] [<extra>] <tree-ish> [path...]"; + +static struct archiver_desc +{ + const char *name; + write_archive_fn_t write_archive; + parse_extra_args_fn_t parse_extra; +} archivers[] = { + { "tar", write_tar_archive, NULL }, + { "zip", write_zip_archive, parse_extra_zip_args }, +}; + +static int run_remote_archiver(const char *remote, int argc, + const char **argv) +{ + char *url, buf[LARGE_PACKET_MAX]; + int fd[2], i, len, rv; + pid_t pid; + const char *exec = "git-upload-archive"; + int exec_at = 0; + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strncmp("--exec=", arg, 7)) { + if (exec_at) + die("multiple --exec specified"); + exec = arg + 7; + exec_at = i; + break; + } + } + + url = xstrdup(remote); + pid = git_connect(fd, url, exec); + if (pid < 0) + return pid; + + for (i = 1; i < argc; i++) { + if (i == exec_at) + continue; + packet_write(fd[1], "argument %s\n", argv[i]); + } + packet_flush(fd[1]); + + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (!len) + die("git-archive: expected ACK/NAK, got EOF"); + if (buf[len-1] == '\n') + buf[--len] = 0; + if (strcmp(buf, "ACK")) { + if (len > 5 && !strncmp(buf, "NACK ", 5)) + die("git-archive: NACK %s", buf + 5); + die("git-archive: protocol error"); + } + + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (len) + die("git-archive: expected a flush"); + + /* Now, start reading from fd[0] and spit it out to stdout */ + rv = recv_sideband("archive", fd[0], 1, 2); + close(fd[0]); + rv |= finish_connect(pid); + + return !!rv; +} + +static int init_archiver(const char *name, struct archiver *ar) +{ + int rv = -1, i; + + for (i = 0; i < ARRAY_SIZE(archivers); i++) { + if (!strcmp(name, archivers[i].name)) { + memset(ar, 0, sizeof(*ar)); + ar->name = archivers[i].name; + ar->write_archive = archivers[i].write_archive; + ar->parse_extra = archivers[i].parse_extra; + rv = 0; + break; + } + } + return rv; +} + +void parse_pathspec_arg(const char **pathspec, struct archiver_args *ar_args) +{ + ar_args->pathspec = get_pathspec(ar_args->base, pathspec); +} + +void parse_treeish_arg(const char **argv, struct archiver_args *ar_args, + const char *prefix) +{ + const char *name = argv[0]; + const unsigned char *commit_sha1; + time_t archive_time; + struct tree *tree; + struct commit *commit; + unsigned char sha1[20]; + + if (get_sha1(name, sha1)) + die("Not a valid object name"); + + commit = lookup_commit_reference_gently(sha1, 1); + if (commit) { + commit_sha1 = commit->object.sha1; + archive_time = commit->date; + } else { + commit_sha1 = NULL; + archive_time = time(NULL); + } + + tree = parse_tree_indirect(sha1); + if (tree == NULL) + die("not a tree object"); + + if (prefix) { + unsigned char tree_sha1[20]; + unsigned int mode; + int err; + + err = get_tree_entry(tree->object.sha1, prefix, + tree_sha1, &mode); + if (err || !S_ISDIR(mode)) + die("current working directory is untracked"); + + tree = parse_tree_indirect(tree_sha1); + } + ar_args->tree = tree; + ar_args->commit_sha1 = commit_sha1; + ar_args->time = archive_time; +} + +int parse_archive_args(int argc, const char **argv, struct archiver *ar) +{ + const char *extra_argv[MAX_EXTRA_ARGS]; + int extra_argc = 0; + const char *format = NULL; /* might want to default to "tar" */ + const char *base = ""; + int verbose = 0; + int i; + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (!strcmp(arg, "--list") || !strcmp(arg, "-l")) { + for (i = 0; i < ARRAY_SIZE(archivers); i++) + printf("%s\n", archivers[i].name); + exit(0); + } + if (!strcmp(arg, "--verbose") || !strcmp(arg, "-v")) { + verbose = 1; + continue; + } + if (!strncmp(arg, "--format=", 9)) { + format = arg + 9; + continue; + } + if (!strncmp(arg, "--prefix=", 9)) { + base = arg + 9; + continue; + } + if (!strcmp(arg, "--")) { + i++; + break; + } + if (arg[0] == '-') { + if (extra_argc > MAX_EXTRA_ARGS - 1) + die("Too many extra options"); + extra_argv[extra_argc++] = arg; + continue; + } + break; + } + + /* We need at least one parameter -- tree-ish */ + if (argc - 1 < i) + usage(archive_usage); + if (!format) + die("You must specify an archive format"); + if (init_archiver(format, ar) < 0) + die("Unknown archive format '%s'", format); + + if (extra_argc) { + if (!ar->parse_extra) + die("'%s' format does not handle %s", + ar->name, extra_argv[0]); + ar->args.extra = ar->parse_extra(extra_argc, extra_argv); + } + ar->args.verbose = verbose; + ar->args.base = base; + + return i; +} + +static const char *extract_remote_arg(int *ac, const char **av) +{ + int ix, iy, cnt = *ac; + int no_more_options = 0; + const char *remote = NULL; + + for (ix = iy = 1; ix < cnt; ix++) { + const char *arg = av[ix]; + if (!strcmp(arg, "--")) + no_more_options = 1; + if (!no_more_options) { + if (!strncmp(arg, "--remote=", 9)) { + if (remote) + die("Multiple --remote specified"); + remote = arg + 9; + continue; + } + if (arg[0] != '-') + no_more_options = 1; + } + if (ix != iy) + av[iy] = arg; + iy++; + } + if (remote) { + av[--cnt] = NULL; + *ac = cnt; + } + return remote; +} + +int cmd_archive(int argc, const char **argv, const char *prefix) +{ + struct archiver ar; + int tree_idx; + const char *remote = NULL; + + remote = extract_remote_arg(&argc, argv); + if (remote) + return run_remote_archiver(remote, argc, argv); + + setvbuf(stderr, NULL, _IOLBF, BUFSIZ); + + memset(&ar, 0, sizeof(ar)); + tree_idx = parse_archive_args(argc, argv, &ar); + if (prefix == NULL) + prefix = setup_git_directory(); + + argv += tree_idx; + parse_treeish_arg(argv, &ar.args, prefix); + parse_pathspec_arg(argv + 1, &ar.args); + + return ar.write_archive(&ar.args); +} diff --git a/builtin-blame.c b/builtin-blame.c new file mode 100644 index 0000000000..4a1accf13c --- /dev/null +++ b/builtin-blame.c @@ -0,0 +1,1929 @@ +/* + * Pickaxe + * + * Copyright (c) 2006, Junio C Hamano + */ + +#include "cache.h" +#include "builtin.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree-walk.h" +#include "diff.h" +#include "diffcore.h" +#include "revision.h" +#include "xdiff-interface.h" + +static char blame_usage[] = +"git-blame [-c] [-l] [-t] [-f] [-n] [-p] [-L n,m] [-S <revs-file>] [-M] [-C] [-C] [commit] [--] file\n" +" -c, --compatibility Use the same output mode as git-annotate (Default: off)\n" +" -b Show blank SHA-1 for boundary commits (Default: off)\n" +" -l, --long Show long commit SHA1 (Default: off)\n" +" --root Do not treat root commits as boundaries (Default: off)\n" +" -t, --time Show raw timestamp (Default: off)\n" +" -f, --show-name Show original filename (Default: auto)\n" +" -n, --show-number Show original linenumber (Default: off)\n" +" -p, --porcelain Show in a format designed for machine consumption\n" +" -L n,m Process only line range n,m, counting from 1\n" +" -M, -C Find line movements within and across files\n" +" -S revs-file Use revisions from revs-file instead of calling git-rev-list\n"; + +static int longest_file; +static int longest_author; +static int max_orig_digits; +static int max_digits; +static int max_score_digits; +static int show_root; +static int blank_boundary; + +#ifndef DEBUG +#define DEBUG 0 +#endif + +/* stats */ +static int num_read_blob; +static int num_get_patch; +static int num_commits; + +#define PICKAXE_BLAME_MOVE 01 +#define PICKAXE_BLAME_COPY 02 +#define PICKAXE_BLAME_COPY_HARDER 04 + +/* + * blame for a blame_entry with score lower than these thresholds + * is not passed to the parent using move/copy logic. + */ +static unsigned blame_move_score; +static unsigned blame_copy_score; +#define BLAME_DEFAULT_MOVE_SCORE 20 +#define BLAME_DEFAULT_COPY_SCORE 40 + +/* bits #0..7 in revision.h, #8..11 used for merge_bases() in commit.c */ +#define METAINFO_SHOWN (1u<<12) +#define MORE_THAN_ONE_PATH (1u<<13) + +/* + * One blob in a commit that is being suspected + */ +struct origin { + int refcnt; + struct commit *commit; + mmfile_t file; + unsigned char blob_sha1[20]; + char path[FLEX_ARRAY]; +}; + +static char *fill_origin_blob(struct origin *o, mmfile_t *file) +{ + if (!o->file.ptr) { + char type[10]; + num_read_blob++; + file->ptr = read_sha1_file(o->blob_sha1, type, + (unsigned long *)(&(file->size))); + o->file = *file; + } + else + *file = o->file; + return file->ptr; +} + +static inline struct origin *origin_incref(struct origin *o) +{ + if (o) + o->refcnt++; + return o; +} + +static void origin_decref(struct origin *o) +{ + if (o && --o->refcnt <= 0) { + if (o->file.ptr) + free(o->file.ptr); + memset(o, 0, sizeof(*o)); + free(o); + } +} + +struct blame_entry { + struct blame_entry *prev; + struct blame_entry *next; + + /* the first line of this group in the final image; + * internally all line numbers are 0 based. + */ + int lno; + + /* how many lines this group has */ + int num_lines; + + /* the commit that introduced this group into the final image */ + struct origin *suspect; + + /* true if the suspect is truly guilty; false while we have not + * checked if the group came from one of its parents. + */ + char guilty; + + /* the line number of the first line of this group in the + * suspect's file; internally all line numbers are 0 based. + */ + int s_lno; + + /* how significant this entry is -- cached to avoid + * scanning the lines over and over + */ + unsigned score; +}; + +struct scoreboard { + /* the final commit (i.e. where we started digging from) */ + struct commit *final; + + const char *path; + + /* the contents in the final; pointed into by buf pointers of + * blame_entries + */ + const char *final_buf; + unsigned long final_buf_size; + + /* linked list of blames */ + struct blame_entry *ent; + + /* look-up a line in the final buffer */ + int num_lines; + int *lineno; +}; + +static int cmp_suspect(struct origin *a, struct origin *b) +{ + int cmp = hashcmp(a->commit->object.sha1, b->commit->object.sha1); + if (cmp) + return cmp; + return strcmp(a->path, b->path); +} + +#define cmp_suspect(a, b) ( ((a)==(b)) ? 0 : cmp_suspect(a,b) ) + +static void sanity_check_refcnt(struct scoreboard *); + +static void coalesce(struct scoreboard *sb) +{ + struct blame_entry *ent, *next; + + for (ent = sb->ent; ent && (next = ent->next); ent = next) { + if (!cmp_suspect(ent->suspect, next->suspect) && + ent->guilty == next->guilty && + ent->s_lno + ent->num_lines == next->s_lno) { + ent->num_lines += next->num_lines; + ent->next = next->next; + if (ent->next) + ent->next->prev = ent; + origin_decref(next->suspect); + free(next); + ent->score = 0; + next = ent; /* again */ + } + } + + if (DEBUG) /* sanity */ + sanity_check_refcnt(sb); +} + +static struct origin *make_origin(struct commit *commit, const char *path) +{ + struct origin *o; + o = xcalloc(1, sizeof(*o) + strlen(path) + 1); + o->commit = commit; + o->refcnt = 1; + strcpy(o->path, path); + return o; +} + +static struct origin *get_origin(struct scoreboard *sb, + struct commit *commit, + const char *path) +{ + struct blame_entry *e; + + for (e = sb->ent; e; e = e->next) { + if (e->suspect->commit == commit && + !strcmp(e->suspect->path, path)) + return origin_incref(e->suspect); + } + return make_origin(commit, path); +} + +static int fill_blob_sha1(struct origin *origin) +{ + unsigned mode; + char type[10]; + + if (!is_null_sha1(origin->blob_sha1)) + return 0; + if (get_tree_entry(origin->commit->object.sha1, + origin->path, + origin->blob_sha1, &mode)) + goto error_out; + if (sha1_object_info(origin->blob_sha1, type, NULL) || + strcmp(type, blob_type)) + goto error_out; + return 0; + error_out: + hashclr(origin->blob_sha1); + return -1; +} + +static struct origin *find_origin(struct scoreboard *sb, + struct commit *parent, + struct origin *origin) +{ + struct origin *porigin = NULL; + struct diff_options diff_opts; + const char *paths[2]; + + if (parent->util) { + /* This is a freestanding copy of origin and not + * refcounted. + */ + struct origin *cached = parent->util; + if (!strcmp(cached->path, origin->path)) { + porigin = get_origin(sb, parent, cached->path); + if (porigin->refcnt == 1) + hashcpy(porigin->blob_sha1, cached->blob_sha1); + return porigin; + } + /* otherwise it was not very useful; free it */ + free(parent->util); + parent->util = NULL; + } + + /* See if the origin->path is different between parent + * and origin first. Most of the time they are the + * same and diff-tree is fairly efficient about this. + */ + diff_setup(&diff_opts); + diff_opts.recursive = 1; + diff_opts.detect_rename = 0; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + paths[0] = origin->path; + paths[1] = NULL; + + diff_tree_setup_paths(paths, &diff_opts); + if (diff_setup_done(&diff_opts) < 0) + die("diff-setup"); + diff_tree_sha1(parent->tree->object.sha1, + origin->commit->tree->object.sha1, + "", &diff_opts); + diffcore_std(&diff_opts); + + /* It is either one entry that says "modified", or "created", + * or nothing. + */ + if (!diff_queued_diff.nr) { + /* The path is the same as parent */ + porigin = get_origin(sb, parent, origin->path); + hashcpy(porigin->blob_sha1, origin->blob_sha1); + } + else if (diff_queued_diff.nr != 1) + die("internal error in blame::find_origin"); + else { + struct diff_filepair *p = diff_queued_diff.queue[0]; + switch (p->status) { + default: + die("internal error in blame::find_origin (%c)", + p->status); + case 'M': + porigin = get_origin(sb, parent, origin->path); + hashcpy(porigin->blob_sha1, p->one->sha1); + break; + case 'A': + case 'T': + /* Did not exist in parent, or type changed */ + break; + } + } + diff_flush(&diff_opts); + if (porigin) { + struct origin *cached; + cached = make_origin(porigin->commit, porigin->path); + hashcpy(cached->blob_sha1, porigin->blob_sha1); + parent->util = cached; + } + return porigin; +} + +static struct origin *find_rename(struct scoreboard *sb, + struct commit *parent, + struct origin *origin) +{ + struct origin *porigin = NULL; + struct diff_options diff_opts; + int i; + const char *paths[2]; + + diff_setup(&diff_opts); + diff_opts.recursive = 1; + diff_opts.detect_rename = DIFF_DETECT_RENAME; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_opts.single_follow = origin->path; + paths[0] = NULL; + diff_tree_setup_paths(paths, &diff_opts); + if (diff_setup_done(&diff_opts) < 0) + die("diff-setup"); + diff_tree_sha1(parent->tree->object.sha1, + origin->commit->tree->object.sha1, + "", &diff_opts); + diffcore_std(&diff_opts); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + if ((p->status == 'R' || p->status == 'C') && + !strcmp(p->two->path, origin->path)) { + porigin = get_origin(sb, parent, p->one->path); + hashcpy(porigin->blob_sha1, p->one->sha1); + break; + } + } + diff_flush(&diff_opts); + return porigin; +} + +struct chunk { + /* line number in postimage; up to but not including this + * line is the same as preimage + */ + int same; + + /* preimage line number after this chunk */ + int p_next; + + /* postimage line number after this chunk */ + int t_next; +}; + +struct patch { + struct chunk *chunks; + int num; +}; + +struct blame_diff_state { + struct xdiff_emit_state xm; + struct patch *ret; + unsigned hunk_post_context; + unsigned hunk_in_pre_context : 1; +}; + +static void process_u_diff(void *state_, char *line, unsigned long len) +{ + struct blame_diff_state *state = state_; + struct chunk *chunk; + int off1, off2, len1, len2, num; + + num = state->ret->num; + if (len < 4 || line[0] != '@' || line[1] != '@') { + if (state->hunk_in_pre_context && line[0] == ' ') + state->ret->chunks[num - 1].same++; + else { + state->hunk_in_pre_context = 0; + if (line[0] == ' ') + state->hunk_post_context++; + else + state->hunk_post_context = 0; + } + return; + } + + if (num && state->hunk_post_context) { + chunk = &state->ret->chunks[num - 1]; + chunk->p_next -= state->hunk_post_context; + chunk->t_next -= state->hunk_post_context; + } + state->ret->num = ++num; + state->ret->chunks = xrealloc(state->ret->chunks, + sizeof(struct chunk) * num); + chunk = &state->ret->chunks[num - 1]; + if (parse_hunk_header(line, len, &off1, &len1, &off2, &len2)) { + state->ret->num--; + return; + } + + /* Line numbers in patch output are one based. */ + off1--; + off2--; + + chunk->same = len2 ? off2 : (off2 + 1); + + chunk->p_next = off1 + (len1 ? len1 : 1); + chunk->t_next = chunk->same + len2; + state->hunk_in_pre_context = 1; + state->hunk_post_context = 0; +} + +static struct patch *compare_buffer(mmfile_t *file_p, mmfile_t *file_o, + int context) +{ + struct blame_diff_state state; + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + + xpp.flags = XDF_NEED_MINIMAL; + xecfg.ctxlen = context; + xecfg.flags = 0; + ecb.outf = xdiff_outf; + ecb.priv = &state; + memset(&state, 0, sizeof(state)); + state.xm.consume = process_u_diff; + state.ret = xmalloc(sizeof(struct patch)); + state.ret->chunks = NULL; + state.ret->num = 0; + + xdl_diff(file_p, file_o, &xpp, &xecfg, &ecb); + + if (state.ret->num) { + struct chunk *chunk; + chunk = &state.ret->chunks[state.ret->num - 1]; + chunk->p_next -= state.hunk_post_context; + chunk->t_next -= state.hunk_post_context; + } + return state.ret; +} + +static struct patch *get_patch(struct origin *parent, struct origin *origin) +{ + mmfile_t file_p, file_o; + struct patch *patch; + + fill_origin_blob(parent, &file_p); + fill_origin_blob(origin, &file_o); + if (!file_p.ptr || !file_o.ptr) + return NULL; + patch = compare_buffer(&file_p, &file_o, 0); + num_get_patch++; + return patch; +} + +static void free_patch(struct patch *p) +{ + free(p->chunks); + free(p); +} + +static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e) +{ + struct blame_entry *ent, *prev = NULL; + + origin_incref(e->suspect); + + for (ent = sb->ent; ent && ent->lno < e->lno; ent = ent->next) + prev = ent; + + /* prev, if not NULL, is the last one that is below e */ + e->prev = prev; + if (prev) { + e->next = prev->next; + prev->next = e; + } + else { + e->next = sb->ent; + sb->ent = e; + } + if (e->next) + e->next->prev = e; +} + +static void dup_entry(struct blame_entry *dst, struct blame_entry *src) +{ + struct blame_entry *p, *n; + + p = dst->prev; + n = dst->next; + origin_incref(src->suspect); + origin_decref(dst->suspect); + memcpy(dst, src, sizeof(*src)); + dst->prev = p; + dst->next = n; + dst->score = 0; +} + +static const char *nth_line(struct scoreboard *sb, int lno) +{ + return sb->final_buf + sb->lineno[lno]; +} + +static void split_overlap(struct blame_entry *split, + struct blame_entry *e, + int tlno, int plno, int same, + struct origin *parent) +{ + /* it is known that lines between tlno to same came from + * parent, and e has an overlap with that range. it also is + * known that parent's line plno corresponds to e's line tlno. + * + * <---- e -----> + * <------> + * <------------> + * <------------> + * <------------------> + * + * Potentially we need to split e into three parts; before + * this chunk, the chunk to be blamed for parent, and after + * that portion. + */ + int chunk_end_lno; + memset(split, 0, sizeof(struct blame_entry [3])); + + if (e->s_lno < tlno) { + /* there is a pre-chunk part not blamed on parent */ + split[0].suspect = origin_incref(e->suspect); + split[0].lno = e->lno; + split[0].s_lno = e->s_lno; + split[0].num_lines = tlno - e->s_lno; + split[1].lno = e->lno + tlno - e->s_lno; + split[1].s_lno = plno; + } + else { + split[1].lno = e->lno; + split[1].s_lno = plno + (e->s_lno - tlno); + } + + if (same < e->s_lno + e->num_lines) { + /* there is a post-chunk part not blamed on parent */ + split[2].suspect = origin_incref(e->suspect); + split[2].lno = e->lno + (same - e->s_lno); + split[2].s_lno = e->s_lno + (same - e->s_lno); + split[2].num_lines = e->s_lno + e->num_lines - same; + chunk_end_lno = split[2].lno; + } + else + chunk_end_lno = e->lno + e->num_lines; + split[1].num_lines = chunk_end_lno - split[1].lno; + + if (split[1].num_lines < 1) + return; + split[1].suspect = origin_incref(parent); +} + +static void split_blame(struct scoreboard *sb, + struct blame_entry *split, + struct blame_entry *e) +{ + struct blame_entry *new_entry; + + if (split[0].suspect && split[2].suspect) { + /* we need to split e into two and add another for parent */ + dup_entry(e, &split[0]); + + new_entry = xmalloc(sizeof(*new_entry)); + memcpy(new_entry, &(split[2]), sizeof(struct blame_entry)); + add_blame_entry(sb, new_entry); + + new_entry = xmalloc(sizeof(*new_entry)); + memcpy(new_entry, &(split[1]), sizeof(struct blame_entry)); + add_blame_entry(sb, new_entry); + } + else if (!split[0].suspect && !split[2].suspect) + /* parent covers the entire area */ + dup_entry(e, &split[1]); + else if (split[0].suspect) { + dup_entry(e, &split[0]); + + new_entry = xmalloc(sizeof(*new_entry)); + memcpy(new_entry, &(split[1]), sizeof(struct blame_entry)); + add_blame_entry(sb, new_entry); + } + else { + dup_entry(e, &split[1]); + + new_entry = xmalloc(sizeof(*new_entry)); + memcpy(new_entry, &(split[2]), sizeof(struct blame_entry)); + add_blame_entry(sb, new_entry); + } + + if (DEBUG) { /* sanity */ + struct blame_entry *ent; + int lno = sb->ent->lno, corrupt = 0; + + for (ent = sb->ent; ent; ent = ent->next) { + if (lno != ent->lno) + corrupt = 1; + if (ent->s_lno < 0) + corrupt = 1; + lno += ent->num_lines; + } + if (corrupt) { + lno = sb->ent->lno; + for (ent = sb->ent; ent; ent = ent->next) { + printf("L %8d l %8d n %8d\n", + lno, ent->lno, ent->num_lines); + lno = ent->lno + ent->num_lines; + } + die("oops"); + } + } +} + +static void decref_split(struct blame_entry *split) +{ + int i; + + for (i = 0; i < 3; i++) + origin_decref(split[i].suspect); +} + +static void blame_overlap(struct scoreboard *sb, struct blame_entry *e, + int tlno, int plno, int same, + struct origin *parent) +{ + struct blame_entry split[3]; + + split_overlap(split, e, tlno, plno, same, parent); + if (split[1].suspect) + split_blame(sb, split, e); + decref_split(split); +} + +static int find_last_in_target(struct scoreboard *sb, struct origin *target) +{ + struct blame_entry *e; + int last_in_target = -1; + + for (e = sb->ent; e; e = e->next) { + if (e->guilty || cmp_suspect(e->suspect, target)) + continue; + if (last_in_target < e->s_lno + e->num_lines) + last_in_target = e->s_lno + e->num_lines; + } + return last_in_target; +} + +static void blame_chunk(struct scoreboard *sb, + int tlno, int plno, int same, + struct origin *target, struct origin *parent) +{ + struct blame_entry *e; + + for (e = sb->ent; e; e = e->next) { + if (e->guilty || cmp_suspect(e->suspect, target)) + continue; + if (same <= e->s_lno) + continue; + if (tlno < e->s_lno + e->num_lines) + blame_overlap(sb, e, tlno, plno, same, parent); + } +} + +static int pass_blame_to_parent(struct scoreboard *sb, + struct origin *target, + struct origin *parent) +{ + int i, last_in_target, plno, tlno; + struct patch *patch; + + last_in_target = find_last_in_target(sb, target); + if (last_in_target < 0) + return 1; /* nothing remains for this target */ + + patch = get_patch(parent, target); + plno = tlno = 0; + for (i = 0; i < patch->num; i++) { + struct chunk *chunk = &patch->chunks[i]; + + blame_chunk(sb, tlno, plno, chunk->same, target, parent); + plno = chunk->p_next; + tlno = chunk->t_next; + } + /* rest (i.e. anything above tlno) are the same as parent */ + blame_chunk(sb, tlno, plno, last_in_target, target, parent); + + free_patch(patch); + return 0; +} + +static unsigned ent_score(struct scoreboard *sb, struct blame_entry *e) +{ + unsigned score; + const char *cp, *ep; + + if (e->score) + return e->score; + + score = 1; + cp = nth_line(sb, e->lno); + ep = nth_line(sb, e->lno + e->num_lines); + while (cp < ep) { + unsigned ch = *((unsigned char *)cp); + if (isalnum(ch)) + score++; + cp++; + } + e->score = score; + return score; +} + +static void copy_split_if_better(struct scoreboard *sb, + struct blame_entry *best_so_far, + struct blame_entry *this) +{ + int i; + + if (!this[1].suspect) + return; + if (best_so_far[1].suspect) { + if (ent_score(sb, &this[1]) < ent_score(sb, &best_so_far[1])) + return; + } + + for (i = 0; i < 3; i++) + origin_incref(this[i].suspect); + decref_split(best_so_far); + memcpy(best_so_far, this, sizeof(struct blame_entry [3])); +} + +static void find_copy_in_blob(struct scoreboard *sb, + struct blame_entry *ent, + struct origin *parent, + struct blame_entry *split, + mmfile_t *file_p) +{ + const char *cp; + int cnt; + mmfile_t file_o; + struct patch *patch; + int i, plno, tlno; + + cp = nth_line(sb, ent->lno); + file_o.ptr = (char*) cp; + cnt = ent->num_lines; + + while (cnt && cp < sb->final_buf + sb->final_buf_size) { + if (*cp++ == '\n') + cnt--; + } + file_o.size = cp - file_o.ptr; + + patch = compare_buffer(file_p, &file_o, 1); + + memset(split, 0, sizeof(struct blame_entry [3])); + plno = tlno = 0; + for (i = 0; i < patch->num; i++) { + struct chunk *chunk = &patch->chunks[i]; + + /* tlno to chunk->same are the same as ent */ + if (ent->num_lines <= tlno) + break; + if (tlno < chunk->same) { + struct blame_entry this[3]; + split_overlap(this, ent, + tlno + ent->s_lno, plno, + chunk->same + ent->s_lno, + parent); + copy_split_if_better(sb, split, this); + decref_split(this); + } + plno = chunk->p_next; + tlno = chunk->t_next; + } + free_patch(patch); +} + +static int find_move_in_parent(struct scoreboard *sb, + struct origin *target, + struct origin *parent) +{ + int last_in_target, made_progress; + struct blame_entry *e, split[3]; + mmfile_t file_p; + + last_in_target = find_last_in_target(sb, target); + if (last_in_target < 0) + return 1; /* nothing remains for this target */ + + fill_origin_blob(parent, &file_p); + if (!file_p.ptr) + return 0; + + made_progress = 1; + while (made_progress) { + made_progress = 0; + for (e = sb->ent; e; e = e->next) { + if (e->guilty || cmp_suspect(e->suspect, target)) + continue; + find_copy_in_blob(sb, e, parent, split, &file_p); + if (split[1].suspect && + blame_move_score < ent_score(sb, &split[1])) { + split_blame(sb, split, e); + made_progress = 1; + } + decref_split(split); + } + } + return 0; +} + + +struct blame_list { + struct blame_entry *ent; + struct blame_entry split[3]; +}; + +static struct blame_list *setup_blame_list(struct scoreboard *sb, + struct origin *target, + int *num_ents_p) +{ + struct blame_entry *e; + int num_ents, i; + struct blame_list *blame_list = NULL; + + /* Count the number of entries the target is suspected for, + * and prepare a list of entry and the best split. + */ + for (e = sb->ent, num_ents = 0; e; e = e->next) + if (!e->guilty && !cmp_suspect(e->suspect, target)) + num_ents++; + if (num_ents) { + blame_list = xcalloc(num_ents, sizeof(struct blame_list)); + for (e = sb->ent, i = 0; e; e = e->next) + if (!e->guilty && !cmp_suspect(e->suspect, target)) + blame_list[i++].ent = e; + } + *num_ents_p = num_ents; + return blame_list; +} + +static int find_copy_in_parent(struct scoreboard *sb, + struct origin *target, + struct commit *parent, + struct origin *porigin, + int opt) +{ + struct diff_options diff_opts; + const char *paths[1]; + int i, j; + int retval; + struct blame_list *blame_list; + int num_ents; + + blame_list = setup_blame_list(sb, target, &num_ents); + if (!blame_list) + return 1; /* nothing remains for this target */ + + diff_setup(&diff_opts); + diff_opts.recursive = 1; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + + paths[0] = NULL; + diff_tree_setup_paths(paths, &diff_opts); + if (diff_setup_done(&diff_opts) < 0) + die("diff-setup"); + + /* Try "find copies harder" on new path if requested; + * we do not want to use diffcore_rename() actually to + * match things up; find_copies_harder is set only to + * force diff_tree_sha1() to feed all filepairs to diff_queue, + * and this code needs to be after diff_setup_done(), which + * usually makes find-copies-harder imply copy detection. + */ + if ((opt & PICKAXE_BLAME_COPY_HARDER) && + (!porigin || strcmp(target->path, porigin->path))) + diff_opts.find_copies_harder = 1; + + diff_tree_sha1(parent->tree->object.sha1, + target->commit->tree->object.sha1, + "", &diff_opts); + + if (!diff_opts.find_copies_harder) + diffcore_std(&diff_opts); + + retval = 0; + while (1) { + int made_progress = 0; + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + struct origin *norigin; + mmfile_t file_p; + struct blame_entry this[3]; + + if (!DIFF_FILE_VALID(p->one)) + continue; /* does not exist in parent */ + if (porigin && !strcmp(p->one->path, porigin->path)) + /* find_move already dealt with this path */ + continue; + + norigin = get_origin(sb, parent, p->one->path); + hashcpy(norigin->blob_sha1, p->one->sha1); + fill_origin_blob(norigin, &file_p); + if (!file_p.ptr) + continue; + + for (j = 0; j < num_ents; j++) { + find_copy_in_blob(sb, blame_list[j].ent, + norigin, this, &file_p); + copy_split_if_better(sb, blame_list[j].split, + this); + decref_split(this); + } + origin_decref(norigin); + } + + for (j = 0; j < num_ents; j++) { + struct blame_entry *split = blame_list[j].split; + if (split[1].suspect && + blame_copy_score < ent_score(sb, &split[1])) { + split_blame(sb, split, blame_list[j].ent); + made_progress = 1; + } + decref_split(split); + } + free(blame_list); + + if (!made_progress) + break; + blame_list = setup_blame_list(sb, target, &num_ents); + if (!blame_list) { + retval = 1; + break; + } + } + diff_flush(&diff_opts); + + return retval; +} + +/* The blobs of origin and porigin exactly match, so everything + * origin is suspected for can be blamed on the parent. + */ +static void pass_whole_blame(struct scoreboard *sb, + struct origin *origin, struct origin *porigin) +{ + struct blame_entry *e; + + if (!porigin->file.ptr && origin->file.ptr) { + /* Steal its file */ + porigin->file = origin->file; + origin->file.ptr = NULL; + } + for (e = sb->ent; e; e = e->next) { + if (cmp_suspect(e->suspect, origin)) + continue; + origin_incref(porigin); + origin_decref(e->suspect); + e->suspect = porigin; + } +} + +#define MAXPARENT 16 + +static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) +{ + int i, pass; + struct commit *commit = origin->commit; + struct commit_list *parent; + struct origin *parent_origin[MAXPARENT], *porigin; + + memset(parent_origin, 0, sizeof(parent_origin)); + + /* The first pass looks for unrenamed path to optimize for + * common cases, then we look for renames in the second pass. + */ + for (pass = 0; pass < 2; pass++) { + struct origin *(*find)(struct scoreboard *, + struct commit *, struct origin *); + find = pass ? find_rename : find_origin; + + for (i = 0, parent = commit->parents; + i < MAXPARENT && parent; + parent = parent->next, i++) { + struct commit *p = parent->item; + int j, same; + + if (parent_origin[i]) + continue; + if (parse_commit(p)) + continue; + porigin = find(sb, p, origin); + if (!porigin) + continue; + if (!hashcmp(porigin->blob_sha1, origin->blob_sha1)) { + pass_whole_blame(sb, origin, porigin); + origin_decref(porigin); + goto finish; + } + for (j = same = 0; j < i; j++) + if (parent_origin[j] && + !hashcmp(parent_origin[j]->blob_sha1, + porigin->blob_sha1)) { + same = 1; + break; + } + if (!same) + parent_origin[i] = porigin; + else + origin_decref(porigin); + } + } + + num_commits++; + for (i = 0, parent = commit->parents; + i < MAXPARENT && parent; + parent = parent->next, i++) { + struct origin *porigin = parent_origin[i]; + if (!porigin) + continue; + if (pass_blame_to_parent(sb, origin, porigin)) + goto finish; + } + + /* + * Optionally run "miff" to find moves in parents' files here. + */ + if (opt & PICKAXE_BLAME_MOVE) + for (i = 0, parent = commit->parents; + i < MAXPARENT && parent; + parent = parent->next, i++) { + struct origin *porigin = parent_origin[i]; + if (!porigin) + continue; + if (find_move_in_parent(sb, origin, porigin)) + goto finish; + } + + /* + * Optionally run "ciff" to find copies from parents' files here. + */ + if (opt & PICKAXE_BLAME_COPY) + for (i = 0, parent = commit->parents; + i < MAXPARENT && parent; + parent = parent->next, i++) { + struct origin *porigin = parent_origin[i]; + if (find_copy_in_parent(sb, origin, parent->item, + porigin, opt)) + goto finish; + } + + finish: + for (i = 0; i < MAXPARENT; i++) + origin_decref(parent_origin[i]); +} + +static void assign_blame(struct scoreboard *sb, struct rev_info *revs, int opt) +{ + while (1) { + struct blame_entry *ent; + struct commit *commit; + struct origin *suspect = NULL; + + /* find one suspect to break down */ + for (ent = sb->ent; !suspect && ent; ent = ent->next) + if (!ent->guilty) + suspect = ent->suspect; + if (!suspect) + return; /* all done */ + + origin_incref(suspect); + commit = suspect->commit; + if (!commit->object.parsed) + parse_commit(commit); + if (!(commit->object.flags & UNINTERESTING) && + !(revs->max_age != -1 && commit->date < revs->max_age)) + pass_blame(sb, suspect, opt); + else { + commit->object.flags |= UNINTERESTING; + if (commit->object.parsed) + mark_parents_uninteresting(commit); + } + /* treat root commit as boundary */ + if (!commit->parents && !show_root) + commit->object.flags |= UNINTERESTING; + + /* Take responsibility for the remaining entries */ + for (ent = sb->ent; ent; ent = ent->next) + if (!cmp_suspect(ent->suspect, suspect)) + ent->guilty = 1; + origin_decref(suspect); + + if (DEBUG) /* sanity */ + sanity_check_refcnt(sb); + } +} + +static const char *format_time(unsigned long time, const char *tz_str, + int show_raw_time) +{ + static char time_buf[128]; + time_t t = time; + int minutes, tz; + struct tm *tm; + + if (show_raw_time) { + sprintf(time_buf, "%lu %s", time, tz_str); + return time_buf; + } + + tz = atoi(tz_str); + minutes = tz < 0 ? -tz : tz; + minutes = (minutes / 100)*60 + (minutes % 100); + minutes = tz < 0 ? -minutes : minutes; + t = time + minutes * 60; + tm = gmtime(&t); + + strftime(time_buf, sizeof(time_buf), "%Y-%m-%d %H:%M:%S ", tm); + strcat(time_buf, tz_str); + return time_buf; +} + +struct commit_info +{ + char *author; + char *author_mail; + unsigned long author_time; + char *author_tz; + + /* filled only when asked for details */ + char *committer; + char *committer_mail; + unsigned long committer_time; + char *committer_tz; + + char *summary; +}; + +static void get_ac_line(const char *inbuf, const char *what, + int bufsz, char *person, char **mail, + unsigned long *time, char **tz) +{ + int len; + char *tmp, *endp; + + tmp = strstr(inbuf, what); + if (!tmp) + goto error_out; + tmp += strlen(what); + endp = strchr(tmp, '\n'); + if (!endp) + len = strlen(tmp); + else + len = endp - tmp; + if (bufsz <= len) { + error_out: + /* Ugh */ + person = *mail = *tz = "(unknown)"; + *time = 0; + return; + } + memcpy(person, tmp, len); + + tmp = person; + tmp += len; + *tmp = 0; + while (*tmp != ' ') + tmp--; + *tz = tmp+1; + + *tmp = 0; + while (*tmp != ' ') + tmp--; + *time = strtoul(tmp, NULL, 10); + + *tmp = 0; + while (*tmp != ' ') + tmp--; + *mail = tmp + 1; + *tmp = 0; +} + +static void get_commit_info(struct commit *commit, + struct commit_info *ret, + int detailed) +{ + int len; + char *tmp, *endp; + static char author_buf[1024]; + static char committer_buf[1024]; + static char summary_buf[1024]; + + /* We've operated without save_commit_buffer, so + * we now need to populate them for output. + */ + if (!commit->buffer) { + char type[20]; + unsigned long size; + commit->buffer = + read_sha1_file(commit->object.sha1, type, &size); + } + ret->author = author_buf; + get_ac_line(commit->buffer, "\nauthor ", + sizeof(author_buf), author_buf, &ret->author_mail, + &ret->author_time, &ret->author_tz); + + if (!detailed) + return; + + ret->committer = committer_buf; + get_ac_line(commit->buffer, "\ncommitter ", + sizeof(committer_buf), committer_buf, &ret->committer_mail, + &ret->committer_time, &ret->committer_tz); + + ret->summary = summary_buf; + tmp = strstr(commit->buffer, "\n\n"); + if (!tmp) { + error_out: + sprintf(summary_buf, "(%s)", sha1_to_hex(commit->object.sha1)); + return; + } + tmp += 2; + endp = strchr(tmp, '\n'); + if (!endp) + goto error_out; + len = endp - tmp; + if (len >= sizeof(summary_buf)) + goto error_out; + memcpy(summary_buf, tmp, len); + summary_buf[len] = 0; +} + +#define OUTPUT_ANNOTATE_COMPAT 001 +#define OUTPUT_LONG_OBJECT_NAME 002 +#define OUTPUT_RAW_TIMESTAMP 004 +#define OUTPUT_PORCELAIN 010 +#define OUTPUT_SHOW_NAME 020 +#define OUTPUT_SHOW_NUMBER 040 +#define OUTPUT_SHOW_SCORE 0100 + +static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent) +{ + int cnt; + const char *cp; + struct origin *suspect = ent->suspect; + char hex[41]; + + strcpy(hex, sha1_to_hex(suspect->commit->object.sha1)); + printf("%s%c%d %d %d\n", + hex, + ent->guilty ? ' ' : '*', // purely for debugging + ent->s_lno + 1, + ent->lno + 1, + ent->num_lines); + if (!(suspect->commit->object.flags & METAINFO_SHOWN)) { + struct commit_info ci; + suspect->commit->object.flags |= METAINFO_SHOWN; + get_commit_info(suspect->commit, &ci, 1); + printf("author %s\n", ci.author); + printf("author-mail %s\n", ci.author_mail); + printf("author-time %lu\n", ci.author_time); + printf("author-tz %s\n", ci.author_tz); + printf("committer %s\n", ci.committer); + printf("committer-mail %s\n", ci.committer_mail); + printf("committer-time %lu\n", ci.committer_time); + printf("committer-tz %s\n", ci.committer_tz); + printf("filename %s\n", suspect->path); + printf("summary %s\n", ci.summary); + if (suspect->commit->object.flags & UNINTERESTING) + printf("boundary\n"); + } + else if (suspect->commit->object.flags & MORE_THAN_ONE_PATH) + printf("filename %s\n", suspect->path); + + cp = nth_line(sb, ent->lno); + for (cnt = 0; cnt < ent->num_lines; cnt++) { + char ch; + if (cnt) + printf("%s %d %d\n", hex, + ent->s_lno + 1 + cnt, + ent->lno + 1 + cnt); + putchar('\t'); + do { + ch = *cp++; + putchar(ch); + } while (ch != '\n' && + cp < sb->final_buf + sb->final_buf_size); + } +} + +static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt) +{ + int cnt; + const char *cp; + struct origin *suspect = ent->suspect; + struct commit_info ci; + char hex[41]; + int show_raw_time = !!(opt & OUTPUT_RAW_TIMESTAMP); + + get_commit_info(suspect->commit, &ci, 1); + strcpy(hex, sha1_to_hex(suspect->commit->object.sha1)); + + cp = nth_line(sb, ent->lno); + for (cnt = 0; cnt < ent->num_lines; cnt++) { + char ch; + int length = (opt & OUTPUT_LONG_OBJECT_NAME) ? 40 : 8; + + if (suspect->commit->object.flags & UNINTERESTING) { + if (!blank_boundary) { + length--; + putchar('^'); + } + else + memset(hex, ' ', length); + } + + printf("%.*s", length, hex); + if (opt & OUTPUT_ANNOTATE_COMPAT) + printf("\t(%10s\t%10s\t%d)", ci.author, + format_time(ci.author_time, ci.author_tz, + show_raw_time), + ent->lno + 1 + cnt); + else { + if (opt & OUTPUT_SHOW_SCORE) + printf(" %*d %02d", + max_score_digits, ent->score, + ent->suspect->refcnt); + if (opt & OUTPUT_SHOW_NAME) + printf(" %-*.*s", longest_file, longest_file, + suspect->path); + if (opt & OUTPUT_SHOW_NUMBER) + printf(" %*d", max_orig_digits, + ent->s_lno + 1 + cnt); + printf(" (%-*.*s %10s %*d) ", + longest_author, longest_author, ci.author, + format_time(ci.author_time, ci.author_tz, + show_raw_time), + max_digits, ent->lno + 1 + cnt); + } + do { + ch = *cp++; + putchar(ch); + } while (ch != '\n' && + cp < sb->final_buf + sb->final_buf_size); + } +} + +static void output(struct scoreboard *sb, int option) +{ + struct blame_entry *ent; + + if (option & OUTPUT_PORCELAIN) { + for (ent = sb->ent; ent; ent = ent->next) { + struct blame_entry *oth; + struct origin *suspect = ent->suspect; + struct commit *commit = suspect->commit; + if (commit->object.flags & MORE_THAN_ONE_PATH) + continue; + for (oth = ent->next; oth; oth = oth->next) { + if ((oth->suspect->commit != commit) || + !strcmp(oth->suspect->path, suspect->path)) + continue; + commit->object.flags |= MORE_THAN_ONE_PATH; + break; + } + } + } + + for (ent = sb->ent; ent; ent = ent->next) { + if (option & OUTPUT_PORCELAIN) + emit_porcelain(sb, ent); + else { + emit_other(sb, ent, option); + } + } +} + +static int prepare_lines(struct scoreboard *sb) +{ + const char *buf = sb->final_buf; + unsigned long len = sb->final_buf_size; + int num = 0, incomplete = 0, bol = 1; + + if (len && buf[len-1] != '\n') + incomplete++; /* incomplete line at the end */ + while (len--) { + if (bol) { + sb->lineno = xrealloc(sb->lineno, + sizeof(int* ) * (num + 1)); + sb->lineno[num] = buf - sb->final_buf; + bol = 0; + } + if (*buf++ == '\n') { + num++; + bol = 1; + } + } + sb->lineno = xrealloc(sb->lineno, + sizeof(int* ) * (num + incomplete + 1)); + sb->lineno[num + incomplete] = buf - sb->final_buf; + sb->num_lines = num + incomplete; + return sb->num_lines; +} + +static int read_ancestry(const char *graft_file) +{ + FILE *fp = fopen(graft_file, "r"); + char buf[1024]; + if (!fp) + return -1; + while (fgets(buf, sizeof(buf), fp)) { + /* The format is just "Commit Parent1 Parent2 ...\n" */ + int len = strlen(buf); + struct commit_graft *graft = read_graft_line(buf, len); + if (graft) + register_commit_graft(graft, 0); + } + fclose(fp); + return 0; +} + +static int lineno_width(int lines) +{ + int i, width; + + for (width = 1, i = 10; i <= lines + 1; width++) + i *= 10; + return width; +} + +static void find_alignment(struct scoreboard *sb, int *option) +{ + int longest_src_lines = 0; + int longest_dst_lines = 0; + unsigned largest_score = 0; + struct blame_entry *e; + + for (e = sb->ent; e; e = e->next) { + struct origin *suspect = e->suspect; + struct commit_info ci; + int num; + + if (strcmp(suspect->path, sb->path)) + *option |= OUTPUT_SHOW_NAME; + num = strlen(suspect->path); + if (longest_file < num) + longest_file = num; + if (!(suspect->commit->object.flags & METAINFO_SHOWN)) { + suspect->commit->object.flags |= METAINFO_SHOWN; + get_commit_info(suspect->commit, &ci, 1); + num = strlen(ci.author); + if (longest_author < num) + longest_author = num; + } + num = e->s_lno + e->num_lines; + if (longest_src_lines < num) + longest_src_lines = num; + num = e->lno + e->num_lines; + if (longest_dst_lines < num) + longest_dst_lines = num; + if (largest_score < ent_score(sb, e)) + largest_score = ent_score(sb, e); + } + max_orig_digits = lineno_width(longest_src_lines); + max_digits = lineno_width(longest_dst_lines); + max_score_digits = lineno_width(largest_score); +} + +static void sanity_check_refcnt(struct scoreboard *sb) +{ + int baa = 0; + struct blame_entry *ent; + + for (ent = sb->ent; ent; ent = ent->next) { + /* Nobody should have zero or negative refcnt */ + if (ent->suspect->refcnt <= 0) { + fprintf(stderr, "%s in %s has negative refcnt %d\n", + ent->suspect->path, + sha1_to_hex(ent->suspect->commit->object.sha1), + ent->suspect->refcnt); + baa = 1; + } + } + for (ent = sb->ent; ent; ent = ent->next) { + /* Mark the ones that haven't been checked */ + if (0 < ent->suspect->refcnt) + ent->suspect->refcnt = -ent->suspect->refcnt; + } + for (ent = sb->ent; ent; ent = ent->next) { + /* then pick each and see if they have the the correct + * refcnt. + */ + int found; + struct blame_entry *e; + struct origin *suspect = ent->suspect; + + if (0 < suspect->refcnt) + continue; + suspect->refcnt = -suspect->refcnt; /* Unmark */ + for (found = 0, e = sb->ent; e; e = e->next) { + if (e->suspect != suspect) + continue; + found++; + } + if (suspect->refcnt != found) { + fprintf(stderr, "%s in %s has refcnt %d, not %d\n", + ent->suspect->path, + sha1_to_hex(ent->suspect->commit->object.sha1), + ent->suspect->refcnt, found); + baa = 2; + } + } + if (baa) { + int opt = 0160; + find_alignment(sb, &opt); + output(sb, opt); + die("Baa %d!", baa); + } +} + +static int has_path_in_work_tree(const char *path) +{ + struct stat st; + return !lstat(path, &st); +} + +static unsigned parse_score(const char *arg) +{ + char *end; + unsigned long score = strtoul(arg, &end, 10); + if (*end) + return 0; + return score; +} + +static const char *add_prefix(const char *prefix, const char *path) +{ + if (!prefix || !prefix[0]) + return path; + return prefix_path(prefix, strlen(prefix), path); +} + +static const char *parse_loc(const char *spec, + struct scoreboard *sb, long lno, + long begin, long *ret) +{ + char *term; + const char *line; + long num; + int reg_error; + regex_t regexp; + regmatch_t match[1]; + + /* Allow "-L <something>,+20" to mean starting at <something> + * for 20 lines, or "-L <something>,-5" for 5 lines ending at + * <something>. + */ + if (1 < begin && (spec[0] == '+' || spec[0] == '-')) { + num = strtol(spec + 1, &term, 10); + if (term != spec + 1) { + if (spec[0] == '-') + num = 0 - num; + if (0 < num) + *ret = begin + num - 2; + else if (!num) + *ret = begin; + else + *ret = begin + num; + return term; + } + return spec; + } + num = strtol(spec, &term, 10); + if (term != spec) { + *ret = num; + return term; + } + if (spec[0] != '/') + return spec; + + /* it could be a regexp of form /.../ */ + for (term = (char*) spec + 1; *term && *term != '/'; term++) { + if (*term == '\\') + term++; + } + if (*term != '/') + return spec; + + /* try [spec+1 .. term-1] as regexp */ + *term = 0; + begin--; /* input is in human terms */ + line = nth_line(sb, begin); + + if (!(reg_error = regcomp(®exp, spec + 1, REG_NEWLINE)) && + !(reg_error = regexec(®exp, line, 1, match, 0))) { + const char *cp = line + match[0].rm_so; + const char *nline; + + while (begin++ < lno) { + nline = nth_line(sb, begin); + if (line <= cp && cp < nline) + break; + line = nline; + } + *ret = begin; + regfree(®exp); + *term++ = '/'; + return term; + } + else { + char errbuf[1024]; + regerror(reg_error, ®exp, errbuf, 1024); + die("-L parameter '%s': %s", spec + 1, errbuf); + } +} + +static void prepare_blame_range(struct scoreboard *sb, + const char *bottomtop, + long lno, + long *bottom, long *top) +{ + const char *term; + + term = parse_loc(bottomtop, sb, lno, 1, bottom); + if (*term == ',') { + term = parse_loc(term + 1, sb, lno, *bottom + 1, top); + if (*term) + usage(blame_usage); + } + if (*term) + usage(blame_usage); +} + +static int git_blame_config(const char *var, const char *value) +{ + if (!strcmp(var, "blame.showroot")) { + show_root = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "blame.blankboundary")) { + blank_boundary = git_config_bool(var, value); + return 0; + } + return git_default_config(var, value); +} + +int cmd_blame(int argc, const char **argv, const char *prefix) +{ + struct rev_info revs; + const char *path; + struct scoreboard sb; + struct origin *o; + struct blame_entry *ent; + int i, seen_dashdash, unk, opt; + long bottom, top, lno; + int output_option = 0; + const char *revs_file = NULL; + const char *final_commit_name = NULL; + char type[10]; + const char *bottomtop = NULL; + + git_config(git_blame_config); + save_commit_buffer = 0; + + opt = 0; + seen_dashdash = 0; + for (unk = i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (*arg != '-') + break; + else if (!strcmp("-b", arg)) + blank_boundary = 1; + else if (!strcmp("--root", arg)) + show_root = 1; + else if (!strcmp("-c", arg)) + output_option |= OUTPUT_ANNOTATE_COMPAT; + else if (!strcmp("-t", arg)) + output_option |= OUTPUT_RAW_TIMESTAMP; + else if (!strcmp("-l", arg)) + output_option |= OUTPUT_LONG_OBJECT_NAME; + else if (!strcmp("-S", arg) && ++i < argc) + revs_file = argv[i]; + else if (!strncmp("-M", arg, 2)) { + opt |= PICKAXE_BLAME_MOVE; + blame_move_score = parse_score(arg+2); + } + else if (!strncmp("-C", arg, 2)) { + if (opt & PICKAXE_BLAME_COPY) + opt |= PICKAXE_BLAME_COPY_HARDER; + opt |= PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE; + blame_copy_score = parse_score(arg+2); + } + else if (!strncmp("-L", arg, 2)) { + if (!arg[2]) { + if (++i >= argc) + usage(blame_usage); + arg = argv[i]; + } + else + arg += 2; + if (bottomtop) + die("More than one '-L n,m' option given"); + bottomtop = arg; + } + else if (!strcmp("--score-debug", arg)) + output_option |= OUTPUT_SHOW_SCORE; + else if (!strcmp("-f", arg) || + !strcmp("--show-name", arg)) + output_option |= OUTPUT_SHOW_NAME; + else if (!strcmp("-n", arg) || + !strcmp("--show-number", arg)) + output_option |= OUTPUT_SHOW_NUMBER; + else if (!strcmp("-p", arg) || + !strcmp("--porcelain", arg)) + output_option |= OUTPUT_PORCELAIN; + else if (!strcmp("--", arg)) { + seen_dashdash = 1; + i++; + break; + } + else + argv[unk++] = arg; + } + + if (!blame_move_score) + blame_move_score = BLAME_DEFAULT_MOVE_SCORE; + if (!blame_copy_score) + blame_copy_score = BLAME_DEFAULT_COPY_SCORE; + + /* We have collected options unknown to us in argv[1..unk] + * which are to be passed to revision machinery if we are + * going to do the "bottom" procesing. + * + * The remaining are: + * + * (1) if seen_dashdash, its either + * "-options -- <path>" or + * "-options -- <path> <rev>". + * but the latter is allowed only if there is no + * options that we passed to revision machinery. + * + * (2) otherwise, we may have "--" somewhere later and + * might be looking at the first one of multiple 'rev' + * parameters (e.g. " master ^next ^maint -- path"). + * See if there is a dashdash first, and give the + * arguments before that to revision machinery. + * After that there must be one 'path'. + * + * (3) otherwise, its one of the three: + * "-options <path> <rev>" + * "-options <rev> <path>" + * "-options <path>" + * but again the first one is allowed only if + * there is no options that we passed to revision + * machinery. + */ + + if (seen_dashdash) { + /* (1) */ + if (argc <= i) + usage(blame_usage); + path = add_prefix(prefix, argv[i]); + if (i + 1 == argc - 1) { + if (unk != 1) + usage(blame_usage); + argv[unk++] = argv[i + 1]; + } + else if (i + 1 != argc) + /* garbage at end */ + usage(blame_usage); + } + else { + int j; + for (j = i; !seen_dashdash && j < argc; j++) + if (!strcmp(argv[j], "--")) + seen_dashdash = j; + if (seen_dashdash) { + if (seen_dashdash + 1 != argc - 1) + usage(blame_usage); + path = add_prefix(prefix, argv[seen_dashdash + 1]); + for (j = i; j < seen_dashdash; j++) + argv[unk++] = argv[j]; + } + else { + /* (3) */ + path = add_prefix(prefix, argv[i]); + if (i + 1 == argc - 1) { + final_commit_name = argv[i + 1]; + + /* if (unk == 1) we could be getting + * old-style + */ + if (unk == 1 && !has_path_in_work_tree(path)) { + path = add_prefix(prefix, argv[i + 1]); + final_commit_name = argv[i]; + } + } + else if (i != argc - 1) + usage(blame_usage); /* garbage at end */ + + if (!has_path_in_work_tree(path)) + die("cannot stat path %s: %s", + path, strerror(errno)); + } + } + + if (final_commit_name) + argv[unk++] = final_commit_name; + + /* Now we got rev and path. We do not want the path pruning + * but we may want "bottom" processing. + */ + argv[unk++] = "--"; /* terminate the rev name */ + argv[unk] = NULL; + + init_revisions(&revs, NULL); + setup_revisions(unk, argv, &revs, "HEAD"); + memset(&sb, 0, sizeof(sb)); + + /* There must be one and only one positive commit in the + * revs->pending array. + */ + for (i = 0; i < revs.pending.nr; i++) { + struct object *obj = revs.pending.objects[i].item; + if (obj->flags & UNINTERESTING) + continue; + while (obj->type == OBJ_TAG) + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", + revs.pending.objects[i].name); + if (sb.final) + die("More than one commit to dig from %s and %s?", + revs.pending.objects[i].name, + final_commit_name); + sb.final = (struct commit *) obj; + final_commit_name = revs.pending.objects[i].name; + } + + if (!sb.final) { + /* "--not A B -- path" without anything positive */ + unsigned char head_sha1[20]; + + final_commit_name = "HEAD"; + if (get_sha1(final_commit_name, head_sha1)) + die("No such ref: HEAD"); + sb.final = lookup_commit_reference(head_sha1); + add_pending_object(&revs, &(sb.final->object), "HEAD"); + } + + /* If we have bottom, this will mark the ancestors of the + * bottom commits we would reach while traversing as + * uninteresting. + */ + prepare_revision_walk(&revs); + + o = get_origin(&sb, sb.final, path); + if (fill_blob_sha1(o)) + die("no such path %s in %s", path, final_commit_name); + + sb.final_buf = read_sha1_file(o->blob_sha1, type, &sb.final_buf_size); + num_read_blob++; + lno = prepare_lines(&sb); + + bottom = top = 0; + if (bottomtop) + prepare_blame_range(&sb, bottomtop, lno, &bottom, &top); + if (bottom && top && top < bottom) { + long tmp; + tmp = top; top = bottom; bottom = tmp; + } + if (bottom < 1) + bottom = 1; + if (top < 1) + top = lno; + bottom--; + if (lno < top) + die("file %s has only %lu lines", path, lno); + + ent = xcalloc(1, sizeof(*ent)); + ent->lno = bottom; + ent->num_lines = top - bottom; + ent->suspect = o; + ent->s_lno = bottom; + + sb.ent = ent; + sb.path = path; + + if (revs_file && read_ancestry(revs_file)) + die("reading graft file %s failed: %s", + revs_file, strerror(errno)); + + assign_blame(&sb, &revs, opt); + + coalesce(&sb); + + if (!(output_option & OUTPUT_PORCELAIN)) + find_alignment(&sb, &output_option); + + output(&sb, output_option); + free((void *)sb.final_buf); + for (ent = sb.ent; ent; ) { + struct blame_entry *e = ent->next; + free(ent); + ent = e; + } + + if (DEBUG) { + printf("num read blob: %d\n", num_read_blob); + printf("num get patch: %d\n", num_get_patch); + printf("num commits: %d\n", num_commits); + } + return 0; +} diff --git a/builtin-branch.c b/builtin-branch.c new file mode 100644 index 0000000000..c760e188ea --- /dev/null +++ b/builtin-branch.c @@ -0,0 +1,494 @@ +/* + * Builtin "git branch" + * + * Copyright (c) 2006 Kristian Høgsberg <krh@redhat.com> + * Based on git-branch.sh by Junio C Hamano. + */ + +#include "cache.h" +#include "color.h" +#include "refs.h" +#include "commit.h" +#include "builtin.h" + +static const char builtin_branch_usage[] = + "git-branch [-r] (-d | -D) <branchname> | [-l] [-f] <branchname> [<start-point>] | (-m | -M) [<oldbranch>] <newbranch> | [--color | --no-color] [-r | -a] [-v [--abbrev=<length>]]"; + +#define REF_UNKNOWN_TYPE 0x00 +#define REF_LOCAL_BRANCH 0x01 +#define REF_REMOTE_BRANCH 0x02 +#define REF_TAG 0x04 + +static const char *head; +static unsigned char head_sha1[20]; + +static int branch_use_color; +static char branch_colors[][COLOR_MAXLEN] = { + "\033[m", /* reset */ + "", /* PLAIN (normal) */ + "\033[31m", /* REMOTE (red) */ + "", /* LOCAL (normal) */ + "\033[32m", /* CURRENT (green) */ +}; +enum color_branch { + COLOR_BRANCH_RESET = 0, + COLOR_BRANCH_PLAIN = 1, + COLOR_BRANCH_REMOTE = 2, + COLOR_BRANCH_LOCAL = 3, + COLOR_BRANCH_CURRENT = 4, +}; + +static int parse_branch_color_slot(const char *var, int ofs) +{ + if (!strcasecmp(var+ofs, "plain")) + return COLOR_BRANCH_PLAIN; + if (!strcasecmp(var+ofs, "reset")) + return COLOR_BRANCH_RESET; + if (!strcasecmp(var+ofs, "remote")) + return COLOR_BRANCH_REMOTE; + if (!strcasecmp(var+ofs, "local")) + return COLOR_BRANCH_LOCAL; + if (!strcasecmp(var+ofs, "current")) + return COLOR_BRANCH_CURRENT; + die("bad config variable '%s'", var); +} + +int git_branch_config(const char *var, const char *value) +{ + if (!strcmp(var, "color.branch")) { + branch_use_color = git_config_colorbool(var, value); + return 0; + } + if (!strncmp(var, "color.branch.", 13)) { + int slot = parse_branch_color_slot(var, 13); + color_parse(value, var, branch_colors[slot]); + return 0; + } + return git_default_config(var, value); +} + +const char *branch_get_color(enum color_branch ix) +{ + if (branch_use_color) + return branch_colors[ix]; + return ""; +} + +static int delete_branches(int argc, const char **argv, int force, int kinds) +{ + struct commit *rev, *head_rev = head_rev; + unsigned char sha1[20]; + char *name = NULL; + const char *fmt, *remote; + int i; + int ret = 0; + + switch (kinds) { + case REF_REMOTE_BRANCH: + fmt = "refs/remotes/%s"; + remote = "remote "; + force = 1; + break; + case REF_LOCAL_BRANCH: + fmt = "refs/heads/%s"; + remote = ""; + break; + default: + die("cannot use -a with -d"); + } + + if (!force) { + head_rev = lookup_commit_reference(head_sha1); + if (!head_rev) + die("Couldn't look up commit object for HEAD"); + } + for (i = 0; i < argc; i++) { + if (kinds == REF_LOCAL_BRANCH && !strcmp(head, argv[i])) { + error("Cannot delete the branch '%s' " + "which you are currently on.", argv[i]); + ret = 1; + continue; + } + + if (name) + free(name); + + name = xstrdup(mkpath(fmt, argv[i])); + if (!resolve_ref(name, sha1, 1, NULL)) { + error("%sbranch '%s' not found.", + remote, argv[i]); + ret = 1; + continue; + } + + rev = lookup_commit_reference(sha1); + if (!rev) { + error("Couldn't look up commit object for '%s'", name); + ret = 1; + continue; + } + + /* This checks whether the merge bases of branch and + * HEAD contains branch -- which means that the HEAD + * contains everything in both. + */ + + if (!force && + !in_merge_bases(rev, head_rev)) { + error("The branch '%s' is not a strict subset of " + "your current HEAD.\n" + "If you are sure you want to delete it, " + "run 'git branch -D %s'.", argv[i], argv[i]); + ret = 1; + continue; + } + + if (delete_ref(name, sha1)) { + error("Error deleting %sbranch '%s'", remote, + argv[i]); + ret = 1; + } else + printf("Deleted %sbranch %s.\n", remote, argv[i]); + + } + + if (name) + free(name); + + return(ret); +} + +struct ref_item { + char *name; + unsigned int kind; + unsigned char sha1[20]; +}; + +struct ref_list { + int index, alloc, maxwidth; + struct ref_item *list; + int kinds; +}; + +static int append_ref(const char *refname, const unsigned char *sha1, int flags, void *cb_data) +{ + struct ref_list *ref_list = (struct ref_list*)(cb_data); + struct ref_item *newitem; + int kind = REF_UNKNOWN_TYPE; + int len; + + /* Detect kind */ + if (!strncmp(refname, "refs/heads/", 11)) { + kind = REF_LOCAL_BRANCH; + refname += 11; + } else if (!strncmp(refname, "refs/remotes/", 13)) { + kind = REF_REMOTE_BRANCH; + refname += 13; + } else if (!strncmp(refname, "refs/tags/", 10)) { + kind = REF_TAG; + refname += 10; + } + + /* Don't add types the caller doesn't want */ + if ((kind & ref_list->kinds) == 0) + return 0; + + /* Resize buffer */ + if (ref_list->index >= ref_list->alloc) { + ref_list->alloc = alloc_nr(ref_list->alloc); + ref_list->list = xrealloc(ref_list->list, + ref_list->alloc * sizeof(struct ref_item)); + } + + /* Record the new item */ + newitem = &(ref_list->list[ref_list->index++]); + newitem->name = xstrdup(refname); + newitem->kind = kind; + hashcpy(newitem->sha1, sha1); + len = strlen(newitem->name); + if (len > ref_list->maxwidth) + ref_list->maxwidth = len; + + return 0; +} + +static void free_ref_list(struct ref_list *ref_list) +{ + int i; + + for (i = 0; i < ref_list->index; i++) + free(ref_list->list[i].name); + free(ref_list->list); +} + +static int ref_cmp(const void *r1, const void *r2) +{ + struct ref_item *c1 = (struct ref_item *)(r1); + struct ref_item *c2 = (struct ref_item *)(r2); + + if (c1->kind != c2->kind) + return c1->kind - c2->kind; + return strcmp(c1->name, c2->name); +} + +static void print_ref_item(struct ref_item *item, int maxwidth, int verbose, + int abbrev, int current) +{ + char c; + int color; + struct commit *commit; + char subject[256]; + + switch (item->kind) { + case REF_LOCAL_BRANCH: + color = COLOR_BRANCH_LOCAL; + break; + case REF_REMOTE_BRANCH: + color = COLOR_BRANCH_REMOTE; + break; + default: + color = COLOR_BRANCH_PLAIN; + break; + } + + c = ' '; + if (current) { + c = '*'; + color = COLOR_BRANCH_CURRENT; + } + + if (verbose) { + commit = lookup_commit(item->sha1); + if (commit && !parse_commit(commit)) + pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, + subject, sizeof(subject), 0, + NULL, NULL, 0); + else + strcpy(subject, " **** invalid ref ****"); + printf("%c %s%-*s%s %s %s\n", c, branch_get_color(color), + maxwidth, item->name, + branch_get_color(COLOR_BRANCH_RESET), + find_unique_abbrev(item->sha1, abbrev), subject); + } else { + printf("%c %s%s%s\n", c, branch_get_color(color), item->name, + branch_get_color(COLOR_BRANCH_RESET)); + } +} + +static void print_ref_list(int kinds, int detached, int verbose, int abbrev) +{ + int i; + struct ref_list ref_list; + + memset(&ref_list, 0, sizeof(ref_list)); + ref_list.kinds = kinds; + for_each_ref(append_ref, &ref_list); + + qsort(ref_list.list, ref_list.index, sizeof(struct ref_item), ref_cmp); + + detached = (detached && (kinds & REF_LOCAL_BRANCH)); + if (detached) { + struct ref_item item; + item.name = "(no branch)"; + item.kind = REF_LOCAL_BRANCH; + hashcpy(item.sha1, head_sha1); + if (strlen(item.name) > ref_list.maxwidth) + ref_list.maxwidth = strlen(item.name); + print_ref_item(&item, ref_list.maxwidth, verbose, abbrev, 1); + } + + for (i = 0; i < ref_list.index; i++) { + int current = !detached && + (ref_list.list[i].kind == REF_LOCAL_BRANCH) && + !strcmp(ref_list.list[i].name, head); + print_ref_item(&ref_list.list[i], ref_list.maxwidth, verbose, + abbrev, current); + } + + free_ref_list(&ref_list); +} + +static void create_branch(const char *name, const char *start_name, + unsigned char *start_sha1, + int force, int reflog) +{ + struct ref_lock *lock; + struct commit *commit; + unsigned char sha1[20]; + char ref[PATH_MAX], msg[PATH_MAX + 20]; + + snprintf(ref, sizeof ref, "refs/heads/%s", name); + if (check_ref_format(ref)) + die("'%s' is not a valid branch name.", name); + + if (resolve_ref(ref, sha1, 1, NULL)) { + if (!force) + die("A branch named '%s' already exists.", name); + else if (!strcmp(head, name)) + die("Cannot force update the current branch."); + } + + if (start_sha1) + /* detached HEAD */ + hashcpy(sha1, start_sha1); + else if (get_sha1(start_name, sha1)) + die("Not a valid object name: '%s'.", start_name); + + if ((commit = lookup_commit_reference(sha1)) == NULL) + die("Not a valid branch point: '%s'.", start_name); + hashcpy(sha1, commit->object.sha1); + + lock = lock_any_ref_for_update(ref, NULL); + if (!lock) + die("Failed to lock ref for update: %s.", strerror(errno)); + + if (reflog) { + log_all_ref_updates = 1; + snprintf(msg, sizeof msg, "branch: Created from %s", + start_name); + } + + if (write_ref_sha1(lock, sha1, msg) < 0) + die("Failed to write ref: %s.", strerror(errno)); +} + +static void rename_branch(const char *oldname, const char *newname, int force) +{ + char oldref[PATH_MAX], newref[PATH_MAX], logmsg[PATH_MAX*2 + 100]; + unsigned char sha1[20]; + + if (!oldname) + die("cannot rename the curren branch while not on any."); + + if (snprintf(oldref, sizeof(oldref), "refs/heads/%s", oldname) > sizeof(oldref)) + die("Old branchname too long"); + + if (check_ref_format(oldref)) + die("Invalid branch name: %s", oldref); + + if (snprintf(newref, sizeof(newref), "refs/heads/%s", newname) > sizeof(newref)) + die("New branchname too long"); + + if (check_ref_format(newref)) + die("Invalid branch name: %s", newref); + + if (resolve_ref(newref, sha1, 1, NULL) && !force) + die("A branch named '%s' already exists.", newname); + + snprintf(logmsg, sizeof(logmsg), "Branch: renamed %s to %s", + oldref, newref); + + if (rename_ref(oldref, newref, logmsg)) + die("Branch rename failed"); + + if (!strcmp(oldname, head) && create_symref("HEAD", newref)) + die("Branch renamed to %s, but HEAD is not updated!", newname); +} + +int cmd_branch(int argc, const char **argv, const char *prefix) +{ + int delete = 0, force_delete = 0, force_create = 0; + int rename = 0, force_rename = 0; + int verbose = 0, abbrev = DEFAULT_ABBREV, detached = 0; + int reflog = 0; + int kinds = REF_LOCAL_BRANCH; + int i; + + setup_ident(); + git_config(git_branch_config); + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (arg[0] != '-') + break; + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strcmp(arg, "-d")) { + delete = 1; + continue; + } + if (!strcmp(arg, "-D")) { + delete = 1; + force_delete = 1; + continue; + } + if (!strcmp(arg, "-f")) { + force_create = 1; + continue; + } + if (!strcmp(arg, "-m")) { + rename = 1; + continue; + } + if (!strcmp(arg, "-M")) { + rename = 1; + force_rename = 1; + continue; + } + if (!strcmp(arg, "-r")) { + kinds = REF_REMOTE_BRANCH; + continue; + } + if (!strcmp(arg, "-a")) { + kinds = REF_REMOTE_BRANCH | REF_LOCAL_BRANCH; + continue; + } + if (!strcmp(arg, "-l")) { + reflog = 1; + continue; + } + if (!strncmp(arg, "--abbrev=", 9)) { + abbrev = atoi(arg+9); + continue; + } + if (!strcmp(arg, "-v")) { + verbose = 1; + continue; + } + if (!strcmp(arg, "--color")) { + branch_use_color = 1; + continue; + } + if (!strcmp(arg, "--no-color")) { + branch_use_color = 0; + continue; + } + usage(builtin_branch_usage); + } + + if ((delete && rename) || (delete && force_create) || + (rename && force_create)) + usage(builtin_branch_usage); + + head = xstrdup(resolve_ref("HEAD", head_sha1, 0, NULL)); + if (!head) + die("Failed to resolve HEAD as a valid ref."); + if (!strcmp(head, "HEAD")) { + detached = 1; + } + else { + if (strncmp(head, "refs/heads/", 11)) + die("HEAD not found below refs/heads!"); + head += 11; + } + + if (delete) + return delete_branches(argc - i, argv + i, force_delete, kinds); + else if (i == argc) + print_ref_list(kinds, detached, verbose, abbrev); + else if (rename && (i == argc - 1)) + rename_branch(head, argv[i], force_rename); + else if (rename && (i == argc - 2)) + rename_branch(argv[i], argv[i + 1], force_rename); + else if (i == argc - 1) + create_branch(argv[i], head, head_sha1, force_create, reflog); + else if (i == argc - 2) + create_branch(argv[i], argv[i+1], NULL, force_create, reflog); + else + usage(builtin_branch_usage); + + return 0; +} diff --git a/builtin-cat-file.c b/builtin-cat-file.c index 7a6fa56e93..6c16bfa1ae 100644 --- a/builtin-cat-file.c +++ b/builtin-cat-file.c @@ -54,7 +54,7 @@ static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long write_or_die(1, tagger, sp - tagger); date = strtoul(sp, &ep, 10); tz = strtol(ep, NULL, 10); - sp = show_date(date, tz); + sp = show_date(date, tz, 0); write_or_die(1, sp, strlen(sp)); xwrite(1, "\n", 1); break; diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index 6b55f931cb..b097c888a0 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -45,7 +45,7 @@ static int line_termination = '\n'; static int checkout_stage; /* default to checkout stage0 */ static int to_tempfile; -static char topath[4][MAXPATHLEN+1]; +static char topath[4][PATH_MAX + 1]; static struct checkout state; diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c index e2e690a1ae..0651e5927e 100644 --- a/builtin-commit-tree.c +++ b/builtin-commit-tree.c @@ -7,6 +7,7 @@ #include "commit.h" #include "tree.h" #include "builtin.h" +#include "utf8.h" #define BLOCKING (1ul << 14) @@ -32,7 +33,7 @@ static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...) len = vsnprintf(one_line, sizeof(one_line), fmt, args); va_end(args); size = *sizep; - newsize = size + len; + newsize = size + len + 1; alloc = (size + 32767) & ~32767; buf = *bufp; if (newsize > alloc) { @@ -40,7 +41,7 @@ static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...) buf = xrealloc(buf, alloc); *bufp = buf; } - *sizep = newsize; + *sizep = newsize - 1; memcpy(buf + size, one_line, len); } @@ -77,6 +78,11 @@ static int new_parent(int idx) return 1; } +static const char commit_utf8_warn[] = +"Warning: commit message does not conform to UTF-8.\n" +"You may want to amend it after fixing the message, or set the config\n" +"variable i18n.commitencoding to the encoding your project uses.\n"; + int cmd_commit_tree(int argc, const char **argv, const char *prefix) { int i; @@ -86,6 +92,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) char comment[1000]; char *buffer; unsigned int size; + int encoding_is_utf8; setup_ident(); git_config(git_default_config); @@ -101,14 +108,18 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) a = argv[i]; b = argv[i+1]; if (!b || strcmp(a, "-p")) usage(commit_tree_usage); + + if (parents >= MAXPARENT) + die("Too many parents (%d max)", MAXPARENT); if (get_sha1(b, parent_sha1[parents])) die("Not a valid object name %s", b); check_valid(parent_sha1[parents], commit_type); if (new_parent(parents)) parents++; } - if (!parents) - fprintf(stderr, "Committing initial tree %s\n", argv[1]); + + /* Not having i18n.commitencoding is the same as having utf-8 */ + encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); init_buffer(&buffer, &size); add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1)); @@ -123,12 +134,21 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) /* Person/date information */ add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); - add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1)); + add_buffer(&buffer, &size, "committer %s\n", git_committer_info(1)); + if (!encoding_is_utf8) + add_buffer(&buffer, &size, + "encoding %s\n", git_commit_encoding); + add_buffer(&buffer, &size, "\n"); /* And add the comment */ while (fgets(comment, sizeof(comment), stdin) != NULL) add_buffer(&buffer, &size, "%s", comment); + /* And check the encoding */ + buffer[size] = '\0'; + if (encoding_is_utf8 && !is_utf8(buffer)) + fprintf(stderr, commit_utf8_warn); + if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) { printf("%s\n", sha1_to_hex(commit_sha1)); return 0; diff --git a/builtin-count-objects.c b/builtin-count-objects.c index 1d3729aa99..f5b22bb80e 100644 --- a/builtin-count-objects.c +++ b/builtin-count-objects.c @@ -62,7 +62,7 @@ static void count_objects(DIR *d, char *path, int len, int verbose, hex[40] = 0; if (get_sha1_hex(hex, sha1)) die("internal error"); - if (has_sha1_pack(sha1)) + if (has_sha1_pack(sha1, NULL)) (*packed_loose)++; } } @@ -105,16 +105,19 @@ int cmd_count_objects(int ac, const char **av, const char *prefix) } if (verbose) { struct packed_git *p; + unsigned long num_pack = 0; if (!packed_git) prepare_packed_git(); for (p = packed_git; p; p = p->next) { if (!p->pack_local) continue; packed += num_packed_objects(p); + num_pack++; } printf("count: %lu\n", loose); printf("size: %lu\n", loose_size / 2); printf("in-pack: %lu\n", packed); + printf("packs: %lu\n", num_pack); printf("prune-packable: %lu\n", packed_loose); printf("garbage: %lu\n", garbage); } diff --git a/describe.c b/builtin-describe.c index 2b9301fc12..a8c98cea16 100644 --- a/describe.c +++ b/builtin-describe.c @@ -2,8 +2,10 @@ #include "commit.h" #include "tag.h" #include "refs.h" - -#define SEEN (1u << 0) +#include "diff.h" +#include "diffcore.h" +#include "revision.h" +#include "builtin.h" static const char describe_usage[] = "git-describe [--all] [--tags] [--abbrev=<n>] <committish>*"; @@ -15,7 +17,7 @@ static int abbrev = DEFAULT_ABBREV; static int names, allocs; static struct commit_name { - const struct commit *commit; + struct commit *commit; int prio; /* annotated tag = 2, tag = 1, head = 0 */ char path[FLEX_ARRAY]; /* more */ } **name_array = NULL; @@ -34,7 +36,7 @@ static struct commit_name *match(struct commit *cmit) } static void add_to_known_names(const char *path, - const struct commit *commit, + struct commit *commit, int prio) { int idx; @@ -42,7 +44,7 @@ static void add_to_known_names(const char *path, struct commit_name *name = xmalloc(sizeof(struct commit_name) + len); name->commit = commit; - name->prio = prio; + name->prio = prio; memcpy(name->path, path, len); idx = names; if (idx >= allocs) { @@ -53,7 +55,7 @@ static void add_to_known_names(const char *path, names = ++idx; } -static int get_name(const char *path, const unsigned char *sha1) +static int get_name(const char *path, const unsigned char *sha1, int flag, void *cb_data) { struct commit *commit = lookup_commit_reference_gently(sha1, 1); struct object *object; @@ -97,6 +99,12 @@ static int compare_names(const void *_a, const void *_b) return (a_date > b_date) ? -1 : (a_date == b_date) ? 0 : 1; } +struct possible_tag { + struct possible_tag *next; + struct commit_name *name; + unsigned long depth; +}; + static void describe(const char *arg, int last_one) { unsigned char sha1[20]; @@ -104,6 +112,7 @@ static void describe(const char *arg, int last_one) struct commit_list *list; static int initialized = 0; struct commit_name *n; + struct possible_tag *all_matches, *min_match, *cur_match; if (get_sha1(arg, sha1)) die("Not a valid object name %s", arg); @@ -113,7 +122,7 @@ static void describe(const char *arg, int last_one) if (!initialized) { initialized = 1; - for_each_ref(get_name); + for_each_ref(get_name, NULL); qsort(name_array, names, sizeof(*name_array), compare_names); } @@ -124,22 +133,71 @@ static void describe(const char *arg, int last_one) } list = NULL; + all_matches = NULL; + cur_match = NULL; commit_list_insert(cmit, &list); while (list) { - struct commit *c = pop_most_recent_commit(&list, SEEN); + struct commit *c = pop_commit(&list); n = match(c); if (n) { - printf("%s-g%s\n", n->path, - find_unique_abbrev(cmit->object.sha1, abbrev)); - if (!last_one) - clear_commit_marks(cmit, SEEN); - return; + struct possible_tag *p = xmalloc(sizeof(*p)); + p->name = n; + p->next = NULL; + if (cur_match) + cur_match->next = p; + else + all_matches = p; + cur_match = p; + } else { + struct commit_list *parents = c->parents; + while (parents) { + struct commit *p = parents->item; + parse_commit(p); + if (!(p->object.flags & SEEN)) { + p->object.flags |= SEEN; + insert_by_date(p, &list); + } + parents = parents->next; + } + } + } + + if (!all_matches) + die("cannot describe '%s'", sha1_to_hex(cmit->object.sha1)); + + min_match = NULL; + for (cur_match = all_matches; cur_match; cur_match = cur_match->next) { + struct rev_info revs; + struct commit *tagged = cur_match->name->commit; + + clear_commit_marks(cmit, -1); + init_revisions(&revs, NULL); + tagged->object.flags |= UNINTERESTING; + add_pending_object(&revs, &tagged->object, NULL); + add_pending_object(&revs, &cmit->object, NULL); + + prepare_revision_walk(&revs); + cur_match->depth = 0; + while ((!min_match || cur_match->depth < min_match->depth) + && get_revision(&revs)) + cur_match->depth++; + if (!min_match || cur_match->depth < min_match->depth) + min_match = cur_match; + free_commit_list(revs.commits); + } + printf("%s-g%s\n", min_match->name->path, + find_unique_abbrev(cmit->object.sha1, abbrev)); + + if (!last_one) { + for (cur_match = all_matches; cur_match; cur_match = min_match) { + min_match = cur_match->next; + free(cur_match); } + clear_commit_marks(cmit, SEEN); } - die("cannot describe '%s'", sha1_to_hex(cmit->object.sha1)); } -int main(int argc, char **argv) +int cmd_describe(int argc, const char **argv, const char *prefix) { int i; @@ -154,14 +212,16 @@ int main(int argc, char **argv) tags = 1; else if (!strncmp(arg, "--abbrev=", 9)) { abbrev = strtoul(arg + 9, NULL, 10); - if (abbrev < MINIMUM_ABBREV || 40 <= abbrev) + if (abbrev < MINIMUM_ABBREV || 40 < abbrev) abbrev = DEFAULT_ABBREV; } else usage(describe_usage); } - if (i == argc) + save_commit_buffer = 0; + + if (argc <= i) describe("HEAD", 1); else while (i < argc) { diff --git a/builtin-fmt-merge-msg.c b/builtin-fmt-merge-msg.c index 28b5dfd054..87d3d63ec7 100644 --- a/builtin-fmt-merge-msg.c +++ b/builtin-fmt-merge-msg.c @@ -27,8 +27,8 @@ static void append_to_list(struct list *list, char *value, void *payload) { if (list->nr == list->alloc) { list->alloc += 32; - list->list = realloc(list->list, sizeof(char *) * list->alloc); - list->payload = realloc(list->payload, + list->list = xrealloc(list->list, sizeof(char *) * list->alloc); + list->payload = xrealloc(list->payload, sizeof(char *) * list->alloc); } list->payload[list->nr] = payload; @@ -55,8 +55,7 @@ static void free_list(struct list *list) for (i = 0; i < list->nr; i++) { free(list->list[i]); - if (list->payload[i]) - free(list->payload[i]); + free(list->payload[i]); } free(list->list); free(list->payload); @@ -112,43 +111,43 @@ static int handle_line(char *line) i = find_in_list(&srcs, src); if (i < 0) { i = srcs.nr; - append_to_list(&srcs, strdup(src), + append_to_list(&srcs, xstrdup(src), xcalloc(1, sizeof(struct src_data))); } src_data = srcs.payload[i]; if (pulling_head) { - origin = strdup(src); + origin = xstrdup(src); src_data->head_status |= 1; } else if (!strncmp(line, "branch ", 7)) { - origin = strdup(line + 7); + origin = xstrdup(line + 7); append_to_list(&src_data->branch, origin, NULL); src_data->head_status |= 2; } else if (!strncmp(line, "tag ", 4)) { origin = line; - append_to_list(&src_data->tag, strdup(origin + 4), NULL); + append_to_list(&src_data->tag, xstrdup(origin + 4), NULL); src_data->head_status |= 2; } else if (!strncmp(line, "remote branch ", 14)) { - origin = strdup(line + 14); + origin = xstrdup(line + 14); append_to_list(&src_data->r_branch, origin, NULL); src_data->head_status |= 2; } else { - origin = strdup(src); - append_to_list(&src_data->generic, strdup(line), NULL); + origin = xstrdup(src); + append_to_list(&src_data->generic, xstrdup(line), NULL); src_data->head_status |= 2; } if (!strcmp(".", src) || !strcmp(src, origin)) { int len = strlen(origin); if (origin[0] == '\'' && origin[len - 1] == '\'') { - char *new_origin = malloc(len - 1); + char *new_origin = xmalloc(len - 1); memcpy(new_origin, origin + 1, len - 2); - new_origin[len - 1] = 0; + new_origin[len - 2] = 0; origin = new_origin; } else - origin = strdup(origin); + origin = xstrdup(origin); } else { - char *new_origin = malloc(strlen(origin) + strlen(src) + 5); + char *new_origin = xmalloc(strlen(origin) + strlen(src) + 5); sprintf(new_origin, "%s of %s", origin, src); origin = new_origin; } @@ -204,7 +203,7 @@ static void shortlog(const char *name, unsigned char *sha1, bol = strstr(commit->buffer, "\n\n"); if (!bol) { - append_to_list(&subjects, strdup(sha1_to_hex( + append_to_list(&subjects, xstrdup(sha1_to_hex( commit->object.sha1)), NULL); continue; @@ -215,11 +214,11 @@ static void shortlog(const char *name, unsigned char *sha1, if (eol) { int len = eol - bol; - oneline = malloc(len + 1); + oneline = xmalloc(len + 1); memcpy(oneline, bol, len); oneline[len] = 0; } else - oneline = strdup(bol); + oneline = xstrdup(bol); append_to_list(&subjects, oneline, NULL); } @@ -250,7 +249,7 @@ int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix) FILE *in = stdin; const char *sep = ""; unsigned char head_sha1[20]; - const char *head, *current_branch; + const char *current_branch; git_config(fmt_merge_msg_config); @@ -278,10 +277,9 @@ int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix) usage(fmt_merge_msg_usage); /* get current branch */ - head = strdup(git_path("HEAD")); - current_branch = resolve_ref(head, head_sha1, 1); - current_branch += strlen(head) - 4; - free((char *)head); + current_branch = resolve_ref("HEAD", head_sha1, 1, NULL); + if (!current_branch) + die("No current branch"); if (!strncmp(current_branch, "refs/heads/", 11)) current_branch += 11; diff --git a/builtin-for-each-ref.c b/builtin-for-each-ref.c new file mode 100644 index 0000000000..af72a12a57 --- /dev/null +++ b/builtin-for-each-ref.c @@ -0,0 +1,895 @@ +#include "cache.h" +#include "refs.h" +#include "object.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "quote.h" + +/* Quoting styles */ +#define QUOTE_NONE 0 +#define QUOTE_SHELL 1 +#define QUOTE_PERL 2 +#define QUOTE_PYTHON 3 + +typedef enum { FIELD_STR, FIELD_ULONG, FIELD_TIME } cmp_type; + +struct atom_value { + const char *s; + unsigned long ul; /* used for sorting when not FIELD_STR */ +}; + +struct ref_sort { + struct ref_sort *next; + int atom; /* index into used_atom array */ + unsigned reverse : 1; +}; + +struct refinfo { + char *refname; + unsigned char objectname[20]; + struct atom_value *value; +}; + +static struct { + const char *name; + cmp_type cmp_type; +} valid_atom[] = { + { "refname" }, + { "objecttype" }, + { "objectsize", FIELD_ULONG }, + { "objectname" }, + { "tree" }, + { "parent" }, /* NEEDSWORK: how to address 2nd and later parents? */ + { "numparent", FIELD_ULONG }, + { "object" }, + { "type" }, + { "tag" }, + { "author" }, + { "authorname" }, + { "authoremail" }, + { "authordate", FIELD_TIME }, + { "committer" }, + { "committername" }, + { "committeremail" }, + { "committerdate", FIELD_TIME }, + { "tagger" }, + { "taggername" }, + { "taggeremail" }, + { "taggerdate", FIELD_TIME }, + { "creator" }, + { "creatordate", FIELD_TIME }, + { "subject" }, + { "body" }, + { "contents" }, +}; + +/* + * An atom is a valid field atom listed above, possibly prefixed with + * a "*" to denote deref_tag(). + * + * We parse given format string and sort specifiers, and make a list + * of properties that we need to extract out of objects. refinfo + * structure will hold an array of values extracted that can be + * indexed with the "atom number", which is an index into this + * array. + */ +static const char **used_atom; +static cmp_type *used_atom_type; +static int used_atom_cnt, sort_atom_limit, need_tagged; + +/* + * Used to parse format string and sort specifiers + */ +static int parse_atom(const char *atom, const char *ep) +{ + const char *sp; + char *n; + int i, at; + + sp = atom; + if (*sp == '*' && sp < ep) + sp++; /* deref */ + if (ep <= sp) + die("malformed field name: %.*s", (int)(ep-atom), atom); + + /* Do we have the atom already used elsewhere? */ + for (i = 0; i < used_atom_cnt; i++) { + int len = strlen(used_atom[i]); + if (len == ep - atom && !memcmp(used_atom[i], atom, len)) + return i; + } + + /* Is the atom a valid one? */ + for (i = 0; i < ARRAY_SIZE(valid_atom); i++) { + int len = strlen(valid_atom[i].name); + if (len == ep - sp && !memcmp(valid_atom[i].name, sp, len)) + break; + } + + if (ARRAY_SIZE(valid_atom) <= i) + die("unknown field name: %.*s", (int)(ep-atom), atom); + + /* Add it in, including the deref prefix */ + at = used_atom_cnt; + used_atom_cnt++; + used_atom = xrealloc(used_atom, + (sizeof *used_atom) * used_atom_cnt); + used_atom_type = xrealloc(used_atom_type, + (sizeof(*used_atom_type) * used_atom_cnt)); + n = xmalloc(ep - atom + 1); + memcpy(n, atom, ep - atom); + n[ep-atom] = 0; + used_atom[at] = n; + used_atom_type[at] = valid_atom[i].cmp_type; + return at; +} + +/* + * In a format string, find the next occurrence of %(atom). + */ +static const char *find_next(const char *cp) +{ + while (*cp) { + if (*cp == '%') { + /* %( is the start of an atom; + * %% is a quoteed per-cent. + */ + if (cp[1] == '(') + return cp; + else if (cp[1] == '%') + cp++; /* skip over two % */ + /* otherwise this is a singleton, literal % */ + } + cp++; + } + return NULL; +} + +/* + * Make sure the format string is well formed, and parse out + * the used atoms. + */ +static void verify_format(const char *format) +{ + const char *cp, *sp; + for (cp = format; *cp && (sp = find_next(cp)); ) { + const char *ep = strchr(sp, ')'); + if (!ep) + die("malformatted format string %s", sp); + /* sp points at "%(" and ep points at the closing ")" */ + parse_atom(sp + 2, ep); + cp = ep + 1; + } +} + +/* + * Given an object name, read the object data and size, and return a + * "struct object". If the object data we are returning is also borrowed + * by the "struct object" representation, set *eaten as well---it is a + * signal from parse_object_buffer to us not to free the buffer. + */ +static void *get_obj(const unsigned char *sha1, struct object **obj, unsigned long *sz, int *eaten) +{ + char type[20]; + void *buf = read_sha1_file(sha1, type, sz); + + if (buf) + *obj = parse_object_buffer(sha1, type, *sz, buf, eaten); + else + *obj = NULL; + return buf; +} + +/* See grab_values */ +static void grab_common_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + int i; + + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + if (!strcmp(name, "objecttype")) + v->s = type_names[obj->type]; + else if (!strcmp(name, "objectsize")) { + char *s = xmalloc(40); + sprintf(s, "%lu", sz); + v->ul = sz; + v->s = s; + } + else if (!strcmp(name, "objectname")) { + char *s = xmalloc(41); + strcpy(s, sha1_to_hex(obj->sha1)); + v->s = s; + } + } +} + +/* See grab_values */ +static void grab_tag_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + int i; + struct tag *tag = (struct tag *) obj; + + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + if (!strcmp(name, "tag")) + v->s = tag->tag; + } +} + +static int num_parents(struct commit *commit) +{ + struct commit_list *parents; + int i; + + for (i = 0, parents = commit->parents; + parents; + parents = parents->next) + i++; + return i; +} + +/* See grab_values */ +static void grab_commit_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + int i; + struct commit *commit = (struct commit *) obj; + + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + if (!strcmp(name, "tree")) { + char *s = xmalloc(41); + strcpy(s, sha1_to_hex(commit->tree->object.sha1)); + v->s = s; + } + if (!strcmp(name, "numparent")) { + char *s = xmalloc(40); + sprintf(s, "%lu", v->ul); + v->s = s; + v->ul = num_parents(commit); + } + else if (!strcmp(name, "parent")) { + int num = num_parents(commit); + int i; + struct commit_list *parents; + char *s = xmalloc(42 * num); + v->s = s; + for (i = 0, parents = commit->parents; + parents; + parents = parents->next, i = i + 42) { + struct commit *parent = parents->item; + strcpy(s+i, sha1_to_hex(parent->object.sha1)); + if (parents->next) + s[i+40] = ' '; + } + } + } +} + +static const char *find_wholine(const char *who, int wholen, const char *buf, unsigned long sz) +{ + const char *eol; + while (*buf) { + if (!strncmp(buf, who, wholen) && + buf[wholen] == ' ') + return buf + wholen + 1; + eol = strchr(buf, '\n'); + if (!eol) + return ""; + eol++; + if (eol[1] == '\n') + return ""; /* end of header */ + buf = eol; + } + return ""; +} + +static char *copy_line(const char *buf) +{ + const char *eol = strchr(buf, '\n'); + char *line; + int len; + if (!eol) + return ""; + len = eol - buf; + line = xmalloc(len + 1); + memcpy(line, buf, len); + line[len] = 0; + return line; +} + +static char *copy_name(const char *buf) +{ + const char *eol = strchr(buf, '\n'); + const char *eoname = strstr(buf, " <"); + char *line; + int len; + if (!(eoname && eol && eoname < eol)) + return ""; + len = eoname - buf; + line = xmalloc(len + 1); + memcpy(line, buf, len); + line[len] = 0; + return line; +} + +static char *copy_email(const char *buf) +{ + const char *email = strchr(buf, '<'); + const char *eoemail = strchr(email, '>'); + char *line; + int len; + if (!email || !eoemail) + return ""; + eoemail++; + len = eoemail - email; + line = xmalloc(len + 1); + memcpy(line, email, len); + line[len] = 0; + return line; +} + +static void grab_date(const char *buf, struct atom_value *v) +{ + const char *eoemail = strstr(buf, "> "); + char *zone; + unsigned long timestamp; + long tz; + + if (!eoemail) + goto bad; + timestamp = strtoul(eoemail + 2, &zone, 10); + if (timestamp == ULONG_MAX) + goto bad; + tz = strtol(zone, NULL, 10); + if ((tz == LONG_MIN || tz == LONG_MAX) && errno == ERANGE) + goto bad; + v->s = xstrdup(show_date(timestamp, tz, 0)); + v->ul = timestamp; + return; + bad: + v->s = ""; + v->ul = 0; +} + +/* See grab_values */ +static void grab_person(const char *who, struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + int i; + int wholen = strlen(who); + const char *wholine = NULL; + + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + if (strncmp(who, name, wholen)) + continue; + if (name[wholen] != 0 && + strcmp(name + wholen, "name") && + strcmp(name + wholen, "email") && + strcmp(name + wholen, "date")) + continue; + if (!wholine) + wholine = find_wholine(who, wholen, buf, sz); + if (!wholine) + return; /* no point looking for it */ + if (name[wholen] == 0) + v->s = copy_line(wholine); + else if (!strcmp(name + wholen, "name")) + v->s = copy_name(wholine); + else if (!strcmp(name + wholen, "email")) + v->s = copy_email(wholine); + else if (!strcmp(name + wholen, "date")) + grab_date(wholine, v); + } + + /* For a tag or a commit object, if "creator" or "creatordate" is + * requested, do something special. + */ + if (strcmp(who, "tagger") && strcmp(who, "committer")) + return; /* "author" for commit object is not wanted */ + if (!wholine) + wholine = find_wholine(who, wholen, buf, sz); + if (!wholine) + return; + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + + if (!strcmp(name, "creatordate")) + grab_date(wholine, v); + else if (!strcmp(name, "creator")) + v->s = copy_line(wholine); + } +} + +static void find_subpos(const char *buf, unsigned long sz, const char **sub, const char **body) +{ + while (*buf) { + const char *eol = strchr(buf, '\n'); + if (!eol) + return; + if (eol[1] == '\n') { + buf = eol + 1; + break; /* found end of header */ + } + buf = eol + 1; + } + while (*buf == '\n') + buf++; + if (!*buf) + return; + *sub = buf; /* first non-empty line */ + buf = strchr(buf, '\n'); + if (!buf) + return; /* no body */ + while (*buf == '\n') + buf++; /* skip blank between subject and body */ + *body = buf; +} + +/* See grab_values */ +static void grab_sub_body_contents(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + int i; + const char *subpos = NULL, *bodypos = NULL; + + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) + continue; + if (deref) + name++; + if (strcmp(name, "subject") && + strcmp(name, "body") && + strcmp(name, "contents")) + continue; + if (!subpos) + find_subpos(buf, sz, &subpos, &bodypos); + if (!subpos) + return; + + if (!strcmp(name, "subject")) + v->s = copy_line(subpos); + else if (!strcmp(name, "body")) + v->s = xstrdup(bodypos); + else if (!strcmp(name, "contents")) + v->s = xstrdup(subpos); + } +} + +/* We want to have empty print-string for field requests + * that do not apply (e.g. "authordate" for a tag object) + */ +static void fill_missing_values(struct atom_value *val) +{ + int i; + for (i = 0; i < used_atom_cnt; i++) { + struct atom_value *v = &val[i]; + if (v->s == NULL) + v->s = ""; + } +} + +/* + * val is a list of atom_value to hold returned values. Extract + * the values for atoms in used_atom array out of (obj, buf, sz). + * when deref is false, (obj, buf, sz) is the object that is + * pointed at by the ref itself; otherwise it is the object the + * ref (which is a tag) refers to. + */ +static void grab_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) +{ + grab_common_values(val, deref, obj, buf, sz); + switch (obj->type) { + case OBJ_TAG: + grab_tag_values(val, deref, obj, buf, sz); + grab_sub_body_contents(val, deref, obj, buf, sz); + grab_person("tagger", val, deref, obj, buf, sz); + break; + case OBJ_COMMIT: + grab_commit_values(val, deref, obj, buf, sz); + grab_sub_body_contents(val, deref, obj, buf, sz); + grab_person("author", val, deref, obj, buf, sz); + grab_person("committer", val, deref, obj, buf, sz); + break; + case OBJ_TREE: + // grab_tree_values(val, deref, obj, buf, sz); + break; + case OBJ_BLOB: + // grab_blob_values(val, deref, obj, buf, sz); + break; + default: + die("Eh? Object of type %d?", obj->type); + } +} + +/* + * Parse the object referred by ref, and grab needed value. + */ +static void populate_value(struct refinfo *ref) +{ + void *buf; + struct object *obj; + int eaten, i; + unsigned long size; + const unsigned char *tagged; + + ref->value = xcalloc(sizeof(struct atom_value), used_atom_cnt); + + buf = get_obj(ref->objectname, &obj, &size, &eaten); + if (!buf) + die("missing object %s for %s", + sha1_to_hex(ref->objectname), ref->refname); + if (!obj) + die("parse_object_buffer failed on %s for %s", + sha1_to_hex(ref->objectname), ref->refname); + + /* Fill in specials first */ + for (i = 0; i < used_atom_cnt; i++) { + const char *name = used_atom[i]; + struct atom_value *v = &ref->value[i]; + if (!strcmp(name, "refname")) + v->s = ref->refname; + else if (!strcmp(name, "*refname")) { + int len = strlen(ref->refname); + char *s = xmalloc(len + 4); + sprintf(s, "%s^{}", ref->refname); + v->s = s; + } + } + + grab_values(ref->value, 0, obj, buf, size); + if (!eaten) + free(buf); + + /* If there is no atom that wants to know about tagged + * object, we are done. + */ + if (!need_tagged || (obj->type != OBJ_TAG)) + return; + + /* If it is a tag object, see if we use a value that derefs + * the object, and if we do grab the object it refers to. + */ + tagged = ((struct tag *)obj)->tagged->sha1; + + /* NEEDSWORK: This derefs tag only once, which + * is good to deal with chains of trust, but + * is not consistent with what deref_tag() does + * which peels the onion to the core. + */ + buf = get_obj(tagged, &obj, &size, &eaten); + if (!buf) + die("missing object %s for %s", + sha1_to_hex(tagged), ref->refname); + if (!obj) + die("parse_object_buffer failed on %s for %s", + sha1_to_hex(tagged), ref->refname); + grab_values(ref->value, 1, obj, buf, size); + if (!eaten) + free(buf); +} + +/* + * Given a ref, return the value for the atom. This lazily gets value + * out of the object by calling populate value. + */ +static void get_value(struct refinfo *ref, int atom, struct atom_value **v) +{ + if (!ref->value) { + populate_value(ref); + fill_missing_values(ref->value); + } + *v = &ref->value[atom]; +} + +struct grab_ref_cbdata { + struct refinfo **grab_array; + const char **grab_pattern; + int grab_cnt; +}; + +/* + * A call-back given to for_each_ref(). It is unfortunate that we + * need to use global variables to pass extra information to this + * function. + */ +static int grab_single_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) +{ + struct grab_ref_cbdata *cb = cb_data; + struct refinfo *ref; + int cnt; + + if (*cb->grab_pattern) { + const char **pattern; + int namelen = strlen(refname); + for (pattern = cb->grab_pattern; *pattern; pattern++) { + const char *p = *pattern; + int plen = strlen(p); + + if ((plen <= namelen) && + !strncmp(refname, p, plen) && + (refname[plen] == '\0' || + refname[plen] == '/')) + break; + if (!fnmatch(p, refname, FNM_PATHNAME)) + break; + } + if (!*pattern) + return 0; + } + + /* We do not open the object yet; sort may only need refname + * to do its job and the resulting list may yet to be pruned + * by maxcount logic. + */ + ref = xcalloc(1, sizeof(*ref)); + ref->refname = xstrdup(refname); + hashcpy(ref->objectname, sha1); + + cnt = cb->grab_cnt; + cb->grab_array = xrealloc(cb->grab_array, + sizeof(*cb->grab_array) * (cnt + 1)); + cb->grab_array[cnt++] = ref; + cb->grab_cnt = cnt; + return 0; +} + +static int cmp_ref_sort(struct ref_sort *s, struct refinfo *a, struct refinfo *b) +{ + struct atom_value *va, *vb; + int cmp; + cmp_type cmp_type = used_atom_type[s->atom]; + + get_value(a, s->atom, &va); + get_value(b, s->atom, &vb); + switch (cmp_type) { + case FIELD_STR: + cmp = strcmp(va->s, vb->s); + break; + default: + if (va->ul < vb->ul) + cmp = -1; + else if (va->ul == vb->ul) + cmp = 0; + else + cmp = 1; + break; + } + return (s->reverse) ? -cmp : cmp; +} + +static struct ref_sort *ref_sort; +static int compare_refs(const void *a_, const void *b_) +{ + struct refinfo *a = *((struct refinfo **)a_); + struct refinfo *b = *((struct refinfo **)b_); + struct ref_sort *s; + + for (s = ref_sort; s; s = s->next) { + int cmp = cmp_ref_sort(s, a, b); + if (cmp) + return cmp; + } + return 0; +} + +static void sort_refs(struct ref_sort *sort, struct refinfo **refs, int num_refs) +{ + ref_sort = sort; + qsort(refs, num_refs, sizeof(struct refinfo *), compare_refs); +} + +static void print_value(struct refinfo *ref, int atom, int quote_style) +{ + struct atom_value *v; + get_value(ref, atom, &v); + switch (quote_style) { + case QUOTE_NONE: + fputs(v->s, stdout); + break; + case QUOTE_SHELL: + sq_quote_print(stdout, v->s); + break; + case QUOTE_PERL: + perl_quote_print(stdout, v->s); + break; + case QUOTE_PYTHON: + python_quote_print(stdout, v->s); + break; + } +} + +static int hex1(char ch) +{ + if ('0' <= ch && ch <= '9') + return ch - '0'; + else if ('a' <= ch && ch <= 'f') + return ch - 'a' + 10; + else if ('A' <= ch && ch <= 'F') + return ch - 'A' + 10; + return -1; +} +static int hex2(const char *cp) +{ + if (cp[0] && cp[1]) + return (hex1(cp[0]) << 4) | hex1(cp[1]); + else + return -1; +} + +static void emit(const char *cp, const char *ep) +{ + while (*cp && (!ep || cp < ep)) { + if (*cp == '%') { + if (cp[1] == '%') + cp++; + else { + int ch = hex2(cp + 1); + if (0 <= ch) { + putchar(ch); + cp += 3; + continue; + } + } + } + putchar(*cp); + cp++; + } +} + +static void show_ref(struct refinfo *info, const char *format, int quote_style) +{ + const char *cp, *sp, *ep; + + for (cp = format; *cp && (sp = find_next(cp)); cp = ep + 1) { + ep = strchr(sp, ')'); + if (cp < sp) + emit(cp, sp); + print_value(info, parse_atom(sp + 2, ep), quote_style); + } + if (*cp) { + sp = cp + strlen(cp); + emit(cp, sp); + } + putchar('\n'); +} + +static struct ref_sort *default_sort(void) +{ + static const char cstr_name[] = "refname"; + + struct ref_sort *sort = xcalloc(1, sizeof(*sort)); + + sort->next = NULL; + sort->atom = parse_atom(cstr_name, cstr_name + strlen(cstr_name)); + return sort; +} + +int cmd_for_each_ref(int ac, const char **av, char *prefix) +{ + int i, num_refs; + const char *format = NULL; + struct ref_sort *sort = NULL, **sort_tail = &sort; + int maxcount = 0; + int quote_style = -1; /* unspecified yet */ + struct refinfo **refs; + struct grab_ref_cbdata cbdata; + + for (i = 1; i < ac; i++) { + const char *arg = av[i]; + if (arg[0] != '-') + break; + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strncmp(arg, "--format=", 9)) { + if (format) + die("more than one --format?"); + format = arg + 9; + continue; + } + if (!strcmp(arg, "-s") || !strcmp(arg, "--shell") ) { + if (0 <= quote_style) + die("more than one quoting style?"); + quote_style = QUOTE_SHELL; + continue; + } + if (!strcmp(arg, "-p") || !strcmp(arg, "--perl") ) { + if (0 <= quote_style) + die("more than one quoting style?"); + quote_style = QUOTE_PERL; + continue; + } + if (!strcmp(arg, "--python") ) { + if (0 <= quote_style) + die("more than one quoting style?"); + quote_style = QUOTE_PYTHON; + continue; + } + if (!strncmp(arg, "--count=", 8)) { + if (maxcount) + die("more than one --count?"); + maxcount = atoi(arg + 8); + if (maxcount <= 0) + die("The number %s did not parse", arg); + continue; + } + if (!strncmp(arg, "--sort=", 7)) { + struct ref_sort *s = xcalloc(1, sizeof(*s)); + int len; + + s->next = NULL; + *sort_tail = s; + sort_tail = &s->next; + + arg += 7; + if (*arg == '-') { + s->reverse = 1; + arg++; + } + len = strlen(arg); + sort->atom = parse_atom(arg, arg+len); + continue; + } + break; + } + if (quote_style < 0) + quote_style = QUOTE_NONE; + + if (!sort) + sort = default_sort(); + sort_atom_limit = used_atom_cnt; + if (!format) + format = "%(objectname) %(objecttype)\t%(refname)"; + + verify_format(format); + + memset(&cbdata, 0, sizeof(cbdata)); + cbdata.grab_pattern = av + i; + for_each_ref(grab_single_ref, &cbdata); + refs = cbdata.grab_array; + num_refs = cbdata.grab_cnt; + + for (i = 0; i < used_atom_cnt; i++) { + if (used_atom[i][0] == '*') { + need_tagged = 1; + break; + } + } + + sort_refs(sort, refs, num_refs); + + if (!maxcount || num_refs < maxcount) + maxcount = num_refs; + for (i = 0; i < maxcount; i++) + show_ref(refs[i], format, quote_style); + return 0; +} diff --git a/builtin-grep.c b/builtin-grep.c index 0bd517b264..2bfbdb7140 100644 --- a/builtin-grep.c +++ b/builtin-grep.c @@ -10,9 +10,7 @@ #include "tag.h" #include "tree-walk.h" #include "builtin.h" -#include <regex.h> -#include <fnmatch.h> -#include <sys/wait.h> +#include "grep.h" /* * git grep pathspecs are somewhat different from diff-tree pathspecs; @@ -82,499 +80,6 @@ static int pathspec_matches(const char **paths, const char *name) return 0; } -enum grep_pat_token { - GREP_PATTERN, - GREP_AND, - GREP_OPEN_PAREN, - GREP_CLOSE_PAREN, - GREP_NOT, - GREP_OR, -}; - -struct grep_pat { - struct grep_pat *next; - const char *origin; - int no; - enum grep_pat_token token; - const char *pattern; - regex_t regexp; -}; - -enum grep_expr_node { - GREP_NODE_ATOM, - GREP_NODE_NOT, - GREP_NODE_AND, - GREP_NODE_OR, -}; - -struct grep_expr { - enum grep_expr_node node; - union { - struct grep_pat *atom; - struct grep_expr *unary; - struct { - struct grep_expr *left; - struct grep_expr *right; - } binary; - } u; -}; - -struct grep_opt { - struct grep_pat *pattern_list; - struct grep_pat **pattern_tail; - struct grep_expr *pattern_expression; - int prefix_length; - regex_t regexp; - unsigned linenum:1; - unsigned invert:1; - unsigned name_only:1; - unsigned unmatch_name_only:1; - unsigned count:1; - unsigned word_regexp:1; - unsigned fixed:1; -#define GREP_BINARY_DEFAULT 0 -#define GREP_BINARY_NOMATCH 1 -#define GREP_BINARY_TEXT 2 - unsigned binary:2; - unsigned extended:1; - unsigned relative:1; - int regflags; - unsigned pre_context; - unsigned post_context; -}; - -static void add_pattern(struct grep_opt *opt, const char *pat, - const char *origin, int no, enum grep_pat_token t) -{ - struct grep_pat *p = xcalloc(1, sizeof(*p)); - p->pattern = pat; - p->origin = origin; - p->no = no; - p->token = t; - *opt->pattern_tail = p; - opt->pattern_tail = &p->next; - p->next = NULL; -} - -static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) -{ - int err = regcomp(&p->regexp, p->pattern, opt->regflags); - if (err) { - char errbuf[1024]; - char where[1024]; - if (p->no) - sprintf(where, "In '%s' at %d, ", - p->origin, p->no); - else if (p->origin) - sprintf(where, "%s, ", p->origin); - else - where[0] = 0; - regerror(err, &p->regexp, errbuf, 1024); - regfree(&p->regexp); - die("%s'%s': %s", where, p->pattern, errbuf); - } -} - -static struct grep_expr *compile_pattern_expr(struct grep_pat **); -static struct grep_expr *compile_pattern_atom(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x; - - p = *list; - switch (p->token) { - case GREP_PATTERN: /* atom */ - x = xcalloc(1, sizeof (struct grep_expr)); - x->node = GREP_NODE_ATOM; - x->u.atom = p; - *list = p->next; - return x; - case GREP_OPEN_PAREN: - *list = p->next; - x = compile_pattern_expr(list); - if (!x) - return NULL; - if (!*list || (*list)->token != GREP_CLOSE_PAREN) - die("unmatched parenthesis"); - *list = (*list)->next; - return x; - default: - return NULL; - } -} - -static struct grep_expr *compile_pattern_not(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x; - - p = *list; - switch (p->token) { - case GREP_NOT: - if (!p->next) - die("--not not followed by pattern expression"); - *list = p->next; - x = xcalloc(1, sizeof (struct grep_expr)); - x->node = GREP_NODE_NOT; - x->u.unary = compile_pattern_not(list); - if (!x->u.unary) - die("--not followed by non pattern expression"); - return x; - default: - return compile_pattern_atom(list); - } -} - -static struct grep_expr *compile_pattern_and(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x, *y, *z; - - x = compile_pattern_not(list); - p = *list; - if (p && p->token == GREP_AND) { - if (!p->next) - die("--and not followed by pattern expression"); - *list = p->next; - y = compile_pattern_and(list); - if (!y) - die("--and not followed by pattern expression"); - z = xcalloc(1, sizeof (struct grep_expr)); - z->node = GREP_NODE_AND; - z->u.binary.left = x; - z->u.binary.right = y; - return z; - } - return x; -} - -static struct grep_expr *compile_pattern_or(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x, *y, *z; - - x = compile_pattern_and(list); - p = *list; - if (x && p && p->token != GREP_CLOSE_PAREN) { - y = compile_pattern_or(list); - if (!y) - die("not a pattern expression %s", p->pattern); - z = xcalloc(1, sizeof (struct grep_expr)); - z->node = GREP_NODE_OR; - z->u.binary.left = x; - z->u.binary.right = y; - return z; - } - return x; -} - -static struct grep_expr *compile_pattern_expr(struct grep_pat **list) -{ - return compile_pattern_or(list); -} - -static void compile_patterns(struct grep_opt *opt) -{ - struct grep_pat *p; - - /* First compile regexps */ - for (p = opt->pattern_list; p; p = p->next) { - if (p->token == GREP_PATTERN) - compile_regexp(p, opt); - else - opt->extended = 1; - } - - if (!opt->extended) - return; - - /* Then bundle them up in an expression. - * A classic recursive descent parser would do. - */ - p = opt->pattern_list; - opt->pattern_expression = compile_pattern_expr(&p); -#if DEBUG - dump_pattern_exp(opt->pattern_expression, 0); -#endif - if (p) - die("incomplete pattern expression: %s", p->pattern); -} - -static char *end_of_line(char *cp, unsigned long *left) -{ - unsigned long l = *left; - while (l && *cp != '\n') { - l--; - cp++; - } - *left = l; - return cp; -} - -static int word_char(char ch) -{ - return isalnum(ch) || ch == '_'; -} - -static void show_line(struct grep_opt *opt, const char *bol, const char *eol, - const char *name, unsigned lno, char sign) -{ - printf("%s%c", name, sign); - if (opt->linenum) - printf("%d%c", lno, sign); - printf("%.*s\n", (int)(eol-bol), bol); -} - -/* - * NEEDSWORK: share code with diff.c - */ -#define FIRST_FEW_BYTES 8000 -static int buffer_is_binary(const char *ptr, unsigned long size) -{ - if (FIRST_FEW_BYTES < size) - size = FIRST_FEW_BYTES; - return !!memchr(ptr, 0, size); -} - -static int fixmatch(const char *pattern, char *line, regmatch_t *match) -{ - char *hit = strstr(line, pattern); - if (!hit) { - match->rm_so = match->rm_eo = -1; - return REG_NOMATCH; - } - else { - match->rm_so = hit - line; - match->rm_eo = match->rm_so + strlen(pattern); - return 0; - } -} - -static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol) -{ - int hit = 0; - int at_true_bol = 1; - regmatch_t pmatch[10]; - - again: - if (!opt->fixed) { - regex_t *exp = &p->regexp; - hit = !regexec(exp, bol, ARRAY_SIZE(pmatch), - pmatch, 0); - } - else { - hit = !fixmatch(p->pattern, bol, pmatch); - } - - if (hit && opt->word_regexp) { - if ((pmatch[0].rm_so < 0) || - (eol - bol) <= pmatch[0].rm_so || - (pmatch[0].rm_eo < 0) || - (eol - bol) < pmatch[0].rm_eo) - die("regexp returned nonsense"); - - /* Match beginning must be either beginning of the - * line, or at word boundary (i.e. the last char must - * not be a word char). Similarly, match end must be - * either end of the line, or at word boundary - * (i.e. the next char must not be a word char). - */ - if ( ((pmatch[0].rm_so == 0 && at_true_bol) || - !word_char(bol[pmatch[0].rm_so-1])) && - ((pmatch[0].rm_eo == (eol-bol)) || - !word_char(bol[pmatch[0].rm_eo])) ) - ; - else - hit = 0; - - if (!hit && pmatch[0].rm_so + bol + 1 < eol) { - /* There could be more than one match on the - * line, and the first match might not be - * strict word match. But later ones could be! - */ - bol = pmatch[0].rm_so + bol + 1; - at_true_bol = 0; - goto again; - } - } - return hit; -} - -static int match_expr_eval(struct grep_opt *opt, - struct grep_expr *x, - char *bol, char *eol) -{ - switch (x->node) { - case GREP_NODE_ATOM: - return match_one_pattern(opt, x->u.atom, bol, eol); - break; - case GREP_NODE_NOT: - return !match_expr_eval(opt, x->u.unary, bol, eol); - case GREP_NODE_AND: - return (match_expr_eval(opt, x->u.binary.left, bol, eol) && - match_expr_eval(opt, x->u.binary.right, bol, eol)); - case GREP_NODE_OR: - return (match_expr_eval(opt, x->u.binary.left, bol, eol) || - match_expr_eval(opt, x->u.binary.right, bol, eol)); - } - die("Unexpected node type (internal error) %d\n", x->node); -} - -static int match_expr(struct grep_opt *opt, char *bol, char *eol) -{ - struct grep_expr *x = opt->pattern_expression; - return match_expr_eval(opt, x, bol, eol); -} - -static int match_line(struct grep_opt *opt, char *bol, char *eol) -{ - struct grep_pat *p; - if (opt->extended) - return match_expr(opt, bol, eol); - for (p = opt->pattern_list; p; p = p->next) { - if (match_one_pattern(opt, p, bol, eol)) - return 1; - } - return 0; -} - -static int grep_buffer(struct grep_opt *opt, const char *name, - char *buf, unsigned long size) -{ - char *bol = buf; - unsigned long left = size; - unsigned lno = 1; - struct pre_context_line { - char *bol; - char *eol; - } *prev = NULL, *pcl; - unsigned last_hit = 0; - unsigned last_shown = 0; - int binary_match_only = 0; - const char *hunk_mark = ""; - unsigned count = 0; - - if (buffer_is_binary(buf, size)) { - switch (opt->binary) { - case GREP_BINARY_DEFAULT: - binary_match_only = 1; - break; - case GREP_BINARY_NOMATCH: - return 0; /* Assume unmatch */ - break; - default: - break; - } - } - - if (opt->pre_context) - prev = xcalloc(opt->pre_context, sizeof(*prev)); - if (opt->pre_context || opt->post_context) - hunk_mark = "--\n"; - - while (left) { - char *eol, ch; - int hit = 0; - - eol = end_of_line(bol, &left); - ch = *eol; - *eol = 0; - - hit = match_line(opt, bol, eol); - - /* "grep -v -e foo -e bla" should list lines - * that do not have either, so inversion should - * be done outside. - */ - if (opt->invert) - hit = !hit; - if (opt->unmatch_name_only) { - if (hit) - return 0; - goto next_line; - } - if (hit) { - count++; - if (binary_match_only) { - printf("Binary file %s matches\n", name); - return 1; - } - if (opt->name_only) { - printf("%s\n", name); - return 1; - } - /* Hit at this line. If we haven't shown the - * pre-context lines, we would need to show them. - * When asked to do "count", this still show - * the context which is nonsense, but the user - * deserves to get that ;-). - */ - if (opt->pre_context) { - unsigned from; - if (opt->pre_context < lno) - from = lno - opt->pre_context; - else - from = 1; - if (from <= last_shown) - from = last_shown + 1; - if (last_shown && from != last_shown + 1) - printf(hunk_mark); - while (from < lno) { - pcl = &prev[lno-from-1]; - show_line(opt, pcl->bol, pcl->eol, - name, from, '-'); - from++; - } - last_shown = lno-1; - } - if (last_shown && lno != last_shown + 1) - printf(hunk_mark); - if (!opt->count) - show_line(opt, bol, eol, name, lno, ':'); - last_shown = last_hit = lno; - } - else if (last_hit && - lno <= last_hit + opt->post_context) { - /* If the last hit is within the post context, - * we need to show this line. - */ - if (last_shown && lno != last_shown + 1) - printf(hunk_mark); - show_line(opt, bol, eol, name, lno, '-'); - last_shown = lno; - } - if (opt->pre_context) { - memmove(prev+1, prev, - (opt->pre_context-1) * sizeof(*prev)); - prev->bol = bol; - prev->eol = eol; - } - - next_line: - *eol = ch; - bol = eol + 1; - if (!left) - break; - left--; - lno++; - } - - if (opt->unmatch_name_only) { - /* We did not see any hit, so we want to show this */ - printf("%s\n", name); - return 1; - } - - /* NEEDSWORK: - * The real "grep -c foo *.c" gives many "bar.c:0" lines, - * which feels mostly useless but sometimes useful. Maybe - * make it another option? For now suppress them. - */ - if (opt->count && count) - printf("%s:%u\n", name, count); - return !!last_hit; -} - static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len) { unsigned long size; @@ -631,7 +136,7 @@ static int grep_file(struct grep_opt *opt, const char *filename) if (i < 0) goto err_ret; data = xmalloc(st.st_size + 1); - if (st.st_size != xread(i, data, st.st_size)) { + if (st.st_size != read_in_full(i, data, st.st_size)) { error("'%s': short read %s", filename, strerror(errno)); close(i); free(data); @@ -694,6 +199,8 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached) push_arg("-F"); if (opt->linenum) push_arg("-n"); + if (!opt->pathname) + push_arg("-h"); if (opt->regflags & REG_EXTENDED) push_arg("-E"); if (opt->regflags & REG_ICASE) @@ -758,7 +265,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached) for (i = 0; i < active_nr; i++) { struct cache_entry *ce = active_cache[i]; char *name; - if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode))) + if (!S_ISREG(ntohl(ce->ce_mode))) continue; if (!pathspec_matches(paths, ce->name)) continue; @@ -770,12 +277,19 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached) memcpy(name + 2, ce->name, len + 1); } argv[argc++] = name; - if (argc < MAXARGS) + if (argc < MAXARGS && !ce_stage(ce)) continue; status = exec_grep(argc, argv); if (0 < status) hit = 1; argc = nr; + if (ce_stage(ce)) { + do { + i++; + } while (i < active_nr && + !strcmp(ce->name, active_cache[i]->name)); + i--; /* compensate for loop control */ + } } if (argc > nr) { status = exec_grep(argc, argv); @@ -806,15 +320,26 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) for (nr = 0; nr < active_nr; nr++) { struct cache_entry *ce = active_cache[nr]; - if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode))) + if (!S_ISREG(ntohl(ce->ce_mode))) continue; if (!pathspec_matches(paths, ce->name)) continue; - if (cached) + if (cached) { + if (ce_stage(ce)) + continue; hit |= grep_sha1(opt, ce->sha1, ce->name, 0); + } else hit |= grep_file(opt, ce->name); + if (ce_stage(ce)) { + do { + nr++; + } while (nr < active_nr && + !strcmp(ce->name, active_cache[nr]->name)); + nr--; /* compensate for loop control */ + } } + free_grep_patterns(opt); return hit; } @@ -914,6 +439,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) memset(&opt, 0, sizeof(opt)); opt.prefix_length = (prefix && *prefix) ? strlen(prefix) : 0; opt.relative = 1; + opt.pathname = 1; opt.pattern_tail = &opt.pattern_list; opt.regflags = REG_NEWLINE; @@ -973,10 +499,12 @@ int cmd_grep(int argc, const char **argv, const char *prefix) opt.linenum = 1; continue; } + if (!strcmp("-h", arg)) { + opt.pathname = 0; + continue; + } if (!strcmp("-H", arg)) { - /* We always show the pathname, so this - * is a noop. - */ + opt.pathname = 1; continue; } if (!strcmp("-l", arg) || @@ -1051,8 +579,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix) /* ignore empty line like grep does */ if (!buf[0]) continue; - add_pattern(&opt, strdup(buf), argv[1], ++lno, - GREP_PATTERN); + append_grep_pattern(&opt, xstrdup(buf), + argv[1], ++lno, + GREP_PATTERN); } fclose(patterns); argv++; @@ -1060,27 +589,36 @@ int cmd_grep(int argc, const char **argv, const char *prefix) continue; } if (!strcmp("--not", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_NOT); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_NOT); continue; } if (!strcmp("--and", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_AND); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_AND); continue; } if (!strcmp("--or", arg)) continue; /* no-op */ if (!strcmp("(", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_OPEN_PAREN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_OPEN_PAREN); continue; } if (!strcmp(")", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_CLOSE_PAREN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_CLOSE_PAREN); + continue; + } + if (!strcmp("--all-match", arg)) { + opt.all_match = 1; continue; } if (!strcmp("-e", arg)) { if (1 < argc) { - add_pattern(&opt, argv[1], "-e option", 0, - GREP_PATTERN); + append_grep_pattern(&opt, argv[1], + "-e option", 0, + GREP_PATTERN); argv++; argc--; continue; @@ -1102,8 +640,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix) /* First unrecognized non-option token */ if (!opt.pattern_list) { - add_pattern(&opt, arg, "command line", 0, - GREP_PATTERN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_PATTERN); break; } else { @@ -1120,8 +658,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) die("no pattern given."); if ((opt.regflags != REG_NEWLINE) && opt.fixed) die("cannot mix --fixed-strings and regexp"); - if (!opt.fixed) - compile_patterns(&opt); + compile_grep_patterns(&opt); /* Check revs and then paths */ for (i = 1; i < argc; i++) { @@ -1176,5 +713,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix) if (grep_object(&opt, paths, real_obj, list.objects[i].name)) hit = 1; } + free_grep_patterns(&opt); return !hit; } diff --git a/builtin-init-db.c b/builtin-init-db.c index 5085018e46..8e7540b692 100644 --- a/builtin-init-db.c +++ b/builtin-init-db.c @@ -10,6 +10,12 @@ #define DEFAULT_GIT_TEMPLATE_DIR "/usr/share/git-core/templates/" #endif +#ifdef NO_TRUSTABLE_FILEMODE +#define TEST_FILEMODE 0 +#else +#define TEST_FILEMODE 1 +#endif + static void safe_create_dir(const char *dir, int share) { if (mkdir(dir, 0777) < 0) { @@ -50,7 +56,7 @@ static void copy_templates_1(char *path, int baselen, /* Note: if ".git/hooks" file exists in the repository being * re-initialized, /etc/core-git/templates/hooks/update would - * cause git-init-db to fail here. I think this is sane but + * cause git-init to fail here. I think this is sane but * it means that the set of templates we ship by default, along * with the way the namespace under .git/ is organized, should * be really carefully chosen. @@ -124,8 +130,11 @@ static void copy_templates(const char *git_dir, int len, const char *template_di int template_len; DIR *dir; - if (!template_dir) - template_dir = DEFAULT_GIT_TEMPLATE_DIR; + if (!template_dir) { + template_dir = getenv(TEMPLATE_DIR_ENVIRONMENT); + if (!template_dir) + template_dir = DEFAULT_GIT_TEMPLATE_DIR; + } strcpy(template_path, template_dir); template_len = strlen(template_path); if (template_path[template_len-1] != '/') { @@ -164,13 +173,15 @@ static void copy_templates(const char *git_dir, int len, const char *template_di closedir(dir); } -static void create_default_files(const char *git_dir, const char *template_path) +static int create_default_files(const char *git_dir, const char *template_path) { unsigned len = strlen(git_dir); static char path[PATH_MAX]; unsigned char sha1[20]; struct stat st1; char repo_version_string[10]; + int reinit; + int filemode; if (len > sizeof(path)-50) die("insane git directory %s", git_dir); @@ -218,8 +229,9 @@ static void create_default_files(const char *git_dir, const char *template_path) * branch, if it does not exist yet. */ strcpy(path + len, "HEAD"); - if (read_ref(path, sha1) < 0) { - if (create_symref(path, "refs/heads/master") < 0) + reinit = !read_ref("HEAD", sha1); + if (!reinit) { + if (create_symref("HEAD", "refs/heads/master") < 0) exit(1); } @@ -231,18 +243,27 @@ static void create_default_files(const char *git_dir, const char *template_path) strcpy(path + len, "config"); /* Check filemode trustability */ - if (!lstat(path, &st1)) { + filemode = TEST_FILEMODE; + if (TEST_FILEMODE && !lstat(path, &st1)) { struct stat st2; - int filemode = (!chmod(path, st1.st_mode ^ S_IXUSR) && + filemode = (!chmod(path, st1.st_mode ^ S_IXUSR) && !lstat(path, &st2) && st1.st_mode != st2.st_mode); - git_config_set("core.filemode", - filemode ? "true" : "false"); } + git_config_set("core.filemode", filemode ? "true" : "false"); + + if (is_bare_repository()) { + git_config_set("core.bare", "true"); + } + else { + git_config_set("core.bare", "false"); + git_config_set("core.logallrefupdates", "true"); + } + return reinit; } static const char init_db_usage[] = -"git-init-db [--template=<template-directory>] [--shared]"; +"git-init [--template=<template-directory>] [--shared]"; /* * If you want to, you can share the DB area with any number of branches. @@ -256,7 +277,7 @@ int cmd_init_db(int argc, const char **argv, const char *prefix) const char *sha1_dir; const char *template_dir = NULL; char *path; - int len, i; + int len, i, reinit; for (i = 1; i < argc; i++, argv++) { const char *arg = argv[1]; @@ -274,10 +295,8 @@ int cmd_init_db(int argc, const char **argv, const char *prefix) * Set up the default .git directory contents */ git_dir = getenv(GIT_DIR_ENVIRONMENT); - if (!git_dir) { + if (!git_dir) git_dir = DEFAULT_GIT_DIR_ENVIRONMENT; - fprintf(stderr, "defaulting to local storage area\n"); - } safe_create_dir(git_dir, 0); /* Check to see if the repository version is right. @@ -287,7 +306,7 @@ int cmd_init_db(int argc, const char **argv, const char *prefix) */ check_repository_format(); - create_default_files(git_dir, template_dir); + reinit = create_default_files(git_dir, template_dir); /* * And set up the object store. @@ -311,7 +330,13 @@ int cmd_init_db(int argc, const char **argv, const char *prefix) */ sprintf(buf, "%d", shared_repository); git_config_set("core.sharedrepository", buf); + git_config_set("receive.denyNonFastforwards", "true"); } + printf("%s%s Git repository in %s/\n", + reinit ? "Reinitialized existing" : "Initialized empty", + shared_repository ? " shared" : "", + git_dir); + return 0; } diff --git a/builtin-log.c b/builtin-log.c index 691cf3aef7..a59b4acef1 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -10,8 +10,9 @@ #include "revision.h" #include "log-tree.h" #include "builtin.h" -#include <time.h> -#include <sys/time.h> +#include "tag.h" + +static int default_show_root = 1; /* this is in builtin-diff.c */ void add_head(struct rev_info *revs); @@ -19,14 +20,27 @@ void add_head(struct rev_info *revs); static void cmd_log_init(int argc, const char **argv, const char *prefix, struct rev_info *rev) { + int i; + rev->abbrev = DEFAULT_ABBREV; rev->commit_format = CMIT_FMT_DEFAULT; rev->verbose_header = 1; + rev->show_root_diff = default_show_root; argc = setup_revisions(argc, argv, rev, "HEAD"); if (rev->diffopt.pickaxe || rev->diffopt.filter) rev->always_show_header = 0; - if (argc > 1) - die("unrecognized argument: %s", argv[1]); + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strncmp(arg, "--encoding=", 11)) { + arg += 11; + if (strcmp(arg, "none")) + git_log_output_encoding = strdup(arg); + else + git_log_output_encoding = ""; + } + else + die("unrecognized argument: %s", arg); + } } static int cmd_log_walk(struct rev_info *rev) @@ -44,11 +58,20 @@ static int cmd_log_walk(struct rev_info *rev) return 0; } +static int git_log_config(const char *var, const char *value) +{ + if (!strcmp(var, "log.showroot")) { + default_show_root = git_config_bool(var, value); + return 0; + } + return git_diff_ui_config(var, value); +} + int cmd_whatchanged(int argc, const char **argv, const char *prefix) { struct rev_info rev; - git_config(git_diff_ui_config); + git_config(git_log_config); init_revisions(&rev, prefix); rev.diff = 1; rev.diffopt.recursive = 1; @@ -59,11 +82,45 @@ int cmd_whatchanged(int argc, const char **argv, const char *prefix) return cmd_log_walk(&rev); } +static int show_object(const unsigned char *sha1, int suppress_header) +{ + unsigned long size; + char type[20]; + char *buf = read_sha1_file(sha1, type, &size); + int offset = 0; + + if (!buf) + return error("Could not read object %s", sha1_to_hex(sha1)); + + if (suppress_header) + while (offset < size && buf[offset++] != '\n') { + int new_offset = offset; + while (new_offset < size && buf[new_offset++] != '\n') + ; /* do nothing */ + offset = new_offset; + } + + if (offset < size) + fwrite(buf + offset, size - offset, 1, stdout); + free(buf); + return 0; +} + +static int show_tree_object(const unsigned char *sha1, + const char *base, int baselen, + const char *pathname, unsigned mode, int stage) +{ + printf("%s%s\n", pathname, S_ISDIR(mode) ? "/" : ""); + return 0; +} + int cmd_show(int argc, const char **argv, const char *prefix) { struct rev_info rev; + struct object_array_entry *objects; + int i, count, ret = 0; - git_config(git_diff_ui_config); + git_config(git_log_config); init_revisions(&rev, prefix); rev.diff = 1; rev.diffopt.recursive = 1; @@ -73,14 +130,59 @@ int cmd_show(int argc, const char **argv, const char *prefix) rev.ignore_merges = 0; rev.no_walk = 1; cmd_log_init(argc, argv, prefix, &rev); - return cmd_log_walk(&rev); + + count = rev.pending.nr; + objects = rev.pending.objects; + for (i = 0; i < count && !ret; i++) { + struct object *o = objects[i].item; + const char *name = objects[i].name; + switch (o->type) { + case OBJ_BLOB: + ret = show_object(o->sha1, 0); + break; + case OBJ_TAG: { + struct tag *t = (struct tag *)o; + + printf("%stag %s%s\n\n", + diff_get_color(rev.diffopt.color_diff, + DIFF_COMMIT), + t->tag, + diff_get_color(rev.diffopt.color_diff, + DIFF_RESET)); + ret = show_object(o->sha1, 1); + objects[i].item = (struct object *)t->tagged; + i--; + break; + } + case OBJ_TREE: + printf("%stree %s%s\n\n", + diff_get_color(rev.diffopt.color_diff, + DIFF_COMMIT), + name, + diff_get_color(rev.diffopt.color_diff, + DIFF_RESET)); + read_tree_recursive((struct tree *)o, "", 0, 0, NULL, + show_tree_object); + break; + case OBJ_COMMIT: + rev.pending.nr = rev.pending.alloc = 0; + rev.pending.objects = NULL; + add_object_array(o, name, &rev.pending); + ret = cmd_log_walk(&rev); + break; + default: + ret = error("Unknown type: %d", o->type); + } + } + free(objects); + return ret; } int cmd_log(int argc, const char **argv, const char *prefix) { struct rev_info rev; - git_config(git_diff_ui_config); + git_config(git_log_config); init_revisions(&rev, prefix); rev.always_show_header = 1; cmd_log_init(argc, argv, prefix, &rev); @@ -101,15 +203,15 @@ static int git_format_config(const char *var, const char *value) if (!strcmp(var, "format.headers")) { int len = strlen(value); extra_headers_size += len + 1; - extra_headers = realloc(extra_headers, extra_headers_size); + extra_headers = xrealloc(extra_headers, extra_headers_size); extra_headers[extra_headers_size - len - 1] = 0; strcat(extra_headers, value); return 0; } - if (!strcmp(var, "diff.color")) { + if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) { return 0; } - return git_diff_ui_config(var, value); + return git_log_config(var, value); } @@ -171,8 +273,11 @@ static void reopen_stdout(struct commit *commit, int nr, int keep_subject) static int get_patch_id(struct commit *commit, struct diff_options *options, unsigned char *sha1) { - diff_tree_sha1(commit->parents->item->object.sha1, commit->object.sha1, - "", options); + if (commit->parents) + diff_tree_sha1(commit->parents->item->object.sha1, + commit->object.sha1, "", options); + else + diff_root_tree_sha1(commit->object.sha1, "", options); diffcore_std(options); return diff_flush_patch_id(options, sha1); } @@ -348,6 +453,9 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix) if (!rev.diffopt.output_format) rev.diffopt.output_format = DIFF_FORMAT_DIFFSTAT | DIFF_FORMAT_PATCH; + if (!output_directory) + output_directory = prefix; + if (output_directory) { if (use_stdout) die("standard output, or directory, which one?"); @@ -381,7 +489,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix) continue; nr++; - list = realloc(list, nr * sizeof(list[0])); + list = xrealloc(list, nr * sizeof(list[0])); list[nr - 1] = commit; } total = nr; @@ -434,3 +542,109 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix) return 0; } +static int add_pending_commit(const char *arg, struct rev_info *revs, int flags) +{ + unsigned char sha1[20]; + if (get_sha1(arg, sha1) == 0) { + struct commit *commit = lookup_commit_reference(sha1); + if (commit) { + commit->object.flags |= flags; + add_pending_object(revs, &commit->object, arg); + return 0; + } + } + return -1; +} + +static const char cherry_usage[] = +"git-cherry [-v] <upstream> [<head>] [<limit>]"; +int cmd_cherry(int argc, const char **argv, const char *prefix) +{ + struct rev_info revs; + struct diff_options patch_id_opts; + struct commit *commit; + struct commit_list *list = NULL; + const char *upstream; + const char *head = "HEAD"; + const char *limit = NULL; + int verbose = 0; + + if (argc > 1 && !strcmp(argv[1], "-v")) { + verbose = 1; + argc--; + argv++; + } + + switch (argc) { + case 4: + limit = argv[3]; + /* FALLTHROUGH */ + case 3: + head = argv[2]; + /* FALLTHROUGH */ + case 2: + upstream = argv[1]; + break; + default: + usage(cherry_usage); + } + + init_revisions(&revs, prefix); + revs.diff = 1; + revs.combine_merges = 0; + revs.ignore_merges = 1; + revs.diffopt.recursive = 1; + + if (add_pending_commit(head, &revs, 0)) + die("Unknown commit %s", head); + if (add_pending_commit(upstream, &revs, UNINTERESTING)) + die("Unknown commit %s", upstream); + + /* Don't say anything if head and upstream are the same. */ + if (revs.pending.nr == 2) { + struct object_array_entry *o = revs.pending.objects; + if (hashcmp(o[0].item->sha1, o[1].item->sha1) == 0) + return 0; + } + + get_patch_ids(&revs, &patch_id_opts, prefix); + + if (limit && add_pending_commit(limit, &revs, UNINTERESTING)) + die("Unknown commit %s", limit); + + /* reverse the list of commits */ + prepare_revision_walk(&revs); + while ((commit = get_revision(&revs)) != NULL) { + /* ignore merges */ + if (commit->parents && commit->parents->next) + continue; + + commit_list_insert(commit, &list); + } + + while (list) { + unsigned char sha1[20]; + char sign = '+'; + + commit = list->item; + if (!get_patch_id(commit, &patch_id_opts, sha1) && + lookup_object(sha1)) + sign = '-'; + + if (verbose) { + static char buf[16384]; + pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, + buf, sizeof(buf), 0, NULL, NULL, 0); + printf("%c %s %s\n", sign, + sha1_to_hex(commit->object.sha1), buf); + } + else { + printf("%c %s\n", sign, + sha1_to_hex(commit->object.sha1)); + } + + list = list->next; + } + + return 0; +} diff --git a/builtin-ls-files.c b/builtin-ls-files.c index ad8c41e731..21c2a6e2d9 100644 --- a/builtin-ls-files.c +++ b/builtin-ls-files.c @@ -5,8 +5,6 @@ * * Copyright (C) Linus Torvalds, 2005 */ -#include <fnmatch.h> - #include "cache.h" #include "quote.h" #include "dir.h" @@ -487,10 +485,14 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix) for (num = 0; pathspec[num]; num++) { if (ps_matched[num]) continue; - error("pathspec '%s' did not match any.", + error("pathspec '%s' did not match any file(s) known to git.", pathspec[num] + prefix_offset); errors++; } + + if (errors) + fprintf(stderr, "Did you forget to 'git add'?\n"); + return errors ? 1 : 0; } diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c index 0c65f93145..583da38b67 100644 --- a/builtin-mailinfo.c +++ b/builtin-mailinfo.c @@ -2,17 +2,9 @@ * Another stupid program, this one parsing the headers of an * email to figure out authorship and subject */ -#define _GNU_SOURCE -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <ctype.h> -#ifndef NO_ICONV -#include <iconv.h> -#endif -#include "git-compat-util.h" #include "cache.h" #include "builtin.h" +#include "utf8.h" static FILE *cmitmsg, *patchfile, *fin, *fout; @@ -451,17 +443,6 @@ static int read_one_header_line(char *line, int sz, FILE *in) return ofs; } -static unsigned hexval(int c) -{ - if (c >= '0' && c <= '9') - return c - '0'; - if (c >= 'a' && c <= 'f') - return c - 'a' + 10; - if (c >= 'A' && c <= 'F') - return c - 'A' + 10; - return ~0; -} - static int decode_q_segment(char *in, char *ot, char *ep, int rfc2047) { int c; @@ -530,40 +511,15 @@ static int decode_b_segment(char *in, char *ot, char *ep) static void convert_to_utf8(char *line, char *charset) { -#ifndef NO_ICONV - char *in, *out; - size_t insize, outsize, nrc; - char outbuf[4096]; /* cheat */ static char latin_one[] = "latin1"; char *input_charset = *charset ? charset : latin_one; - iconv_t conv = iconv_open(metainfo_charset, input_charset); - - if (conv == (iconv_t) -1) { - static int warned_latin1_once = 0; - if (input_charset != latin_one) { - fprintf(stderr, "cannot convert from %s to %s\n", - input_charset, metainfo_charset); - *charset = 0; - } - else if (!warned_latin1_once) { - warned_latin1_once = 1; - fprintf(stderr, "tried to convert from %s to %s, " - "but your iconv does not work with it.\n", - input_charset, metainfo_charset); - } - return; - } - in = line; - insize = strlen(in); - out = outbuf; - outsize = sizeof(outbuf); - nrc = iconv(conv, &in, &insize, &out, &outsize); - iconv_close(conv); - if (nrc == (size_t) -1) - return; - *out = 0; - strcpy(line, outbuf); -#endif + char *out = reencode_string(line, metainfo_charset, input_charset); + + if (!out) + die("cannot convert from %s to %s\n", + input_charset, metainfo_charset); + strcpy(line, out); + free(out); } static int decode_header_bq(char *it) @@ -838,16 +794,23 @@ static const char mailinfo_usage[] = int cmd_mailinfo(int argc, const char **argv, const char *prefix) { + const char *def_charset; + /* NEEDSWORK: might want to do the optional .git/ directory * discovery */ git_config(git_default_config); + def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8"); + metainfo_charset = def_charset; + while (1 < argc && argv[1][0] == '-') { if (!strcmp(argv[1], "-k")) keep_subject = 1; else if (!strcmp(argv[1], "-u")) - metainfo_charset = git_commit_encoding; + metainfo_charset = def_charset; + else if (!strcmp(argv[1], "-n")) + metainfo_charset = NULL; else if (!strncmp(argv[1], "--encoding=", 11)) metainfo_charset = argv[1] + 11; else diff --git a/builtin-mailsplit.c b/builtin-mailsplit.c index 91a699d34d..3bca855aae 100644 --- a/builtin-mailsplit.c +++ b/builtin-mailsplit.c @@ -4,13 +4,6 @@ * It just splits a mbox into a list of files: "0001" "0002" .. * so you can process them further from there. */ -#include <unistd.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <string.h> -#include <stdio.h> #include "cache.h" #include "builtin.h" diff --git a/builtin-merge-file.c b/builtin-merge-file.c new file mode 100644 index 0000000000..9135773908 --- /dev/null +++ b/builtin-merge-file.c @@ -0,0 +1,63 @@ +#include "cache.h" +#include "xdiff/xdiff.h" +#include "xdiff-interface.h" + +static const char merge_file_usage[] = +"git merge-file [-p | --stdout] [-q | --quiet] [-L name1 [-L orig [-L name2]]] file1 orig_file file2"; + +int cmd_merge_file(int argc, char **argv, char **envp) +{ + char *names[3]; + mmfile_t mmfs[3]; + mmbuffer_t result = {NULL, 0}; + xpparam_t xpp = {XDF_NEED_MINIMAL}; + int ret = 0, i = 0, to_stdout = 0; + + while (argc > 4) { + if (!strcmp(argv[1], "-L") && i < 3) { + names[i++] = argv[2]; + argc--; + argv++; + } else if (!strcmp(argv[1], "-p") || + !strcmp(argv[1], "--stdout")) + to_stdout = 1; + else if (!strcmp(argv[1], "-q") || + !strcmp(argv[1], "--quiet")) + freopen("/dev/null", "w", stderr); + else + usage(merge_file_usage); + argc--; + argv++; + } + + if (argc != 4) + usage(merge_file_usage); + + for (; i < 3; i++) + names[i] = argv[i + 1]; + + for (i = 0; i < 3; i++) + if (read_mmfile(mmfs + i, argv[i + 1])) + return -1; + + ret = xdl_merge(mmfs + 1, mmfs + 0, names[0], mmfs + 2, names[2], + &xpp, XDL_MERGE_ZEALOUS, &result); + + for (i = 0; i < 3; i++) + free(mmfs[i].ptr); + + if (ret >= 0) { + char *filename = argv[1]; + FILE *f = to_stdout ? stdout : fopen(filename, "wb"); + + if (!f) + ret = error("Could not open %s for writing", filename); + else if (fwrite(result.ptr, result.size, 1, f) != 1) + ret = error("Could not write to %s", filename); + else if (fclose(f)) + ret = error("Could not close %s", filename); + free(result.ptr); + } + + return ret; +} diff --git a/builtin-mv.c b/builtin-mv.c index ff882bec47..737af350b8 100644 --- a/builtin-mv.c +++ b/builtin-mv.c @@ -3,8 +3,6 @@ * * Copyright (C) 2006 Johannes Schindelin */ -#include <fnmatch.h> - #include "cache.h" #include "builtin.h" #include "dir.h" @@ -146,21 +144,24 @@ int cmd_mv(int argc, const char **argv, const char *prefix) && lstat(dst, &st) == 0) bad = "cannot move directory over file"; else if (src_is_dir) { + const char *src_w_slash = add_slash(src); + int len_w_slash = length + 1; int first, last; modes[i] = WORKING_DIRECTORY; - first = cache_name_pos(src, length); + first = cache_name_pos(src_w_slash, len_w_slash); if (first >= 0) - die ("Huh? %s/ is in index?", src); + die ("Huh? %.*s is in index?", + len_w_slash, src_w_slash); first = -1 - first; for (last = first; last < active_nr; last++) { const char *path = active_cache[last]->name; - if (strncmp(path, src, length) - || path[length] != '/') + if (strncmp(path, src_w_slash, len_w_slash)) break; } + free((char *)src_w_slash); if (last - first < 1) bad = "source directory is empty"; @@ -168,13 +169,13 @@ int cmd_mv(int argc, const char **argv, const char *prefix) int j, dst_len; if (last - first > 0) { - source = realloc(source, + source = xrealloc(source, (count + last - first) * sizeof(char *)); - destination = realloc(destination, + destination = xrealloc(destination, (count + last - first) * sizeof(char *)); - modes = realloc(modes, + modes = xrealloc(modes, (count + last - first) * sizeof(enum update_mode)); } @@ -262,10 +263,10 @@ int cmd_mv(int argc, const char **argv, const char *prefix) } else { for (i = 0; i < changed.nr; i++) { const char *path = changed.items[i].path; - int i = cache_name_pos(path, strlen(path)); - struct cache_entry *ce = active_cache[i]; + int j = cache_name_pos(path, strlen(path)); + struct cache_entry *ce = active_cache[j]; - if (i < 0) + if (j < 0) die ("Huh? Cache entry for %s unknown?", path); refresh_cache_entry(ce, 0); } @@ -278,6 +279,7 @@ int cmd_mv(int argc, const char **argv, const char *prefix) for (i = 0; i < deleted.nr; i++) { const char *path = deleted.items[i].path; remove_file_from_cache(path); + cache_tree_invalidate_path(active_cache_tree, path); } if (active_cache_changed) { diff --git a/builtin-name-rev.c b/builtin-name-rev.c index d44e782c99..b4f15cc38a 100644 --- a/builtin-name-rev.c +++ b/builtin-name-rev.c @@ -1,4 +1,3 @@ -#include <stdlib.h> #include "builtin.h" #include "cache.h" #include "commit.h" @@ -75,11 +74,10 @@ copy_data: } } -static int tags_only; - -static int name_ref(const char *path, const unsigned char *sha1) +static int name_ref(const char *path, const unsigned char *sha1, int flags, void *cb_data) { struct object *o = parse_object(sha1); + int tags_only = *(int*)cb_data; int deref = 0; if (tags_only && strncmp(path, "refs/tags/", 10)) @@ -100,7 +98,7 @@ static int name_ref(const char *path, const unsigned char *sha1) else if (!strncmp(path, "refs/", 5)) path = path + 5; - name_rev(commit, strdup(path), 0, 0, deref); + name_rev(commit, xstrdup(path), 0, 0, deref); } return 0; } @@ -131,6 +129,7 @@ int cmd_name_rev(int argc, const char **argv, const char *prefix) { struct object_array revs = { 0, 0, NULL }; int as_is = 0, all = 0, transform_stdin = 0; + int tags_only = 0; git_config(git_default_config); @@ -186,7 +185,7 @@ int cmd_name_rev(int argc, const char **argv, const char *prefix) add_object_array((struct object *)commit, *argv, &revs); } - for_each_ref(name_ref); + for_each_ref(name_ref, &tags_only); if (transform_stdin) { char buffer[2048]; diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c index 46f524dfc3..42dd8c87a2 100644 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@ -9,10 +9,16 @@ #include "pack.h" #include "csum-file.h" #include "tree-walk.h" -#include <sys/time.h> -#include <signal.h> +#include "diff.h" +#include "revision.h" +#include "list-objects.h" -static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; +static const char pack_usage[] = "\ +git-pack-objects [{ -q | --progress | --all-progress }] \n\ + [--local] [--incremental] [--window=N] [--depth=N] \n\ + [--no-reuse-delta] [--delta-base-offset] [--non-empty] \n\ + [--revs [--unpacked | --all]*] [--reflog] [--stdout | base-name] \n\ + [<ref-list | <object-list]"; struct object_entry { unsigned char sha1[20]; @@ -26,6 +32,7 @@ struct object_entry { enum object_type type; enum object_type in_pack_type; /* could be delta */ unsigned long delta_size; /* delta data size (uncompressed) */ +#define in_pack_header_size delta_size /* only when reusing pack data */ struct object_entry *delta; /* delta base object */ struct packed_git *in_pack; /* already in pack */ unsigned int in_pack_offset; @@ -57,6 +64,8 @@ static int non_empty; static int no_reuse_delta; static int local; static int incremental; +static int allow_ofs_delta; + static struct object_entry **sorted_by_sha, **sorted_by_type; static struct object_entry *objects; static int nr_objects, nr_alloc, nr_result; @@ -65,6 +74,8 @@ static unsigned char pack_file_sha1[20]; static int progress = 1; static volatile sig_atomic_t progress_update; static int window = 10; +static int pack_to_stdout; +static int num_preferred_base; /* * The object names in objects array are hashed with this hashtable, @@ -79,17 +90,25 @@ static int object_ix_hashsz; * Pack index for existing packs give us easy access to the offsets into * corresponding pack file where each object's data starts, but the entries * do not store the size of the compressed representation (uncompressed - * size is easily available by examining the pack entry header). We build - * a hashtable of existing packs (pack_revindex), and keep reverse index - * here -- pack index file is sorted by object name mapping to offset; this - * pack_revindex[].revindex array is an ordered list of offsets, so if you - * know the offset of an object, next offset is where its packed - * representation ends. + * size is easily available by examining the pack entry header). It is + * also rather expensive to find the sha1 for an object given its offset. + * + * We build a hashtable of existing packs (pack_revindex), and keep reverse + * index here -- pack index file is sorted by object name mapping to offset; + * this pack_revindex[].revindex array is a list of offset/index_nr pairs + * ordered by offset, so if you know the offset of an object, next offset + * is where its packed representation ends and the index_nr can be used to + * get the object sha1 from the main index. */ +struct revindex_entry { + unsigned int offset; + unsigned int nr; +}; struct pack_revindex { struct packed_git *p; - unsigned long *revindex; -} *pack_revindex = NULL; + struct revindex_entry *revindex; +}; +static struct pack_revindex *pack_revindex; static int pack_revindex_hashsz; /* @@ -136,14 +155,9 @@ static void prepare_pack_ix(void) static int cmp_offset(const void *a_, const void *b_) { - unsigned long a = *(unsigned long *) a_; - unsigned long b = *(unsigned long *) b_; - if (a < b) - return -1; - else if (a == b) - return 0; - else - return 1; + const struct revindex_entry *a = a_; + const struct revindex_entry *b = b_; + return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0; } /* @@ -156,25 +170,27 @@ static void prepare_pack_revindex(struct pack_revindex *rix) int i; void *index = p->index_base + 256; - rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); + rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1)); for (i = 0; i < num_ent; i++) { unsigned int hl = *((unsigned int *)((char *) index + 24*i)); - rix->revindex[i] = ntohl(hl); + rix->revindex[i].offset = ntohl(hl); + rix->revindex[i].nr = i; } /* This knows the pack format -- the 20-byte trailer * follows immediately after the last object data. */ - rix->revindex[num_ent] = p->pack_size - 20; - qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); + rix->revindex[num_ent].offset = p->pack_size - 20; + rix->revindex[num_ent].nr = -1; + qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset); } -static unsigned long find_packed_object_size(struct packed_git *p, - unsigned long ofs) +static struct revindex_entry * find_packed_object(struct packed_git *p, + unsigned int ofs) { int num; int lo, hi; struct pack_revindex *rix; - unsigned long *revindex; + struct revindex_entry *revindex; num = pack_revindex_ix(p); if (num < 0) die("internal error: pack revindex uninitialized"); @@ -186,10 +202,10 @@ static unsigned long find_packed_object_size(struct packed_git *p, hi = num_packed_objects(p) + 1; do { int mi = (lo + hi) / 2; - if (revindex[mi] == ofs) { - return revindex[mi+1] - ofs; + if (revindex[mi].offset == ofs) { + return revindex + mi; } - else if (ofs < revindex[mi]) + else if (ofs < revindex[mi].offset) hi = mi; else lo = mi + 1; @@ -197,6 +213,20 @@ static unsigned long find_packed_object_size(struct packed_git *p, die("internal error: pack revindex corrupt"); } +static unsigned long find_packed_object_size(struct packed_git *p, + unsigned long ofs) +{ + struct revindex_entry *entry = find_packed_object(p, ofs); + return entry[1].offset - ofs; +} + +static unsigned char *find_packed_object_name(struct packed_git *p, + unsigned long ofs) +{ + struct revindex_entry *entry = find_packed_object(p, ofs); + return (unsigned char *)(p->index_base + 256) + 24 * entry->nr + 4; +} + static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) { unsigned long othersize, delta_size; @@ -227,7 +257,7 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha int n = 1; unsigned char c; - if (type < OBJ_COMMIT || type > OBJ_DELTA) + if (type < OBJ_COMMIT || type > OBJ_REF_DELTA) die("bad type %d", type); c = (type << 4) | (size & 15); @@ -242,6 +272,105 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha return n; } +/* + * we are going to reuse the existing object data as is. make + * sure it is not corrupt. + */ +static int check_pack_inflate(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + unsigned long len, + unsigned long expect) +{ + z_stream stream; + unsigned char fakebuf[4096], *in; + int st; + + memset(&stream, 0, sizeof(stream)); + inflateInit(&stream); + do { + in = use_pack(p, w_curs, offset, &stream.avail_in); + stream.next_in = in; + stream.next_out = fakebuf; + stream.avail_out = sizeof(fakebuf); + st = inflate(&stream, Z_FINISH); + offset += stream.next_in - in; + } while (st == Z_OK || st == Z_BUF_ERROR); + inflateEnd(&stream); + return (st == Z_STREAM_END && + stream.total_out == expect && + stream.total_in == len) ? 0 : -1; +} + +static void copy_pack_data(struct sha1file *f, + struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + unsigned long len) +{ + unsigned char *in; + unsigned int avail; + + while (len) { + in = use_pack(p, w_curs, offset, &avail); + if (avail > len) + avail = len; + sha1write(f, in, avail); + offset += avail; + len -= avail; + } +} + +static int check_loose_inflate(unsigned char *data, unsigned long len, unsigned long expect) +{ + z_stream stream; + unsigned char fakebuf[4096]; + int st; + + memset(&stream, 0, sizeof(stream)); + stream.next_in = data; + stream.avail_in = len; + stream.next_out = fakebuf; + stream.avail_out = sizeof(fakebuf); + inflateInit(&stream); + + while (1) { + st = inflate(&stream, Z_FINISH); + if (st == Z_STREAM_END || st == Z_OK) { + st = (stream.total_out == expect && + stream.total_in == len) ? 0 : -1; + break; + } + if (st != Z_BUF_ERROR) { + st = -1; + break; + } + stream.next_out = fakebuf; + stream.avail_out = sizeof(fakebuf); + } + inflateEnd(&stream); + return st; +} + +static int revalidate_loose_object(struct object_entry *entry, + unsigned char *map, + unsigned long mapsize) +{ + /* we already know this is a loose object with new type header. */ + enum object_type type; + unsigned long size, used; + + if (pack_to_stdout) + return 0; + + used = unpack_object_header_gently(map, mapsize, &type, &size); + if (!used) + return -1; + map += used; + mapsize -= used; + return check_loose_inflate(map, mapsize, size); +} + static unsigned long write_object(struct sha1file *f, struct object_entry *entry) { @@ -253,13 +382,10 @@ static unsigned long write_object(struct sha1file *f, enum object_type obj_type; int to_reuse = 0; - if (entry->preferred_base) - return 0; - obj_type = entry->type; if (! entry->in_pack) to_reuse = 0; /* can't reuse what we don't have */ - else if (obj_type == OBJ_DELTA) + else if (obj_type == OBJ_REF_DELTA || obj_type == OBJ_OFS_DELTA) to_reuse = 1; /* check_object() decided it for us */ else if (obj_type != entry->in_pack_type) to_reuse = 0; /* pack has delta which is unusable */ @@ -276,6 +402,9 @@ static unsigned long write_object(struct sha1file *f, map = map_sha1_file(entry->sha1, &mapsize); if (map && !legacy_loose_object(map)) { /* We can copy straight into the pack file */ + if (revalidate_loose_object(entry, map, mapsize)) + die("corrupt loose object %s", + sha1_to_hex(entry->sha1)); sha1write(f, map, mapsize); munmap(map, mapsize); written++; @@ -286,7 +415,7 @@ static unsigned long write_object(struct sha1file *f, munmap(map, mapsize); } - if (! to_reuse) { + if (!to_reuse) { buf = read_sha1_file(entry->sha1, type, &size); if (!buf) die("unable to read %s", sha1_to_hex(entry->sha1)); @@ -296,18 +425,35 @@ static unsigned long write_object(struct sha1file *f, if (entry->delta) { buf = delta_against(buf, size, entry); size = entry->delta_size; - obj_type = OBJ_DELTA; + obj_type = (allow_ofs_delta && entry->delta->offset) ? + OBJ_OFS_DELTA : OBJ_REF_DELTA; } /* * The object header is a byte of 'type' followed by zero or - * more bytes of length. For deltas, the 20 bytes of delta - * sha1 follows that. + * more bytes of length. */ hdrlen = encode_header(obj_type, size, header); sha1write(f, header, hdrlen); - if (entry->delta) { - sha1write(f, entry->delta, 20); + if (obj_type == OBJ_OFS_DELTA) { + /* + * Deltas with relative base contain an additional + * encoding of the relative offset for the delta + * base from this object's position in the pack. + */ + unsigned long ofs = entry->offset - entry->delta->offset; + unsigned pos = sizeof(header) - 1; + header[pos] = ofs & 127; + while (ofs >>= 7) + header[--pos] = 128 | (--ofs & 127); + sha1write(f, header + pos, sizeof(header) - pos); + hdrlen += sizeof(header) - pos; + } else if (obj_type == OBJ_REF_DELTA) { + /* + * Deltas with a base reference contain + * an additional 20 bytes for the base sha1. + */ + sha1write(f, entry->delta->sha1, 20); hdrlen += 20; } datalen = sha1write_compressed(f, buf, size); @@ -315,18 +461,40 @@ static unsigned long write_object(struct sha1file *f, } else { struct packed_git *p = entry->in_pack; - use_packed_git(p); - - datalen = find_packed_object_size(p, entry->in_pack_offset); - buf = (char *) p->pack_base + entry->in_pack_offset; - sha1write(f, buf, datalen); - unuse_packed_git(p); - hdrlen = 0; /* not really */ - if (obj_type == OBJ_DELTA) + struct pack_window *w_curs = NULL; + unsigned long offset; + + if (entry->delta) { + obj_type = (allow_ofs_delta && entry->delta->offset) ? + OBJ_OFS_DELTA : OBJ_REF_DELTA; reused_delta++; + } + hdrlen = encode_header(obj_type, entry->size, header); + sha1write(f, header, hdrlen); + if (obj_type == OBJ_OFS_DELTA) { + unsigned long ofs = entry->offset - entry->delta->offset; + unsigned pos = sizeof(header) - 1; + header[pos] = ofs & 127; + while (ofs >>= 7) + header[--pos] = 128 | (--ofs & 127); + sha1write(f, header + pos, sizeof(header) - pos); + hdrlen += sizeof(header) - pos; + } else if (obj_type == OBJ_REF_DELTA) { + sha1write(f, entry->delta->sha1, 20); + hdrlen += 20; + } + + offset = entry->in_pack_offset + entry->in_pack_header_size; + datalen = find_packed_object_size(p, entry->in_pack_offset) + - entry->in_pack_header_size; + if (!pack_to_stdout && check_pack_inflate(p, &w_curs, + offset, datalen, entry->size)) + die("corrupt delta in pack %s", sha1_to_hex(entry->sha1)); + copy_pack_data(f, p, &w_curs, offset, datalen); + unuse_pack(&w_curs); reused++; } - if (obj_type == OBJ_DELTA) + if (entry->delta) written_delta++; written++; return hdrlen + datalen; @@ -336,17 +504,16 @@ static unsigned long write_one(struct sha1file *f, struct object_entry *e, unsigned long offset) { - if (e->offset) + if (e->offset || e->preferred_base) /* offset starts from header size and cannot be zero * if it is written already. */ return offset; - e->offset = offset; - offset += write_object(f, e); - /* if we are deltified, write out its base object. */ + /* if we are deltified, write out its base object first. */ if (e->delta) offset = write_one(f, e->delta, offset); - return offset; + e->offset = offset; + return offset + write_object(f, e); } static void write_pack_file(void) @@ -356,15 +523,15 @@ static void write_pack_file(void) unsigned long offset; struct pack_header hdr; unsigned last_percent = 999; - int do_progress = 0; + int do_progress = progress; - if (!base_name) + if (!base_name) { f = sha1fd(1, "<stdout>"); - else { + do_progress >>= 1; + } + else f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack"); - do_progress = progress; - } if (do_progress) fprintf(stderr, "Writing %d objects.\n", nr_result); @@ -390,6 +557,8 @@ static void write_pack_file(void) if (do_progress) fputc('\n', stderr); done: + if (written != nr_result) + die("wrote %d objects while expecting %d", written, nr_result); sha1close(f, pack_file_sha1, 1); } @@ -510,15 +679,15 @@ static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclud if (!exclude) { for (p = packed_git; p; p = p->next) { - struct pack_entry e; - if (find_pack_entry_one(sha1, &e, p)) { + unsigned long offset = find_pack_entry_one(sha1, p); + if (offset) { if (incremental) return 0; if (local && !p->pack_local) return 0; if (!found_pack) { - found_offset = e.offset; - found_pack = e.p; + found_offset = offset; + found_pack = p; } } } @@ -755,7 +924,7 @@ static int check_pbase_path(unsigned hash) return 0; } -static void add_preferred_base_object(char *name, unsigned hash) +static void add_preferred_base_object(const char *name, unsigned hash) { struct pbase_tree *it; int cmplen = name_cmp_len(name); @@ -784,6 +953,9 @@ static void add_preferred_base(unsigned char *sha1) unsigned long size; unsigned char tree_sha1[20]; + if (window <= num_preferred_base++) + return; + data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); if (!data) return; @@ -809,26 +981,67 @@ static void check_object(struct object_entry *entry) char type[20]; if (entry->in_pack && !entry->preferred_base) { - unsigned char base[20]; - unsigned long size; - struct object_entry *base_entry; + struct packed_git *p = entry->in_pack; + struct pack_window *w_curs = NULL; + unsigned long left = p->pack_size - entry->in_pack_offset; + unsigned long size, used; + unsigned char *buf; + struct object_entry *base_entry = NULL; + + buf = use_pack(p, &w_curs, entry->in_pack_offset, NULL); /* We want in_pack_type even if we do not reuse delta. * There is no point not reusing non-delta representations. */ - check_reuse_pack_delta(entry->in_pack, - entry->in_pack_offset, - base, &size, - &entry->in_pack_type); + used = unpack_object_header_gently(buf, left, + &entry->in_pack_type, &size); /* Check if it is delta, and the base is also an object * we are going to pack. If so we will reuse the existing * delta. */ - if (!no_reuse_delta && - entry->in_pack_type == OBJ_DELTA && - (base_entry = locate_object_entry(base)) && - (!base_entry->preferred_base)) { + if (!no_reuse_delta) { + unsigned char c, *base_name; + unsigned long ofs; + unsigned long used_0; + /* there is at least 20 bytes left in the pack */ + switch (entry->in_pack_type) { + case OBJ_REF_DELTA: + base_name = use_pack(p, &w_curs, + entry->in_pack_offset + used, NULL); + used += 20; + break; + case OBJ_OFS_DELTA: + buf = use_pack(p, &w_curs, + entry->in_pack_offset + used, NULL); + used_0 = 0; + c = buf[used_0++]; + ofs = c & 127; + while (c & 128) { + ofs += 1; + if (!ofs || ofs & ~(~0UL >> 7)) + die("delta base offset overflow in pack for %s", + sha1_to_hex(entry->sha1)); + c = buf[used_0++]; + ofs = (ofs << 7) + (c & 127); + } + if (ofs >= entry->in_pack_offset) + die("delta base offset out of bound for %s", + sha1_to_hex(entry->sha1)); + ofs = entry->in_pack_offset - ofs; + base_name = find_packed_object_name(p, ofs); + used += used_0; + break; + default: + base_name = NULL; + } + if (base_name) + base_entry = locate_object_entry(base_name); + } + unuse_pack(&w_curs); + entry->in_pack_header_size = used; + + if (base_entry) { /* Depth value does not matter - find_deltas() * will never consider reused delta as the @@ -837,9 +1050,9 @@ static void check_object(struct object_entry *entry) */ /* uncompressed size of the delta data */ - entry->size = entry->delta_size = size; + entry->size = size; entry->delta = base_entry; - entry->type = OBJ_DELTA; + entry->type = entry->in_pack_type; entry->delta_sibling = base_entry->delta_child; base_entry->delta_child = entry; @@ -1011,7 +1224,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, * on an earlier try, but only when reusing delta data. */ if (!no_reuse_delta && trg_entry->in_pack && - trg_entry->in_pack == src_entry->in_pack) + trg_entry->in_pack == src_entry->in_pack && + trg_entry->in_pack_type != OBJ_REF_DELTA && + trg_entry->in_pack_type != OBJ_OFS_DELTA) return 0; /* @@ -1163,7 +1378,7 @@ static void prepare_pack(int window, int depth) find_deltas(sorted_by_type, window+1, depth); } -static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) +static int reuse_cached_pack(unsigned char *sha1) { static const char cache[] = "pack-cache/pack-%s.%s"; char *cached_pack, *cached_idx; @@ -1243,14 +1458,105 @@ static int git_pack_config(const char *k, const char *v) return git_default_config(k, v); } +static void read_object_list_from_stdin(void) +{ + char line[40 + 1 + PATH_MAX + 2]; + unsigned char sha1[20]; + unsigned hash; + + for (;;) { + if (!fgets(line, sizeof(line), stdin)) { + if (feof(stdin)) + break; + if (!ferror(stdin)) + die("fgets returned NULL, not EOF, not error!"); + if (errno != EINTR) + die("fgets: %s", strerror(errno)); + clearerr(stdin); + continue; + } + if (line[0] == '-') { + if (get_sha1_hex(line+1, sha1)) + die("expected edge sha1, got garbage:\n %s", + line); + add_preferred_base(sha1); + continue; + } + if (get_sha1_hex(line, sha1)) + die("expected sha1, got garbage:\n %s", line); + + hash = name_hash(line+41); + add_preferred_base_object(line+41, hash); + add_object_entry(sha1, hash, 0); + } +} + +static void show_commit(struct commit *commit) +{ + unsigned hash = name_hash(""); + add_preferred_base_object("", hash); + add_object_entry(commit->object.sha1, hash, 0); +} + +static void show_object(struct object_array_entry *p) +{ + unsigned hash = name_hash(p->name); + add_preferred_base_object(p->name, hash); + add_object_entry(p->item->sha1, hash, 0); +} + +static void show_edge(struct commit *commit) +{ + add_preferred_base(commit->object.sha1); +} + +static void get_object_list(int ac, const char **av) +{ + struct rev_info revs; + char line[1000]; + int flags = 0; + + init_revisions(&revs, NULL); + save_commit_buffer = 0; + track_object_refs = 0; + setup_revisions(ac, av, &revs, NULL); + + while (fgets(line, sizeof(line), stdin) != NULL) { + int len = strlen(line); + if (line[len - 1] == '\n') + line[--len] = 0; + if (!len) + break; + if (*line == '-') { + if (!strcmp(line, "--not")) { + flags ^= UNINTERESTING; + continue; + } + die("not a rev '%s'", line); + } + if (handle_revision_arg(line, &revs, flags, 1)) + die("bad revision '%s'", line); + } + + prepare_revision_walk(&revs); + mark_edges_uninteresting(revs.commits, &revs, show_edge); + traverse_commit_list(&revs, show_commit, show_object); +} + int cmd_pack_objects(int argc, const char **argv, const char *prefix) { SHA_CTX ctx; - char line[40 + 1 + PATH_MAX + 2]; - int depth = 10, pack_to_stdout = 0; + int depth = 10; struct object_entry **list; - int num_preferred_base = 0; + int use_internal_rev_list = 0; + int thin = 0; int i; + const char *rp_av[64]; + int rp_ac; + + rp_av[0] = "pack-objects"; + rp_av[1] = "--objects"; /* --thin will make it --objects-edge */ + rp_ac = 2; git_config(git_pack_config); @@ -1258,63 +1564,104 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) for (i = 1; i < argc; i++) { const char *arg = argv[i]; - if (*arg == '-') { - if (!strcmp("--non-empty", arg)) { - non_empty = 1; - continue; - } - if (!strcmp("--local", arg)) { - local = 1; - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("--incremental", arg)) { - incremental = 1; - continue; - } - if (!strncmp("--window=", arg, 9)) { - char *end; - window = strtoul(arg+9, &end, 0); - if (!arg[9] || *end) - usage(pack_usage); - continue; - } - if (!strncmp("--depth=", arg, 8)) { - char *end; - depth = strtoul(arg+8, &end, 0); - if (!arg[8] || *end) - usage(pack_usage); - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("-q", arg)) { - progress = 0; - continue; - } - if (!strcmp("--no-reuse-delta", arg)) { - no_reuse_delta = 1; - continue; - } - if (!strcmp("--stdout", arg)) { - pack_to_stdout = 1; - continue; - } - usage(pack_usage); + if (*arg != '-') + break; + + if (!strcmp("--non-empty", arg)) { + non_empty = 1; + continue; + } + if (!strcmp("--local", arg)) { + local = 1; + continue; + } + if (!strcmp("--incremental", arg)) { + incremental = 1; + continue; + } + if (!strncmp("--window=", arg, 9)) { + char *end; + window = strtoul(arg+9, &end, 0); + if (!arg[9] || *end) + usage(pack_usage); + continue; } - if (base_name) - usage(pack_usage); - base_name = arg; + if (!strncmp("--depth=", arg, 8)) { + char *end; + depth = strtoul(arg+8, &end, 0); + if (!arg[8] || *end) + usage(pack_usage); + continue; + } + if (!strcmp("--progress", arg)) { + progress = 1; + continue; + } + if (!strcmp("--all-progress", arg)) { + progress = 2; + continue; + } + if (!strcmp("-q", arg)) { + progress = 0; + continue; + } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } + if (!strcmp("--delta-base-offset", arg)) { + allow_ofs_delta = 1; + continue; + } + if (!strcmp("--stdout", arg)) { + pack_to_stdout = 1; + continue; + } + if (!strcmp("--revs", arg)) { + use_internal_rev_list = 1; + continue; + } + if (!strcmp("--unpacked", arg) || + !strncmp("--unpacked=", arg, 11) || + !strcmp("--reflog", arg) || + !strcmp("--all", arg)) { + use_internal_rev_list = 1; + if (ARRAY_SIZE(rp_av) - 1 <= rp_ac) + die("too many internal rev-list options"); + rp_av[rp_ac++] = arg; + continue; + } + if (!strcmp("--thin", arg)) { + use_internal_rev_list = 1; + thin = 1; + rp_av[1] = "--objects-edge"; + continue; + } + usage(pack_usage); } + /* Traditionally "pack-objects [options] base extra" failed; + * we would however want to take refs parameter that would + * have been given to upstream rev-list ourselves, which means + * we somehow want to say what the base name is. So the + * syntax would be: + * + * pack-objects [options] base <refs...> + * + * in other words, we would treat the first non-option as the + * base_name and send everything else to the internal revision + * walker. + */ + + if (!pack_to_stdout) + base_name = argv[i++]; + if (pack_to_stdout != !base_name) usage(pack_usage); + if (!pack_to_stdout && thin) + die("--thin cannot be used to build an indexable pack."); + prepare_packed_git(); if (progress) { @@ -1322,35 +1669,13 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) setup_progress_signal(); } - for (;;) { - unsigned char sha1[20]; - unsigned hash; - - if (!fgets(line, sizeof(line), stdin)) { - if (feof(stdin)) - break; - if (!ferror(stdin)) - die("fgets returned NULL, not EOF, not error!"); - if (errno != EINTR) - die("fgets: %s", strerror(errno)); - clearerr(stdin); - continue; - } - - if (line[0] == '-') { - if (get_sha1_hex(line+1, sha1)) - die("expected edge sha1, got garbage:\n %s", - line+1); - if (num_preferred_base++ < window) - add_preferred_base(sha1); - continue; - } - if (get_sha1_hex(line, sha1)) - die("expected sha1, got garbage:\n %s", line); - hash = name_hash(line+41); - add_preferred_base_object(line+41, hash); - add_object_entry(sha1, hash, 0); + if (!use_internal_rev_list) + read_object_list_from_stdin(); + else { + rp_av[rp_ac] = NULL; + get_object_list(rp_ac, rp_av); } + if (progress) fprintf(stderr, "Done counting %d objects.\n", nr_objects); sorted_by_sha = create_final_object_list(); @@ -1367,12 +1692,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (progress && (nr_objects != nr_result)) fprintf(stderr, "Result has %d objects.\n", nr_result); - if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) + if (reuse_cached_pack(object_list_sha1)) ; else { if (nr_result) prepare_pack(window, depth); - if (progress && pack_to_stdout) { + if (progress == 1 && pack_to_stdout) { /* the other end usually displays progress itself */ struct itimerval v = {{0,},}; setitimer(ITIMER_REAL, &v, NULL); @@ -1386,7 +1711,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) } } if (progress) - fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", - nr_result, written, written_delta, reused, reused_delta); + fprintf(stderr, "Total %d (delta %d), reused %d (delta %d)\n", + written, written_delta, reused, reused_delta); return 0; } diff --git a/builtin-pack-refs.c b/builtin-pack-refs.c new file mode 100644 index 0000000000..6de7128b9d --- /dev/null +++ b/builtin-pack-refs.c @@ -0,0 +1,132 @@ +#include "cache.h" +#include "refs.h" +#include "object.h" +#include "tag.h" + +static const char builtin_pack_refs_usage[] = +"git-pack-refs [--all] [--prune | --no-prune]"; + +struct ref_to_prune { + struct ref_to_prune *next; + unsigned char sha1[20]; + char name[FLEX_ARRAY]; +}; + +struct pack_refs_cb_data { + int prune; + int all; + struct ref_to_prune *ref_to_prune; + FILE *refs_file; +}; + +static int do_not_prune(int flags) +{ + /* If it is already packed or if it is a symref, + * do not prune it. + */ + return (flags & (REF_ISSYMREF|REF_ISPACKED)); +} + +static int handle_one_ref(const char *path, const unsigned char *sha1, + int flags, void *cb_data) +{ + struct pack_refs_cb_data *cb = cb_data; + int is_tag_ref; + + /* Do not pack the symbolic refs */ + if ((flags & REF_ISSYMREF)) + return 0; + is_tag_ref = !strncmp(path, "refs/tags/", 10); + if (!cb->all && !is_tag_ref) + return 0; + + fprintf(cb->refs_file, "%s %s\n", sha1_to_hex(sha1), path); + if (is_tag_ref) { + struct object *o = parse_object(sha1); + if (o->type == OBJ_TAG) { + o = deref_tag(o, path, 0); + if (o) + fprintf(cb->refs_file, "^%s\n", + sha1_to_hex(o->sha1)); + } + } + + if (cb->prune && !do_not_prune(flags)) { + int namelen = strlen(path) + 1; + struct ref_to_prune *n = xcalloc(1, sizeof(*n) + namelen); + hashcpy(n->sha1, sha1); + strcpy(n->name, path); + n->next = cb->ref_to_prune; + cb->ref_to_prune = n; + } + return 0; +} + +/* make sure nobody touched the ref, and unlink */ +static void prune_ref(struct ref_to_prune *r) +{ + struct ref_lock *lock = lock_ref_sha1(r->name + 5, r->sha1); + + if (lock) { + unlink(git_path("%s", r->name)); + unlock_ref(lock); + } +} + +static void prune_refs(struct ref_to_prune *r) +{ + while (r) { + prune_ref(r); + r = r->next; + } +} + +static struct lock_file packed; + +int cmd_pack_refs(int argc, const char **argv, const char *prefix) +{ + int fd, i; + struct pack_refs_cb_data cbdata; + + memset(&cbdata, 0, sizeof(cbdata)); + + cbdata.prune = 1; + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strcmp(arg, "--prune")) { + cbdata.prune = 1; /* now the default */ + continue; + } + if (!strcmp(arg, "--no-prune")) { + cbdata.prune = 0; + continue; + } + if (!strcmp(arg, "--all")) { + cbdata.all = 1; + continue; + } + /* perhaps other parameters later... */ + break; + } + if (i != argc) + usage(builtin_pack_refs_usage); + + fd = hold_lock_file_for_update(&packed, git_path("packed-refs"), 1); + cbdata.refs_file = fdopen(fd, "w"); + if (!cbdata.refs_file) + die("unable to create ref-pack file structure (%s)", + strerror(errno)); + + /* perhaps other traits later as well */ + fprintf(cbdata.refs_file, "# pack-refs with: peeled \n"); + + for_each_ref(handle_one_ref, &cbdata); + fflush(cbdata.refs_file); + fsync(fd); + fclose(cbdata.refs_file); + if (commit_lock_file(&packed) < 0) + die("unable to overwrite old ref-pack file (%s)", strerror(errno)); + if (cbdata.prune) + prune_refs(cbdata.ref_to_prune); + return 0; +} diff --git a/builtin-prune-packed.c b/builtin-prune-packed.c index d3dd94d9ef..a57b76d7b7 100644 --- a/builtin-prune-packed.c +++ b/builtin-prune-packed.c @@ -4,9 +4,10 @@ static const char prune_packed_usage[] = "git-prune-packed [-n]"; -static int dryrun; +#define DRY_RUN 01 +#define VERBOSE 02 -static void prune_dir(int i, DIR *dir, char *pathname, int len) +static void prune_dir(int i, DIR *dir, char *pathname, int len, int opts) { struct dirent *de; char hex[40]; @@ -19,10 +20,10 @@ static void prune_dir(int i, DIR *dir, char *pathname, int len) memcpy(hex+2, de->d_name, 38); if (get_sha1_hex(hex, sha1)) continue; - if (!has_sha1_pack(sha1)) + if (!has_sha1_pack(sha1, NULL)) continue; memcpy(pathname + len, de->d_name, 38); - if (dryrun) + if (opts & DRY_RUN) printf("rm -f %s\n", pathname); else if (unlink(pathname) < 0) error("unable to unlink %s", pathname); @@ -31,7 +32,7 @@ static void prune_dir(int i, DIR *dir, char *pathname, int len) rmdir(pathname); } -static void prune_packed_objects(void) +void prune_packed_objects(int opts) { int i; static char pathname[PATH_MAX]; @@ -48,23 +49,31 @@ static void prune_packed_objects(void) sprintf(pathname + len, "%02x/", i); d = opendir(pathname); + if (opts == VERBOSE && (d || i == 255)) + fprintf(stderr, "Removing unused objects %d%%...\015", + ((i+1) * 100) / 256); if (!d) continue; - prune_dir(i, d, pathname, len + 3); + prune_dir(i, d, pathname, len + 3, opts); closedir(d); } + if (opts == VERBOSE) + fprintf(stderr, "\nDone.\n"); } int cmd_prune_packed(int argc, const char **argv, const char *prefix) { int i; + int opts = VERBOSE; for (i = 1; i < argc; i++) { const char *arg = argv[i]; if (*arg == '-') { if (!strcmp(arg, "-n")) - dryrun = 1; + opts |= DRY_RUN; + else if (!strcmp(arg, "-q")) + opts &= ~VERBOSE; else usage(prune_packed_usage); continue; @@ -73,6 +82,6 @@ int cmd_prune_packed(int argc, const char **argv, const char *prefix) usage(prune_packed_usage); } sync(); - prune_packed_objects(); + prune_packed_objects(opts); return 0; } diff --git a/builtin-prune.c b/builtin-prune.c index fc885ce55b..6f0ba0d04d 100644 --- a/builtin-prune.c +++ b/builtin-prune.c @@ -1,23 +1,24 @@ #include "cache.h" -#include "refs.h" -#include "tag.h" #include "commit.h" -#include "tree.h" -#include "blob.h" -#include "tree-walk.h" #include "diff.h" #include "revision.h" #include "builtin.h" -#include "cache-tree.h" +#include "reachable.h" static const char prune_usage[] = "git-prune [-n]"; static int show_only; -static struct rev_info revs; static int prune_object(char *path, const char *filename, const unsigned char *sha1) { + char buf[20]; + const char *type; + if (show_only) { - printf("would prune %s/%s\n", path, filename); + if (sha1_object_info(sha1, buf, NULL)) + type = "unknown"; + else + type = buf; + printf("%s %s\n", sha1_to_hex(sha1), type); return 0; } unlink(mkpath("%s/%s", path, filename)); @@ -78,148 +79,10 @@ static void prune_object_dir(const char *path) } } -static void process_blob(struct blob *blob, - struct object_array *p, - struct name_path *path, - const char *name) -{ - struct object *obj = &blob->object; - - if (obj->flags & SEEN) - return; - obj->flags |= SEEN; - /* Nothing to do, really .. The blob lookup was the important part */ -} - -static void process_tree(struct tree *tree, - struct object_array *p, - struct name_path *path, - const char *name) -{ - struct object *obj = &tree->object; - struct tree_desc desc; - struct name_entry entry; - struct name_path me; - - if (obj->flags & SEEN) - return; - obj->flags |= SEEN; - if (parse_tree(tree) < 0) - die("bad tree object %s", sha1_to_hex(obj->sha1)); - name = strdup(name); - add_object(obj, p, path, name); - me.up = path; - me.elem = name; - me.elem_len = strlen(name); - - desc.buf = tree->buffer; - desc.size = tree->size; - - while (tree_entry(&desc, &entry)) { - if (S_ISDIR(entry.mode)) - process_tree(lookup_tree(entry.sha1), p, &me, entry.path); - else - process_blob(lookup_blob(entry.sha1), p, &me, entry.path); - } - free(tree->buffer); - tree->buffer = NULL; -} - -static void process_tag(struct tag *tag, struct object_array *p, const char *name) -{ - struct object *obj = &tag->object; - struct name_path me; - - if (obj->flags & SEEN) - return; - obj->flags |= SEEN; - - me.up = NULL; - me.elem = "tag:/"; - me.elem_len = 5; - - if (parse_tag(tag) < 0) - die("bad tag object %s", sha1_to_hex(obj->sha1)); - add_object(tag->tagged, p, NULL, name); -} - -static void walk_commit_list(struct rev_info *revs) -{ - int i; - struct commit *commit; - struct object_array objects = { 0, 0, NULL }; - - /* Walk all commits, process their trees */ - while ((commit = get_revision(revs)) != NULL) - process_tree(commit->tree, &objects, NULL, ""); - - /* Then walk all the pending objects, recursively processing them too */ - for (i = 0; i < revs->pending.nr; i++) { - struct object_array_entry *pending = revs->pending.objects + i; - struct object *obj = pending->item; - const char *name = pending->name; - if (obj->type == OBJ_TAG) { - process_tag((struct tag *) obj, &objects, name); - continue; - } - if (obj->type == OBJ_TREE) { - process_tree((struct tree *)obj, &objects, NULL, name); - continue; - } - if (obj->type == OBJ_BLOB) { - process_blob((struct blob *)obj, &objects, NULL, name); - continue; - } - die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); - } -} - -static int add_one_ref(const char *path, const unsigned char *sha1) -{ - struct object *object = parse_object(sha1); - if (!object) - die("bad object ref: %s:%s", path, sha1_to_hex(sha1)); - add_pending_object(&revs, object, ""); - return 0; -} - -static void add_one_tree(const unsigned char *sha1) -{ - struct tree *tree = lookup_tree(sha1); - add_pending_object(&revs, &tree->object, ""); -} - -static void add_cache_tree(struct cache_tree *it) -{ - int i; - - if (it->entry_count >= 0) - add_one_tree(it->sha1); - for (i = 0; i < it->subtree_nr; i++) - add_cache_tree(it->down[i]->cache_tree); -} - -static void add_cache_refs(void) -{ - int i; - - read_cache(); - for (i = 0; i < active_nr; i++) { - lookup_blob(active_cache[i]->sha1); - /* - * We could add the blobs to the pending list, but quite - * frankly, we don't care. Once we've looked them up, and - * added them as objects, we've really done everything - * there is to do for a blob - */ - } - if (active_cache_tree) - add_cache_tree(active_cache_tree); -} - int cmd_prune(int argc, const char **argv, const char *prefix) { int i; + struct rev_info revs; for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -230,30 +93,13 @@ int cmd_prune(int argc, const char **argv, const char *prefix) usage(prune_usage); } - /* - * Set up revision parsing, and mark us as being interested - * in all object types, not just commits. - */ + save_commit_buffer = 0; init_revisions(&revs, prefix); - revs.tag_objects = 1; - revs.blob_objects = 1; - revs.tree_objects = 1; - - /* Add all external refs */ - for_each_ref(add_one_ref); - - /* Add all refs from the index file */ - add_cache_refs(); - - /* - * Set up the revision walk - this will move all commits - * from the pending list to the commit walking list. - */ - prepare_revision_walk(&revs); - - walk_commit_list(&revs); + mark_reachable_objects(&revs, 1); prune_object_dir(get_object_directory()); + sync(); + prune_packed_objects(show_only); return 0; } diff --git a/builtin-push.c b/builtin-push.c index 2b5e6fa9ed..7a3d2bb064 100644 --- a/builtin-push.c +++ b/builtin-push.c @@ -10,7 +10,7 @@ static const char push_usage[] = "git-push [--all] [--tags] [-f | --force] <repository> [<refspec>...]"; -static int all, tags, force, thin = 1; +static int all, tags, force, thin = 1, verbose; static const char *execute; #define BUF_SIZE (2084) @@ -27,13 +27,13 @@ static void add_refspec(const char *ref) refspec_nr = nr; } -static int expand_one_ref(const char *ref, const unsigned char *sha1) +static int expand_one_ref(const char *ref, const unsigned char *sha1, int flag, void *cb_data) { /* Ignore the "refs/" at the beginning of the refname */ ref += 5; if (!strncmp(ref, "tags/", 5)) - add_refspec(strdup(ref)); + add_refspec(xstrdup(ref)); return 0; } @@ -51,17 +51,42 @@ static void expand_refspecs(void) } if (!tags) return; - for_each_ref(expand_one_ref); + for_each_ref(expand_one_ref, NULL); } static void set_refspecs(const char **refs, int nr) { if (nr) { - size_t bytes = nr * sizeof(char *); - - refspec = xrealloc(refspec, bytes); - memcpy(refspec, refs, bytes); - refspec_nr = nr; + int pass; + for (pass = 0; pass < 2; pass++) { + /* pass 0 counts and allocates, pass 1 fills */ + int i, cnt; + for (i = cnt = 0; i < nr; i++) { + if (!strcmp("tag", refs[i])) { + int len; + char *tag; + if (nr <= ++i) + die("tag <tag> shorthand without <tag>"); + if (pass) { + len = strlen(refs[i]) + 11; + tag = xmalloc(len); + strcpy(tag, "refs/tags/"); + strcat(tag, refs[i]); + refspec[cnt] = tag; + } + cnt++; + continue; + } + if (pass) + refspec[cnt] = refs[i]; + cnt++; + } + if (!pass) { + size_t bytes = cnt * sizeof(char *); + refspec_nr = cnt; + refspec = xrealloc(refspec, bytes); + } + } } expand_refspecs(); } @@ -78,12 +103,12 @@ static int get_remotes_uri(const char *repo, const char *uri[MAX_URI]) int is_refspec; char *s, *p; - if (!strncmp("URL: ", buffer, 5)) { + if (!strncmp("URL:", buffer, 4)) { is_refspec = 0; - s = buffer + 5; - } else if (!strncmp("Push: ", buffer, 6)) { + s = buffer + 4; + } else if (!strncmp("Push:", buffer, 5)) { is_refspec = 1; - s = buffer + 6; + s = buffer + 5; } else continue; @@ -100,12 +125,12 @@ static int get_remotes_uri(const char *repo, const char *uri[MAX_URI]) if (!is_refspec) { if (n < MAX_URI) - uri[n++] = strdup(s); + uri[n++] = xstrdup(s); else error("more than %d URL's specified, ignoring the rest", MAX_URI); } else if (is_refspec && !has_explicit_refspec) - add_refspec(strdup(s)); + add_refspec(xstrdup(s)); } fclose(f); if (!n) @@ -125,13 +150,13 @@ static int get_remote_config(const char* key, const char* value) !strncmp(key + 7, config_repo, config_repo_len)) { if (!strcmp(key + 7 + config_repo_len, ".url")) { if (config_current_uri < MAX_URI) - config_uri[config_current_uri++] = strdup(value); + config_uri[config_current_uri++] = xstrdup(value); else error("more than %d URL's specified, ignoring the rest", MAX_URI); } else if (config_get_refspecs && !strcmp(key + 7 + config_repo_len, ".push")) - add_refspec(strdup(value)); + add_refspec(xstrdup(value)); } return 0; } @@ -232,7 +257,7 @@ static int do_push(const char *repo) common_argc = argc; for (i = 0; i < n; i++) { - int error; + int err; int dest_argc = common_argc; int dest_refspec_nr = refspec_nr; const char **dest_refspec = refspec; @@ -248,10 +273,12 @@ static int do_push(const char *repo) while (dest_refspec_nr--) argv[dest_argc++] = *dest_refspec++; argv[dest_argc] = NULL; - error = run_command_v(argc, argv); - if (!error) + if (verbose) + fprintf(stderr, "Pushing to %s\n", dest); + err = run_command_v(argv); + if (!err) continue; - switch (error) { + switch (err) { case -ERR_RUN_COMMAND_FORK: die("unable to fork for %s", sender); case -ERR_RUN_COMMAND_EXEC: @@ -262,7 +289,7 @@ static int do_push(const char *repo) case -ERR_RUN_COMMAND_WAITPID_NOEXIT: die("%s died with strange error", sender); default: - return -error; + return -err; } } return 0; @@ -281,6 +308,14 @@ int cmd_push(int argc, const char **argv, const char *prefix) i++; break; } + if (!strcmp(arg, "-v")) { + verbose=1; + continue; + } + if (!strncmp(arg, "--repo=", 7)) { + repo = arg+7; + continue; + } if (!strcmp(arg, "--all")) { all = 1; continue; diff --git a/builtin-read-tree.c b/builtin-read-tree.c index c1867d2a00..8ba436dbac 100644 --- a/builtin-read-tree.c +++ b/builtin-read-tree.c @@ -10,6 +10,7 @@ #include "tree-walk.h" #include "cache-tree.h" #include "unpack-trees.h" +#include "dir.h" #include "builtin.h" static struct object_list *trees; @@ -84,7 +85,7 @@ static void prime_cache_tree(void) } -static const char read_tree_usage[] = "git-read-tree (<sha> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <sha1> [<sha2> [<sha3>]])"; +static const char read_tree_usage[] = "git-read-tree (<sha> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] [--exclude-per-directory=<gitignore>] <sha1> [<sha2> [<sha3>]])"; static struct lock_file lock_file; @@ -178,6 +179,23 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix) continue; } + if (!strncmp(arg, "--exclude-per-directory=", 24)) { + struct dir_struct *dir; + + if (opts.dir) + die("more than one --exclude-per-directory are given."); + + dir = calloc(1, sizeof(*opts.dir)); + dir->show_ignored = 1; + dir->exclude_per_dir = arg + 24; + opts.dir = dir; + /* We do not need to nor want to do read-directory + * here; we are merely interested in reusing the + * per directory ignore stack mechanism. + */ + continue; + } + /* using -u and -i at the same time makes no sense */ if (1 < opts.index_only + opts.update) usage(read_tree_usage); @@ -190,6 +208,8 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix) } if ((opts.update||opts.index_only) && !opts.merge) usage(read_tree_usage); + if ((opts.dir && !opts.update)) + die("--exclude-per-directory is meaningless unless -u"); if (opts.prefix) { int pfxlen = strlen(opts.prefix); diff --git a/builtin-reflog.c b/builtin-reflog.c new file mode 100644 index 0000000000..7206b7a013 --- /dev/null +++ b/builtin-reflog.c @@ -0,0 +1,385 @@ +#include "cache.h" +#include "builtin.h" +#include "commit.h" +#include "refs.h" +#include "dir.h" +#include "tree-walk.h" +#include "diff.h" +#include "revision.h" +#include "reachable.h" + +/* + * reflog expire + */ + +static const char reflog_expire_usage[] = +"git-reflog expire [--verbose] [--dry-run] [--fix-stale] [--expire=<time>] [--expire-unreachable=<time>] [--all] <refs>..."; + +static unsigned long default_reflog_expire; +static unsigned long default_reflog_expire_unreachable; + +struct cmd_reflog_expire_cb { + struct rev_info revs; + int dry_run; + int stalefix; + int verbose; + unsigned long expire_total; + unsigned long expire_unreachable; +}; + +struct expire_reflog_cb { + FILE *newlog; + const char *ref; + struct commit *ref_commit; + struct cmd_reflog_expire_cb *cmd; +}; + +#define INCOMPLETE (1u<<10) +#define STUDYING (1u<<11) + +static int tree_is_complete(const unsigned char *sha1) +{ + struct tree_desc desc; + struct name_entry entry; + int complete; + struct tree *tree; + + tree = lookup_tree(sha1); + if (!tree) + return 0; + if (tree->object.flags & SEEN) + return 1; + if (tree->object.flags & INCOMPLETE) + return 0; + + desc.buf = tree->buffer; + desc.size = tree->size; + if (!desc.buf) { + char type[20]; + void *data = read_sha1_file(sha1, type, &desc.size); + if (!data) { + tree->object.flags |= INCOMPLETE; + return 0; + } + desc.buf = data; + tree->buffer = data; + } + complete = 1; + while (tree_entry(&desc, &entry)) { + if (!has_sha1_file(entry.sha1) || + (S_ISDIR(entry.mode) && !tree_is_complete(entry.sha1))) { + tree->object.flags |= INCOMPLETE; + complete = 0; + } + } + free(tree->buffer); + tree->buffer = NULL; + + if (complete) + tree->object.flags |= SEEN; + return complete; +} + +static int commit_is_complete(struct commit *commit) +{ + struct object_array study; + struct object_array found; + int is_incomplete = 0; + int i; + + /* early return */ + if (commit->object.flags & SEEN) + return 1; + if (commit->object.flags & INCOMPLETE) + return 0; + /* + * Find all commits that are reachable and are not marked as + * SEEN. Then make sure the trees and blobs contained are + * complete. After that, mark these commits also as SEEN. + * If some of the objects that are needed to complete this + * commit are missing, mark this commit as INCOMPLETE. + */ + memset(&study, 0, sizeof(study)); + memset(&found, 0, sizeof(found)); + add_object_array(&commit->object, NULL, &study); + add_object_array(&commit->object, NULL, &found); + commit->object.flags |= STUDYING; + while (study.nr) { + struct commit *c; + struct commit_list *parent; + + c = (struct commit *)study.objects[--study.nr].item; + if (!c->object.parsed && !parse_object(c->object.sha1)) + c->object.flags |= INCOMPLETE; + + if (c->object.flags & INCOMPLETE) { + is_incomplete = 1; + break; + } + else if (c->object.flags & SEEN) + continue; + for (parent = c->parents; parent; parent = parent->next) { + struct commit *p = parent->item; + if (p->object.flags & STUDYING) + continue; + p->object.flags |= STUDYING; + add_object_array(&p->object, NULL, &study); + add_object_array(&p->object, NULL, &found); + } + } + if (!is_incomplete) { + /* + * make sure all commits in "found" array have all the + * necessary objects. + */ + for (i = 0; i < found.nr; i++) { + struct commit *c = + (struct commit *)found.objects[i].item; + if (!tree_is_complete(c->tree->object.sha1)) { + is_incomplete = 1; + c->object.flags |= INCOMPLETE; + } + } + if (!is_incomplete) { + /* mark all found commits as complete, iow SEEN */ + for (i = 0; i < found.nr; i++) + found.objects[i].item->flags |= SEEN; + } + } + /* clear flags from the objects we traversed */ + for (i = 0; i < found.nr; i++) + found.objects[i].item->flags &= ~STUDYING; + if (is_incomplete) + commit->object.flags |= INCOMPLETE; + else { + /* + * If we come here, we have (1) traversed the ancestry chain + * from the "commit" until we reach SEEN commits (which are + * known to be complete), and (2) made sure that the commits + * encountered during the above traversal refer to trees that + * are complete. Which means that we know *all* the commits + * we have seen during this process are complete. + */ + for (i = 0; i < found.nr; i++) + found.objects[i].item->flags |= SEEN; + } + /* free object arrays */ + free(study.objects); + free(found.objects); + return !is_incomplete; +} + +static int keep_entry(struct commit **it, unsigned char *sha1) +{ + struct commit *commit; + + if (is_null_sha1(sha1)) + return 1; + commit = lookup_commit_reference_gently(sha1, 1); + if (!commit) + return 0; + + /* + * Make sure everything in this commit exists. + * + * We have walked all the objects reachable from the refs + * and cache earlier. The commits reachable by this commit + * must meet SEEN commits -- and then we should mark them as + * SEEN as well. + */ + if (!commit_is_complete(commit)) + return 0; + *it = commit; + return 1; +} + +static int expire_reflog_ent(unsigned char *osha1, unsigned char *nsha1, + const char *email, unsigned long timestamp, int tz, + const char *message, void *cb_data) +{ + struct expire_reflog_cb *cb = cb_data; + struct commit *old, *new; + + if (timestamp < cb->cmd->expire_total) + goto prune; + + old = new = NULL; + if (cb->cmd->stalefix && + (!keep_entry(&old, osha1) || !keep_entry(&new, nsha1))) + goto prune; + + if (timestamp < cb->cmd->expire_unreachable) { + if (!cb->ref_commit) + goto prune; + if (!old && !is_null_sha1(osha1)) + old = lookup_commit_reference_gently(osha1, 1); + if (!new && !is_null_sha1(nsha1)) + new = lookup_commit_reference_gently(nsha1, 1); + if ((old && !in_merge_bases(old, cb->ref_commit)) || + (new && !in_merge_bases(new, cb->ref_commit))) + goto prune; + } + + if (cb->newlog) { + char sign = (tz < 0) ? '-' : '+'; + int zone = (tz < 0) ? (-tz) : tz; + fprintf(cb->newlog, "%s %s %s %lu %c%04d\t%s", + sha1_to_hex(osha1), sha1_to_hex(nsha1), + email, timestamp, sign, zone, + message); + } + if (cb->cmd->verbose) + printf("keep %s", message); + return 0; + prune: + if (!cb->newlog || cb->cmd->verbose) + printf("%sprune %s", cb->newlog ? "" : "would ", message); + return 0; +} + +static int expire_reflog(const char *ref, const unsigned char *sha1, int unused, void *cb_data) +{ + struct cmd_reflog_expire_cb *cmd = cb_data; + struct expire_reflog_cb cb; + struct ref_lock *lock; + char *newlog_path = NULL; + int status = 0; + + if (strncmp(ref, "refs/", 5)) + return error("not a ref '%s'", ref); + + memset(&cb, 0, sizeof(cb)); + /* we take the lock for the ref itself to prevent it from + * getting updated. + */ + lock = lock_ref_sha1(ref + 5, sha1); + if (!lock) + return error("cannot lock ref '%s'", ref); + if (!file_exists(lock->log_file)) + goto finish; + if (!cmd->dry_run) { + newlog_path = xstrdup(git_path("logs/%s.lock", ref)); + cb.newlog = fopen(newlog_path, "w"); + } + + cb.ref_commit = lookup_commit_reference_gently(sha1, 1); + if (!cb.ref_commit) + fprintf(stderr, + "warning: ref '%s' does not point at a commit\n", ref); + cb.ref = ref; + cb.cmd = cmd; + for_each_reflog_ent(ref, expire_reflog_ent, &cb); + finish: + if (cb.newlog) { + if (fclose(cb.newlog)) + status |= error("%s: %s", strerror(errno), + newlog_path); + if (rename(newlog_path, lock->log_file)) { + status |= error("cannot rename %s to %s", + newlog_path, lock->log_file); + unlink(newlog_path); + } + } + free(newlog_path); + unlock_ref(lock); + return status; +} + +static int reflog_expire_config(const char *var, const char *value) +{ + if (!strcmp(var, "gc.reflogexpire")) + default_reflog_expire = approxidate(value); + else if (!strcmp(var, "gc.reflogexpireunreachable")) + default_reflog_expire_unreachable = approxidate(value); + else + return git_default_config(var, value); + return 0; +} + +static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) +{ + struct cmd_reflog_expire_cb cb; + unsigned long now = time(NULL); + int i, status, do_all; + + git_config(reflog_expire_config); + + save_commit_buffer = 0; + do_all = status = 0; + memset(&cb, 0, sizeof(cb)); + + if (!default_reflog_expire_unreachable) + default_reflog_expire_unreachable = now - 30 * 24 * 3600; + if (!default_reflog_expire) + default_reflog_expire = now - 90 * 24 * 3600; + cb.expire_total = default_reflog_expire; + cb.expire_unreachable = default_reflog_expire_unreachable; + + /* + * We can trust the commits and objects reachable from refs + * even in older repository. We cannot trust what's reachable + * from reflog if the repository was pruned with older git. + */ + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strcmp(arg, "--dry-run") || !strcmp(arg, "-n")) + cb.dry_run = 1; + else if (!strncmp(arg, "--expire=", 9)) + cb.expire_total = approxidate(arg + 9); + else if (!strncmp(arg, "--expire-unreachable=", 21)) + cb.expire_unreachable = approxidate(arg + 21); + else if (!strcmp(arg, "--stale-fix")) + cb.stalefix = 1; + else if (!strcmp(arg, "--all")) + do_all = 1; + else if (!strcmp(arg, "--verbose")) + cb.verbose = 1; + else if (!strcmp(arg, "--")) { + i++; + break; + } + else if (arg[0] == '-') + usage(reflog_expire_usage); + else + break; + } + if (cb.stalefix) { + init_revisions(&cb.revs, prefix); + if (cb.verbose) + printf("Marking reachable objects..."); + mark_reachable_objects(&cb.revs, 0); + if (cb.verbose) + putchar('\n'); + } + + if (do_all) + status |= for_each_ref(expire_reflog, &cb); + while (i < argc) { + const char *ref = argv[i++]; + unsigned char sha1[20]; + if (!resolve_ref(ref, sha1, 1, NULL)) { + status |= error("%s points nowhere!", ref); + continue; + } + status |= expire_reflog(ref, sha1, 0, &cb); + } + return status; +} + +/* + * main "reflog" + */ + +static const char reflog_usage[] = +"git-reflog (expire | ...)"; + +int cmd_reflog(int argc, const char **argv, const char *prefix) +{ + if (argc < 2) + usage(reflog_usage); + else if (!strcmp(argv[1], "expire")) + return cmd_reflog_expire(argc - 1, argv + 1, prefix); + else + usage(reflog_usage); +} diff --git a/builtin-repo-config.c b/builtin-repo-config.c index c416480208..90633119d4 100644 --- a/builtin-repo-config.c +++ b/builtin-repo-config.c @@ -1,9 +1,8 @@ #include "builtin.h" #include "cache.h" -#include <regex.h> static const char git_config_set_usage[] = -"git-repo-config [ --bool | --int ] [--get | --get-all | --get-regexp | --replace-all | --unset | --unset-all] name [value [value_regex]] | --list"; +"git-repo-config [ --global ] [ --bool | --int ] [--get | --get-all | --get-regexp | --replace-all | --add | --unset | --unset-all] name [value [value_regex]] | --rename-section old_name new_name | --list"; static char *key; static regex_t *key_regexp; @@ -67,24 +66,24 @@ static int get_value(const char* key_, const char* regex_) char *global = NULL, *repo_config = NULL; const char *local; - local = getenv("GIT_CONFIG"); + local = getenv(CONFIG_ENVIRONMENT); if (!local) { const char *home = getenv("HOME"); - local = getenv("GIT_CONFIG_LOCAL"); + local = getenv(CONFIG_LOCAL_ENVIRONMENT); if (!local) - local = repo_config = strdup(git_path("config")); + local = repo_config = xstrdup(git_path("config")); if (home) - global = strdup(mkpath("%s/.gitconfig", home)); + global = xstrdup(mkpath("%s/.gitconfig", home)); } - key = strdup(key_); + key = xstrdup(key_); for (tl=key+strlen(key)-1; tl >= key && *tl != '.'; --tl) *tl = tolower(*tl); for (tl=key; *tl && *tl != '.'; ++tl) *tl = tolower(*tl); if (use_key_regexp) { - key_regexp = (regex_t*)malloc(sizeof(regex_t)); + key_regexp = (regex_t*)xmalloc(sizeof(regex_t)); if (regcomp(key_regexp, key, REG_EXTENDED)) { fprintf(stderr, "Invalid key pattern: %s\n", key_); goto free_strings; @@ -97,7 +96,7 @@ static int get_value(const char* key_, const char* regex_) regex_++; } - regexp = (regex_t*)malloc(sizeof(regex_t)); + regexp = (regex_t*)xmalloc(sizeof(regex_t)); if (regcomp(regexp, regex_, REG_EXTENDED)) { fprintf(stderr, "Invalid pattern: %s\n", regex_); goto free_strings; @@ -119,13 +118,11 @@ static int get_value(const char* key_, const char* regex_) if (do_all) ret = !seen; else - ret = (seen == 1) ? 0 : 1; + ret = (seen == 1) ? 0 : seen > 1 ? 2 : 1; free_strings: - if (repo_config) - free(repo_config); - if (global) - free(global); + free(repo_config); + free(global); return ret; } @@ -141,7 +138,28 @@ int cmd_repo_config(int argc, const char **argv, const char *prefix) type = T_BOOL; else if (!strcmp(argv[1], "--list") || !strcmp(argv[1], "-l")) return git_config(show_all_config); - else + else if (!strcmp(argv[1], "--global")) { + char *home = getenv("HOME"); + if (home) { + char *user_config = xstrdup(mkpath("%s/.gitconfig", home)); + setenv("GIT_CONFIG", user_config, 1); + free(user_config); + } else { + die("$HOME not set"); + } + } else if (!strcmp(argv[1], "--rename-section")) { + int ret; + if (argc != 4) + usage(git_config_set_usage); + ret = git_config_rename_section(argv[2], argv[3]); + if (ret < 0) + return ret; + if (ret == 0) { + fprintf(stderr, "No such section!\n"); + return 1; + } + return 0; + } else break; argc--; argv++; @@ -183,7 +201,9 @@ int cmd_repo_config(int argc, const char **argv, const char *prefix) use_key_regexp = 1; do_all = 1; return get_value(argv[2], argv[3]); - } else if (!strcmp(argv[1], "--replace-all")) + } else if (!strcmp(argv[1], "--add")) + return git_config_set_multivar(argv[2], argv[3], "^$", 0); + else if (!strcmp(argv[1], "--replace-all")) return git_config_set_multivar(argv[2], argv[3], NULL, 1); else diff --git a/builtin-rerere.c b/builtin-rerere.c new file mode 100644 index 0000000000..318d959d89 --- /dev/null +++ b/builtin-rerere.c @@ -0,0 +1,421 @@ +#include "cache.h" +#include "path-list.h" +#include "xdiff/xdiff.h" +#include "xdiff-interface.h" + +#include <time.h> + +static const char git_rerere_usage[] = +"git-rerere [clear | status | diff | gc]"; + +/* these values are days */ +static int cutoff_noresolve = 15; +static int cutoff_resolve = 60; + +static char *merge_rr_path; + +static const char *rr_path(const char *name, const char *file) +{ + return git_path("rr-cache/%s/%s", name, file); +} + +static void read_rr(struct path_list *rr) +{ + unsigned char sha1[20]; + char buf[PATH_MAX]; + FILE *in = fopen(merge_rr_path, "r"); + if (!in) + return; + while (fread(buf, 40, 1, in) == 1) { + int i; + char *name; + if (get_sha1_hex(buf, sha1)) + die("corrupt MERGE_RR"); + buf[40] = '\0'; + name = xstrdup(buf); + if (fgetc(in) != '\t') + die("corrupt MERGE_RR"); + for (i = 0; i < sizeof(buf) && (buf[i] = fgetc(in)); i++) + ; /* do nothing */ + if (i == sizeof(buf)) + die("filename too long"); + path_list_insert(buf, rr)->util = xstrdup(name); + } + fclose(in); +} + +static struct lock_file write_lock; + +static int write_rr(struct path_list *rr, int out_fd) +{ + int i; + for (i = 0; i < rr->nr; i++) { + const char *path = rr->items[i].path; + int length = strlen(path) + 1; + if (write_in_full(out_fd, rr->items[i].util, 40) != 40 || + write_in_full(out_fd, "\t", 1) != 1 || + write_in_full(out_fd, path, length) != length) + die("unable to write rerere record"); + } + close(out_fd); + return commit_lock_file(&write_lock); +} + +struct buffer { + char *ptr; + int nr, alloc; +}; + +static void append_line(struct buffer *buffer, const char *line) +{ + int len = strlen(line); + + if (buffer->nr + len > buffer->alloc) { + buffer->alloc = alloc_nr(buffer->nr + len); + buffer->ptr = xrealloc(buffer->ptr, buffer->alloc); + } + memcpy(buffer->ptr + buffer->nr, line, len); + buffer->nr += len; +} + +static int handle_file(const char *path, + unsigned char *sha1, const char *output) +{ + SHA_CTX ctx; + char buf[1024]; + int hunk = 0, hunk_no = 0; + struct buffer minus = { NULL, 0, 0 }, plus = { NULL, 0, 0 }; + struct buffer *one = &minus, *two = + + FILE *f = fopen(path, "r"); + FILE *out; + + if (!f) + return error("Could not open %s", path); + + if (output) { + out = fopen(output, "w"); + if (!out) { + fclose(f); + return error("Could not write %s", output); + } + } else + out = NULL; + + if (sha1) + SHA1_Init(&ctx); + + while (fgets(buf, sizeof(buf), f)) { + if (!strncmp("<<<<<<< ", buf, 8)) + hunk = 1; + else if (!strncmp("=======", buf, 7)) + hunk = 2; + else if (!strncmp(">>>>>>> ", buf, 8)) { + hunk_no++; + hunk = 0; + if (memcmp(one->ptr, two->ptr, one->nr < two->nr ? + one->nr : two->nr) > 0) { + struct buffer *swap = one; + one = two; + two = swap; + } + if (out) { + fputs("<<<<<<<\n", out); + fwrite(one->ptr, one->nr, 1, out); + fputs("=======\n", out); + fwrite(two->ptr, two->nr, 1, out); + fputs(">>>>>>>\n", out); + } + if (sha1) { + SHA1_Update(&ctx, one->ptr, one->nr); + SHA1_Update(&ctx, "\0", 1); + SHA1_Update(&ctx, two->ptr, two->nr); + SHA1_Update(&ctx, "\0", 1); + } + } else if (hunk == 1) + append_line(one, buf); + else if (hunk == 2) + append_line(two, buf); + else if (out) + fputs(buf, out); + } + + fclose(f); + if (out) + fclose(out); + if (sha1) + SHA1_Final(sha1, &ctx); + return hunk_no; +} + +static int find_conflict(struct path_list *conflict) +{ + int i; + if (read_cache() < 0) + return error("Could not read index"); + for (i = 0; i + 2 < active_nr; i++) { + struct cache_entry *e1 = active_cache[i]; + struct cache_entry *e2 = active_cache[i + 1]; + struct cache_entry *e3 = active_cache[i + 2]; + if (ce_stage(e1) == 1 && ce_stage(e2) == 2 && + ce_stage(e3) == 3 && ce_same_name(e1, e2) && + ce_same_name(e1, e3)) { + path_list_insert((const char *)e1->name, conflict); + i += 3; + } + } + return 0; +} + +static int merge(const char *name, const char *path) +{ + int ret; + mmfile_t cur, base, other; + mmbuffer_t result = {NULL, 0}; + xpparam_t xpp = {XDF_NEED_MINIMAL}; + + if (handle_file(path, NULL, rr_path(name, "thisimage")) < 0) + return 1; + + if (read_mmfile(&cur, rr_path(name, "thisimage")) || + read_mmfile(&base, rr_path(name, "preimage")) || + read_mmfile(&other, rr_path(name, "postimage"))) + return 1; + ret = xdl_merge(&base, &cur, "", &other, "", + &xpp, XDL_MERGE_ZEALOUS, &result); + if (!ret) { + FILE *f = fopen(path, "w"); + if (!f) + return error("Could not write to %s", path); + fwrite(result.ptr, result.size, 1, f); + fclose(f); + } + + free(cur.ptr); + free(base.ptr); + free(other.ptr); + free(result.ptr); + + return ret; +} + +static void unlink_rr_item(const char *name) +{ + unlink(rr_path(name, "thisimage")); + unlink(rr_path(name, "preimage")); + unlink(rr_path(name, "postimage")); + rmdir(git_path("rr-cache/%s", name)); +} + +static void garbage_collect(struct path_list *rr) +{ + struct path_list to_remove = { NULL, 0, 0, 1 }; + char buf[1024]; + DIR *dir; + struct dirent *e; + int len, i, cutoff; + time_t now = time(NULL), then; + + strlcpy(buf, git_path("rr-cache"), sizeof(buf)); + len = strlen(buf); + dir = opendir(buf); + strcpy(buf + len++, "/"); + while ((e = readdir(dir))) { + const char *name = e->d_name; + struct stat st; + if (name[0] == '.' && (name[1] == '\0' || + (name[1] == '.' && name[2] == '\0'))) + continue; + i = snprintf(buf + len, sizeof(buf) - len, "%s", name); + strlcpy(buf + len + i, "/preimage", sizeof(buf) - len - i); + if (stat(buf, &st)) + continue; + then = st.st_mtime; + strlcpy(buf + len + i, "/postimage", sizeof(buf) - len - i); + cutoff = stat(buf, &st) ? cutoff_noresolve : cutoff_resolve; + if (then < now - cutoff * 86400) { + buf[len + i] = '\0'; + path_list_insert(xstrdup(name), &to_remove); + } + } + for (i = 0; i < to_remove.nr; i++) + unlink_rr_item(to_remove.items[i].path); + path_list_clear(&to_remove, 0); +} + +static int outf(void *dummy, mmbuffer_t *ptr, int nbuf) +{ + int i; + for (i = 0; i < nbuf; i++) + if (write_in_full(1, ptr[i].ptr, ptr[i].size) != ptr[i].size) + return -1; + return 0; +} + +static int diff_two(const char *file1, const char *label1, + const char *file2, const char *label2) +{ + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + mmfile_t minus, plus; + + if (read_mmfile(&minus, file1) || read_mmfile(&plus, file2)) + return 1; + + printf("--- a/%s\n+++ b/%s\n", label1, label2); + fflush(stdout); + xpp.flags = XDF_NEED_MINIMAL; + xecfg.ctxlen = 3; + xecfg.flags = 0; + ecb.outf = outf; + xdl_diff(&minus, &plus, &xpp, &xecfg, &ecb); + + free(minus.ptr); + free(plus.ptr); + return 0; +} + +static int copy_file(const char *src, const char *dest) +{ + FILE *in, *out; + char buffer[32768]; + int count; + + if (!(in = fopen(src, "r"))) + return error("Could not open %s", src); + if (!(out = fopen(dest, "w"))) + return error("Could not open %s", dest); + while ((count = fread(buffer, 1, sizeof(buffer), in))) + fwrite(buffer, 1, count, out); + fclose(in); + fclose(out); + return 0; +} + +static int do_plain_rerere(struct path_list *rr, int fd) +{ + struct path_list conflict = { NULL, 0, 0, 1 }; + int i; + + find_conflict(&conflict); + + /* + * MERGE_RR records paths with conflicts immediately after merge + * failed. Some of the conflicted paths might have been hand resolved + * in the working tree since then, but the initial run would catch all + * and register their preimages. + */ + + for (i = 0; i < conflict.nr; i++) { + const char *path = conflict.items[i].path; + if (!path_list_has_path(rr, path)) { + unsigned char sha1[20]; + char *hex; + int ret; + ret = handle_file(path, sha1, NULL); + if (ret < 1) + continue; + hex = xstrdup(sha1_to_hex(sha1)); + path_list_insert(path, rr)->util = hex; + if (mkdir(git_path("rr-cache/%s", hex), 0755)) + continue;; + handle_file(path, NULL, rr_path(hex, "preimage")); + fprintf(stderr, "Recorded preimage for '%s'\n", path); + } + } + + /* + * Now some of the paths that had conflicts earlier might have been + * hand resolved. Others may be similar to a conflict already that + * was resolved before. + */ + + for (i = 0; i < rr->nr; i++) { + struct stat st; + int ret; + const char *path = rr->items[i].path; + const char *name = (const char *)rr->items[i].util; + + if (!stat(rr_path(name, "preimage"), &st) && + !stat(rr_path(name, "postimage"), &st)) { + if (!merge(name, path)) { + fprintf(stderr, "Resolved '%s' using " + "previous resolution.\n", path); + goto tail_optimization; + } + } + + /* Let's see if we have resolved it. */ + ret = handle_file(path, NULL, NULL); + if (ret) + continue; + + fprintf(stderr, "Recorded resolution for '%s'.\n", path); + copy_file(path, rr_path(name, "postimage")); +tail_optimization: + if (i < rr->nr - 1) + memmove(rr->items + i, + rr->items + i + 1, + sizeof(rr->items[0]) * (rr->nr - i - 1)); + rr->nr--; + i--; + } + + return write_rr(rr, fd); +} + +static int git_rerere_config(const char *var, const char *value) +{ + if (!strcmp(var, "gc.rerereresolved")) + cutoff_resolve = git_config_int(var, value); + else if (!strcmp(var, "gc.rerereunresolved")) + cutoff_noresolve = git_config_int(var, value); + else + return git_default_config(var, value); + return 0; +} + +int cmd_rerere(int argc, const char **argv, const char *prefix) +{ + struct path_list merge_rr = { NULL, 0, 0, 1 }; + int i, fd = -1; + struct stat st; + + if (stat(git_path("rr-cache"), &st) || !S_ISDIR(st.st_mode)) + return 0; + + git_config(git_rerere_config); + + merge_rr_path = xstrdup(git_path("rr-cache/MERGE_RR")); + fd = hold_lock_file_for_update(&write_lock, merge_rr_path, 1); + read_rr(&merge_rr); + + if (argc < 2) + return do_plain_rerere(&merge_rr, fd); + else if (!strcmp(argv[1], "clear")) { + for (i = 0; i < merge_rr.nr; i++) { + const char *name = (const char *)merge_rr.items[i].util; + if (!stat(git_path("rr-cache/%s", name), &st) && + S_ISDIR(st.st_mode) && + stat(rr_path(name, "postimage"), &st)) + unlink_rr_item(name); + } + unlink(merge_rr_path); + } else if (!strcmp(argv[1], "gc")) + garbage_collect(&merge_rr); + else if (!strcmp(argv[1], "status")) + for (i = 0; i < merge_rr.nr; i++) + printf("%s\n", merge_rr.items[i].path); + else if (!strcmp(argv[1], "diff")) + for (i = 0; i < merge_rr.nr; i++) { + const char *path = merge_rr.items[i].path; + const char *name = (const char *)merge_rr.items[i].util; + diff_two(rr_path(name, "preimage"), path, path, path); + } + else + usage(git_rerere_usage); + + path_list_clear(&merge_rr, 1); + return 0; +} + diff --git a/builtin-rev-list.c b/builtin-rev-list.c index bc48a3e230..1bb3a06680 100644 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@ -7,6 +7,7 @@ #include "tree-walk.h" #include "diff.h" #include "revision.h" +#include "list-objects.h" #include "builtin.h" /* bits #0-15 in revision.h */ @@ -23,6 +24,7 @@ static const char rev_list_usage[] = " --no-merges\n" " --remove-empty\n" " --all\n" +" --stdin\n" " ordering output:\n" " --topo-order\n" " --date-order\n" @@ -52,6 +54,12 @@ static void show_commit(struct commit *commit) fputs(header_prefix, stdout); if (commit->object.flags & BOUNDARY) putchar('-'); + else if (revs.left_right) { + if (commit->object.flags & SYMMETRIC_LEFT) + putchar('<'); + else + putchar('>'); + } if (revs.abbrev_commit && revs.abbrev) fputs(find_unique_abbrev(commit->object.sha1, revs.abbrev), stdout); @@ -85,7 +93,7 @@ static void show_commit(struct commit *commit) static char pretty_header[16384]; pretty_print_commit(revs.commit_format, commit, ~0, pretty_header, sizeof(pretty_header), - revs.abbrev, NULL, NULL); + revs.abbrev, NULL, NULL, revs.relative_date); printf("%s%c", pretty_header, hdr_termination); } fflush(stdout); @@ -93,110 +101,28 @@ static void show_commit(struct commit *commit) free_commit_list(commit->parents); commit->parents = NULL; } - if (commit->buffer) { - free(commit->buffer); - commit->buffer = NULL; - } -} - -static void process_blob(struct blob *blob, - struct object_array *p, - struct name_path *path, - const char *name) -{ - struct object *obj = &blob->object; - - if (!revs.blob_objects) - return; - if (obj->flags & (UNINTERESTING | SEEN)) - return; - obj->flags |= SEEN; - name = strdup(name); - add_object(obj, p, path, name); + free(commit->buffer); + commit->buffer = NULL; } -static void process_tree(struct tree *tree, - struct object_array *p, - struct name_path *path, - const char *name) +static void show_object(struct object_array_entry *p) { - struct object *obj = &tree->object; - struct tree_desc desc; - struct name_entry entry; - struct name_path me; - - if (!revs.tree_objects) - return; - if (obj->flags & (UNINTERESTING | SEEN)) - return; - if (parse_tree(tree) < 0) - die("bad tree object %s", sha1_to_hex(obj->sha1)); - obj->flags |= SEEN; - name = strdup(name); - add_object(obj, p, path, name); - me.up = path; - me.elem = name; - me.elem_len = strlen(name); - - desc.buf = tree->buffer; - desc.size = tree->size; - - while (tree_entry(&desc, &entry)) { - if (S_ISDIR(entry.mode)) - process_tree(lookup_tree(entry.sha1), p, &me, entry.path); - else - process_blob(lookup_blob(entry.sha1), p, &me, entry.path); + /* An object with name "foo\n0000000..." can be used to + * confuse downstream git-pack-objects very badly. + */ + const char *ep = strchr(p->name, '\n'); + if (ep) { + printf("%s %.*s\n", sha1_to_hex(p->item->sha1), + (int) (ep - p->name), + p->name); } - free(tree->buffer); - tree->buffer = NULL; + else + printf("%s %s\n", sha1_to_hex(p->item->sha1), p->name); } -static void show_commit_list(struct rev_info *revs) +static void show_edge(struct commit *commit) { - int i; - struct commit *commit; - struct object_array objects = { 0, 0, NULL }; - - while ((commit = get_revision(revs)) != NULL) { - process_tree(commit->tree, &objects, NULL, ""); - show_commit(commit); - } - for (i = 0; i < revs->pending.nr; i++) { - struct object_array_entry *pending = revs->pending.objects + i; - struct object *obj = pending->item; - const char *name = pending->name; - if (obj->flags & (UNINTERESTING | SEEN)) - continue; - if (obj->type == OBJ_TAG) { - obj->flags |= SEEN; - add_object_array(obj, name, &objects); - continue; - } - if (obj->type == OBJ_TREE) { - process_tree((struct tree *)obj, &objects, NULL, name); - continue; - } - if (obj->type == OBJ_BLOB) { - process_blob((struct blob *)obj, &objects, NULL, name); - continue; - } - die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); - } - for (i = 0; i < objects.nr; i++) { - struct object_array_entry *p = objects.objects + i; - - /* An object with name "foo\n0000000..." can be used to - * confuse downstream git-pack-objects very badly. - */ - const char *ep = strchr(p->name, '\n'); - if (ep) { - printf("%s %.*s\n", sha1_to_hex(p->item->sha1), - (int) (ep - p->name), - p->name); - } - else - printf("%s %s\n", sha1_to_hex(p->item->sha1), p->name); - } + printf("-%s\n", sha1_to_hex(commit->object.sha1)); } /* @@ -277,32 +203,20 @@ static struct commit_list *find_bisection(struct commit_list *list) return best; } -static void mark_edge_parents_uninteresting(struct commit *commit) -{ - struct commit_list *parents; - - for (parents = commit->parents; parents; parents = parents->next) { - struct commit *parent = parents->item; - if (!(parent->object.flags & UNINTERESTING)) - continue; - mark_tree_uninteresting(parent->tree); - if (revs.edge_hint && !(parent->object.flags & SHOWN)) { - parent->object.flags |= SHOWN; - printf("-%s\n", sha1_to_hex(parent->object.sha1)); - } - } -} - -static void mark_edges_uninteresting(struct commit_list *list) +static void read_revisions_from_stdin(struct rev_info *revs) { - for ( ; list; list = list->next) { - struct commit *commit = list->item; + char line[1000]; - if (commit->object.flags & UNINTERESTING) { - mark_tree_uninteresting(commit->tree); - continue; - } - mark_edge_parents_uninteresting(commit); + while (fgets(line, sizeof(line), stdin) != NULL) { + int len = strlen(line); + if (line[len - 1] == '\n') + line[--len] = 0; + if (!len) + break; + if (line[0] == '-') + die("options not supported in --stdin mode"); + if (handle_revision_arg(line, revs, 0, 1)) + die("bad revision '%s'", line); } } @@ -310,6 +224,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) { struct commit_list *list; int i; + int read_from_stdin = 0; init_revisions(&revs, prefix); revs.abbrev = 0; @@ -331,6 +246,12 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) bisect_list = 1; continue; } + if (!strcmp(arg, "--stdin")) { + if (read_from_stdin++) + die("--stdin given twice?"); + read_revisions_from_stdin(&revs); + continue; + } usage(rev_list_usage); } @@ -354,19 +275,19 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) revs.diff) usage(rev_list_usage); - save_commit_buffer = revs.verbose_header; + save_commit_buffer = revs.verbose_header || revs.grep_filter; track_object_refs = 0; if (bisect_list) revs.limited = 1; prepare_revision_walk(&revs); if (revs.tree_objects) - mark_edges_uninteresting(revs.commits); + mark_edges_uninteresting(revs.commits, &revs, show_edge); if (bisect_list) revs.commits = find_bisection(revs.commits); - show_commit_list(&revs); + traverse_commit_list(&revs, show_commit, show_object); return 0; } diff --git a/builtin-rev-parse.c b/builtin-rev-parse.c index fd3ccc8546..3b716fba13 100644 --- a/builtin-rev-parse.c +++ b/builtin-rev-parse.c @@ -137,7 +137,7 @@ static void show_default(void) } } -static int show_reference(const char *refname, const unsigned char *sha1) +static int show_reference(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { show_rev(NORMAL, sha1, refname); return 0; @@ -299,19 +299,19 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) continue; } if (!strcmp(arg, "--all")) { - for_each_ref(show_reference); + for_each_ref(show_reference, NULL); continue; } if (!strcmp(arg, "--branches")) { - for_each_branch_ref(show_reference); + for_each_branch_ref(show_reference, NULL); continue; } if (!strcmp(arg, "--tags")) { - for_each_tag_ref(show_reference); + for_each_tag_ref(show_reference, NULL); continue; } if (!strcmp(arg, "--remotes")) { - for_each_remote_ref(show_reference); + for_each_remote_ref(show_reference, NULL); continue; } if (!strcmp(arg, "--show-prefix")) { diff --git a/builtin-rm.c b/builtin-rm.c index 593d86744c..d81f289c3c 100644 --- a/builtin-rm.c +++ b/builtin-rm.c @@ -7,9 +7,10 @@ #include "builtin.h" #include "dir.h" #include "cache-tree.h" +#include "tree-walk.h" static const char builtin_rm_usage[] = -"git-rm [-n] [-v] [-f] <filepattern>..."; +"git-rm [-n] [-f] [--cached] <filepattern>..."; static struct { int nr, alloc; @@ -31,8 +32,12 @@ static int remove_file(const char *name) char *slash; ret = unlink(name); + if (ret && errno == ENOENT) + /* The user has removed it from the filesystem by hand */ + ret = errno = 0; + if (!ret && (slash = strrchr(name, '/'))) { - char *n = strdup(name); + char *n = xstrdup(name); do { n[slash - name] = 0; name = n; @@ -41,12 +46,75 @@ static int remove_file(const char *name) return ret; } +static int check_local_mod(unsigned char *head) +{ + /* items in list are already sorted in the cache order, + * so we could do this a lot more efficiently by using + * tree_desc based traversal if we wanted to, but I am + * lazy, and who cares if removal of files is a tad + * slower than the theoretical maximum speed? + */ + int i, no_head; + int errs = 0; + + no_head = is_null_sha1(head); + for (i = 0; i < list.nr; i++) { + struct stat st; + int pos; + struct cache_entry *ce; + const char *name = list.name[i]; + unsigned char sha1[20]; + unsigned mode; + + pos = cache_name_pos(name, strlen(name)); + if (pos < 0) + continue; /* removing unmerged entry */ + ce = active_cache[pos]; + + if (lstat(ce->name, &st) < 0) { + if (errno != ENOENT) + fprintf(stderr, "warning: '%s': %s", + ce->name, strerror(errno)); + /* It already vanished from the working tree */ + continue; + } + else if (S_ISDIR(st.st_mode)) { + /* if a file was removed and it is now a + * directory, that is the same as ENOENT as + * far as git is concerned; we do not track + * directories. + */ + continue; + } + if (ce_match_stat(ce, &st, 0)) + errs = error("'%s' has local modifications " + "(hint: try -f)", ce->name); + if (no_head) + continue; + /* + * It is Ok to remove a newly added path, as long as + * it is cache-clean. + */ + if (get_tree_entry(head, name, sha1, &mode)) + continue; + /* + * Otherwise make sure the version from the HEAD + * matches the index. + */ + if (ce->ce_mode != create_ce_mode(mode) || + hashcmp(ce->sha1, sha1)) + errs = error("'%s' has changes staged in the index " + "(hint: try -f)", name); + } + return errs; +} + static struct lock_file lock_file; int cmd_rm(int argc, const char **argv, const char *prefix) { int i, newfd; - int verbose = 0, show_only = 0, force = 0; + int show_only = 0, force = 0, index_only = 0, recursive = 0; const char **pathspec; char *seen; @@ -62,23 +130,20 @@ int cmd_rm(int argc, const char **argv, const char *prefix) if (*arg != '-') break; - if (!strcmp(arg, "--")) { + else if (!strcmp(arg, "--")) { i++; break; } - if (!strcmp(arg, "-n")) { + else if (!strcmp(arg, "-n")) show_only = 1; - continue; - } - if (!strcmp(arg, "-v")) { - verbose = 1; - continue; - } - if (!strcmp(arg, "-f")) { + else if (!strcmp(arg, "--cached")) + index_only = 1; + else if (!strcmp(arg, "-f")) force = 1; - continue; - } - usage(builtin_rm_usage); + else if (!strcmp(arg, "-r")) + recursive = 1; + else + usage(builtin_rm_usage); } if (argc <= i) usage(builtin_rm_usage); @@ -99,14 +164,36 @@ int cmd_rm(int argc, const char **argv, const char *prefix) if (pathspec) { const char *match; for (i = 0; (match = pathspec[i]) != NULL ; i++) { - if (*match && !seen[i]) - die("pathspec '%s' did not match any files", match); + if (!seen[i]) + die("pathspec '%s' did not match any files", + match); + if (!recursive && seen[i] == MATCHED_RECURSIVELY) + die("not removing '%s' recursively without -r", + *match ? match : "."); } } /* + * If not forced, the file, the index and the HEAD (if exists) + * must match; but the file can already been removed, since + * this sequence is a natural "novice" way: + * + * rm F; git fm F + * + * Further, if HEAD commit exists, "diff-index --cached" must + * report no changes unless forced. + */ + if (!force) { + unsigned char sha1[20]; + if (get_sha1("HEAD", sha1)) + hashclr(sha1); + if (check_local_mod(sha1)) + exit(1); + } + + /* * First remove the names from the index: we won't commit - * the index unless all of them succeed + * the index unless all of them succeed. */ for (i = 0; i < list.nr; i++) { const char *path = list.name[i]; @@ -121,14 +208,14 @@ int cmd_rm(int argc, const char **argv, const char *prefix) return 0; /* - * Then, if we used "-f", remove the filenames from the - * workspace. If we fail to remove the first one, we + * Then, unless we used "--cached", remove the filenames from + * the workspace. If we fail to remove the first one, we * abort the "git rm" (but once we've successfully removed * any file at all, we'll go ahead and commit to it all: * by then we've already committed ourselves and can't fail * in the middle) */ - if (force) { + if (!index_only) { int removed = 0; for (i = 0; i < list.nr; i++) { const char *path = list.name[i]; diff --git a/builtin-runstatus.c b/builtin-runstatus.c new file mode 100644 index 0000000000..4b489b1214 --- /dev/null +++ b/builtin-runstatus.c @@ -0,0 +1,36 @@ +#include "cache.h" +#include "wt-status.h" + +extern int wt_status_use_color; + +static const char runstatus_usage[] = +"git-runstatus [--color|--nocolor] [--amend] [--verbose] [--untracked]"; + +int cmd_runstatus(int argc, const char **argv, const char *prefix) +{ + struct wt_status s; + int i; + + git_config(git_status_config); + wt_status_prepare(&s); + + for (i = 1; i < argc; i++) { + if (!strcmp(argv[i], "--color")) + wt_status_use_color = 1; + else if (!strcmp(argv[i], "--nocolor")) + wt_status_use_color = 0; + else if (!strcmp(argv[i], "--amend")) { + s.amend = 1; + s.reference = "HEAD^1"; + } + else if (!strcmp(argv[i], "--verbose")) + s.verbose = 1; + else if (!strcmp(argv[i], "--untracked")) + s.untracked = 1; + else + usage(runstatus_usage); + } + + wt_status_print(&s); + return s.commitable ? 0 : 1; +} diff --git a/builtin-shortlog.c b/builtin-shortlog.c new file mode 100644 index 0000000000..edb40429ec --- /dev/null +++ b/builtin-shortlog.c @@ -0,0 +1,341 @@ +#include "builtin.h" +#include "cache.h" +#include "commit.h" +#include "diff.h" +#include "path-list.h" +#include "revision.h" + +static const char shortlog_usage[] = +"git-shortlog [-n] [-s] [<commit-id>... ]"; + +static char *common_repo_prefix; + +static int compare_by_number(const void *a1, const void *a2) +{ + const struct path_list_item *i1 = a1, *i2 = a2; + const struct path_list *l1 = i1->util, *l2 = i2->util; + + if (l1->nr < l2->nr) + return 1; + else if (l1->nr == l2->nr) + return 0; + else + return -1; +} + +static struct path_list mailmap = {NULL, 0, 0, 0}; + +static int read_mailmap(const char *filename) +{ + char buffer[1024]; + FILE *f = fopen(filename, "r"); + + if (f == NULL) + return 1; + while (fgets(buffer, sizeof(buffer), f) != NULL) { + char *end_of_name, *left_bracket, *right_bracket; + char *name, *email; + int i; + if (buffer[0] == '#') { + static const char abbrev[] = "# repo-abbrev:"; + int abblen = sizeof(abbrev) - 1; + int len = strlen(buffer); + + if (len && buffer[len - 1] == '\n') + buffer[--len] = 0; + if (!strncmp(buffer, abbrev, abblen)) { + char *cp; + + if (common_repo_prefix) + free(common_repo_prefix); + common_repo_prefix = xmalloc(len); + + for (cp = buffer + abblen; isspace(*cp); cp++) + ; /* nothing */ + strcpy(common_repo_prefix, cp); + } + continue; + } + if ((left_bracket = strchr(buffer, '<')) == NULL) + continue; + if ((right_bracket = strchr(left_bracket + 1, '>')) == NULL) + continue; + if (right_bracket == left_bracket + 1) + continue; + for (end_of_name = left_bracket; end_of_name != buffer + && isspace(end_of_name[-1]); end_of_name--) + /* keep on looking */ + if (end_of_name == buffer) + continue; + name = xmalloc(end_of_name - buffer + 1); + strlcpy(name, buffer, end_of_name - buffer + 1); + email = xmalloc(right_bracket - left_bracket); + for (i = 0; i < right_bracket - left_bracket - 1; i++) + email[i] = tolower(left_bracket[i + 1]); + email[right_bracket - left_bracket - 1] = '\0'; + path_list_insert(email, &mailmap)->util = name; + } + fclose(f); + return 0; +} + +static int map_email(char *email, char *name, int maxlen) +{ + char *p; + struct path_list_item *item; + + /* autocomplete common developers */ + p = strchr(email, '>'); + if (!p) + return 0; + + *p = '\0'; + /* downcase the email address */ + for (p = email; *p; p++) + *p = tolower(*p); + item = path_list_lookup(email, &mailmap); + if (item != NULL) { + const char *realname = (const char *)item->util; + strncpy(name, realname, maxlen); + return 1; + } + return 0; +} + +static void insert_author_oneline(struct path_list *list, + const char *author, int authorlen, + const char *oneline, int onelinelen) +{ + const char *dot3 = common_repo_prefix; + char *buffer, *p; + struct path_list_item *item; + struct path_list *onelines; + + while (authorlen > 0 && isspace(author[authorlen - 1])) + authorlen--; + + buffer = xmalloc(authorlen + 1); + memcpy(buffer, author, authorlen); + buffer[authorlen] = '\0'; + + item = path_list_insert(buffer, list); + if (item->util == NULL) + item->util = xcalloc(1, sizeof(struct path_list)); + else + free(buffer); + + if (!strncmp(oneline, "[PATCH", 6)) { + char *eob = strchr(oneline, ']'); + + if (eob) { + while (isspace(eob[1]) && eob[1] != '\n') + eob++; + if (eob - oneline < onelinelen) { + onelinelen -= eob - oneline; + oneline = eob; + } + } + } + + while (onelinelen > 0 && isspace(oneline[0])) { + oneline++; + onelinelen--; + } + + while (onelinelen > 0 && isspace(oneline[onelinelen - 1])) + onelinelen--; + + buffer = xmalloc(onelinelen + 1); + memcpy(buffer, oneline, onelinelen); + buffer[onelinelen] = '\0'; + + if (dot3) { + int dot3len = strlen(dot3); + if (dot3len > 5) { + while ((p = strstr(buffer, dot3)) != NULL) { + int taillen = strlen(p) - dot3len; + memcpy(p, "/.../", 5); + memmove(p + 5, p + dot3len, taillen + 1); + } + } + } + + onelines = item->util; + if (onelines->nr >= onelines->alloc) { + onelines->alloc = alloc_nr(onelines->nr); + onelines->items = xrealloc(onelines->items, + onelines->alloc + * sizeof(struct path_list_item)); + } + + onelines->items[onelines->nr].util = NULL; + onelines->items[onelines->nr++].path = buffer; +} + +static void read_from_stdin(struct path_list *list) +{ + char buffer[1024]; + + while (fgets(buffer, sizeof(buffer), stdin) != NULL) { + char *bob; + if ((buffer[0] == 'A' || buffer[0] == 'a') && + !strncmp(buffer + 1, "uthor: ", 7) && + (bob = strchr(buffer + 7, '<')) != NULL) { + char buffer2[1024], offset = 0; + + if (map_email(bob + 1, buffer, sizeof(buffer))) + bob = buffer + strlen(buffer); + else { + offset = 8; + while (buffer + offset < bob && + isspace(bob[-1])) + bob--; + } + + while (fgets(buffer2, sizeof(buffer2), stdin) && + buffer2[0] != '\n') + ; /* chomp input */ + if (fgets(buffer2, sizeof(buffer2), stdin)) { + int l2 = strlen(buffer2); + int i; + for (i = 0; i < l2; i++) + if (!isspace(buffer2[i])) + break; + insert_author_oneline(list, + buffer + offset, + bob - buffer - offset, + buffer2 + i, l2 - i); + } + } + } +} + +static void get_from_rev(struct rev_info *rev, struct path_list *list) +{ + char scratch[1024]; + struct commit *commit; + + prepare_revision_walk(rev); + while ((commit = get_revision(rev)) != NULL) { + char *author = NULL, *oneline, *buffer; + int authorlen = authorlen, onelinelen; + + /* get author and oneline */ + for (buffer = commit->buffer; buffer && *buffer != '\0' && + *buffer != '\n'; ) { + char *eol = strchr(buffer, '\n'); + + if (eol == NULL) + eol = buffer + strlen(buffer); + else + eol++; + + if (!strncmp(buffer, "author ", 7)) { + char *bracket = strchr(buffer, '<'); + + if (bracket == NULL || bracket > eol) + die("Invalid commit buffer: %s", + sha1_to_hex(commit->object.sha1)); + + if (map_email(bracket + 1, scratch, + sizeof(scratch))) { + author = scratch; + authorlen = strlen(scratch); + } else { + if (bracket[-1] == ' ') + bracket--; + + author = buffer + 7; + authorlen = bracket - buffer - 7; + } + } + buffer = eol; + } + + if (author == NULL) + die ("Missing author: %s", + sha1_to_hex(commit->object.sha1)); + + if (buffer == NULL || *buffer == '\0') { + oneline = "<none>"; + onelinelen = sizeof(oneline) + 1; + } else { + char *eol; + + oneline = buffer + 1; + eol = strchr(oneline, '\n'); + if (eol == NULL) + onelinelen = strlen(oneline); + else + onelinelen = eol - oneline; + } + + insert_author_oneline(list, + author, authorlen, oneline, onelinelen); + } + +} + +int cmd_shortlog(int argc, const char **argv, const char *prefix) +{ + struct rev_info rev; + struct path_list list = { NULL, 0, 0, 1 }; + int i, j, sort_by_number = 0, summary = 0; + + /* since -n is a shadowed rev argument, parse our args first */ + while (argc > 1) { + if (!strcmp(argv[1], "-n") || !strcmp(argv[1], "--numbered")) + sort_by_number = 1; + else if (!strcmp(argv[1], "-s") || + !strcmp(argv[1], "--summary")) + summary = 1; + else if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) + usage(shortlog_usage); + else + break; + argv++; + argc--; + } + init_revisions(&rev, prefix); + argc = setup_revisions(argc, argv, &rev, NULL); + if (argc > 1) + die ("unrecognized argument: %s", argv[1]); + + if (!access(".mailmap", R_OK)) + read_mailmap(".mailmap"); + + if (rev.pending.nr == 0) + read_from_stdin(&list); + else + get_from_rev(&rev, &list); + + if (sort_by_number) + qsort(list.items, list.nr, sizeof(struct path_list_item), + compare_by_number); + + for (i = 0; i < list.nr; i++) { + struct path_list *onelines = list.items[i].util; + + if (summary) { + printf("%s: %d\n", list.items[i].path, onelines->nr); + } else { + printf("%s (%d):\n", list.items[i].path, onelines->nr); + for (j = onelines->nr - 1; j >= 0; j--) + printf(" %s\n", onelines->items[j].path); + printf("\n"); + } + + onelines->strdup_paths = 1; + path_list_clear(onelines, 1); + free(onelines); + list.items[i].util = NULL; + } + + list.strdup_paths = 1; + path_list_clear(&list, 1); + mailmap.strdup_paths = 1; + path_list_clear(&mailmap, 1); + + return 0; +} + diff --git a/builtin-show-branch.c b/builtin-show-branch.c index 18786f88e3..c67f2fa2fe 100644 --- a/builtin-show-branch.c +++ b/builtin-show-branch.c @@ -1,12 +1,10 @@ -#include <stdlib.h> -#include <fnmatch.h> #include "cache.h" #include "commit.h" #include "refs.h" #include "builtin.h" static const char show_branch_usage[] = -"git-show-branch [--sparse] [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...]"; +"git-show-branch [--sparse] [--current] [--all] [--remotes] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...] | --reflog[=n] <branch>"; static int default_num; static int default_alloc; @@ -17,6 +15,8 @@ static const char **default_arg; #define REV_SHIFT 2 #define MAX_REVS (FLAG_BITS - REV_SHIFT) /* should not exceed bits_per_int - REV_SHIFT */ +#define DEFAULT_REFLOG 4 + static struct commit *interesting(struct commit_list *list) { while (list) { @@ -163,7 +163,7 @@ static void name_commits(struct commit_list *list, en += sprintf(en, "^"); else en += sprintf(en, "^%d", nth); - name_commit(p, strdup(newname), 0); + name_commit(p, xstrdup(newname), 0); i++; name_first_parent_chain(p); } @@ -261,7 +261,7 @@ static void show_one_commit(struct commit *commit, int no_name) struct commit_name *name = commit->util; if (commit->object.parsed) pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - pretty, sizeof(pretty), 0, NULL, NULL); + pretty, sizeof(pretty), 0, NULL, NULL, 0); else strcpy(pretty, "(unavailable)"); if (!strncmp(pretty, "[PATCH] ", 8)) @@ -346,7 +346,7 @@ static void sort_ref_range(int bottom, int top) compare_ref_name); } -static int append_ref(const char *refname, const unsigned char *sha1) +static int append_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { struct commit *commit = lookup_commit_reference_gently(sha1, 1); int i; @@ -364,12 +364,12 @@ static int append_ref(const char *refname, const unsigned char *sha1) refname, MAX_REVS); return 0; } - ref_name[ref_name_cnt++] = strdup(refname); + ref_name[ref_name_cnt++] = xstrdup(refname); ref_name[ref_name_cnt] = NULL; return 0; } -static int append_head_ref(const char *refname, const unsigned char *sha1) +static int append_head_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { unsigned char tmp[20]; int ofs = 11; @@ -380,14 +380,28 @@ static int append_head_ref(const char *refname, const unsigned char *sha1) */ if (get_sha1(refname + ofs, tmp) || hashcmp(tmp, sha1)) ofs = 5; - return append_ref(refname + ofs, sha1); + return append_ref(refname + ofs, sha1, flag, cb_data); +} + +static int append_remote_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) +{ + unsigned char tmp[20]; + int ofs = 13; + if (strncmp(refname, "refs/remotes/", ofs)) + return 0; + /* If both heads/foo and tags/foo exists, get_sha1 would + * get confused. + */ + if (get_sha1(refname + ofs, tmp) || hashcmp(tmp, sha1)) + ofs = 5; + return append_ref(refname + ofs, sha1, flag, cb_data); } -static int append_tag_ref(const char *refname, const unsigned char *sha1) +static int append_tag_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { if (strncmp(refname, "refs/tags/", 10)) return 0; - return append_ref(refname + 5, sha1); + return append_ref(refname + 5, sha1, flag, cb_data); } static const char *match_ref_pattern = NULL; @@ -401,7 +415,7 @@ static int count_slash(const char *s) return cnt; } -static int append_matching_ref(const char *refname, const unsigned char *sha1) +static int append_matching_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { /* we want to allow pattern hold/<asterisk> to show all * branches under refs/heads/hold/, and v0.99.9? to show @@ -417,41 +431,39 @@ static int append_matching_ref(const char *refname, const unsigned char *sha1) if (fnmatch(match_ref_pattern, tail, 0)) return 0; if (!strncmp("refs/heads/", refname, 11)) - return append_head_ref(refname, sha1); + return append_head_ref(refname, sha1, flag, cb_data); if (!strncmp("refs/tags/", refname, 10)) - return append_tag_ref(refname, sha1); - return append_ref(refname, sha1); + return append_tag_ref(refname, sha1, flag, cb_data); + return append_ref(refname, sha1, flag, cb_data); } -static void snarf_refs(int head, int tag) +static void snarf_refs(int head, int remotes) { if (head) { int orig_cnt = ref_name_cnt; - for_each_ref(append_head_ref); + for_each_ref(append_head_ref, NULL); sort_ref_range(orig_cnt, ref_name_cnt); } - if (tag) { + if (remotes) { int orig_cnt = ref_name_cnt; - for_each_ref(append_tag_ref); + for_each_ref(append_remote_ref, NULL); sort_ref_range(orig_cnt, ref_name_cnt); } } -static int rev_is_head(char *head_path, int headlen, char *name, +static int rev_is_head(char *head, int headlen, char *name, unsigned char *head_sha1, unsigned char *sha1) { - int namelen; - if ((!head_path[0]) || + if ((!head[0]) || (head_sha1 && sha1 && hashcmp(head_sha1, sha1))) return 0; - namelen = strlen(name); - if ((headlen < namelen) || - memcmp(head_path + headlen - namelen, name, namelen)) - return 0; - if (headlen == namelen || - head_path[headlen - namelen - 1] == '/') - return 1; - return 0; + if (!strncmp(head, "refs/heads/", 11)) + head += 11; + if (!strncmp(name, "refs/heads/", 11)) + name += 11; + else if (!strncmp(name, "heads/", 6)) + name += 6; + return !strcmp(head, name); } static int show_merge_base(struct commit_list *seen, int num_rev) @@ -495,7 +507,7 @@ static void append_one_rev(const char *av) { unsigned char revkey[20]; if (!get_sha1(av, revkey)) { - append_ref(av, revkey); + append_ref(av, revkey, 0, NULL); return; } if (strchr(av, '*') || strchr(av, '?') || strchr(av, '[')) { @@ -503,7 +515,7 @@ static void append_one_rev(const char *av) int saved_matches = ref_name_cnt; match_ref_pattern = av; match_ref_slash = count_slash(av); - for_each_ref(append_matching_ref); + for_each_ref(append_matching_ref, NULL); if (saved_matches == ref_name_cnt && ref_name_cnt < MAX_REVS) error("no matching refs with %s", av); @@ -521,7 +533,7 @@ static int git_show_branch_config(const char *var, const char *value) default_alloc = default_alloc * 3 / 2 + 20; default_arg = xrealloc(default_arg, sizeof *default_arg * default_alloc); } - default_arg[default_num++] = strdup(value); + default_arg[default_num++] = xstrdup(value); default_arg[default_num] = NULL; return 0; } @@ -556,12 +568,12 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) struct commit_list *list = NULL, *seen = NULL; unsigned int rev_mask[MAX_REVS]; int num_rev, i, extra = 0; - int all_heads = 0, all_tags = 0; + int all_heads = 0, all_remotes = 0; int all_mask, all_revs; int lifo = 1; - char head_path[128]; - const char *head_path_p; - int head_path_len; + char head[128]; + const char *head_p; + int head_len; unsigned char head_sha1[20]; int merge_base = 0; int independent = 0; @@ -572,6 +584,7 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) int head_at = -1; int topics = 0; int dense = 1; + int reflog = 0; git_config(git_show_branch_config); @@ -587,12 +600,10 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) ac--; av++; break; } - else if (!strcmp(arg, "--all")) - all_heads = all_tags = 1; - else if (!strcmp(arg, "--heads")) - all_heads = 1; - else if (!strcmp(arg, "--tags")) - all_tags = 1; + else if (!strcmp(arg, "--all") || !strcmp(arg, "-a")) + all_heads = all_remotes = 1; + else if (!strcmp(arg, "--remotes") || !strcmp(arg, "-r")) + all_remotes = 1; else if (!strcmp(arg, "--more")) extra = 1; else if (!strcmp(arg, "--list")) @@ -617,6 +628,15 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) dense = 0; else if (!strcmp(arg, "--date-order")) lifo = 0; + else if (!strcmp(arg, "--reflog")) { + reflog = DEFAULT_REFLOG; + } + else if (!strncmp(arg, "--reflog=", 9)) { + char *end; + reflog = strtoul(arg + 9, &end, 10); + if (*end != '\0') + die("unrecognized reflog count '%s'", arg + 9); + } else usage(show_branch_usage); ac--; av++; @@ -624,45 +644,58 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) ac--; av++; /* Only one of these is allowed */ - if (1 < independent + merge_base + (extra != 0)) + if (1 < independent + merge_base + (extra != 0) + (!!reflog)) usage(show_branch_usage); /* If nothing is specified, show all branches by default */ - if (ac + all_heads + all_tags == 0) + if (ac + all_heads + all_remotes == 0) all_heads = 1; - if (all_heads + all_tags) - snarf_refs(all_heads, all_tags); - while (0 < ac) { - append_one_rev(*av); - ac--; av++; + if (all_heads + all_remotes) + snarf_refs(all_heads, all_remotes); + if (reflog) { + int reflen; + if (!ac) + die("--reflog option needs one branch name"); + reflen = strlen(*av); + for (i = 0; i < reflog; i++) { + char *name = xmalloc(reflen + 20); + sprintf(name, "%s@{%d}", *av, i); + append_one_rev(name); + } + } + else { + while (0 < ac) { + append_one_rev(*av); + ac--; av++; + } } - head_path_p = resolve_ref(git_path("HEAD"), head_sha1, 1); - if (head_path_p) { - head_path_len = strlen(head_path_p); - memcpy(head_path, head_path_p, head_path_len + 1); + head_p = resolve_ref("HEAD", head_sha1, 1, NULL); + if (head_p) { + head_len = strlen(head_p); + memcpy(head, head_p, head_len + 1); } else { - head_path_len = 0; - head_path[0] = 0; + head_len = 0; + head[0] = 0; } - if (with_current_branch && head_path_p) { + if (with_current_branch && head_p) { int has_head = 0; for (i = 0; !has_head && i < ref_name_cnt; i++) { /* We are only interested in adding the branch * HEAD points at. */ - if (rev_is_head(head_path, - head_path_len, + if (rev_is_head(head, + head_len, ref_name[i], head_sha1, NULL)) has_head++; } if (!has_head) { - int pfxlen = strlen(git_path("refs/heads/")); - append_one_rev(head_path + pfxlen); + int pfxlen = strlen("refs/heads/"); + append_one_rev(head + pfxlen); } } @@ -713,8 +746,8 @@ int cmd_show_branch(int ac, const char **av, const char *prefix) if (1 < num_rev || extra < 0) { for (i = 0; i < num_rev; i++) { int j; - int is_head = rev_is_head(head_path, - head_path_len, + int is_head = rev_is_head(head, + head_len, ref_name[i], head_sha1, rev[i]->object.sha1); diff --git a/builtin-show-ref.c b/builtin-show-ref.c new file mode 100644 index 0000000000..853f13f6ae --- /dev/null +++ b/builtin-show-ref.c @@ -0,0 +1,250 @@ +#include "cache.h" +#include "refs.h" +#include "object.h" +#include "tag.h" +#include "path-list.h" + +static const char show_ref_usage[] = "git show-ref [-q|--quiet] [--verify] [-h|--head] [-d|--dereference] [-s|--hash[=<length>]] [--abbrev[=<length>]] [--tags] [--heads] [--] [pattern*] < ref-list"; + +static int deref_tags = 0, show_head = 0, tags_only = 0, heads_only = 0, + found_match = 0, verify = 0, quiet = 0, hash_only = 0, abbrev = 0; +static const char **pattern; + +static void show_one(const char *refname, const unsigned char *sha1) +{ + const char *hex = find_unique_abbrev(sha1, abbrev); + if (hash_only) + printf("%s\n", hex); + else + printf("%s %s\n", hex, refname); +} + +static int show_ref(const char *refname, const unsigned char *sha1, int flag, void *cbdata) +{ + struct object *obj; + const char *hex; + unsigned char peeled[20]; + + if (tags_only || heads_only) { + int match; + + match = heads_only && !strncmp(refname, "refs/heads/", 11); + match |= tags_only && !strncmp(refname, "refs/tags/", 10); + if (!match) + return 0; + } + if (pattern) { + int reflen = strlen(refname); + const char **p = pattern, *m; + while ((m = *p++) != NULL) { + int len = strlen(m); + if (len > reflen) + continue; + if (memcmp(m, refname + reflen - len, len)) + continue; + if (len == reflen) + goto match; + /* "--verify" requires an exact match */ + if (verify) + continue; + if (refname[reflen - len - 1] == '/') + goto match; + } + return 0; + } + +match: + found_match++; + + /* This changes the semantics slightly that even under quiet we + * detect and return error if the repository is corrupt and + * ref points at a nonexistent object. + */ + if (!has_sha1_file(sha1)) + die("git-show-ref: bad ref %s (%s)", refname, + sha1_to_hex(sha1)); + + if (quiet) + return 0; + + show_one(refname, sha1); + + if (!deref_tags) + return 0; + + if ((flag & REF_ISPACKED) && !peel_ref(refname, peeled)) { + if (!is_null_sha1(peeled)) { + hex = find_unique_abbrev(peeled, abbrev); + printf("%s %s^{}\n", hex, refname); + } + } + else { + obj = parse_object(sha1); + if (!obj) + die("git-show-ref: bad ref %s (%s)", refname, + sha1_to_hex(sha1)); + if (obj->type == OBJ_TAG) { + obj = deref_tag(obj, refname, 0); + hex = find_unique_abbrev(obj->sha1, abbrev); + printf("%s %s^{}\n", hex, refname); + } + } + return 0; +} + +static int add_existing(const char *refname, const unsigned char *sha1, int flag, void *cbdata) +{ + struct path_list *list = (struct path_list *)cbdata; + path_list_insert(refname, list); + return 0; +} + +/* + * read "^(?:<anything>\s)?<refname>(?:\^\{\})?$" from the standard input, + * and + * (1) strip "^{}" at the end of line if any; + * (2) ignore if match is provided and does not head-match refname; + * (3) warn if refname is not a well-formed refname and skip; + * (4) ignore if refname is a ref that exists in the local repository; + * (5) otherwise output the line. + */ +static int exclude_existing(const char *match) +{ + static struct path_list existing_refs = { NULL, 0, 0, 0 }; + char buf[1024]; + int matchlen = match ? strlen(match) : 0; + + for_each_ref(add_existing, &existing_refs); + while (fgets(buf, sizeof(buf), stdin)) { + char *ref; + int len = strlen(buf); + + if (len > 0 && buf[len - 1] == '\n') + buf[--len] = '\0'; + if (3 <= len && !strcmp(buf + len - 3, "^{}")) { + len -= 3; + buf[len] = '\0'; + } + for (ref = buf + len; buf < ref; ref--) + if (isspace(ref[-1])) + break; + if (match) { + int reflen = buf + len - ref; + if (reflen < matchlen) + continue; + if (strncmp(ref, match, matchlen)) + continue; + } + if (check_ref_format(ref)) { + fprintf(stderr, "warning: ref '%s' ignored\n", ref); + continue; + } + if (!path_list_has_path(&existing_refs, ref)) { + printf("%s\n", buf); + } + } + return 0; +} + +int cmd_show_ref(int argc, const char **argv, const char *prefix) +{ + int i; + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (*arg != '-') { + pattern = argv + i; + break; + } + if (!strcmp(arg, "--")) { + pattern = argv + i + 1; + if (!*pattern) + pattern = NULL; + break; + } + if (!strcmp(arg, "-q") || !strcmp(arg, "--quiet")) { + quiet = 1; + continue; + } + if (!strcmp(arg, "-h") || !strcmp(arg, "--head")) { + show_head = 1; + continue; + } + if (!strcmp(arg, "-d") || !strcmp(arg, "--dereference")) { + deref_tags = 1; + continue; + } + if (!strcmp(arg, "-s") || !strcmp(arg, "--hash")) { + hash_only = 1; + continue; + } + if (!strncmp(arg, "--hash=", 7) || + (!strncmp(arg, "--abbrev", 8) && + (arg[8] == '=' || arg[8] == '\0'))) { + if (arg[2] != 'h' && !arg[8]) + /* --abbrev only */ + abbrev = DEFAULT_ABBREV; + else { + /* --hash= or --abbrev= */ + char *end; + if (arg[2] == 'h') { + hash_only = 1; + arg += 7; + } + else + arg += 9; + abbrev = strtoul(arg, &end, 10); + if (*end || abbrev > 40) + usage(show_ref_usage); + if (abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + } + continue; + } + if (!strcmp(arg, "--verify")) { + verify = 1; + continue; + } + if (!strcmp(arg, "--tags")) { + tags_only = 1; + continue; + } + if (!strcmp(arg, "--heads")) { + heads_only = 1; + continue; + } + if (!strcmp(arg, "--exclude-existing")) + return exclude_existing(NULL); + if (!strncmp(arg, "--exclude-existing=", 19)) + return exclude_existing(arg + 19); + usage(show_ref_usage); + } + + if (verify) { + unsigned char sha1[20]; + + while (*pattern) { + if (!strncmp(*pattern, "refs/", 5) && + resolve_ref(*pattern, sha1, 1, NULL)) { + if (!quiet) + show_one(*pattern, sha1); + } + else if (!quiet) + die("'%s' - not a valid ref", *pattern); + else + return 1; + pattern++; + } + return 0; + } + + if (show_head) + head_ref(show_ref, NULL); + for_each_ref(show_ref, NULL); + if (!found_match) { + if (verify && !quiet) + die("No match"); + return 1; + } + return 0; +} diff --git a/builtin-stripspace.c b/builtin-stripspace.c index 09cc9108cd..f0d4d9e2d1 100644 --- a/builtin-stripspace.c +++ b/builtin-stripspace.c @@ -1,6 +1,3 @@ -#include <stdio.h> -#include <string.h> -#include <ctype.h> #include "builtin.h" /* diff --git a/builtin-symbolic-ref.c b/builtin-symbolic-ref.c index b4ec6f28ed..d8be0527f4 100644 --- a/builtin-symbolic-ref.c +++ b/builtin-symbolic-ref.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "refs.h" static const char git_symbolic_ref_usage[] = "git-symbolic-ref name [ref]"; @@ -7,15 +8,14 @@ static const char git_symbolic_ref_usage[] = static void check_symref(const char *HEAD) { unsigned char sha1[20]; - const char *git_HEAD = strdup(git_path("%s", HEAD)); - const char *git_refs_heads_master = resolve_ref(git_HEAD, sha1, 0); - if (git_refs_heads_master) { - /* we want to strip the .git/ part */ - int pfxlen = strlen(git_HEAD) - strlen(HEAD); - puts(git_refs_heads_master + pfxlen); - } - else + int flag; + const char *refs_heads_master = resolve_ref(HEAD, sha1, 0, &flag); + + if (!refs_heads_master) die("No such ref: %s", HEAD); + else if (!(flag & REF_ISSYMREF)) + die("ref %s is not a symbolic ref", HEAD); + puts(refs_heads_master); } int cmd_symbolic_ref(int argc, const char **argv, const char *prefix) @@ -26,7 +26,7 @@ int cmd_symbolic_ref(int argc, const char **argv, const char *prefix) check_symref(argv[1]); break; case 3: - create_symref(strdup(git_path("%s", argv[1])), argv[2]); + create_symref(argv[1], argv[2]); break; default: usage(git_symbolic_ref_usage); diff --git a/builtin-tar-tree.c b/builtin-tar-tree.c index e0bcb0a1e1..8055ddab9b 100644 --- a/builtin-tar-tree.c +++ b/builtin-tar-tree.c @@ -1,399 +1,70 @@ /* * Copyright (c) 2005, 2006 Rene Scharfe */ -#include <time.h> #include "cache.h" -#include "tree-walk.h" #include "commit.h" -#include "strbuf.h" #include "tar.h" #include "builtin.h" -#include "pkt-line.h" - -#define RECORDSIZE (512) -#define BLOCKSIZE (RECORDSIZE * 20) +#include "quote.h" static const char tar_tree_usage[] = -"git-tar-tree [--remote=<repo>] <tree-ish> [basedir]"; - -static char block[BLOCKSIZE]; -static unsigned long offset; - -static time_t archive_time; -static int tar_umask; - -/* writes out the whole block, but only if it is full */ -static void write_if_needed(void) -{ - if (offset == BLOCKSIZE) { - write_or_die(1, block, BLOCKSIZE); - offset = 0; - } -} - -/* - * queues up writes, so that all our write(2) calls write exactly one - * full block; pads writes to RECORDSIZE - */ -static void write_blocked(const void *data, unsigned long size) -{ - const char *buf = data; - unsigned long tail; - - if (offset) { - unsigned long chunk = BLOCKSIZE - offset; - if (size < chunk) - chunk = size; - memcpy(block + offset, buf, chunk); - size -= chunk; - offset += chunk; - buf += chunk; - write_if_needed(); - } - while (size >= BLOCKSIZE) { - write_or_die(1, buf, BLOCKSIZE); - size -= BLOCKSIZE; - buf += BLOCKSIZE; - } - if (size) { - memcpy(block + offset, buf, size); - offset += size; - } - tail = offset % RECORDSIZE; - if (tail) { - memset(block + offset, 0, RECORDSIZE - tail); - offset += RECORDSIZE - tail; - } - write_if_needed(); -} - -/* - * The end of tar archives is marked by 2*512 nul bytes and after that - * follows the rest of the block (if any). - */ -static void write_trailer(void) -{ - int tail = BLOCKSIZE - offset; - memset(block + offset, 0, tail); - write_or_die(1, block, BLOCKSIZE); - if (tail < 2 * RECORDSIZE) { - memset(block, 0, offset); - write_or_die(1, block, BLOCKSIZE); - } -} - -static void strbuf_append_string(struct strbuf *sb, const char *s) -{ - int slen = strlen(s); - int total = sb->len + slen; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - memcpy(sb->buf + sb->len, s, slen); - sb->len = total; -} - -/* - * pax extended header records have the format "%u %s=%s\n". %u contains - * the size of the whole string (including the %u), the first %s is the - * keyword, the second one is the value. This function constructs such a - * string and appends it to a struct strbuf. - */ -static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, - const char *value, unsigned int valuelen) -{ - char *p; - int len, total, tmp; - - /* "%u %s=%s\n" */ - len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; - for (tmp = len; tmp > 9; tmp /= 10) - len++; - - total = sb->len + len; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - - p = sb->buf; - p += sprintf(p, "%u %s=", len, keyword); - memcpy(p, value, valuelen); - p += valuelen; - *p = '\n'; - sb->len = total; -} - -static unsigned int ustar_header_chksum(const struct ustar_header *header) -{ - char *p = (char *)header; - unsigned int chksum = 0; - while (p < header->chksum) - chksum += *p++; - chksum += sizeof(header->chksum) * ' '; - p += sizeof(header->chksum); - while (p < (char *)header + sizeof(struct ustar_header)) - chksum += *p++; - return chksum; -} - -static int get_path_prefix(const struct strbuf *path, int maxlen) -{ - int i = path->len; - if (i > maxlen) - i = maxlen; - do { - i--; - } while (i > 0 && path->buf[i] != '/'); - return i; -} - -static void write_entry(const unsigned char *sha1, struct strbuf *path, - unsigned int mode, void *buffer, unsigned long size) -{ - struct ustar_header header; - struct strbuf ext_header; - - memset(&header, 0, sizeof(header)); - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - - if (!sha1) { - *header.typeflag = TYPEFLAG_GLOBAL_HEADER; - mode = 0100666; - strcpy(header.name, "pax_global_header"); - } else if (!path) { - *header.typeflag = TYPEFLAG_EXT_HEADER; - mode = 0100666; - sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); - } else { - if (S_ISDIR(mode)) { - *header.typeflag = TYPEFLAG_DIR; - mode = (mode | 0777) & ~tar_umask; - } else if (S_ISLNK(mode)) { - *header.typeflag = TYPEFLAG_LNK; - mode |= 0777; - } else if (S_ISREG(mode)) { - *header.typeflag = TYPEFLAG_REG; - mode = (mode | ((mode & 0100) ? 0777 : 0666)) & ~tar_umask; - } else { - error("unsupported file mode: 0%o (SHA1: %s)", - mode, sha1_to_hex(sha1)); - return; - } - if (path->len > sizeof(header.name)) { - int plen = get_path_prefix(path, sizeof(header.prefix)); - int rest = path->len - plen - 1; - if (plen > 0 && rest <= sizeof(header.name)) { - memcpy(header.prefix, path->buf, plen); - memcpy(header.name, path->buf + plen + 1, rest); - } else { - sprintf(header.name, "%s.data", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "path", - path->buf, path->len); - } - } else - memcpy(header.name, path->buf, path->len); - } - - if (S_ISLNK(mode) && buffer) { - if (size > sizeof(header.linkname)) { - sprintf(header.linkname, "see %s.paxheader", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "linkpath", - buffer, size); - } else - memcpy(header.linkname, buffer, size); - } - - sprintf(header.mode, "%07o", mode & 07777); - sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); - sprintf(header.mtime, "%011lo", archive_time); - - /* XXX: should we provide more meaningful info here? */ - sprintf(header.uid, "%07o", 0); - sprintf(header.gid, "%07o", 0); - strlcpy(header.uname, "git", sizeof(header.uname)); - strlcpy(header.gname, "git", sizeof(header.gname)); - sprintf(header.devmajor, "%07o", 0); - sprintf(header.devminor, "%07o", 0); +"git-tar-tree [--remote=<repo>] <tree-ish> [basedir]\n" +"*** Note that this command is now deprecated; use git-archive instead."; - memcpy(header.magic, "ustar", 6); - memcpy(header.version, "00", 2); - - sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); - - if (ext_header.len > 0) { - write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); - } - write_blocked(&header, sizeof(header)); - if (S_ISREG(mode) && buffer && size > 0) - write_blocked(buffer, size); -} - -static void write_global_extended_header(const unsigned char *sha1) -{ - struct strbuf ext_header; - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); - write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); -} - -static void traverse_tree(struct tree_desc *tree, struct strbuf *path) -{ - int pathlen = path->len; - struct name_entry entry; - - while (tree_entry(tree, &entry)) { - void *eltbuf; - char elttype[20]; - unsigned long eltsize; - - eltbuf = read_sha1_file(entry.sha1, elttype, &eltsize); - if (!eltbuf) - die("cannot read %s", sha1_to_hex(entry.sha1)); - - path->len = pathlen; - strbuf_append_string(path, entry.path); - if (S_ISDIR(entry.mode)) - strbuf_append_string(path, "/"); - - write_entry(entry.sha1, path, entry.mode, eltbuf, eltsize); - - if (S_ISDIR(entry.mode)) { - struct tree_desc subtree; - subtree.buf = eltbuf; - subtree.size = eltsize; - traverse_tree(&subtree, path); - } - free(eltbuf); - } -} - -int git_tar_config(const char *var, const char *value) +int cmd_tar_tree(int argc, const char **argv, const char *prefix) { - if (!strcmp(var, "tar.umask")) { - if (!strcmp(value, "user")) { - tar_umask = umask(0); - umask(tar_umask); - } else { - tar_umask = git_config_int(var, value); - } - return 0; + /* + * git-tar-tree is now a wrapper around git-archive --format=tar + * + * $0 --remote=<repo> arg... ==> + * git-archive --format=tar --remote=<repo> arg... + * $0 tree-ish ==> + * git-archive --format=tar tree-ish + * $0 tree-ish basedir ==> + * git-archive --format-tar --prefix=basedir tree-ish + */ + int i; + const char **nargv = xcalloc(sizeof(*nargv), argc + 2); + char *basedir_arg; + int nargc = 0; + + nargv[nargc++] = "git-archive"; + nargv[nargc++] = "--format=tar"; + + if (2 <= argc && !strncmp("--remote=", argv[1], 9)) { + nargv[nargc++] = argv[1]; + argv++; + argc--; } - return git_default_config(var, value); -} - -static int generate_tar(int argc, const char **argv, const char *prefix) -{ - unsigned char sha1[20], tree_sha1[20]; - struct commit *commit; - struct tree_desc tree; - struct strbuf current_path; - void *buffer; - - current_path.buf = xmalloc(PATH_MAX); - current_path.alloc = PATH_MAX; - current_path.len = current_path.eof = 0; - - git_config(git_tar_config); - switch (argc) { - case 3: - strbuf_append_string(¤t_path, argv[2]); - strbuf_append_string(¤t_path, "/"); - /* FALLTHROUGH */ - case 2: - if (get_sha1(argv[1], sha1)) - die("Not a valid object name %s", argv[1]); - break; default: usage(tar_tree_usage); + break; + case 3: + /* base-path */ + basedir_arg = xmalloc(strlen(argv[2]) + 11); + sprintf(basedir_arg, "--prefix=%s/", argv[2]); + nargv[nargc++] = basedir_arg; + /* fallthru */ + case 2: + /* tree-ish */ + nargv[nargc++] = argv[1]; } - - commit = lookup_commit_reference_gently(sha1, 1); - if (commit) { - write_global_extended_header(commit->object.sha1); - archive_time = commit->date; - } else - archive_time = time(NULL); - - tree.buf = buffer = read_object_with_reference(sha1, tree_type, - &tree.size, tree_sha1); - if (!tree.buf) - die("not a reference to a tag, commit or tree object: %s", - sha1_to_hex(sha1)); - - if (current_path.len > 0) - write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); - traverse_tree(&tree, ¤t_path); - write_trailer(); - free(buffer); - free(current_path.buf); - return 0; -} - -static const char *exec = "git-upload-tar"; - -static int remote_tar(int argc, const char **argv) -{ - int fd[2], ret, len; - pid_t pid; - char buf[1024]; - char *url; - - if (argc < 3 || 4 < argc) - usage(tar_tree_usage); - - /* --remote=<repo> */ - url = strdup(argv[1]+9); - pid = git_connect(fd, url, exec); - if (pid < 0) - return 1; - - packet_write(fd[1], "want %s\n", argv[2]); - if (argv[3]) - packet_write(fd[1], "base %s\n", argv[3]); - packet_flush(fd[1]); - - len = packet_read_line(fd[0], buf, sizeof(buf)); - if (!len) - die("git-tar-tree: expected ACK/NAK, got EOF"); - if (buf[len-1] == '\n') - buf[--len] = 0; - if (strcmp(buf, "ACK")) { - if (5 < len && !strncmp(buf, "NACK ", 5)) - die("git-tar-tree: NACK %s", buf + 5); - die("git-tar-tree: protocol error"); + nargv[nargc] = NULL; + + fprintf(stderr, + "*** git-tar-tree is now deprecated.\n" + "*** Running git-archive instead.\n***"); + for (i = 0; i < nargc; i++) { + fputc(' ', stderr); + sq_quote_print(stderr, nargv[i]); } - /* expect a flush */ - len = packet_read_line(fd[0], buf, sizeof(buf)); - if (len) - die("git-tar-tree: expected a flush"); - - /* Now, start reading from fd[0] and spit it out to stdout */ - ret = copy_fd(fd[0], 1); - close(fd[0]); - - ret |= finish_connect(pid); - return !!ret; -} - -int cmd_tar_tree(int argc, const char **argv, const char *prefix) -{ - if (argc < 2) - usage(tar_tree_usage); - if (!strncmp("--remote=", argv[1], 9)) - return remote_tar(argc, argv); - return generate_tar(argc, argv, prefix); + fputc('\n', stderr); + return cmd_archive(nargc, nargv, prefix); } /* ustar header + extended global header content */ +#define RECORDSIZE (512) #define HEADERSIZE (2 * RECORDSIZE) int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix) @@ -403,7 +74,7 @@ int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix) char *content = buffer + RECORDSIZE; ssize_t n; - n = xread(0, buffer, HEADERSIZE); + n = read_in_full(0, buffer, HEADERSIZE); if (n < HEADERSIZE) die("git-get-tar-commit-id: read error"); if (header->typeflag[0] != 'g') @@ -411,7 +82,7 @@ int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix) if (memcmp(content, "52 comment=", 11)) return 1; - n = xwrite(1, content + 11, 41); + n = write_in_full(1, content + 11, 41); if (n < 41) die("git-get-tar-commit-id: write error"); diff --git a/builtin-unpack-objects.c b/builtin-unpack-objects.c index ca0ebc2585..d351e02649 100644 --- a/builtin-unpack-objects.c +++ b/builtin-unpack-objects.c @@ -8,31 +8,27 @@ #include "tag.h" #include "tree.h" -#include <sys/time.h> - -static int dry_run, quiet; -static const char unpack_usage[] = "git-unpack-objects [-n] [-q] < pack-file"; +static int dry_run, quiet, recover, has_errors; +static const char unpack_usage[] = "git-unpack-objects [-n] [-q] [-r] < pack-file"; /* We always read in 4kB chunks. */ static unsigned char buffer[4096]; -static unsigned long offset, len, eof; +static unsigned long offset, len, consumed_bytes; static SHA_CTX ctx; /* * Make sure at least "min" bytes are available in the buffer, and * return the pointer to the buffer. */ -static void * fill(int min) +static void *fill(int min) { if (min <= len) return buffer + offset; - if (eof) - die("unable to fill input"); if (min > sizeof(buffer)) die("cannot fill %d bytes", min); if (offset) { SHA1_Update(&ctx, buffer, offset); - memcpy(buffer, buffer + offset, len); + memmove(buffer, buffer + offset, len); offset = 0; } do { @@ -53,6 +49,7 @@ static void use(int bytes) die("used more bytes than were available"); len -= bytes; offset += bytes; + consumed_bytes += bytes; } static void *get_data(unsigned long size) @@ -73,8 +70,15 @@ static void *get_data(unsigned long size) use(len - stream.avail_in); if (stream.total_out == size && ret == Z_STREAM_END) break; - if (ret != Z_OK) - die("inflate returned %d\n", ret); + if (ret != Z_OK) { + error("inflate returned %d\n", ret); + free(buf); + buf = NULL; + if (!recover) + exit(1); + has_errors = 1; + break; + } stream.next_in = fill(1); stream.avail_in = len; } @@ -84,37 +88,51 @@ static void *get_data(unsigned long size) struct delta_info { unsigned char base_sha1[20]; + unsigned long base_offset; unsigned long size; void *delta; + unsigned nr; struct delta_info *next; }; static struct delta_info *delta_list; -static void add_delta_to_list(unsigned char *base_sha1, void *delta, unsigned long size) +static void add_delta_to_list(unsigned nr, unsigned const char *base_sha1, + unsigned long base_offset, + void *delta, unsigned long size) { struct delta_info *info = xmalloc(sizeof(*info)); hashcpy(info->base_sha1, base_sha1); + info->base_offset = base_offset; info->size = size; info->delta = delta; + info->nr = nr; info->next = delta_list; delta_list = info; } -static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size); +struct obj_info { + unsigned long offset; + unsigned char sha1[20]; +}; + +static struct obj_info *obj_list; + +static void added_object(unsigned nr, const char *type, void *data, + unsigned long size); -static void write_object(void *buf, unsigned long size, const char *type) +static void write_object(unsigned nr, void *buf, unsigned long size, + const char *type) { - unsigned char sha1[20]; - if (write_sha1_file(buf, size, type, sha1) < 0) + if (write_sha1_file(buf, size, type, obj_list[nr].sha1) < 0) die("failed to write object"); - added_object(sha1, type, buf, size); + added_object(nr, type, buf, size); } -static int resolve_delta(const char *type, - void *base, unsigned long base_size, - void *delta, unsigned long delta_size) +static void resolve_delta(unsigned nr, const char *type, + void *base, unsigned long base_size, + void *delta, unsigned long delta_size) { void *result; unsigned long result_size; @@ -125,21 +143,23 @@ static int resolve_delta(const char *type, if (!result) die("failed to apply delta"); free(delta); - write_object(result, result_size, type); + write_object(nr, result, result_size, type); free(result); - return 0; } -static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size) +static void added_object(unsigned nr, const char *type, void *data, + unsigned long size) { struct delta_info **p = &delta_list; struct delta_info *info; while ((info = *p) != NULL) { - if (!hashcmp(info->base_sha1, sha1)) { + if (!hashcmp(info->base_sha1, obj_list[nr].sha1) || + info->base_offset == obj_list[nr].offset) { *p = info->next; p = &delta_list; - resolve_delta(type, data, size, info->delta, info->size); + resolve_delta(info->nr, type, data, size, + info->delta, info->size); free(info); continue; } @@ -147,7 +167,8 @@ static void added_object(unsigned char *sha1, const char *type, void *data, unsi } } -static int unpack_non_delta_entry(enum object_type kind, unsigned long size) +static void unpack_non_delta_entry(enum object_type kind, unsigned long size, + unsigned nr) { void *buf = get_data(size); const char *type; @@ -159,39 +180,92 @@ static int unpack_non_delta_entry(enum object_type kind, unsigned long size) case OBJ_TAG: type = tag_type; break; default: die("bad type %d", kind); } - if (!dry_run) - write_object(buf, size, type); + if (!dry_run && buf) + write_object(nr, buf, size, type); free(buf); - return 0; } -static int unpack_delta_entry(unsigned long delta_size) +static void unpack_delta_entry(enum object_type kind, unsigned long delta_size, + unsigned nr) { void *delta_data, *base; unsigned long base_size; char type[20]; unsigned char base_sha1[20]; - int result; - hashcpy(base_sha1, fill(20)); - use(20); + if (kind == OBJ_REF_DELTA) { + hashcpy(base_sha1, fill(20)); + use(20); + delta_data = get_data(delta_size); + if (dry_run || !delta_data) { + free(delta_data); + return; + } + if (!has_sha1_file(base_sha1)) { + hashcpy(obj_list[nr].sha1, null_sha1); + add_delta_to_list(nr, base_sha1, 0, delta_data, delta_size); + return; + } + } else { + unsigned base_found = 0; + unsigned char *pack, c; + unsigned long base_offset; + unsigned lo, mid, hi; - delta_data = get_data(delta_size); - if (dry_run) { - free(delta_data); - return 0; - } + pack = fill(1); + c = *pack; + use(1); + base_offset = c & 127; + while (c & 128) { + base_offset += 1; + if (!base_offset || base_offset & ~(~0UL >> 7)) + die("offset value overflow for delta base object"); + pack = fill(1); + c = *pack; + use(1); + base_offset = (base_offset << 7) + (c & 127); + } + base_offset = obj_list[nr].offset - base_offset; - if (!has_sha1_file(base_sha1)) { - add_delta_to_list(base_sha1, delta_data, delta_size); - return 0; + delta_data = get_data(delta_size); + if (dry_run || !delta_data) { + free(delta_data); + return; + } + lo = 0; + hi = nr; + while (lo < hi) { + mid = (lo + hi)/2; + if (base_offset < obj_list[mid].offset) { + hi = mid; + } else if (base_offset > obj_list[mid].offset) { + lo = mid + 1; + } else { + hashcpy(base_sha1, obj_list[mid].sha1); + base_found = !is_null_sha1(base_sha1); + break; + } + } + if (!base_found) { + /* The delta base object is itself a delta that + has not been resolved yet. */ + hashcpy(obj_list[nr].sha1, null_sha1); + add_delta_to_list(nr, null_sha1, base_offset, delta_data, delta_size); + return; + } } + base = read_sha1_file(base_sha1, type, &base_size); - if (!base) - die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1)); - result = resolve_delta(type, base, base_size, delta_data, delta_size); + if (!base) { + error("failed to read delta-pack base object %s", + sha1_to_hex(base_sha1)); + if (!recover) + exit(1); + has_errors = 1; + return; + } + resolve_delta(nr, type, base, base_size, delta_data, delta_size); free(base); - return result; } static void unpack_one(unsigned nr, unsigned total) @@ -201,6 +275,8 @@ static void unpack_one(unsigned nr, unsigned total) unsigned long size; enum object_type type; + obj_list[nr].offset = consumed_bytes; + pack = fill(1); c = *pack; use(1); @@ -209,7 +285,7 @@ static void unpack_one(unsigned nr, unsigned total) shift = 4; while (c & 0x80) { pack = fill(1); - c = *pack++; + c = *pack; use(1); size += (c & 0x7f) << shift; shift += 7; @@ -218,13 +294,14 @@ static void unpack_one(unsigned nr, unsigned total) static unsigned long last_sec; static unsigned last_percent; struct timeval now; - unsigned percentage = (nr * 100) / total; + unsigned percentage = ((nr+1) * 100) / total; gettimeofday(&now, NULL); if (percentage != last_percent || now.tv_sec != last_sec) { last_sec = now.tv_sec; last_percent = percentage; - fprintf(stderr, "%4u%% (%u/%u) done\r", percentage, nr, total); + fprintf(stderr, "%4u%% (%u/%u) done\r", + percentage, (nr+1), total); } } switch (type) { @@ -232,13 +309,18 @@ static void unpack_one(unsigned nr, unsigned total) case OBJ_TREE: case OBJ_BLOB: case OBJ_TAG: - unpack_non_delta_entry(type, size); + unpack_non_delta_entry(type, size, nr); return; - case OBJ_DELTA: - unpack_delta_entry(size); + case OBJ_REF_DELTA: + case OBJ_OFS_DELTA: + unpack_delta_entry(type, size, nr); return; default: - die("bad object type %d", type); + error("bad object type %d", type); + has_errors = 1; + if (recover) + return; + exit(1); } } @@ -254,9 +336,10 @@ static void unpack_all(void) die("unknown pack file version %d", ntohl(hdr->hdr_version)); fprintf(stderr, "Unpacking %d objects\n", nr_objects); + obj_list = xmalloc(nr_objects * sizeof(*obj_list)); use(sizeof(struct pack_header)); for (i = 0; i < nr_objects; i++) - unpack_one(i+1, nr_objects); + unpack_one(i, nr_objects); if (delta_list) die("unresolved deltas left after unpacking"); } @@ -282,6 +365,25 @@ int cmd_unpack_objects(int argc, const char **argv, const char *prefix) quiet = 1; continue; } + if (!strcmp(arg, "-r")) { + recover = 1; + continue; + } + if (!strncmp(arg, "--pack_header=", 14)) { + struct pack_header *hdr; + char *c; + + hdr = (struct pack_header *)buffer; + hdr->hdr_signature = htonl(PACK_SIGNATURE); + hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10)); + if (*c != ',') + die("bad %s", arg); + hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10)); + if (*c) + die("bad %s", arg); + len = sizeof(*hdr); + continue; + } usage(unpack_usage); } @@ -308,5 +410,5 @@ int cmd_unpack_objects(int argc, const char **argv, const char *prefix) /* All done */ if (!quiet) fprintf(stderr, "\n"); - return 0; + return has_errors; } diff --git a/builtin-update-index.c b/builtin-update-index.c index 8675126471..182331d341 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -112,11 +112,13 @@ static int add_file_to_cache(const char *path) ce->ce_mode = create_ce_mode(st.st_mode); if (!trust_executable_bit) { /* If there is an existing entry, pick the mode bits - * from it. + * from it, otherwise assume unexecutable. */ int pos = cache_name_pos(path, namelen); if (0 <= pos) ce->ce_mode = active_cache[pos]->ce_mode; + else if (S_ISREG(st.st_mode)) + ce->ce_mode = create_ce_mode(S_IFREG | 0666); } if (index_path(ce->sha1, path, &st, !info_only)) @@ -306,7 +308,7 @@ static void read_index_info(int line_termination) } static const char update_index_usage[] = -"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again] [--ignore-missing] [-z] [--verbose] [--] <file>..."; +"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again | -g] [--ignore-missing] [-z] [--verbose] [--] <file>..."; static unsigned char head_sha1[20]; static unsigned char merge_head_sha1[20]; @@ -404,9 +406,9 @@ static int unresolve_one(const char *path) static void read_head_pointers(void) { - if (read_ref(git_path("HEAD"), head_sha1)) + if (read_ref("HEAD", head_sha1)) die("No HEAD -- no initial commit yet?\n"); - if (read_ref(git_path("MERGE_HEAD"), merge_head_sha1)) { + if (read_ref("MERGE_HEAD", merge_head_sha1)) { fprintf(stderr, "Not in the middle of a merge.\n"); exit(0); } @@ -443,7 +445,7 @@ static int do_reupdate(int ac, const char **av, int has_head = 1; const char **pathspec = get_pathspec(prefix, av + 1); - if (read_ref(git_path("HEAD"), head_sha1)) + if (read_ref("HEAD", head_sha1)) /* If there is no HEAD, that means it is an initial * commit. Update everything in the index. */ @@ -595,7 +597,7 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) active_cache_changed = 0; goto finish; } - if (!strcmp(path, "--again")) { + if (!strcmp(path, "--again") || !strcmp(path, "-g")) { has_errors = do_reupdate(argc - i, argv + i, prefix, prefix_length); if (has_errors) diff --git a/builtin-update-ref.c b/builtin-update-ref.c index 90a3da53ad..b34e5987dd 100644 --- a/builtin-update-ref.c +++ b/builtin-update-ref.c @@ -3,15 +3,16 @@ #include "builtin.h" static const char git_update_ref_usage[] = -"git-update-ref <refname> <value> [<oldval>] [-m <reason>]"; +"git-update-ref [-m <reason>] (-d <refname> <value> | <refname> <value> [<oldval>])"; int cmd_update_ref(int argc, const char **argv, const char *prefix) { const char *refname=NULL, *value=NULL, *oldval=NULL, *msg=NULL; struct ref_lock *lock; unsigned char sha1[20], oldsha1[20]; - int i; + int i, delete; + delete = 0; setup_ident(); git_config(git_default_config); @@ -26,6 +27,10 @@ int cmd_update_ref(int argc, const char **argv, const char *prefix) die("Refusing to perform update with \\n in message."); continue; } + if (!strcmp("-d", argv[i])) { + delete = 1; + continue; + } if (!refname) { refname = argv[i]; continue; @@ -44,11 +49,18 @@ int cmd_update_ref(int argc, const char **argv, const char *prefix) if (get_sha1(value, sha1)) die("%s: not a valid SHA1", value); + + if (delete) { + if (oldval) + usage(git_update_ref_usage); + return delete_ref(refname, sha1); + } + hashclr(oldsha1); - if (oldval && get_sha1(oldval, oldsha1)) + if (oldval && *oldval && get_sha1(oldval, oldsha1)) die("%s: not a valid old SHA1", oldval); - lock = lock_any_ref_for_update(refname, oldval ? oldsha1 : NULL, 0); + lock = lock_any_ref_for_update(refname, oldval ? oldsha1 : NULL); if (!lock) return 1; if (write_ref_sha1(lock, sha1, msg) < 0) diff --git a/builtin-upload-archive.c b/builtin-upload-archive.c new file mode 100644 index 0000000000..48ae09e9b5 --- /dev/null +++ b/builtin-upload-archive.c @@ -0,0 +1,172 @@ +/* + * Copyright (c) 2006 Franck Bui-Huu + */ +#include "cache.h" +#include "builtin.h" +#include "archive.h" +#include "pkt-line.h" +#include "sideband.h" + +static const char upload_archive_usage[] = + "git-upload-archive <repo>"; + +static const char deadchild[] = +"git-upload-archive: archiver died with error"; + +static const char lostchild[] = +"git-upload-archive: archiver process was lost"; + + +static int run_upload_archive(int argc, const char **argv, const char *prefix) +{ + struct archiver ar; + const char *sent_argv[MAX_ARGS]; + const char *arg_cmd = "argument "; + char *p, buf[4096]; + int treeish_idx; + int sent_argc; + int len; + + if (argc != 2) + usage(upload_archive_usage); + + if (strlen(argv[1]) > sizeof(buf)) + die("insanely long repository name"); + + strcpy(buf, argv[1]); /* enter-repo smudges its argument */ + + if (!enter_repo(buf, 0)) + die("not a git archive"); + + /* put received options in sent_argv[] */ + sent_argc = 1; + sent_argv[0] = "git-upload-archive"; + for (p = buf;;) { + /* This will die if not enough free space in buf */ + len = packet_read_line(0, p, (buf + sizeof buf) - p); + if (len == 0) + break; /* got a flush */ + if (sent_argc > MAX_ARGS - 2) + die("Too many options (>29)"); + + if (p[len-1] == '\n') { + p[--len] = 0; + } + if (len < strlen(arg_cmd) || + strncmp(arg_cmd, p, strlen(arg_cmd))) + die("'argument' token or flush expected"); + + len -= strlen(arg_cmd); + memmove(p, p + strlen(arg_cmd), len); + sent_argv[sent_argc++] = p; + p += len; + *p++ = 0; + } + sent_argv[sent_argc] = NULL; + + /* parse all options sent by the client */ + treeish_idx = parse_archive_args(sent_argc, sent_argv, &ar); + + parse_treeish_arg(sent_argv + treeish_idx, &ar.args, prefix); + parse_pathspec_arg(sent_argv + treeish_idx + 1, &ar.args); + + return ar.write_archive(&ar.args); +} + +static void error_clnt(const char *fmt, ...) +{ + char buf[1024]; + va_list params; + int len; + + va_start(params, fmt); + len = vsprintf(buf, fmt, params); + va_end(params); + send_sideband(1, 3, buf, len, LARGE_PACKET_MAX); + die("sent error to the client: %s", buf); +} + +static void process_input(int child_fd, int band) +{ + char buf[16384]; + ssize_t sz = read(child_fd, buf, sizeof(buf)); + if (sz < 0) { + if (errno != EAGAIN && errno != EINTR) + error_clnt("read error: %s\n", strerror(errno)); + return; + } + send_sideband(1, band, buf, sz, LARGE_PACKET_MAX); +} + +int cmd_upload_archive(int argc, const char **argv, const char *prefix) +{ + pid_t writer; + int fd1[2], fd2[2]; + /* + * Set up sideband subprocess. + * + * We (parent) monitor and read from child, sending its fd#1 and fd#2 + * multiplexed out to our fd#1. If the child dies, we tell the other + * end over channel #3. + */ + if (pipe(fd1) < 0 || pipe(fd2) < 0) { + int err = errno; + packet_write(1, "NACK pipe failed on the remote side\n"); + die("upload-archive: %s", strerror(err)); + } + writer = fork(); + if (writer < 0) { + int err = errno; + packet_write(1, "NACK fork failed on the remote side\n"); + die("upload-archive: %s", strerror(err)); + } + if (!writer) { + /* child - connect fd#1 and fd#2 to the pipe */ + dup2(fd1[1], 1); + dup2(fd2[1], 2); + close(fd1[1]); close(fd2[1]); + close(fd1[0]); close(fd2[0]); /* we do not read from pipe */ + + exit(run_upload_archive(argc, argv, prefix)); + } + + /* parent - read from child, multiplex and send out to fd#1 */ + close(fd1[1]); close(fd2[1]); /* we do not write to pipe */ + packet_write(1, "ACK\n"); + packet_flush(1); + + while (1) { + struct pollfd pfd[2]; + int status; + + pfd[0].fd = fd1[0]; + pfd[0].events = POLLIN; + pfd[1].fd = fd2[0]; + pfd[1].events = POLLIN; + if (poll(pfd, 2, -1) < 0) { + if (errno != EINTR) { + error("poll failed resuming: %s", + strerror(errno)); + sleep(1); + } + continue; + } + if (pfd[0].revents & POLLIN) + /* Data stream ready */ + process_input(pfd[0].fd, 1); + if (pfd[1].revents & POLLIN) + /* Status stream ready */ + process_input(pfd[1].fd, 2); + /* Always finish to read data when available */ + if ((pfd[0].revents | pfd[1].revents) & POLLIN) + continue; + + if (waitpid(writer, &status, 0) < 0) + error_clnt("%s", lostchild); + else if (!WIFEXITED(status) || WEXITSTATUS(status) > 0) + error_clnt("%s", deadchild); + packet_flush(1); + break; + } + return 0; +} diff --git a/builtin-upload-tar.c b/builtin-upload-tar.c deleted file mode 100644 index 7b401bbb77..0000000000 --- a/builtin-upload-tar.c +++ /dev/null @@ -1,74 +0,0 @@ -/* - * Copyright (c) 2006 Junio C Hamano - */ -#include "cache.h" -#include "pkt-line.h" -#include "exec_cmd.h" -#include "builtin.h" - -static const char upload_tar_usage[] = "git-upload-tar <repo>"; - -static int nak(const char *reason) -{ - packet_write(1, "NACK %s\n", reason); - packet_flush(1); - return 1; -} - -int cmd_upload_tar(int argc, const char **argv, const char *prefix) -{ - int len; - const char *dir = argv[1]; - char buf[8192]; - unsigned char sha1[20]; - char *base = NULL; - char hex[41]; - int ac; - const char *av[4]; - - if (argc != 2) - usage(upload_tar_usage); - if (strlen(dir) < sizeof(buf)-1) - strcpy(buf, dir); /* enter-repo smudges its argument */ - else - packet_write(1, "NACK insanely long repository name %s\n", dir); - if (!enter_repo(buf, 0)) { - packet_write(1, "NACK not a git archive %s\n", dir); - packet_flush(1); - return 1; - } - - len = packet_read_line(0, buf, sizeof(buf)); - if (len < 5 || strncmp("want ", buf, 5)) - return nak("expected want"); - if (buf[len-1] == '\n') - buf[--len] = 0; - if (get_sha1(buf + 5, sha1)) - return nak("expected sha1"); - strcpy(hex, sha1_to_hex(sha1)); - - len = packet_read_line(0, buf, sizeof(buf)); - if (len) { - if (len < 5 || strncmp("base ", buf, 5)) - return nak("expected (optional) base"); - if (buf[len-1] == '\n') - buf[--len] = 0; - base = strdup(buf + 5); - len = packet_read_line(0, buf, sizeof(buf)); - } - if (len) - return nak("expected flush"); - - packet_write(1, "ACK\n"); - packet_flush(1); - - ac = 0; - av[ac++] = "tar-tree"; - av[ac++] = hex; - if (base) - av[ac++] = base; - av[ac++] = NULL; - execv_git_cmd(av); - /* should it return that is an error */ - return 1; -} diff --git a/builtin-verify-pack.c b/builtin-verify-pack.c index 7d39d9bcd1..4e31c273f4 100644 --- a/builtin-verify-pack.c +++ b/builtin-verify-pack.c @@ -55,6 +55,7 @@ int cmd_verify_pack(int argc, const char **argv, const char *prefix) int no_more_options = 0; int nothing_done = 1; + git_config(git_default_config); while (1 < argc) { if (!no_more_options && argv[1][0] == '-') { if (!strcmp("-v", argv[1])) @@ -1,8 +1,7 @@ #ifndef BUILTIN_H #define BUILTIN_H -#include <stdio.h> -#include <limits.h> +#include "git-compat-util.h" extern const char git_version_string[]; extern const char git_usage_string[]; @@ -12,20 +11,28 @@ extern int mailinfo(FILE *in, FILE *out, int ks, const char *encoding, const cha extern int split_mbox(const char **mbox, const char *dir, int allow_bare, int nr_prec, int skip); extern void stripspace(FILE *in, FILE *out); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); +extern void prune_packed_objects(int); extern int cmd_add(int argc, const char **argv, const char *prefix); +extern int cmd_annotate(int argc, const char **argv, const char *prefix); extern int cmd_apply(int argc, const char **argv, const char *prefix); +extern int cmd_archive(int argc, const char **argv, const char *prefix); +extern int cmd_blame(int argc, const char **argv, const char *prefix); +extern int cmd_branch(int argc, const char **argv, const char *prefix); extern int cmd_cat_file(int argc, const char **argv, const char *prefix); extern int cmd_checkout_index(int argc, const char **argv, const char *prefix); extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix); +extern int cmd_cherry(int argc, const char **argv, const char *prefix); extern int cmd_commit_tree(int argc, const char **argv, const char *prefix); extern int cmd_count_objects(int argc, const char **argv, const char *prefix); +extern int cmd_describe(int argc, const char **argv, const char *prefix); extern int cmd_diff_files(int argc, const char **argv, const char *prefix); extern int cmd_diff_index(int argc, const char **argv, const char *prefix); extern int cmd_diff(int argc, const char **argv, const char *prefix); extern int cmd_diff_stages(int argc, const char **argv, const char *prefix); extern int cmd_diff_tree(int argc, const char **argv, const char *prefix); extern int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix); +extern int cmd_for_each_ref(int argc, const char **argv, const char *prefix); extern int cmd_format_patch(int argc, const char **argv, const char *prefix); extern int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix); extern int cmd_grep(int argc, const char **argv, const char *prefix); @@ -36,29 +43,38 @@ extern int cmd_ls_files(int argc, const char **argv, const char *prefix); extern int cmd_ls_tree(int argc, const char **argv, const char *prefix); extern int cmd_mailinfo(int argc, const char **argv, const char *prefix); extern int cmd_mailsplit(int argc, const char **argv, const char *prefix); +extern int cmd_merge_file(int argc, const char **argv, const char *prefix); extern int cmd_mv(int argc, const char **argv, const char *prefix); extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); +extern int cmd_pickaxe(int argc, const char **argv, const char *prefix); extern int cmd_prune(int argc, const char **argv, const char *prefix); extern int cmd_prune_packed(int argc, const char **argv, const char *prefix); extern int cmd_push(int argc, const char **argv, const char *prefix); extern int cmd_read_tree(int argc, const char **argv, const char *prefix); +extern int cmd_reflog(int argc, const char **argv, const char *prefix); extern int cmd_repo_config(int argc, const char **argv, const char *prefix); +extern int cmd_rerere(int argc, const char **argv, const char *prefix); extern int cmd_rev_list(int argc, const char **argv, const char *prefix); extern int cmd_rev_parse(int argc, const char **argv, const char *prefix); extern int cmd_rm(int argc, const char **argv, const char *prefix); -extern int cmd_show_branch(int argc, const char **argv, const char *prefix); +extern int cmd_runstatus(int argc, const char **argv, const char *prefix); +extern int cmd_shortlog(int argc, const char **argv, const char *prefix); extern int cmd_show(int argc, const char **argv, const char *prefix); +extern int cmd_show_branch(int argc, const char **argv, const char *prefix); extern int cmd_stripspace(int argc, const char **argv, const char *prefix); extern int cmd_symbolic_ref(int argc, const char **argv, const char *prefix); extern int cmd_tar_tree(int argc, const char **argv, const char *prefix); extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); extern int cmd_update_index(int argc, const char **argv, const char *prefix); extern int cmd_update_ref(int argc, const char **argv, const char *prefix); +extern int cmd_upload_archive(int argc, const char **argv, const char *prefix); extern int cmd_upload_tar(int argc, const char **argv, const char *prefix); extern int cmd_version(int argc, const char **argv, const char *prefix); extern int cmd_whatchanged(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int cmd_verify_pack(int argc, const char **argv, const char *prefix); +extern int cmd_show_ref(int argc, const char **argv, const char *prefix); +extern int cmd_pack_refs(int argc, const char **argv, const char *prefix); #endif diff --git a/cache-tree.c b/cache-tree.c index 323c68a670..9b73c8669a 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -2,7 +2,9 @@ #include "tree.h" #include "cache-tree.h" +#ifndef DEBUG #define DEBUG 0 +#endif struct cache_tree *cache_tree(void) { @@ -280,6 +282,8 @@ static int update_one(struct cache_tree *it, baselen + sublen + 1, missing_ok, dryrun); + if (subcnt < 0) + return subcnt; i += subcnt - 1; sub->used = 1; } @@ -344,12 +348,8 @@ static int update_one(struct cache_tree *it, #endif } - if (dryrun) { - unsigned char hdr[200]; - int hdrlen; - write_sha1_file_prepare(buffer, offset, tree_type, it->sha1, - hdr, &hdrlen); - } + if (dryrun) + hash_sha1_file(buffer, offset, tree_type, it->sha1); else write_sha1_file(buffer, offset, tree_type, it->sha1); free(buffer); @@ -122,8 +122,14 @@ extern int cache_errno; #define DB_ENVIRONMENT "GIT_OBJECT_DIRECTORY" #define INDEX_ENVIRONMENT "GIT_INDEX_FILE" #define GRAFT_ENVIRONMENT "GIT_GRAFT_FILE" - -extern char *get_git_dir(void); +#define TEMPLATE_DIR_ENVIRONMENT "GIT_TEMPLATE_DIR" +#define CONFIG_ENVIRONMENT "GIT_CONFIG" +#define CONFIG_LOCAL_ENVIRONMENT "GIT_CONFIG_LOCAL" +#define EXEC_PATH_ENVIRONMENT "GIT_EXEC_PATH" + +extern int is_bare_repository_cfg; +extern int is_bare_repository(void); +extern const char *get_git_dir(void); extern char *get_object_directory(void); extern char *get_refs_directory(void); extern char *get_index_file(void); @@ -145,6 +151,7 @@ extern void verify_non_filename(const char *prefix, const char *name); extern int read_cache(void); extern int read_cache_from(const char *path); extern int write_cache(int newfd, struct cache_entry **cache, int entries); +extern int discard_cache(void); extern int verify_path(const char *path); extern int cache_name_pos(const char *name, int namelen); #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ @@ -173,11 +180,13 @@ extern int refresh_cache(unsigned int flags); struct lock_file { struct lock_file *next; + char on_list; char filename[PATH_MAX]; }; extern int hold_lock_file_for_update(struct lock_file *, const char *path, int); extern int commit_lock_file(struct lock_file *); extern void rollback_lock_file(struct lock_file *); +extern int delete_ref(const char *, unsigned char *sha1); /* Environment bits from configuration mechanism */ extern int use_legacy_headers; @@ -189,6 +198,8 @@ extern int warn_ambiguous_refs; extern int shared_repository; extern const char *apply_default_whitespace; extern int zlib_compression_level; +extern size_t packed_git_window_size; +extern size_t packed_git_limit; #define GIT_REPO_VERSION 0 extern int repository_format_version; @@ -243,22 +254,17 @@ char *enter_repo(char *path, int strict); extern int sha1_object_info(const unsigned char *, char *, unsigned long *); extern void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size); extern void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size); +extern int hash_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *sha1); extern int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *return_sha1); -extern char *write_sha1_file_prepare(void *buf, - unsigned long len, - const char *type, - unsigned char *sha1, - unsigned char *hdr, - int *hdrlen); extern int check_sha1_signature(const unsigned char *sha1, void *buf, unsigned long size, const char *type); extern int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, size_t bufsize, size_t *bufposn); extern int write_sha1_to_fd(int fd, const unsigned char *sha1); -extern int move_temp_to_file(const char *tmpfile, char *filename); +extern int move_temp_to_file(const char *tmpfile, const char *filename); -extern int has_sha1_pack(const unsigned char *sha1); +extern int has_sha1_pack(const unsigned char *sha1, const char **ignore); extern int has_sha1_file(const unsigned char *sha1); extern void *map_sha1_file(const unsigned char *sha1, unsigned long *); extern int legacy_loose_object(unsigned char *); @@ -266,6 +272,24 @@ extern int legacy_loose_object(unsigned char *); extern int has_pack_file(const unsigned char *sha1); extern int has_pack_index(const unsigned char *sha1); +enum object_type { + OBJ_NONE = 0, + OBJ_COMMIT = 1, + OBJ_TREE = 2, + OBJ_BLOB = 3, + OBJ_TAG = 4, + /* 5 for future expansion */ + OBJ_OFS_DELTA = 6, + OBJ_REF_DELTA = 7, + OBJ_BAD, +}; + +extern signed char hexval_table[256]; +static inline unsigned int hexval(unsigned int c) +{ + return hexval_table[c]; +} + /* Convert to/from hex/sha1 representation */ #define MINIMUM_ABBREV 4 #define DEFAULT_ABBREV 7 @@ -274,9 +298,9 @@ extern int get_sha1(const char *str, unsigned char *sha1); extern int get_sha1_hex(const char *hex, unsigned char *sha1); extern char *sha1_to_hex(const unsigned char *sha1); /* static buffer result! */ extern int read_ref(const char *filename, unsigned char *sha1); -extern const char *resolve_ref(const char *path, unsigned char *sha1, int); -extern int create_symref(const char *git_HEAD, const char *refs_heads_master); -extern int validate_symref(const char *git_HEAD); +extern const char *resolve_ref(const char *path, unsigned char *sha1, int, int *); +extern int create_symref(const char *ref, const char *refs_heads_master); +extern int validate_headref(const char *ref); extern int base_name_compare(const char *name1, int len1, int mode1, const char *name2, int len2, int mode2); extern int cache_name_compare(const char *name1, int len1, const char *name2, int len2); @@ -286,13 +310,14 @@ extern void *read_object_with_reference(const unsigned char *sha1, unsigned long *size, unsigned char *sha1_ret); -const char *show_date(unsigned long time, int timezone); +const char *show_date(unsigned long time, int timezone, int relative); const char *show_rfc2822_date(unsigned long time, int timezone); int parse_date(const char *date, char *buf, int bufsize); void datestamp(char *buf, int bufsize); unsigned long approxidate(const char *); extern int setup_ident(void); +extern void ignore_missing_committer_name(); extern const char *git_author_info(int); extern const char *git_committer_info(int); @@ -314,14 +339,22 @@ extern struct alternate_object_database { } *alt_odb_list; extern void prepare_alt_odb(void); +struct pack_window { + struct pack_window *next; + unsigned char *base; + off_t offset; + size_t len; + unsigned int last_used; + unsigned int inuse_cnt; +}; + extern struct packed_git { struct packed_git *next; - unsigned long index_size; - unsigned long pack_size; + struct pack_window *windows; unsigned int *index_base; - void *pack_base; - unsigned int pack_last_used; - unsigned int pack_use_cnt; + off_t index_size; + off_t pack_size; + int pack_fd; int pack_local; unsigned char sha1[20]; /* something like ".git/objects/pack/xxxxx.pack" */ @@ -347,7 +380,7 @@ struct ref { #define REF_HEADS (1u << 1) #define REF_TAGS (1u << 2) -extern int git_connect(int fd[2], char *url, const char *prog); +extern pid_t git_connect(int fd[2], char *url, const char *prog); extern int finish_connect(pid_t pid); extern int path_match(const char *path, int nr, char **match); extern int match_refs(struct ref *src, struct ref *dst, struct ref ***dst_tail, @@ -361,19 +394,22 @@ extern struct packed_git *parse_pack_index_file(const unsigned char *sha1, char *idx_path); extern void prepare_packed_git(void); +extern void reprepare_packed_git(void); extern void install_packed_git(struct packed_git *pack); extern struct packed_git *find_sha1_pack(const unsigned char *sha1, struct packed_git *packs); -extern int use_packed_git(struct packed_git *); -extern void unuse_packed_git(struct packed_git *); +extern void pack_report(); +extern unsigned char* use_pack(struct packed_git *, struct pack_window **, unsigned long, unsigned int *); +extern void unuse_pack(struct pack_window **); extern struct packed_git *add_packed_git(char *, int, int); extern int num_packed_objects(const struct packed_git *p); extern int nth_packed_object_sha1(const struct packed_git *, int, unsigned char*); -extern int find_pack_entry_one(const unsigned char *, struct pack_entry *, struct packed_git *); -extern void *unpack_entry_gently(struct pack_entry *, char *, unsigned long *); -extern void packed_object_info_detail(struct pack_entry *, char *, unsigned long *, unsigned long *, unsigned int *, unsigned char *); +extern unsigned long find_pack_entry_one(const unsigned char *, struct packed_git *); +extern void *unpack_entry(struct packed_git *, unsigned long, char *, unsigned long *); +extern unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); +extern void packed_object_info_detail(struct packed_git *, unsigned long, char *, unsigned long *, unsigned long *, unsigned int *, unsigned char *); /* Dumb servers support */ extern int update_server_info(int); @@ -386,21 +422,23 @@ extern int git_config_int(const char *, const char *); extern int git_config_bool(const char *, const char *); extern int git_config_set(const char *, const char *); extern int git_config_set_multivar(const char *, const char *, const char *, int); +extern int git_config_rename_section(const char *, const char *); extern int check_repository_format_version(const char *var, const char *value); #define MAX_GITNAME (1000) extern char git_default_email[MAX_GITNAME]; extern char git_default_name[MAX_GITNAME]; -#define MAX_ENCODING_LENGTH 64 -extern char git_commit_encoding[MAX_ENCODING_LENGTH]; +extern char *git_commit_encoding; +extern char *git_log_output_encoding; extern int copy_fd(int ifd, int ofd); +extern int read_in_full(int fd, void *buf, size_t count); +extern void read_or_die(int fd, void *buf, size_t count); +extern int write_in_full(int fd, const void *buf, size_t count); extern void write_or_die(int fd, const void *buf, size_t count); - -/* Finish off pack transfer receiving end */ -extern int receive_unpack_pack(int fd[2], const char *me, int quiet, int); -extern int receive_keep_pack(int fd[2], const char *me, int quiet, int); +extern int write_or_whine(int fd, const void *buf, size_t count, const char *msg); +extern int write_or_whine_pipe(int fd, const void *buf, size_t count, const char *msg); /* pager.c */ extern void setup_pager(void); @@ -422,4 +460,9 @@ extern struct commit *alloc_commit_node(void); extern struct tag *alloc_tag_node(void); extern void alloc_report(void); +/* trace.c */ +extern int nfvasprintf(char **str, const char *fmt, va_list va); +extern void trace_printf(const char *format, ...); +extern void trace_argv_printf(const char **argv, int count, const char *format, ...); + #endif /* CACHE_H */ diff --git a/check-builtins.sh b/check-builtins.sh new file mode 100755 index 0000000000..d6fe6cf174 --- /dev/null +++ b/check-builtins.sh @@ -0,0 +1,34 @@ +#!/bin/sh + +{ + cat <<\EOF +sayIt: + $(foreach b,$(BUILT_INS),echo XXX $b YYY;) +EOF + cat Makefile +} | +make -f - sayIt 2>/dev/null | +sed -n -e 's/.*XXX \(.*\) YYY.*/\1/p' | +sort | +{ + bad=0 + while read builtin + do + base=`expr "$builtin" : 'git-\(.*\)'` + x=`sed -ne 's/.*{ "'$base'", \(cmd_[^, ]*\).*/'$base' \1/p' git.c` + if test -z "$x" + then + echo "$base is builtin but not listed in git.c command list" + bad=1 + fi + for sfx in sh perl py + do + if test -f "$builtin.$sfx" + then + echo "$base is builtin but $builtin.$sfx still exists" + bad=1 + fi + done + done + exit $bad +} diff --git a/color.c b/color.c new file mode 100644 index 0000000000..09d82eec3d --- /dev/null +++ b/color.c @@ -0,0 +1,173 @@ +#include "cache.h" +#include "color.h" + +#define COLOR_RESET "\033[m" + +static int parse_color(const char *name, int len) +{ + static const char * const color_names[] = { + "normal", "black", "red", "green", "yellow", + "blue", "magenta", "cyan", "white" + }; + char *end; + int i; + for (i = 0; i < ARRAY_SIZE(color_names); i++) { + const char *str = color_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return i - 1; + } + i = strtol(name, &end, 10); + if (*name && !*end && i >= -1 && i <= 255) + return i; + return -2; +} + +static int parse_attr(const char *name, int len) +{ + static const int attr_values[] = { 1, 2, 4, 5, 7 }; + static const char * const attr_names[] = { + "bold", "dim", "ul", "blink", "reverse" + }; + int i; + for (i = 0; i < ARRAY_SIZE(attr_names); i++) { + const char *str = attr_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return attr_values[i]; + } + return -1; +} + +void color_parse(const char *value, const char *var, char *dst) +{ + const char *ptr = value; + int attr = -1; + int fg = -2; + int bg = -2; + + if (!strcasecmp(value, "reset")) { + strcpy(dst, "\033[m"); + return; + } + + /* [fg [bg]] [attr] */ + while (*ptr) { + const char *word = ptr; + int val, len = 0; + + while (word[len] && !isspace(word[len])) + len++; + + ptr = word + len; + while (*ptr && isspace(*ptr)) + ptr++; + + val = parse_color(word, len); + if (val >= -1) { + if (fg == -2) { + fg = val; + continue; + } + if (bg == -2) { + bg = val; + continue; + } + goto bad; + } + val = parse_attr(word, len); + if (val < 0 || attr != -1) + goto bad; + attr = val; + } + + if (attr >= 0 || fg >= 0 || bg >= 0) { + int sep = 0; + + *dst++ = '\033'; + *dst++ = '['; + if (attr >= 0) { + *dst++ = '0' + attr; + sep++; + } + if (fg >= 0) { + if (sep++) + *dst++ = ';'; + if (fg < 8) { + *dst++ = '3'; + *dst++ = '0' + fg; + } else { + dst += sprintf(dst, "38;5;%d", fg); + } + } + if (bg >= 0) { + if (sep++) + *dst++ = ';'; + if (bg < 8) { + *dst++ = '4'; + *dst++ = '0' + bg; + } else { + dst += sprintf(dst, "48;5;%d", bg); + } + } + *dst++ = 'm'; + } + *dst = 0; + return; +bad: + die("bad config value '%s' for variable '%s'", value, var); +} + +int git_config_colorbool(const char *var, const char *value) +{ + if (!value) + return 1; + if (!strcasecmp(value, "auto")) { + if (isatty(1) || (pager_in_use && pager_use_color)) { + char *term = getenv("TERM"); + if (term && strcmp(term, "dumb")) + return 1; + } + return 0; + } + if (!strcasecmp(value, "never")) + return 0; + if (!strcasecmp(value, "always")) + return 1; + return git_config_bool(var, value); +} + +static int color_vprintf(const char *color, const char *fmt, + va_list args, const char *trail) +{ + int r = 0; + + if (*color) + r += printf("%s", color); + r += vprintf(fmt, args); + if (*color) + r += printf("%s", COLOR_RESET); + if (trail) + r += printf("%s", trail); + return r; +} + + + +int color_printf(const char *color, const char *fmt, ...) +{ + va_list args; + int r; + va_start(args, fmt); + r = color_vprintf(color, fmt, args, NULL); + va_end(args); + return r; +} + +int color_printf_ln(const char *color, const char *fmt, ...) +{ + va_list args; + int r; + va_start(args, fmt); + r = color_vprintf(color, fmt, args, "\n"); + va_end(args); + return r; +} diff --git a/color.h b/color.h new file mode 100644 index 0000000000..88bb8ff1bd --- /dev/null +++ b/color.h @@ -0,0 +1,12 @@ +#ifndef COLOR_H +#define COLOR_H + +/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ +#define COLOR_MAXLEN 24 + +int git_config_colorbool(const char *var, const char *value); +void color_parse(const char *var, const char *value, char *dst); +int color_printf(const char *color, const char *fmt, ...); +int color_printf_ln(const char *color, const char *fmt, ...); + +#endif /* COLOR_H */ diff --git a/combine-diff.c b/combine-diff.c index 46d9121baf..29d0c9cf95 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -489,6 +489,16 @@ static void show_parent_lno(struct sline *sline, unsigned long l0, unsigned long printf(" -%lu,%lu", l0, l1-l0); } +static int hunk_comment_line(const char *bol) +{ + int ch; + + if (!bol) + return 0; + ch = *bol & 0xff; + return (isalpha(ch) || ch == '_' || ch == '$'); +} + static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent, int use_color) { @@ -508,8 +518,13 @@ static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent, struct sline *sl = &sline[lno]; unsigned long hunk_end; unsigned long rlines; - while (lno <= cnt && !(sline[lno].flag & mark)) + const char *hunk_comment = NULL; + + while (lno <= cnt && !(sline[lno].flag & mark)) { + if (hunk_comment_line(sline[lno].bol)) + hunk_comment = sline[lno].bol; lno++; + } if (cnt < lno) break; else { @@ -526,6 +541,22 @@ static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent, show_parent_lno(sline, lno, hunk_end, i); printf(" +%lu,%lu ", lno+1, rlines); for (i = 0; i <= num_parent; i++) putchar(combine_marker); + + if (hunk_comment) { + int comment_end = 0; + for (i = 0; i < 40; i++) { + int ch = hunk_comment[i] & 0xff; + if (!ch || ch == '\n') + break; + if (!isspace(ch)) + comment_end = i; + } + if (comment_end) + putchar(' '); + for (i = 0; i < comment_end; i++) + putchar(hunk_comment[i]); + } + printf("%s\n", c_reset); while (lno < hunk_end) { struct lline *ll; @@ -707,8 +738,10 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent, int use_color = opt->color_diff; const char *c_meta = diff_get_color(use_color, DIFF_METAINFO); const char *c_reset = diff_get_color(use_color, DIFF_RESET); + int added = 0; + int deleted = 0; - if (rev->loginfo) + if (rev->loginfo && !rev->no_commit_id) show_log(rev, opt->msg_sep); dump_quoted_path(dense ? "diff --cc " : "diff --combined ", elem->path, c_meta, c_reset); @@ -722,7 +755,10 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent, printf("..%s%s\n", abb, c_reset); if (mode_differs) { - int added = !!elem->mode; + deleted = !elem->mode; + + /* We say it was added if nobody had it */ + added = !deleted; for (i = 0; added && i < num_parent; i++) if (elem->parent[i].status != DIFF_STATUS_ADDED) @@ -731,7 +767,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent, printf("%snew file mode %06o", c_meta, elem->mode); else { - if (!elem->mode) + if (deleted) printf("%sdeleted file ", c_meta); printf("mode "); for (i = 0; i < num_parent; i++) { @@ -743,8 +779,14 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent, } printf("%s\n", c_reset); } - dump_quoted_path("--- a/", elem->path, c_meta, c_reset); - dump_quoted_path("+++ b/", elem->path, c_meta, c_reset); + if (added) + dump_quoted_path("--- /dev/", "null", c_meta, c_reset); + else + dump_quoted_path("--- a/", elem->path, c_meta, c_reset); + if (deleted) + dump_quoted_path("+++ /dev/", "null", c_meta, c_reset); + else + dump_quoted_path("+++ b/", elem->path, c_meta, c_reset); dump_sline(sline, cnt, num_parent, opt->color_diff); } free(result); @@ -777,7 +819,7 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, struct re if (!line_termination) inter_name_termination = 0; - if (rev->loginfo) + if (rev->loginfo && !rev->no_commit_id) show_log(rev, opt->msg_sep); if (opt->output_format & DIFF_FORMAT_RAW) { @@ -849,15 +891,17 @@ void diff_tree_combined(const unsigned char *sha1, diffopts.output_format = DIFF_FORMAT_NO_OUTPUT; diffopts.recursive = 1; - show_log_first = !!rev->loginfo; + show_log_first = !!rev->loginfo && !rev->no_commit_id; needsep = 0; /* find set of paths that everybody touches */ for (i = 0; i < num_parent; i++) { /* show stat against the first parent even * when doing combined diff. */ - if (i == 0 && opt->output_format & DIFF_FORMAT_DIFFSTAT) - diffopts.output_format = DIFF_FORMAT_DIFFSTAT; + int stat_opt = (opt->output_format & + (DIFF_FORMAT_NUMSTAT|DIFF_FORMAT_DIFFSTAT)); + if (i == 0 && stat_opt) + diffopts.output_format = stat_opt; else diffopts.output_format = DIFF_FORMAT_NO_OUTPUT; diff_tree_sha1(parent[i], sha1, "", &diffopts); @@ -887,7 +931,8 @@ void diff_tree_combined(const unsigned char *sha1, } needsep = 1; } - else if (opt->output_format & DIFF_FORMAT_DIFFSTAT) + else if (opt->output_format & + (DIFF_FORMAT_NUMSTAT|DIFF_FORMAT_DIFFSTAT)) needsep = 1; if (opt->output_format & DIFF_FORMAT_PATCH) { if (needsep) @@ -1,6 +1,8 @@ #include "cache.h" #include "tag.h" #include "commit.h" +#include "pkt-line.h" +#include "utf8.h" int save_commit_buffer = 1; @@ -221,6 +223,8 @@ static void prepare_commit_graft(void) return; graft_file = get_graft_file(); read_graft_file(graft_file); + /* make sure shallows are read */ + is_repository_shallow(); commit_graft_prepared = 1; } @@ -234,6 +238,39 @@ static struct commit_graft *lookup_commit_graft(const unsigned char *sha1) return commit_graft[pos]; } +int write_shallow_commits(int fd, int use_pack_protocol) +{ + int i, count = 0; + for (i = 0; i < commit_graft_nr; i++) + if (commit_graft[i]->nr_parent < 0) { + const char *hex = + sha1_to_hex(commit_graft[i]->sha1); + count++; + if (use_pack_protocol) + packet_write(fd, "shallow %s", hex); + else { + if (write_in_full(fd, hex, 40) != 40) + break; + if (write_in_full(fd, "\n", 1) != 1) + break; + } + } + return count; +} + +int unregister_shallow(const unsigned char *sha1) +{ + int pos = commit_graft_pos(sha1); + if (pos < 0) + return -1; + if (pos + 1 < commit_graft_nr) + memcpy(commit_graft + pos, commit_graft + pos + 1, + sizeof(struct commit_graft *) + * (commit_graft_nr - pos - 1)); + commit_graft_nr--; + return 0; +} + int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) { char *tail = buffer; @@ -467,7 +504,8 @@ static int add_rfc2047(char *buf, const char *line, int len) return bp - buf; } -static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const char *line) +static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, + const char *line, int relative_date) { char *date; int namelen; @@ -507,14 +545,16 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c } switch (fmt) { case CMIT_FMT_MEDIUM: - ret += sprintf(buf + ret, "Date: %s\n", show_date(time, tz)); + ret += sprintf(buf + ret, "Date: %s\n", + show_date(time, tz, relative_date)); break; case CMIT_FMT_EMAIL: ret += sprintf(buf + ret, "Date: %s\n", show_rfc2822_date(time, tz)); break; case CMIT_FMT_FULLER: - ret += sprintf(buf + ret, "%sDate: %s\n", what, show_date(time, tz)); + ret += sprintf(buf + ret, "%sDate: %s\n", what, + show_date(time, tz, relative_date)); break; default: /* notin' */ @@ -545,10 +585,13 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com while (parent) { struct commit *p = parent->item; - const char *hex = abbrev - ? find_unique_abbrev(p->object.sha1, abbrev) - : sha1_to_hex(p->object.sha1); - const char *dots = (abbrev && strlen(hex) != 40) ? "..." : ""; + const char *hex = NULL; + const char *dots; + if (abbrev) + hex = find_unique_abbrev(p->object.sha1, abbrev); + if (!hex) + hex = sha1_to_hex(p->object.sha1); + dots = (abbrev && strlen(hex) != 40) ? "..." : ""; parent = parent->next; offset += sprintf(buf + offset, " %s%s", hex, dots); @@ -557,14 +600,121 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com return offset; } -unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject) +static char *get_header(const struct commit *commit, const char *key) { - int hdr = 1, body = 0; + int key_len = strlen(key); + const char *line = commit->buffer; + + for (;;) { + const char *eol = strchr(line, '\n'), *next; + + if (line == eol) + return NULL; + if (!eol) { + eol = line + strlen(line); + next = NULL; + } else + next = eol + 1; + if (!strncmp(line, key, key_len) && line[key_len] == ' ') { + int len = eol - line - key_len; + char *ret = xmalloc(len); + memcpy(ret, line + key_len + 1, len - 1); + ret[len - 1] = '\0'; + return ret; + } + line = next; + } +} + +static char *replace_encoding_header(char *buf, char *encoding) +{ + char *encoding_header = strstr(buf, "\nencoding "); + char *end_of_encoding_header; + int encoding_header_pos; + int encoding_header_len; + int new_len; + int need_len; + int buflen = strlen(buf) + 1; + + if (!encoding_header) + return buf; /* should not happen but be defensive */ + encoding_header++; + end_of_encoding_header = strchr(encoding_header, '\n'); + if (!end_of_encoding_header) + return buf; /* should not happen but be defensive */ + end_of_encoding_header++; + + encoding_header_len = end_of_encoding_header - encoding_header; + encoding_header_pos = encoding_header - buf; + + if (is_encoding_utf8(encoding)) { + /* we have re-coded to UTF-8; drop the header */ + memmove(encoding_header, end_of_encoding_header, + buflen - (encoding_header_pos + encoding_header_len)); + return buf; + } + new_len = strlen(encoding); + need_len = new_len + strlen("encoding \n"); + if (encoding_header_len < need_len) { + buf = xrealloc(buf, buflen + (need_len - encoding_header_len)); + encoding_header = buf + encoding_header_pos; + end_of_encoding_header = encoding_header + encoding_header_len; + } + memmove(end_of_encoding_header + (need_len - encoding_header_len), + end_of_encoding_header, + buflen - (encoding_header_pos + encoding_header_len)); + memcpy(encoding_header + 9, encoding, strlen(encoding)); + encoding_header[9 + new_len] = '\n'; + return buf; +} + +static char *logmsg_reencode(const struct commit *commit) +{ + char *encoding; + char *out; + char *output_encoding = (git_log_output_encoding + ? git_log_output_encoding + : git_commit_encoding); + + if (!output_encoding) + output_encoding = "utf-8"; + else if (!*output_encoding) + return NULL; + encoding = get_header(commit, "encoding"); + if (!encoding) + return NULL; + if (!strcmp(encoding, output_encoding)) + out = strdup(commit->buffer); + else + out = reencode_string(commit->buffer, + output_encoding, encoding); + if (out) + out = replace_encoding_header(out, output_encoding); + + free(encoding); + if (!out) + return NULL; + return out; +} + +unsigned long pretty_print_commit(enum cmit_fmt fmt, + const struct commit *commit, + unsigned long len, + char *buf, unsigned long space, + int abbrev, const char *subject, + const char *after_subject, + int relative_date) +{ + int hdr = 1, body = 0, seen_title = 0; unsigned long offset = 0; int indent = 4; int parents_shown = 0; const char *msg = commit->buffer; int plain_non_ascii = 0; + char *reencoded = logmsg_reencode(commit); + + if (reencoded) + msg = reencoded; if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) indent = 0; @@ -581,7 +731,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit for (in_body = i = 0; (ch = msg[i]) && i < len; i++) { if (!in_body) { /* author could be non 7-bit ASCII but - * the log may so; skip over the + * the log may be so; skip over the * header part first. */ if (ch == '\n' && @@ -646,12 +796,14 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit if (!memcmp(line, "author ", 7)) offset += add_user_info("Author", fmt, buf + offset, - line + 7); + line + 7, + relative_date); if (!memcmp(line, "committer ", 10) && (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) offset += add_user_info("Commit", fmt, buf + offset, - line + 10); + line + 10, + relative_date); continue; } @@ -659,6 +811,8 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit body = 1; if (is_empty_line(line, &linelen)) { + if (!seen_title) + continue; if (!body) continue; if (subject) @@ -667,6 +821,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit break; } + seen_title = 1; if (subject) { int slen = strlen(subject); memcpy(buf + offset, subject, slen); @@ -710,6 +865,8 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit if (fmt == CMIT_FMT_EMAIL && !body) buf[offset++] = '\n'; buf[offset] = '\0'; + + free(reencoded); return offset; } @@ -855,13 +1012,15 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo, free(nodes); } -/* merge-rebase stuff */ +/* merge-base stuff */ + +/* bits #0..15 in revision.h */ +#define PARENT1 (1u<<16) +#define PARENT2 (1u<<17) +#define STALE (1u<<18) +#define RESULT (1u<<19) -/* bits #0..7 in revision.h */ -#define PARENT1 (1u<< 8) -#define PARENT2 (1u<< 9) -#define STALE (1u<<10) -#define RESULT (1u<<11) +static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT); static struct commit *interesting(struct commit_list *list) { @@ -927,6 +1086,7 @@ static struct commit_list *merge_bases(struct commit *one, struct commit *two) } /* Clean up the result to remove stale ones */ + free_commit_list(list); list = result; result = NULL; while (list) { struct commit_list *n = list->next; @@ -942,7 +1102,6 @@ struct commit_list *get_merge_bases(struct commit *one, struct commit *two, int cleanup) { - const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT); struct commit_list *list; struct commit **rslt; struct commit_list *result; @@ -998,3 +1157,20 @@ struct commit_list *get_merge_bases(struct commit *one, free(rslt); return result; } + +int in_merge_bases(struct commit *rev1, struct commit *rev2) +{ + struct commit_list *bases, *b; + int ret = 0; + + bases = get_merge_bases(rev1, rev2, 1); + for (b = bases; b; b = b->next) { + if (!hashcmp(rev1->object.sha1, b->item->object.sha1)) { + ret = 1; + break; + } + } + + free_commit_list(bases); + return ret; +} @@ -52,7 +52,7 @@ enum cmit_fmt { }; extern enum cmit_fmt get_commit_format(const char *arg); -extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject); +extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject, int relative_date); /** Removes the first commit from a list sorted by date, and adds all * of its parents. @@ -97,7 +97,7 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo, struct commit_graft { unsigned char sha1[20]; - int nr_parent; + int nr_parent; /* < 0 if shallow commit */ unsigned char parent[FLEX_ARRAY][20]; /* more */ }; @@ -107,4 +107,12 @@ int read_graft_file(const char *graft_file); extern struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2, int cleanup); +extern int register_shallow(const unsigned char *sha1); +extern int unregister_shallow(const unsigned char *sha1); +extern int write_shallow_commits(int fd, int use_pack_protocol); +extern int is_repository_shallow(); +extern struct commit_list *get_shallow_commits(struct object_array *heads, + int depth, int shallow_flag, int not_shallow_flag); + +int in_merge_bases(struct commit *rev1, struct commit *rev2); #endif /* COMMIT_H */ diff --git a/compat/inet_ntop.c b/compat/inet_ntop.c index ec8c1bff53..4d7ab9d975 100644 --- a/compat/inet_ntop.c +++ b/compat/inet_ntop.c @@ -93,7 +93,7 @@ inet_ntop6(src, dst, size) */ char tmp[sizeof "ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255"], *tp; struct { int base, len; } best, cur; - u_int words[NS_IN6ADDRSZ / NS_INT16SZ]; + unsigned int words[NS_IN6ADDRSZ / NS_INT16SZ]; int i; /* diff --git a/compat/inet_pton.c b/compat/inet_pton.c new file mode 100644 index 0000000000..5704e0d2b6 --- /dev/null +++ b/compat/inet_pton.c @@ -0,0 +1,220 @@ +/* + * Copyright (C) 1996-2001 Internet Software Consortium. + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND INTERNET SOFTWARE CONSORTIUM + * DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL + * INTERNET SOFTWARE CONSORTIUM BE LIABLE FOR ANY SPECIAL, DIRECT, + * INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING + * FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, + * NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION + * WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#include <errno.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <stdio.h> +#include <string.h> + +#ifndef NS_INT16SZ +#define NS_INT16SZ 2 +#endif + +#ifndef NS_INADDRSZ +#define NS_INADDRSZ 4 +#endif + +#ifndef NS_IN6ADDRSZ +#define NS_IN6ADDRSZ 16 +#endif + +/* + * WARNING: Don't even consider trying to compile this on a system where + * sizeof(int) < 4. sizeof(int) > 4 is fine; all the world's not a VAX. + */ + +static int inet_pton4(const char *src, unsigned char *dst); +static int inet_pton6(const char *src, unsigned char *dst); + +/* int + * inet_pton4(src, dst) + * like inet_aton() but without all the hexadecimal and shorthand. + * return: + * 1 if `src' is a valid dotted quad, else 0. + * notice: + * does not touch `dst' unless it's returning 1. + * author: + * Paul Vixie, 1996. + */ +static int +inet_pton4(const char *src, unsigned char *dst) +{ + static const char digits[] = "0123456789"; + int saw_digit, octets, ch; + unsigned char tmp[NS_INADDRSZ], *tp; + + saw_digit = 0; + octets = 0; + *(tp = tmp) = 0; + while ((ch = *src++) != '\0') { + const char *pch; + + if ((pch = strchr(digits, ch)) != NULL) { + unsigned int new = *tp * 10 + (pch - digits); + + if (new > 255) + return (0); + *tp = new; + if (! saw_digit) { + if (++octets > 4) + return (0); + saw_digit = 1; + } + } else if (ch == '.' && saw_digit) { + if (octets == 4) + return (0); + *++tp = 0; + saw_digit = 0; + } else + return (0); + } + if (octets < 4) + return (0); + memcpy(dst, tmp, NS_INADDRSZ); + return (1); +} + +/* int + * inet_pton6(src, dst) + * convert presentation level address to network order binary form. + * return: + * 1 if `src' is a valid [RFC1884 2.2] address, else 0. + * notice: + * (1) does not touch `dst' unless it's returning 1. + * (2) :: in a full address is silently ignored. + * credit: + * inspired by Mark Andrews. + * author: + * Paul Vixie, 1996. + */ + +#ifndef NO_IPV6 +static int +inet_pton6(const char *src, unsigned char *dst) +{ + static const char xdigits_l[] = "0123456789abcdef", + xdigits_u[] = "0123456789ABCDEF"; + unsigned char tmp[NS_IN6ADDRSZ], *tp, *endp, *colonp; + const char *xdigits, *curtok; + int ch, saw_xdigit; + unsigned int val; + + memset((tp = tmp), '\0', NS_IN6ADDRSZ); + endp = tp + NS_IN6ADDRSZ; + colonp = NULL; + /* Leading :: requires some special handling. */ + if (*src == ':') + if (*++src != ':') + return (0); + curtok = src; + saw_xdigit = 0; + val = 0; + while ((ch = *src++) != '\0') { + const char *pch; + + if ((pch = strchr((xdigits = xdigits_l), ch)) == NULL) + pch = strchr((xdigits = xdigits_u), ch); + if (pch != NULL) { + val <<= 4; + val |= (pch - xdigits); + if (val > 0xffff) + return (0); + saw_xdigit = 1; + continue; + } + if (ch == ':') { + curtok = src; + if (!saw_xdigit) { + if (colonp) + return (0); + colonp = tp; + continue; + } + if (tp + NS_INT16SZ > endp) + return (0); + *tp++ = (unsigned char) (val >> 8) & 0xff; + *tp++ = (unsigned char) val & 0xff; + saw_xdigit = 0; + val = 0; + continue; + } + if (ch == '.' && ((tp + NS_INADDRSZ) <= endp) && + inet_pton4(curtok, tp) > 0) { + tp += NS_INADDRSZ; + saw_xdigit = 0; + break; /* '\0' was seen by inet_pton4(). */ + } + return (0); + } + if (saw_xdigit) { + if (tp + NS_INT16SZ > endp) + return (0); + *tp++ = (unsigned char) (val >> 8) & 0xff; + *tp++ = (unsigned char) val & 0xff; + } + if (colonp != NULL) { + /* + * Since some memmove()'s erroneously fail to handle + * overlapping regions, we'll do the shift by hand. + */ + const int n = tp - colonp; + int i; + + for (i = 1; i <= n; i++) { + endp[- i] = colonp[n - i]; + colonp[n - i] = 0; + } + tp = endp; + } + if (tp != endp) + return (0); + memcpy(dst, tmp, NS_IN6ADDRSZ); + return (1); +} +#endif + +/* int + * isc_net_pton(af, src, dst) + * convert from presentation format (which usually means ASCII printable) + * to network format (which is usually some kind of binary format). + * return: + * 1 if the address was valid for the specified address family + * 0 if the address wasn't valid (`dst' is untouched in this case) + * -1 if some other error occurred (`dst' is untouched in this case, too) + * author: + * Paul Vixie, 1996. + */ +int +inet_pton(int af, const char *src, void *dst) +{ + switch (af) { + case AF_INET: + return (inet_pton4(src, dst)); +#ifndef NO_IPV6 + case AF_INET6: + return (inet_pton6(src, dst)); +#endif + default: + errno = EAFNOSUPPORT; + return (-1); + } + /* NOTREACHED */ +} diff --git a/compat/mmap.c b/compat/mmap.c index 55cb120764..4cfaee3136 100644 --- a/compat/mmap.c +++ b/compat/mmap.c @@ -1,20 +1,11 @@ -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <errno.h> #include "../git-compat-util.h" -void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_t offset) +void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset) { - int n = 0; + size_t n = 0; if (start != NULL || !(flags & MAP_PRIVATE)) - die("Invalid usage of gitfakemmap."); - - if (lseek(fd, offset, SEEK_SET) < 0) { - errno = EINVAL; - return MAP_FAILED; - } + die("Invalid usage of mmap when built with NO_MMAP"); start = xmalloc(length); if (start == NULL) { @@ -23,14 +14,16 @@ void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_ } while (n < length) { - int count = read(fd, start+n, length-n); + ssize_t count = pread(fd, (char *)start + n, length - n, offset + n); if (count == 0) { - memset(start+n, 0, length-n); + memset((char *)start+n, 0, length-n); break; } if (count < 0) { + if (errno == EAGAIN || errno == EINTR) + continue; free(start); errno = EACCES; return MAP_FAILED; @@ -42,7 +35,7 @@ void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_ return start; } -int gitfakemunmap(void *start, size_t length) +int git_munmap(void *start, size_t length) { free(start); return 0; diff --git a/compat/pread.c b/compat/pread.c new file mode 100644 index 0000000000..978cac4ec9 --- /dev/null +++ b/compat/pread.c @@ -0,0 +1,18 @@ +#include "../git-compat-util.h" + +ssize_t git_pread(int fd, void *buf, size_t count, off_t offset) +{ + off_t current_offset; + ssize_t rc; + + current_offset = lseek(fd, 0, SEEK_CUR); + + if (lseek(fd, offset, SEEK_SET) < 0) + return -1; + + rc = read_in_full(fd, buf, count); + + if (current_offset != lseek(fd, current_offset, SEEK_SET)) + return -1; + return rc; +} diff --git a/compat/setenv.c b/compat/setenv.c index b7d7678598..3a22ea7b75 100644 --- a/compat/setenv.c +++ b/compat/setenv.c @@ -1,5 +1,4 @@ -#include <stdlib.h> -#include <string.h> +#include "../git-compat-util.h" int gitsetenv(const char *name, const char *value, int replace) { diff --git a/compat/strlcpy.c b/compat/strlcpy.c index b66856a3a5..4024c36030 100644 --- a/compat/strlcpy.c +++ b/compat/strlcpy.c @@ -1,4 +1,4 @@ -#include <string.h> +#include "../git-compat-util.h" size_t gitstrlcpy(char *dest, const char *src, size_t size) { diff --git a/compat/subprocess.py b/compat/subprocess.py deleted file mode 100644 index 6474eab119..0000000000 --- a/compat/subprocess.py +++ /dev/null @@ -1,1149 +0,0 @@ -# subprocess - Subprocesses with accessible I/O streams -# -# For more information about this module, see PEP 324. -# -# This module should remain compatible with Python 2.2, see PEP 291. -# -# Copyright (c) 2003-2005 by Peter Astrand <astrand@lysator.liu.se> -# -# Licensed to PSF under a Contributor Agreement. -# See http://www.python.org/2.4/license for licensing details. - -r"""subprocess - Subprocesses with accessible I/O streams - -This module allows you to spawn processes, connect to their -input/output/error pipes, and obtain their return codes. This module -intends to replace several other, older modules and functions, like: - -os.system -os.spawn* -os.popen* -popen2.* -commands.* - -Information about how the subprocess module can be used to replace these -modules and functions can be found below. - - - -Using the subprocess module -=========================== -This module defines one class called Popen: - -class Popen(args, bufsize=0, executable=None, - stdin=None, stdout=None, stderr=None, - preexec_fn=None, close_fds=False, shell=False, - cwd=None, env=None, universal_newlines=False, - startupinfo=None, creationflags=0): - - -Arguments are: - -args should be a string, or a sequence of program arguments. The -program to execute is normally the first item in the args sequence or -string, but can be explicitly set by using the executable argument. - -On UNIX, with shell=False (default): In this case, the Popen class -uses os.execvp() to execute the child program. args should normally -be a sequence. A string will be treated as a sequence with the string -as the only item (the program to execute). - -On UNIX, with shell=True: If args is a string, it specifies the -command string to execute through the shell. If args is a sequence, -the first item specifies the command string, and any additional items -will be treated as additional shell arguments. - -On Windows: the Popen class uses CreateProcess() to execute the child -program, which operates on strings. If args is a sequence, it will be -converted to a string using the list2cmdline method. Please note that -not all MS Windows applications interpret the command line the same -way: The list2cmdline is designed for applications using the same -rules as the MS C runtime. - -bufsize, if given, has the same meaning as the corresponding argument -to the built-in open() function: 0 means unbuffered, 1 means line -buffered, any other positive value means use a buffer of -(approximately) that size. A negative bufsize means to use the system -default, which usually means fully buffered. The default value for -bufsize is 0 (unbuffered). - -stdin, stdout and stderr specify the executed programs' standard -input, standard output and standard error file handles, respectively. -Valid values are PIPE, an existing file descriptor (a positive -integer), an existing file object, and None. PIPE indicates that a -new pipe to the child should be created. With None, no redirection -will occur; the child's file handles will be inherited from the -parent. Additionally, stderr can be STDOUT, which indicates that the -stderr data from the applications should be captured into the same -file handle as for stdout. - -If preexec_fn is set to a callable object, this object will be called -in the child process just before the child is executed. - -If close_fds is true, all file descriptors except 0, 1 and 2 will be -closed before the child process is executed. - -if shell is true, the specified command will be executed through the -shell. - -If cwd is not None, the current directory will be changed to cwd -before the child is executed. - -If env is not None, it defines the environment variables for the new -process. - -If universal_newlines is true, the file objects stdout and stderr are -opened as a text files, but lines may be terminated by any of '\n', -the Unix end-of-line convention, '\r', the Macintosh convention or -'\r\n', the Windows convention. All of these external representations -are seen as '\n' by the Python program. Note: This feature is only -available if Python is built with universal newline support (the -default). Also, the newlines attribute of the file objects stdout, -stdin and stderr are not updated by the communicate() method. - -The startupinfo and creationflags, if given, will be passed to the -underlying CreateProcess() function. They can specify things such as -appearance of the main window and priority for the new process. -(Windows only) - - -This module also defines two shortcut functions: - -call(*args, **kwargs): - Run command with arguments. Wait for command to complete, then - return the returncode attribute. - - The arguments are the same as for the Popen constructor. Example: - - retcode = call(["ls", "-l"]) - - -Exceptions ----------- -Exceptions raised in the child process, before the new program has -started to execute, will be re-raised in the parent. Additionally, -the exception object will have one extra attribute called -'child_traceback', which is a string containing traceback information -from the childs point of view. - -The most common exception raised is OSError. This occurs, for -example, when trying to execute a non-existent file. Applications -should prepare for OSErrors. - -A ValueError will be raised if Popen is called with invalid arguments. - - -Security --------- -Unlike some other popen functions, this implementation will never call -/bin/sh implicitly. This means that all characters, including shell -metacharacters, can safely be passed to child processes. - - -Popen objects -============= -Instances of the Popen class have the following methods: - -poll() - Check if child process has terminated. Returns returncode - attribute. - -wait() - Wait for child process to terminate. Returns returncode attribute. - -communicate(input=None) - Interact with process: Send data to stdin. Read data from stdout - and stderr, until end-of-file is reached. Wait for process to - terminate. The optional stdin argument should be a string to be - sent to the child process, or None, if no data should be sent to - the child. - - communicate() returns a tuple (stdout, stderr). - - Note: The data read is buffered in memory, so do not use this - method if the data size is large or unlimited. - -The following attributes are also available: - -stdin - If the stdin argument is PIPE, this attribute is a file object - that provides input to the child process. Otherwise, it is None. - -stdout - If the stdout argument is PIPE, this attribute is a file object - that provides output from the child process. Otherwise, it is - None. - -stderr - If the stderr argument is PIPE, this attribute is file object that - provides error output from the child process. Otherwise, it is - None. - -pid - The process ID of the child process. - -returncode - The child return code. A None value indicates that the process - hasn't terminated yet. A negative value -N indicates that the - child was terminated by signal N (UNIX only). - - -Replacing older functions with the subprocess module -==================================================== -In this section, "a ==> b" means that b can be used as a replacement -for a. - -Note: All functions in this section fail (more or less) silently if -the executed program cannot be found; this module raises an OSError -exception. - -In the following examples, we assume that the subprocess module is -imported with "from subprocess import *". - - -Replacing /bin/sh shell backquote ---------------------------------- -output=`mycmd myarg` -==> -output = Popen(["mycmd", "myarg"], stdout=PIPE).communicate()[0] - - -Replacing shell pipe line -------------------------- -output=`dmesg | grep hda` -==> -p1 = Popen(["dmesg"], stdout=PIPE) -p2 = Popen(["grep", "hda"], stdin=p1.stdout, stdout=PIPE) -output = p2.communicate()[0] - - -Replacing os.system() ---------------------- -sts = os.system("mycmd" + " myarg") -==> -p = Popen("mycmd" + " myarg", shell=True) -sts = os.waitpid(p.pid, 0) - -Note: - -* Calling the program through the shell is usually not required. - -* It's easier to look at the returncode attribute than the - exitstatus. - -A more real-world example would look like this: - -try: - retcode = call("mycmd" + " myarg", shell=True) - if retcode < 0: - print >>sys.stderr, "Child was terminated by signal", -retcode - else: - print >>sys.stderr, "Child returned", retcode -except OSError, e: - print >>sys.stderr, "Execution failed:", e - - -Replacing os.spawn* -------------------- -P_NOWAIT example: - -pid = os.spawnlp(os.P_NOWAIT, "/bin/mycmd", "mycmd", "myarg") -==> -pid = Popen(["/bin/mycmd", "myarg"]).pid - - -P_WAIT example: - -retcode = os.spawnlp(os.P_WAIT, "/bin/mycmd", "mycmd", "myarg") -==> -retcode = call(["/bin/mycmd", "myarg"]) - - -Vector example: - -os.spawnvp(os.P_NOWAIT, path, args) -==> -Popen([path] + args[1:]) - - -Environment example: - -os.spawnlpe(os.P_NOWAIT, "/bin/mycmd", "mycmd", "myarg", env) -==> -Popen(["/bin/mycmd", "myarg"], env={"PATH": "/usr/bin"}) - - -Replacing os.popen* -------------------- -pipe = os.popen(cmd, mode='r', bufsize) -==> -pipe = Popen(cmd, shell=True, bufsize=bufsize, stdout=PIPE).stdout - -pipe = os.popen(cmd, mode='w', bufsize) -==> -pipe = Popen(cmd, shell=True, bufsize=bufsize, stdin=PIPE).stdin - - -(child_stdin, child_stdout) = os.popen2(cmd, mode, bufsize) -==> -p = Popen(cmd, shell=True, bufsize=bufsize, - stdin=PIPE, stdout=PIPE, close_fds=True) -(child_stdin, child_stdout) = (p.stdin, p.stdout) - - -(child_stdin, - child_stdout, - child_stderr) = os.popen3(cmd, mode, bufsize) -==> -p = Popen(cmd, shell=True, bufsize=bufsize, - stdin=PIPE, stdout=PIPE, stderr=PIPE, close_fds=True) -(child_stdin, - child_stdout, - child_stderr) = (p.stdin, p.stdout, p.stderr) - - -(child_stdin, child_stdout_and_stderr) = os.popen4(cmd, mode, bufsize) -==> -p = Popen(cmd, shell=True, bufsize=bufsize, - stdin=PIPE, stdout=PIPE, stderr=STDOUT, close_fds=True) -(child_stdin, child_stdout_and_stderr) = (p.stdin, p.stdout) - - -Replacing popen2.* ------------------- -Note: If the cmd argument to popen2 functions is a string, the command -is executed through /bin/sh. If it is a list, the command is directly -executed. - -(child_stdout, child_stdin) = popen2.popen2("somestring", bufsize, mode) -==> -p = Popen(["somestring"], shell=True, bufsize=bufsize - stdin=PIPE, stdout=PIPE, close_fds=True) -(child_stdout, child_stdin) = (p.stdout, p.stdin) - - -(child_stdout, child_stdin) = popen2.popen2(["mycmd", "myarg"], bufsize, mode) -==> -p = Popen(["mycmd", "myarg"], bufsize=bufsize, - stdin=PIPE, stdout=PIPE, close_fds=True) -(child_stdout, child_stdin) = (p.stdout, p.stdin) - -The popen2.Popen3 and popen3.Popen4 basically works as subprocess.Popen, -except that: - -* subprocess.Popen raises an exception if the execution fails -* the capturestderr argument is replaced with the stderr argument. -* stdin=PIPE and stdout=PIPE must be specified. -* popen2 closes all filedescriptors by default, but you have to specify - close_fds=True with subprocess.Popen. - - -""" - -import sys -mswindows = (sys.platform == "win32") - -import os -import types -import traceback - -if mswindows: - import threading - import msvcrt - if 0: # <-- change this to use pywin32 instead of the _subprocess driver - import pywintypes - from win32api import GetStdHandle, STD_INPUT_HANDLE, \ - STD_OUTPUT_HANDLE, STD_ERROR_HANDLE - from win32api import GetCurrentProcess, DuplicateHandle, \ - GetModuleFileName, GetVersion - from win32con import DUPLICATE_SAME_ACCESS, SW_HIDE - from win32pipe import CreatePipe - from win32process import CreateProcess, STARTUPINFO, \ - GetExitCodeProcess, STARTF_USESTDHANDLES, \ - STARTF_USESHOWWINDOW, CREATE_NEW_CONSOLE - from win32event import WaitForSingleObject, INFINITE, WAIT_OBJECT_0 - else: - from _subprocess import * - class STARTUPINFO: - dwFlags = 0 - hStdInput = None - hStdOutput = None - hStdError = None - class pywintypes: - error = IOError -else: - import select - import errno - import fcntl - import pickle - -__all__ = ["Popen", "PIPE", "STDOUT", "call"] - -try: - MAXFD = os.sysconf("SC_OPEN_MAX") -except: - MAXFD = 256 - -# True/False does not exist on 2.2.0 -try: - False -except NameError: - False = 0 - True = 1 - -_active = [] - -def _cleanup(): - for inst in _active[:]: - inst.poll() - -PIPE = -1 -STDOUT = -2 - - -def call(*args, **kwargs): - """Run command with arguments. Wait for command to complete, then - return the returncode attribute. - - The arguments are the same as for the Popen constructor. Example: - - retcode = call(["ls", "-l"]) - """ - return Popen(*args, **kwargs).wait() - - -def list2cmdline(seq): - """ - Translate a sequence of arguments into a command line - string, using the same rules as the MS C runtime: - - 1) Arguments are delimited by white space, which is either a - space or a tab. - - 2) A string surrounded by double quotation marks is - interpreted as a single argument, regardless of white space - contained within. A quoted string can be embedded in an - argument. - - 3) A double quotation mark preceded by a backslash is - interpreted as a literal double quotation mark. - - 4) Backslashes are interpreted literally, unless they - immediately precede a double quotation mark. - - 5) If backslashes immediately precede a double quotation mark, - every pair of backslashes is interpreted as a literal - backslash. If the number of backslashes is odd, the last - backslash escapes the next double quotation mark as - described in rule 3. - """ - - # See - # http://msdn.microsoft.com/library/en-us/vccelng/htm/progs_12.asp - result = [] - needquote = False - for arg in seq: - bs_buf = [] - - # Add a space to separate this argument from the others - if result: - result.append(' ') - - needquote = (" " in arg) or ("\t" in arg) - if needquote: - result.append('"') - - for c in arg: - if c == '\\': - # Don't know if we need to double yet. - bs_buf.append(c) - elif c == '"': - # Double backspaces. - result.append('\\' * len(bs_buf)*2) - bs_buf = [] - result.append('\\"') - else: - # Normal char - if bs_buf: - result.extend(bs_buf) - bs_buf = [] - result.append(c) - - # Add remaining backspaces, if any. - if bs_buf: - result.extend(bs_buf) - - if needquote: - result.extend(bs_buf) - result.append('"') - - return ''.join(result) - - -class Popen(object): - def __init__(self, args, bufsize=0, executable=None, - stdin=None, stdout=None, stderr=None, - preexec_fn=None, close_fds=False, shell=False, - cwd=None, env=None, universal_newlines=False, - startupinfo=None, creationflags=0): - """Create new Popen instance.""" - _cleanup() - - if not isinstance(bufsize, (int, long)): - raise TypeError("bufsize must be an integer") - - if mswindows: - if preexec_fn is not None: - raise ValueError("preexec_fn is not supported on Windows " - "platforms") - if close_fds: - raise ValueError("close_fds is not supported on Windows " - "platforms") - else: - # POSIX - if startupinfo is not None: - raise ValueError("startupinfo is only supported on Windows " - "platforms") - if creationflags != 0: - raise ValueError("creationflags is only supported on Windows " - "platforms") - - self.stdin = None - self.stdout = None - self.stderr = None - self.pid = None - self.returncode = None - self.universal_newlines = universal_newlines - - # Input and output objects. The general principle is like - # this: - # - # Parent Child - # ------ ----- - # p2cwrite ---stdin---> p2cread - # c2pread <--stdout--- c2pwrite - # errread <--stderr--- errwrite - # - # On POSIX, the child objects are file descriptors. On - # Windows, these are Windows file handles. The parent objects - # are file descriptors on both platforms. The parent objects - # are None when not using PIPEs. The child objects are None - # when not redirecting. - - (p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite) = self._get_handles(stdin, stdout, stderr) - - self._execute_child(args, executable, preexec_fn, close_fds, - cwd, env, universal_newlines, - startupinfo, creationflags, shell, - p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite) - - if p2cwrite: - self.stdin = os.fdopen(p2cwrite, 'wb', bufsize) - if c2pread: - if universal_newlines: - self.stdout = os.fdopen(c2pread, 'rU', bufsize) - else: - self.stdout = os.fdopen(c2pread, 'rb', bufsize) - if errread: - if universal_newlines: - self.stderr = os.fdopen(errread, 'rU', bufsize) - else: - self.stderr = os.fdopen(errread, 'rb', bufsize) - - _active.append(self) - - - def _translate_newlines(self, data): - data = data.replace("\r\n", "\n") - data = data.replace("\r", "\n") - return data - - - if mswindows: - # - # Windows methods - # - def _get_handles(self, stdin, stdout, stderr): - """Construct and return tuple with IO objects: - p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite - """ - if stdin == None and stdout == None and stderr == None: - return (None, None, None, None, None, None) - - p2cread, p2cwrite = None, None - c2pread, c2pwrite = None, None - errread, errwrite = None, None - - if stdin == None: - p2cread = GetStdHandle(STD_INPUT_HANDLE) - elif stdin == PIPE: - p2cread, p2cwrite = CreatePipe(None, 0) - # Detach and turn into fd - p2cwrite = p2cwrite.Detach() - p2cwrite = msvcrt.open_osfhandle(p2cwrite, 0) - elif type(stdin) == types.IntType: - p2cread = msvcrt.get_osfhandle(stdin) - else: - # Assuming file-like object - p2cread = msvcrt.get_osfhandle(stdin.fileno()) - p2cread = self._make_inheritable(p2cread) - - if stdout == None: - c2pwrite = GetStdHandle(STD_OUTPUT_HANDLE) - elif stdout == PIPE: - c2pread, c2pwrite = CreatePipe(None, 0) - # Detach and turn into fd - c2pread = c2pread.Detach() - c2pread = msvcrt.open_osfhandle(c2pread, 0) - elif type(stdout) == types.IntType: - c2pwrite = msvcrt.get_osfhandle(stdout) - else: - # Assuming file-like object - c2pwrite = msvcrt.get_osfhandle(stdout.fileno()) - c2pwrite = self._make_inheritable(c2pwrite) - - if stderr == None: - errwrite = GetStdHandle(STD_ERROR_HANDLE) - elif stderr == PIPE: - errread, errwrite = CreatePipe(None, 0) - # Detach and turn into fd - errread = errread.Detach() - errread = msvcrt.open_osfhandle(errread, 0) - elif stderr == STDOUT: - errwrite = c2pwrite - elif type(stderr) == types.IntType: - errwrite = msvcrt.get_osfhandle(stderr) - else: - # Assuming file-like object - errwrite = msvcrt.get_osfhandle(stderr.fileno()) - errwrite = self._make_inheritable(errwrite) - - return (p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite) - - - def _make_inheritable(self, handle): - """Return a duplicate of handle, which is inheritable""" - return DuplicateHandle(GetCurrentProcess(), handle, - GetCurrentProcess(), 0, 1, - DUPLICATE_SAME_ACCESS) - - - def _find_w9xpopen(self): - """Find and return absolute path to w9xpopen.exe""" - w9xpopen = os.path.join(os.path.dirname(GetModuleFileName(0)), - "w9xpopen.exe") - if not os.path.exists(w9xpopen): - # Eeek - file-not-found - possibly an embedding - # situation - see if we can locate it in sys.exec_prefix - w9xpopen = os.path.join(os.path.dirname(sys.exec_prefix), - "w9xpopen.exe") - if not os.path.exists(w9xpopen): - raise RuntimeError("Cannot locate w9xpopen.exe, which is " - "needed for Popen to work with your " - "shell or platform.") - return w9xpopen - - - def _execute_child(self, args, executable, preexec_fn, close_fds, - cwd, env, universal_newlines, - startupinfo, creationflags, shell, - p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite): - """Execute program (MS Windows version)""" - - if not isinstance(args, types.StringTypes): - args = list2cmdline(args) - - # Process startup details - default_startupinfo = STARTUPINFO() - if startupinfo == None: - startupinfo = default_startupinfo - if not None in (p2cread, c2pwrite, errwrite): - startupinfo.dwFlags |= STARTF_USESTDHANDLES - startupinfo.hStdInput = p2cread - startupinfo.hStdOutput = c2pwrite - startupinfo.hStdError = errwrite - - if shell: - default_startupinfo.dwFlags |= STARTF_USESHOWWINDOW - default_startupinfo.wShowWindow = SW_HIDE - comspec = os.environ.get("COMSPEC", "cmd.exe") - args = comspec + " /c " + args - if (GetVersion() >= 0x80000000L or - os.path.basename(comspec).lower() == "command.com"): - # Win9x, or using command.com on NT. We need to - # use the w9xpopen intermediate program. For more - # information, see KB Q150956 - # (http://web.archive.org/web/20011105084002/http://support.microsoft.com/support/kb/articles/Q150/9/56.asp) - w9xpopen = self._find_w9xpopen() - args = '"%s" %s' % (w9xpopen, args) - # Not passing CREATE_NEW_CONSOLE has been known to - # cause random failures on win9x. Specifically a - # dialog: "Your program accessed mem currently in - # use at xxx" and a hopeful warning about the - # stability of your system. Cost is Ctrl+C wont - # kill children. - creationflags |= CREATE_NEW_CONSOLE - - # Start the process - try: - hp, ht, pid, tid = CreateProcess(executable, args, - # no special security - None, None, - # must inherit handles to pass std - # handles - 1, - creationflags, - env, - cwd, - startupinfo) - except pywintypes.error, e: - # Translate pywintypes.error to WindowsError, which is - # a subclass of OSError. FIXME: We should really - # translate errno using _sys_errlist (or simliar), but - # how can this be done from Python? - raise WindowsError(*e.args) - - # Retain the process handle, but close the thread handle - self._handle = hp - self.pid = pid - ht.Close() - - # Child is launched. Close the parent's copy of those pipe - # handles that only the child should have open. You need - # to make sure that no handles to the write end of the - # output pipe are maintained in this process or else the - # pipe will not close when the child process exits and the - # ReadFile will hang. - if p2cread != None: - p2cread.Close() - if c2pwrite != None: - c2pwrite.Close() - if errwrite != None: - errwrite.Close() - - - def poll(self): - """Check if child process has terminated. Returns returncode - attribute.""" - if self.returncode == None: - if WaitForSingleObject(self._handle, 0) == WAIT_OBJECT_0: - self.returncode = GetExitCodeProcess(self._handle) - _active.remove(self) - return self.returncode - - - def wait(self): - """Wait for child process to terminate. Returns returncode - attribute.""" - if self.returncode == None: - obj = WaitForSingleObject(self._handle, INFINITE) - self.returncode = GetExitCodeProcess(self._handle) - _active.remove(self) - return self.returncode - - - def _readerthread(self, fh, buffer): - buffer.append(fh.read()) - - - def communicate(self, input=None): - """Interact with process: Send data to stdin. Read data from - stdout and stderr, until end-of-file is reached. Wait for - process to terminate. The optional input argument should be a - string to be sent to the child process, or None, if no data - should be sent to the child. - - communicate() returns a tuple (stdout, stderr).""" - stdout = None # Return - stderr = None # Return - - if self.stdout: - stdout = [] - stdout_thread = threading.Thread(target=self._readerthread, - args=(self.stdout, stdout)) - stdout_thread.setDaemon(True) - stdout_thread.start() - if self.stderr: - stderr = [] - stderr_thread = threading.Thread(target=self._readerthread, - args=(self.stderr, stderr)) - stderr_thread.setDaemon(True) - stderr_thread.start() - - if self.stdin: - if input != None: - self.stdin.write(input) - self.stdin.close() - - if self.stdout: - stdout_thread.join() - if self.stderr: - stderr_thread.join() - - # All data exchanged. Translate lists into strings. - if stdout != None: - stdout = stdout[0] - if stderr != None: - stderr = stderr[0] - - # Translate newlines, if requested. We cannot let the file - # object do the translation: It is based on stdio, which is - # impossible to combine with select (unless forcing no - # buffering). - if self.universal_newlines and hasattr(open, 'newlines'): - if stdout: - stdout = self._translate_newlines(stdout) - if stderr: - stderr = self._translate_newlines(stderr) - - self.wait() - return (stdout, stderr) - - else: - # - # POSIX methods - # - def _get_handles(self, stdin, stdout, stderr): - """Construct and return tuple with IO objects: - p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite - """ - p2cread, p2cwrite = None, None - c2pread, c2pwrite = None, None - errread, errwrite = None, None - - if stdin == None: - pass - elif stdin == PIPE: - p2cread, p2cwrite = os.pipe() - elif type(stdin) == types.IntType: - p2cread = stdin - else: - # Assuming file-like object - p2cread = stdin.fileno() - - if stdout == None: - pass - elif stdout == PIPE: - c2pread, c2pwrite = os.pipe() - elif type(stdout) == types.IntType: - c2pwrite = stdout - else: - # Assuming file-like object - c2pwrite = stdout.fileno() - - if stderr == None: - pass - elif stderr == PIPE: - errread, errwrite = os.pipe() - elif stderr == STDOUT: - errwrite = c2pwrite - elif type(stderr) == types.IntType: - errwrite = stderr - else: - # Assuming file-like object - errwrite = stderr.fileno() - - return (p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite) - - - def _set_cloexec_flag(self, fd): - try: - cloexec_flag = fcntl.FD_CLOEXEC - except AttributeError: - cloexec_flag = 1 - - old = fcntl.fcntl(fd, fcntl.F_GETFD) - fcntl.fcntl(fd, fcntl.F_SETFD, old | cloexec_flag) - - - def _close_fds(self, but): - for i in range(3, MAXFD): - if i == but: - continue - try: - os.close(i) - except: - pass - - - def _execute_child(self, args, executable, preexec_fn, close_fds, - cwd, env, universal_newlines, - startupinfo, creationflags, shell, - p2cread, p2cwrite, - c2pread, c2pwrite, - errread, errwrite): - """Execute program (POSIX version)""" - - if isinstance(args, types.StringTypes): - args = [args] - - if shell: - args = ["/bin/sh", "-c"] + args - - if executable == None: - executable = args[0] - - # For transferring possible exec failure from child to parent - # The first char specifies the exception type: 0 means - # OSError, 1 means some other error. - errpipe_read, errpipe_write = os.pipe() - self._set_cloexec_flag(errpipe_write) - - self.pid = os.fork() - if self.pid == 0: - # Child - try: - # Close parent's pipe ends - if p2cwrite: - os.close(p2cwrite) - if c2pread: - os.close(c2pread) - if errread: - os.close(errread) - os.close(errpipe_read) - - # Dup fds for child - if p2cread: - os.dup2(p2cread, 0) - if c2pwrite: - os.dup2(c2pwrite, 1) - if errwrite: - os.dup2(errwrite, 2) - - # Close pipe fds. Make sure we doesn't close the same - # fd more than once. - if p2cread: - os.close(p2cread) - if c2pwrite and c2pwrite not in (p2cread,): - os.close(c2pwrite) - if errwrite and errwrite not in (p2cread, c2pwrite): - os.close(errwrite) - - # Close all other fds, if asked for - if close_fds: - self._close_fds(but=errpipe_write) - - if cwd != None: - os.chdir(cwd) - - if preexec_fn: - apply(preexec_fn) - - if env == None: - os.execvp(executable, args) - else: - os.execvpe(executable, args, env) - - except: - exc_type, exc_value, tb = sys.exc_info() - # Save the traceback and attach it to the exception object - exc_lines = traceback.format_exception(exc_type, - exc_value, - tb) - exc_value.child_traceback = ''.join(exc_lines) - os.write(errpipe_write, pickle.dumps(exc_value)) - - # This exitcode won't be reported to applications, so it - # really doesn't matter what we return. - os._exit(255) - - # Parent - os.close(errpipe_write) - if p2cread and p2cwrite: - os.close(p2cread) - if c2pwrite and c2pread: - os.close(c2pwrite) - if errwrite and errread: - os.close(errwrite) - - # Wait for exec to fail or succeed; possibly raising exception - data = os.read(errpipe_read, 1048576) # Exceptions limited to 1 MB - os.close(errpipe_read) - if data != "": - os.waitpid(self.pid, 0) - child_exception = pickle.loads(data) - raise child_exception - - - def _handle_exitstatus(self, sts): - if os.WIFSIGNALED(sts): - self.returncode = -os.WTERMSIG(sts) - elif os.WIFEXITED(sts): - self.returncode = os.WEXITSTATUS(sts) - else: - # Should never happen - raise RuntimeError("Unknown child exit status!") - - _active.remove(self) - - - def poll(self): - """Check if child process has terminated. Returns returncode - attribute.""" - if self.returncode == None: - try: - pid, sts = os.waitpid(self.pid, os.WNOHANG) - if pid == self.pid: - self._handle_exitstatus(sts) - except os.error: - pass - return self.returncode - - - def wait(self): - """Wait for child process to terminate. Returns returncode - attribute.""" - if self.returncode == None: - pid, sts = os.waitpid(self.pid, 0) - self._handle_exitstatus(sts) - return self.returncode - - - def communicate(self, input=None): - """Interact with process: Send data to stdin. Read data from - stdout and stderr, until end-of-file is reached. Wait for - process to terminate. The optional input argument should be a - string to be sent to the child process, or None, if no data - should be sent to the child. - - communicate() returns a tuple (stdout, stderr).""" - read_set = [] - write_set = [] - stdout = None # Return - stderr = None # Return - - if self.stdin: - # Flush stdio buffer. This might block, if the user has - # been writing to .stdin in an uncontrolled fashion. - self.stdin.flush() - if input: - write_set.append(self.stdin) - else: - self.stdin.close() - if self.stdout: - read_set.append(self.stdout) - stdout = [] - if self.stderr: - read_set.append(self.stderr) - stderr = [] - - while read_set or write_set: - rlist, wlist, xlist = select.select(read_set, write_set, []) - - if self.stdin in wlist: - # When select has indicated that the file is writable, - # we can write up to PIPE_BUF bytes without risk - # blocking. POSIX defines PIPE_BUF >= 512 - bytes_written = os.write(self.stdin.fileno(), input[:512]) - input = input[bytes_written:] - if not input: - self.stdin.close() - write_set.remove(self.stdin) - - if self.stdout in rlist: - data = os.read(self.stdout.fileno(), 1024) - if data == "": - self.stdout.close() - read_set.remove(self.stdout) - stdout.append(data) - - if self.stderr in rlist: - data = os.read(self.stderr.fileno(), 1024) - if data == "": - self.stderr.close() - read_set.remove(self.stderr) - stderr.append(data) - - # All data exchanged. Translate lists into strings. - if stdout != None: - stdout = ''.join(stdout) - if stderr != None: - stderr = ''.join(stderr) - - # Translate newlines, if requested. We cannot let the file - # object do the translation: It is based on stdio, which is - # impossible to combine with select (unless forcing no - # buffering). - if self.universal_newlines and hasattr(open, 'newlines'): - if stdout: - stdout = self._translate_newlines(stdout) - if stderr: - stderr = self._translate_newlines(stderr) - - self.wait() - return (stdout, stderr) - - -def _demo_posix(): - # - # Example 1: Simple redirection: Get process list - # - plist = Popen(["ps"], stdout=PIPE).communicate()[0] - print "Process list:" - print plist - - # - # Example 2: Change uid before executing child - # - if os.getuid() == 0: - p = Popen(["id"], preexec_fn=lambda: os.setuid(100)) - p.wait() - - # - # Example 3: Connecting several subprocesses - # - print "Looking for 'hda'..." - p1 = Popen(["dmesg"], stdout=PIPE) - p2 = Popen(["grep", "hda"], stdin=p1.stdout, stdout=PIPE) - print repr(p2.communicate()[0]) - - # - # Example 4: Catch execution error - # - print - print "Trying a weird file..." - try: - print Popen(["/this/path/does/not/exist"]).communicate() - except OSError, e: - if e.errno == errno.ENOENT: - print "The file didn't exist. I thought so..." - print "Child traceback:" - print e.child_traceback - else: - print "Error", e.errno - else: - print >>sys.stderr, "Gosh. No error." - - -def _demo_windows(): - # - # Example 1: Connecting several subprocesses - # - print "Looking for 'PROMPT' in set output..." - p1 = Popen("set", stdout=PIPE, shell=True) - p2 = Popen('find "PROMPT"', stdin=p1.stdout, stdout=PIPE) - print repr(p2.communicate()[0]) - - # - # Example 2: Simple execution of program - # - print "Executing calc..." - p = Popen("calc") - p.wait() - - -if __name__ == "__main__": - if mswindows: - _demo_windows() - else: - _demo_posix() diff --git a/compat/unsetenv.c b/compat/unsetenv.c index 3a5e4ec04a..eb29f5e084 100644 --- a/compat/unsetenv.c +++ b/compat/unsetenv.c @@ -1,5 +1,4 @@ -#include <stdlib.h> -#include <string.h> +#include "../git-compat-util.h" void gitunsetenv (const char *name) { @@ -6,7 +6,6 @@ * */ #include "cache.h" -#include <regex.h> #define MAXNAME (256) @@ -103,6 +102,11 @@ static char *parse_value(void) } } +static inline int iskeychar(int c) +{ + return isalnum(c) || c == '-'; +} + static int get_value(config_fn_t fn, char *name, unsigned int len) { int c; @@ -113,7 +117,7 @@ static int get_value(config_fn_t fn, char *name, unsigned int len) c = get_next_char(); if (c == EOF) break; - if (!isalnum(c)) + if (!iskeychar(c)) break; name[len++] = tolower(c); if (len >= MAXNAME) @@ -181,7 +185,7 @@ static int get_base_var(char *name) return baselen; if (isspace(c)) return get_extended_base_var(name, baselen, c); - if (!isalnum(c) && c != '.') + if (!iskeychar(c) && c != '.') return -1; if (baselen > MAXNAME / 2) return -1; @@ -234,6 +238,12 @@ int git_config_int(const char *name, const char *value) int val = strtol(value, &end, 0); if (!*end) return val; + if (!strcasecmp(end, "k")) + return val * 1024; + if (!strcasecmp(end, "m")) + return val * 1024 * 1024; + if (!strcasecmp(end, "g")) + return val * 1024 * 1024 * 1024; } die("bad config value for '%s' in %s", name, config_file_name); } @@ -259,6 +269,11 @@ int git_default_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.bare")) { + is_bare_repository_cfg = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "core.ignorestat")) { assume_unchanged = git_config_bool(var, value); return 0; @@ -294,6 +309,21 @@ int git_default_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.packedgitwindowsize")) { + int pgsz = getpagesize(); + packed_git_window_size = git_config_int(var, value); + packed_git_window_size /= pgsz; + if (packed_git_window_size < 2) + packed_git_window_size = 2; + packed_git_window_size *= pgsz; + return 0; + } + + if (!strcmp(var, "core.packedgitlimit")) { + packed_git_limit = git_config_int(var, value); + return 0; + } + if (!strcmp(var, "user.name")) { strlcpy(git_default_name, value, sizeof(git_default_name)); return 0; @@ -305,11 +335,17 @@ int git_default_config(const char *var, const char *value) } if (!strcmp(var, "i18n.commitencoding")) { - strlcpy(git_commit_encoding, value, sizeof(git_commit_encoding)); + git_commit_encoding = strdup(value); + return 0; + } + + if (!strcmp(var, "i18n.logoutputencoding")) { + git_log_output_encoding = strdup(value); return 0; } - if (!strcmp(var, "pager.color")) { + + if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) { pager_use_color = git_config_bool(var,value); return 0; } @@ -345,24 +381,23 @@ int git_config(config_fn_t fn) * $GIT_CONFIG_LOCAL will make it process it in addition to the * global config file, the same way it would the per-repository * config file otherwise. */ - filename = getenv("GIT_CONFIG"); + filename = getenv(CONFIG_ENVIRONMENT); if (!filename) { home = getenv("HOME"); - filename = getenv("GIT_CONFIG_LOCAL"); + filename = getenv(CONFIG_LOCAL_ENVIRONMENT); if (!filename) - filename = repo_config = strdup(git_path("config")); + filename = repo_config = xstrdup(git_path("config")); } if (home) { - char *user_config = strdup(mkpath("%s/.gitconfig", home)); + char *user_config = xstrdup(mkpath("%s/.gitconfig", home)); if (!access(user_config, R_OK)) ret = git_config_from_file(fn, user_config); free(user_config); } ret += git_config_from_file(fn, filename); - if (repo_config) - free(repo_config); + free(repo_config); return ret; } @@ -434,7 +469,15 @@ static int store_aux(const char* key, const char* value) return 0; } -static void store_write_section(int fd, const char* key) +static int write_error() +{ + fprintf(stderr, "Failed to write new configuration file\n"); + + /* Same error code as "failed to rename". */ + return 4; +} + +static int store_write_section(int fd, const char* key) { const char *dot = strchr(key, '.'); int len1 = store.baselen, len2 = -1; @@ -448,37 +491,74 @@ static void store_write_section(int fd, const char* key) } } - write(fd, "[", 1); - write(fd, key, len1); + if (write_in_full(fd, "[", 1) != 1 || + write_in_full(fd, key, len1) != len1) + return 0; if (len2 >= 0) { - write(fd, " \"", 2); + if (write_in_full(fd, " \"", 2) != 2) + return 0; while (--len2 >= 0) { unsigned char c = *++dot; if (c == '"') - write(fd, "\\", 1); - write(fd, &c, 1); + if (write_in_full(fd, "\\", 1) != 1) + return 0; + if (write_in_full(fd, &c, 1) != 1) + return 0; } - write(fd, "\"", 1); + if (write_in_full(fd, "\"", 1) != 1) + return 0; } - write(fd, "]\n", 2); + if (write_in_full(fd, "]\n", 2) != 2) + return 0; + + return 1; } -static void store_write_pair(int fd, const char* key, const char* value) +static int store_write_pair(int fd, const char* key, const char* value) { int i; + int length = strlen(key+store.baselen+1); + int quote = 0; - write(fd, "\t", 1); - write(fd, key+store.baselen+1, - strlen(key+store.baselen+1)); - write(fd, " = ", 3); + /* Check to see if the value needs to be quoted. */ + if (value[0] == ' ') + quote = 1; + for (i = 0; value[i]; i++) + if (value[i] == ';' || value[i] == '#') + quote = 1; + if (value[i-1] == ' ') + quote = 1; + + if (write_in_full(fd, "\t", 1) != 1 || + write_in_full(fd, key+store.baselen+1, length) != length || + write_in_full(fd, " = ", 3) != 3) + return 0; + if (quote && write_in_full(fd, "\"", 1) != 1) + return 0; for (i = 0; value[i]; i++) switch (value[i]) { - case '\n': write(fd, "\\n", 2); break; - case '\t': write(fd, "\\t", 2); break; - case '"': case '\\': write(fd, "\\", 1); - default: write(fd, value+i, 1); - } - write(fd, "\n", 1); + case '\n': + if (write_in_full(fd, "\\n", 2) != 2) + return 0; + break; + case '\t': + if (write_in_full(fd, "\\t", 2) != 2) + return 0; + break; + case '"': + case '\\': + if (write_in_full(fd, "\\", 1) != 1) + return 0; + default: + if (write_in_full(fd, value+i, 1) != 1) + return 0; + break; + } + if (quote && write_in_full(fd, "\"", 1) != 1) + return 0; + if (write_in_full(fd, "\n", 1) != 1) + return 0; + return 1; } static int find_beginning_of_line(const char* contents, int size, @@ -540,14 +620,14 @@ int git_config_set_multivar(const char* key, const char* value, char* lock_file; const char* last_dot = strrchr(key, '.'); - config_filename = getenv("GIT_CONFIG"); + config_filename = getenv(CONFIG_ENVIRONMENT); if (!config_filename) { - config_filename = getenv("GIT_CONFIG_LOCAL"); + config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT); if (!config_filename) config_filename = git_path("config"); } - config_filename = strdup(config_filename); - lock_file = strdup(mkpath("%s.lock", config_filename)); + config_filename = xstrdup(config_filename); + lock_file = xstrdup(mkpath("%s.lock", config_filename)); /* * Since "key" actually contains the section name and the real @@ -566,7 +646,7 @@ int git_config_set_multivar(const char* key, const char* value, /* * Validate the key and while at it, lower case it for matching. */ - store.key = (char*)malloc(strlen(key)+1); + store.key = xmalloc(strlen(key) + 1); dot = 0; for (i = 0; key[i]; i++) { unsigned char c = key[i]; @@ -574,7 +654,7 @@ int git_config_set_multivar(const char* key, const char* value, dot = 1; /* Leave the extended basename untouched.. */ if (!dot || i > store.baselen) { - if (!isalnum(c) || (i == store.baselen+1 && !isalpha(c))) { + if (!iskeychar(c) || (i == store.baselen+1 && !isalpha(c))) { fprintf(stderr, "invalid key: %s\n", key); free(store.key); ret = 1; @@ -618,9 +698,10 @@ int git_config_set_multivar(const char* key, const char* value, } store.key = (char*)key; - store_write_section(fd, key); - store_write_pair(fd, key, value); - } else{ + if (!store_write_section(fd, key) || + !store_write_pair(fd, key, value)) + goto write_err_out; + } else { struct stat st; char* contents; int i, copy_begin, copy_end, new_line = 0; @@ -634,7 +715,7 @@ int git_config_set_multivar(const char* key, const char* value, } else store.do_not_match = 0; - store.value_regex = (regex_t*)malloc(sizeof(regex_t)); + store.value_regex = (regex_t*)xmalloc(sizeof(regex_t)); if (regcomp(store.value_regex, value_regex, REG_EXTENDED)) { fprintf(stderr, "Invalid pattern: %s\n", @@ -680,7 +761,7 @@ int git_config_set_multivar(const char* key, const char* value, } fstat(in_fd, &st); - contents = mmap(NULL, st.st_size, PROT_READ, + contents = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, in_fd, 0); close(in_fd); @@ -699,25 +780,33 @@ int git_config_set_multivar(const char* key, const char* value, /* write the first part of the config */ if (copy_end > copy_begin) { - write(fd, contents + copy_begin, - copy_end - copy_begin); - if (new_line) - write(fd, "\n", 1); + if (write_in_full(fd, contents + copy_begin, + copy_end - copy_begin) < + copy_end - copy_begin) + goto write_err_out; + if (new_line && + write_in_full(fd, "\n", 1) != 1) + goto write_err_out; } copy_begin = store.offset[i]; } /* write the pair (value == NULL means unset) */ if (value != NULL) { - if (store.state == START) - store_write_section(fd, key); - store_write_pair(fd, key, value); + if (store.state == START) { + if (!store_write_section(fd, key)) + goto write_err_out; + } + if (!store_write_pair(fd, key, value)) + goto write_err_out; } /* write the rest of the config */ if (copy_begin < st.st_size) - write(fd, contents + copy_begin, - st.st_size - copy_begin); + if (write_in_full(fd, contents + copy_begin, + st.st_size - copy_begin) < + st.st_size - copy_begin) + goto write_err_out; munmap(contents, st.st_size); unlink(config_filename); @@ -734,13 +823,96 @@ int git_config_set_multivar(const char* key, const char* value, out_free: if (0 <= fd) close(fd); - if (config_filename) - free(config_filename); + free(config_filename); if (lock_file) { unlink(lock_file); free(lock_file); } return ret; + +write_err_out: + ret = write_error(); + goto out_free; + } +int git_config_rename_section(const char *old_name, const char *new_name) +{ + int ret = 0; + char *config_filename; + struct lock_file *lock = xcalloc(sizeof(struct lock_file), 1); + int out_fd; + char buf[1024]; + + config_filename = getenv(CONFIG_ENVIRONMENT); + if (!config_filename) { + config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT); + if (!config_filename) + config_filename = git_path("config"); + } + config_filename = xstrdup(config_filename); + out_fd = hold_lock_file_for_update(lock, config_filename, 0); + if (out_fd < 0) { + ret = error("Could not lock config file!"); + goto out; + } + + if (!(config_file = fopen(config_filename, "rb"))) { + ret = error("Could not open config file!"); + goto out; + } + + while (fgets(buf, sizeof(buf), config_file)) { + int i; + int length; + for (i = 0; buf[i] && isspace(buf[i]); i++) + ; /* do nothing */ + if (buf[i] == '[') { + /* it's a section */ + int j = 0, dot = 0; + for (i++; buf[i] && buf[i] != ']'; i++) { + if (!dot && isspace(buf[i])) { + dot = 1; + if (old_name[j++] != '.') + break; + for (i++; isspace(buf[i]); i++) + ; /* do nothing */ + if (buf[i] != '"') + break; + continue; + } + if (buf[i] == '\\' && dot) + i++; + else if (buf[i] == '"' && dot) { + for (i++; isspace(buf[i]); i++) + ; /* do_nothing */ + break; + } + if (buf[i] != old_name[j++]) + break; + } + if (buf[i] == ']') { + /* old_name matches */ + ret++; + store.baselen = strlen(new_name); + if (!store_write_section(out_fd, new_name)) { + ret = write_error(); + goto out; + } + continue; + } + } + length = strlen(buf); + if (write_in_full(out_fd, buf, length) != length) { + ret = write_error(); + goto out; + } + } + fclose(config_file); + if (close(out_fd) || commit_lock_file(lock) < 0) + ret = error("Cannot commit config file!"); + out: + free(config_filename); + return ret; +} diff --git a/config.mak.in b/config.mak.in index 369e6116e0..9a578405d8 100644 --- a/config.mak.in +++ b/config.mak.in @@ -2,6 +2,7 @@ # @configure_input@ CC = @CC@ +CFLAGS = @CFLAGS@ AR = @AR@ TAR = @TAR@ #INSTALL = @INSTALL@ # needs install-sh or install.sh in sources @@ -12,7 +13,6 @@ bindir = @bindir@ #gitexecdir = @libexecdir@/git-core/ datarootdir = @datarootdir@ template_dir = @datadir@/git-core/templates/ -GIT_PYTHON_DIR = @datadir@/git-core/python mandir=@mandir@ @@ -22,7 +22,6 @@ VPATH = @srcdir@ export exec_prefix mandir export srcdir VPATH -NO_PYTHON=@NO_PYTHON@ NEEDS_SSL_WITH_CRYPTO=@NEEDS_SSL_WITH_CRYPTO@ NO_OPENSSL=@NO_OPENSSL@ NO_CURL=@NO_CURL@ @@ -37,4 +36,5 @@ NO_C99_FORMAT=@NO_C99_FORMAT@ NO_STRCASESTR=@NO_STRCASESTR@ NO_STRLCPY=@NO_STRLCPY@ NO_SETENV=@NO_SETENV@ +NO_ICONV=@NO_ICONV@ diff --git a/configure.ac b/configure.ac index 36f9cd94d8..7cfb3a0666 100644 --- a/configure.ac +++ b/configure.ac @@ -75,43 +75,15 @@ GIT_ARG_SET_PATH(shell) # Define PERL_PATH to provide path to Perl. GIT_ARG_SET_PATH(perl) # -# Define NO_PYTHON if you want to lose all benefits of the recursive merge. -# Define PYTHON_PATH to provide path to Python. -AC_ARG_WITH(python,[AS_HELP_STRING([--with-python=PATH], [provide PATH to python]) -AS_HELP_STRING([--without-python], [don't use python scripts])], - [if test "$withval" = "no"; then \ - NO_PYTHON=YesPlease; \ - elif test "$withval" = "yes"; then \ - NO_PYTHON=; \ - else \ - NO_PYTHON=; \ - PYTHON_PATH=$withval; \ - fi; \ - ]) -AC_SUBST(NO_PYTHON) -AC_SUBST(PYTHON_PATH) ## Checks for programs. AC_MSG_NOTICE([CHECKS for programs]) # -AC_PROG_CC +AC_PROG_CC([cc gcc]) #AC_PROG_INSTALL # needs install-sh or install.sh in sources AC_CHECK_TOOL(AR, ar, :) AC_CHECK_PROGS(TAR, [gtar tar]) -# -# Define NO_PYTHON if you want to lose all benefits of the recursive merge. -# Define PYTHON_PATH to provide path to Python. -if test -z "$NO_PYTHON"; then - if test -z "$PYTHON_PATH"; then - AC_PATH_PROGS(PYTHON_PATH, [python python2.4 python2.3 python2]) - fi - if test -n "$PYTHON_PATH"; then - GIT_CONF_APPEND_LINE([PYTHON_PATH=@PYTHON_PATH@]) - NO_PYTHON="" - fi -fi - ## Checks for libraries. AC_MSG_NOTICE([CHECKS for libraries]) @@ -143,10 +115,15 @@ AC_CHECK_LIB([expat], [XML_ParserCreate], AC_SUBST(NO_EXPAT) # # Define NEEDS_LIBICONV if linking with libc is not enough (Darwin). +# Define NO_ICONV if neither libc nor libiconv support iconv. AC_CHECK_LIB([c], [iconv], -[NEEDS_LIBICONV=], -[NEEDS_LIBICONV=YesPlease]) + [NEEDS_LIBICONV=], + AC_CHECK_LIB([iconv], [iconv], + [NEEDS_LIBICONV=YesPlease], + [NO_ICONV=YesPlease])) AC_SUBST(NEEDS_LIBICONV) +AC_SUBST(NO_ICONV) +test -n "$NEEDS_LIBICONV" && LIBS="$LIBS -liconv" # # Define NEEDS_SOCKET if linking with libc is not enough (SunOS, # Patrick Mauritz). @@ -204,8 +181,8 @@ AC_SUBST(NO_IPV6) # do not support the 'size specifiers' introduced by C99, namely ll, hh, # j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t). # some C compilers supported these specifiers prior to C99 as an extension. -AC_CACHE_CHECK(whether formatted IO functions support C99 size specifiers, - ac_cv_c_c99_format, +AC_CACHE_CHECK([whether formatted IO functions support C99 size specifiers], + [ac_cv_c_c99_format], [# Actually git uses only %z (%zu) in alloc.c, and %t (%td) in mktag.c AC_RUN_IFELSE( [AC_LANG_PROGRAM([AC_INCLUDES_DEFAULT], @@ -258,12 +235,6 @@ AC_SUBST(NO_SETENV) # # Define NO_SYMLINK_HEAD if you never want .git/HEAD to be a symbolic link. # Enable it on Windows. By default, symrefs are still used. -# -# Define WITH_OWN_SUBPROCESS_PY if you want to use with python 2.3. -# -# Define NO_ACCURATE_DIFF if your diff program at least sometimes misses -# a missing newline at the end of the file. - ## Site configuration (override autodetection) ## --with-PACKAGE[=ARG] and --without-PACKAGE @@ -329,13 +300,19 @@ GIT_PARSE_WITH(expat)) # library directories by defining CFLAGS and LDFLAGS appropriately. # # Define NO_MMAP if you want to avoid mmap. +# +# Define NO_ICONV if your libc does not properly support iconv. +AC_ARG_WITH(iconv, +AS_HELP_STRING([--without-iconv], +[if your architecture doesn't properly support iconv]) +AS_HELP_STRING([--with-iconv=PATH], +[PATH is prefix for libiconv library and headers]) +AS_HELP_STRING([], +[used only if you need linking with libiconv]), +GIT_PARSE_WITH(iconv)) ## --enable-FEATURE[=ARG] and --disable-FEATURE # -# Define COLLISION_CHECK below if you believe that SHA1's -# 1461501637330902918203684832716283019655932542976 hashes do not give you -# sufficient guarantee that no collisions between objects will ever happen. -# # Define USE_NSEC below if you want git to care about sub-second file mtimes # and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and # it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely @@ -3,12 +3,6 @@ #include "pkt-line.h" #include "quote.h" #include "refs.h" -#include <sys/wait.h> -#include <sys/socket.h> -#include <netinet/in.h> -#include <arpa/inet.h> -#include <netdb.h> -#include <signal.h> static char *server_capabilities; @@ -17,7 +11,7 @@ static int check_ref(const char *name, int len, unsigned int flags) if (!flags) return 1; - if (len > 45 || memcmp(name, "refs/", 5)) + if (len < 5 || memcmp(name, "refs/", 5)) return 0; /* Skip the "refs/" part */ @@ -69,7 +63,7 @@ struct ref **get_remote_heads(int in, struct ref **list, if (len != name_len + 41) { if (server_capabilities) free(server_capabilities); - server_capabilities = strdup(name + name_len + 1); + server_capabilities = xstrdup(name + name_len + 1); } if (!check_ref(name, name_len, flags)) @@ -144,6 +138,7 @@ struct refspec { * +A:B means overwrite remote B with local A. * +A is a shorthand for +A:A. * A is a shorthand for A:A. + * :B means delete remote B. */ static struct refspec *parse_ref_spec(int nr_refspec, char **refspec) { @@ -174,21 +169,58 @@ static int count_refspec_match(const char *pattern, struct ref *refs, struct ref **matched_ref) { - int match; int patlen = strlen(pattern); + struct ref *matched_weak = NULL; + struct ref *matched = NULL; + int weak_match = 0; + int match = 0; - for (match = 0; refs; refs = refs->next) { + for (weak_match = match = 0; refs; refs = refs->next) { char *name = refs->name; int namelen = strlen(name); + int weak_match; + if (namelen < patlen || memcmp(name + namelen - patlen, pattern, patlen)) continue; if (namelen != patlen && name[namelen - patlen - 1] != '/') continue; - match++; - *matched_ref = refs; + + /* A match is "weak" if it is with refs outside + * heads or tags, and did not specify the pattern + * in full (e.g. "refs/remotes/origin/master") or at + * least from the toplevel (e.g. "remotes/origin/master"); + * otherwise "git push $URL master" would result in + * ambiguity between remotes/origin/master and heads/master + * at the remote site. + */ + if (namelen != patlen && + patlen != namelen - 5 && + strncmp(name, "refs/heads/", 11) && + strncmp(name, "refs/tags/", 10)) { + /* We want to catch the case where only weak + * matches are found and there are multiple + * matches, and where more than one strong + * matches are found, as ambiguous. One + * strong match with zero or more weak matches + * are acceptable as a unique match. + */ + matched_weak = refs; + weak_match++; + } + else { + matched = refs; + match++; + } + } + if (!matched) { + *matched_ref = matched_weak; + return weak_match; + } + else { + *matched_ref = matched; + return match; } - return match; } static void link_dst_tail(struct ref *ref, struct ref ***tail) @@ -203,6 +235,13 @@ static struct ref *try_explicit_object_name(const char *name) unsigned char sha1[20]; struct ref *ref; int len; + + if (!*name) { + ref = xcalloc(1, sizeof(*ref) + 20); + strcpy(ref->name, "(delete)"); + hashclr(ref->new_sha1); + return ref; + } if (get_sha1(name, sha1)) return NULL; len = strlen(name) + 1; @@ -225,7 +264,8 @@ static int match_explicit_refs(struct ref *src, struct ref *dst, break; case 0: /* The source could be in the get_sha1() format - * not a reference name. + * not a reference name. :refs/other is a + * way to delete 'other' ref at the remote end. */ matched_src = try_explicit_object_name(rs[i].src); if (matched_src) @@ -599,12 +639,19 @@ static void git_proxy_connect(int fd[2], char *host) close(pipefd[1][0]); } +#define MAX_CMD_LEN 1024 + /* - * Yeah, yeah, fixme. Need to pass in the heads etc. + * This returns 0 if the transport protocol does not need fork(2), + * or a process id if it does. Once done, finish the connection + * with finish_connect() with the value returned from this function + * (it is safe to call finish_connect() with 0 to support the former + * case). + * + * Does not return a negative value on error; it just dies. */ -int git_connect(int fd[2], char *url, const char *prog) +pid_t git_connect(int fd[2], char *url, const char *prog) { - char command[1024]; char *host, *path = url; char *end; int c; @@ -661,7 +708,7 @@ int git_connect(int fd[2], char *url, const char *prog) if (path[1] == '~') path++; else { - path = strdup(ptr); + path = xstrdup(ptr); free_path = 1; } @@ -672,7 +719,7 @@ int git_connect(int fd[2], char *url, const char *prog) /* These underlying connection commands die() if they * cannot connect. */ - char *target_host = strdup(host); + char *target_host = xstrdup(host); if (git_use_proxy(host)) git_proxy_connect(fd, host); else @@ -697,8 +744,18 @@ int git_connect(int fd[2], char *url, const char *prog) if (pid < 0) die("unable to fork"); if (!pid) { - snprintf(command, sizeof(command), "%s %s", prog, - sq_quote(path)); + char command[MAX_CMD_LEN]; + char *posn = command; + int size = MAX_CMD_LEN; + int of = 0; + + of |= add_to_string(&posn, &size, prog, 0); + of |= add_to_string(&posn, &size, " ", 0); + of |= add_to_string(&posn, &size, path, 1); + + if (of) + die("command line too long"); + dup2(pipefd[1][0], 0); dup2(pipefd[0][1], 1); close(pipefd[0][0]); @@ -737,6 +794,9 @@ int git_connect(int fd[2], char *url, const char *prog) int finish_connect(pid_t pid) { + if (pid == 0) + return 0; + while (waitpid(pid, NULL, 0) < 0) { if (errno != EINTR) return -1; diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash new file mode 100755 index 0000000000..7c7520ea29 --- /dev/null +++ b/contrib/completion/git-completion.bash @@ -0,0 +1,886 @@ +# +# bash completion support for core Git. +# +# Copyright (C) 2006 Shawn Pearce +# Conceptually based on gitcompletion (http://gitweb.hawaga.org.uk/). +# +# The contained completion routines provide support for completing: +# +# *) local and remote branch names +# *) local and remote tag names +# *) .git/remotes file names +# *) git 'subcommands' +# *) tree paths within 'ref:path/to/file' expressions +# +# To use these routines: +# +# 1) Copy this file to somewhere (e.g. ~/.git-completion.sh). +# 2) Added the following line to your .bashrc: +# source ~/.git-completion.sh +# +# 3) You may want to make sure the git executable is available +# in your PATH before this script is sourced, as some caching +# is performed while the script loads. If git isn't found +# at source time then all lookups will be done on demand, +# which may be slightly slower. +# +# 4) Consider changing your PS1 to also show the current branch: +# PS1='[\u@\h \W$(__git_ps1 " (%s)")]\$ ' +# +# The argument to __git_ps1 will be displayed only if you +# are currently in a git repository. The %s token will be +# the name of the current branch. +# + +__gitdir () +{ + if [ -z "$1" ]; then + if [ -n "$__git_dir" ]; then + echo "$__git_dir" + elif [ -d .git ]; then + echo .git + else + git rev-parse --git-dir 2>/dev/null + fi + elif [ -d "$1/.git" ]; then + echo "$1/.git" + else + echo "$1" + fi +} + +__git_ps1 () +{ + local b="$(git symbolic-ref HEAD 2>/dev/null)" + if [ -n "$b" ]; then + if [ -n "$1" ]; then + printf "$1" "${b##refs/heads/}" + else + printf " (%s)" "${b##refs/heads/}" + fi + fi +} + +__git_heads () +{ + local cmd i is_hash=y dir="$(__gitdir "$1")" + if [ -d "$dir" ]; then + for i in $(git --git-dir="$dir" \ + for-each-ref --format='%(refname)' \ + refs/heads ); do + echo "${i#refs/heads/}" + done + return + fi + for i in $(git-ls-remote "$1" 2>/dev/null); do + case "$is_hash,$i" in + y,*) is_hash=n ;; + n,*^{}) is_hash=y ;; + n,refs/heads/*) is_hash=y; echo "${i#refs/heads/}" ;; + n,*) is_hash=y; echo "$i" ;; + esac + done +} + +__git_refs () +{ + local cmd i is_hash=y dir="$(__gitdir "$1")" + if [ -d "$dir" ]; then + if [ -e "$dir/HEAD" ]; then echo HEAD; fi + for i in $(git --git-dir="$dir" \ + for-each-ref --format='%(refname)' \ + refs/tags refs/heads refs/remotes); do + case "$i" in + refs/tags/*) echo "${i#refs/tags/}" ;; + refs/heads/*) echo "${i#refs/heads/}" ;; + refs/remotes/*) echo "${i#refs/remotes/}" ;; + *) echo "$i" ;; + esac + done + return + fi + for i in $(git-ls-remote "$dir" 2>/dev/null); do + case "$is_hash,$i" in + y,*) is_hash=n ;; + n,*^{}) is_hash=y ;; + n,refs/tags/*) is_hash=y; echo "${i#refs/tags/}" ;; + n,refs/heads/*) is_hash=y; echo "${i#refs/heads/}" ;; + n,refs/remotes/*) is_hash=y; echo "${i#refs/remotes/}" ;; + n,*) is_hash=y; echo "$i" ;; + esac + done +} + +__git_refs2 () +{ + local i + for i in $(__git_refs "$1"); do + echo "$i:$i" + done +} + +__git_refs_remotes () +{ + local cmd i is_hash=y + for i in $(git-ls-remote "$1" 2>/dev/null); do + case "$is_hash,$i" in + n,refs/heads/*) + is_hash=y + echo "$i:refs/remotes/$1/${i#refs/heads/}" + ;; + y,*) is_hash=n ;; + n,*^{}) is_hash=y ;; + n,refs/tags/*) is_hash=y;; + n,*) is_hash=y; ;; + esac + done +} + +__git_remotes () +{ + local i ngoff IFS=$'\n' d="$(__gitdir)" + shopt -q nullglob || ngoff=1 + shopt -s nullglob + for i in "$d/remotes"/*; do + echo ${i#$d/remotes/} + done + [ "$ngoff" ] && shopt -u nullglob + for i in $(git --git-dir="$d" repo-config --list); do + case "$i" in + remote.*.url=*) + i="${i#remote.}" + echo "${i/.url=*/}" + ;; + esac + done +} + +__git_merge_strategies () +{ + if [ -n "$__git_merge_strategylist" ]; then + echo "$__git_merge_strategylist" + return + fi + sed -n "/^all_strategies='/{ + s/^all_strategies='// + s/'// + p + q + }" "$(git --exec-path)/git-merge" +} +__git_merge_strategylist= +__git_merge_strategylist="$(__git_merge_strategies 2>/dev/null)" + +__git_complete_file () +{ + local pfx ls ref cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + ?*:*) + ref="${cur%%:*}" + cur="${cur#*:}" + case "$cur" in + ?*/*) + pfx="${cur%/*}" + cur="${cur##*/}" + ls="$ref:$pfx" + pfx="$pfx/" + ;; + *) + ls="$ref" + ;; + esac + COMPREPLY=($(compgen -P "$pfx" \ + -W "$(git --git-dir="$(__gitdir)" ls-tree "$ls" \ + | sed '/^100... blob /s,^.* ,, + /^040000 tree /{ + s,^.* ,, + s,$,/, + } + s/^.* //')" \ + -- "$cur")) + ;; + *) + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) + ;; + esac +} + +__git_complete_revlist () +{ + local pfx cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + *...*) + pfx="${cur%...*}..." + cur="${cur#*...}" + COMPREPLY=($(compgen -P "$pfx" -W "$(__git_refs)" -- "$cur")) + ;; + *..*) + pfx="${cur%..*}.." + cur="${cur#*..}" + COMPREPLY=($(compgen -P "$pfx" -W "$(__git_refs)" -- "$cur")) + ;; + *) + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) + ;; + esac +} + +__git_commands () +{ + if [ -n "$__git_commandlist" ]; then + echo "$__git_commandlist" + return + fi + local i IFS=" "$'\n' + for i in $(git help -a|egrep '^ ') + do + case $i in + check-ref-format) : plumbing;; + commit-tree) : plumbing;; + convert-objects) : plumbing;; + cvsserver) : daemon;; + daemon) : daemon;; + fetch-pack) : plumbing;; + hash-object) : plumbing;; + http-*) : transport;; + index-pack) : plumbing;; + local-fetch) : plumbing;; + mailinfo) : plumbing;; + mailsplit) : plumbing;; + merge-*) : plumbing;; + mktree) : plumbing;; + mktag) : plumbing;; + pack-objects) : plumbing;; + pack-redundant) : plumbing;; + pack-refs) : plumbing;; + parse-remote) : plumbing;; + patch-id) : plumbing;; + peek-remote) : plumbing;; + read-tree) : plumbing;; + receive-pack) : plumbing;; + rerere) : plumbing;; + rev-list) : plumbing;; + rev-parse) : plumbing;; + runstatus) : plumbing;; + sh-setup) : internal;; + shell) : daemon;; + send-pack) : plumbing;; + show-index) : plumbing;; + ssh-*) : transport;; + stripspace) : plumbing;; + symbolic-ref) : plumbing;; + unpack-file) : plumbing;; + unpack-objects) : plumbing;; + update-ref) : plumbing;; + update-server-info) : daemon;; + upload-archive) : plumbing;; + upload-pack) : plumbing;; + write-tree) : plumbing;; + *) echo $i;; + esac + done +} +__git_commandlist= +__git_commandlist="$(__git_commands 2>/dev/null)" + +__git_aliases () +{ + local i IFS=$'\n' + for i in $(git --git-dir="$(__gitdir)" repo-config --list); do + case "$i" in + alias.*) + i="${i#alias.}" + echo "${i/=*/}" + ;; + esac + done +} + +__git_aliased_command () +{ + local word cmdline=$(git --git-dir="$(__gitdir)" \ + repo-config --get "alias.$1") + for word in $cmdline; do + if [ "${word##-*}" ]; then + echo $word + return + fi + done +} + +__git_whitespacelist="nowarn warn error error-all strip" + +_git_am () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + if [ -d .dotest ]; then + COMPREPLY=($(compgen -W " + --skip --resolved + " -- "$cur")) + return + fi + case "$cur" in + --whitespace=*) + COMPREPLY=($(compgen -W "$__git_whitespacelist" \ + -- "${cur##--whitespace=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W " + --signoff --utf8 --binary --3way --interactive + --whitespace= + " -- "$cur")) + return + esac + COMPREPLY=() +} + +_git_apply () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --whitespace=*) + COMPREPLY=($(compgen -W "$__git_whitespacelist" \ + -- "${cur##--whitespace=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W " + --stat --numstat --summary --check --index + --cached --index-info --reverse --reject --unidiff-zero + --apply --no-add --exclude= + --whitespace= --inaccurate-eof --verbose + " -- "$cur")) + return + esac + COMPREPLY=() +} + +_git_branch () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "-l -f -d -D $(__git_refs)" -- "$cur")) +} + +_git_cat_file () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "${COMP_WORDS[0]},$COMP_CWORD" in + git-cat-file*,1) + COMPREPLY=($(compgen -W "-p -t blob tree commit tag" -- "$cur")) + ;; + git,2) + COMPREPLY=($(compgen -W "-p -t blob tree commit tag" -- "$cur")) + ;; + *) + __git_complete_file + ;; + esac +} + +_git_checkout () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "-l -b $(__git_refs)" -- "$cur")) +} + +_git_cherry_pick () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --*) + COMPREPLY=($(compgen -W " + --edit --no-commit + " -- "$cur")) + ;; + *) + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) + ;; + esac +} + +_git_commit () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --*) + COMPREPLY=($(compgen -W " + --all --author= --signoff --verify --no-verify + --edit --amend --include --only + " -- "$cur")) + return + esac + COMPREPLY=() +} + +_git_diff () +{ + __git_complete_file +} + +_git_diff_tree () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "-r -p -M $(__git_refs)" -- "$cur")) +} + +_git_fetch () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + + case "${COMP_WORDS[0]},$COMP_CWORD" in + git-fetch*,1) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + git,2) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + *) + case "$cur" in + *:*) + cur="${cur#*:}" + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) + ;; + *) + local remote + case "${COMP_WORDS[0]}" in + git-fetch) remote="${COMP_WORDS[1]}" ;; + git) remote="${COMP_WORDS[2]}" ;; + esac + COMPREPLY=($(compgen -W "$(__git_refs2 "$remote")" -- "$cur")) + ;; + esac + ;; + esac +} + +_git_format_patch () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --*) + COMPREPLY=($(compgen -W " + --stdout --attach --thread + --output-directory + --numbered --start-number + --keep-subject + --signoff + --in-reply-to= + --full-index --binary + " -- "$cur")) + return + ;; + esac + __git_complete_revlist +} + +_git_ls_remote () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) +} + +_git_ls_tree () +{ + __git_complete_file +} + +_git_log () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --pretty=*) + COMPREPLY=($(compgen -W " + oneline short medium full fuller email raw + " -- "${cur##--pretty=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W " + --max-count= --max-age= --since= --after= + --min-age= --before= --until= + --root --not --topo-order --date-order + --no-merges + --abbrev-commit --abbrev= + --relative-date + --author= --committer= --grep= + --all-match + --pretty= --name-status --name-only + " -- "$cur")) + return + ;; + esac + __git_complete_revlist +} + +_git_merge () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "${COMP_WORDS[COMP_CWORD-1]}" in + -s|--strategy) + COMPREPLY=($(compgen -W "$(__git_merge_strategies)" -- "$cur")) + return + esac + case "$cur" in + --strategy=*) + COMPREPLY=($(compgen -W "$(__git_merge_strategies)" \ + -- "${cur##--strategy=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W " + --no-commit --no-summary --squash --strategy + " -- "$cur")) + return + esac + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) +} + +_git_merge_base () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) +} + +_git_name_rev () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "--tags --all --stdin" -- "$cur")) +} + +_git_pull () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + + case "${COMP_WORDS[0]},$COMP_CWORD" in + git-pull*,1) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + git,2) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + *) + local remote + case "${COMP_WORDS[0]}" in + git-pull) remote="${COMP_WORDS[1]}" ;; + git) remote="${COMP_WORDS[2]}" ;; + esac + COMPREPLY=($(compgen -W "$(__git_refs "$remote")" -- "$cur")) + ;; + esac +} + +_git_push () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + + case "${COMP_WORDS[0]},$COMP_CWORD" in + git-push*,1) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + git,2) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + ;; + *) + case "$cur" in + *:*) + local remote + case "${COMP_WORDS[0]}" in + git-push) remote="${COMP_WORDS[1]}" ;; + git) remote="${COMP_WORDS[2]}" ;; + esac + cur="${cur#*:}" + COMPREPLY=($(compgen -W "$(__git_refs "$remote")" -- "$cur")) + ;; + *) + COMPREPLY=($(compgen -W "$(__git_refs2)" -- "$cur")) + ;; + esac + ;; + esac +} + +_git_rebase () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + if [ -d .dotest ]; then + COMPREPLY=($(compgen -W " + --continue --skip --abort + " -- "$cur")) + return + fi + case "${COMP_WORDS[COMP_CWORD-1]}" in + -s|--strategy) + COMPREPLY=($(compgen -W "$(__git_merge_strategies)" -- "$cur")) + return + esac + case "$cur" in + --strategy=*) + COMPREPLY=($(compgen -W "$(__git_merge_strategies)" \ + -- "${cur##--strategy=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W " + --onto --merge --strategy + " -- "$cur")) + return + esac + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) +} + +_git_repo_config () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + local prv="${COMP_WORDS[COMP_CWORD-1]}" + case "$prv" in + branch.*.remote) + COMPREPLY=($(compgen -W "$(__git_remotes)" -- "$cur")) + return + ;; + branch.*.merge) + COMPREPLY=($(compgen -W "$(__git_refs)" -- "$cur")) + return + ;; + remote.*.fetch) + local remote="${prv#remote.}" + remote="${remote%.fetch}" + COMPREPLY=($(compgen -W "$(__git_refs_remotes "$remote")" \ + -- "$cur")) + return + ;; + remote.*.push) + local remote="${prv#remote.}" + remote="${remote%.push}" + COMPREPLY=($(compgen -W "$(git --git-dir="$(__gitdir)" \ + for-each-ref --format='%(refname):%(refname)' \ + refs/heads)" -- "$cur")) + return + ;; + *.*) + COMPREPLY=() + return + ;; + esac + case "$cur" in + --*) + COMPREPLY=($(compgen -W " + --global --list --replace-all + --get --get-all --get-regexp + --unset --unset-all + " -- "$cur")) + return + ;; + branch.*.*) + local pfx="${cur%.*}." + cur="${cur##*.}" + COMPREPLY=($(compgen -P "$pfx" -W "remote merge" -- "$cur")) + return + ;; + branch.*) + local pfx="${cur%.*}." + cur="${cur#*.}" + COMPREPLY=($(compgen -P "$pfx" -S . \ + -W "$(__git_heads)" -- "$cur")) + return + ;; + remote.*.*) + local pfx="${cur%.*}." + cur="${cur##*.}" + COMPREPLY=($(compgen -P "$pfx" -W "url fetch push" -- "$cur")) + return + ;; + remote.*) + local pfx="${cur%.*}." + cur="${cur#*.}" + COMPREPLY=($(compgen -P "$pfx" -S . \ + -W "$(__git_remotes)" -- "$cur")) + return + ;; + esac + COMPREPLY=($(compgen -W " + apply.whitespace + core.fileMode + core.gitProxy + core.ignoreStat + core.preferSymlinkRefs + core.logAllRefUpdates + core.repositoryFormatVersion + core.sharedRepository + core.warnAmbiguousRefs + core.compression + core.legacyHeaders + i18n.commitEncoding + i18n.logOutputEncoding + diff.color + color.diff + diff.renameLimit + diff.renames + pager.color + color.pager + status.color + color.status + log.showroot + show.difftree + showbranch.default + whatchanged.difftree + http.sslVerify + http.sslCert + http.sslKey + http.sslCAInfo + http.sslCAPath + http.maxRequests + http.lowSpeedLimit http.lowSpeedTime + http.noEPSV + pack.window + repack.useDeltaBaseOffset + pull.octopus pull.twohead + merge.summary + receive.unpackLimit + receive.denyNonFastForwards + user.name user.email + tar.umask + gitcvs.enabled + gitcvs.logfile + branch. remote. + " -- "$cur")) +} + +_git_reset () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + local opt="--mixed --hard --soft" + COMPREPLY=($(compgen -W "$opt $(__git_refs)" -- "$cur")) +} + +_git_show () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + case "$cur" in + --pretty=*) + COMPREPLY=($(compgen -W " + oneline short medium full fuller email raw + " -- "${cur##--pretty=}")) + return + ;; + --*) + COMPREPLY=($(compgen -W "--pretty=" -- "$cur")) + return + ;; + esac + __git_complete_file +} + +_git () +{ + local i c=1 command __git_dir + + while [ $c -lt $COMP_CWORD ]; do + i="${COMP_WORDS[c]}" + case "$i" in + --git-dir=*) __git_dir="${i#--git-dir=}" ;; + --bare) __git_dir="." ;; + --version|--help|-p|--paginate) ;; + *) command="$i"; break ;; + esac + c=$((++c)) + done + + if [ $c -eq $COMP_CWORD -a -z "$command" ]; then + COMPREPLY=($(compgen -W " + --git-dir= --version --exec-path + $(__git_commands) + $(__git_aliases) + " -- "${COMP_WORDS[COMP_CWORD]}")) + return; + fi + + local expansion=$(__git_aliased_command "$command") + [ "$expansion" ] && command="$expansion" + + case "$command" in + am) _git_am ;; + apply) _git_apply ;; + branch) _git_branch ;; + cat-file) _git_cat_file ;; + checkout) _git_checkout ;; + cherry-pick) _git_cherry_pick ;; + commit) _git_commit ;; + diff) _git_diff ;; + diff-tree) _git_diff_tree ;; + fetch) _git_fetch ;; + format-patch) _git_format_patch ;; + log) _git_log ;; + ls-remote) _git_ls_remote ;; + ls-tree) _git_ls_tree ;; + merge) _git_merge;; + merge-base) _git_merge_base ;; + name-rev) _git_name_rev ;; + pull) _git_pull ;; + push) _git_push ;; + rebase) _git_rebase ;; + repo-config) _git_repo_config ;; + reset) _git_reset ;; + show) _git_show ;; + show-branch) _git_log ;; + whatchanged) _git_log ;; + *) COMPREPLY=() ;; + esac +} + +_gitk () +{ + local cur="${COMP_WORDS[COMP_CWORD]}" + COMPREPLY=($(compgen -W "--all $(__git_refs)" -- "$cur")) +} + +complete -o default -o nospace -F _git git +complete -o default -F _gitk gitk +complete -o default -F _git_am git-am +complete -o default -F _git_apply git-apply +complete -o default -F _git_branch git-branch +complete -o default -o nospace -F _git_cat_file git-cat-file +complete -o default -F _git_checkout git-checkout +complete -o default -F _git_cherry_pick git-cherry-pick +complete -o default -F _git_commit git-commit +complete -o default -o nospace -F _git_diff git-diff +complete -o default -F _git_diff_tree git-diff-tree +complete -o default -o nospace -F _git_fetch git-fetch +complete -o default -o nospace -F _git_format_patch git-format-patch +complete -o default -o nospace -F _git_log git-log +complete -o default -F _git_ls_remote git-ls-remote +complete -o default -o nospace -F _git_ls_tree git-ls-tree +complete -o default -F _git_merge git-merge +complete -o default -F _git_merge_base git-merge-base +complete -o default -F _git_name_rev git-name-rev +complete -o default -o nospace -F _git_pull git-pull +complete -o default -o nospace -F _git_push git-push +complete -o default -F _git_rebase git-rebase +complete -o default -F _git_repo_config git-repo-config +complete -o default -F _git_reset git-reset +complete -o default -o nospace -F _git_show git-show +complete -o default -o nospace -F _git_log git-show-branch +complete -o default -o nospace -F _git_log git-whatchanged + +# The following are necessary only for Cygwin, and only are needed +# when the user has tab-completed the executable name and consequently +# included the '.exe' suffix. +# +if [ Cygwin = "$(uname -o 2>/dev/null)" ]; then +complete -o default -F _git_apply git-apply.exe +complete -o default -o nospace -F _git git.exe +complete -o default -F _git_branch git-branch.exe +complete -o default -o nospace -F _git_cat_file git-cat-file.exe +complete -o default -o nospace -F _git_diff git-diff.exe +complete -o default -o nospace -F _git_diff_tree git-diff-tree.exe +complete -o default -o nospace -F _git_format_patch git-format-patch.exe +complete -o default -o nospace -F _git_log git-log.exe +complete -o default -o nospace -F _git_ls_tree git-ls-tree.exe +complete -o default -F _git_merge_base git-merge-base.exe +complete -o default -F _git_name_rev git-name-rev.exe +complete -o default -o nospace -F _git_push git-push.exe +complete -o default -F _git_repo_config git-repo-config +complete -o default -o nospace -F _git_show git-show.exe +complete -o default -o nospace -F _git_log git-show-branch.exe +complete -o default -o nospace -F _git_log git-whatchanged.exe +fi diff --git a/contrib/emacs/git.el b/contrib/emacs/git.el index 68de9be0c7..d90ba816e0 100644 --- a/contrib/emacs/git.el +++ b/contrib/emacs/git.el @@ -49,6 +49,7 @@ (eval-when-compile (require 'cl)) (require 'ewoc) +(require 'log-edit) ;;;; Customizations @@ -147,6 +148,13 @@ if there is already one that displays the same directory." (defconst git-log-msg-separator "--- log message follows this line ---") +(defvar git-log-edit-font-lock-keywords + `(("^\\(Author:\\|Date:\\|Parent:\\|Signed-off-by:\\)\\(.*\\)$" + (1 font-lock-keyword-face) + (2 font-lock-function-name-face)) + (,(concat "^\\(" (regexp-quote git-log-msg-separator) "\\)$") + (1 font-lock-comment-face)))) + (defun git-get-env-strings (env) "Build a list of NAME=VALUE strings from a list of environment strings." (mapcar (lambda (entry) (concat (car entry) "=" (cdr entry))) env)) @@ -272,6 +280,15 @@ and returns the process output as a string." (git-run-command nil nil "update-index" "--info-only" "--add" "--" (file-relative-name ignore-name))) (git-add-status-file (if created 'added 'modified) (file-relative-name ignore-name)))) +; propertize definition for XEmacs, stolen from erc-compat +(eval-when-compile + (unless (fboundp 'propertize) + (defun propertize (string &rest props) + (let ((string (copy-sequence string))) + (while props + (put-text-property 0 (length string) (nth 0 props) (nth 1 props) string) + (setq props (cddr props))) + string)))) ;;;; Wrappers for basic git commands ;;;; ------------------------------------------------------------ @@ -422,8 +439,8 @@ and returns the process output as a string." (propertize (concat " (" (if (eq state 'copy) "copied from " - (if (eq (git-fileinfo->state info) 'added) "renamed to " - "renamed from ")) + (if (eq (git-fileinfo->state info) 'added) "renamed from " + "renamed to ")) (git-escape-file-name (git-fileinfo->orig-name info)) ")") 'face 'git-status-face) ""))) @@ -440,11 +457,10 @@ and returns the process output as a string." (defun git-fileinfo-prettyprint (info) "Pretty-printer for the git-fileinfo structure." - (insert (format " %s %s %s %s%s" - (if (git-fileinfo->marked info) (propertize "*" 'face 'git-mark-face) " ") - (git-status-code-as-string (git-fileinfo->state info)) - (git-permissions-as-string (git-fileinfo->old-perm info) (git-fileinfo->new-perm info)) - (git-escape-file-name (git-fileinfo->name info)) + (insert (concat " " (if (git-fileinfo->marked info) (propertize "*" 'face 'git-mark-face) " ") + " " (git-status-code-as-string (git-fileinfo->state info)) + " " (git-permissions-as-string (git-fileinfo->old-perm info) (git-fileinfo->new-perm info)) + " " (git-escape-file-name (git-fileinfo->name info)) (git-rename-as-string info)))) (defun git-parse-status (status) @@ -589,6 +605,7 @@ and returns the process output as a string." (let ((commit (git-commit-tree buffer tree head))) (git-update-ref "HEAD" commit head) (condition-case nil (delete-file ".git/MERGE_HEAD") (error nil)) + (condition-case nil (delete-file ".git/MERGE_MSG") (error nil)) (with-current-buffer buffer (erase-buffer)) (git-set-files-state files 'uptodate) (when (file-directory-p ".git/rr-cache") @@ -670,6 +687,32 @@ and returns the process output as a string." (unless git-status (error "Not in git-status buffer.")) (ewoc-goto-prev git-status n)) +(defun git-next-unmerged-file (&optional n) + "Move the selection down N unmerged files." + (interactive "p") + (unless git-status (error "Not in git-status buffer.")) + (let* ((last (ewoc-locate git-status)) + (node (ewoc-next git-status last))) + (while (and node (> n 0)) + (when (eq 'unmerged (git-fileinfo->state (ewoc-data node))) + (setq n (1- n)) + (setq last node)) + (setq node (ewoc-next git-status node))) + (ewoc-goto-node git-status last))) + +(defun git-prev-unmerged-file (&optional n) + "Move the selection up N unmerged files." + (interactive "p") + (unless git-status (error "Not in git-status buffer.")) + (let* ((last (ewoc-locate git-status)) + (node (ewoc-prev git-status last))) + (while (and node (> n 0)) + (when (eq 'unmerged (git-fileinfo->state (ewoc-data node))) + (setq n (1- n)) + (setq last node)) + (setq node (ewoc-prev git-status node))) + (ewoc-goto-node git-status last))) + (defun git-add-file () "Add marked file(s) to the index cache." (interactive) @@ -750,7 +793,7 @@ and returns the process output as a string." (interactive) (let ((files (git-marked-files-state 'unmerged))) (when files - (apply #'git-run-command nil nil "update-index" "--info-only" "--" (git-get-filenames files)) + (apply #'git-run-command nil nil "update-index" "--" (git-get-filenames files)) (git-set-files-state files 'modified) (git-refresh-files)))) @@ -862,18 +905,14 @@ and returns the process output as a string." 'face 'git-header-face) (propertize git-log-msg-separator 'face 'git-separator-face) "\n") - (cond ((and merge-heads (file-readable-p ".git/MERGE_MSG")) + (cond ((file-readable-p ".git/MERGE_MSG") (insert-file-contents ".git/MERGE_MSG")) (sign-off (insert (format "\n\nSigned-off-by: %s <%s>\n" (git-get-committer-name) (git-get-committer-email))))))) - (let ((log-edit-font-lock-keywords - `(("^\\(Author:\\|Date:\\|Parent:\\|Signed-off-by:\\)\\(.*\\)" - (1 font-lock-keyword-face) - (2 font-lock-function-name-face)) - (,(concat "^\\(" (regexp-quote git-log-msg-separator) "\\)$") - (1 font-lock-comment-face))))) - (log-edit #'git-do-commit nil #'git-log-edit-files buffer)))) + (log-edit #'git-do-commit nil #'git-log-edit-files buffer) + (setq font-lock-keywords (font-lock-compile-keywords git-log-edit-font-lock-keywords)) + (re-search-forward (regexp-quote (concat git-log-msg-separator "\n")) nil t))) (defun git-find-file () "Visit the current file in its own buffer." @@ -884,6 +923,15 @@ and returns the process output as a string." (when (eq 'unmerged (git-fileinfo->state info)) (smerge-mode)))) +(defun git-find-file-other-window () + "Visit the current file in its own buffer in another window." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let ((info (ewoc-data (ewoc-locate git-status)))) + (find-file-other-window (git-fileinfo->name info)) + (when (eq 'unmerged (git-fileinfo->state info)) + (smerge-mode)))) + (defun git-find-file-imerge () "Visit the current file in interactive merge mode." (interactive) @@ -967,7 +1015,10 @@ and returns the process output as a string." (define-key map "m" 'git-mark-file) (define-key map "M" 'git-mark-all) (define-key map "n" 'git-next-file) + (define-key map "N" 'git-next-unmerged-file) + (define-key map "o" 'git-find-file-other-window) (define-key map "p" 'git-prev-file) + (define-key map "P" 'git-prev-unmerged-file) (define-key map "q" 'git-status-quit) (define-key map "r" 'git-remove-file) (define-key map "R" 'git-resolve-file) diff --git a/contrib/emacs/vc-git.el b/contrib/emacs/vc-git.el index 4a8f79092d..3eb4bd19e9 100644 --- a/contrib/emacs/vc-git.el +++ b/contrib/emacs/vc-git.el @@ -23,13 +23,18 @@ ;; system. ;; ;; To install: put this file on the load-path and add GIT to the list -;; of supported backends in `vc-handled-backends'. +;; of supported backends in `vc-handled-backends'; the following line, +;; placed in your ~/.emacs, will accomplish this: +;; +;; (add-to-list 'vc-handled-backends 'GIT) ;; ;; TODO ;; - changelog generation ;; - working with revisions other than HEAD ;; +(eval-when-compile (require 'cl)) + (defvar git-commits-coding-system 'utf-8 "Default coding system for git commits.") @@ -53,8 +58,9 @@ (with-temp-buffer (let* ((dir (file-name-directory file)) (name (file-relative-name file dir))) - (when dir (cd dir)) - (and (ignore-errors (eq 0 (call-process "git" nil '(t nil) nil "ls-files" "-c" "-z" "--" name))) + (and (ignore-errors + (when dir (cd dir)) + (eq 0 (call-process "git" nil '(t nil) nil "ls-files" "-c" "-z" "--" name))) (let ((str (buffer-string))) (and (> (length str) (length name)) (string= (substring str 0 (1+ (length name))) (concat name "\0")))))))) @@ -119,10 +125,10 @@ (defun vc-git-annotate-command (file buf &optional rev) ; FIXME: rev is ignored (let ((name (file-relative-name file))) - (call-process "git" nil buf nil "annotate" name))) + (call-process "git" nil buf nil "blame" name))) (defun vc-git-annotate-time () - (and (re-search-forward "[0-9a-f]+\t(.*\t\\([0-9]+\\)-\\([0-9]+\\)-\\([0-9]+\\) \\([0-9]+\\):\\([0-9]+\\):\\([0-9]+\\) \\([-+0-9]+\\)\t[0-9]+)" nil t) + (and (re-search-forward "[0-9a-f]+ (.* \\([0-9]+\\)-\\([0-9]+\\)-\\([0-9]+\\) \\([0-9]+\\):\\([0-9]+\\):\\([0-9]+\\) \\([-+0-9]+\\) +[0-9]+)" nil t) (vc-annotate-convert-time (apply #'encode-time (mapcar (lambda (match) (string-to-number (match-string match))) '(6 5 4 3 2 1 7)))))) diff --git a/contrib/gitview/gitview.txt b/contrib/gitview/gitview.txt index 6924df286e..77c29de305 100644 --- a/contrib/gitview/gitview.txt +++ b/contrib/gitview/gitview.txt @@ -7,40 +7,50 @@ gitview - A GTK based repository browser for git SYNOPSIS -------- -'gitview' [options] [args] +'gitview' [options] [args] DESCRIPTION --------- -Dependencies +Dependencies: * Python 2.4 * PyGTK 2.8 or later * PyCairo 1.0 or later OPTIONS ------- - --without-diff - If the user doesn't want to list the commit diffs in the main window. This may speed up the repository browsing. - - <args> - All the valid option for git-rev-list(1) - Key Bindings: - F4: - To maximize the window - F5: - To reread references. - F11: - Full screen - F12: - Leave full screen +------- +--without-diff:: + + If the user doesn't want to list the commit diffs in the main window. + This may speed up the repository browsing. + +<args>:: + + All the valid option for gitlink:git-rev-list[1]. + +Key Bindings +------------ +F4:: + To maximize the window + +F5:: + To reread references. + +F11:: + Full screen + +F12:: + Leave full screen EXAMPLES ------- - gitview v2.6.12.. include/scsi drivers/scsi - Show as the changes since version v2.6.12 that changed any file in the include/scsi - or drivers/scsi subdirectories +-------- + +gitview v2.6.12.. include/scsi drivers/scsi:: + + Show as the changes since version v2.6.12 that changed any file in the + include/scsi or drivers/scsi subdirectories - gitview --since=2.weeks.ago - Show the changes during the last two weeks +gitview --since=2.weeks.ago:: + Show the changes during the last two weeks diff --git a/contrib/mailmap.linux b/contrib/mailmap.linux new file mode 100644 index 0000000000..e4907f80f1 --- /dev/null +++ b/contrib/mailmap.linux @@ -0,0 +1,42 @@ +# +# Even with git, we don't always have name translations. +# So have an email->real name table to translate the +# (hopefully few) missing names +# +# repo-abbrev: /pub/scm/linux/kernel/git/ +# +Adrian Bunk <bunk@stusta.de> +Andreas Herrmann <aherrman@de.ibm.com> +Andrew Morton <akpm@osdl.org> +Andrew Vasquez <andrew.vasquez@qlogic.com> +Christoph Hellwig <hch@lst.de> +Corey Minyard <minyard@acm.org> +David Woodhouse <dwmw2@shinybook.infradead.org> +Domen Puncer <domen@coderock.org> +Douglas Gilbert <dougg@torque.net> +Ed L Cashin <ecashin@coraid.com> +Evgeniy Polyakov <johnpol@2ka.mipt.ru> +Felix Moeller <felix@derklecks.de> +Frank Zago <fzago@systemfabricworks.com> +Greg Kroah-Hartman <gregkh@suse.de> +James Bottomley <jejb@mulgrave.(none)> +James Bottomley <jejb@titanic.il.steeleye.com> +Jeff Garzik <jgarzik@pretzel.yyz.us> +Jens Axboe <axboe@suse.de> +Kay Sievers <kay.sievers@vrfy.org> +Mitesh shah <mshah@teja.com> +Morten Welinder <terra@gnome.org> +Morten Welinder <welinder@anemone.rentec.com> +Morten Welinder <welinder@darter.rentec.com> +Morten Welinder <welinder@troll.com> +Nguyen Anh Quynh <aquynh@gmail.com> +Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> +Peter A Jonsson <pj@ludd.ltu.se> +Ralf Wildenhues <Ralf.Wildenhues@gmx.de> +Rudolf Marek <R.Marek@sh.cvut.cz> +Rui Saraiva <rmps@joel.ist.utl.pt> +Sachin P Sant <ssant@in.ibm.com> +Santtu Hyrkk,Av(B <santtu.hyrkko@gmail.com> +Simon Kelley <simon@thekelleys.org.uk> +Tejun Heo <htejun@gmail.com> +Tony Luck <tony.luck@intel.com> diff --git a/contrib/vim/README b/contrib/vim/README new file mode 100644 index 0000000000..9e7881fea9 --- /dev/null +++ b/contrib/vim/README @@ -0,0 +1,8 @@ +To syntax highlight git's commit messages, you need to: + 1. Copy syntax/gitcommit.vim to vim's syntax directory: + $ mkdir -p $HOME/.vim/syntax + $ cp syntax/gitcommit.vim $HOME/.vim/syntax + 2. Auto-detect the editing of git commit files: + $ cat >>$HOME/.vimrc <<'EOF' + autocmd BufNewFile,BufRead COMMIT_EDITMSG set filetype=gitcommit + EOF diff --git a/contrib/vim/syntax/gitcommit.vim b/contrib/vim/syntax/gitcommit.vim new file mode 100644 index 0000000000..d911efbb4b --- /dev/null +++ b/contrib/vim/syntax/gitcommit.vim @@ -0,0 +1,18 @@ +syn region gitLine start=/^#/ end=/$/ +syn region gitCommit start=/^# Added but not yet committed:$/ end=/^#$/ contains=gitHead,gitCommitFile +syn region gitHead contained start=/^# (.*)/ end=/^#$/ +syn region gitChanged start=/^# Changed but not added:/ end=/^#$/ contains=gitHead,gitChangedFile +syn region gitUntracked start=/^# Untracked files:/ end=/^#$/ contains=gitHead,gitUntrackedFile + +syn match gitCommitFile contained /^#\t.*/hs=s+2 +syn match gitChangedFile contained /^#\t.*/hs=s+2 +syn match gitUntrackedFile contained /^#\t.*/hs=s+2 + +hi def link gitLine Comment +hi def link gitCommit Comment +hi def link gitChanged Comment +hi def link gitHead Comment +hi def link gitUntracked Comment +hi def link gitCommitFile Type +hi def link gitChangedFile Constant +hi def link gitUntrackedFile Constant diff --git a/convert-objects.c b/convert-objects.c index 631678b08a..a630132985 100644 --- a/convert-objects.c +++ b/convert-objects.c @@ -1,7 +1,3 @@ -#define _XOPEN_SOURCE 500 /* glibc2 and AIX 5.3L need this */ -#define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */ -#define _GNU_SOURCE -#include <time.h> #include "cache.h" #include "blob.h" #include "commit.h" @@ -1,25 +1,28 @@ -#include <signal.h> -#include <sys/wait.h> -#include <sys/socket.h> -#include <sys/time.h> -#include <sys/poll.h> -#include <netdb.h> -#include <netinet/in.h> -#include <arpa/inet.h> -#include <syslog.h> -#include "pkt-line.h" #include "cache.h" +#include "pkt-line.h" #include "exec_cmd.h" +#include "interpolate.h" + +#include <syslog.h> + +#ifndef HOST_NAME_MAX +#define HOST_NAME_MAX 256 +#endif static int log_syslog; static int verbose; static int reuseaddr; static const char daemon_usage[] = -"git-daemon [--verbose] [--syslog] [--inetd | --port=n] [--export-all]\n" +"git-daemon [--verbose] [--syslog] [--export-all]\n" " [--timeout=n] [--init-timeout=n] [--strict-paths]\n" " [--base-path=path] [--user-path | --user-path=path]\n" -" [--reuseaddr] [--detach] [--pid-file=file] [directory...]"; +" [--interpolated-path=path]\n" +" [--reuseaddr] [--detach] [--pid-file=file]\n" +" [--[enable|disable|allow-override|forbid-override]=service]\n" +" [--inetd | [--listen=host_or_ipaddr] [--port=n]\n" +" [--user=user [--group=group]]\n" +" [directory...]"; /* List of acceptable pathname prefixes */ static char **ok_paths; @@ -30,6 +33,10 @@ static int export_all_trees; /* Take all paths relative to this one if non-NULL */ static char *base_path; +static char *interpolated_path; + +/* Flag indicating client sent extra args. */ +static int saw_extended_args; /* If defined, ~user notation is allowed and the string is inserted * after ~user/. E.g. a request to git://host/~alice/frotz would @@ -41,6 +48,27 @@ static const char *user_path; static unsigned int timeout; static unsigned int init_timeout; +/* + * Static table for now. Ugh. + * Feel free to make dynamic as needed. + */ +#define INTERP_SLOT_HOST (0) +#define INTERP_SLOT_CANON_HOST (1) +#define INTERP_SLOT_IP (2) +#define INTERP_SLOT_PORT (3) +#define INTERP_SLOT_DIR (4) +#define INTERP_SLOT_PERCENT (5) + +static struct interp interp_table[] = { + { "%H", 0}, + { "%CH", 0}, + { "%IP", 0}, + { "%P", 0}, + { "%D", 0}, + { "%%", 0}, +}; + + static void logreport(int priority, const char *err, va_list params) { /* We should do a single write so that it is atomic and output @@ -74,7 +102,7 @@ static void logreport(int priority, const char *err, va_list params) buf[buflen++] = '\n'; buf[buflen] = '\0'; - write(2, buf, buflen); + write_in_full(2, buf, buflen); } static void logerror(const char *err, ...) @@ -148,10 +176,14 @@ static int avoid_alias(char *p) } } -static char *path_ok(char *dir) +static char *path_ok(struct interp *itable) { static char rpath[PATH_MAX]; + static char interp_path[PATH_MAX]; char *path; + char *dir; + + dir = itable[INTERP_SLOT_DIR].value; if (avoid_alias(dir)) { logerror("'%s': aliased", dir); @@ -180,16 +212,27 @@ static char *path_ok(char *dir) dir = rpath; } } + else if (interpolated_path && saw_extended_args) { + if (*dir != '/') { + /* Allow only absolute */ + logerror("'%s': Non-absolute path denied (interpolated-path active)", dir); + return NULL; + } + + interpolate(interp_path, PATH_MAX, interpolated_path, + interp_table, ARRAY_SIZE(interp_table)); + loginfo("Interpolated dir '%s'", interp_path); + + dir = interp_path; + } else if (base_path) { if (*dir != '/') { /* Allow only absolute */ logerror("'%s': Non-absolute path denied (base-path active)", dir); return NULL; } - else { - snprintf(rpath, PATH_MAX, "%s%s", base_path, dir); - dir = rpath; - } + snprintf(rpath, PATH_MAX, "%s%s", base_path, dir); + dir = rpath; } path = enter_repo(dir, strict_paths); @@ -229,15 +272,46 @@ static char *path_ok(char *dir) return NULL; /* Fallthrough. Deny by default */ } -static int upload(char *dir) +typedef int (*daemon_service_fn)(void); +struct daemon_service { + const char *name; + const char *config_name; + daemon_service_fn fn; + int enabled; + int overridable; +}; + +static struct daemon_service *service_looking_at; +static int service_enabled; + +static int git_daemon_config(const char *var, const char *value) +{ + if (!strncmp(var, "daemon.", 7) && + !strcmp(var + 7, service_looking_at->config_name)) { + service_enabled = git_config_bool(var, value); + return 0; + } + + /* we are not interested in parsing any other configuration here */ + return 0; +} + +static int run_service(struct interp *itable, struct daemon_service *service) { - /* Timeout as string */ - char timeout_buf[64]; const char *path; + int enabled = service->enabled; - loginfo("Request for '%s'", dir); + loginfo("Request %s for '%s'", + service->name, + itable[INTERP_SLOT_DIR].value); - if (!(path = path_ok(dir))) + if (!enabled && !service->overridable) { + logerror("'%s': service not enabled.", service->name); + errno = EACCES; + return -1; + } + + if (!(path = path_ok(itable))) return -1; /* @@ -257,12 +331,34 @@ static int upload(char *dir) return -1; } + if (service->overridable) { + service_looking_at = service; + service_enabled = -1; + git_config(git_daemon_config); + if (0 <= service_enabled) + enabled = service_enabled; + } + if (!enabled) { + logerror("'%s': service not enabled for '%s'", + service->name, path); + errno = EACCES; + return -1; + } + /* * We'll ignore SIGTERM from now on, we have a * good client. */ signal(SIGTERM, SIG_IGN); + return service->fn(); +} + +static int upload_pack(void) +{ + /* Timeout as string */ + char timeout_buf[64]; + snprintf(timeout_buf, sizeof timeout_buf, "--timeout=%u", timeout); /* git-upload-pack only ever reads stuff, so this is safe */ @@ -270,10 +366,143 @@ static int upload(char *dir) return -1; } +static int upload_archive(void) +{ + execl_git_cmd("upload-archive", ".", NULL); + return -1; +} + +static struct daemon_service daemon_service[] = { + { "upload-archive", "uploadarch", upload_archive, 0, 1 }, + { "upload-pack", "uploadpack", upload_pack, 1, 1 }, +}; + +static void enable_service(const char *name, int ena) { + int i; + for (i = 0; i < ARRAY_SIZE(daemon_service); i++) { + if (!strcmp(daemon_service[i].name, name)) { + daemon_service[i].enabled = ena; + return; + } + } + die("No such service %s", name); +} + +static void make_service_overridable(const char *name, int ena) { + int i; + for (i = 0; i < ARRAY_SIZE(daemon_service); i++) { + if (!strcmp(daemon_service[i].name, name)) { + daemon_service[i].overridable = ena; + return; + } + } + die("No such service %s", name); +} + +/* + * Separate the "extra args" information as supplied by the client connection. + * Any resulting data is squirrelled away in the given interpolation table. + */ +static void parse_extra_args(struct interp *table, char *extra_args, int buflen) +{ + char *val; + int vallen; + char *end = extra_args + buflen; + + while (extra_args < end && *extra_args) { + saw_extended_args = 1; + if (strncasecmp("host=", extra_args, 5) == 0) { + val = extra_args + 5; + vallen = strlen(val) + 1; + if (*val) { + /* Split <host>:<port> at colon. */ + char *host = val; + char *port = strrchr(host, ':'); + if (port) { + *port = 0; + port++; + interp_set_entry(table, INTERP_SLOT_PORT, port); + } + interp_set_entry(table, INTERP_SLOT_HOST, host); + } + + /* On to the next one */ + extra_args = val + vallen; + } + } +} + +void fill_in_extra_table_entries(struct interp *itable) +{ + char *hp; + + /* + * Replace literal host with lowercase-ized hostname. + */ + hp = interp_table[INTERP_SLOT_HOST].value; + if (!hp) + return; + for ( ; *hp; hp++) + *hp = tolower(*hp); + + /* + * Locate canonical hostname and its IP address. + */ +#ifndef NO_IPV6 + { + struct addrinfo hints; + struct addrinfo *ai, *ai0; + int gai; + static char addrbuf[HOST_NAME_MAX + 1]; + + memset(&hints, 0, sizeof(hints)); + hints.ai_flags = AI_CANONNAME; + + gai = getaddrinfo(interp_table[INTERP_SLOT_HOST].value, 0, &hints, &ai0); + if (!gai) { + for (ai = ai0; ai; ai = ai->ai_next) { + struct sockaddr_in *sin_addr = (void *)ai->ai_addr; + + inet_ntop(AF_INET, &sin_addr->sin_addr, + addrbuf, sizeof(addrbuf)); + interp_set_entry(interp_table, + INTERP_SLOT_CANON_HOST, ai->ai_canonname); + interp_set_entry(interp_table, + INTERP_SLOT_IP, addrbuf); + break; + } + freeaddrinfo(ai0); + } + } +#else + { + struct hostent *hent; + struct sockaddr_in sa; + char **ap; + static char addrbuf[HOST_NAME_MAX + 1]; + + hent = gethostbyname(interp_table[INTERP_SLOT_HOST].value); + + ap = hent->h_addr_list; + memset(&sa, 0, sizeof sa); + sa.sin_family = hent->h_addrtype; + sa.sin_port = htons(0); + memcpy(&sa.sin_addr, *ap, hent->h_length); + + inet_ntop(hent->h_addrtype, &sa.sin_addr, + addrbuf, sizeof(addrbuf)); + + interp_set_entry(interp_table, INTERP_SLOT_CANON_HOST, hent->h_name); + interp_set_entry(interp_table, INTERP_SLOT_IP, addrbuf); + } +#endif +} + + static int execute(struct sockaddr *addr) { static char line[1000]; - int pktlen, len; + int pktlen, len, i; if (addr) { char addrbuf[256] = ""; @@ -307,11 +536,37 @@ static int execute(struct sockaddr *addr) loginfo("Extended attributes (%d bytes) exist <%.*s>", (int) pktlen - len, (int) pktlen - len, line + len + 1); - if (len && line[len-1] == '\n') + if (len && line[len-1] == '\n') { line[--len] = 0; + pktlen--; + } - if (!strncmp("git-upload-pack ", line, 16)) - return upload(line+16); + /* + * Initialize the path interpolation table for this connection. + */ + interp_clear_table(interp_table, ARRAY_SIZE(interp_table)); + interp_set_entry(interp_table, INTERP_SLOT_PERCENT, "%"); + + if (len != pktlen) { + parse_extra_args(interp_table, line + len + 1, pktlen - len - 1); + fill_in_extra_table_entries(interp_table); + } + + for (i = 0; i < ARRAY_SIZE(daemon_service); i++) { + struct daemon_service *s = &(daemon_service[i]); + int namelen = strlen(s->name); + if (!strncmp("git-", line, 4) && + !strncmp(s->name, line + 4, namelen) && + line[namelen + 4] == ' ') { + /* + * Note: The directory here is probably context sensitive, + * and might depend on the actual service being performed. + */ + interp_set_entry(interp_table, + INTERP_SLOT_DIR, line + namelen + 5); + return run_service(interp_table, s); + } + } logerror("Protocol error: '%s'", line); return -1; @@ -504,29 +759,27 @@ static int set_reuse_addr(int sockfd) #ifndef NO_IPV6 -static int socksetup(int port, int **socklist_p) +static int socksetup(char *listen_addr, int listen_port, int **socklist_p) { int socknum = 0, *socklist = NULL; int maxfd = -1; char pbuf[NI_MAXSERV]; - struct addrinfo hints, *ai0, *ai; int gai; - sprintf(pbuf, "%d", port); + sprintf(pbuf, "%d", listen_port); memset(&hints, 0, sizeof(hints)); hints.ai_family = AF_UNSPEC; hints.ai_socktype = SOCK_STREAM; hints.ai_protocol = IPPROTO_TCP; hints.ai_flags = AI_PASSIVE; - gai = getaddrinfo(NULL, pbuf, &hints, &ai0); + gai = getaddrinfo(listen_addr, pbuf, &hints, &ai0); if (gai) die("getaddrinfo() failed: %s\n", gai_strerror(gai)); for (ai = ai0; ai; ai = ai->ai_next) { int sockfd; - int *newlist; sockfd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol); if (sockfd < 0) @@ -560,11 +813,7 @@ static int socksetup(int port, int **socklist_p) continue; /* not fatal */ } - newlist = realloc(socklist, sizeof(int) * (socknum + 1)); - if (!newlist) - die("memory allocation failed: %s", strerror(errno)); - - socklist = newlist; + socklist = xrealloc(socklist, sizeof(int) * (socknum + 1)); socklist[socknum++] = sockfd; if (maxfd < sockfd) @@ -579,20 +828,27 @@ static int socksetup(int port, int **socklist_p) #else /* NO_IPV6 */ -static int socksetup(int port, int **socklist_p) +static int socksetup(char *listen_addr, int listen_port, int **socklist_p) { struct sockaddr_in sin; int sockfd; + memset(&sin, 0, sizeof sin); + sin.sin_family = AF_INET; + sin.sin_port = htons(listen_port); + + if (listen_addr) { + /* Well, host better be an IP address here. */ + if (inet_pton(AF_INET, listen_addr, &sin.sin_addr.s_addr) <= 0) + return 0; + } else { + sin.sin_addr.s_addr = htonl(INADDR_ANY); + } + sockfd = socket(AF_INET, SOCK_STREAM, 0); if (sockfd < 0) return 0; - memset(&sin, 0, sizeof sin); - sin.sin_family = AF_INET; - sin.sin_addr.s_addr = htonl(INADDR_ANY); - sin.sin_port = htons(port); - if (set_reuse_addr(sockfd)) { close(sockfd); return 0; @@ -701,23 +957,33 @@ static void store_pid(const char *path) fclose(f); } -static int serve(int port) +static int serve(char *listen_addr, int listen_port, struct passwd *pass, gid_t gid) { int socknum, *socklist; - socknum = socksetup(port, &socklist); + socknum = socksetup(listen_addr, listen_port, &socklist); if (socknum == 0) - die("unable to allocate any listen sockets on port %u", port); + die("unable to allocate any listen sockets on host %s port %u", + listen_addr, listen_port); + + if (pass && gid && + (initgroups(pass->pw_name, gid) || setgid (gid) || + setuid(pass->pw_uid))) + die("cannot drop privileges"); return service_loop(socknum, socklist); } int main(int argc, char **argv) { - int port = DEFAULT_GIT_PORT; + int listen_port = 0; + char *listen_addr = NULL; int inetd_mode = 0; - const char *pid_file = NULL; + const char *pid_file = NULL, *user_name = NULL, *group_name = NULL; int detach = 0; + struct passwd *pass = NULL; + struct group *group; + gid_t gid = 0; int i; /* Without this we cannot rely on waitpid() to tell @@ -728,12 +994,20 @@ int main(int argc, char **argv) for (i = 1; i < argc; i++) { char *arg = argv[i]; + if (!strncmp(arg, "--listen=", 9)) { + char *p = arg + 9; + char *ph = listen_addr = xmalloc(strlen(arg + 9) + 1); + while (*p) + *ph++ = tolower(*p++); + *ph = 0; + continue; + } if (!strncmp(arg, "--port=", 7)) { char *end; unsigned long n; n = strtoul(arg+7, &end, 0); if (arg[7] && !*end) { - port = n; + listen_port = n; continue; } } @@ -770,6 +1044,10 @@ int main(int argc, char **argv) base_path = arg+12; continue; } + if (!strncmp(arg, "--interpolated-path=", 20)) { + interpolated_path = arg+20; + continue; + } if (!strcmp(arg, "--reuseaddr")) { reuseaddr = 1; continue; @@ -791,6 +1069,30 @@ int main(int argc, char **argv) log_syslog = 1; continue; } + if (!strncmp(arg, "--user=", 7)) { + user_name = arg + 7; + continue; + } + if (!strncmp(arg, "--group=", 8)) { + group_name = arg + 8; + continue; + } + if (!strncmp(arg, "--enable=", 9)) { + enable_service(arg + 9, 1); + continue; + } + if (!strncmp(arg, "--disable=", 10)) { + enable_service(arg + 10, 0); + continue; + } + if (!strncmp(arg, "--allow-override=", 17)) { + make_service_overridable(arg + 17, 1); + continue; + } + if (!strncmp(arg, "--forbid-override=", 18)) { + make_service_overridable(arg + 18, 0); + continue; + } if (!strcmp(arg, "--")) { ok_paths = &argv[i+1]; break; @@ -802,6 +1104,33 @@ int main(int argc, char **argv) usage(daemon_usage); } + if (inetd_mode && (group_name || user_name)) + die("--user and --group are incompatible with --inetd"); + + if (inetd_mode && (listen_port || listen_addr)) + die("--listen= and --port= are incompatible with --inetd"); + else if (listen_port == 0) + listen_port = DEFAULT_GIT_PORT; + + if (group_name && !user_name) + die("--group supplied without --user"); + + if (user_name) { + pass = getpwnam(user_name); + if (!pass) + die("user not found - %s", user_name); + + if (!group_name) + gid = pass->pw_gid; + else { + group = getgrnam(group_name); + if (!group) + die("group not found - %s", group_name); + + gid = group->gr_gid; + } + } + if (log_syslog) { openlog("git-daemon", 0, LOG_DAEMON); set_die_routine(daemon_die); @@ -831,5 +1160,5 @@ int main(int argc, char **argv) if (pid_file) store_pid(pid_file); - return serve(port); + return serve(listen_addr, listen_port, pass, gid); } @@ -4,9 +4,6 @@ * Copyright (C) Linus Torvalds, 2005 */ -#include <time.h> -#include <sys/time.h> - #include "cache.h" static time_t my_mktime(struct tm *tm) @@ -37,6 +34,16 @@ static const char *weekday_names[] = { "Sundays", "Mondays", "Tuesdays", "Wednesdays", "Thursdays", "Fridays", "Saturdays" }; +static time_t gm_time_t(unsigned long time, int tz) +{ + int minutes; + + minutes = tz < 0 ? -tz : tz; + minutes = (minutes / 100)*60 + (minutes % 100); + minutes = tz < 0 ? -minutes : minutes; + return time + minutes * 60; +} + /* * The "tz" thing is passed in as this strange "decimal parse of tz" * thing, which means that tz -0100 is passed in as the integer -100, @@ -44,21 +51,58 @@ static const char *weekday_names[] = { */ static struct tm *time_to_tm(unsigned long time, int tz) { - time_t t; - int minutes; - - minutes = tz < 0 ? -tz : tz; - minutes = (minutes / 100)*60 + (minutes % 100); - minutes = tz < 0 ? -minutes : minutes; - t = time + minutes * 60; + time_t t = gm_time_t(time, tz); return gmtime(&t); } -const char *show_date(unsigned long time, int tz) +const char *show_date(unsigned long time, int tz, int relative) { struct tm *tm; static char timebuf[200]; + if (relative) { + unsigned long diff; + time_t t = gm_time_t(time, tz); + struct timeval now; + gettimeofday(&now, NULL); + if (now.tv_sec < t) + return "in the future"; + diff = now.tv_sec - t; + if (diff < 90) { + snprintf(timebuf, sizeof(timebuf), "%lu seconds ago", diff); + return timebuf; + } + /* Turn it into minutes */ + diff = (diff + 30) / 60; + if (diff < 90) { + snprintf(timebuf, sizeof(timebuf), "%lu minutes ago", diff); + return timebuf; + } + /* Turn it into hours */ + diff = (diff + 30) / 60; + if (diff < 36) { + snprintf(timebuf, sizeof(timebuf), "%lu hours ago", diff); + return timebuf; + } + /* We deal with number of days from here on */ + diff = (diff + 12) / 24; + if (diff < 14) { + snprintf(timebuf, sizeof(timebuf), "%lu days ago", diff); + return timebuf; + } + /* Say weeks for the past 10 weeks or so */ + if (diff < 70) { + snprintf(timebuf, sizeof(timebuf), "%lu weeks ago", (diff + 3) / 7); + return timebuf; + } + /* Say months for the past 12 months or so */ + if (diff < 360) { + snprintf(timebuf, sizeof(timebuf), "%lu months ago", (diff + 15) / 30); + return timebuf; + } + /* Else fall back on absolute format.. */ + } + tm = time_to_tm(time, tz); if (!tm) return NULL; @@ -209,8 +253,12 @@ static int match_alpha(const char *date, struct tm *tm, int *offset) } if (match_string(date, "PM") == 2) { - if (tm->tm_hour > 0 && tm->tm_hour < 12) - tm->tm_hour += 12; + tm->tm_hour = (tm->tm_hour % 12) + 12; + return 2; + } + + if (match_string(date, "AM") == 2) { + tm->tm_hour = (tm->tm_hour % 12) + 0; return 2; } @@ -551,6 +599,34 @@ static void date_tea(struct tm *tm, int *num) date_time(tm, 17); } +static void date_pm(struct tm *tm, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12) + 12; +} + +static void date_am(struct tm *tm, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12); +} + static const struct special { const char *name; void (*fn)(struct tm *, int *); @@ -559,6 +635,8 @@ static const struct special { { "noon", date_noon }, { "midnight", date_midnight }, { "tea", date_tea }, + { "PM", date_pm }, + { "AM", date_am }, { NULL } }; @@ -584,10 +662,10 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num) const struct typelen *tl; const struct special *s; const char *end = date; - int n = 1, i; + int i; - while (isalpha(*++end)) - n++; + while (isalpha(*++end)); + ; for (i = 0; i < 12; i++) { int match = match_string(date, month_names[i]); @@ -665,6 +743,27 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num) return end; } +static const char *approxidate_digit(const char *date, struct tm *tm, int *num) +{ + char *end; + unsigned long number = strtoul(date, &end, 10); + + switch (*end) { + case ':': + case '.': + case '/': + case '-': + if (isdigit(end[1])) { + int match = match_multi_number(number, *end, date, end, tm); + if (match) + return date + match; + } + } + + *num = number; + return end; +} + unsigned long approxidate(const char *date) { int number = 0; @@ -684,9 +783,7 @@ unsigned long approxidate(const char *date) break; date++; if (isdigit(c)) { - char *end; - number = strtoul(date-1, &end, 10); - date = end; + date = approxidate_digit(date-1, &tm, &number); continue; } if (isalpha(c)) diff --git a/diff-delta.c b/diff-delta.c index 51e2e56177..9f998d0a73 100644 --- a/diff-delta.c +++ b/diff-delta.c @@ -18,11 +18,8 @@ * licensing gets turned into GPLv2 within this project. */ -#include <stdlib.h> -#include <string.h> -#include "delta.h" - #include "git-compat-util.h" +#include "delta.h" /* maximum hash entry list for the same hash bucket */ #define HASH_LIMIT 64 @@ -392,7 +389,7 @@ create_delta(const struct delta_index *index, outsize = max_size + MAX_OP_SIZE + 1; if (max_size && outpos > max_size) break; - out = realloc(out, outsize); + out = xrealloc(out, outsize); if (!out) { free(tmp); return NULL; diff --git a/diff-lib.c b/diff-lib.c index 9edfa92626..2c9be60ed9 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -97,7 +97,7 @@ int run_diff_files(struct rev_info *revs, int silent_on_removed) * Show the diff for the 'ce' if we found the one * from the desired stage. */ - diff_unmerge(&revs->diffopt, ce->name); + diff_unmerge(&revs->diffopt, ce->name, 0, null_sha1); if (ce_stage(ce) != diff_unmerged_stage) continue; } @@ -213,6 +213,31 @@ static int show_modified(struct rev_info *revs, return -1; } + if (revs->combine_merges && !cached && + (hashcmp(sha1, old->sha1) || hashcmp(old->sha1, new->sha1))) { + struct combine_diff_path *p; + int pathlen = ce_namelen(new); + + p = xmalloc(combine_diff_path_size(2, pathlen)); + p->path = (char *) &p->parent[2]; + p->next = NULL; + p->len = pathlen; + memcpy(p->path, new->name, pathlen); + p->path[pathlen] = 0; + p->mode = ntohl(mode); + hashclr(p->sha1); + memset(p->parent, 0, 2 * sizeof(struct combine_diff_parent)); + p->parent[0].status = DIFF_STATUS_MODIFIED; + p->parent[0].mode = ntohl(new->ce_mode); + hashcpy(p->parent[0].sha1, new->sha1); + p->parent[1].status = DIFF_STATUS_MODIFIED; + p->parent[1].mode = ntohl(old->ce_mode); + hashcpy(p->parent[1].sha1, old->sha1); + show_combined_diff(p, 2, revs->dense_combined_merges, revs); + free(p); + return 0; + } + oldmode = old->ce_mode; if (mode == oldmode && !hashcmp(sha1, old->sha1) && !revs->diffopt.find_copies_harder) @@ -272,9 +297,12 @@ static int diff_cache(struct rev_info *revs, !show_modified(revs, ce, ac[1], 0, cached, match_missing)) break; - /* fallthru */ + diff_unmerge(&revs->diffopt, ce->name, + ntohl(ce->ce_mode), ce->sha1); + break; case 3: - diff_unmerge(&revs->diffopt, ce->name); + diff_unmerge(&revs->diffopt, ce->name, + 0, null_sha1); break; default: @@ -1,15 +1,19 @@ /* * Copyright (C) 2005 Junio C Hamano */ -#include <sys/types.h> -#include <sys/wait.h> -#include <signal.h> #include "cache.h" #include "quote.h" #include "diff.h" #include "diffcore.h" #include "delta.h" #include "xdiff-interface.h" +#include "color.h" + +#ifdef NO_FAST_WORKING_DIRECTORY +#define FAST_WORKING_DIRECTORY 0 +#else +#define FAST_WORKING_DIRECTORY 1 +#endif static int use_size_cache; @@ -17,15 +21,15 @@ static int diff_detect_rename_default; static int diff_rename_limit_default = -1; static int diff_use_color_default; -/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ -static char diff_colors[][24] = { +static char diff_colors[][COLOR_MAXLEN] = { "\033[m", /* reset */ - "", /* normal */ - "\033[1m", /* bold */ - "\033[36m", /* cyan */ - "\033[31m", /* red */ - "\033[32m", /* green */ - "\033[33m" /* yellow */ + "", /* PLAIN (normal) */ + "\033[1m", /* METAINFO (bold) */ + "\033[36m", /* FRAGINFO (cyan) */ + "\033[31m", /* OLD (red) */ + "\033[32m", /* NEW (green) */ + "\033[33m", /* COMMIT (yellow) */ + "\033[41m", /* WHITESPACE (red background) */ }; static int parse_diff_color_slot(const char *var, int ofs) @@ -42,122 +46,11 @@ static int parse_diff_color_slot(const char *var, int ofs) return DIFF_FILE_NEW; if (!strcasecmp(var+ofs, "commit")) return DIFF_COMMIT; + if (!strcasecmp(var+ofs, "whitespace")) + return DIFF_WHITESPACE; die("bad config variable '%s'", var); } -static int parse_color(const char *name, int len) -{ - static const char * const color_names[] = { - "normal", "black", "red", "green", "yellow", - "blue", "magenta", "cyan", "white" - }; - char *end; - int i; - for (i = 0; i < ARRAY_SIZE(color_names); i++) { - const char *str = color_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return i - 1; - } - i = strtol(name, &end, 10); - if (*name && !*end && i >= -1 && i <= 255) - return i; - return -2; -} - -static int parse_attr(const char *name, int len) -{ - static const int attr_values[] = { 1, 2, 4, 5, 7 }; - static const char * const attr_names[] = { - "bold", "dim", "ul", "blink", "reverse" - }; - int i; - for (i = 0; i < ARRAY_SIZE(attr_names); i++) { - const char *str = attr_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return attr_values[i]; - } - return -1; -} - -static void parse_diff_color_value(const char *value, const char *var, char *dst) -{ - const char *ptr = value; - int attr = -1; - int fg = -2; - int bg = -2; - - if (!strcasecmp(value, "reset")) { - strcpy(dst, "\033[m"); - return; - } - - /* [fg [bg]] [attr] */ - while (*ptr) { - const char *word = ptr; - int val, len = 0; - - while (word[len] && !isspace(word[len])) - len++; - - ptr = word + len; - while (*ptr && isspace(*ptr)) - ptr++; - - val = parse_color(word, len); - if (val >= -1) { - if (fg == -2) { - fg = val; - continue; - } - if (bg == -2) { - bg = val; - continue; - } - goto bad; - } - val = parse_attr(word, len); - if (val < 0 || attr != -1) - goto bad; - attr = val; - } - - if (attr >= 0 || fg >= 0 || bg >= 0) { - int sep = 0; - - *dst++ = '\033'; - *dst++ = '['; - if (attr >= 0) { - *dst++ = '0' + attr; - sep++; - } - if (fg >= 0) { - if (sep++) - *dst++ = ';'; - if (fg < 8) { - *dst++ = '3'; - *dst++ = '0' + fg; - } else { - dst += sprintf(dst, "38;5;%d", fg); - } - } - if (bg >= 0) { - if (sep++) - *dst++ = ';'; - if (bg < 8) { - *dst++ = '4'; - *dst++ = '0' + bg; - } else { - dst += sprintf(dst, "48;5;%d", bg); - } - } - *dst++ = 'm'; - } - *dst = 0; - return; -bad: - die("bad config value '%s' for variable '%s'", value, var); -} - /* * These are to give UI layer defaults. * The core-level commands such as git-diff-files should @@ -170,23 +63,8 @@ int git_diff_ui_config(const char *var, const char *value) diff_rename_limit_default = git_config_int(var, value); return 0; } - if (!strcmp(var, "diff.color")) { - if (!value) - diff_use_color_default = 1; /* bool */ - else if (!strcasecmp(value, "auto")) { - diff_use_color_default = 0; - if (isatty(1) || (pager_in_use && pager_use_color)) { - char *term = getenv("TERM"); - if (term && strcmp(term, "dumb")) - diff_use_color_default = 1; - } - } - else if (!strcasecmp(value, "never")) - diff_use_color_default = 0; - else if (!strcasecmp(value, "always")) - diff_use_color_default = 1; - else - diff_use_color_default = git_config_bool(var, value); + if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) { + diff_use_color_default = git_config_colorbool(var, value); return 0; } if (!strcmp(var, "diff.renames")) { @@ -199,9 +77,9 @@ int git_diff_ui_config(const char *var, const char *value) diff_detect_rename_default = DIFF_DETECT_RENAME; return 0; } - if (!strncmp(var, "diff.color.", 11)) { + if (!strncmp(var, "diff.color.", 11) || !strncmp(var, "color.diff.", 11)) { int slot = parse_diff_color_slot(var, 11); - parse_diff_color_value(value, var, diff_colors[slot]); + color_parse(value, var, diff_colors[slot]); return 0; } return git_default_config(var, value); @@ -216,7 +94,7 @@ static char *quote_one(const char *str) return NULL; needlen = quote_c_style(str, NULL, NULL, 0); if (!needlen) - return strdup(str); + return xstrdup(str); xp = xmalloc(needlen + 1); quote_c_style(str, xp, NULL, 0); return xp; @@ -333,7 +211,7 @@ static void emit_rewrite_diff(const char *name_a, diff_populate_filespec(two, 0); lc_a = count_lines(one->data, one->size); lc_b = count_lines(two->data, two->size); - printf("--- %s\n+++ %s\n@@ -", name_a, name_b); + printf("--- a/%s\n+++ b/%s\n@@ -", name_a, name_b); print_line_count(lc_a); printf(" +"); print_line_count(lc_b); @@ -511,9 +389,89 @@ const char *diff_get_color(int diff_use_color, enum color_diff ix) return ""; } +static void emit_line(const char *set, const char *reset, const char *line, int len) +{ + if (len > 0 && line[len-1] == '\n') + len--; + fputs(set, stdout); + fwrite(line, len, 1, stdout); + puts(reset); +} + +static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) +{ + int col0 = ecbdata->nparents; + int last_tab_in_indent = -1; + int last_space_in_indent = -1; + int i; + int tail = len; + int need_highlight_leading_space = 0; + const char *ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE); + const char *set = diff_get_color(ecbdata->color_diff, DIFF_FILE_NEW); + + if (!*ws) { + emit_line(set, reset, line, len); + return; + } + + /* The line is a newly added line. Does it have funny leading + * whitespaces? In indent, SP should never precede a TAB. + */ + for (i = col0; i < len; i++) { + if (line[i] == '\t') { + last_tab_in_indent = i; + if (0 <= last_space_in_indent) + need_highlight_leading_space = 1; + } + else if (line[i] == ' ') + last_space_in_indent = i; + else + break; + } + fputs(set, stdout); + fwrite(line, col0, 1, stdout); + fputs(reset, stdout); + if (((i == len) || line[i] == '\n') && i != col0) { + /* The whole line was indent */ + emit_line(ws, reset, line + col0, len - col0); + return; + } + i = col0; + if (need_highlight_leading_space) { + while (i < last_tab_in_indent) { + if (line[i] == ' ') { + fputs(ws, stdout); + putchar(' '); + fputs(reset, stdout); + } + else + putchar(line[i]); + i++; + } + } + tail = len - 1; + if (line[tail] == '\n' && i < tail) + tail--; + while (i < tail) { + if (!isspace(line[tail])) + break; + tail--; + } + if ((i < tail && line[tail + 1] != '\n')) { + /* This has whitespace between tail+1..len */ + fputs(set, stdout); + fwrite(line + i, tail - i + 1, 1, stdout); + fputs(reset, stdout); + emit_line(ws, reset, line + tail + 1, len - tail - 1); + } + else + emit_line(set, reset, line + i, len - i); +} + static void fn_out_consume(void *priv, char *line, unsigned long len) { int i; + int color; struct emit_callback *ecbdata = priv; const char *set = diff_get_color(ecbdata->color_diff, DIFF_METAINFO); const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET); @@ -531,45 +489,52 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) ; if (2 <= i && i < len && line[i] == ' ') { ecbdata->nparents = i - 1; - set = diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO); + emit_line(diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO), + reset, line, len); + return; } - else if (len < ecbdata->nparents) + + if (len < ecbdata->nparents) { set = reset; - else { - int nparents = ecbdata->nparents; - int color = DIFF_PLAIN; - if (ecbdata->diff_words && nparents != 1) - /* fall back to normal diff */ - free_diff_words_data(ecbdata); - if (ecbdata->diff_words) { - if (line[0] == '-') { - diff_words_append(line, len, - &ecbdata->diff_words->minus); - return; - } else if (line[0] == '+') { - diff_words_append(line, len, - &ecbdata->diff_words->plus); - return; - } - if (ecbdata->diff_words->minus.text.size || - ecbdata->diff_words->plus.text.size) - diff_words_show(ecbdata->diff_words); - line++; - len--; - } else - for (i = 0; i < nparents && len; i++) { - if (line[i] == '-') - color = DIFF_FILE_OLD; - else if (line[i] == '+') - color = DIFF_FILE_NEW; - } - set = diff_get_color(ecbdata->color_diff, color); + emit_line(reset, reset, line, len); + return; } - if (len > 0 && line[len-1] == '\n') + + color = DIFF_PLAIN; + if (ecbdata->diff_words && ecbdata->nparents != 1) + /* fall back to normal diff */ + free_diff_words_data(ecbdata); + if (ecbdata->diff_words) { + if (line[0] == '-') { + diff_words_append(line, len, + &ecbdata->diff_words->minus); + return; + } else if (line[0] == '+') { + diff_words_append(line, len, + &ecbdata->diff_words->plus); + return; + } + if (ecbdata->diff_words->minus.text.size || + ecbdata->diff_words->plus.text.size) + diff_words_show(ecbdata->diff_words); + line++; len--; - fputs (set, stdout); - fwrite (line, len, 1, stdout); - puts (reset); + emit_line(set, reset, line, len); + return; + } + for (i = 0; i < ecbdata->nparents && len; i++) { + if (line[i] == '-') + color = DIFF_FILE_OLD; + else if (line[i] == '+') + color = DIFF_FILE_NEW; + } + + if (color != DIFF_FILE_NEW) { + emit_line(diff_get_color(ecbdata->color_diff, color), + reset, line, len); + return; + } + emit_add_line(reset, ecbdata, line, len); } static char *pprint_rename(const char *a, const char *b) @@ -658,7 +623,7 @@ static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat, x->is_renamed = 1; } else - x->name = strdup(name_a); + x->name = xstrdup(name_a); return x; } @@ -673,21 +638,76 @@ static void diffstat_consume(void *priv, char *line, unsigned long len) x->deleted++; } -static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"; -static const char minuses[]= "----------------------------------------------------------------------"; const char mime_boundary_leader[] = "------------"; -static void show_stats(struct diffstat_t* data) +static int scale_linear(int it, int width, int max_change) +{ + /* + * make sure that at least one '-' is printed if there were deletions, + * and likewise for '+'. + */ + if (max_change < 2) + return it; + return ((it - 1) * (width - 1) + max_change - 1) / (max_change - 1); +} + +static void show_name(const char *prefix, const char *name, int len, + const char *reset, const char *set) +{ + printf(" %s%s%-*s%s |", set, prefix, len, name, reset); +} + +static void show_graph(char ch, int cnt, const char *set, const char *reset) +{ + if (cnt <= 0) + return; + printf("%s", set); + while (cnt--) + putchar(ch); + printf("%s", reset); +} + +static void show_stats(struct diffstat_t* data, struct diff_options *options) { int i, len, add, del, total, adds = 0, dels = 0; - int max, max_change = 0, max_len = 0; + int max_change = 0, max_len = 0; int total_files = data->nr; + int width, name_width; + const char *reset, *set, *add_c, *del_c; if (data->nr == 0) return; + width = options->stat_width ? options->stat_width : 80; + name_width = options->stat_name_width ? options->stat_name_width : 50; + + /* Sanity: give at least 5 columns to the graph, + * but leave at least 10 columns for the name. + */ + if (width < name_width + 15) { + if (name_width <= 25) + width = name_width + 15; + else + name_width = width - 15; + } + + /* Find the longest filename and max number of changes */ + reset = diff_get_color(options->color_diff, DIFF_RESET); + set = diff_get_color(options->color_diff, DIFF_PLAIN); + add_c = diff_get_color(options->color_diff, DIFF_FILE_NEW); + del_c = diff_get_color(options->color_diff, DIFF_FILE_OLD); + for (i = 0; i < data->nr; i++) { struct diffstat_file *file = data->files[i]; + int change = file->added + file->deleted; + + len = quote_c_style(file->name, NULL, NULL, 0); + if (len) { + char *qname = xmalloc(len + 1); + quote_c_style(file->name, qname, NULL, 0); + free(file->name); + file->name = qname; + } len = strlen(file->name); if (max_len < len) @@ -695,54 +715,53 @@ static void show_stats(struct diffstat_t* data) if (file->is_binary || file->is_unmerged) continue; - if (max_change < file->added + file->deleted) - max_change = file->added + file->deleted; + if (max_change < change) + max_change = change; } + /* Compute the width of the graph part; + * 10 is for one blank at the beginning of the line plus + * " | count " between the name and the graph. + * + * From here on, name_width is the width of the name area, + * and width is the width of the graph area. + */ + name_width = (name_width < max_len) ? name_width : max_len; + if (width < (name_width + 10) + max_change) + width = width - (name_width + 10); + else + width = max_change; + for (i = 0; i < data->nr; i++) { const char *prefix = ""; char *name = data->files[i]->name; int added = data->files[i]->added; int deleted = data->files[i]->deleted; - - if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { - char *qname = xmalloc(len + 1); - quote_c_style(name, qname, NULL, 0); - free(name); - data->files[i]->name = name = qname; - } + int name_len; /* * "scale" the filename */ - len = strlen(name); - max = max_len; - if (max > 50) - max = 50; - if (len > max) { + len = name_width; + name_len = strlen(name); + if (name_width < name_len) { char *slash; prefix = "..."; - max -= 3; - name += len - max; + len -= 3; + name += name_len - len; slash = strchr(name, '/'); if (slash) name = slash; } - len = max; - - /* - * scale the add/delete - */ - max = max_change; - if (max + len > 70) - max = 70 - len; if (data->files[i]->is_binary) { - printf(" %s%-*s | Bin\n", prefix, len, name); + show_name(prefix, name, len, reset, set); + printf(" Bin\n"); goto free_diffstat_file; } else if (data->files[i]->is_unmerged) { - printf(" %s%-*s | Unmerged\n", prefix, len, name); + show_name(prefix, name, len, reset, set); + printf(" Unmerged\n"); goto free_diffstat_file; } else if (!data->files[i]->is_renamed && @@ -751,27 +770,81 @@ static void show_stats(struct diffstat_t* data) goto free_diffstat_file; } + /* + * scale the add/delete + */ add = added; del = deleted; total = add + del; adds += add; dels += del; - if (max_change > 0) { - total = (total * max + max_change / 2) / max_change; - add = (add * max + max_change / 2) / max_change; - del = total - add; + if (width <= max_change) { + add = scale_linear(add, width, max_change); + del = scale_linear(del, width, max_change); + total = add + del; } - printf(" %s%-*s |%5d %.*s%.*s\n", prefix, - len, name, added + deleted, - add, pluses, del, minuses); + show_name(prefix, name, len, reset, set); + printf("%5d ", added + deleted); + show_graph('+', add, add_c, reset); + show_graph('-', del, del_c, reset); + putchar('\n'); free_diffstat_file: free(data->files[i]->name); free(data->files[i]); } free(data->files); + printf("%s %d files changed, %d insertions(+), %d deletions(-)%s\n", + set, total_files, adds, dels, reset); +} + +static void show_shortstats(struct diffstat_t* data) +{ + int i, adds = 0, dels = 0, total_files = data->nr; + + if (data->nr == 0) + return; + + for (i = 0; i < data->nr; i++) { + if (!data->files[i]->is_binary && + !data->files[i]->is_unmerged) { + int added = data->files[i]->added; + int deleted= data->files[i]->deleted; + if (!data->files[i]->is_renamed && + (added + deleted == 0)) { + total_files--; + } else { + adds += added; + dels += deleted; + } + } + free(data->files[i]->name); + free(data->files[i]); + } + free(data->files); + printf(" %d files changed, %d insertions(+), %d deletions(-)\n", - total_files, adds, dels); + total_files, adds, dels); +} + +static void show_numstat(struct diffstat_t* data, struct diff_options *options) +{ + int i; + + for (i = 0; i < data->nr; i++) { + struct diffstat_file *file = data->files[i]; + + if (file->is_binary) + printf("-\t-\t"); + else + printf("%d\t%d\t", file->added, file->deleted); + if (options->line_termination && + quote_c_style(file->name, NULL, NULL, 0)) + quote_c_style(file->name, NULL, stdout, 0); + else + fputs(file->name, stdout); + putchar(options->line_termination); + } } struct checkdiff_t { @@ -787,8 +860,6 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) if (line[0] == '+') { int i, spaces = 0; - data->lineno++; - /* check space before tab */ for (i = 1; i < len && (line[i] == ' ' || line[i] == '\t'); i++) if (line[i] == ' ') @@ -803,6 +874,8 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) if (isspace(line[len - 1])) printf("%s:%d: white space at end: %.*s\n", data->filename, data->lineno, (int)len, line); + + data->lineno++; } else if (line[0] == ' ') data->lineno++; else if (line[0] == '@') { @@ -838,7 +911,7 @@ static unsigned char *deflate_it(char *data, return deflated; } -static void emit_binary_diff(mmfile_t *one, mmfile_t *two) +static void emit_binary_diff_body(mmfile_t *one, mmfile_t *two) { void *cp; void *delta; @@ -849,7 +922,6 @@ static void emit_binary_diff(mmfile_t *one, mmfile_t *two) unsigned long deflate_size; unsigned long data_size; - printf("GIT binary patch\n"); /* We could do deflated delta, or we could do just deflated two, * whichever is smaller. */ @@ -898,6 +970,13 @@ static void emit_binary_diff(mmfile_t *one, mmfile_t *two) free(data); } +static void emit_binary_diff(mmfile_t *one, mmfile_t *two) +{ + printf("GIT binary patch\n"); + emit_binary_diff_body(one, two); + emit_binary_diff_body(two, one); +} + #define FIRST_FEW_BYTES 8000 static int mmfile_is_binary(mmfile_t *mf) { @@ -1111,7 +1190,7 @@ void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, * the work tree has that object contents, return true, so that * prepare_temp_file() does not have to inflate and extract. */ -static int work_tree_matches(const char *name, const unsigned char *sha1) +static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file) { struct cache_entry *ce; struct stat st; @@ -1132,6 +1211,18 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) if (!active_cache) return 0; + /* We want to avoid the working directory if our caller + * doesn't need the data in a normal file, this system + * is rather slow with its stat/open/mmap/close syscalls, + * and the object is contained in a pack file. The pack + * is probably already open and will be faster to obtain + * the data through than the working directory. Loose + * objects however would tend to be slower as they need + * to be individually opened and inflated. + */ + if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1, NULL)) + return 0; + len = strlen(name); pos = cache_name_pos(name, len); if (pos < 0) @@ -1218,7 +1309,7 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) if (s->data) return err; if (!s->sha1_valid || - work_tree_matches(s->path, s->sha1)) { + reuse_worktree_file(s->path, s->sha1, 0)) { struct stat st; int fd; if (lstat(s->path, &st) < 0) { @@ -1250,10 +1341,8 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) fd = open(s->path, O_RDONLY); if (fd < 0) goto err_empty; - s->data = mmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0); + s->data = xmmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (s->data == MAP_FAILED) - goto err_empty; s->should_munmap = 1; } else { @@ -1300,7 +1389,7 @@ static void prep_temp_blob(struct diff_tempfile *temp, fd = git_mkstemp(temp->tmp_path, TEMPFILE_PATH_LEN, ".diff_XXXXXX"); if (fd < 0) die("unable to create temp-file"); - if (write(fd, blob, size) != size) + if (write_in_full(fd, blob, size) != size) die("unable to write temp-file"); close(fd); temp->name = temp->tmp_path; @@ -1325,7 +1414,7 @@ static void prepare_temp_file(const char *name, } if (!one->sha1_valid || - work_tree_matches(name, one->sha1)) { + reuse_worktree_file(name, one->sha1, 1)) { struct stat st; if (lstat(name, &st) < 0) { if (errno == ENOENT) @@ -1582,6 +1671,12 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) if (hashcmp(one->sha1, two->sha1)) { int abbrev = o->full_index ? 40 : DEFAULT_ABBREV; + if (o->binary) { + mmfile_t mf; + if ((!fill_mmfile(&mf, one) && mmfile_is_binary(&mf)) || + (!fill_mmfile(&mf, two) && mmfile_is_binary(&mf))) + abbrev = 40; + } len += snprintf(msg + len, sizeof(msg) - len, "index %.*s..%.*s", abbrev, sha1_to_hex(one->sha1), @@ -1698,7 +1793,9 @@ int diff_setup_done(struct diff_options *options) DIFF_FORMAT_CHECKDIFF | DIFF_FORMAT_NO_OUTPUT)) options->output_format &= ~(DIFF_FORMAT_RAW | + DIFF_FORMAT_NUMSTAT | DIFF_FORMAT_DIFFSTAT | + DIFF_FORMAT_SHORTSTAT | DIFF_FORMAT_SUMMARY | DIFF_FORMAT_PATCH); @@ -1707,7 +1804,10 @@ int diff_setup_done(struct diff_options *options) * recursive bits for other formats here. */ if (options->output_format & (DIFF_FORMAT_PATCH | + DIFF_FORMAT_NUMSTAT | DIFF_FORMAT_DIFFSTAT | + DIFF_FORMAT_SHORTSTAT | + DIFF_FORMAT_SUMMARY | DIFF_FORMAT_CHECKDIFF)) options->recursive = 1; /* @@ -1795,8 +1895,39 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac) else if (!strcmp(arg, "--patch-with-raw")) { options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_RAW; } - else if (!strcmp(arg, "--stat")) + else if (!strcmp(arg, "--numstat")) { + options->output_format |= DIFF_FORMAT_NUMSTAT; + } + else if (!strcmp(arg, "--shortstat")) { + options->output_format |= DIFF_FORMAT_SHORTSTAT; + } + else if (!strncmp(arg, "--stat", 6)) { + char *end; + int width = options->stat_width; + int name_width = options->stat_name_width; + arg += 6; + end = (char *)arg; + + switch (*arg) { + case '-': + if (!strncmp(arg, "-width=", 7)) + width = strtoul(arg + 7, &end, 10); + else if (!strncmp(arg, "-name-width=", 12)) + name_width = strtoul(arg + 12, &end, 10); + break; + case '=': + width = strtoul(arg+1, &end, 10); + if (*end == ',') + name_width = strtoul(end+1, &end, 10); + } + + /* Important! This checks all the error cases! */ + if (*end) + return 0; options->output_format |= DIFF_FORMAT_DIFFSTAT; + options->stat_name_width = name_width; + options->stat_width = width; + } else if (!strcmp(arg, "--check")) options->output_format |= DIFF_FORMAT_CHECKDIFF; else if (!strcmp(arg, "--summary")) @@ -1812,7 +1943,7 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac) options->full_index = 1; else if (!strcmp(arg, "--binary")) { options->output_format |= DIFF_FORMAT_PATCH; - options->full_index = options->binary = 1; + options->binary = 1; } else if (!strcmp(arg, "-a") || !strcmp(arg, "--text")) { options->text = 1; @@ -2544,7 +2675,7 @@ void diff_flush(struct diff_options *options) separator++; } - if (output_format & DIFF_FORMAT_DIFFSTAT) { + if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT)) { struct diffstat_t diffstat; memset(&diffstat, 0, sizeof(struct diffstat_t)); @@ -2554,7 +2685,12 @@ void diff_flush(struct diff_options *options) if (check_pair_status(p)) diff_flush_stat(p, options, &diffstat); } - show_stats(&diffstat); + if (output_format & DIFF_FORMAT_NUMSTAT) + show_numstat(&diffstat, options); + if (output_format & DIFF_FORMAT_DIFFSTAT) + show_stats(&diffstat, options); + else if (output_format & DIFF_FORMAT_SHORTSTAT) + show_shortstats(&diffstat); separator++; } @@ -2581,6 +2717,9 @@ void diff_flush(struct diff_options *options) } } + if (output_format & DIFF_FORMAT_CALLBACK) + options->format_callback(q, options, options->format_callback_data); + for (i = 0; i < q->nr; i++) diff_free_filepair(q->queue[i]); free_queue: @@ -2734,10 +2873,12 @@ void diff_change(struct diff_options *options, } void diff_unmerge(struct diff_options *options, - const char *path) + const char *path, + unsigned mode, const unsigned char *sha1) { struct diff_filespec *one, *two; one = alloc_filespec(path); two = alloc_filespec(path); - diff_queue(&diff_queued_diff, one, two); + fill_filespec(one, sha1, mode); + diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1; } @@ -8,6 +8,7 @@ struct rev_info; struct diff_options; +struct diff_queue_struct; typedef void (*change_fn_t)(struct diff_options *options, unsigned old_mode, unsigned new_mode, @@ -20,25 +21,33 @@ typedef void (*add_remove_fn_t)(struct diff_options *options, const unsigned char *sha1, const char *base, const char *path); +typedef void (*diff_format_fn_t)(struct diff_queue_struct *q, + struct diff_options *options, void *data); + #define DIFF_FORMAT_RAW 0x0001 #define DIFF_FORMAT_DIFFSTAT 0x0002 -#define DIFF_FORMAT_SUMMARY 0x0004 -#define DIFF_FORMAT_PATCH 0x0008 +#define DIFF_FORMAT_NUMSTAT 0x0004 +#define DIFF_FORMAT_SUMMARY 0x0008 +#define DIFF_FORMAT_PATCH 0x0010 +#define DIFF_FORMAT_SHORTSTAT 0x0020 /* These override all above */ -#define DIFF_FORMAT_NAME 0x0010 -#define DIFF_FORMAT_NAME_STATUS 0x0020 -#define DIFF_FORMAT_CHECKDIFF 0x0040 +#define DIFF_FORMAT_NAME 0x0100 +#define DIFF_FORMAT_NAME_STATUS 0x0200 +#define DIFF_FORMAT_CHECKDIFF 0x0400 /* Same as output_format = 0 but we know that -s flag was given * and we should not give default value to output_format. */ -#define DIFF_FORMAT_NO_OUTPUT 0x0080 +#define DIFF_FORMAT_NO_OUTPUT 0x0800 + +#define DIFF_FORMAT_CALLBACK 0x1000 struct diff_options { const char *filter; const char *orderfile; const char *pickaxe; + const char *single_follow; unsigned recursive:1, tree_in_recursive:1, binary:1, @@ -63,11 +72,16 @@ struct diff_options { const char *stat_sep; long xdl_opts; + int stat_width; + int stat_name_width; + int nr_paths; const char **paths; int *pathlens; change_fn_t change; add_remove_fn_t add_remove; + diff_format_fn_t format_callback; + void *format_callback_data; }; enum color_diff { @@ -78,6 +92,7 @@ enum color_diff { DIFF_FILE_OLD = 4, DIFF_FILE_NEW = 5, DIFF_COMMIT = 6, + DIFF_WHITESPACE = 7, }; const char *diff_get_color(int diff_use_color, enum color_diff ix); @@ -89,6 +104,8 @@ extern int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt); extern int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt); +extern int diff_root_tree_sha1(const unsigned char *new, const char *base, + struct diff_options *opt); struct combine_diff_path { struct combine_diff_path *next; @@ -127,7 +144,9 @@ extern void diff_change(struct diff_options *, const char *base, const char *path); extern void diff_unmerge(struct diff_options *, - const char *path); + const char *path, + unsigned mode, + const unsigned char *sha1); extern int diff_scoreopt_parse(const char *opt); @@ -158,6 +177,7 @@ extern void diffcore_std_no_resolve(struct diff_options *); " --patch-with-raw\n" \ " output both a patch and the diff-raw format.\n" \ " --stat show diffstat instead of patch.\n" \ +" --numstat show numeric diffstat instead of patch.\n" \ " --patch-with-stat\n" \ " output a patch and prepend its diffstat.\n" \ " --name-only show only names of changed files.\n" \ diff --git a/diffcore-order.c b/diffcore-order.c index aef6da6044..7ad0946185 100644 --- a/diffcore-order.c +++ b/diffcore-order.c @@ -4,7 +4,6 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include <fnmatch.h> static char **order; static int order_cnt; diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c index cfcce315ba..de44adabf0 100644 --- a/diffcore-pickaxe.c +++ b/diffcore-pickaxe.c @@ -5,8 +5,6 @@ #include "diff.h" #include "diffcore.h" -#include <regex.h> - static unsigned int contains(struct diff_filespec *one, const char *needle, unsigned long len, regex_t *regexp) diff --git a/diffcore-rename.c b/diffcore-rename.c index ef239012b6..91fa2bea51 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -109,6 +109,8 @@ static int is_exact_match(struct diff_filespec *src, return 0; if (src->size != dst->size) return 0; + if (src->sha1_valid && dst->sha1_valid) + return !hashcmp(src->sha1, dst->sha1); if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0)) return 0; if (src->size == dst->size && @@ -256,11 +258,15 @@ void diffcore_rename(struct diff_options *options) for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; - if (!DIFF_FILE_VALID(p->one)) + if (!DIFF_FILE_VALID(p->one)) { if (!DIFF_FILE_VALID(p->two)) continue; /* unmerged */ + else if (options->single_follow && + strcmp(options->single_follow, p->two->path)) + continue; /* not interested */ else locate_rename_dst(p->two, 1); + } else if (!DIFF_FILE_VALID(p->two)) { /* If the source is a broken "delete", and * they did not really want to get broken, diff --git a/diffcore.h b/diffcore.h index 2249bc2c05..1ea80671e3 100644 --- a/diffcore.h +++ b/diffcore.h @@ -54,9 +54,9 @@ struct diff_filepair { unsigned source_stays : 1; /* all of R/C are copies */ unsigned broken_pair : 1; unsigned renamed_pair : 1; + unsigned is_unmerged : 1; }; -#define DIFF_PAIR_UNMERGED(p) \ - (!DIFF_FILE_VALID((p)->one) && !DIFF_FILE_VALID((p)->two)) +#define DIFF_PAIR_UNMERGED(p) ((p)->is_unmerged) #define DIFF_PAIR_RENAME(p) ((p)->renamed_pair) @@ -5,9 +5,6 @@ * Copyright (C) Linus Torvalds, 2005-2006 * Junio Hamano, 2005-2006 */ -#include <dirent.h> -#include <fnmatch.h> - #include "cache.h" #include "dir.h" @@ -43,6 +40,18 @@ int common_prefix(const char **pathspec) return prefix; } +/* + * Does 'match' matches the given name? + * A match is found if + * + * (1) the 'match' string is leading directory of 'name', or + * (2) the 'match' string is a wildcard and matches 'name', or + * (3) the 'match' string is exactly the same as 'name'. + * + * and the return value tells which case it was. + * + * It returns 0 when there is no match. + */ static int match_one(const char *match, const char *name, int namelen) { int matchlen; @@ -50,27 +59,30 @@ static int match_one(const char *match, const char *name, int namelen) /* If the match was just the prefix, we matched */ matchlen = strlen(match); if (!matchlen) - return 1; + return MATCHED_RECURSIVELY; /* * If we don't match the matchstring exactly, * we need to match by fnmatch */ if (strncmp(match, name, matchlen)) - return !fnmatch(match, name, 0); + return !fnmatch(match, name, 0) ? MATCHED_FNMATCH : 0; - /* - * If we did match the string exactly, we still - * need to make sure that it happened on a path - * component boundary (ie either the last character - * of the match was '/', or the next character of - * the name was '/' or the terminating NUL. - */ - return match[matchlen-1] == '/' || - name[matchlen] == '/' || - !name[matchlen]; + if (!name[matchlen]) + return MATCHED_EXACTLY; + if (match[matchlen-1] == '/' || name[matchlen] == '/') + return MATCHED_RECURSIVELY; + return 0; } +/* + * Given a name and a list of pathspecs, see if the name matches + * any of the pathspecs. The caller is also interested in seeing + * all pathspec matches some names it calls this function with + * (otherwise the user could have mistyped the unmatched pathspec), + * and a mark is left in seen[] array for pathspec element that + * actually matched anything. + */ int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen) { int retval; @@ -80,12 +92,16 @@ int match_pathspec(const char **pathspec, const char *name, int namelen, int pre namelen -= prefix; for (retval = 0; (match = *pathspec++) != NULL; seen++) { - if (retval & *seen) + int how; + if (retval && *seen == MATCHED_EXACTLY) continue; match += prefix; - if (match_one(match, name, namelen)) { - retval = 1; - *seen = 1; + how = match_one(match, name, namelen); + if (how) { + if (retval < how) + retval = how; + if (*seen < how) + *seen = how; } } return retval; @@ -101,8 +117,8 @@ void add_exclude(const char *string, const char *base, x->baselen = baselen; if (which->nr == which->alloc) { which->alloc = alloc_nr(which->alloc); - which->excludes = realloc(which->excludes, - which->alloc * sizeof(x)); + which->excludes = xrealloc(which->excludes, + which->alloc * sizeof(x)); } which->excludes[which->nr++] = x; } @@ -112,23 +128,21 @@ static int add_excludes_from_file_1(const char *fname, int baselen, struct exclude_list *which) { + struct stat st; int fd, i; long size; char *buf, *entry; fd = open(fname, O_RDONLY); - if (fd < 0) - goto err; - size = lseek(fd, 0, SEEK_END); - if (size < 0) + if (fd < 0 || fstat(fd, &st) < 0) goto err; - lseek(fd, 0, SEEK_SET); + size = st.st_size; if (size == 0) { close(fd); return 0; } buf = xmalloc(size+1); - if (read(fd, buf, size) != size) + if (read_in_full(fd, buf, size) != size) goto err; close(fd); @@ -158,7 +172,7 @@ void add_excludes_from_file(struct dir_struct *dir, const char *fname) die("cannot use %s as an exclude file", fname); } -static int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen) +int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen) { char exclude_file[PATH_MAX]; struct exclude_list *el = &dir->exclude_list[EXC_DIRS]; @@ -172,7 +186,7 @@ static int push_exclude_per_directory(struct dir_struct *dir, const char *base, return current_nr; } -static void pop_exclude_per_directory(struct dir_struct *dir, int stk) +void pop_exclude_per_directory(struct dir_struct *dir, int stk) { struct exclude_list *el = &dir->exclude_list[EXC_DIRS]; @@ -246,12 +260,12 @@ int excluded(struct dir_struct *dir, const char *pathname) return 0; } -static void add_name(struct dir_struct *dir, const char *pathname, int len) +struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len) { struct dir_entry *ent; if (cache_name_pos(pathname, len) >= 0) - return; + return NULL; if (dir->nr == dir->alloc) { int alloc = alloc_nr(dir->alloc); @@ -259,10 +273,12 @@ static void add_name(struct dir_struct *dir, const char *pathname, int len) dir->entries = xrealloc(dir->entries, alloc*sizeof(ent)); } ent = xmalloc(sizeof(*ent) + len + 1); + ent->ignored = ent->ignored_dir = 0; ent->len = len; memcpy(ent->name, pathname, len); ent->name[len] = 0; dir->entries[dir->nr++] = ent; + return ent; } static int dir_exists(const char *dirname, int len) @@ -285,7 +301,7 @@ static int dir_exists(const char *dirname, int len) * Also, we ignore the name ".git" (even if it is not a directory). * That likely will not change. */ -static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen) +static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen, int check_only) { DIR *fdir = opendir(path); int contents = 0; @@ -293,7 +309,7 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co if (fdir) { int exclude_stk; struct dirent *de; - char fullname[MAXPATHLEN + 1]; + char fullname[PATH_MAX + 1]; memcpy(fullname, base, baselen); exclude_stk = push_exclude_per_directory(dir, base, baselen); @@ -316,7 +332,6 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co switch (DTYPE(de)) { struct stat st; - int subdir, rewind_base; default: continue; case DT_UNKNOWN: @@ -330,26 +345,30 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co case DT_DIR: memcpy(fullname + baselen + len, "/", 2); len++; - rewind_base = dir->nr; - subdir = read_directory_recursive(dir, fullname, fullname, - baselen + len); if (dir->show_other_directories && - (subdir || !dir->hide_empty_directories) && !dir_exists(fullname, baselen + len)) { - /* Rewind the read subdirectory */ - while (dir->nr > rewind_base) - free(dir->entries[--dir->nr]); + if (dir->hide_empty_directories && + !read_directory_recursive(dir, + fullname, fullname, + baselen + len, 1)) + continue; break; } - contents += subdir; + + contents += read_directory_recursive(dir, + fullname, fullname, baselen + len, 0); continue; case DT_REG: case DT_LNK: break; } - add_name(dir, fullname, baselen + len); contents++; + if (check_only) + goto exit_early; + else + dir_add_name(dir, fullname, baselen + len); } +exit_early: closedir(fdir); pop_exclude_per_directory(dir, exclude_stk); @@ -395,7 +414,14 @@ int read_directory(struct dir_struct *dir, const char *path, const char *base, i } } - read_directory_recursive(dir, path, base, baselen); + read_directory_recursive(dir, path, base, baselen, 0); qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name); return dir->nr; } + +int +file_exists(const char *f) +{ + struct stat sb; + return stat(f, &sb) == 0; +} @@ -13,7 +13,9 @@ struct dir_entry { - int len; + unsigned int ignored : 1; + unsigned int ignored_dir : 1; + unsigned int len : 30; char name[FLEX_ARRAY]; /* more */ }; @@ -40,12 +42,21 @@ struct dir_struct { }; extern int common_prefix(const char **pathspec); + +#define MATCHED_RECURSIVELY 1 +#define MATCHED_FNMATCH 2 +#define MATCHED_EXACTLY 3 extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen); extern int read_directory(struct dir_struct *, const char *path, const char *base, int baselen); +extern int push_exclude_per_directory(struct dir_struct *, const char *, int); +extern void pop_exclude_per_directory(struct dir_struct *, int); + extern int excluded(struct dir_struct *, const char *); extern void add_excludes_from_file(struct dir_struct *, const char *fname); extern void add_exclude(const char *string, const char *base, int baselen, struct exclude_list *which); +extern int file_exists(const char *); +extern struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len); #endif @@ -1,5 +1,3 @@ -#include <sys/types.h> -#include <dirent.h> #include "cache.h" #include "blob.h" @@ -91,7 +89,7 @@ static int write_entry(struct cache_entry *ce, char *path, struct checkout *stat return error("git-checkout-index: unable to create file %s (%s)", path, strerror(errno)); } - wrote = write(fd, new, size); + wrote = write_in_full(fd, new, size); close(fd); free(new); if (wrote != size) @@ -106,7 +104,7 @@ static int write_entry(struct cache_entry *ce, char *path, struct checkout *stat return error("git-checkout-index: unable to create " "file %s (%s)", path, strerror(errno)); } - wrote = write(fd, new, size); + wrote = write_in_full(fd, new, size); close(fd); free(new); if (wrote != size) @@ -135,7 +133,7 @@ static int write_entry(struct cache_entry *ce, char *path, struct checkout *stat int checkout_entry(struct cache_entry *ce, struct checkout *state, char *topath) { - static char path[MAXPATHLEN+1]; + static char path[PATH_MAX + 1]; struct stat st; int len = state->base_dir_len; @@ -172,5 +170,3 @@ int checkout_entry(struct cache_entry *ce, struct checkout *state, char *topath) create_directories(path, state); return write_entry(ce, path, state, 0); } - - diff --git a/environment.c b/environment.c index e6bd0033b4..54c22f8248 100644 --- a/environment.c +++ b/environment.c @@ -15,18 +15,23 @@ int use_legacy_headers = 1; int trust_executable_bit = 1; int assume_unchanged; int prefer_symlink_refs; -int log_all_ref_updates; +int is_bare_repository_cfg = -1; /* unspecified */ +int log_all_ref_updates = -1; /* unspecified */ int warn_ambiguous_refs = 1; int repository_format_version; -char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; +char *git_commit_encoding; +char *git_log_output_encoding; int shared_repository = PERM_UMASK; const char *apply_default_whitespace; int zlib_compression_level = Z_DEFAULT_COMPRESSION; +size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE; +size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT; int pager_in_use; int pager_use_color = 1; -static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir, - *git_graft_file; +static const char *git_dir; +static char *git_object_dir, *git_index_file, *git_refs_dir, *git_graft_file; + static void setup_git_env(void) { git_dir = getenv(GIT_DIR_ENVIRONMENT); @@ -46,10 +51,23 @@ static void setup_git_env(void) } git_graft_file = getenv(GRAFT_ENVIRONMENT); if (!git_graft_file) - git_graft_file = strdup(git_path("info/grafts")); + git_graft_file = xstrdup(git_path("info/grafts")); +} + +int is_bare_repository(void) +{ + const char *dir, *s; + if (0 <= is_bare_repository_cfg) + return is_bare_repository_cfg; + + dir = get_git_dir(); + if (!strcmp(dir, DEFAULT_GIT_DIR_ENVIRONMENT)) + return 0; + s = strrchr(dir, '/'); + return !s || strcmp(s + 1, DEFAULT_GIT_DIR_ENVIRONMENT); } -char *get_git_dir(void) +const char *get_git_dir(void) { if (!git_dir) setup_git_env(); diff --git a/exec_cmd.c b/exec_cmd.c index e30936d72c..3996bce33f 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -21,7 +21,7 @@ const char *git_exec_path(void) if (current_exec_path) return current_exec_path; - env = getenv("GIT_EXEC_PATH"); + env = getenv(EXEC_PATH_ENVIRONMENT); if (env && *env) { return env; } @@ -35,7 +35,7 @@ int execv_git_cmd(const char **argv) char git_command[PATH_MAX + 1]; int i; const char *paths[] = { current_exec_path, - getenv("GIT_EXEC_PATH"), + getenv(EXEC_PATH_ENVIRONMENT), builtin_exec_path }; for (i = 0; i < ARRAY_SIZE(paths); ++i) { @@ -97,26 +97,12 @@ int execv_git_cmd(const char **argv) tmp = argv[0]; argv[0] = git_command; - if (getenv("GIT_TRACE")) { - const char **p = argv; - fputs("trace: exec:", stderr); - while (*p) { - fputc(' ', stderr); - sq_quote_print(stderr, *p); - ++p; - } - putc('\n', stderr); - fflush(stderr); - } + trace_argv_printf(argv, -1, "trace: exec:"); /* execve() can only ever return if it fails */ execve(git_command, (char **)argv, environ); - if (getenv("GIT_TRACE")) { - fprintf(stderr, "trace: exec failed: %s\n", - strerror(errno)); - fflush(stderr); - } + trace_printf("trace: exec failed: %s\n", strerror(errno)); argv[0] = tmp; } diff --git a/fast-import.c b/fast-import.c index 38e24bf6a6..492a8594bf 100644 --- a/fast-import.c +++ b/fast-import.c @@ -604,7 +604,7 @@ static size_t encode_header( int n = 1; unsigned char c; - if (type < OBJ_COMMIT || type > OBJ_DELTA) + if (type < OBJ_COMMIT || type > OBJ_REF_DELTA) die("bad type %d", type); c = (type << 4) | (size & 15); @@ -671,7 +671,7 @@ static int store_object( last->depth++; s.next_in = delta; s.avail_in = deltalen; - hdrlen = encode_header(OBJ_DELTA, deltalen, hdr); + hdrlen = encode_header(OBJ_REF_DELTA, deltalen, hdr); write_or_die(pack_fd, hdr, hdrlen); write_or_die(pack_fd, last->sha1, sizeof(sha1)); pack_size += hdrlen + sizeof(sha1); @@ -781,7 +781,7 @@ static void *unpack_non_delta_entry(unsigned long o, unsigned long sz) return result; } -static void *unpack_entry(unsigned long offset, +static void *gfi_unpack_entry(unsigned long offset, unsigned long *sizep, unsigned int *delta_depth); @@ -799,7 +799,7 @@ static void *unpack_delta_entry(unsigned long offset, base_oe = find_object(base_sha1); if (!base_oe) die("I'm broken; I can't find a base I know must be here."); - base = unpack_entry(base_oe->offset, &base_size, delta_depth); + base = gfi_unpack_entry(base_oe->offset, &base_size, delta_depth); delta_data = unpack_non_delta_entry(offset + 20, delta_size); result = patch_delta(base, base_size, delta_data, delta_size, @@ -813,7 +813,7 @@ static void *unpack_delta_entry(unsigned long offset, return result; } -static void *unpack_entry(unsigned long offset, +static void *gfi_unpack_entry(unsigned long offset, unsigned long *sizep, unsigned int *delta_depth) { @@ -822,7 +822,7 @@ static void *unpack_entry(unsigned long offset, offset = unpack_object_header(offset, &kind, &size); switch (kind) { - case OBJ_DELTA: + case OBJ_REF_DELTA: return unpack_delta_entry(offset, size, sizep, delta_depth); case OBJ_COMMIT: case OBJ_TREE: @@ -867,7 +867,7 @@ static void load_tree(struct tree_entry *root) if (myoe) { if (myoe->type != OBJ_TREE) die("Not a tree: %s", sha1_to_hex(sha1)); - buf = unpack_entry(myoe->offset, &size, &t->delta_depth); + buf = gfi_unpack_entry(myoe->offset, &size, &t->delta_depth); } else { char type[20]; buf = read_sha1_file(sha1, type, &size); @@ -1212,7 +1212,7 @@ static void dump_branches() for (i = 0; i < branch_table_sz; i++) { for (b = branch_table[i]; b; b = b->table_next_branch) { - lock = lock_any_ref_for_update(b->name, NULL, 0); + lock = lock_any_ref_for_update(b->name, NULL); if (!lock || write_ref_sha1(lock, b->sha1, msg) < 0) die("Can't write %s", b->name); } @@ -1228,7 +1228,7 @@ static void dump_tags() for (t = first_tag; t; t = t->next_tag) { sprintf(path, "refs/tags/%s", t->name); - lock = lock_any_ref_for_update(path, NULL, 0); + lock = lock_any_ref_for_update(path, NULL); if (!lock || write_ref_sha1(lock, t->sha1, msg) < 0) die("Can't write %s", path); } @@ -1476,7 +1476,7 @@ static void cmd_from(struct branch *b) if (oe->type != OBJ_COMMIT) die("Mark :%lu not a commit", idnum); hashcpy(b->sha1, oe->sha1); - buf = unpack_entry(oe->offset, &size, &depth); + buf = gfi_unpack_entry(oe->offset, &size, &depth); if (!buf || size < 46) die("Not a valid commit: %s", from); if (memcmp("tree ", buf, 5) diff --git a/fetch-clone.c b/fetch-clone.c deleted file mode 100644 index c5cf4776fa..0000000000 --- a/fetch-clone.c +++ /dev/null @@ -1,300 +0,0 @@ -#include "cache.h" -#include "exec_cmd.h" -#include "pkt-line.h" -#include <sys/wait.h> -#include <sys/time.h> - -static int finish_pack(const char *pack_tmp_name, const char *me) -{ - int pipe_fd[2]; - pid_t pid; - char idx[PATH_MAX]; - char final[PATH_MAX]; - char hash[41]; - unsigned char sha1[20]; - char *cp; - int err = 0; - - if (pipe(pipe_fd) < 0) - die("%s: unable to set up pipe", me); - - strcpy(idx, pack_tmp_name); /* ".git/objects/pack-XXXXXX" */ - cp = strrchr(idx, '/'); - memcpy(cp, "/pidx", 5); - - pid = fork(); - if (pid < 0) - die("%s: unable to fork off git-index-pack", me); - if (!pid) { - close(0); - dup2(pipe_fd[1], 1); - close(pipe_fd[0]); - close(pipe_fd[1]); - execl_git_cmd("index-pack", "-o", idx, pack_tmp_name, NULL); - error("cannot exec git-index-pack <%s> <%s>", - idx, pack_tmp_name); - exit(1); - } - close(pipe_fd[1]); - if (read(pipe_fd[0], hash, 40) != 40) { - error("%s: unable to read from git-index-pack", me); - err = 1; - } - close(pipe_fd[0]); - - for (;;) { - int status, code; - - if (waitpid(pid, &status, 0) < 0) { - if (errno == EINTR) - continue; - error("waitpid failed (%s)", strerror(errno)); - goto error_die; - } - if (WIFSIGNALED(status)) { - int sig = WTERMSIG(status); - error("git-index-pack died of signal %d", sig); - goto error_die; - } - if (!WIFEXITED(status)) { - error("git-index-pack died of unnatural causes %d", - status); - goto error_die; - } - code = WEXITSTATUS(status); - if (code) { - error("git-index-pack died with error code %d", code); - goto error_die; - } - if (err) - goto error_die; - break; - } - hash[40] = 0; - if (get_sha1_hex(hash, sha1)) { - error("git-index-pack reported nonsense '%s'", hash); - goto error_die; - } - /* Now we have pack in pack_tmp_name[], and - * idx in idx[]; rename them to their final names. - */ - snprintf(final, sizeof(final), - "%s/pack/pack-%s.pack", get_object_directory(), hash); - move_temp_to_file(pack_tmp_name, final); - chmod(final, 0444); - snprintf(final, sizeof(final), - "%s/pack/pack-%s.idx", get_object_directory(), hash); - move_temp_to_file(idx, final); - chmod(final, 0444); - return 0; - - error_die: - unlink(idx); - unlink(pack_tmp_name); - exit(1); -} - -static pid_t setup_sideband(int sideband, const char *me, int fd[2], int xd[2]) -{ - pid_t side_pid; - - if (!sideband) { - fd[0] = xd[0]; - fd[1] = xd[1]; - return 0; - } - /* xd[] is talking with upload-pack; subprocess reads from - * xd[0], spits out band#2 to stderr, and feeds us band#1 - * through our fd[0]. - */ - if (pipe(fd) < 0) - die("%s: unable to set up pipe", me); - side_pid = fork(); - if (side_pid < 0) - die("%s: unable to fork off sideband demultiplexer", me); - if (!side_pid) { - /* subprocess */ - close(fd[0]); - if (xd[0] != xd[1]) - close(xd[1]); - while (1) { - char buf[1024]; - int len = packet_read_line(xd[0], buf, sizeof(buf)); - if (len == 0) - break; - if (len < 1) - die("%s: protocol error: no band designator", - me); - len--; - switch (buf[0] & 0xFF) { - case 3: - safe_write(2, "remote: ", 8); - safe_write(2, buf+1, len); - safe_write(2, "\n", 1); - exit(1); - case 2: - safe_write(2, "remote: ", 8); - safe_write(2, buf+1, len); - continue; - case 1: - safe_write(fd[1], buf+1, len); - continue; - default: - die("%s: protocol error: bad band #%d", - me, (buf[0] & 0xFF)); - } - } - exit(0); - } - close(xd[0]); - close(fd[1]); - fd[1] = xd[1]; - return side_pid; -} - -int receive_unpack_pack(int xd[2], const char *me, int quiet, int sideband) -{ - int status; - pid_t pid, side_pid; - int fd[2]; - - side_pid = setup_sideband(sideband, me, fd, xd); - pid = fork(); - if (pid < 0) - die("%s: unable to fork off git-unpack-objects", me); - if (!pid) { - dup2(fd[0], 0); - close(fd[0]); - close(fd[1]); - execl_git_cmd("unpack-objects", quiet ? "-q" : NULL, NULL); - die("git-unpack-objects exec failed"); - } - close(fd[0]); - close(fd[1]); - while (waitpid(pid, &status, 0) < 0) { - if (errno != EINTR) - die("waiting for git-unpack-objects: %s", - strerror(errno)); - } - if (WIFEXITED(status)) { - int code = WEXITSTATUS(status); - if (code) - die("git-unpack-objects died with error code %d", - code); - return 0; - } - if (WIFSIGNALED(status)) { - int sig = WTERMSIG(status); - die("git-unpack-objects died of signal %d", sig); - } - die("git-unpack-objects died of unnatural causes %d", status); -} - -/* - * We average out the download speed over this many "events", where - * an event is a minimum of about half a second. That way, we get - * a reasonably stable number. - */ -#define NR_AVERAGE (4) - -/* - * A "binary msec" is a power-of-two-msec, aka 1/1024th of a second. - * Keeping the time in that format means that "bytes / msecs" means - * the same as kB/s (modulo rounding). - * - * 1000512 is a magic number (usecs in a second, rounded up by half - * of 1024, to make "rounding" come out right ;) - */ -#define usec_to_binarymsec(x) ((int)(x) / (1000512 >> 10)) - -int receive_keep_pack(int xd[2], const char *me, int quiet, int sideband) -{ - char tmpfile[PATH_MAX]; - int ofd, ifd, fd[2]; - unsigned long total; - static struct timeval prev_tv; - struct average { - unsigned long bytes; - unsigned long time; - } download[NR_AVERAGE] = { {0, 0}, }; - unsigned long avg_bytes, avg_time; - int idx = 0; - - setup_sideband(sideband, me, fd, xd); - - ifd = fd[0]; - snprintf(tmpfile, sizeof(tmpfile), - "%s/pack/tmp-XXXXXX", get_object_directory()); - ofd = mkstemp(tmpfile); - if (ofd < 0) - return error("unable to create temporary file %s", tmpfile); - - gettimeofday(&prev_tv, NULL); - total = 0; - avg_bytes = 0; - avg_time = 0; - while (1) { - char buf[8192]; - ssize_t sz, wsz, pos; - sz = read(ifd, buf, sizeof(buf)); - if (sz == 0) - break; - if (sz < 0) { - if (errno != EINTR && errno != EAGAIN) { - error("error reading pack (%s)", strerror(errno)); - close(ofd); - unlink(tmpfile); - return -1; - } - sz = 0; - } - pos = 0; - while (pos < sz) { - wsz = write(ofd, buf + pos, sz - pos); - if (wsz < 0) { - error("error writing pack (%s)", - strerror(errno)); - close(ofd); - unlink(tmpfile); - return -1; - } - pos += wsz; - } - total += sz; - if (!quiet) { - static unsigned long last; - struct timeval tv; - unsigned long diff = total - last; - /* not really "msecs", but a power-of-two millisec (1/1024th of a sec) */ - unsigned long msecs; - - gettimeofday(&tv, NULL); - msecs = tv.tv_sec - prev_tv.tv_sec; - msecs <<= 10; - msecs += usec_to_binarymsec(tv.tv_usec - prev_tv.tv_usec); - - if (msecs > 500) { - prev_tv = tv; - last = total; - - /* Update averages ..*/ - avg_bytes += diff; - avg_time += msecs; - avg_bytes -= download[idx].bytes; - avg_time -= download[idx].time; - download[idx].bytes = diff; - download[idx].time = msecs; - idx++; - if (idx >= NR_AVERAGE) - idx = 0; - - fprintf(stderr, "%4lu.%03luMB (%lu kB/s) \r", - total >> 20, - 1000*((total >> 10) & 1023)>>10, - avg_bytes / avg_time ); - } - } - } - close(ofd); - return finish_pack(tmpfile, me); -} diff --git a/fetch-pack.c b/fetch-pack.c index 377feded1c..1530a94794 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -3,13 +3,16 @@ #include "pkt-line.h" #include "commit.h" #include "tag.h" +#include "exec_cmd.h" +#include "sideband.h" static int keep_pack; static int quiet; static int verbose; static int fetch_all; +static int depth; static const char fetch_pack_usage[] = -"git-fetch-pack [--all] [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; +"git-fetch-pack [--all] [-q] [-v] [-k] [--thin] [--exec=upload-pack] [--depth=<n>] [host:]directory <refs>..."; static const char *exec = "git-upload-pack"; #define COMPLETE (1U << 0) @@ -42,7 +45,7 @@ static void rev_list_push(struct commit *commit, int mark) } } -static int rev_list_insert_ref(const char *path, const unsigned char *sha1) +static int rev_list_insert_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) { struct object *o = deref_tag(parse_object(sha1), path, 0); @@ -143,7 +146,7 @@ static int find_common(int fd[2], unsigned char *result_sha1, unsigned in_vain = 0; int got_continue = 0; - for_each_ref(rev_list_insert_ref); + for_each_ref(rev_list_insert_ref, NULL); fetching = 0; for ( ; refs ; refs = refs->next) { @@ -166,19 +169,52 @@ static int find_common(int fd[2], unsigned char *result_sha1, } if (!fetching) - packet_write(fd[1], "want %s%s%s%s\n", + packet_write(fd[1], "want %s%s%s%s%s%s\n", sha1_to_hex(remote), (multi_ack ? " multi_ack" : ""), - (use_sideband ? " side-band" : ""), - (use_thin_pack ? " thin-pack" : "")); + (use_sideband == 2 ? " side-band-64k" : ""), + (use_sideband == 1 ? " side-band" : ""), + (use_thin_pack ? " thin-pack" : ""), + " ofs-delta"); else packet_write(fd[1], "want %s\n", sha1_to_hex(remote)); fetching++; } + if (is_repository_shallow()) + write_shallow_commits(fd[1], 1); + if (depth > 0) + packet_write(fd[1], "deepen %d", depth); packet_flush(fd[1]); if (!fetching) return 1; + if (depth > 0) { + char line[1024]; + unsigned char sha1[20]; + int len; + + while ((len = packet_read_line(fd[0], line, sizeof(line)))) { + if (!strncmp("shallow ", line, 8)) { + if (get_sha1_hex(line + 8, sha1)) + die("invalid shallow line: %s", line); + register_shallow(sha1); + continue; + } + if (!strncmp("unshallow ", line, 10)) { + if (get_sha1_hex(line + 10, sha1)) + die("invalid unshallow line: %s", line); + if (!lookup_object(sha1)) + die("object not found: %s", line); + /* make sure that it is parsed as shallow */ + parse_object(sha1); + if (unregister_shallow(sha1)) + die("no shallow found: %s", line); + continue; + } + die("expected shallow/unshallow, got %s", line); + } + } + flushes = 0; retval = -1; while ((sha1 = get_rev())) { @@ -252,7 +288,7 @@ done: static struct commit_list *complete; -static int mark_complete(const char *path, const unsigned char *sha1) +static int mark_complete(const char *path, const unsigned char *sha1, int flag, void *cb_data) { struct object *o = parse_object(sha1); @@ -305,7 +341,8 @@ static void filter_refs(struct ref **refs, int nr_match, char **match) if (!memcmp(ref->name, "refs/", 5) && check_ref_format(ref->name + 5)) ; /* trash */ - else if (fetch_all) { + else if (fetch_all && + (!depth || strncmp(ref->name, "refs/tags/", 10) )) { *newtail = ref; ref->next = NULL; newtail = &ref->next; @@ -364,9 +401,11 @@ static int everything_local(struct ref **refs, int nr_match, char **match) } } - for_each_ref(mark_complete); - if (cutoff) - mark_recent_complete_commits(cutoff); + if (!depth) { + for_each_ref(mark_complete, NULL); + if (cutoff) + mark_recent_complete_commits(cutoff); + } /* * Mark all complete remote refs as common refs. @@ -414,6 +453,103 @@ static int everything_local(struct ref **refs, int nr_match, char **match) return retval; } +static pid_t setup_sideband(int fd[2], int xd[2]) +{ + pid_t side_pid; + + if (!use_sideband) { + fd[0] = xd[0]; + fd[1] = xd[1]; + return 0; + } + /* xd[] is talking with upload-pack; subprocess reads from + * xd[0], spits out band#2 to stderr, and feeds us band#1 + * through our fd[0]. + */ + if (pipe(fd) < 0) + die("fetch-pack: unable to set up pipe"); + side_pid = fork(); + if (side_pid < 0) + die("fetch-pack: unable to fork off sideband demultiplexer"); + if (!side_pid) { + /* subprocess */ + close(fd[0]); + if (xd[0] != xd[1]) + close(xd[1]); + if (recv_sideband("fetch-pack", xd[0], fd[1], 2)) + exit(1); + exit(0); + } + close(xd[0]); + close(fd[1]); + fd[1] = xd[1]; + return side_pid; +} + +static int get_pack(int xd[2], const char **argv) +{ + int status; + pid_t pid, side_pid; + int fd[2]; + + side_pid = setup_sideband(fd, xd); + pid = fork(); + if (pid < 0) + die("fetch-pack: unable to fork off %s", argv[0]); + if (!pid) { + dup2(fd[0], 0); + close(fd[0]); + close(fd[1]); + execv_git_cmd(argv); + die("%s exec failed", argv[0]); + } + close(fd[0]); + close(fd[1]); + while (waitpid(pid, &status, 0) < 0) { + if (errno != EINTR) + die("waiting for %s: %s", argv[0], strerror(errno)); + } + if (WIFEXITED(status)) { + int code = WEXITSTATUS(status); + if (code) + die("%s died with error code %d", argv[0], code); + return 0; + } + if (WIFSIGNALED(status)) { + int sig = WTERMSIG(status); + die("%s died of signal %d", argv[0], sig); + } + die("%s died of unnatural causes %d", argv[0], status); +} + +static int explode_rx_pack(int xd[2]) +{ + const char *argv[3] = { "unpack-objects", quiet ? "-q" : NULL, NULL }; + return get_pack(xd, argv); +} + +static int keep_rx_pack(int xd[2]) +{ + const char *argv[6]; + char keep_arg[256]; + int n = 0; + + argv[n++] = "index-pack"; + argv[n++] = "--stdin"; + if (!quiet) + argv[n++] = "-v"; + if (use_thin_pack) + argv[n++] = "--fix-thin"; + if (keep_pack > 1) { + int s = sprintf(keep_arg, "--keep=fetch-pack %i on ", getpid()); + if (gethostname(keep_arg + s, sizeof(keep_arg) - s)) + strcpy(keep_arg + s, "localhost"); + argv[n++] = keep_arg; + } + argv[n] = NULL; + return get_pack(xd, argv); +} + static int fetch_pack(int fd[2], int nr_match, char **match) { struct ref *ref; @@ -421,12 +557,19 @@ static int fetch_pack(int fd[2], int nr_match, char **match) int status; get_remote_heads(fd[0], &ref, 0, NULL, 0); + if (is_repository_shallow() && !server_supports("shallow")) + die("Server does not support shallow clients"); if (server_supports("multi_ack")) { if (verbose) fprintf(stderr, "Server supports multi_ack\n"); multi_ack = 1; } - if (server_supports("side-band")) { + if (server_supports("side-band-64k")) { + if (verbose) + fprintf(stderr, "Server supports side-band-64k\n"); + use_sideband = 2; + } + else if (server_supports("side-band")) { if (verbose) fprintf(stderr, "Server supports side-band\n"); use_sideband = 1; @@ -440,17 +583,13 @@ static int fetch_pack(int fd[2], int nr_match, char **match) goto all_done; } if (find_common(fd, sha1, ref) < 0) - if (!keep_pack) + if (keep_pack != 1) /* When cloning, it is not unusual to have * no common commit. */ fprintf(stderr, "warning: no common commits\n"); - if (keep_pack) - status = receive_keep_pack(fd, "git-fetch-pack", quiet, use_sideband); - else - status = receive_unpack_pack(fd, "git-fetch-pack", quiet, use_sideband); - + status = (keep_pack) ? keep_rx_pack(fd) : explode_rx_pack(fd); if (status) die("git-fetch-pack: fetch failed."); @@ -463,12 +602,38 @@ static int fetch_pack(int fd[2], int nr_match, char **match) return 0; } +static int remove_duplicates(int nr_heads, char **heads) +{ + int src, dst; + + for (src = dst = 0; src < nr_heads; src++) { + /* If heads[src] is different from any of + * heads[0..dst], push it in. + */ + int i; + for (i = 0; i < dst; i++) { + if (!strcmp(heads[i], heads[src])) + break; + } + if (i < dst) + continue; + if (src != dst) + heads[dst] = heads[src]; + dst++; + } + heads[dst] = 0; + return dst; +} + +static struct lock_file lock; + int main(int argc, char **argv) { int i, ret, nr_heads; char *dest = NULL, **heads; int fd[2]; pid_t pid; + struct stat st; setup_git_directory(); @@ -487,7 +652,7 @@ int main(int argc, char **argv) continue; } if (!strcmp("--keep", arg) || !strcmp("-k", arg)) { - keep_pack = 1; + keep_pack++; continue; } if (!strcmp("--thin", arg)) { @@ -502,6 +667,12 @@ int main(int argc, char **argv) verbose = 1; continue; } + if (!strncmp("--depth=", arg, 8)) { + depth = strtol(arg + 8, NULL, 0); + if (stat(git_path("shallow"), &st)) + st.st_mtime = 0; + continue; + } usage(fetch_pack_usage); } dest = arg; @@ -511,15 +682,15 @@ int main(int argc, char **argv) } if (!dest) usage(fetch_pack_usage); - if (keep_pack) - use_thin_pack = 0; pid = git_connect(fd, dest, exec); if (pid < 0) return 1; + if (heads && nr_heads) + nr_heads = remove_duplicates(nr_heads, heads); ret = fetch_pack(fd, nr_heads, heads); close(fd[0]); close(fd[1]); - finish_connect(pid); + ret |= finish_connect(pid); if (!ret && nr_heads) { /* If the heads to pull were given, we should have @@ -534,5 +705,34 @@ int main(int argc, char **argv) } } - return ret; + if (!ret && depth > 0) { + struct cache_time mtime; + char *shallow = git_path("shallow"); + int fd; + + mtime.sec = st.st_mtime; +#ifdef USE_NSEC + mtime.usec = st.st_mtim.usec; +#endif + if (stat(shallow, &st)) { + if (mtime.sec) + die("shallow file was removed during fetch"); + } else if (st.st_mtime != mtime.sec +#ifdef USE_NSEC + || st.st_mtim.usec != mtime.usec +#endif + ) + die("shallow file was changed during fetch"); + + fd = hold_lock_file_for_update(&lock, shallow, 1); + if (!write_shallow_commits(fd, 0)) { + unlink(shallow); + rollback_lock_file(&lock); + } else { + close(fd); + commit_lock_file(&lock); + } + } + + return !!ret; } @@ -1,6 +1,5 @@ -#include "fetch.h" - #include "cache.h" +#include "fetch.h" #include "commit.h" #include "tree.h" #include "tree-walk.h" @@ -22,14 +21,15 @@ void pull_say(const char *fmt, const char *hex) fprintf(stderr, fmt, hex); } -static void report_missing(const char *what, const unsigned char *missing) +static void report_missing(const struct object *obj) { char missing_hex[41]; - - strcpy(missing_hex, sha1_to_hex(missing));; - fprintf(stderr, - "Cannot obtain needed %s %s\nwhile processing commit %s.\n", - what, missing_hex, sha1_to_hex(current_commit_sha1)); + strcpy(missing_hex, sha1_to_hex(obj->sha1));; + fprintf(stderr, "Cannot obtain needed %s %s\n", + obj->type ? typename(obj->type): "object", missing_hex); + if (!is_null_sha1(current_commit_sha1)) + fprintf(stderr, "while processing commit %s.\n", + sha1_to_hex(current_commit_sha1)); } static int process(struct object *obj); @@ -177,7 +177,7 @@ static int loop(void) */ if (! (obj->flags & TO_SCAN)) { if (fetch(obj->sha1)) { - report_missing(typename(obj->type), obj->sha1); + report_missing(obj); return -1; } } @@ -201,7 +201,7 @@ static int interpret_target(char *target, unsigned char *sha1) return -1; } -static int mark_complete(const char *path, const unsigned char *sha1) +static int mark_complete(const char *path, const unsigned char *sha1, int flag, void *cb_data) { struct commit *commit = lookup_commit_reference_gently(sha1, 1); if (commit) { @@ -234,8 +234,8 @@ int pull_targets_stdin(char ***target, const char ***write_ref) *target = xrealloc(*target, targets_alloc * sizeof(**target)); *write_ref = xrealloc(*write_ref, targets_alloc * sizeof(**write_ref)); } - (*target)[targets] = strdup(tg_one); - (*write_ref)[targets] = rf_one ? strdup(rf_one) : NULL; + (*target)[targets] = xstrdup(tg_one); + (*write_ref)[targets] = rf_one ? xstrdup(rf_one) : NULL; targets++; } return targets; @@ -266,7 +266,7 @@ int pull(int targets, char **target, const char **write_ref, if (!write_ref || !write_ref[i]) continue; - lock[i] = lock_ref_sha1(write_ref[i], NULL, 0); + lock[i] = lock_ref_sha1(write_ref[i], NULL); if (!lock[i]) { error("Can't lock ref %s", write_ref[i]); goto unlock_and_fail; @@ -274,7 +274,7 @@ int pull(int targets, char **target, const char **write_ref, } if (!get_recover) - for_each_ref(mark_complete); + for_each_ref(mark_complete, NULL); for (i = 0; i < targets; i++) { if (interpret_target(target[i], &sha1[20 * i])) { @@ -302,8 +302,7 @@ int pull(int targets, char **target, const char **write_ref, if (ret) goto unlock_and_fail; } - if (msg) - free(msg); + free(msg); return 0; diff --git a/fsck-objects.c b/fsck-objects.c index ae0ec8d039..81f00db90b 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -1,6 +1,3 @@ -#include <sys/types.h> -#include <dirent.h> - #include "cache.h" #include "commit.h" #include "tree.h" @@ -293,7 +290,7 @@ static int fsck_sha1(unsigned char *sha1) { struct object *obj = parse_object(sha1); if (!obj) - return error("%s: object not found", sha1_to_hex(sha1)); + return error("%s: object corrupt or missing", sha1_to_hex(sha1)); if (obj->flags & SEEN) return 0; obj->flags |= SEEN; @@ -402,7 +399,28 @@ static void fsck_dir(int i, char *path) static int default_refs; -static int fsck_handle_ref(const char *refname, const unsigned char *sha1) +static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1, + const char *email, unsigned long timestamp, int tz, + const char *message, void *cb_data) +{ + struct object *obj; + + if (!is_null_sha1(osha1)) { + obj = lookup_object(osha1); + if (obj) { + obj->used = 1; + mark_reachable(obj, REACHABLE); + } + } + obj = lookup_object(nsha1); + if (obj) { + obj->used = 1; + mark_reachable(obj, REACHABLE); + } + return 0; +} + +static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { struct object *obj; @@ -419,14 +437,32 @@ static int fsck_handle_ref(const char *refname, const unsigned char *sha1) default_refs++; obj->used = 1; mark_reachable(obj, REACHABLE); + + for_each_reflog_ent(refname, fsck_handle_reflog_ent, NULL); + return 0; } static void get_default_heads(void) { - for_each_ref(fsck_handle_ref); - if (!default_refs) - die("No default references"); + for_each_ref(fsck_handle_ref, NULL); + + /* + * Not having any default heads isn't really fatal, but + * it does mean that "--unreachable" no longer makes any + * sense (since in this case everything will obviously + * be unreachable by definition. + * + * Showing dangling objects is valid, though (as those + * dangling objects are likely lost heads). + * + * So we just print a warning about it, and clear the + * "show_unreachable" flag. + */ + if (!default_refs) { + error("No default references"); + show_unreachable = 0; + } } static void fsck_object_dir(const char *path) @@ -443,15 +479,14 @@ static void fsck_object_dir(const char *path) static int fsck_head_link(void) { unsigned char sha1[20]; - const char *git_HEAD = strdup(git_path("HEAD")); - const char *git_refs_heads_master = resolve_ref(git_HEAD, sha1, 1); - int pfxlen = strlen(git_HEAD) - 4; /* strip .../.git/ part */ + int flag; + const char *head_points_at = resolve_ref("HEAD", sha1, 1, &flag); - if (!git_refs_heads_master) + if (!head_points_at || !(flag & REF_ISSYMREF)) return error("HEAD is not a symbolic ref"); - if (strncmp(git_refs_heads_master + pfxlen, "refs/heads/", 11)) + if (strncmp(head_points_at, "refs/heads/", 11)) return error("HEAD points to something strange (%s)", - git_refs_heads_master + pfxlen); + head_points_at); if (is_null_sha1(sha1)) return error("HEAD: not a valid git pointer"); return 0; diff --git a/generate-cmdlist.sh b/generate-cmdlist.sh index ec1eda20de..975777f05e 100755 --- a/generate-cmdlist.sh +++ b/generate-cmdlist.sh @@ -4,7 +4,7 @@ echo "/* Automatically generated by $0 */ struct cmdname_help { char name[16]; - char help[64]; + char help[80]; }; struct cmdname_help common_cmds[] = {" @@ -12,6 +12,7 @@ struct cmdname_help common_cmds[] = {" sort <<\EOF | add apply +archive bisect branch checkout @@ -21,7 +22,7 @@ commit diff fetch grep -init-db +init log merge mv @@ -36,7 +37,6 @@ show show-branch status tag -verify-tag EOF while read cmd do diff --git a/git-add--interactive.perl b/git-add--interactive.perl new file mode 100755 index 0000000000..0057f86588 --- /dev/null +++ b/git-add--interactive.perl @@ -0,0 +1,804 @@ +#!/usr/bin/perl -w + + +use strict; + +sub run_cmd_pipe { + my $fh = undef; + open($fh, '-|', @_) or die; + return <$fh>; +} + +my ($GIT_DIR) = run_cmd_pipe(qw(git rev-parse --git-dir)); + +if (!defined $GIT_DIR) { + exit(1); # rev-parse would have already said "not a git repo" +} +chomp($GIT_DIR); + +sub refresh { + my $fh; + open $fh, '-|', qw(git update-index --refresh) + or die; + while (<$fh>) { + ;# ignore 'needs update' + } + close $fh; +} + +sub list_untracked { + map { + chomp $_; + $_; + } + run_cmd_pipe(qw(git ls-files --others + --exclude-per-directory=.gitignore), + "--exclude-from=$GIT_DIR/info/exclude", + '--', @_); +} + +my $status_fmt = '%12s %12s %s'; +my $status_head = sprintf($status_fmt, 'staged', 'unstaged', 'path'); + +# Returns list of hashes, contents of each of which are: +# PRINT: print message +# VALUE: pathname +# BINARY: is a binary path +# INDEX: is index different from HEAD? +# FILE: is file different from index? +# INDEX_ADDDEL: is it add/delete between HEAD and index? +# FILE_ADDDEL: is it add/delete between index and file? + +sub list_modified { + my ($only) = @_; + my (%data, @return); + my ($add, $del, $adddel, $file); + + for (run_cmd_pipe(qw(git diff-index --cached + --numstat --summary HEAD))) { + if (($add, $del, $file) = + /^([-\d]+) ([-\d]+) (.*)/) { + my ($change, $bin); + if ($add eq '-' && $del eq '-') { + $change = 'binary'; + $bin = 1; + } + else { + $change = "+$add/-$del"; + } + $data{$file} = { + INDEX => $change, + BINARY => $bin, + FILE => 'nothing', + } + } + elsif (($adddel, $file) = + /^ (create|delete) mode [0-7]+ (.*)$/) { + $data{$file}{INDEX_ADDDEL} = $adddel; + } + } + + for (run_cmd_pipe(qw(git diff-files --numstat --summary))) { + if (($add, $del, $file) = + /^([-\d]+) ([-\d]+) (.*)/) { + if (!exists $data{$file}) { + $data{$file} = +{ + INDEX => 'unchanged', + BINARY => 0, + }; + } + my ($change, $bin); + if ($add eq '-' && $del eq '-') { + $change = 'binary'; + $bin = 1; + } + else { + $change = "+$add/-$del"; + } + $data{$file}{FILE} = $change; + if ($bin) { + $data{$file}{BINARY} = 1; + } + } + elsif (($adddel, $file) = + /^ (create|delete) mode [0-7]+ (.*)$/) { + $data{$file}{FILE_ADDDEL} = $adddel; + } + } + + for (sort keys %data) { + my $it = $data{$_}; + + if ($only) { + if ($only eq 'index-only') { + next if ($it->{INDEX} eq 'unchanged'); + } + if ($only eq 'file-only') { + next if ($it->{FILE} eq 'nothing'); + } + } + push @return, +{ + VALUE => $_, + PRINT => (sprintf $status_fmt, + $it->{INDEX}, $it->{FILE}, $_), + %$it, + }; + } + return @return; +} + +sub find_unique { + my ($string, @stuff) = @_; + my $found = undef; + for (my $i = 0; $i < @stuff; $i++) { + my $it = $stuff[$i]; + my $hit = undef; + if (ref $it) { + if ((ref $it) eq 'ARRAY') { + $it = $it->[0]; + } + else { + $it = $it->{VALUE}; + } + } + eval { + if ($it =~ /^$string/) { + $hit = 1; + }; + }; + if (defined $hit && defined $found) { + return undef; + } + if ($hit) { + $found = $i + 1; + } + } + return $found; +} + +sub list_and_choose { + my ($opts, @stuff) = @_; + my (@chosen, @return); + my $i; + + TOPLOOP: + while (1) { + my $last_lf = 0; + + if ($opts->{HEADER}) { + if (!$opts->{LIST_FLAT}) { + print " "; + } + print "$opts->{HEADER}\n"; + } + for ($i = 0; $i < @stuff; $i++) { + my $chosen = $chosen[$i] ? '*' : ' '; + my $print = $stuff[$i]; + if (ref $print) { + if ((ref $print) eq 'ARRAY') { + $print = $print->[0]; + } + else { + $print = $print->{PRINT}; + } + } + printf("%s%2d: %s", $chosen, $i+1, $print); + if (($opts->{LIST_FLAT}) && + (($i + 1) % ($opts->{LIST_FLAT}))) { + print "\t"; + $last_lf = 0; + } + else { + print "\n"; + $last_lf = 1; + } + } + if (!$last_lf) { + print "\n"; + } + + return if ($opts->{LIST_ONLY}); + + print $opts->{PROMPT}; + if ($opts->{SINGLETON}) { + print "> "; + } + else { + print ">> "; + } + my $line = <STDIN>; + last if (!$line); + chomp $line; + my $donesomething = 0; + for my $choice (split(/[\s,]+/, $line)) { + my $choose = 1; + my ($bottom, $top); + + # Input that begins with '-'; unchoose + if ($choice =~ s/^-//) { + $choose = 0; + } + # A range can be specified like 5-7 + if ($choice =~ /^(\d+)-(\d+)$/) { + ($bottom, $top) = ($1, $2); + } + elsif ($choice =~ /^\d+$/) { + $bottom = $top = $choice; + } + elsif ($choice eq '*') { + $bottom = 1; + $top = 1 + @stuff; + } + else { + $bottom = $top = find_unique($choice, @stuff); + if (!defined $bottom) { + print "Huh ($choice)?\n"; + next TOPLOOP; + } + } + if ($opts->{SINGLETON} && $bottom != $top) { + print "Huh ($choice)?\n"; + next TOPLOOP; + } + for ($i = $bottom-1; $i <= $top-1; $i++) { + next if (@stuff <= $i); + $chosen[$i] = $choose; + $donesomething++; + } + } + last if (!$donesomething || $opts->{IMMEDIATE}); + } + for ($i = 0; $i < @stuff; $i++) { + if ($chosen[$i]) { + push @return, $stuff[$i]; + } + } + return @return; +} + +sub status_cmd { + list_and_choose({ LIST_ONLY => 1, HEADER => $status_head }, + list_modified()); + print "\n"; +} + +sub say_n_paths { + my $did = shift @_; + my $cnt = scalar @_; + print "$did "; + if (1 < $cnt) { + print "$cnt paths\n"; + } + else { + print "one path\n"; + } +} + +sub update_cmd { + my @mods = list_modified('file-only'); + return if (!@mods); + + my @update = list_and_choose({ PROMPT => 'Update', + HEADER => $status_head, }, + @mods); + if (@update) { + system(qw(git update-index --add --), + map { $_->{VALUE} } @update); + say_n_paths('updated', @update); + } + print "\n"; +} + +sub revert_cmd { + my @update = list_and_choose({ PROMPT => 'Revert', + HEADER => $status_head, }, + list_modified()); + if (@update) { + my @lines = run_cmd_pipe(qw(git ls-tree HEAD --), + map { $_->{VALUE} } @update); + my $fh; + open $fh, '|-', qw(git update-index --index-info) + or die; + for (@lines) { + print $fh $_; + } + close($fh); + for (@update) { + if ($_->{INDEX_ADDDEL} && + $_->{INDEX_ADDDEL} eq 'create') { + system(qw(git update-index --force-remove --), + $_->{VALUE}); + print "note: $_->{VALUE} is untracked now.\n"; + } + } + refresh(); + say_n_paths('reverted', @update); + } + print "\n"; +} + +sub add_untracked_cmd { + my @add = list_and_choose({ PROMPT => 'Add untracked' }, + list_untracked()); + if (@add) { + system(qw(git update-index --add --), @add); + say_n_paths('added', @add); + } + print "\n"; +} + +sub parse_diff { + my ($path) = @_; + my @diff = run_cmd_pipe(qw(git diff-files -p --), $path); + my (@hunk) = { TEXT => [] }; + + for (@diff) { + if (/^@@ /) { + push @hunk, { TEXT => [] }; + } + push @{$hunk[-1]{TEXT}}, $_; + } + return @hunk; +} + +sub hunk_splittable { + my ($text) = @_; + + my @s = split_hunk($text); + return (1 < @s); +} + +sub parse_hunk_header { + my ($line) = @_; + my ($o_ofs, $o_cnt, $n_ofs, $n_cnt) = + $line =~ /^@@ -(\d+)(?:,(\d+)) \+(\d+)(?:,(\d+)) @@/; + return ($o_ofs, $o_cnt, $n_ofs, $n_cnt); +} + +sub split_hunk { + my ($text) = @_; + my @split = (); + + # If there are context lines in the middle of a hunk, + # it can be split, but we would need to take care of + # overlaps later. + + my ($o_ofs, $o_cnt, $n_ofs, $n_cnt) = parse_hunk_header($text->[0]); + my $hunk_start = 1; + my $next_hunk_start; + + OUTER: + while (1) { + my $next_hunk_start = undef; + my $i = $hunk_start - 1; + my $this = +{ + TEXT => [], + OLD => $o_ofs, + NEW => $n_ofs, + OCNT => 0, + NCNT => 0, + ADDDEL => 0, + POSTCTX => 0, + }; + + while (++$i < @$text) { + my $line = $text->[$i]; + if ($line =~ /^ /) { + if ($this->{ADDDEL} && + !defined $next_hunk_start) { + # We have seen leading context and + # adds/dels and then here is another + # context, which is trailing for this + # split hunk and leading for the next + # one. + $next_hunk_start = $i; + } + push @{$this->{TEXT}}, $line; + $this->{OCNT}++; + $this->{NCNT}++; + if (defined $next_hunk_start) { + $this->{POSTCTX}++; + } + next; + } + + # add/del + if (defined $next_hunk_start) { + # We are done with the current hunk and + # this is the first real change for the + # next split one. + $hunk_start = $next_hunk_start; + $o_ofs = $this->{OLD} + $this->{OCNT}; + $n_ofs = $this->{NEW} + $this->{NCNT}; + $o_ofs -= $this->{POSTCTX}; + $n_ofs -= $this->{POSTCTX}; + push @split, $this; + redo OUTER; + } + push @{$this->{TEXT}}, $line; + $this->{ADDDEL}++; + if ($line =~ /^-/) { + $this->{OCNT}++; + } + else { + $this->{NCNT}++; + } + } + + push @split, $this; + last; + } + + for my $hunk (@split) { + $o_ofs = $hunk->{OLD}; + $n_ofs = $hunk->{NEW}; + $o_cnt = $hunk->{OCNT}; + $n_cnt = $hunk->{NCNT}; + + my $head = ("@@ -$o_ofs" . + (($o_cnt != 1) ? ",$o_cnt" : '') . + " +$n_ofs" . + (($n_cnt != 1) ? ",$n_cnt" : '') . + " @@\n"); + unshift @{$hunk->{TEXT}}, $head; + } + return map { $_->{TEXT} } @split; +} + +sub find_last_o_ctx { + my ($it) = @_; + my $text = $it->{TEXT}; + my ($o_ofs, $o_cnt, $n_ofs, $n_cnt) = parse_hunk_header($text->[0]); + my $i = @{$text}; + my $last_o_ctx = $o_ofs + $o_cnt; + while (0 < --$i) { + my $line = $text->[$i]; + if ($line =~ /^ /) { + $last_o_ctx--; + next; + } + last; + } + return $last_o_ctx; +} + +sub merge_hunk { + my ($prev, $this) = @_; + my ($o0_ofs, $o0_cnt, $n0_ofs, $n0_cnt) = + parse_hunk_header($prev->{TEXT}[0]); + my ($o1_ofs, $o1_cnt, $n1_ofs, $n1_cnt) = + parse_hunk_header($this->{TEXT}[0]); + + my (@line, $i, $ofs, $o_cnt, $n_cnt); + $ofs = $o0_ofs; + $o_cnt = $n_cnt = 0; + for ($i = 1; $i < @{$prev->{TEXT}}; $i++) { + my $line = $prev->{TEXT}[$i]; + if ($line =~ /^\+/) { + $n_cnt++; + push @line, $line; + next; + } + + last if ($o1_ofs <= $ofs); + + $o_cnt++; + $ofs++; + if ($line =~ /^ /) { + $n_cnt++; + } + push @line, $line; + } + + for ($i = 1; $i < @{$this->{TEXT}}; $i++) { + my $line = $this->{TEXT}[$i]; + if ($line =~ /^\+/) { + $n_cnt++; + push @line, $line; + next; + } + $ofs++; + $o_cnt++; + if ($line =~ /^ /) { + $n_cnt++; + } + push @line, $line; + } + my $head = ("@@ -$o0_ofs" . + (($o_cnt != 1) ? ",$o_cnt" : '') . + " +$n0_ofs" . + (($n_cnt != 1) ? ",$n_cnt" : '') . + " @@\n"); + @{$prev->{TEXT}} = ($head, @line); +} + +sub coalesce_overlapping_hunks { + my (@in) = @_; + my @out = (); + + my ($last_o_ctx); + + for (grep { $_->{USE} } @in) { + my $text = $_->{TEXT}; + my ($o_ofs, $o_cnt, $n_ofs, $n_cnt) = + parse_hunk_header($text->[0]); + if (defined $last_o_ctx && + $o_ofs <= $last_o_ctx) { + merge_hunk($out[-1], $_); + } + else { + push @out, $_; + } + $last_o_ctx = find_last_o_ctx($out[-1]); + } + return @out; +} + +sub help_patch_cmd { + print <<\EOF ; +y - stage this hunk +n - do not stage this hunk +a - stage this and all the remaining hunks +d - do not stage this hunk nor any of the remaining hunks +j - leave this hunk undecided, see next undecided hunk +J - leave this hunk undecided, see next hunk +k - leave this hunk undecided, see previous undecided hunk +K - leave this hunk undecided, see previous hunk +s - split the current hunk into smaller hunks +EOF +} + +sub patch_update_cmd { + my @mods = list_modified('file-only'); + @mods = grep { !($_->{BINARY}) } @mods; + return if (!@mods); + + my ($it) = list_and_choose({ PROMPT => 'Patch update', + SINGLETON => 1, + IMMEDIATE => 1, + HEADER => $status_head, }, + @mods); + return if (!$it); + + my ($ix, $num); + my $path = $it->{VALUE}; + my ($head, @hunk) = parse_diff($path); + for (@{$head->{TEXT}}) { + print; + } + $num = scalar @hunk; + $ix = 0; + + while (1) { + my ($prev, $next, $other, $undecided, $i); + $other = ''; + + if ($num <= $ix) { + $ix = 0; + } + for ($i = 0; $i < $ix; $i++) { + if (!defined $hunk[$i]{USE}) { + $prev = 1; + $other .= '/k'; + last; + } + } + if ($ix) { + $other .= '/K'; + } + for ($i = $ix + 1; $i < $num; $i++) { + if (!defined $hunk[$i]{USE}) { + $next = 1; + $other .= '/j'; + last; + } + } + if ($ix < $num - 1) { + $other .= '/J'; + } + for ($i = 0; $i < $num; $i++) { + if (!defined $hunk[$i]{USE}) { + $undecided = 1; + last; + } + } + last if (!$undecided); + + if (hunk_splittable($hunk[$ix]{TEXT})) { + $other .= '/s'; + } + for (@{$hunk[$ix]{TEXT}}) { + print; + } + print "Stage this hunk [y/n/a/d$other/?]? "; + my $line = <STDIN>; + if ($line) { + if ($line =~ /^y/i) { + $hunk[$ix]{USE} = 1; + } + elsif ($line =~ /^n/i) { + $hunk[$ix]{USE} = 0; + } + elsif ($line =~ /^a/i) { + while ($ix < $num) { + if (!defined $hunk[$ix]{USE}) { + $hunk[$ix]{USE} = 1; + } + $ix++; + } + next; + } + elsif ($line =~ /^d/i) { + while ($ix < $num) { + if (!defined $hunk[$ix]{USE}) { + $hunk[$ix]{USE} = 0; + } + $ix++; + } + next; + } + elsif ($other =~ /K/ && $line =~ /^K/) { + $ix--; + next; + } + elsif ($other =~ /J/ && $line =~ /^J/) { + $ix++; + next; + } + elsif ($other =~ /k/ && $line =~ /^k/) { + while (1) { + $ix--; + last if (!$ix || + !defined $hunk[$ix]{USE}); + } + next; + } + elsif ($other =~ /j/ && $line =~ /^j/) { + while (1) { + $ix++; + last if ($ix >= $num || + !defined $hunk[$ix]{USE}); + } + next; + } + elsif ($other =~ /s/ && $line =~ /^s/) { + my @split = split_hunk($hunk[$ix]{TEXT}); + if (1 < @split) { + print "Split into ", + scalar(@split), " hunks.\n"; + } + splice(@hunk, $ix, 1, + map { +{ TEXT => $_, USE => undef } } + @split); + $num = scalar @hunk; + next; + } + else { + help_patch_cmd($other); + next; + } + # soft increment + while (1) { + $ix++; + last if ($ix >= $num || + !defined $hunk[$ix]{USE}); + } + } + } + + @hunk = coalesce_overlapping_hunks(@hunk); + + my ($o_lofs, $n_lofs) = (0, 0); + my @result = (); + for (@hunk) { + my $text = $_->{TEXT}; + my ($o_ofs, $o_cnt, $n_ofs, $n_cnt) = + parse_hunk_header($text->[0]); + + if (!$_->{USE}) { + if (!defined $o_cnt) { $o_cnt = 1; } + if (!defined $n_cnt) { $n_cnt = 1; } + + # We would have added ($n_cnt - $o_cnt) lines + # to the postimage if we were to use this hunk, + # but we didn't. So the line number that the next + # hunk starts at would be shifted by that much. + $n_lofs -= ($n_cnt - $o_cnt); + next; + } + else { + if ($n_lofs) { + $n_ofs += $n_lofs; + $text->[0] = ("@@ -$o_ofs" . + ((defined $o_cnt) + ? ",$o_cnt" : '') . + " +$n_ofs" . + ((defined $n_cnt) + ? ",$n_cnt" : '') . + " @@\n"); + } + for (@$text) { + push @result, $_; + } + } + } + + if (@result) { + my $fh; + + open $fh, '|-', qw(git apply --cached); + for (@{$head->{TEXT}}, @result) { + print $fh $_; + } + if (!close $fh) { + for (@{$head->{TEXT}}, @result) { + print STDERR $_; + } + } + refresh(); + } + + print "\n"; +} + +sub diff_cmd { + my @mods = list_modified('index-only'); + @mods = grep { !($_->{BINARY}) } @mods; + return if (!@mods); + my (@them) = list_and_choose({ PROMPT => 'Review diff', + IMMEDIATE => 1, + HEADER => $status_head, }, + @mods); + return if (!@them); + system(qw(git diff-index -p --cached HEAD --), + map { $_->{VALUE} } @them); +} + +sub quit_cmd { + print "Bye.\n"; + exit(0); +} + +sub help_cmd { + print <<\EOF ; +status - show paths with changes +update - add working tree state to the staged set of changes +revert - revert staged set of changes back to the HEAD version +patch - pick hunks and update selectively +diff - view diff between HEAD and index +add untracked - add contents of untracked files to the staged set of changes +EOF +} + +sub main_loop { + my @cmd = ([ 'status', \&status_cmd, ], + [ 'update', \&update_cmd, ], + [ 'revert', \&revert_cmd, ], + [ 'add untracked', \&add_untracked_cmd, ], + [ 'patch', \&patch_update_cmd, ], + [ 'diff', \&diff_cmd, ], + [ 'quit', \&quit_cmd, ], + [ 'help', \&help_cmd, ], + ); + while (1) { + my ($it) = list_and_choose({ PROMPT => 'What now', + SINGLETON => 1, + LIST_FLAT => 4, + HEADER => '*** Commands ***', + IMMEDIATE => 1 }, @cmd); + if ($it) { + eval { + $it->[1]->(); + }; + if ($@) { + print "$@"; + } + } + } +} + +my @z; + +refresh(); +status_cmd(); +main_loop(); @@ -2,10 +2,12 @@ # # Copyright (c) 2005, 2006 Junio C Hamano -USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] +USAGE='[--signoff] [--dotest=<dir>] [--utf8 | --no-utf8] [--binary] [--3way] [--interactive] [--whitespace=<option>] <mbox>... or, when resuming [--skip | --resolved]' . git-sh-setup +set_reflog_action am +require_work_tree git var GIT_COMMITTER_IDENT >/dev/null || exit @@ -87,10 +89,12 @@ It does not apply to blobs recorded in its index." # This is not so wrong. Depending on which base we picked, # orig_tree may be wildly different from ours, but his_tree # has the same set of wildly different changes in parts the - # patch did not touch, so resolve ends up canceling them, + # patch did not touch, so recursive ends up canceling them, # saying that we reverted all those changes. - git-merge-resolve $orig_tree -- HEAD $his_tree || { + eval GITHEAD_$his_tree='"$SUBJECT"' + export GITHEAD_$his_tree + git-merge-recursive $orig_tree -- HEAD $his_tree || { if test -d "$GIT_DIR/rr-cache" then git-rerere @@ -98,11 +102,11 @@ It does not apply to blobs recorded in its index." echo Failed to merge in the changes. exit 1 } + unset GITHEAD_$his_tree } prec=4 -rloga=am -dotest=.dotest sign= utf8= keep= skip= interactive= resolved= binary= ws= resolvemsg= +dotest=.dotest sign= utf8=t keep= skip= interactive= resolved= binary= ws= resolvemsg= while case "$#" in 0) break;; esac do @@ -125,7 +129,9 @@ do -s|--s|--si|--sig|--sign|--signo|--signof|--signoff) sign=t; shift ;; -u|--u|--ut|--utf|--utf8) - utf8=t; shift ;; + utf8=t; shift ;; # this is now default + --no-u|--no-ut|--no-utf|--no-utf8) + utf8=; shift ;; -k|--k|--ke|--kee|--keep) keep=t; shift ;; @@ -141,9 +147,6 @@ do --resolvemsg=*) resolvemsg=$(echo "$1" | sed -e "s/^--resolvemsg=//"); shift ;; - --reflog-action=*) - rloga=`expr "z$1" : 'z-[^=]*=\(.*\)'`; shift ;; - --) shift; break ;; -*) @@ -166,10 +169,25 @@ fi if test -d "$dotest" then - if test ",$#," != ",0," || ! tty -s - then - die "previous dotest directory $dotest still exists but mbox given." - fi + case "$#,$skip$resolved" in + 0,*t*) + # Explicit resume command and we do not have file, so + # we are happy. + : ;; + 0,) + # No file input but without resume parameters; catch + # user error to feed us a patch from standard input + # when there is already .dotest. This is somewhat + # unreliable -- stdin could be /dev/null for example + # and the caller did not intend to feed us a patch but + # wanted to continue unattended. + tty -s + ;; + *) + false + ;; + esac || + die "previous dotest directory $dotest still exists but mbox given." resume=yes else # Make sure we are not given --skip nor --resolved @@ -211,6 +229,8 @@ fi if test "$(cat "$dotest/utf8")" = t then utf8=-u +else + utf8=-n fi if test "$(cat "$dotest/keep")" = t then @@ -231,6 +251,10 @@ last=`cat "$dotest/last"` this=`cat "$dotest/next"` if test "$skip" = t then + if test -d "$GIT_DIR/rr-cache" + then + git-rerere clear + fi this=`expr "$this" + 1` resume= fi @@ -382,17 +406,21 @@ do changed="$(git-diff-index --cached --name-only HEAD)" if test '' = "$changed" then - echo "No changes - did you forget update-index?" + echo "No changes - did you forget to use 'git add'?" stop_here_user_resolve $this fi unmerged=$(git-ls-files -u) if test -n "$unmerged" then echo "You still have unmerged paths in your index" - echo "did you forget update-index?" + echo "did you forget to use 'git add'?" stop_here_user_resolve $this fi apply_status=0 + if test -d "$GIT_DIR/rr-cache" + then + git rerere + fi ;; esac @@ -429,7 +457,7 @@ do parent=$(git-rev-parse --verify HEAD) && commit=$(git-commit-tree $tree -p $parent <"$dotest/final-commit") && echo Committed: $commit && - git-update-ref -m "$rloga: $SUBJECT" HEAD $commit $parent || + git-update-ref -m "$GIT_REFLOG_ACTION: $SUBJECT" HEAD $commit $parent || stop_here $this if test -x "$GIT_DIR"/hooks/post-applypatch diff --git a/git-annotate.perl b/git-annotate.perl deleted file mode 100755 index 215ed26f3a..0000000000 --- a/git-annotate.perl +++ /dev/null @@ -1,708 +0,0 @@ -#!/usr/bin/perl -# Copyright 2006, Ryan Anderson <ryan@michonline.com> -# -# GPL v2 (See COPYING) -# -# This file is licensed under the GPL v2, or a later version -# at the discretion of Linus Torvalds. - -use warnings; -use strict; -use Getopt::Long; -use POSIX qw(strftime gmtime); -use File::Basename qw(basename dirname); - -sub usage() { - print STDERR "Usage: ${\basename $0} [-s] [-S revs-file] file [ revision ] - -l, --long - Show long rev (Defaults off) - -t, --time - Show raw timestamp (Defaults off) - -r, --rename - Follow renames (Defaults on). - -S, --rev-file revs-file - Use revs from revs-file instead of calling git-rev-list - -h, --help - This message. -"; - - exit(1); -} - -our ($help, $longrev, $rename, $rawtime, $starting_rev, $rev_file) = (0, 0, 1); - -my $rc = GetOptions( "long|l" => \$longrev, - "time|t" => \$rawtime, - "help|h" => \$help, - "rename|r" => \$rename, - "rev-file|S=s" => \$rev_file); -if (!$rc or $help or !@ARGV) { - usage(); -} - -my $filename = shift @ARGV; -if (@ARGV) { - $starting_rev = shift @ARGV; -} - -my @stack = ( - { - 'rev' => defined $starting_rev ? $starting_rev : "HEAD", - 'filename' => $filename, - }, -); - -our @filelines = (); - -if (defined $starting_rev) { - @filelines = git_cat_file($starting_rev, $filename); -} else { - open(F,"<",$filename) - or die "Failed to open filename: $!"; - - while(<F>) { - chomp; - push @filelines, $_; - } - close(F); - -} - -our %revs; -our @revqueue; -our $head; - -my $revsprocessed = 0; -while (my $bound = pop @stack) { - my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'}); - foreach my $revinst (@revisions) { - my ($rev, @parents) = @$revinst; - $head ||= $rev; - - if (!defined($rev)) { - $rev = ""; - } - $revs{$rev}{'filename'} = $bound->{'filename'}; - if (scalar @parents > 0) { - $revs{$rev}{'parents'} = \@parents; - next; - } - - if (!$rename) { - next; - } - - my $newbound = find_parent_renames($rev, $bound->{'filename'}); - if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) { - push @stack, $newbound; - $revs{$rev}{'parents'} = [$newbound->{'rev'}]; - } - } -} -push @revqueue, $head; -init_claim( defined $starting_rev ? $head : 'dirty'); -unless (defined $starting_rev) { - my $diff = open_pipe("git","diff","HEAD", "--",$filename) - or die "Failed to call git diff to check for dirty state: $!"; - - _git_diff_parse($diff, [$head], "dirty", ( - 'author' => gitvar_name("GIT_AUTHOR_IDENT"), - 'author_date' => sprintf("%s +0000",time()), - ) - ); - close($diff); -} -handle_rev(); - - -my $i = 0; -foreach my $l (@filelines) { - my ($output, $rev, $committer, $date); - if (ref $l eq 'ARRAY') { - ($output, $rev, $committer, $date) = @$l; - if (!$longrev && length($rev) > 8) { - $rev = substr($rev,0,8); - } - } else { - $output = $l; - ($rev, $committer, $date) = ('unknown', 'unknown', 'unknown'); - } - - printf("%s\t(%10s\t%10s\t%d)%s\n", $rev, $committer, - format_date($date), ++$i, $output); -} - -sub init_claim { - my ($rev) = @_; - for (my $i = 0; $i < @filelines; $i++) { - $filelines[$i] = [ $filelines[$i], '', '', '', 1]; - # line, - # rev, - # author, - # date, - # 1 <-- belongs to the original file. - } - $revs{$rev}{'lines'} = \@filelines; -} - - -sub handle_rev { - my $revseen = 0; - my %seen; - while (my $rev = shift @revqueue) { - next if $seen{$rev}++; - - my %revinfo = git_commit_info($rev); - - if (exists $revs{$rev}{parents} && - scalar @{$revs{$rev}{parents}} != 0) { - - git_diff_parse($revs{$rev}{'parents'}, $rev, %revinfo); - push @revqueue, @{$revs{$rev}{'parents'}}; - - } else { - # We must be at the initial rev here, so claim everything that is left. - for (my $i = 0; $i < @{$revs{$rev}{lines}}; $i++) { - if (ref ${$revs{$rev}{lines}}[$i] eq '' || ${$revs{$rev}{lines}}[$i][1] eq '') { - claim_line($i, $rev, $revs{$rev}{lines}, %revinfo); - } - } - } - } -} - - -sub git_rev_list { - my ($rev, $file) = @_; - - my $revlist; - if ($rev_file) { - open($revlist, '<' . $rev_file) - or die "Failed to open $rev_file : $!"; - } else { - $revlist = open_pipe("git-rev-list","--parents","--remove-empty",$rev,"--",$file) - or die "Failed to exec git-rev-list: $!"; - } - - my @revs; - while(my $line = <$revlist>) { - chomp $line; - my ($rev, @parents) = split /\s+/, $line; - push @revs, [ $rev, @parents ]; - } - close($revlist); - - printf("0 revs found for rev %s (%s)\n", $rev, $file) if (@revs == 0); - return @revs; -} - -sub find_parent_renames { - my ($rev, $file) = @_; - - my $patch = open_pipe("git-diff-tree", "-M50", "-r","--name-status", "-z","$rev") - or die "Failed to exec git-diff: $!"; - - local $/ = "\0"; - my %bound; - my $junk = <$patch>; - while (my $change = <$patch>) { - chomp $change; - my $filename = <$patch>; - if (!defined $filename) { - next; - } - chomp $filename; - - if ($change =~ m/^[AMD]$/ ) { - next; - } elsif ($change =~ m/^R/ ) { - my $oldfilename = $filename; - $filename = <$patch>; - chomp $filename; - if ( $file eq $filename ) { - my $parent = git_find_parent($rev, $oldfilename); - @bound{'rev','filename'} = ($parent, $oldfilename); - last; - } - } - } - close($patch); - - return \%bound; -} - - -sub git_find_parent { - my ($rev, $filename) = @_; - - my $revparent = open_pipe("git-rev-list","--remove-empty", "--parents","--max-count=1","$rev","--",$filename) - or die "Failed to open git-rev-list to find a single parent: $!"; - - my $parentline = <$revparent>; - chomp $parentline; - my ($revfound,$parent) = split m/\s+/, $parentline; - - close($revparent); - - return $parent; -} - -sub git_find_all_parents { - my ($rev) = @_; - - my $revparent = open_pipe("git-rev-list","--remove-empty", "--parents","--max-count=1","$rev") - or die "Failed to open git-rev-list to find a single parent: $!"; - - my $parentline = <$revparent>; - chomp $parentline; - my ($origrev, @parents) = split m/\s+/, $parentline; - - close($revparent); - - return @parents; -} - -sub git_merge_base { - my ($rev1, $rev2) = @_; - - my $mb = open_pipe("git-merge-base", $rev1, $rev2) - or die "Failed to open git-merge-base: $!"; - - my $base = <$mb>; - chomp $base; - - close($mb); - - return $base; -} - -# Construct a set of pseudo parents that are in the same order, -# and the same quantity as the real parents, -# but whose SHA1s are as similar to the logical parents -# as possible. -sub get_pseudo_parents { - my ($all, $fake) = @_; - - my @all = @$all; - my @fake = @$fake; - - my @pseudo; - - my %fake = map {$_ => 1} @fake; - my %seenfake; - - my $fakeidx = 0; - foreach my $p (@all) { - if (exists $fake{$p}) { - if ($fake[$fakeidx] ne $p) { - die sprintf("parent mismatch: %s != %s\nall:%s\nfake:%s\n", - $fake[$fakeidx], $p, - join(", ", @all), - join(", ", @fake), - ); - } - - push @pseudo, $p; - $fakeidx++; - $seenfake{$p}++; - - } else { - my $base = git_merge_base($fake[$fakeidx], $p); - if ($base ne $fake[$fakeidx]) { - die sprintf("Result of merge-base doesn't match fake: %s,%s != %s\n", - $fake[$fakeidx], $p, $base); - } - - # The details of how we parse the diffs - # mean that we cannot have a duplicate - # revision in the list, so if we've already - # seen the revision we would normally add, just use - # the actual revision. - if ($seenfake{$base}) { - push @pseudo, $p; - } else { - push @pseudo, $base; - $seenfake{$base}++; - } - } - } - - return @pseudo; -} - - -# Get a diff between the current revision and a parent. -# Record the commit information that results. -sub git_diff_parse { - my ($parents, $rev, %revinfo) = @_; - - my @pseudo_parents; - my @command = ("git-diff-tree"); - my $revision_spec; - - if (scalar @$parents == 1) { - - $revision_spec = join("..", $parents->[0], $rev); - @pseudo_parents = @$parents; - } else { - my @all_parents = git_find_all_parents($rev); - - if (@all_parents != @$parents) { - @pseudo_parents = get_pseudo_parents(\@all_parents, $parents); - } else { - @pseudo_parents = @$parents; - } - - $revision_spec = $rev; - push @command, "-c"; - } - - my @filenames = ( $revs{$rev}{'filename'} ); - - foreach my $parent (@$parents) { - push @filenames, $revs{$parent}{'filename'}; - } - - push @command, "-p", "-M", $revision_spec, "--", @filenames; - - - my $diff = open_pipe( @command ) - or die "Failed to call git-diff for annotation: $!"; - - _git_diff_parse($diff, \@pseudo_parents, $rev, %revinfo); - - close($diff); -} - -sub _git_diff_parse { - my ($diff, $parents, $rev, %revinfo) = @_; - - my $ri = 0; - - my $slines = $revs{$rev}{'lines'}; - my (%plines, %pi); - - my $gotheader = 0; - my ($remstart); - my $parent_count = @$parents; - - my $diff_header_regexp = "^@"; - $diff_header_regexp .= "@" x @$parents; - $diff_header_regexp .= ' -\d+,\d+' x @$parents; - $diff_header_regexp .= ' \+(\d+),\d+'; - $diff_header_regexp .= " " . ("@" x @$parents); - - my %claim_regexps; - my $allparentplus = '^' . '\\+' x @$parents . '(.*)$'; - - { - my $i = 0; - foreach my $parent (@$parents) { - - $pi{$parent} = 0; - my $r = '^' . '.' x @$parents . '(.*)$'; - my $p = $r; - substr($p,$i+1, 1) = '\\+'; - - my $m = $r; - substr($m,$i+1, 1) = '-'; - - $claim_regexps{$parent}{plus} = $p; - $claim_regexps{$parent}{minus} = $m; - - $plines{$parent} = []; - - $i++; - } - } - - DIFF: - while(<$diff>) { - chomp; - #printf("%d:%s:\n", $gotheader, $_); - if (m/$diff_header_regexp/) { - $remstart = $1 - 1; - # (0-based arrays) - - $gotheader = 1; - - foreach my $parent (@$parents) { - for (my $i = $ri; $i < $remstart; $i++) { - $plines{$parent}[$pi{$parent}++] = $slines->[$i]; - } - } - $ri = $remstart; - - next DIFF; - - } elsif (!$gotheader) { - # Skip over the leadin. - next DIFF; - } - - if (m/^\\/) { - ; - # Skip \No newline at end of file. - # But this can be internationalized, so only look - # for an initial \ - - } else { - my %claims = (); - my $negclaim = 0; - my $allclaimed = 0; - my $line; - - if (m/$allparentplus/) { - claim_line($ri, $rev, $slines, %revinfo); - $allclaimed = 1; - - } - - PARENT: - foreach my $parent (keys %claim_regexps) { - my $m = $claim_regexps{$parent}{minus}; - my $p = $claim_regexps{$parent}{plus}; - - if (m/$m/) { - $line = $1; - $plines{$parent}[$pi{$parent}++] = [ $line, '', '', '', 0 ]; - $negclaim++; - - } elsif (m/$p/) { - $line = $1; - if (get_line($slines, $ri) eq $line) { - # Found a match, claim - $claims{$parent}++; - - } else { - die sprintf("Sync error: %d\n|%s\n|%s\n%s => %s\n", - $ri, $line, - get_line($slines, $ri), - $rev, $parent); - } - } - } - - if (%claims) { - foreach my $parent (@$parents) { - next if $claims{$parent} || $allclaimed; - $plines{$parent}[$pi{$parent}++] = $slines->[$ri]; - #[ $line, '', '', '', 0 ]; - } - $ri++; - - } elsif ($negclaim) { - next DIFF; - - } else { - if (substr($_,scalar @$parents) ne get_line($slines,$ri) ) { - foreach my $parent (@$parents) { - printf("parent %s is on line %d\n", $parent, $pi{$parent}); - } - - my @context; - for (my $i = -2; $i < 2; $i++) { - push @context, get_line($slines, $ri + $i); - } - my $context = join("\n", @context); - - my $justline = substr($_, scalar @$parents); - die sprintf("Line %d, does not match:\n|%s|\n|%s|\n%s\n", - $ri, - $justline, - $context); - } - foreach my $parent (@$parents) { - $plines{$parent}[$pi{$parent}++] = $slines->[$ri]; - } - $ri++; - } - } - } - - for (my $i = $ri; $i < @{$slines} ; $i++) { - foreach my $parent (@$parents) { - push @{$plines{$parent}}, $slines->[$ri]; - } - $ri++; - } - - foreach my $parent (@$parents) { - $revs{$parent}{lines} = $plines{$parent}; - } - - return; -} - -sub get_line { - my ($lines, $index) = @_; - - return ref $lines->[$index] ne '' ? $lines->[$index][0] : $lines->[$index]; -} - -sub git_cat_file { - my ($rev, $filename) = @_; - return () unless defined $rev && defined $filename; - - my $blob = git_ls_tree($rev, $filename); - die "Failed to find a blob for $filename in rev $rev\n" if !defined $blob; - - my $catfile = open_pipe("git","cat-file", "blob", $blob) - or die "Failed to git-cat-file blob $blob (rev $rev, file $filename): " . $!; - - my @lines; - while(<$catfile>) { - chomp; - push @lines, $_; - } - close($catfile); - - return @lines; -} - -sub git_ls_tree { - my ($rev, $filename) = @_; - - my $lstree = open_pipe("git","ls-tree",$rev,$filename) - or die "Failed to call git ls-tree: $!"; - - my ($mode, $type, $blob, $tfilename); - while(<$lstree>) { - chomp; - ($mode, $type, $blob, $tfilename) = split(/\s+/, $_, 4); - last if ($tfilename eq $filename); - } - close($lstree); - - return $blob if ($tfilename eq $filename); - die "git-ls-tree failed to find blob for $filename"; - -} - - - -sub claim_line { - my ($floffset, $rev, $lines, %revinfo) = @_; - my $oline = get_line($lines, $floffset); - @{$lines->[$floffset]} = ( $oline, $rev, - $revinfo{'author'}, $revinfo{'author_date'} ); - #printf("Claiming line %d with rev %s: '%s'\n", - # $floffset, $rev, $oline) if 1; -} - -sub git_commit_info { - my ($rev) = @_; - my $commit = open_pipe("git-cat-file", "commit", $rev) - or die "Failed to call git-cat-file: $!"; - - my %info; - while(<$commit>) { - chomp; - last if (length $_ == 0); - - if (m/^author (.*) <(.*)> (.*)$/) { - $info{'author'} = $1; - $info{'author_email'} = $2; - $info{'author_date'} = $3; - } elsif (m/^committer (.*) <(.*)> (.*)$/) { - $info{'committer'} = $1; - $info{'committer_email'} = $2; - $info{'committer_date'} = $3; - } - } - close($commit); - - return %info; -} - -sub format_date { - if ($rawtime) { - return $_[0]; - } - my ($timestamp, $timezone) = split(' ', $_[0]); - my $minutes = abs($timezone); - $minutes = int($minutes / 100) * 60 + ($minutes % 100); - if ($timezone < 0) { - $minutes = -$minutes; - } - my $t = $timestamp + $minutes * 60; - return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($t)); -} - -# Copied from git-send-email.perl - We need a Git.pm module.. -sub gitvar { - my ($var) = @_; - my $fh; - my $pid = open($fh, '-|'); - die "$!" unless defined $pid; - if (!$pid) { - exec('git-var', $var) or die "$!"; - } - my ($val) = <$fh>; - close $fh or die "$!"; - chomp($val); - return $val; -} - -sub gitvar_name { - my ($name) = @_; - my $val = gitvar($name); - my @field = split(/\s+/, $val); - return join(' ', @field[0...(@field-4)]); -} - -sub open_pipe { - if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { - return open_pipe_activestate(@_); - } else { - return open_pipe_normal(@_); - } -} - -sub open_pipe_activestate { - tie *fh, "Git::ActiveStatePipe", @_; - return *fh; -} - -sub open_pipe_normal { - my (@execlist) = @_; - - my $pid = open my $kid, "-|"; - defined $pid or die "Cannot fork: $!"; - - unless ($pid) { - exec @execlist; - die "Cannot exec @execlist: $!"; - } - - return $kid; -} - -package Git::ActiveStatePipe; -use strict; - -sub TIEHANDLE { - my ($class, @params) = @_; - my $cmdline = join " ", @params; - my @data = qx{$cmdline}; - bless { i => 0, data => \@data }, $class; -} - -sub READLINE { - my $self = shift; - if ($self->{i} >= scalar @{$self->{data}}) { - return undef; - } - return $self->{'data'}->[ $self->{i}++ ]; -} - -sub CLOSE { - my $self = shift; - delete $self->{data}; - delete $self->{i}; -} - -sub EOF { - my $self = shift; - return ($self->{i} >= scalar @{$self->{data}}); -} diff --git a/git-applymbox.sh b/git-applymbox.sh index 5569fdcc34..1f68599ae5 100755 --- a/git-applymbox.sh +++ b/git-applymbox.sh @@ -23,11 +23,12 @@ USAGE='[-u] [-k] [-q] [-m] (-c .dotest/<num> | mbox) [signoff]' git var GIT_COMMITTER_IDENT >/dev/null || exit -keep_subject= query_apply= continue= utf8= resume=t +keep_subject= query_apply= continue= utf8=-u resume=t while case "$#" in 0) break ;; esac do case "$1" in -u) utf8=-u ;; + -n) utf8=-n ;; -k) keep_subject=-k ;; -q) query_apply=t ;; -c) continue="$2"; resume=f; shift ;; diff --git a/git-archimport.perl b/git-archimport.perl index ada60ec240..2e15781246 100755 --- a/git-archimport.perl +++ b/git-archimport.perl @@ -226,7 +226,7 @@ my $import = 0; unless (-d $git_dir) { # initial import if ($psets[0]{type} eq 'i' || $psets[0]{type} eq 't') { print "Starting import from $psets[0]{id}\n"; - `git-init-db`; + `git-init`; die $! if $?; $import = 1; } else { diff --git a/git-bisect.sh b/git-bisect.sh index 06a8d26945..6da31e87a0 100755 --- a/git-bisect.sh +++ b/git-bisect.sh @@ -179,11 +179,12 @@ bisect_reset() { *) usage ;; esac - git checkout "$branch" && - rm -fr "$GIT_DIR/refs/bisect" - rm -f "$GIT_DIR/refs/heads/bisect" "$GIT_DIR/head-name" - rm -f "$GIT_DIR/BISECT_LOG" - rm -f "$GIT_DIR/BISECT_NAMES" + if git checkout "$branch"; then + rm -fr "$GIT_DIR/refs/bisect" + rm -f "$GIT_DIR/refs/heads/bisect" "$GIT_DIR/head-name" + rm -f "$GIT_DIR/BISECT_LOG" + rm -f "$GIT_DIR/BISECT_NAMES" + fi } bisect_replay () { diff --git a/git-branch.sh b/git-branch.sh deleted file mode 100755 index e0501ec23f..0000000000 --- a/git-branch.sh +++ /dev/null @@ -1,130 +0,0 @@ -#!/bin/sh - -USAGE='[-l] [(-d | -D) <branchname>] | [[-f] <branchname> [<start-point>]] | -r' -LONG_USAGE='If no arguments, show available branches and mark current branch with a star. -If one argument, create a new branch <branchname> based off of current HEAD. -If two arguments, create a new branch <branchname> based off of <start-point>.' - -SUBDIRECTORY_OK='Yes' -. git-sh-setup - -headref=$(git-symbolic-ref HEAD | sed -e 's|^refs/heads/||') - -delete_branch () { - option="$1" - shift - for branch_name - do - case ",$headref," in - ",$branch_name,") - die "Cannot delete the branch you are on." ;; - ,,) - die "What branch are you on anyway?" ;; - esac - branch=$(cat "$GIT_DIR/refs/heads/$branch_name") && - branch=$(git-rev-parse --verify "$branch^0") || - die "Seriously, what branch are you talking about?" - case "$option" in - -D) - ;; - *) - mbs=$(git-merge-base -a "$branch" HEAD | tr '\012' ' ') - case " $mbs " in - *' '$branch' '*) - # the merge base of branch and HEAD contains branch -- - # which means that the HEAD contains everything in both. - ;; - *) - echo >&2 "The branch '$branch_name' is not a strict subset of your current HEAD. -If you are sure you want to delete it, run 'git branch -D $branch_name'." - exit 1 - ;; - esac - ;; - esac - rm -f "$GIT_DIR/logs/refs/heads/$branch_name" - rm -f "$GIT_DIR/refs/heads/$branch_name" - echo "Deleted branch $branch_name." - done - exit 0 -} - -ls_remote_branches () { - git-rev-parse --symbolic --all | - sed -ne 's|^refs/\(remotes/\)|\1|p' | - sort -} - -force= -create_log= -while case "$#,$1" in 0,*) break ;; *,-*) ;; *) break ;; esac -do - case "$1" in - -d | -D) - delete_branch "$@" - exit - ;; - -r) - ls_remote_branches - exit - ;; - -f) - force="$1" - ;; - -l) - create_log="yes" - ;; - --) - shift - break - ;; - -*) - usage - ;; - esac - shift -done - -case "$#" in -0) - git-rev-parse --symbolic --branches | - sort | - while read ref - do - if test "$headref" = "$ref" - then - pfx='*' - else - pfx=' ' - fi - echo "$pfx $ref" - done - exit 0 ;; -1) - head=HEAD ;; -2) - head="$2^0" ;; -esac -branchname="$1" - -rev=$(git-rev-parse --verify "$head") || exit - -git-check-ref-format "heads/$branchname" || - die "we do not like '$branchname' as a branch name." - -if [ -e "$GIT_DIR/refs/heads/$branchname" ] -then - if test '' = "$force" - then - die "$branchname already exists." - elif test "$branchname" = "$headref" - then - die "cannot force-update the current branch." - fi -fi -if test "$create_log" = 'yes' -then - mkdir -p $(dirname "$GIT_DIR/logs/refs/heads/$branchname") - touch "$GIT_DIR/logs/refs/heads/$branchname" -fi -git update-ref -m "branch: Created from $head" "refs/heads/$branchname" $rev diff --git a/git-checkout.sh b/git-checkout.sh index 580a9e8a23..a2b8e4fa4a 100755 --- a/git-checkout.sh +++ b/git-checkout.sh @@ -3,9 +3,11 @@ USAGE='[-f] [-b <new_branch>] [-m] [<branch>] [<paths>...]' SUBDIRECTORY_OK=Sometimes . git-sh-setup +require_work_tree -old=$(git-rev-parse HEAD) old_name=HEAD +old=$(git-rev-parse --verify $old_name 2>/dev/null) +oldbranch=$(git-symbolic-ref $old_name 2>/dev/null) new= new_name= force= @@ -13,6 +15,8 @@ branch= newbranch= newbranch_log= merge= +LF=' +' while [ "$#" != "0" ]; do arg="$1" shift @@ -22,7 +26,7 @@ while [ "$#" != "0" ]; do shift [ -z "$newbranch" ] && die "git checkout: -b needs a branch name" - [ -e "$GIT_DIR/refs/heads/$newbranch" ] && + git-show-ref --verify --quiet -- "refs/heads/$newbranch" && die "git checkout: branch $newbranch already exists" git-check-ref-format "heads/$newbranch" || die "git checkout: we do not like '$newbranch' as a branch name." @@ -50,8 +54,9 @@ while [ "$#" != "0" ]; do exit 1 fi new="$rev" - new_name="$arg^0" - if [ -f "$GIT_DIR/refs/heads/$arg" ]; then + new_name="$arg" + if git-show-ref --verify --quiet -- "refs/heads/$arg" + then branch="$arg" fi elif rev=$(git-rev-parse --verify "$arg^{tree}" 2>/dev/null) @@ -76,6 +81,11 @@ while [ "$#" != "0" ]; do esac done +case "$force$merge" in +11) + die "git checkout: -f and -m are incompatible" +esac + # The behaviour of the command with and without explicit path # parameters is quite different. # @@ -106,7 +116,11 @@ Did you intend to checkout '$@' which can not be resolved as commit?" git-ls-tree --full-name -r "$new" "$@" | git-update-index --index-info || exit $? fi - git-checkout-index -f -u -- "$@" + + # Make sure the request is about existing paths. + git-ls-files --error-unmatch -- "$@" >/dev/null || exit + git-ls-files -- "$@" | + git-checkout-index -f -u --stdin exit $? else # Make sure we did not fall back on $arg^{tree} codepath @@ -129,22 +143,58 @@ fi [ -z "$new" ] && new=$old && new_name="$old_name" -# If we don't have an old branch that we're switching to, +# If we don't have an existing branch that we're switching to, # and we don't have a new branch name for the target we -# are switching to, then we'd better just be checking out -# what we already had +# are switching to, then we are detaching our HEAD from any +# branch. However, if "git checkout HEAD" detaches the HEAD +# from the current branch, even though that may be logically +# correct, it feels somewhat funny. More importantly, we do not +# want "git checkout" nor "git checkout -f" to detach HEAD. + +detached= +detach_warn= + +if test -z "$branch$newbranch" && test "$new" != "$old" +then + detached="$new" + if test -n "$oldbranch" + then + detach_warn="warning: you are not on ANY branch anymore. +If you meant to create a new branch from the commit, you need -b to +associate a new branch with the wanted checkout. Example: + git checkout -b <new_branch_name> $arg" + fi +elif test -z "$oldbranch" && test -n "$branch" +then + # Coming back... + if test -z "$force" + then + git show-ref -d -s | grep "$old" >/dev/null || { + echo >&2 \ +"You are not on any branch and switching to branch '$new_name' +may lose your changes. At this point, you can do one of two things: + (1) Decide it is Ok and say 'git checkout -f $new_name'; + (2) Start a new branch from the current commit, by saying + 'git checkout -b <branch-name>'. +Leaving your HEAD detached; not switching to branch '$new_name'." + exit 1; + } + fi +fi -[ -z "$branch$newbranch" ] && - [ "$new" != "$old" ] && - die "git checkout: to checkout the requested commit you need to specify - a name for a new branch which is created and switched to" +if [ "X$old" = X ] +then + echo >&2 "warning: You appear to be on a branch yet to be born." + echo >&2 "warning: Forcing checkout of $new_name." + force=1 +fi if [ "$force" ] then git-read-tree --reset -u $new else git-update-index --refresh >/dev/null - merge_error=$(git-read-tree -m -u $old $new 2>&1) || ( + merge_error=$(git-read-tree -m -u --exclude-per-directory=.gitignore $old $new 2>&1) || ( case "$merge" in '') echo >&2 "$merge_error" @@ -155,7 +205,8 @@ else git diff-files --name-only | git update-index --remove --stdin && work=`git write-tree` && git read-tree --reset -u $new && - git read-tree -m -u --aggressive $old $new $work || exit + git read-tree -m -u --aggressive --exclude-per-directory=.gitignore $old $new $work || + exit if result=`git write-tree 2>/dev/null` then @@ -205,8 +256,25 @@ if [ "$?" -eq 0 ]; then git-update-ref -m "checkout: Created from $new_name" "refs/heads/$newbranch" $new || exit branch="$newbranch" fi - [ "$branch" ] && - GIT_DIR="$GIT_DIR" git-symbolic-ref HEAD "refs/heads/$branch" + if test -n "$branch" + then + GIT_DIR="$GIT_DIR" git-symbolic-ref HEAD "refs/heads/$branch" + elif test -n "$detached" + then + # NEEDSWORK: we would want a command to detach the HEAD + # atomically, instead of this handcrafted command sequence. + # Perhaps: + # git update-ref --detach HEAD $new + # or something like that... + # + echo "$detached" >"$GIT_DIR/HEAD.new" && + mv "$GIT_DIR/HEAD.new" "$GIT_DIR/HEAD" || + die "Cannot detach HEAD" + if test -n "$detach_warn" + then + echo >&2 "$detach_warn" + fi + fi rm -f "$GIT_DIR/MERGE_HEAD" else exit 1 diff --git a/git-cherry.sh b/git-cherry.sh deleted file mode 100755 index f0e8831fa4..0000000000 --- a/git-cherry.sh +++ /dev/null @@ -1,94 +0,0 @@ -#!/bin/sh -# -# Copyright (c) 2005 Junio C Hamano. -# - -USAGE='[-v] <upstream> [<head>] [<limit>]' -LONG_USAGE=' __*__*__*__*__> <upstream> - / - fork-point - \__+__+__+__+__+__+__+__> <head> - -Each commit between the fork-point (or <limit> if given) and <head> is -examined, and compared against the change each commit between the -fork-point and <upstream> introduces. If the change seems to be in -the upstream, it is shown on the standard output with prefix "+". -Otherwise it is shown with prefix "-".' -. git-sh-setup - -case "$1" in -v) verbose=t; shift ;; esac - -case "$#,$1" in -1,*..*) - upstream=$(expr "z$1" : 'z\(.*\)\.\.') ours=$(expr "z$1" : '.*\.\.\(.*\)$') - set x "$upstream" "$ours" - shift ;; -esac - -case "$#" in -1) upstream=`git-rev-parse --verify "$1"` && - ours=`git-rev-parse --verify HEAD` || exit - limit="$upstream" - ;; -2) upstream=`git-rev-parse --verify "$1"` && - ours=`git-rev-parse --verify "$2"` || exit - limit="$upstream" - ;; -3) upstream=`git-rev-parse --verify "$1"` && - ours=`git-rev-parse --verify "$2"` && - limit=`git-rev-parse --verify "$3"` || exit - ;; -*) usage ;; -esac - -# Note that these list commits in reverse order; -# not that the order in inup matters... -inup=`git-rev-list ^$ours $upstream` && -ours=`git-rev-list $ours ^$limit` || exit - -tmp=.cherry-tmp$$ -patch=$tmp-patch -mkdir $patch -trap "rm -rf $tmp-*" 0 1 2 3 15 - -_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]' -_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40" - -for c in $inup -do - git-diff-tree -p $c -done | git-patch-id | -while read id name -do - echo $name >>$patch/$id -done - -LF=' -' - -O= -for c in $ours -do - set x `git-diff-tree -p $c | git-patch-id` - if test "$2" != "" - then - if test -f "$patch/$2" - then - sign=- - else - sign=+ - fi - case "$verbose" in - t) - c=$(git-rev-list --pretty=oneline --max-count=1 $c) - esac - case "$O" in - '') O="$sign $c" ;; - *) O="$sign $c$LF$O" ;; - esac - fi -done -case "$O" in -'') ;; -*) echo "$O" ;; -esac diff --git a/git-clean.sh b/git-clean.sh index 3834323bcf..db177a7886 100755 --- a/git-clean.sh +++ b/git-clean.sh @@ -14,11 +14,11 @@ When optional <paths>... arguments are given, the paths affected are further limited to those that match them.' SUBDIRECTORY_OK=Yes . git-sh-setup +require_work_tree ignored= ignoredonly= cleandir= -quiet= rmf="rm -f --" rmrf="rm -rf --" rm_refuse="echo Not removing" @@ -31,14 +31,13 @@ do cleandir=1 ;; -n) - quiet=1 rmf="echo Would remove" rmrf="echo Would remove" rm_refuse="echo Would not remove" echo1=":" ;; -q) - quiet=1 + echo1=":" ;; -x) ignored=1 diff --git a/git-clone.sh b/git-clone.sh index 7060bdab01..0f7bbbfb39 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -8,11 +8,15 @@ # See git-sh-setup why. unset CDPATH -usage() { - echo >&2 "Usage: $0 [--template=<template_directory>] [--use-separate-remote] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [--origin <name>] [-n] <repo> [<dir>]" +die() { + echo >&2 "$@" exit 1 } +usage() { + die "Usage: $0 [--template=<template_directory>] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [--origin <name>] [--depth <n>] [-n] <repo> [<dir>]" +} + get_repo_base() { (cd "$1" && (cd .git ; pwd)) 2> /dev/null } @@ -31,17 +35,23 @@ clone_dumb_http () { cd "$2" && clone_tmp="$GIT_DIR/clone-tmp" && mkdir -p "$clone_tmp" || exit 1 - http_fetch "$1/info/refs" "$clone_tmp/refs" || { - echo >&2 "Cannot get remote repository information. + if [ -n "$GIT_CURL_FTP_NO_EPSV" -o \ + "`git-repo-config --bool http.noEPSV`" = true ]; then + curl_extra_args="${curl_extra_args} --disable-epsv" + fi + http_fetch "$1/info/refs" "$clone_tmp/refs" || + die "Cannot get remote repository information. Perhaps git-update-server-info needs to be run there?" - exit 1; - } while read sha1 refname do name=`expr "z$refname" : 'zrefs/\(.*\)'` && case "$name" in *^*) continue;; esac + case "$bare,$name" in + yes,* | ,heads/* | ,tags/*) ;; + *) continue ;; + esac if test -n "$use_separate_remote" && branch_name=`expr "z$name" : 'zheads/\(.*\)'` then @@ -109,7 +119,8 @@ bare= reference= origin= origin_override= -use_separate_remote= +use_separate_remote=t +depth= while case "$#,$1" in 0,*) break ;; @@ -127,8 +138,9 @@ while *,--template=*) template="$1" ;; *,-q|*,--quiet) quiet=-q ;; - *,--use-separate-remote) - use_separate_remote=t ;; + *,--use-separate-remote) ;; + *,--no-separate-remote) + die "clones are always made with separate-remote layout" ;; 1,--reference) usage ;; *,--reference) shift; reference="$1" ;; @@ -139,17 +151,12 @@ while '') usage ;; */*) - echo >&2 "'$2' is not suitable for an origin name" - exit 1 + die "'$2' is not suitable for an origin name" esac - git-check-ref-format "heads/$2" || { - echo >&2 "'$2' is not suitable for a branch name" - exit 1 - } - test -z "$origin_override" || { - echo >&2 "Do not give more than one --origin options." - exit 1 - } + git-check-ref-format "heads/$2" || + die "'$2' is not suitable for a branch name" + test -z "$origin_override" || + die "Do not give more than one --origin options." origin_override=yes origin="$2"; shift ;; @@ -157,6 +164,10 @@ while *,-u|*,--upload-pack) shift upload_pack="--exec=$1" ;; + 1,--depth) usage;; + *,--depth) + shift + depth="--depth=$1";; *,-*) usage ;; *) break ;; esac @@ -165,26 +176,18 @@ do done repo="$1" -if test -z "$repo" -then - echo >&2 'you must specify a repository to clone.' - exit 1 -fi +test -n "$repo" || + die 'you must specify a repository to clone.' -# --bare implies --no-checkout +# --bare implies --no-checkout and --no-separate-remote if test yes = "$bare" then if test yes = "$origin_override" then - echo >&2 '--bare and --origin $origin options are incompatible.' - exit 1 - fi - if test t = "$use_separate_remote" - then - echo >&2 '--bare and --use-separate-remote options are incompatible.' - exit 1 + die '--bare and --origin $origin options are incompatible.' fi no_checkout=yes + use_separate_remote= fi if test -z "$origin" @@ -202,7 +205,7 @@ fi dir="$2" # Try using "humanish" part of source repo if user didn't specify one [ -z "$dir" ] && dir=$(echo "$repo" | sed -e 's|/$||' -e 's|:*/*\.git$||' -e 's|.*[/:]||g') -[ -e "$dir" ] && echo "$dir already exists." && usage +[ -e "$dir" ] && die "destination directory '$dir' already exists." mkdir -p "$dir" && D=$(cd "$dir" && pwd) && trap 'err=$?; cd ..; rm -rf "$D"; exit $err' 0 @@ -211,7 +214,7 @@ yes) GIT_DIR="$D" ;; *) GIT_DIR="$D/.git" ;; -esac && export GIT_DIR && git-init-db ${template+"$template"} || usage +esac && export GIT_DIR && git-init ${template+"$template"} || usage if test -n "$reference" then @@ -229,7 +232,7 @@ then cd reference-tmp && tar xf -) else - echo >&2 "$reference: not a local directory." && usage + die "reference repository '$reference' is not a local directory." fi fi @@ -238,10 +241,8 @@ rm -f "$GIT_DIR/CLONE_HEAD" # We do local magic only when the user tells us to. case "$local,$use_local" in yes,yes) - ( cd "$repo/objects" ) || { - echo >&2 "-l flag seen but $repo is not local." - exit 1 - } + ( cd "$repo/objects" ) || + die "-l flag seen but repository '$repo' is not local." case "$local_shared" in no) @@ -271,6 +272,10 @@ yes,yes) *) case "$repo" in rsync://*) + case "$depth" in + "") ;; + *) die "shallow over rsync not supported" ;; + esac rsync $quiet -av --ignore-existing \ --exclude info "$repo/objects/" "$GIT_DIR/objects/" || exit @@ -298,23 +303,24 @@ yes,yes) fi git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD" || exit 1 ;; - https://*|http://*) + https://*|http://*|ftp://*) + case "$depth" in + "") ;; + *) die "shallow over http or ftp not supported" ;; + esac if test -z "@@NO_CURL@@" then clone_dumb_http "$repo" "$D" else - echo >&2 "http transport not supported, rebuild Git with curl support" - exit 1 + die "http transport not supported, rebuild Git with curl support" fi ;; *) - cd "$D" && case "$upload_pack" in - '') git-fetch-pack --all -k $quiet "$repo" ;; - *) git-fetch-pack --all -k $quiet "$upload_pack" "$repo" ;; - esac >"$GIT_DIR/CLONE_HEAD" || { - echo >&2 "fetch-pack from '$repo' failed." - exit 1 - } + case "$upload_pack" in + '') git-fetch-pack --all -k $quiet $depth "$repo" ;; + *) git-fetch-pack --all -k $quiet "$upload_pack" $depth "$repo" ;; + esac >"$GIT_DIR/CLONE_HEAD" || + die "fetch-pack from '$repo' failed." ;; esac ;; @@ -332,12 +338,8 @@ cd "$D" || exit if test -z "$bare" && test -f "$GIT_DIR/REMOTE_HEAD" then - # Figure out which remote branch HEAD points at. - case "$use_separate_remote" in - '') remote_top=refs/heads ;; - *) remote_top="refs/remotes/$origin" ;; - esac - + # a non-bare repository is always in separate-remote layout + remote_top="refs/remotes/$origin" head_sha1=`cat "$GIT_DIR/REMOTE_HEAD"` case "$head_sha1" in 'ref: refs/'*) @@ -353,7 +355,7 @@ then # The name under $remote_top the remote HEAD seems to point at. head_points_at=$( ( - echo "master" + test -f "$GIT_DIR/$remote_top/master" && echo "master" cd "$GIT_DIR/$remote_top" && find . -type f -print | sed -e 's/^\.\///' ) | ( @@ -371,46 +373,34 @@ then ) ) - # Write out remotes/$origin file, and update our "$head_points_at". + # Write out remote.$origin config, and update our "$head_points_at". case "$head_points_at" in ?*) - mkdir -p "$GIT_DIR/remotes" && + # Local default branch git-symbolic-ref HEAD "refs/heads/$head_points_at" && - case "$use_separate_remote" in - t) origin_track="$remote_top/$head_points_at" - git-update-ref HEAD "$head_sha1" ;; - *) origin_track="$remote_top/$origin" - git-update-ref "refs/heads/$origin" "$head_sha1" ;; - esac && - echo >"$GIT_DIR/remotes/$origin" \ - "URL: $repo -Pull: refs/heads/$head_points_at:$origin_track" && - (cd "$GIT_DIR/$remote_top" && find . -type f -print) | - while read dotslref - do - name=`expr "$dotslref" : './\(.*\)'` - if test "z$head_points_at" = "z$name" - then - continue - fi - if test "$use_separate_remote" = '' && - test "z$origin" = "z$name" - then - continue - fi - echo "Pull: refs/heads/${name}:$remote_top/${name}" - done >>"$GIT_DIR/remotes/$origin" && - case "$use_separate_remote" in - t) - rm -f "refs/remotes/$origin/HEAD" - git-symbolic-ref "refs/remotes/$origin/HEAD" \ - "refs/remotes/$origin/$head_points_at" - esac + + # Tracking branch for the primary branch at the remote. + origin_track="$remote_top/$head_points_at" && + git-update-ref HEAD "$head_sha1" && + + # Upstream URL + git-repo-config remote."$origin".url "$repo" && + + # Set up the mappings to track the remote branches. + git-repo-config remote."$origin".fetch \ + "+refs/heads/*:$remote_top/*" '^$' && + rm -f "refs/remotes/$origin/HEAD" + git-symbolic-ref "refs/remotes/$origin/HEAD" \ + "refs/remotes/$origin/$head_points_at" && + + git-repo-config branch."$head_points_at".remote "$origin" && + git-repo-config branch."$head_points_at".merge "refs/heads/$head_points_at" esac case "$no_checkout" in '') - git-read-tree -m -u -v HEAD HEAD + test "z$quiet" = z && v=-v || v= + git-read-tree -m -u $v HEAD HEAD esac fi rm -f "$GIT_DIR/CLONE_HEAD" "$GIT_DIR/REMOTE_HEAD" diff --git a/git-commit.sh b/git-commit.sh index 4cf3fab05c..eddd863015 100755 --- a/git-commit.sh +++ b/git-commit.sh @@ -6,9 +6,9 @@ USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>] [-u] [--amend] [-e] [--author <author>] [[-i | -o] <path>...]' SUBDIRECTORY_OK=Yes . git-sh-setup +require_work_tree git-rev-parse --verify HEAD >/dev/null 2>&1 || initial_commit=t -branch=$(GIT_DIR="$GIT_DIR" git-symbolic-ref HEAD) case "$0" in *status) @@ -32,54 +32,7 @@ save_index () { cp -p "$THIS_INDEX" "$NEXT_INDEX" } -report () { - header="# -# $1: -# ($2) -# -" - trailer="" - while read status name newname - do - printf '%s' "$header" - header="" - trailer="# -" - case "$status" in - M ) echo "# modified: $name";; - D*) echo "# deleted: $name";; - T ) echo "# typechange: $name";; - C*) echo "# copied: $name -> $newname";; - R*) echo "# renamed: $name -> $newname";; - A*) echo "# new file: $name";; - U ) echo "# unmerged: $name";; - esac - done - printf '%s' "$trailer" - [ "$header" ] -} - run_status () { - ( - # We always show status for the whole tree. - cd "$TOP" - - IS_INITIAL="$initial_commit" - REFERENCE=HEAD - case "$amend" in - t) - # If we are amending the initial commit, there - # is no HEAD^1. - if git-rev-parse --verify "HEAD^1" >/dev/null 2>&1 - then - REFERENCE="HEAD^1" - IS_INITIAL= - else - IS_INITIAL=t - fi - ;; - esac - # If TMP_INDEX is defined, that means we are doing # "--only" partial commit, and that index file is used # to build the tree for the commit. Otherwise, if @@ -88,93 +41,22 @@ run_status () { # so the regular index file is what we use to compare. if test '' != "$TMP_INDEX" then - GIT_INDEX_FILE="$TMP_INDEX" - export GIT_INDEX_FILE + GIT_INDEX_FILE="$TMP_INDEX" + export GIT_INDEX_FILE elif test -f "$NEXT_INDEX" then - GIT_INDEX_FILE="$NEXT_INDEX" - export GIT_INDEX_FILE + GIT_INDEX_FILE="$NEXT_INDEX" + export GIT_INDEX_FILE fi - case "$branch" in - refs/heads/master) ;; - *) echo "# On branch $branch" ;; + case "$status_only" in + t) color= ;; + *) color=--nocolor ;; esac - - if test -z "$IS_INITIAL" - then - git-diff-index -M --cached --name-status \ - --diff-filter=MDTCRA $REFERENCE | - sed -e ' - s/\\/\\\\/g - s/ /\\ /g - ' | - report "Updated but not checked in" "will commit" - committable="$?" - else - echo '# -# Initial commit -#' - git-ls-files | - sed -e ' - s/\\/\\\\/g - s/ /\\ /g - s/^/A / - ' | - report "Updated but not checked in" "will commit" - - committable="$?" - fi - - git-diff-files --name-status | - sed -e ' - s/\\/\\\\/g - s/ /\\ /g - ' | - report "Changed but not updated" \ - "use git-update-index to mark for commit" - - option="" - if test -z "$untracked_files"; then - option="--directory --no-empty-directory" - fi - hdr_shown= - if test -f "$GIT_DIR/info/exclude" - then - git-ls-files --others $option \ - --exclude-from="$GIT_DIR/info/exclude" \ - --exclude-per-directory=.gitignore - else - git-ls-files --others $option \ - --exclude-per-directory=.gitignore - fi | - while read line; do - if [ -z "$hdr_shown" ]; then - echo '#' - echo '# Untracked files:' - echo '# (use "git add" to add to commit)' - echo '#' - hdr_shown=1 - fi - echo "# $line" - done - - if test -n "$verbose" -a -z "$IS_INITIAL" - then - git-diff-index --cached -M -p --diff-filter=MDTCRA $REFERENCE - fi - case "$committable" in - 0) - case "$amend" in - t) - echo "# No changes" ;; - *) - echo "nothing to commit" ;; - esac - exit 1 ;; - esac - exit 0 - ) + git-runstatus ${color} \ + ${verbose:+--verbose} \ + ${amend:+--amend} \ + ${untracked_files:+--untracked} } trap ' @@ -198,6 +80,7 @@ no_edit= log_given= log_message= verify=t +quiet= verbose= signoff= force_author= @@ -205,179 +88,185 @@ only_include_assumed= untracked_files= while case "$#" in 0) break;; esac do - case "$1" in - -F|--F|-f|--f|--fi|--fil|--file) - case "$#" in 1) usage ;; esac - shift - no_edit=t - log_given=t$log_given - logfile="$1" - shift - ;; - -F*|-f*) - no_edit=t - log_given=t$log_given - logfile=`expr "z$1" : 'z-[Ff]\(.*\)'` - shift - ;; - --F=*|--f=*|--fi=*|--fil=*|--file=*) - no_edit=t - log_given=t$log_given - logfile=`expr "z$1" : 'z-[^=]*=\(.*\)'` - shift - ;; - -a|--a|--al|--all) - all=t - shift - ;; - --au=*|--aut=*|--auth=*|--autho=*|--author=*) - force_author=`expr "z$1" : 'z-[^=]*=\(.*\)'` - shift - ;; - --au|--aut|--auth|--autho|--author) - case "$#" in 1) usage ;; esac - shift - force_author="$1" - shift - ;; - -e|--e|--ed|--edi|--edit) - edit_flag=t - shift - ;; - -i|--i|--in|--inc|--incl|--inclu|--includ|--include) - also=t - shift - ;; - -o|--o|--on|--onl|--only) - only=t - shift - ;; - -m|--m|--me|--mes|--mess|--messa|--messag|--message) - case "$#" in 1) usage ;; esac - shift - log_given=m$log_given - if test "$log_message" = '' - then - log_message="$1" - else - log_message="$log_message + case "$1" in + -F|--F|-f|--f|--fi|--fil|--file) + case "$#" in 1) usage ;; esac + shift + no_edit=t + log_given=t$log_given + logfile="$1" + shift + ;; + -F*|-f*) + no_edit=t + log_given=t$log_given + logfile=`expr "z$1" : 'z-[Ff]\(.*\)'` + shift + ;; + --F=*|--f=*|--fi=*|--fil=*|--file=*) + no_edit=t + log_given=t$log_given + logfile=`expr "z$1" : 'z-[^=]*=\(.*\)'` + shift + ;; + -a|--a|--al|--all) + all=t + shift + ;; + --au=*|--aut=*|--auth=*|--autho=*|--author=*) + force_author=`expr "z$1" : 'z-[^=]*=\(.*\)'` + shift + ;; + --au|--aut|--auth|--autho|--author) + case "$#" in 1) usage ;; esac + shift + force_author="$1" + shift + ;; + -e|--e|--ed|--edi|--edit) + edit_flag=t + shift + ;; + -i|--i|--in|--inc|--incl|--inclu|--includ|--include) + also=t + shift + ;; + -o|--o|--on|--onl|--only) + only=t + shift + ;; + -m|--m|--me|--mes|--mess|--messa|--messag|--message) + case "$#" in 1) usage ;; esac + shift + log_given=m$log_given + if test "$log_message" = '' + then + log_message="$1" + else + log_message="$log_message $1" - fi - no_edit=t - shift - ;; - -m*) - log_given=m$log_given - if test "$log_message" = '' - then - log_message=`expr "z$1" : 'z-m\(.*\)'` - else - log_message="$log_message + fi + no_edit=t + shift + ;; + -m*) + log_given=m$log_given + if test "$log_message" = '' + then + log_message=`expr "z$1" : 'z-m\(.*\)'` + else + log_message="$log_message `expr "z$1" : 'z-m\(.*\)'`" - fi - no_edit=t - shift - ;; - --m=*|--me=*|--mes=*|--mess=*|--messa=*|--messag=*|--message=*) - log_given=m$log_given - if test "$log_message" = '' - then - log_message=`expr "z$1" : 'z-[^=]*=\(.*\)'` - else - log_message="$log_message + fi + no_edit=t + shift + ;; + --m=*|--me=*|--mes=*|--mess=*|--messa=*|--messag=*|--message=*) + log_given=m$log_given + if test "$log_message" = '' + then + log_message=`expr "z$1" : 'z-[^=]*=\(.*\)'` + else + log_message="$log_message `expr "z$1" : 'zq-[^=]*=\(.*\)'`" - fi - no_edit=t - shift - ;; - -n|--n|--no|--no-|--no-v|--no-ve|--no-ver|--no-veri|--no-verif|--no-verify) - verify= - shift - ;; - --a|--am|--ame|--amen|--amend) - amend=t - log_given=t$log_given - use_commit=HEAD - shift - ;; - -c) - case "$#" in 1) usage ;; esac - shift - log_given=t$log_given - use_commit="$1" - no_edit= - shift - ;; - --ree=*|--reed=*|--reedi=*|--reedit=*|--reedit-=*|--reedit-m=*|\ - --reedit-me=*|--reedit-mes=*|--reedit-mess=*|--reedit-messa=*|\ - --reedit-messag=*|--reedit-message=*) - log_given=t$log_given - use_commit=`expr "z$1" : 'z-[^=]*=\(.*\)'` - no_edit= - shift - ;; - --ree|--reed|--reedi|--reedit|--reedit-|--reedit-m|--reedit-me|\ - --reedit-mes|--reedit-mess|--reedit-messa|--reedit-messag|--reedit-message) - case "$#" in 1) usage ;; esac - shift - log_given=t$log_given - use_commit="$1" - no_edit= - shift - ;; - -C) - case "$#" in 1) usage ;; esac - shift - log_given=t$log_given - use_commit="$1" - no_edit=t - shift - ;; - --reu=*|--reus=*|--reuse=*|--reuse-=*|--reuse-m=*|--reuse-me=*|\ - --reuse-mes=*|--reuse-mess=*|--reuse-messa=*|--reuse-messag=*|\ - --reuse-message=*) - log_given=t$log_given - use_commit=`expr "z$1" : 'z-[^=]*=\(.*\)'` - no_edit=t - shift - ;; - --reu|--reus|--reuse|--reuse-|--reuse-m|--reuse-me|--reuse-mes|\ - --reuse-mess|--reuse-messa|--reuse-messag|--reuse-message) - case "$#" in 1) usage ;; esac - shift - log_given=t$log_given - use_commit="$1" - no_edit=t - shift - ;; - -s|--s|--si|--sig|--sign|--signo|--signof|--signoff) - signoff=t - shift - ;; - -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) - verbose=t - shift - ;; - -u|--u|--un|--unt|--untr|--untra|--untrac|--untrack|--untracke|--untracked|\ - --untracked-|--untracked-f|--untracked-fi|--untracked-fil|--untracked-file|\ - --untracked-files) - untracked_files=t - shift - ;; - --) - shift - break - ;; - -*) - usage - ;; - *) - break - ;; - esac + fi + no_edit=t + shift + ;; + -n|--n|--no|--no-|--no-v|--no-ve|--no-ver|--no-veri|--no-verif|\ + --no-verify) + verify= + shift + ;; + --a|--am|--ame|--amen|--amend) + amend=t + log_given=t$log_given + use_commit=HEAD + shift + ;; + -c) + case "$#" in 1) usage ;; esac + shift + log_given=t$log_given + use_commit="$1" + no_edit= + shift + ;; + --ree=*|--reed=*|--reedi=*|--reedit=*|--reedit-=*|--reedit-m=*|\ + --reedit-me=*|--reedit-mes=*|--reedit-mess=*|--reedit-messa=*|\ + --reedit-messag=*|--reedit-message=*) + log_given=t$log_given + use_commit=`expr "z$1" : 'z-[^=]*=\(.*\)'` + no_edit= + shift + ;; + --ree|--reed|--reedi|--reedit|--reedit-|--reedit-m|--reedit-me|\ + --reedit-mes|--reedit-mess|--reedit-messa|--reedit-messag|\ + --reedit-message) + case "$#" in 1) usage ;; esac + shift + log_given=t$log_given + use_commit="$1" + no_edit= + shift + ;; + -C) + case "$#" in 1) usage ;; esac + shift + log_given=t$log_given + use_commit="$1" + no_edit=t + shift + ;; + --reu=*|--reus=*|--reuse=*|--reuse-=*|--reuse-m=*|--reuse-me=*|\ + --reuse-mes=*|--reuse-mess=*|--reuse-messa=*|--reuse-messag=*|\ + --reuse-message=*) + log_given=t$log_given + use_commit=`expr "z$1" : 'z-[^=]*=\(.*\)'` + no_edit=t + shift + ;; + --reu|--reus|--reuse|--reuse-|--reuse-m|--reuse-me|--reuse-mes|\ + --reuse-mess|--reuse-messa|--reuse-messag|--reuse-message) + case "$#" in 1) usage ;; esac + shift + log_given=t$log_given + use_commit="$1" + no_edit=t + shift + ;; + -s|--s|--si|--sig|--sign|--signo|--signof|--signoff) + signoff=t + shift + ;; + -q|--q|--qu|--qui|--quie|--quiet) + quiet=t + shift + ;; + -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) + verbose=t + shift + ;; + -u|--u|--un|--unt|--untr|--untra|--untrac|--untrack|--untracke|\ + --untracked|--untracked-|--untracked-f|--untracked-fi|--untracked-fil|\ + --untracked-file|--untracked-files) + untracked_files=t + shift + ;; + --) + shift + break + ;; + -*) + usage + ;; + *) + break + ;; + esac done case "$edit_flag" in t) no_edit= ;; esac @@ -386,33 +275,33 @@ case "$edit_flag" in t) no_edit= ;; esac case "$amend,$initial_commit" in t,t) - die "You do not have anything to amend." ;; + die "You do not have anything to amend." ;; t,) - if [ -f "$GIT_DIR/MERGE_HEAD" ]; then - die "You are in the middle of a merge -- cannot amend." - fi ;; + if [ -f "$GIT_DIR/MERGE_HEAD" ]; then + die "You are in the middle of a merge -- cannot amend." + fi ;; esac case "$log_given" in tt*) - die "Only one of -c/-C/-F can be used." ;; + die "Only one of -c/-C/-F can be used." ;; *tm*|*mt*) - die "Option -m cannot be combined with -c/-C/-F." ;; + die "Option -m cannot be combined with -c/-C/-F." ;; esac case "$#,$also,$only,$amend" in *,t,t,*) - die "Only one of --include/--only can be used." ;; + die "Only one of --include/--only can be used." ;; 0,t,,* | 0,,t,) - die "No paths with --include/--only does not make sense." ;; + die "No paths with --include/--only does not make sense." ;; 0,,t,t) - only_include_assumed="# Clever... amending the last one with dirty index." ;; + only_include_assumed="# Clever... amending the last one with dirty index." ;; 0,,,*) - ;; + ;; *,,,*) - only_include_assumed="# Explicit paths specified without -i nor -o; assuming --only paths..." - also= - ;; + only_include_assumed="# Explicit paths specified without -i nor -o; assuming --only paths..." + also= + ;; esac unset only case "$all,$also,$#" in @@ -459,47 +348,37 @@ t,) ,) case "$#" in 0) - ;; # commit as-is + ;; # commit as-is *) - if test -f "$GIT_DIR/MERGE_HEAD" - then - refuse_partial "Cannot do a partial commit during a merge." - fi - TMP_INDEX="$GIT_DIR/tmp-index$$" - if test -z "$initial_commit" - then - # make sure index is clean at the specified paths, or - # they are additions. - dirty_in_index=`git-diff-index --cached --name-status \ - --diff-filter=DMTU HEAD -- "$@"` - test -z "$dirty_in_index" || - refuse_partial "Different in index and the last commit: -$dirty_in_index" - fi - commit_only=`git-ls-files --error-unmatch -- "$@"` || exit - - # Build the temporary index and update the real index - # the same way. - if test -z "$initial_commit" - then - cp "$THIS_INDEX" "$TMP_INDEX" - GIT_INDEX_FILE="$TMP_INDEX" git-read-tree -m HEAD - else - rm -f "$TMP_INDEX" - fi || exit - - echo "$commit_only" | - GIT_INDEX_FILE="$TMP_INDEX" \ - git-update-index --add --remove --stdin && - - save_index && - echo "$commit_only" | - ( - GIT_INDEX_FILE="$NEXT_INDEX" - export GIT_INDEX_FILE - git-update-index --remove --stdin - ) || exit - ;; + if test -f "$GIT_DIR/MERGE_HEAD" + then + refuse_partial "Cannot do a partial commit during a merge." + fi + TMP_INDEX="$GIT_DIR/tmp-index$$" + commit_only=`git-ls-files --error-unmatch -- "$@"` || exit + + # Build a temporary index and update the real index + # the same way. + if test -z "$initial_commit" + then + cp "$THIS_INDEX" "$TMP_INDEX" + GIT_INDEX_FILE="$TMP_INDEX" git-read-tree -m HEAD + else + rm -f "$TMP_INDEX" + fi || exit + + echo "$commit_only" | + GIT_INDEX_FILE="$TMP_INDEX" \ + git-update-index --add --remove --stdin && + + save_index && + echo "$commit_only" | + ( + GIT_INDEX_FILE="$NEXT_INDEX" + export GIT_INDEX_FILE + git-update-index --remove --stdin + ) || exit + ;; esac ;; esac @@ -517,7 +396,7 @@ else fi GIT_INDEX_FILE="$USE_INDEX" \ - git-update-index -q $unmerged_ok_if_status --refresh || exit + git-update-index -q $unmerged_ok_if_status --refresh || exit ################################################################ # If the request is status, just show it and exit. @@ -557,7 +436,7 @@ then elif test "$use_commit" != "" then git-cat-file commit "$use_commit" | sed -e '1,/^$/d' -elif test -f "$GIT_DIR/MERGE_HEAD" && test -f "$GIT_DIR/MERGE_MSG" +elif test -f "$GIT_DIR/MERGE_MSG" then cat "$GIT_DIR/MERGE_MSG" elif test -f "$GIT_DIR/SQUASH_MSG" @@ -638,15 +517,15 @@ then PARENTS=$(git-cat-file commit HEAD | sed -n -e '/^$/q' -e 's/^parent /-p /p') fi - current=$(git-rev-parse --verify HEAD) + current="$(git-rev-parse --verify HEAD)" else if [ -z "$(git-ls-files)" ]; then - echo >&2 Nothing to commit + echo >&2 'nothing to commit (use "git add file1 file2" to include for commit)' exit 1 fi PARENTS="" - current= rloga='commit (initial)' + current='' fi if test -z "$no_edit" @@ -722,8 +601,8 @@ then fi && commit=$(cat "$GIT_DIR"/COMMIT_MSG | git-commit-tree $tree $PARENTS) && rlogm=$(sed -e 1q "$GIT_DIR"/COMMIT_MSG) && - git-update-ref -m "$rloga: $rlogm" HEAD $commit $current && - rm -f -- "$GIT_DIR/MERGE_HEAD" && + git-update-ref -m "$rloga: $rlogm" HEAD $commit "$current" && + rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" && if test -f "$NEXT_INDEX" then mv "$NEXT_INDEX" "$THIS_INDEX" @@ -741,8 +620,17 @@ then git-rerere fi -if test -x "$GIT_DIR"/hooks/post-commit && test "$ret" = 0 +if test "$ret" = 0 then - "$GIT_DIR"/hooks/post-commit + if test -x "$GIT_DIR"/hooks/post-commit + then + "$GIT_DIR"/hooks/post-commit + fi + if test -z "$quiet" + then + echo "Created${initial_commit:+ initial} commit $commit" + git-diff-tree --shortstat --summary --root --no-commit-id HEAD -- + fi fi + exit "$ret" diff --git a/git-compat-util.h b/git-compat-util.h index b2e18954c0..8781e8e22d 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -11,6 +11,13 @@ #define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) +#if !defined(__APPLE__) && !defined(__FreeBSD__) +#define _XOPEN_SOURCE 600 /* glibc2 and AIX 5.3L need 500, OpenBSD needs 600 for S_ISLNK() */ +#define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */ +#endif +#define _GNU_SOURCE +#define _BSD_SOURCE + #include <unistd.h> #include <stdio.h> #include <sys/stat.h> @@ -22,9 +29,34 @@ #include <errno.h> #include <limits.h> #include <sys/param.h> -#include <netinet/in.h> #include <sys/types.h> #include <dirent.h> +#include <sys/time.h> +#include <time.h> +#include <signal.h> +#include <sys/wait.h> +#include <fnmatch.h> +#include <sys/poll.h> +#include <sys/socket.h> +#include <assert.h> +#include <regex.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <arpa/inet.h> +#include <netdb.h> +#include <pwd.h> +#include <grp.h> + +#ifndef NO_ICONV +#include <iconv.h> +#endif + +/* On most systems <limits.h> would have given us this, but + * not on some systems (e.g. GNU/Hurd). + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif #ifdef __GNUC__ #define NORETURN __attribute__((__noreturn__)) @@ -39,10 +71,12 @@ extern void usage(const char *err) NORETURN; extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); extern int error(const char *err, ...) __attribute__((format (printf, 1, 2))); +extern void warn(const char *err, ...) __attribute__((format (printf, 1, 2))); extern void set_usage_routine(void (*routine)(const char *err) NORETURN); extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern void set_error_routine(void (*routine)(const char *err, va_list params)); +extern void set_warn_routine(void (*routine)(const char *warn, va_list params)); #ifdef NO_MMAP @@ -53,17 +87,31 @@ extern void set_error_routine(void (*routine)(const char *err, va_list params)); #define MAP_FAILED ((void*)-1) #endif -#define mmap gitfakemmap -#define munmap gitfakemunmap -extern void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_t offset); -extern int gitfakemunmap(void *start, size_t length); +#define mmap git_mmap +#define munmap git_munmap +extern void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern int git_munmap(void *start, size_t length); + +#define DEFAULT_PACKED_GIT_WINDOW_SIZE (1 * 1024 * 1024) #else /* NO_MMAP */ #include <sys/mman.h> +#define DEFAULT_PACKED_GIT_WINDOW_SIZE \ + (sizeof(void*) >= 8 \ + ? 1 * 1024 * 1024 * 1024 \ + : 32 * 1024 * 1024) #endif /* NO_MMAP */ +#define DEFAULT_PACKED_GIT_LIMIT \ + ((1024L * 1024L) * (sizeof(void*) >= 8 ? 8192 : 256)) + +#ifdef NO_PREAD +#define pread git_pread +extern ssize_t git_pread(int fd, void *buf, size_t count, off_t offset); +#endif + #ifdef NO_SETENV #define setenv gitsetenv extern int gitsetenv(const char *, const char *, int); @@ -84,13 +132,33 @@ extern char *gitstrcasestr(const char *haystack, const char *needle); extern size_t gitstrlcpy(char *, const char *, size_t); #endif +extern void release_pack_memory(size_t); + +static inline char* xstrdup(const char *str) +{ + char *ret = strdup(str); + if (!ret) { + release_pack_memory(strlen(str) + 1); + ret = strdup(str); + if (!ret) + die("Out of memory, strdup failed"); + } + return ret; +} + static inline void *xmalloc(size_t size) { void *ret = malloc(size); if (!ret && !size) ret = malloc(1); - if (!ret) - die("Out of memory, malloc failed"); + if (!ret) { + release_pack_memory(size); + ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory, malloc failed"); + } #ifdef XMALLOC_POISON memset(ret, 0xA5, size); #endif @@ -102,8 +170,14 @@ static inline void *xrealloc(void *ptr, size_t size) void *ret = realloc(ptr, size); if (!ret && !size) ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); + if (!ret) { + release_pack_memory(size); + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } return ret; } @@ -112,8 +186,29 @@ static inline void *xcalloc(size_t nmemb, size_t size) void *ret = calloc(nmemb, size); if (!ret && (!nmemb || !size)) ret = calloc(1, 1); - if (!ret) - die("Out of memory, calloc failed"); + if (!ret) { + release_pack_memory(nmemb * size); + ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) + die("Out of memory, calloc failed"); + } + return ret; +} + +static inline void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die("Out of memory? mmap failed: %s", strerror(errno)); + } return ret; } @@ -172,7 +267,4 @@ static inline int sane_case(int x, int high) return x; } -#ifndef MAXPATHLEN -#define MAXPATHLEN 256 -#endif #endif diff --git a/git-cvsexportcommit.perl b/git-cvsexportcommit.perl index 99b3dc392a..4863c91fe3 100755 --- a/git-cvsexportcommit.perl +++ b/git-cvsexportcommit.perl @@ -1,10 +1,9 @@ #!/usr/bin/perl -w # Known limitations: -# - cannot add or remove binary files # - does not propagate permissions -# - tells "ready for commit" even when things could not be completed -# (eg addition of a binary file) +# - error handling has not been extensively tested +# use strict; use Getopt::Std; @@ -68,9 +67,9 @@ foreach my $line (@commit) { if ($stage eq 'headers') { if ($line =~ m/^parent (\w{40})$/) { # found a parent push @parents, $1; - } elsif ($line =~ m/^author (.+) \d+ \+\d+$/) { + } elsif ($line =~ m/^author (.+) \d+ [-+]\d+$/) { $author = $1; - } elsif ($line =~ m/^committer (.+) \d+ \+\d+$/) { + } elsif ($line =~ m/^committer (.+) \d+ [-+]\d+$/) { $committer = $1; } } else { @@ -115,36 +114,40 @@ if ($opt_a) { } close MSG; -my (@afiles, @dfiles, @mfiles, @dirs); -my @files = safe_pipe_capture('git-diff-tree', '-r', $parent, $commit); -#print @files; -$? && die "Error in git-diff-tree"; -foreach my $f (@files) { - chomp $f; - my @fields = split(m!\s+!, $f); - if ($fields[4] eq 'A') { - my $path = $fields[5]; - push @afiles, $path; - # add any needed parent directories - $path = dirname $path; - while (!-d $path and ! grep { $_ eq $path } @dirs) { - unshift @dirs, $path; - $path = dirname $path; - } - } - if ($fields[4] eq 'M') { - push @mfiles, $fields[5]; - } - if ($fields[4] eq 'R') { - push @dfiles, $fields[5]; - } +`git-diff-tree --binary -p $parent $commit >.cvsexportcommit.diff`;# || die "Cannot diff"; + +## apply non-binary changes +my $fuzz = $opt_p ? 0 : 2; + +print "Checking if patch will apply\n"; + +my @stat; +open APPLY, "GIT_DIR= git-apply -C$fuzz --binary --summary --numstat<.cvsexportcommit.diff|" || die "cannot patch"; +@stat=<APPLY>; +close APPLY || die "Cannot patch"; +my (@bfiles,@files,@afiles,@dfiles); +chomp @stat; +foreach (@stat) { + push (@bfiles,$1) if m/^-\t-\t(.*)$/; + push (@files, $1) if m/^-\t-\t(.*)$/; + push (@files, $1) if m/^\d+\t\d+\t(.*)$/; + push (@afiles,$1) if m/^ create mode [0-7]+ (.*)$/; + push (@dfiles,$1) if m/^ delete mode [0-7]+ (.*)$/; } -$opt_v && print "The commit affects:\n "; -$opt_v && print join ("\n ", @afiles,@mfiles,@dfiles) . "\n\n"; -undef @files; # don't need it anymore +map { s/^"(.*)"$/$1/g } @bfiles,@files; +map { s/\\([0-7]{3})/sprintf('%c',oct $1)/eg } @bfiles,@files; # check that the files are clean and up to date according to cvs my $dirty; +my @dirs; +foreach my $p (@afiles) { + my $path = dirname $p; + while (!-d $path and ! grep { $_ eq $path } @dirs) { + unshift @dirs, $path; + $path = dirname $path; + } +} + foreach my $d (@dirs) { if (-e $d) { $dirty = 1; @@ -153,6 +156,10 @@ foreach my $d (@dirs) { } foreach my $f (@afiles) { # This should return only one value + if ($f =~ m,(.*)/[^/]*$,) { + my $p = $1; + next if (grep { $_ eq $p } @dirs); + } my @status = grep(m/^File/, safe_pipe_capture('cvs', '-q', 'status' ,$f)); if (@status > 1) { warn 'Strange! cvs status returned more than one line?'}; if (-d dirname $f and $status[0] !~ m/Status: Unknown$/ @@ -162,7 +169,9 @@ foreach my $f (@afiles) { warn "Status was: $status[0]\n"; } } -foreach my $f (@mfiles, @dfiles) { + +foreach my $f (@files) { + next if grep { $_ eq $f } @afiles; # TODO:we need to handle removed in cvs my @status = grep(m/^File/, safe_pipe_capture('cvs', '-q', 'status' ,$f)); if (@status > 1) { warn 'Strange! cvs status returned more than one line?'}; @@ -179,72 +188,26 @@ if ($dirty) { } } -### -### NOTE: if you are planning to die() past this point -### you MUST call cleanupcvs(@files) before die() -### +print "Applying\n"; +`GIT_DIR= git-apply -C$fuzz --binary --summary --numstat --apply <.cvsexportcommit.diff` || die "cannot patch"; - -print "Creating new directories\n"; +print "Patch applied successfully. Adding new files and directories to CVS\n"; +my $dirtypatch = 0; foreach my $d (@dirs) { - unless (mkdir $d) { - warn "Could not mkdir $d: $!"; - $dirty = 1; - } - `cvs add $d`; - if ($?) { - $dirty = 1; + if (system('cvs','add',$d)) { + $dirtypatch = 1; warn "Failed to cvs add directory $d -- you may need to do it manually"; } } -print "'Patching' binary files\n"; - -my @bfiles = grep(m/^Binary/, safe_pipe_capture('git-diff-tree', '-p', $parent, $commit)); -@bfiles = map { chomp } @bfiles; -foreach my $f (@bfiles) { - # check that the file in cvs matches the "old" file - # extract the file to $tmpdir and compare with cmp - my $tree = safe_pipe_capture('git-rev-parse', "$parent^{tree}"); - chomp $tree; - my $blob = `git-ls-tree $tree "$f" | cut -f 1 | cut -d ' ' -f 3`; - chomp $blob; - `git-cat-file blob $blob > $tmpdir/blob`; - if (system('cmp', '-s', $f, "$tmpdir/blob")) { - warn "Binary file $f in CVS does not match parent.\n"; - $dirty = 1; - next; - } - - # replace with the new file - `git-cat-file blob $blob > $f`; - - # TODO: something smart with file modes - -} -if ($dirty) { - cleanupcvs(@files); - die "Exiting: Binary files in CVS do not match parent"; -} - -## apply non-binary changes -my $fuzz = $opt_p ? 0 : 2; - -print "Patching non-binary files\n"; -print `(git-diff-tree -p $parent -p $commit | patch -p1 -F $fuzz ) 2>&1`; - -my $dirtypatch = 0; -if (($? >> 8) == 2) { - cleanupcvs(@files); - die "Exiting: Patch reported serious trouble -- you will have to apply this patch manually"; -} elsif (($? >> 8) == 1) { # some hunks failed to apply - $dirtypatch = 1; -} - foreach my $f (@afiles) { - system('cvs', 'add', $f); + if (grep { $_ eq $f } @bfiles) { + system('cvs', 'add','-kb',$f); + } else { + system('cvs', 'add', $f); + } if ($?) { - $dirty = 1; + $dirtypatch = 1; warn "Failed to cvs add $f -- you may need to do it manually"; } } @@ -252,35 +215,40 @@ foreach my $f (@afiles) { foreach my $f (@dfiles) { system('cvs', 'rm', '-f', $f); if ($?) { - $dirty = 1; + $dirtypatch = 1; warn "Failed to cvs rm -f $f -- you may need to do it manually"; } } print "Commit to CVS\n"; -print "Patch: $title\n"; -my $commitfiles = join(' ', @afiles, @mfiles, @dfiles); -my $cmd = "cvs commit -F .msg $commitfiles"; +print "Patch title (first comment line): $title\n"; +my @commitfiles = map { unless (m/\s/) { '\''.$_.'\''; } else { $_; }; } (@files); +my $cmd = "cvs commit -F .msg @commitfiles"; if ($dirtypatch) { print "NOTE: One or more hunks failed to apply cleanly.\n"; - print "Resolve the conflicts and then commit using:\n"; + print "You'll need to apply the patch in .cvsexportcommit.diff manually\n"; + print "using a patch program. After applying the patch and resolving the\n"; + print "problems you may commit using:"; print "\n $cmd\n\n"; exit(1); } - if ($opt_c) { print "Autocommit\n $cmd\n"; - print safe_pipe_capture('cvs', 'commit', '-F', '.msg', @afiles, @mfiles, @dfiles); + print safe_pipe_capture('cvs', 'commit', '-F', '.msg', @files); if ($?) { - cleanupcvs(@files); die "Exiting: The commit did not succeed"; } print "Committed successfully to CVS\n"; } else { print "Ready for you to commit, just run:\n\n $cmd\n"; } + +# clean up +unlink(".cvsexportcommit.diff"); +unlink(".msg"); + sub usage { print STDERR <<END; Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [-f] [-m msgprefix] [ parent ] commit @@ -288,17 +256,6 @@ END exit(1); } -# ensure cvs is clean before we die -sub cleanupcvs { - my @files = @_; - foreach my $f (@files) { - system('cvs', '-q', 'update', '-C', $f); - if ($?) { - warn "Warning! Failed to cleanup state of $f\n"; - } - } -} - # An alternative to `command` that allows input to be passed as an array # to work around shell problems with weird characters in arguments # if the exec returns non-zero we die @@ -312,3 +269,16 @@ sub safe_pipe_capture { } return wantarray ? @output : join('',@output); } + +sub safe_pipe_capture_blob { + my $output; + if (my $pid = open my $child, '-|') { + local $/; + undef $/; + $output = (<$child>); + close $child or die join(' ',@_).": $! $?"; + } else { + exec(@_) or die "$! $?"; # exec() can fail the executable can't be found + } + return $output; +} diff --git a/git-cvsimport.perl b/git-cvsimport.perl index e5a00a1285..35ef0c0ee5 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -29,7 +29,7 @@ use IPC::Open2; $SIG{'PIPE'}="IGNORE"; $ENV{'TZ'}="UTC"; -our($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L); +our ($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L, $opt_a); my (%conv_author_name, %conv_author_email); sub usage() { @@ -37,7 +37,7 @@ sub usage() { Usage: ${\basename $0} # fetch/update GIT from CVS [-o branch-for-HEAD] [-h] [-v] [-d CVSROOT] [-A author-conv-file] [-p opts-for-cvsps] [-C GIT_repository] [-z fuzz] [-i] [-k] [-u] - [-s subst] [-m] [-M regex] [-S regex] [CVS_module] + [-s subst] [-a] [-m] [-M regex] [-S regex] [CVS_module] END exit(1); } @@ -90,21 +90,23 @@ usage if $opt_h; @ARGV <= 1 or usage(); -if($opt_d) { +if ($opt_d) { $ENV{"CVSROOT"} = $opt_d; -} elsif(-f 'CVS/Root') { +} elsif (-f 'CVS/Root') { open my $f, '<', 'CVS/Root' or die 'Failed to open CVS/Root'; $opt_d = <$f>; chomp $opt_d; close $f; $ENV{"CVSROOT"} = $opt_d; -} elsif($ENV{"CVSROOT"}) { +} elsif ($ENV{"CVSROOT"}) { $opt_d = $ENV{"CVSROOT"}; } else { die "CVSROOT needs to be set"; } $opt_o ||= "origin"; $opt_s ||= "-"; +$opt_a ||= 0; + my $git_tree = $opt_C; $git_tree ||= "."; @@ -129,6 +131,11 @@ if ($opt_M) { push (@mergerx, qr/$opt_M/); } +# Remember UTC of our starting time +# we'll want to avoid importing commits +# that are too recent +our $starttime = time(); + select(STDERR); $|=1; select(STDOUT); @@ -141,7 +148,7 @@ use File::Temp qw(tempfile); use POSIX qw(strftime dup2); sub new { - my($what,$repo,$subdir) = @_; + my ($what,$repo,$subdir) = @_; $what=ref($what) if ref($what); my $self = {}; @@ -161,24 +168,38 @@ sub new { sub conn { my $self = shift; my $repo = $self->{'fullrep'}; - if($repo =~ s/^:pserver:(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) { - my($user,$pass,$serv,$port) = ($1,$2,$3,$4); + if ($repo =~ s/^:pserver(?:([^:]*)):(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) { + my ($param,$user,$pass,$serv,$port) = ($1,$2,$3,$4,$5); + + my ($proxyhost,$proxyport); + if ($param && ($param =~ m/proxy=([^;]+)/)) { + $proxyhost = $1; + # Default proxyport, if not specified, is 8080. + $proxyport = 8080; + if ($ENV{"CVS_PROXY_PORT"}) { + $proxyport = $ENV{"CVS_PROXY_PORT"}; + } + if ($param =~ m/proxyport=([^;]+)/) { + $proxyport = $1; + } + } + $user="anonymous" unless defined $user; my $rr2 = "-"; - unless($port) { + unless ($port) { $rr2 = ":pserver:$user\@$serv:$repo"; $port=2401; } my $rr = ":pserver:$user\@$serv:$port$repo"; - unless($pass) { + unless ($pass) { open(H,$ENV{'HOME'}."/.cvspass") and do { # :pserver:cvs@mea.tmt.tele.fi:/cvsroot/zmailer Ah<Z - while(<H>) { + while (<H>) { chomp; s/^\/\d+\s+//; my ($w,$p) = split(/\s/,$_,2); - if($w eq $rr or $w eq $rr2) { + if ($w eq $rr or $w eq $rr2) { $pass = $p; last; } @@ -187,15 +208,45 @@ sub conn { } $pass="A" unless $pass; - my $s = IO::Socket::INET->new(PeerHost => $serv, PeerPort => $port); - die "Socket to $serv: $!\n" unless defined $s; + my ($s, $rep); + if ($proxyhost) { + + # Use a HTTP Proxy. Only works for HTTP proxies that + # don't require user authentication + # + # See: http://www.ietf.org/rfc/rfc2817.txt + + $s = IO::Socket::INET->new(PeerHost => $proxyhost, PeerPort => $proxyport); + die "Socket to $proxyhost: $!\n" unless defined $s; + $s->write("CONNECT $serv:$port HTTP/1.1\r\nHost: $serv:$port\r\n\r\n") + or die "Write to $proxyhost: $!\n"; + $s->flush(); + + $rep = <$s>; + + # The answer should look like 'HTTP/1.x 2yy ....' + if (!($rep =~ m#^HTTP/1\.. 2[0-9][0-9]#)) { + die "Proxy connect: $rep\n"; + } + # Skip up to the empty line of the proxy server output + # including the response headers. + while ($rep = <$s>) { + last if (!defined $rep || + $rep eq "\n" || + $rep eq "\r\n"); + } + } else { + $s = IO::Socket::INET->new(PeerHost => $serv, PeerPort => $port); + die "Socket to $serv: $!\n" unless defined $s; + } + $s->write("BEGIN AUTH REQUEST\n$repo\n$user\n$pass\nEND AUTH REQUEST\n") or die "Write to $serv: $!\n"; $s->flush(); - my $rep = <$s>; + $rep = <$s>; - if($rep ne "I LOVE YOU\n") { + if ($rep ne "I LOVE YOU\n") { $rep="<unknown>" unless $rep; die "AuthReply: $rep\n"; } @@ -227,7 +278,7 @@ sub conn { } } - unless($pid) { + unless ($pid) { $pr->writer(); $pw->reader(); dup2($pw->fileno(),0); @@ -250,7 +301,7 @@ sub conn { $self->{'socketo'}->flush(); chomp(my $rep=$self->readline()); - if($rep !~ s/^Valid-requests\s*//) { + if ($rep !~ s/^Valid-requests\s*//) { $rep="<unknown>" unless $rep; die "Expected Valid-requests from server, but got: $rep\n"; } @@ -262,14 +313,14 @@ sub conn { } sub readline { - my($self) = @_; + my ($self) = @_; return $self->{'socketi'}->getline(); } sub _file { # Request a file with a given revision. # Trial and error says this is a good way to do it. :-/ - my($self,$fn,$rev) = @_; + my ($self,$fn,$rev) = @_; $self->{'socketo'}->write("Argument -N\n") or return undef; $self->{'socketo'}->write("Argument -P\n") or return undef; # -kk: Linus' version doesn't use it - defaults to off @@ -291,12 +342,12 @@ sub _file { sub _line { # Read a line from the server. # ... except that 'line' may be an entire file. ;-) - my($self, $fh) = @_; + my ($self, $fh) = @_; die "Not in lines" unless defined $self->{'lines'}; my $line; my $res=0; - while(defined($line = $self->readline())) { + while (defined($line = $self->readline())) { # M U gnupg-cvs-rep/AUTHORS # Updated gnupg-cvs-rep/ # /daten/src/rsync/gnupg-cvs-rep/AUTHORS @@ -305,7 +356,7 @@ sub _line { # 0 # ok - if($line =~ s/^(?:Created|Updated) //) { + if ($line =~ s/^(?:Created|Updated) //) { $line = $self->readline(); # path $line = $self->readline(); # Entries line my $mode = $self->readline(); chomp $mode; @@ -316,12 +367,12 @@ sub _line { die "Duh: Filesize $cnt" if $cnt !~ /^\d+$/; $line=""; $res = $self->_fetchfile($fh, $cnt); - } elsif($line =~ s/^ //) { + } elsif ($line =~ s/^ //) { print $fh $line; $res += length($line); - } elsif($line =~ /^M\b/) { + } elsif ($line =~ /^M\b/) { # output, do nothing - } elsif($line =~ /^Mbinary\b/) { + } elsif ($line =~ /^Mbinary\b/) { my $cnt; die "EOF from server after 'Mbinary'" unless defined ($cnt = $self->readline()); chomp $cnt; @@ -330,12 +381,12 @@ sub _line { $res += $self->_fetchfile($fh, $cnt); } else { chomp $line; - if($line eq "ok") { + if ($line eq "ok") { # print STDERR "S: ok (".length($res).")\n"; return $res; - } elsif($line =~ s/^E //) { + } elsif ($line =~ s/^E //) { # print STDERR "S: $line\n"; - } elsif($line =~ /^(Remove-entry|Removed) /i) { + } elsif ($line =~ /^(Remove-entry|Removed) /i) { $line = $self->readline(); # filename $line = $self->readline(); # OK chomp $line; @@ -349,7 +400,7 @@ sub _line { return undef; } sub file { - my($self,$fn,$rev) = @_; + my ($self,$fn,$rev) = @_; my $res; my ($fh, $name) = tempfile('gitcvs.XXXXXX', @@ -373,7 +424,7 @@ sub _fetchfile { my ($self, $fh, $cnt) = @_; my $res = 0; my $bufsize = 1024 * 1024; - while($cnt) { + while ($cnt) { if ($bufsize > $cnt) { $bufsize = $cnt; } @@ -394,7 +445,7 @@ my $cvs = CVSconn->new($opt_d, $cvs_tree); sub pdate($) { - my($d) = @_; + my ($d) = @_; m#(\d{2,4})/(\d\d)/(\d\d)\s(\d\d):(\d\d)(?::(\d\d))?# or die "Unparseable date: $d\n"; my $y=$1; $y-=1900 if $y>1900; @@ -402,22 +453,22 @@ sub pdate($) { } sub pmode($) { - my($mode) = @_; + my ($mode) = @_; my $m = 0; my $mm = 0; my $um = 0; for my $x(split(//,$mode)) { - if($x eq ",") { + if ($x eq ",") { $m |= $mm&$um; $mm = 0; $um = 0; - } elsif($x eq "u") { $um |= 0700; - } elsif($x eq "g") { $um |= 0070; - } elsif($x eq "o") { $um |= 0007; - } elsif($x eq "r") { $mm |= 0444; - } elsif($x eq "w") { $mm |= 0222; - } elsif($x eq "x") { $mm |= 0111; - } elsif($x eq "=") { # do nothing + } elsif ($x eq "u") { $um |= 0700; + } elsif ($x eq "g") { $um |= 0070; + } elsif ($x eq "o") { $um |= 0007; + } elsif ($x eq "r") { $mm |= 0444; + } elsif ($x eq "w") { $mm |= 0222; + } elsif ($x eq "x") { $mm |= 0111; + } elsif ($x eq "=") { # do nothing } else { die "Unknown mode: $mode\n"; } } @@ -441,7 +492,7 @@ sub get_headref ($$) { my $git_dir = shift; my $f = "$git_dir/refs/heads/$name"; - if(open(my $fh, $f)) { + if (open(my $fh, $f)) { chomp(my $r = <$fh>); is_sha1($r) or die "Cannot get head id for $name ($r): $!"; return $r; @@ -468,8 +519,8 @@ $orig_git_index = $ENV{GIT_INDEX_FILE} if exists $ENV{GIT_INDEX_FILE}; my %index; # holds filenames of one index per branch -unless(-d $git_dir) { - system("git-init-db"); +unless (-d $git_dir) { + system("git-init"); die "Cannot init the GIT db at $git_tree: $?\n" if $?; system("git-read-tree"); die "Cannot init an empty tree: $?\n" if $?; @@ -487,7 +538,7 @@ unless(-d $git_dir) { chomp ($last_branch = <F>); $last_branch = basename($last_branch); close(F); - unless($last_branch) { + unless ($last_branch) { warn "Cannot read the last branch name: $! -- assuming 'master'\n"; $last_branch = "master"; } @@ -495,22 +546,17 @@ unless(-d $git_dir) { $tip_at_start = `git-rev-parse --verify HEAD`; # Get the last import timestamps - opendir(D,"$git_dir/refs/heads"); - while(defined(my $head = readdir(D))) { - next if $head =~ /^\./; - open(F,"$git_dir/refs/heads/$head") - or die "Bad head branch: $head: $!\n"; - chomp(my $ftag = <F>); - close(F); - open(F,"git-cat-file commit $ftag |"); - while(<F>) { - next unless /^author\s.*\s(\d+)\s[-+]\d{4}$/; - $branch_date{$head} = $1; - last; - } - close(F); + my $fmt = '($ref, $author) = (%(refname), %(author));'; + open(H, "git-for-each-ref --perl --format='$fmt' refs/heads |") or + die "Cannot run git-for-each-ref: $!\n"; + while (defined(my $entry = <H>)) { + my ($ref, $author); + eval($entry) || die "cannot eval refs list: $@"; + my ($head) = ($ref =~ m|^refs/heads/(.*)|); + $author =~ /^.*\s(\d+)\s[-+]\d{4}$/; + $branch_date{$head} = $1; } - closedir(D); + close(H); } -d $git_dir @@ -529,11 +575,13 @@ if ($opt_A) { # run cvsps into a file unless we are getting # it passed as a file via $opt_P # +my $cvspsfile; unless ($opt_P) { print "Running cvsps...\n" if $opt_v; my $pid = open(CVSPS,"-|"); + my $cvspsfh; die "Cannot fork: $!\n" unless defined $pid; - unless($pid) { + unless ($pid) { my @opt; @opt = split(/,/,$opt_p) if defined $opt_p; unshift @opt, '-z', $opt_z if defined $opt_z; @@ -544,18 +592,18 @@ unless ($opt_P) { exec("cvsps","--norc",@opt,"-u","-A",'--root',$opt_d,$cvs_tree); die "Could not start cvsps: $!\n"; } - my ($cvspsfh, $cvspsfile) = tempfile('gitXXXXXX', SUFFIX => '.cvsps', - DIR => File::Spec->tmpdir()); + ($cvspsfh, $cvspsfile) = tempfile('gitXXXXXX', SUFFIX => '.cvsps', + DIR => File::Spec->tmpdir()); while (<CVSPS>) { print $cvspsfh $_; } close CVSPS; close $cvspsfh; - $opt_P = $cvspsfile; +} else { + $cvspsfile = $opt_P; } - -open(CVS, "<$opt_P") or die $!; +open(CVS, "<$cvspsfile") or die $!; ## cvsps output: #--------------------- @@ -603,8 +651,8 @@ sub write_tree () { return $tree; } -my($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg); -my(@old,@new,@skipped,%ignorebranch); +my ($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg); +my (@old,@new,@skipped,%ignorebranch); # commits that cvsps cannot place anywhere... $ignorebranch{'#CVSPS_NO_BRANCH'} = 1; @@ -612,7 +660,7 @@ $ignorebranch{'#CVSPS_NO_BRANCH'} = 1; sub commit { if ($branch eq $opt_o && !$index{branch} && !get_headref($branch, $git_dir)) { # looks like an initial commit - # use the index primed by git-init-db + # use the index primed by git-init $ENV{GIT_INDEX_FILE} = '.git/index'; $index{$branch} = '.git/index'; } else { @@ -645,7 +693,7 @@ sub commit { foreach my $rx (@mergerx) { next unless $logmsg =~ $rx && $1; my $mparent = $1 eq 'HEAD' ? $opt_o : $1; - if(my $sha1 = get_headref($mparent, $git_dir)) { + if (my $sha1 = get_headref($mparent, $git_dir)) { push @commit_args, '-p', $mparent; print "Merge parent branch: $mparent\n" if $opt_v; } @@ -686,9 +734,9 @@ sub commit { system("git-update-ref refs/heads/$branch $cid") == 0 or die "Cannot write branch $branch for update: $!\n"; - if($tag) { - my($in, $out) = ('',''); - my($xtag) = $tag; + if ($tag) { + my ($in, $out) = ('',''); + my ($xtag) = $tag; $xtag =~ s/\s+\*\*.*$//; # Remove stuff like ** INVALID ** and ** FUNKY ** $xtag =~ tr/_/\./ if ( $opt_u ); $xtag =~ s/[\/]/$opt_s/g; @@ -723,25 +771,25 @@ sub commit { }; my $commitcount = 1; -while(<CVS>) { +while (<CVS>) { chomp; - if($state == 0 and /^-+$/) { + if ($state == 0 and /^-+$/) { $state = 1; - } elsif($state == 0) { + } elsif ($state == 0) { $state = 1; redo; - } elsif(($state==0 or $state==1) and s/^PatchSet\s+//) { + } elsif (($state==0 or $state==1) and s/^PatchSet\s+//) { $patchset = 0+$_; $state=2; - } elsif($state == 2 and s/^Date:\s+//) { + } elsif ($state == 2 and s/^Date:\s+//) { $date = pdate($_); - unless($date) { + unless ($date) { print STDERR "Could not parse date: $_\n"; $state=0; next; } $state=3; - } elsif($state == 3 and s/^Author:\s+//) { + } elsif ($state == 3 and s/^Author:\s+//) { s/\s+$//; if (/^(.*?)\s+<(.*)>/) { ($author_name, $author_email) = ($1, $2); @@ -752,55 +800,64 @@ while(<CVS>) { $author_name = $author_email = $_; } $state = 4; - } elsif($state == 4 and s/^Branch:\s+//) { + } elsif ($state == 4 and s/^Branch:\s+//) { s/\s+$//; s/[\/]/$opt_s/g; $branch = $_; $state = 5; - } elsif($state == 5 and s/^Ancestor branch:\s+//) { + } elsif ($state == 5 and s/^Ancestor branch:\s+//) { s/\s+$//; $ancestor = $_; $ancestor = $opt_o if $ancestor eq "HEAD"; $state = 6; - } elsif($state == 5) { + } elsif ($state == 5) { $ancestor = undef; $state = 6; redo; - } elsif($state == 6 and s/^Tag:\s+//) { + } elsif ($state == 6 and s/^Tag:\s+//) { s/\s+$//; - if($_ eq "(none)") { + if ($_ eq "(none)") { $tag = undef; } else { $tag = $_; } $state = 7; - } elsif($state == 7 and /^Log:/) { + } elsif ($state == 7 and /^Log:/) { $logmsg = ""; $state = 8; - } elsif($state == 8 and /^Members:/) { + } elsif ($state == 8 and /^Members:/) { $branch = $opt_o if $branch eq "HEAD"; - if(defined $branch_date{$branch} and $branch_date{$branch} >= $date) { + if (defined $branch_date{$branch} and $branch_date{$branch} >= $date) { # skip print "skip patchset $patchset: $date before $branch_date{$branch}\n" if $opt_v; $state = 11; next; } + if (!$opt_a && $starttime - 300 - (defined $opt_z ? $opt_z : 300) <= $date) { + # skip if the commit is too recent + # that the cvsps default fuzz is 300s, we give ourselves another + # 300s just in case -- this also prevents skipping commits + # due to server clock drift + print "skip patchset $patchset: $date too recent\n" if $opt_v; + $state = 11; + next; + } if (exists $ignorebranch{$branch}) { print STDERR "Skipping $branch\n"; $state = 11; next; } - if($ancestor) { - if($ancestor eq $branch) { + if ($ancestor) { + if ($ancestor eq $branch) { print STDERR "Branch $branch erroneously stems from itself -- changed ancestor to $opt_o\n"; $ancestor = $opt_o; } - if(-f "$git_dir/refs/heads/$branch") { + if (-f "$git_dir/refs/heads/$branch") { print STDERR "Branch $branch already exists!\n"; $state=11; next; } - unless(open(H,"$git_dir/refs/heads/$ancestor")) { + unless (open(H,"$git_dir/refs/heads/$ancestor")) { print STDERR "Branch $ancestor does not exist!\n"; $ignorebranch{$branch} = 1; $state=11; @@ -808,7 +865,7 @@ while(<CVS>) { } chomp(my $id = <H>); close(H); - unless(open(H,"> $git_dir/refs/heads/$branch")) { + unless (open(H,"> $git_dir/refs/heads/$branch")) { print STDERR "Could not create branch $branch: $!\n"; $ignorebranch{$branch} = 1; $state=11; @@ -821,9 +878,9 @@ while(<CVS>) { } $last_branch = $branch if $branch ne $last_branch; $state = 9; - } elsif($state == 8) { + } elsif ($state == 8) { $logmsg .= "$_\n"; - } elsif($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) { + } elsif ($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) { # VERSION:1.96->1.96.2.1 my $init = ($2 eq "INITIAL"); my $fn = $1; @@ -836,7 +893,7 @@ while(<CVS>) { } print "Fetching $fn v $rev\n" if $opt_v; my ($tmpname, $size) = $cvs->file($fn,$rev); - if($size == -1) { + if ($size == -1) { push(@old,$fn); print "Drop $fn\n" if $opt_v; } else { @@ -854,14 +911,14 @@ while(<CVS>) { push(@new,[$mode, $sha, $fn]); # may be resurrected! } unlink($tmpname); - } elsif($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) { + } elsif ($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) { my $fn = $1; $fn =~ s#^/+##; push(@old,$fn); print "Delete $fn\n" if $opt_v; - } elsif($state == 9 and /^\s*$/) { + } elsif ($state == 9 and /^\s*$/) { $state = 10; - } elsif(($state == 9 or $state == 10) and /^-+$/) { + } elsif (($state == 9 or $state == 10) and /^-+$/) { $commitcount++; if ($opt_L && $commitcount > $opt_L) { last; @@ -871,16 +928,30 @@ while(<CVS>) { system("git repack -a -d"); } $state = 1; - } elsif($state == 11 and /^-+$/) { + } elsif ($state == 11 and /^-+$/) { $state = 1; - } elsif(/^-+$/) { # end of unknown-line processing + } elsif (/^-+$/) { # end of unknown-line processing $state = 1; - } elsif($state != 11) { # ignore stuff when skipping + } elsif ($state != 11) { # ignore stuff when skipping print "* UNKNOWN LINE * $_\n"; } } commit() if $branch and $state != 11; +unless ($opt_P) { + unlink($cvspsfile); +} + +# The heuristic of repacking every 1024 commits can leave a +# lot of unpacked data. If there is more than 1MB worth of +# not-packed objects, repack once more. +my $line = `git-count-objects`; +if ($line =~ /^(\d+) objects, (\d+) kilobytes$/) { + my ($n_objects, $kb) = ($1, $2); + 1024 < $kb + and system("git repack -a -d"); +} + foreach my $git_index (values %index) { if ($git_index ne '.git/index') { unlink($git_index); @@ -894,7 +965,7 @@ if (defined $orig_git_index) { } # Now switch back to the branch we were in before all of this happened -if($orig_branch) { +if ($orig_branch) { print "DONE.\n" if $opt_v; if ($opt_i) { exit 0; diff --git a/git-cvsserver.perl b/git-cvsserver.perl index 2130d57020..a33a876ff6 100755 --- a/git-cvsserver.perl +++ b/git-cvsserver.perl @@ -17,6 +17,7 @@ use strict; use warnings; +use bytes; use Fcntl; use File::Temp qw/tempdir tempfile/; @@ -275,7 +276,7 @@ sub req_Directory $state->{directory} = "" if ( $state->{directory} eq "." ); $state->{directory} .= "/" if ( $state->{directory} =~ /\S/ ); - if ( not defined($state->{prependdir}) and $state->{localdir} eq "." and $state->{path} =~ /\S/ ) + if ( (not defined($state->{prependdir}) or $state->{prependdir} eq '') and $state->{localdir} eq "." and $state->{path} =~ /\S/ ) { $log->info("Setting prepend to '$state->{path}'"); $state->{prependdir} = $state->{path}; @@ -805,7 +806,14 @@ sub req_update $meta = $updater->getmeta($filename); } - next unless ( $meta->{revision} ); + if ( ! defined $meta ) + { + $meta = { + name => $filename, + revision => 0, + filehash => 'added' + }; + } my $oldmeta = $meta; @@ -835,7 +843,7 @@ sub req_update and not exists ( $state->{opt}{C} ) ) { $log->info("Tell the client the file is modified"); - print "MT text U\n"; + print "MT text M \n"; print "MT fname $filename\n"; print "MT newline\n"; next; @@ -855,15 +863,36 @@ sub req_update } } elsif ( not defined ( $state->{entries}{$filename}{modified_hash} ) - or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} ) + or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} + or $meta->{filehash} eq 'added' ) { - $log->info("Updating '$filename'"); - # normal update, just send the new revision (either U=Update, or A=Add, or R=Remove) - print "MT +updated\n"; - print "MT text U\n"; - print "MT fname $filename\n"; - print "MT newline\n"; - print "MT -updated\n"; + # normal update, just send the new revision (either U=Update, + # or A=Add, or R=Remove) + if ( defined($wrev) && $wrev < 0 ) + { + $log->info("Tell the client the file is scheduled for removal"); + print "MT text R \n"; + print "MT fname $filename\n"; + print "MT newline\n"; + next; + } + elsif ( !defined($wrev) || $wrev == 0 ) + { + $log->info("Tell the client the file will be added"); + print "MT text A \n"; + print "MT fname $filename\n"; + print "MT newline\n"; + next; + + } + else { + $log->info("Updating '$filename' $wrev"); + print "MT +updated\n"; + print "MT text U \n"; + print "MT fname $filename\n"; + print "MT newline\n"; + print "MT -updated\n"; + } my ( $filepart, $dirpart ) = filenamesplit($filename,1); @@ -917,7 +946,7 @@ sub req_update $log->debug("Temporary directory for merge is $dir"); - my $return = system("merge", $file_local, $file_old, $file_new); + my $return = system("git", "merge-file", $file_local, $file_old, $file_new); $return >>= 8; if ( $return == 0 ) @@ -1152,12 +1181,15 @@ sub req_ci $filename = filecleanup($filename); my $meta = $updater->getmeta($filename); + unless (defined $meta->{revision}) { + $meta->{revision} = 1; + } my ( $filepart, $dirpart ) = filenamesplit($filename, 1); $log->debug("Checked-in $dirpart : $filename"); - if ( $meta->{filehash} eq "deleted" ) + if ( defined $meta->{filehash} && $meta->{filehash} eq "deleted" ) { print "Remove-entry $dirpart\n"; print "$filename\n"; @@ -1709,6 +1741,17 @@ sub argsfromdir return if ( scalar ( @{$state->{args}} ) > 1 ); + my @gethead = @{$updater->gethead}; + + # push added files + foreach my $file (keys %{$state->{entries}}) { + if ( exists $state->{entries}{$file}{revision} && + $state->{entries}{$file}{revision} == 0 ) + { + push @gethead, { name => $file, filehash => 'added' }; + } + } + if ( scalar(@{$state->{args}}) == 1 ) { my $arg = $state->{args}[0]; @@ -1716,7 +1759,7 @@ sub argsfromdir $log->info("Only one arg specified, checking for directory expansion on '$arg'"); - foreach my $file ( @{$updater->gethead} ) + foreach my $file ( @gethead ) { next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) ); next unless ( $file->{name} =~ /^$arg\// or $file->{name} eq $arg ); @@ -1729,7 +1772,7 @@ sub argsfromdir $state->{args} = []; - foreach my $file ( @{$updater->gethead} ) + foreach my $file ( @gethead ) { next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) ); next unless ( $file->{name} =~ s/^$state->{prependdir}// ); @@ -2079,9 +2122,17 @@ sub new mode TEXT NOT NULL ) "); + $self->{dbh}->do(" + CREATE INDEX revision_ix1 + ON revision (name,revision) + "); + $self->{dbh}->do(" + CREATE INDEX revision_ix2 + ON revision (name,commithash) + "); } - # Construct the revision table if required + # Construct the head table if required unless ( $self->{tables}{head} ) { $self->{dbh}->do(" @@ -2095,6 +2146,10 @@ sub new mode TEXT NOT NULL ) "); + $self->{dbh}->do(" + CREATE INDEX head_ix1 + ON head (name) + "); } # Construct the properties table if required @@ -2132,7 +2187,10 @@ sub update # first lets get the commit list $ENV{GIT_DIR} = $self->{git_path}; - my $commitinfo = `git-cat-file commit $self->{module} 2>&1`; + my $commitsha1 = `git rev-parse $self->{module}`; + chomp $commitsha1; + + my $commitinfo = `git cat-file commit $self->{module} 2>&1`; unless ( $commitinfo =~ /tree\s+[a-zA-Z0-9]{40}/ ) { die("Invalid module '$self->{module}'"); @@ -2142,6 +2200,10 @@ sub update my $git_log; my $lastcommit = $self->_get_prop("last_commit"); + if (defined $lastcommit && $lastcommit eq $commitsha1) { # up-to-date + return 1; + } + # Start exclusive lock here... $self->{dbh}->begin_work() or die "Cannot lock database for BEGIN"; @@ -2292,67 +2354,72 @@ sub update if ( defined ( $lastpicked ) ) { - my $filepipe = open(FILELIST, '-|', 'git-diff-tree', '-r', $lastpicked, $commit->{hash}) or die("Cannot call git-diff-tree : $!"); + my $filepipe = open(FILELIST, '-|', 'git-diff-tree', '-z', '-r', $lastpicked, $commit->{hash}) or die("Cannot call git-diff-tree : $!"); + local ($/) = "\0"; while ( <FILELIST> ) { - unless ( /^:\d{6}\s+\d{3}(\d)\d{2}\s+[a-zA-Z0-9]{40}\s+([a-zA-Z0-9]{40})\s+(\w)\s+(.*)$/o ) + chomp; + unless ( /^:\d{6}\s+\d{3}(\d)\d{2}\s+[a-zA-Z0-9]{40}\s+([a-zA-Z0-9]{40})\s+(\w)$/o ) { die("Couldn't process git-diff-tree line : $_"); } + my ($mode, $hash, $change) = ($1, $2, $3); + my $name = <FILELIST>; + chomp($name); - # $log->debug("File mode=$1, hash=$2, change=$3, name=$4"); + # $log->debug("File mode=$mode, hash=$hash, change=$change, name=$name"); my $git_perms = ""; - $git_perms .= "r" if ( $1 & 4 ); - $git_perms .= "w" if ( $1 & 2 ); - $git_perms .= "x" if ( $1 & 1 ); + $git_perms .= "r" if ( $mode & 4 ); + $git_perms .= "w" if ( $mode & 2 ); + $git_perms .= "x" if ( $mode & 1 ); $git_perms = "rw" if ( $git_perms eq "" ); - if ( $3 eq "D" ) + if ( $change eq "D" ) { - #$log->debug("DELETE $4"); - $head->{$4} = { - name => $4, - revision => $head->{$4}{revision} + 1, + #$log->debug("DELETE $name"); + $head->{$name} = { + name => $name, + revision => $head->{$name}{revision} + 1, filehash => "deleted", commithash => $commit->{hash}, modified => $commit->{date}, author => $commit->{author}, mode => $git_perms, }; - $self->insert_rev($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + $self->insert_rev($name, $head->{$name}{revision}, $hash, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); } - elsif ( $3 eq "M" ) + elsif ( $change eq "M" ) { - #$log->debug("MODIFIED $4"); - $head->{$4} = { - name => $4, - revision => $head->{$4}{revision} + 1, - filehash => $2, + #$log->debug("MODIFIED $name"); + $head->{$name} = { + name => $name, + revision => $head->{$name}{revision} + 1, + filehash => $hash, commithash => $commit->{hash}, modified => $commit->{date}, author => $commit->{author}, mode => $git_perms, }; - $self->insert_rev($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + $self->insert_rev($name, $head->{$name}{revision}, $hash, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); } - elsif ( $3 eq "A" ) + elsif ( $change eq "A" ) { - #$log->debug("ADDED $4"); - $head->{$4} = { - name => $4, + #$log->debug("ADDED $name"); + $head->{$name} = { + name => $name, revision => 1, - filehash => $2, + filehash => $hash, commithash => $commit->{hash}, modified => $commit->{date}, author => $commit->{author}, mode => $git_perms, }; - $self->insert_rev($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + $self->insert_rev($name, $head->{$name}{revision}, $hash, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); } else { - $log->warn("UNKNOWN FILE CHANGE mode=$1, hash=$2, change=$3, name=$4"); + $log->warn("UNKNOWN FILE CHANGE mode=$mode, hash=$hash, change=$change, name=$name"); die; } } @@ -2361,10 +2428,12 @@ sub update # this is used to detect files removed from the repo my $seen_files = {}; - my $filepipe = open(FILELIST, '-|', 'git-ls-tree', '-r', $commit->{hash}) or die("Cannot call git-ls-tree : $!"); + my $filepipe = open(FILELIST, '-|', 'git-ls-tree', '-z', '-r', $commit->{hash}) or die("Cannot call git-ls-tree : $!"); + local $/ = "\0"; while ( <FILELIST> ) { - unless ( /^(\d+)\s+(\w+)\s+([a-zA-Z0-9]+)\s+(.*)$/o ) + chomp; + unless ( /^(\d+)\s+(\w+)\s+([a-zA-Z0-9]+)\t(.*)$/o ) { die("Couldn't process git-ls-tree line : $_"); } diff --git a/git-fetch.sh b/git-fetch.sh index c2eebee798..c58704d794 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -2,7 +2,15 @@ # USAGE='<fetch-options> <repository> <refspec>...' +SUBDIRECTORY_OK=Yes . git-sh-setup +set_reflog_action "fetch $*" + +TOP=$(git-rev-parse --show-cdup) +if test ! -z "$TOP" +then + cd "$TOP" +fi . git-parse-remote _x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]' _x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40" @@ -11,7 +19,6 @@ LF=' ' IFS="$LF" -rloga=fetch no_tags= tags= append= @@ -20,7 +27,8 @@ verbose= update_head_ok= exec= upload_pack= -keep=--thin +keep= +shallow_depth= while case "$#" in 0) break ;; esac do case "$1" in @@ -51,10 +59,14 @@ do verbose=Yes ;; -k|--k|--ke|--kee|--keep) - keep=--keep + keep='-k -k' + ;; + --depth=*) + shallow_depth="--depth=`expr "z$1" : 'z-[^=]*=\(.*\)'`" ;; - --reflog-action=*) - rloga=`expr "z$1" : 'z-[^=]*=\(.*\)'` + --depth) + shift + shallow_depth="--depth=$1" ;; -*) usage @@ -68,11 +80,10 @@ done case "$#" in 0) - test -f "$GIT_DIR/branches/origin" || - test -f "$GIT_DIR/remotes/origin" || - git-repo-config --get remote.origin.url >/dev/null || - die "Where do you want to fetch from today?" - set origin ;; + origin=$(get_default_remote) + test -n "$(get_remote_url ${origin})" || + die "Where do you want to fetch from today?" + set x $origin ; shift ;; esac remote_nick="$1" @@ -81,14 +92,15 @@ refs= rref= rsync_slurped_objects= -rloga="$rloga $remote_nick" -test "$remote_nick" = "$remote" || rloga="$rloga $remote" - if test "" = "$append" then : >"$GIT_DIR/FETCH_HEAD" fi +# Global that is reused later +ls_remote_result=$(git ls-remote $upload_pack "$remote") || + die "Cannot get the repository state from $remote" + append_fetch_head () { head_="$1" remote_="$2" @@ -130,39 +142,45 @@ append_fetch_head () { then headc_=$(git-rev-parse --verify "$head_^0") || exit echo "$headc_ $not_for_merge_ $note_" >>"$GIT_DIR/FETCH_HEAD" - [ "$verbose" ] && echo >&2 "* committish: $head_" - [ "$verbose" ] && echo >&2 " $note_" else echo "$head_ not-for-merge $note_" >>"$GIT_DIR/FETCH_HEAD" - [ "$verbose" ] && echo >&2 "* non-commit: $head_" - [ "$verbose" ] && echo >&2 " $note_" - fi - if test "$local_name_" != "" - then - # We are storing the head locally. Make sure that it is - # a fast forward (aka "reverse push"). - fast_forward_local "$local_name_" "$head_" "$note_" fi + + update_local_ref "$local_name_" "$head_" "$note_" } -fast_forward_local () { - mkdir -p "$(dirname "$GIT_DIR/$1")" +update_local_ref () { + # If we are storing the head locally make sure that it is + # a fast forward (aka "reverse push"). + + label_=$(git-cat-file -t $2) + newshort_=$(git-rev-parse --short $2) + if test -z "$1" ; then + [ "$verbose" ] && echo >&2 "* fetched $3" + [ "$verbose" ] && echo >&2 " $label_: $newshort_" + return 0 + fi + oldshort_=$(git show-ref --hash --abbrev "$1" 2>/dev/null) + case "$1" in refs/tags/*) # Tags need not be pointing at commits so there # is no way to guarantee "fast-forward" anyway. - if test -f "$GIT_DIR/$1" + if test -n "$oldshort_" then - if now_=$(cat "$GIT_DIR/$1") && test "$now_" = "$2" + if now_=$(git show-ref --hash "$1") && test "$now_" = "$2" then - [ "$verbose" ] && echo >&2 "* $1: same as $3" ||: + [ "$verbose" ] && echo >&2 "* $1: same as $3" + [ "$verbose" ] && echo >&2 " $label_: $newshort_" ||: else echo >&2 "* $1: updating with $3" - git-update-ref -m "$rloga: updating tag" "$1" "$2" + echo >&2 " $label_: $newshort_" + git-update-ref -m "$GIT_REFLOG_ACTION: updating tag" "$1" "$2" fi else echo >&2 "* $1: storing $3" - git-update-ref -m "$rloga: storing tag" "$1" "$2" + echo >&2 " $label_: $newshort_" + git-update-ref -m "$GIT_REFLOG_ACTION: storing tag" "$1" "$2" fi ;; @@ -179,42 +197,46 @@ fast_forward_local () { if test -n "$verbose" then echo >&2 "* $1: same as $3" + echo >&2 " $label_: $newshort_" fi ;; *,$local) echo >&2 "* $1: fast forward to $3" - echo >&2 " from $local to $2" - git-update-ref -m "$rloga: fast-forward" "$1" "$2" "$local" + echo >&2 " old..new: $oldshort_..$newshort_" + git-update-ref -m "$GIT_REFLOG_ACTION: fast-forward" "$1" "$2" "$local" ;; *) false ;; esac || { - echo >&2 "* $1: does not fast forward to $3;" case ",$force,$single_force," in *,t,*) - echo >&2 " forcing update." - git-update-ref -m "$rloga: forced-update" "$1" "$2" "$local" + echo >&2 "* $1: forcing update to non-fast forward $3" + echo >&2 " old...new: $oldshort_...$newshort_" + git-update-ref -m "$GIT_REFLOG_ACTION: forced-update" "$1" "$2" "$local" ;; *) - echo >&2 " not updating." + echo >&2 "* $1: not updating to non-fast forward $3" + echo >&2 " old...new: $oldshort_...$newshort_" exit 1 ;; esac } else echo >&2 "* $1: storing $3" - git-update-ref -m "$rloga: storing head" "$1" "$2" + echo >&2 " $label_: $newshort_" + git-update-ref -m "$GIT_REFLOG_ACTION: storing head" "$1" "$2" fi ;; esac } -case "$update_head_ok" in -'') +# updating the current HEAD with git-fetch in a bare +# repository is always fine. +if test -z "$update_head_ok" && test $(is_bare_repository) = false +then orig_head=$(git-rev-parse --verify HEAD 2>/dev/null) - ;; -esac +fi # If --tags (and later --heads or --all) is specified, then we are # not talking about defaults stored in Pull: line of remotes or @@ -224,11 +246,8 @@ esac reflist=$(get_remote_refs_for_fetch "$@") if test "$tags" then - taglist=`IFS=" " && - ( - git-ls-remote $upload_pack --tags "$remote" || - echo fail ouch - ) | + taglist=`IFS=' ' && + echo "$ls_remote_result" | while read sha1 name do case "$sha1" in @@ -237,6 +256,8 @@ then esac case "$name" in *^*) continue ;; + refs/tags/*) ;; + *) continue ;; esac if git-check-ref-format "$name" then @@ -258,6 +279,7 @@ fi fetch_main () { reflist="$1" refs= + rref= for ref in $reflist do @@ -286,30 +308,37 @@ fetch_main () { # There are transports that can fetch only one head at a time... case "$remote" in - http://* | https://*) + http://* | https://* | ftp://*) + test -n "$shallow_depth" && + die "shallow clone with http not supported" + proto=`expr "$remote" : '\([^:]*\):'` if [ -n "$GIT_SSL_NO_VERIFY" ]; then curl_extra_args="-k" fi - max_depth=5 - depth=0 - head="ref: $remote_name" - while (expr "z$head" : "zref:" && expr $depth \< $max_depth) >/dev/null - do - remote_name_quoted=$(@@PERL@@ -e ' - my $u = $ARGV[0]; - $u =~ s/^ref:\s*//; - $u =~ s{([^-a-zA-Z0-9/.])}{sprintf"%%%02x",ord($1)}eg; - print "$u"; - ' "$head") - head=$(curl -nsfL $curl_extra_args "$remote/$remote_name_quoted") - depth=$( expr \( $depth + 1 \) ) - done + if [ -n "$GIT_CURL_FTP_NO_EPSV" -o \ + "`git-repo-config --bool http.noEPSV`" = true ]; then + noepsv_opt="--disable-epsv" + fi + + # Find $remote_name from ls-remote output. + head=$( + IFS=' ' + echo "$ls_remote_result" | + while read sha1 name + do + test "z$name" = "z$remote_name" || continue + echo "$sha1" + break + done + ) expr "z$head" : "z$_x40\$" >/dev/null || - die "Failed to fetch $remote_name from $remote" - echo >&2 Fetching "$remote_name from $remote" using http + die "No such ref $remote_name at $remote" + echo >&2 "Fetching $remote_name from $remote using $proto" git-http-fetch -v -a "$head" "$remote/" || exit ;; rsync://*) + test -n "$shallow_depth" && + die "shallow clone with rsync not supported" TMP_HEAD="$GIT_DIR/TMP_HEAD" rsync -L -q "$remote/$remote_name" "$TMP_HEAD" || exit 1 head=$(git-rev-parse --verify TMP_HEAD) @@ -345,25 +374,41 @@ fetch_main () { esac append_fetch_head "$head" "$remote" \ - "$remote_name" "$remote_nick" "$local_name" "$not_for_merge" + "$remote_name" "$remote_nick" "$local_name" "$not_for_merge" || exit done case "$remote" in - http://* | https://* | rsync://* ) + http://* | https://* | ftp://* | rsync://* ) ;; # we are already done. *) ( : subshell because we muck with IFS IFS=" $LF" ( - git-fetch-pack $exec $keep "$remote" $rref || echo failed "$remote" + git-fetch-pack --thin $exec $keep $shallow_depth "$remote" $rref || + echo failed "$remote" ) | - while read sha1 remote_name - do + ( + trap ' + if test -n "$keepfile" && test -f "$keepfile" + then + rm -f "$keepfile" + fi + ' 0 + + keepfile= + while read sha1 remote_name + do case "$sha1" in failed) echo >&2 "Fetch failure: $remote" exit 1 ;; + # special line coming from index-pack with the pack name + pack) + continue ;; + keep) + keepfile="$GIT_OBJECT_DIRECTORY/pack/pack-$remote_name.keep" + continue ;; esac found= single_force= @@ -392,14 +437,16 @@ fetch_main () { done local_name=$(expr "z$found" : 'z[^:]*:\(.*\)') append_fetch_head "$sha1" "$remote" \ - "$remote_name" "$remote_nick" "$local_name" "$not_for_merge" - done + "$remote_name" "$remote_nick" "$local_name" \ + "$not_for_merge" || exit + done + ) ) || exit ;; esac } -fetch_main "$reflist" +fetch_main "$reflist" || exit # automated tag following case "$no_tags$tags" in @@ -408,16 +455,11 @@ case "$no_tags$tags" in *:refs/*) # effective only when we are following remote branch # using local tracking branch. - taglist=$(IFS=" " && - git-ls-remote $upload_pack --tags "$remote" | - sed -ne 's|^\([0-9a-f]*\)[ ]\(refs/tags/.*\)^{}$|\1 \2|p' | + taglist=$(IFS=' ' && + echo "$ls_remote_result" | + git-show-ref --exclude-existing=refs/tags/ | while read sha1 name do - test -f "$GIT_DIR/$name" && continue - git-check-ref-format "$name" || { - echo >&2 "warning: tag ${name} ignored" - continue - } git-cat-file -t "$sha1" >/dev/null 2>&1 || continue echo >&2 "Auto-following $name" echo ".${name}:${name}" @@ -426,21 +468,23 @@ case "$no_tags$tags" in case "$taglist" in '') ;; ?*) - fetch_main "$taglist" ;; + # do not deepen a shallow tree when following tags + shallow_depth= + fetch_main "$taglist" || exit ;; esac esac # If the original head was empty (i.e. no "master" yet), or # if we were told not to worry, we do not have to check. -case ",$update_head_ok,$orig_head," in -*,, | t,* ) +case "$orig_head" in +'') ;; -*) +?*) curr_head=$(git-rev-parse --verify HEAD 2>/dev/null) if test "$curr_head" != "$orig_head" then git-update-ref \ - -m "$rloga: Undoing incorrectly fetched HEAD." \ + -m "$GIT_REFLOG_ACTION: Undoing incorrectly fetched HEAD." \ HEAD "$orig_head" die "Cannot fetch into the current branch." fi diff --git a/git-gc.sh b/git-gc.sh new file mode 100755 index 0000000000..6de55f7292 --- /dev/null +++ b/git-gc.sh @@ -0,0 +1,15 @@ +#!/bin/sh +# +# Copyright (c) 2006, Shawn O. Pearce +# +# Cleanup unreachable files and optimize the repository. + +USAGE='' +SUBDIRECTORY_OK=Yes +. git-sh-setup + +git-pack-refs --prune && +git-reflog expire --all && +git-repack -a -d -l && +git-prune && +git-rerere gc || exit diff --git a/git-instaweb.sh b/git-instaweb.sh index 16cd351f7f..80adc8307b 100755 --- a/git-instaweb.sh +++ b/git-instaweb.sh @@ -53,6 +53,9 @@ start_httpd () { return fi done + echo "$httpd_only not found. Install $httpd_only or use" \ + "--httpd to specify another http daemon." + exit 1 fi if test $? != 0; then echo "Could not execute http daemon $httpd." @@ -160,10 +163,20 @@ apache2_conf () { test "$local" = true && bind='127.0.0.1:' echo 'text/css css' > $fqgitdir/mime.types cat > "$conf" <<EOF +ServerName "git-instaweb" ServerRoot "$fqgitdir/gitweb" DocumentRoot "$fqgitdir/gitweb" PidFile "$fqgitdir/pid" Listen $bind$port +EOF + + for mod in mime dir; do + if test -e $module_path/mod_${mod}.so; then + echo "LoadModule ${mod}_module " \ + "$module_path/mod_${mod}.so" >> "$conf" + fi + done + cat >> "$conf" <<EOF TypesConfig $fqgitdir/mime.types DirectoryIndex gitweb.cgi EOF diff --git a/git-ls-remote.sh b/git-ls-remote.sh index 2fdcaf7886..03b624ef33 100755 --- a/git-ls-remote.sh +++ b/git-ls-remote.sh @@ -49,10 +49,14 @@ trap "rm -fr $tmp-*" 0 1 2 3 15 tmpdir=$tmp-d case "$peek_repo" in -http://* | https://* ) +http://* | https://* | ftp://* ) if [ -n "$GIT_SSL_NO_VERIFY" ]; then curl_extra_args="-k" fi + if [ -n "$GIT_CURL_FTP_NO_EPSV" -o \ + "`git-repo-config --bool http.noEPSV`" = true ]; then + curl_extra_args="${curl_extra_args} --disable-epsv" + fi curl -nsf $curl_extra_args --header "Pragma: no-cache" "$peek_repo/info/refs" || echo "failed slurping" ;; @@ -90,7 +94,7 @@ while read sha1 path do case "$sha1" in failed) - die "Failed to find remote refs" + exit 1 ;; esac case "$path" in refs/heads/*) diff --git a/git-merge-one-file.sh b/git-merge-one-file.sh index fba4b0cb5f..7d62d7902c 100755 --- a/git-merge-one-file.sh +++ b/git-merge-one-file.sh @@ -23,6 +23,12 @@ case "${1:-.}${2:-.}${3:-.}" in "$1.." | "$1.$1" | "$1$1.") if [ "$2" ]; then echo "Removing $4" + else + # read-tree checked that index matches HEAD already, + # so we know we do not have this path tracked. + # there may be an unrelated working tree file here, + # which we should just leave unmolested. + exit 0 fi if test -f "$4"; then rm -f -- "$4" && @@ -34,8 +40,16 @@ case "${1:-.}${2:-.}${3:-.}" in # # Added in one. # -".$2." | "..$3" ) +".$2.") + # the other side did not add and we added so there is nothing + # to be done. + ;; +"..$3") echo "Adding $4" + test -f "$4" || { + echo "ERROR: untracked $4 is overwritten by the merge." + exit 1 + } git-update-index --add --cacheinfo "$6$7" "$2$3" "$4" && exec git-checkout-index -u -f -- "$4" ;; @@ -90,7 +104,7 @@ case "${1:-.}${2:-.}${3:-.}" in # Be careful for funny filename such as "-L" in "$4", which # would confuse "merge" greatly. src1=`git-unpack-file $2` - merge "$src1" "$orig" "$src2" + git-merge-file "$src1" "$orig" "$src2" ret=$? # Create the working tree file, using "our tree" version from the diff --git a/git-merge-recursive.py b/git-merge-recursive.py deleted file mode 100755 index 4039435ce4..0000000000 --- a/git-merge-recursive.py +++ /dev/null @@ -1,944 +0,0 @@ -#!/usr/bin/python -# -# Copyright (C) 2005 Fredrik Kuivinen -# - -import sys -sys.path.append('''@@GIT_PYTHON_PATH@@''') - -import math, random, os, re, signal, tempfile, stat, errno, traceback -from heapq import heappush, heappop -from sets import Set - -from gitMergeCommon import * - -outputIndent = 0 -def output(*args): - sys.stdout.write(' '*outputIndent) - printList(args) - -originalIndexFile = os.environ.get('GIT_INDEX_FILE', - os.environ.get('GIT_DIR', '.git') + '/index') -temporaryIndexFile = os.environ.get('GIT_DIR', '.git') + \ - '/merge-recursive-tmp-index' -def setupIndex(temporary): - try: - os.unlink(temporaryIndexFile) - except OSError: - pass - if temporary: - newIndex = temporaryIndexFile - else: - newIndex = originalIndexFile - os.environ['GIT_INDEX_FILE'] = newIndex - -# This is a global variable which is used in a number of places but -# only written to in the 'merge' function. - -# cacheOnly == True => Don't leave any non-stage 0 entries in the cache and -# don't update the working directory. -# False => Leave unmerged entries in the cache and update -# the working directory. - -cacheOnly = False - -# The entry point to the merge code -# --------------------------------- - -def merge(h1, h2, branch1Name, branch2Name, graph, callDepth=0, ancestor=None): - '''Merge the commits h1 and h2, return the resulting virtual - commit object and a flag indicating the cleanness of the merge.''' - assert(isinstance(h1, Commit) and isinstance(h2, Commit)) - - global outputIndent - - output('Merging:') - output(h1) - output(h2) - sys.stdout.flush() - - if ancestor: - ca = [ancestor] - else: - assert(isinstance(graph, Graph)) - ca = getCommonAncestors(graph, h1, h2) - output('found', len(ca), 'common ancestor(s):') - for x in ca: - output(x) - sys.stdout.flush() - - mergedCA = ca[0] - for h in ca[1:]: - outputIndent = callDepth+1 - [mergedCA, dummy] = merge(mergedCA, h, - 'Temporary merge branch 1', - 'Temporary merge branch 2', - graph, callDepth+1) - outputIndent = callDepth - assert(isinstance(mergedCA, Commit)) - - global cacheOnly - if callDepth == 0: - setupIndex(False) - cacheOnly = False - else: - setupIndex(True) - runProgram(['git-read-tree', h1.tree()]) - cacheOnly = True - - [shaRes, clean] = mergeTrees(h1.tree(), h2.tree(), mergedCA.tree(), - branch1Name, branch2Name) - - if graph and (clean or cacheOnly): - res = Commit(None, [h1, h2], tree=shaRes) - graph.addNode(res) - else: - res = None - - return [res, clean] - -getFilesRE = re.compile(r'^([0-7]+) (\S+) ([0-9a-f]{40})\t(.*)$', re.S) -def getFilesAndDirs(tree): - files = Set() - dirs = Set() - out = runProgram(['git-ls-tree', '-r', '-z', '-t', tree]) - for l in out.split('\0'): - m = getFilesRE.match(l) - if m: - if m.group(2) == 'tree': - dirs.add(m.group(4)) - elif m.group(2) == 'blob': - files.add(m.group(4)) - - return [files, dirs] - -# Those two global variables are used in a number of places but only -# written to in 'mergeTrees' and 'uniquePath'. They keep track of -# every file and directory in the two branches that are about to be -# merged. -currentFileSet = None -currentDirectorySet = None - -def mergeTrees(head, merge, common, branch1Name, branch2Name): - '''Merge the trees 'head' and 'merge' with the common ancestor - 'common'. The name of the head branch is 'branch1Name' and the name of - the merge branch is 'branch2Name'. Return a tuple (tree, cleanMerge) - where tree is the resulting tree and cleanMerge is True iff the - merge was clean.''' - - assert(isSha(head) and isSha(merge) and isSha(common)) - - if common == merge: - output('Already uptodate!') - return [head, True] - - if cacheOnly: - updateArg = '-i' - else: - updateArg = '-u' - - [out, code] = runProgram(['git-read-tree', updateArg, '-m', - common, head, merge], returnCode = True) - if code != 0: - die('git-read-tree:', out) - - [tree, code] = runProgram('git-write-tree', returnCode=True) - tree = tree.rstrip() - if code != 0: - global currentFileSet, currentDirectorySet - [currentFileSet, currentDirectorySet] = getFilesAndDirs(head) - [filesM, dirsM] = getFilesAndDirs(merge) - currentFileSet.union_update(filesM) - currentDirectorySet.union_update(dirsM) - - entries = unmergedCacheEntries() - renamesHead = getRenames(head, common, head, merge, entries) - renamesMerge = getRenames(merge, common, head, merge, entries) - - cleanMerge = processRenames(renamesHead, renamesMerge, - branch1Name, branch2Name) - for entry in entries: - if entry.processed: - continue - if not processEntry(entry, branch1Name, branch2Name): - cleanMerge = False - - if cleanMerge or cacheOnly: - tree = runProgram('git-write-tree').rstrip() - else: - tree = None - else: - cleanMerge = True - - return [tree, cleanMerge] - -# Low level file merging, update and removal -# ------------------------------------------ - -def mergeFile(oPath, oSha, oMode, aPath, aSha, aMode, bPath, bSha, bMode, - branch1Name, branch2Name): - - merge = False - clean = True - - if stat.S_IFMT(aMode) != stat.S_IFMT(bMode): - clean = False - if stat.S_ISREG(aMode): - mode = aMode - sha = aSha - else: - mode = bMode - sha = bSha - else: - if aSha != oSha and bSha != oSha: - merge = True - - if aMode == oMode: - mode = bMode - else: - mode = aMode - - if aSha == oSha: - sha = bSha - elif bSha == oSha: - sha = aSha - elif stat.S_ISREG(aMode): - assert(stat.S_ISREG(bMode)) - - orig = runProgram(['git-unpack-file', oSha]).rstrip() - src1 = runProgram(['git-unpack-file', aSha]).rstrip() - src2 = runProgram(['git-unpack-file', bSha]).rstrip() - try: - [out, code] = runProgram(['merge', - '-L', branch1Name + '/' + aPath, - '-L', 'orig/' + oPath, - '-L', branch2Name + '/' + bPath, - src1, orig, src2], returnCode=True) - except ProgramError, e: - print >>sys.stderr, e - die("Failed to execute 'merge'. merge(1) is used as the " - "file-level merge tool. Is 'merge' in your path?") - - sha = runProgram(['git-hash-object', '-t', 'blob', '-w', - src1]).rstrip() - - os.unlink(orig) - os.unlink(src1) - os.unlink(src2) - - clean = (code == 0) - else: - assert(stat.S_ISLNK(aMode) and stat.S_ISLNK(bMode)) - sha = aSha - - if aSha != bSha: - clean = False - - return [sha, mode, clean, merge] - -def updateFile(clean, sha, mode, path): - updateCache = cacheOnly or clean - updateWd = not cacheOnly - - return updateFileExt(sha, mode, path, updateCache, updateWd) - -def updateFileExt(sha, mode, path, updateCache, updateWd): - if cacheOnly: - updateWd = False - - if updateWd: - pathComponents = path.split('/') - for x in xrange(1, len(pathComponents)): - p = '/'.join(pathComponents[0:x]) - - try: - createDir = not stat.S_ISDIR(os.lstat(p).st_mode) - except OSError: - createDir = True - - if createDir: - try: - os.mkdir(p) - except OSError, e: - die("Couldn't create directory", p, e.strerror) - - prog = ['git-cat-file', 'blob', sha] - if stat.S_ISREG(mode): - try: - os.unlink(path) - except OSError: - pass - if mode & 0100: - mode = 0777 - else: - mode = 0666 - fd = os.open(path, os.O_WRONLY | os.O_TRUNC | os.O_CREAT, mode) - proc = subprocess.Popen(prog, stdout=fd) - proc.wait() - os.close(fd) - elif stat.S_ISLNK(mode): - linkTarget = runProgram(prog) - os.symlink(linkTarget, path) - else: - assert(False) - - if updateWd and updateCache: - runProgram(['git-update-index', '--add', '--', path]) - elif updateCache: - runProgram(['git-update-index', '--add', '--cacheinfo', - '0%o' % mode, sha, path]) - -def setIndexStages(path, - oSHA1, oMode, - aSHA1, aMode, - bSHA1, bMode, - clear=True): - istring = [] - if clear: - istring.append("0 " + ("0" * 40) + "\t" + path + "\0") - if oMode: - istring.append("%o %s %d\t%s\0" % (oMode, oSHA1, 1, path)) - if aMode: - istring.append("%o %s %d\t%s\0" % (aMode, aSHA1, 2, path)) - if bMode: - istring.append("%o %s %d\t%s\0" % (bMode, bSHA1, 3, path)) - - runProgram(['git-update-index', '-z', '--index-info'], - input="".join(istring)) - -def removeFile(clean, path): - updateCache = cacheOnly or clean - updateWd = not cacheOnly - - if updateCache: - runProgram(['git-update-index', '--force-remove', '--', path]) - - if updateWd: - try: - os.unlink(path) - except OSError, e: - if e.errno != errno.ENOENT and e.errno != errno.EISDIR: - raise - try: - os.removedirs(os.path.dirname(path)) - except OSError: - pass - -def uniquePath(path, branch): - def fileExists(path): - try: - os.lstat(path) - return True - except OSError, e: - if e.errno == errno.ENOENT: - return False - else: - raise - - branch = branch.replace('/', '_') - newPath = path + '~' + branch - suffix = 0 - while newPath in currentFileSet or \ - newPath in currentDirectorySet or \ - fileExists(newPath): - suffix += 1 - newPath = path + '~' + branch + '_' + str(suffix) - currentFileSet.add(newPath) - return newPath - -# Cache entry management -# ---------------------- - -class CacheEntry: - def __init__(self, path): - class Stage: - def __init__(self): - self.sha1 = None - self.mode = None - - # Used for debugging only - def __str__(self): - if self.mode != None: - m = '0%o' % self.mode - else: - m = 'None' - - if self.sha1: - sha1 = self.sha1 - else: - sha1 = 'None' - return 'sha1: ' + sha1 + ' mode: ' + m - - self.stages = [Stage(), Stage(), Stage(), Stage()] - self.path = path - self.processed = False - - def __str__(self): - return 'path: ' + self.path + ' stages: ' + repr([str(x) for x in self.stages]) - -class CacheEntryContainer: - def __init__(self): - self.entries = {} - - def add(self, entry): - self.entries[entry.path] = entry - - def get(self, path): - return self.entries.get(path) - - def __iter__(self): - return self.entries.itervalues() - -unmergedRE = re.compile(r'^([0-7]+) ([0-9a-f]{40}) ([1-3])\t(.*)$', re.S) -def unmergedCacheEntries(): - '''Create a dictionary mapping file names to CacheEntry - objects. The dictionary contains one entry for every path with a - non-zero stage entry.''' - - lines = runProgram(['git-ls-files', '-z', '--unmerged']).split('\0') - lines.pop() - - res = CacheEntryContainer() - for l in lines: - m = unmergedRE.match(l) - if m: - mode = int(m.group(1), 8) - sha1 = m.group(2) - stage = int(m.group(3)) - path = m.group(4) - - e = res.get(path) - if not e: - e = CacheEntry(path) - res.add(e) - - e.stages[stage].mode = mode - e.stages[stage].sha1 = sha1 - else: - die('Error: Merge program failed: Unexpected output from', - 'git-ls-files:', l) - return res - -lsTreeRE = re.compile(r'^([0-7]+) (\S+) ([0-9a-f]{40})\t(.*)\n$', re.S) -def getCacheEntry(path, origTree, aTree, bTree): - '''Returns a CacheEntry object which doesn't have to correspond to - a real cache entry in Git's index.''' - - def parse(out): - if out == '': - return [None, None] - else: - m = lsTreeRE.match(out) - if not m: - die('Unexpected output from git-ls-tree:', out) - elif m.group(2) == 'blob': - return [m.group(3), int(m.group(1), 8)] - else: - return [None, None] - - res = CacheEntry(path) - - [oSha, oMode] = parse(runProgram(['git-ls-tree', origTree, '--', path])) - [aSha, aMode] = parse(runProgram(['git-ls-tree', aTree, '--', path])) - [bSha, bMode] = parse(runProgram(['git-ls-tree', bTree, '--', path])) - - res.stages[1].sha1 = oSha - res.stages[1].mode = oMode - res.stages[2].sha1 = aSha - res.stages[2].mode = aMode - res.stages[3].sha1 = bSha - res.stages[3].mode = bMode - - return res - -# Rename detection and handling -# ----------------------------- - -class RenameEntry: - def __init__(self, - src, srcSha, srcMode, srcCacheEntry, - dst, dstSha, dstMode, dstCacheEntry, - score): - self.srcName = src - self.srcSha = srcSha - self.srcMode = srcMode - self.srcCacheEntry = srcCacheEntry - self.dstName = dst - self.dstSha = dstSha - self.dstMode = dstMode - self.dstCacheEntry = dstCacheEntry - self.score = score - - self.processed = False - -class RenameEntryContainer: - def __init__(self): - self.entriesSrc = {} - self.entriesDst = {} - - def add(self, entry): - self.entriesSrc[entry.srcName] = entry - self.entriesDst[entry.dstName] = entry - - def getSrc(self, path): - return self.entriesSrc.get(path) - - def getDst(self, path): - return self.entriesDst.get(path) - - def __iter__(self): - return self.entriesSrc.itervalues() - -parseDiffRenamesRE = re.compile('^:([0-7]+) ([0-7]+) ([0-9a-f]{40}) ([0-9a-f]{40}) R([0-9]*)$') -def getRenames(tree, oTree, aTree, bTree, cacheEntries): - '''Get information of all renames which occured between 'oTree' and - 'tree'. We need the three trees in the merge ('oTree', 'aTree' and - 'bTree') to be able to associate the correct cache entries with - the rename information. 'tree' is always equal to either aTree or bTree.''' - - assert(tree == aTree or tree == bTree) - inp = runProgram(['git-diff-tree', '-M', '--diff-filter=R', '-r', - '-z', oTree, tree]) - - ret = RenameEntryContainer() - try: - recs = inp.split("\0") - recs.pop() # remove last entry (which is '') - it = recs.__iter__() - while True: - rec = it.next() - m = parseDiffRenamesRE.match(rec) - - if not m: - die('Unexpected output from git-diff-tree:', rec) - - srcMode = int(m.group(1), 8) - dstMode = int(m.group(2), 8) - srcSha = m.group(3) - dstSha = m.group(4) - score = m.group(5) - src = it.next() - dst = it.next() - - srcCacheEntry = cacheEntries.get(src) - if not srcCacheEntry: - srcCacheEntry = getCacheEntry(src, oTree, aTree, bTree) - cacheEntries.add(srcCacheEntry) - - dstCacheEntry = cacheEntries.get(dst) - if not dstCacheEntry: - dstCacheEntry = getCacheEntry(dst, oTree, aTree, bTree) - cacheEntries.add(dstCacheEntry) - - ret.add(RenameEntry(src, srcSha, srcMode, srcCacheEntry, - dst, dstSha, dstMode, dstCacheEntry, - score)) - except StopIteration: - pass - return ret - -def fmtRename(src, dst): - srcPath = src.split('/') - dstPath = dst.split('/') - path = [] - endIndex = min(len(srcPath), len(dstPath)) - 1 - for x in range(0, endIndex): - if srcPath[x] == dstPath[x]: - path.append(srcPath[x]) - else: - endIndex = x - break - - if len(path) > 0: - return '/'.join(path) + \ - '/{' + '/'.join(srcPath[endIndex:]) + ' => ' + \ - '/'.join(dstPath[endIndex:]) + '}' - else: - return src + ' => ' + dst - -def processRenames(renamesA, renamesB, branchNameA, branchNameB): - srcNames = Set() - for x in renamesA: - srcNames.add(x.srcName) - for x in renamesB: - srcNames.add(x.srcName) - - cleanMerge = True - for path in srcNames: - if renamesA.getSrc(path): - renames1 = renamesA - renames2 = renamesB - branchName1 = branchNameA - branchName2 = branchNameB - else: - renames1 = renamesB - renames2 = renamesA - branchName1 = branchNameB - branchName2 = branchNameA - - ren1 = renames1.getSrc(path) - ren2 = renames2.getSrc(path) - - ren1.dstCacheEntry.processed = True - ren1.srcCacheEntry.processed = True - - if ren1.processed: - continue - - ren1.processed = True - - if ren2: - # Renamed in 1 and renamed in 2 - assert(ren1.srcName == ren2.srcName) - ren2.dstCacheEntry.processed = True - ren2.processed = True - - if ren1.dstName != ren2.dstName: - output('CONFLICT (rename/rename): Rename', - fmtRename(path, ren1.dstName), 'in branch', branchName1, - 'rename', fmtRename(path, ren2.dstName), 'in', - branchName2) - cleanMerge = False - - if ren1.dstName in currentDirectorySet: - dstName1 = uniquePath(ren1.dstName, branchName1) - output(ren1.dstName, 'is a directory in', branchName2, - 'adding as', dstName1, 'instead.') - removeFile(False, ren1.dstName) - else: - dstName1 = ren1.dstName - - if ren2.dstName in currentDirectorySet: - dstName2 = uniquePath(ren2.dstName, branchName2) - output(ren2.dstName, 'is a directory in', branchName1, - 'adding as', dstName2, 'instead.') - removeFile(False, ren2.dstName) - else: - dstName2 = ren2.dstName - setIndexStages(dstName1, - None, None, - ren1.dstSha, ren1.dstMode, - None, None) - setIndexStages(dstName2, - None, None, - None, None, - ren2.dstSha, ren2.dstMode) - - else: - removeFile(True, ren1.srcName) - - [resSha, resMode, clean, merge] = \ - mergeFile(ren1.srcName, ren1.srcSha, ren1.srcMode, - ren1.dstName, ren1.dstSha, ren1.dstMode, - ren2.dstName, ren2.dstSha, ren2.dstMode, - branchName1, branchName2) - - if merge or not clean: - output('Renaming', fmtRename(path, ren1.dstName)) - - if merge: - output('Auto-merging', ren1.dstName) - - if not clean: - output('CONFLICT (content): merge conflict in', - ren1.dstName) - cleanMerge = False - - if not cacheOnly: - setIndexStages(ren1.dstName, - ren1.srcSha, ren1.srcMode, - ren1.dstSha, ren1.dstMode, - ren2.dstSha, ren2.dstMode) - - updateFile(clean, resSha, resMode, ren1.dstName) - else: - removeFile(True, ren1.srcName) - - # Renamed in 1, maybe changed in 2 - if renamesA == renames1: - stage = 3 - else: - stage = 2 - - srcShaOtherBranch = ren1.srcCacheEntry.stages[stage].sha1 - srcModeOtherBranch = ren1.srcCacheEntry.stages[stage].mode - - dstShaOtherBranch = ren1.dstCacheEntry.stages[stage].sha1 - dstModeOtherBranch = ren1.dstCacheEntry.stages[stage].mode - - tryMerge = False - - if ren1.dstName in currentDirectorySet: - newPath = uniquePath(ren1.dstName, branchName1) - output('CONFLICT (rename/directory): Rename', - fmtRename(ren1.srcName, ren1.dstName), 'in', branchName1, - 'directory', ren1.dstName, 'added in', branchName2) - output('Renaming', ren1.srcName, 'to', newPath, 'instead') - cleanMerge = False - removeFile(False, ren1.dstName) - updateFile(False, ren1.dstSha, ren1.dstMode, newPath) - elif srcShaOtherBranch == None: - output('CONFLICT (rename/delete): Rename', - fmtRename(ren1.srcName, ren1.dstName), 'in', - branchName1, 'and deleted in', branchName2) - cleanMerge = False - updateFile(False, ren1.dstSha, ren1.dstMode, ren1.dstName) - elif dstShaOtherBranch: - newPath = uniquePath(ren1.dstName, branchName2) - output('CONFLICT (rename/add): Rename', - fmtRename(ren1.srcName, ren1.dstName), 'in', - branchName1 + '.', ren1.dstName, 'added in', branchName2) - output('Adding as', newPath, 'instead') - updateFile(False, dstShaOtherBranch, dstModeOtherBranch, newPath) - cleanMerge = False - tryMerge = True - elif renames2.getDst(ren1.dstName): - dst2 = renames2.getDst(ren1.dstName) - newPath1 = uniquePath(ren1.dstName, branchName1) - newPath2 = uniquePath(dst2.dstName, branchName2) - output('CONFLICT (rename/rename): Rename', - fmtRename(ren1.srcName, ren1.dstName), 'in', - branchName1+'. Rename', - fmtRename(dst2.srcName, dst2.dstName), 'in', branchName2) - output('Renaming', ren1.srcName, 'to', newPath1, 'and', - dst2.srcName, 'to', newPath2, 'instead') - removeFile(False, ren1.dstName) - updateFile(False, ren1.dstSha, ren1.dstMode, newPath1) - updateFile(False, dst2.dstSha, dst2.dstMode, newPath2) - dst2.processed = True - cleanMerge = False - else: - tryMerge = True - - if tryMerge: - - oName, oSHA1, oMode = ren1.srcName, ren1.srcSha, ren1.srcMode - aName, bName = ren1.dstName, ren1.srcName - aSHA1, bSHA1 = ren1.dstSha, srcShaOtherBranch - aMode, bMode = ren1.dstMode, srcModeOtherBranch - aBranch, bBranch = branchName1, branchName2 - - if renamesA != renames1: - aName, bName = bName, aName - aSHA1, bSHA1 = bSHA1, aSHA1 - aMode, bMode = bMode, aMode - aBranch, bBranch = bBranch, aBranch - - [resSha, resMode, clean, merge] = \ - mergeFile(oName, oSHA1, oMode, - aName, aSHA1, aMode, - bName, bSHA1, bMode, - aBranch, bBranch); - - if merge or not clean: - output('Renaming', fmtRename(ren1.srcName, ren1.dstName)) - - if merge: - output('Auto-merging', ren1.dstName) - - if not clean: - output('CONFLICT (rename/modify): Merge conflict in', - ren1.dstName) - cleanMerge = False - - if not cacheOnly: - setIndexStages(ren1.dstName, - oSHA1, oMode, - aSHA1, aMode, - bSHA1, bMode) - - updateFile(clean, resSha, resMode, ren1.dstName) - - return cleanMerge - -# Per entry merge function -# ------------------------ - -def processEntry(entry, branch1Name, branch2Name): - '''Merge one cache entry.''' - - debug('processing', entry.path, 'clean cache:', cacheOnly) - - cleanMerge = True - - path = entry.path - oSha = entry.stages[1].sha1 - oMode = entry.stages[1].mode - aSha = entry.stages[2].sha1 - aMode = entry.stages[2].mode - bSha = entry.stages[3].sha1 - bMode = entry.stages[3].mode - - assert(oSha == None or isSha(oSha)) - assert(aSha == None or isSha(aSha)) - assert(bSha == None or isSha(bSha)) - - assert(oMode == None or type(oMode) is int) - assert(aMode == None or type(aMode) is int) - assert(bMode == None or type(bMode) is int) - - if (oSha and (not aSha or not bSha)): - # - # Case A: Deleted in one - # - if (not aSha and not bSha) or \ - (aSha == oSha and not bSha) or \ - (not aSha and bSha == oSha): - # Deleted in both or deleted in one and unchanged in the other - if aSha: - output('Removing', path) - removeFile(True, path) - else: - # Deleted in one and changed in the other - cleanMerge = False - if not aSha: - output('CONFLICT (delete/modify):', path, 'deleted in', - branch1Name, 'and modified in', branch2Name + '.', - 'Version', branch2Name, 'of', path, 'left in tree.') - mode = bMode - sha = bSha - else: - output('CONFLICT (modify/delete):', path, 'deleted in', - branch2Name, 'and modified in', branch1Name + '.', - 'Version', branch1Name, 'of', path, 'left in tree.') - mode = aMode - sha = aSha - - updateFile(False, sha, mode, path) - - elif (not oSha and aSha and not bSha) or \ - (not oSha and not aSha and bSha): - # - # Case B: Added in one. - # - if aSha: - addBranch = branch1Name - otherBranch = branch2Name - mode = aMode - sha = aSha - conf = 'file/directory' - else: - addBranch = branch2Name - otherBranch = branch1Name - mode = bMode - sha = bSha - conf = 'directory/file' - - if path in currentDirectorySet: - cleanMerge = False - newPath = uniquePath(path, addBranch) - output('CONFLICT (' + conf + '):', - 'There is a directory with name', path, 'in', - otherBranch + '. Adding', path, 'as', newPath) - - removeFile(False, path) - updateFile(False, sha, mode, newPath) - else: - output('Adding', path) - updateFile(True, sha, mode, path) - - elif not oSha and aSha and bSha: - # - # Case C: Added in both (check for same permissions). - # - if aSha == bSha: - if aMode != bMode: - cleanMerge = False - output('CONFLICT: File', path, - 'added identically in both branches, but permissions', - 'conflict', '0%o' % aMode, '->', '0%o' % bMode) - output('CONFLICT: adding with permission:', '0%o' % aMode) - - updateFile(False, aSha, aMode, path) - else: - # This case is handled by git-read-tree - assert(False) - else: - cleanMerge = False - newPath1 = uniquePath(path, branch1Name) - newPath2 = uniquePath(path, branch2Name) - output('CONFLICT (add/add): File', path, - 'added non-identically in both branches. Adding as', - newPath1, 'and', newPath2, 'instead.') - removeFile(False, path) - updateFile(False, aSha, aMode, newPath1) - updateFile(False, bSha, bMode, newPath2) - - elif oSha and aSha and bSha: - # - # case D: Modified in both, but differently. - # - output('Auto-merging', path) - [sha, mode, clean, dummy] = \ - mergeFile(path, oSha, oMode, - path, aSha, aMode, - path, bSha, bMode, - branch1Name, branch2Name) - if clean: - updateFile(True, sha, mode, path) - else: - cleanMerge = False - output('CONFLICT (content): Merge conflict in', path) - - if cacheOnly: - updateFile(False, sha, mode, path) - else: - updateFileExt(sha, mode, path, updateCache=False, updateWd=True) - else: - die("ERROR: Fatal merge failure, shouldn't happen.") - - return cleanMerge - -def usage(): - die('Usage:', sys.argv[0], ' <base>... -- <head> <remote>..') - -# main entry point as merge strategy module -# The first parameters up to -- are merge bases, and the rest are heads. - -if len(sys.argv) < 4: - usage() - -bases = [] -for nextArg in xrange(1, len(sys.argv)): - if sys.argv[nextArg] == '--': - if len(sys.argv) != nextArg + 3: - die('Not handling anything other than two heads merge.') - try: - h1 = firstBranch = sys.argv[nextArg + 1] - h2 = secondBranch = sys.argv[nextArg + 2] - except IndexError: - usage() - break - else: - bases.append(sys.argv[nextArg]) - -print 'Merging', h1, 'with', h2 - -try: - h1 = runProgram(['git-rev-parse', '--verify', h1 + '^0']).rstrip() - h2 = runProgram(['git-rev-parse', '--verify', h2 + '^0']).rstrip() - - if len(bases) == 1: - base = runProgram(['git-rev-parse', '--verify', - bases[0] + '^0']).rstrip() - ancestor = Commit(base, None) - [dummy, clean] = merge(Commit(h1, None), Commit(h2, None), - firstBranch, secondBranch, None, 0, - ancestor) - else: - graph = buildGraph([h1, h2]) - [dummy, clean] = merge(graph.shaMap[h1], graph.shaMap[h2], - firstBranch, secondBranch, graph) - - print '' -except: - if isinstance(sys.exc_info()[1], SystemExit): - raise - else: - traceback.print_exc(None, sys.stderr) - sys.exit(2) - -if clean: - sys.exit(0) -else: - sys.exit(1) diff --git a/git-merge.sh b/git-merge.sh index a9cfafb1df..3eef048efc 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -3,23 +3,25 @@ # Copyright (c) 2005 Junio C Hamano # -USAGE='[-n] [--no-commit] [--squash] [-s <strategy>]... <merge-message> <head> <remote>+' +USAGE='[-n] [--no-commit] [--squash] [-s <strategy>] [-m=<merge-message>] <commit>+' + . git-sh-setup +set_reflog_action "merge $*" +require_work_tree + +test -z "$(git ls-files -u)" || + die "You are in a middle of conflicted merge." LF=' ' -all_strategies='recursive octopus resolve stupid ours' +all_strategies='recur recursive octopus resolve stupid ours' default_twohead_strategies='recursive' default_octopus_strategies='octopus' no_trivial_merge_strategies='ours' use_strategies= index_merge=t -if test "@@NO_PYTHON@@"; then - all_strategies='resolve octopus stupid ours' - default_twohead_strategies='resolve' -fi dropsave() { rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" \ @@ -35,7 +37,7 @@ savestate() { restorestate() { if test -f "$GIT_DIR/MERGE_SAVE" then - git reset --hard $head + git reset --hard $head >/dev/null cpio -iuv <"$GIT_DIR/MERGE_SAVE" git-update-index --refresh >/dev/null fi @@ -60,10 +62,10 @@ squash_message () { finish () { if test '' = "$2" then - rlogm="$rloga" + rlogm="$GIT_REFLOG_ACTION" else echo "$2" - rlogm="$rloga: $2" + rlogm="$GIT_REFLOG_ACTION: $2" fi case "$squash" in t) @@ -94,7 +96,25 @@ finish () { esac } -rloga= +merge_name () { + remote="$1" + rh=$(git-rev-parse --verify "$remote^0" 2>/dev/null) || return + bh=$(git-show-ref -s --verify "refs/heads/$remote" 2>/dev/null) + if test "$rh" = "$bh" + then + echo "$rh branch '$remote' of ." + elif truname=$(expr "$remote" : '\(.*\)~[1-9][0-9]*$') && + git-show-ref -q --verify "refs/heads/$truname" 2>/dev/null + then + echo "$rh branch '$truname' (early part) of ." + else + echo "$rh commit '$remote'" + fi +} + +case "$#" in 0) usage ;; esac + +have_message= while case "$#" in 0) break ;; esac do case "$1" in @@ -124,8 +144,17 @@ do die "available strategies are: $all_strategies" ;; esac ;; - --reflog-action=*) - rloga=`expr "z$1" : 'z-[^=]*=\(.*\)'` + -m=*|--m=*|--me=*|--mes=*|--mess=*|--messa=*|--messag=*|--message=*) + merge_msg=`expr "z$1" : 'z-[^=]*=\(.*\)'` + have_message=t + ;; + -m|--m|--me|--mes|--mess|--messa|--messag|--message) + shift + case "$#" in + 1) usage ;; + esac + merge_msg="$1" + have_message=t ;; -*) usage ;; *) break ;; @@ -133,22 +162,68 @@ do shift done -merge_msg="$1" -shift -head_arg="$1" -head=$(git-rev-parse --verify "$1"^0) || usage -shift +# This could be traditional "merge <msg> HEAD <commit>..." and the +# way we can tell it is to see if the second token is HEAD, but some +# people might have misused the interface and used a committish that +# is the same as HEAD there instead. Traditional format never would +# have "-m" so it is an additional safety measure to check for it. + +if test -z "$have_message" && + second_token=$(git-rev-parse --verify "$2^0" 2>/dev/null) && + head_commit=$(git-rev-parse --verify "HEAD" 2>/dev/null) && + test "$second_token" = "$head_commit" +then + merge_msg="$1" + shift + head_arg="$1" + shift +elif ! git-rev-parse --verify HEAD >/dev/null 2>&1 +then + # If the merged head is a valid one there is no reason to + # forbid "git merge" into a branch yet to be born. We do + # the same for "git pull". + if test 1 -ne $# + then + echo >&2 "Can merge only exactly one commit into empty head" + exit 1 + fi + + rh=$(git rev-parse --verify "$1^0") || + die "$1 - not something we can merge" + + git-update-ref -m "initial pull" HEAD "$rh" "" && + git-read-tree --reset -u HEAD + exit + +else + # We are invoked directly as the first-class UI. + head_arg=HEAD + + # All the rest are the commits being merged; prepare + # the standard merge summary message to be appended to + # the given message. If remote is invalid we will die + # later in the common codepath so we discard the error + # in this loop. + merge_name=$(for remote + do + merge_name "$remote" + done | git-fmt-merge-msg + ) + merge_msg="${merge_msg:+$merge_msg$LF$LF}$merge_name" +fi +head=$(git-rev-parse --verify "$head_arg"^0) || usage # All the rest are remote heads test "$#" = 0 && usage ;# we need at least one remote head. -test "$rloga" = '' && rloga="merge: $@" remoteheads= for remote do - remotehead=$(git-rev-parse --verify "$remote"^0) || + remotehead=$(git-rev-parse --verify "$remote"^0 2>/dev/null) || die "$remote - not something we can merge" remoteheads="${remoteheads}$remotehead " + eval GITHEAD_$remotehead='"$remote"' + export GITHEAD_$remotehead done set x $remoteheads ; shift @@ -156,9 +231,21 @@ case "$use_strategies" in '') case "$#" in 1) - use_strategies="$default_twohead_strategies" ;; + var="`git-repo-config --get pull.twohead`" + if test -n "$var" + then + use_strategies="$var" + else + use_strategies="$default_twohead_strategies" + fi ;; *) - use_strategies="$default_octopus_strategies" ;; + var="`git-repo-config --get pull.octopus`" + if test -n "$var" + then + use_strategies="$var" + else + use_strategies="$default_octopus_strategies" + fi ;; esac ;; esac @@ -198,10 +285,10 @@ f,*) ;; ?,1,"$head",*) # Again the most common case of merging one remote. - echo "Updating from $head to $1" + echo "Updating $(git-rev-parse --short $head)..$(git-rev-parse --short $1)" git-update-index --refresh 2>/dev/null new_head=$(git-rev-parse --verify "$1^0") && - git-read-tree -u -v -m $head "$new_head" && + git-read-tree -v -m -u --exclude-per-directory=.gitignore $head "$new_head" && finish "$new_head" "Fast forward" dropsave exit 0 @@ -336,7 +423,14 @@ fi case "$best_strategy" in '') restorestate - echo >&2 "No merge strategy handled the merge." + case "$use_strategies" in + ?*' '?*) + echo >&2 "No merge strategy handled the merge." + ;; + *) + echo >&2 "Merge with strategy $use_strategies failed." + ;; + esac exit 2 ;; "$wt_strategy") diff --git a/git-p4import.py b/git-p4import.py index 908941dd77..5c56cace0e 100644 --- a/git-p4import.py +++ b/git-p4import.py @@ -163,7 +163,7 @@ class git_command: self.gitdir = self.get_single("rev-parse --git-dir") report(2, "gdir:", self.gitdir) except: - die("Not a git repository... did you forget to \"git init-db\" ?") + die("Not a git repository... did you forget to \"git init\" ?") try: self.cdup = self.get_single("rev-parse --show-cdup") if self.cdup != "": diff --git a/git-parse-remote.sh b/git-parse-remote.sh index 187f0883c9..d2e4c2b9ae 100755 --- a/git-parse-remote.sh +++ b/git-parse-remote.sh @@ -7,18 +7,7 @@ GIT_DIR=$(git-rev-parse --git-dir 2>/dev/null) || :; get_data_source () { case "$1" in */*) - # Not so fast. This could be the partial URL shorthand... - token=$(expr "z$1" : 'z\([^/]*\)/') - remainder=$(expr "z$1" : 'z[^/]*/\(.*\)') - if test "$(git-repo-config --get "remote.$token.url")" - then - echo config-partial - elif test -f "$GIT_DIR/branches/$token" - then - echo branches-partial - else - echo '' - fi + echo '' ;; *) if test "$(git-repo-config --get "remote.$1.url")" @@ -40,12 +29,7 @@ get_remote_url () { data_source=$(get_data_source "$1") case "$data_source" in '') - echo "$1" ;; - config-partial) - token=$(expr "z$1" : 'z\([^/]*\)/') - remainder=$(expr "z$1" : 'z[^/]*/\(.*\)') - url=$(git-repo-config --get "remote.$token.url") - echo "$url/$remainder" + echo "$1" ;; config) git-repo-config --get "remote.$1.url" @@ -54,24 +38,26 @@ get_remote_url () { sed -ne '/^URL: */{ s///p q - }' "$GIT_DIR/remotes/$1" ;; + }' "$GIT_DIR/remotes/$1" + ;; branches) - sed -e 's/#.*//' "$GIT_DIR/branches/$1" ;; - branches-partial) - token=$(expr "z$1" : 'z\([^/]*\)/') - remainder=$(expr "z$1" : 'z[^/]*/\(.*\)') - url=$(sed -e 's/#.*//' "$GIT_DIR/branches/$token") - echo "$url/$remainder" + sed -e 's/#.*//' "$GIT_DIR/branches/$1" ;; *) die "internal error: get-remote-url $1" ;; esac } +get_default_remote () { + curr_branch=$(git-symbolic-ref HEAD | sed -e 's|^refs/heads/||') + origin=$(git-repo-config --get "branch.$curr_branch.remote") + echo ${origin:-origin} +} + get_remote_default_refs_for_push () { data_source=$(get_data_source "$1") case "$data_source" in - '' | config-partial | branches | branches-partial) + '' | branches) ;; # no default push mapping, just send matching refs. config) git-repo-config --get-all "remote.$1.push" ;; @@ -84,11 +70,83 @@ get_remote_default_refs_for_push () { esac } +# Called from canon_refs_list_for_fetch -d "$remote", which +# is called from get_remote_default_refs_for_fetch to grok +# refspecs that are retrieved from the configuration, but not +# from get_remote_refs_for_fetch when it deals with refspecs +# supplied on the command line. $ls_remote_result has the list +# of refs available at remote. +# +# The first token returned is either "explicit" or "glob"; this +# is to help prevent randomly "globbed" ref from being chosen as +# a merge candidate +expand_refs_wildcard () { + first_one=yes + for ref + do + lref=${ref#'+'} + # a non glob pattern is given back as-is. + expr "z$lref" : 'zrefs/.*/\*:refs/.*/\*$' >/dev/null || { + if test -n "$first_one" + then + echo "explicit" + first_one= + fi + echo "$ref" + continue + } + + # glob + if test -n "$first_one" + then + echo "glob" + first_one= + fi + from=`expr "z$lref" : 'z\(refs/.*/\)\*:refs/.*/\*$'` + to=`expr "z$lref" : 'zrefs/.*/\*:\(refs/.*/\)\*$'` + local_force= + test "z$lref" = "z$ref" || local_force='+' + echo "$ls_remote_result" | + sed -e '/\^{}$/d' | + ( + IFS=' ' + while read sha1 name + do + # ignore the ones that do not start with $from + mapped=${name#"$from"} + test "z$name" = "z$mapped" && continue + echo "${local_force}${name}:${to}${mapped}" + done + ) + done +} + # Subroutine to canonicalize remote:local notation. canon_refs_list_for_fetch () { - # Leave only the first one alone; add prefix . to the rest + # If called from get_remote_default_refs_for_fetch + # leave the branches in branch.${curr_branch}.merge alone, + # or the first one otherwise; add prefix . to the rest # to prevent the secondary branches to be merged by default. - dot_prefix= + merge_branches= + curr_branch= + if test "$1" = "-d" + then + shift ; remote="$1" ; shift + set $(expand_refs_wildcard "$@") + is_explicit="$1" + shift + if test "$remote" = "$(get_default_remote)" + then + curr_branch=$(git-symbolic-ref HEAD | \ + sed -e 's|^refs/heads/||') + merge_branches=$(git-repo-config \ + --get-all "branch.${curr_branch}.merge") + fi + if test -z "$merge_branches" && test $is_explicit != explicit + then + merge_branches=..this.will.never.match.any.ref.. + fi + fi for ref do force= @@ -101,6 +159,22 @@ canon_refs_list_for_fetch () { expr "z$ref" : 'z.*:' >/dev/null || ref="${ref}:" remote=$(expr "z$ref" : 'z\([^:]*\):') local=$(expr "z$ref" : 'z[^:]*:\(.*\)') + dot_prefix=. + if test -z "$merge_branches" + then + merge_branches=$remote + dot_prefix= + else + for merge_branch in $merge_branches + do + if test "$remote" = "$merge_branch" || + test "$local" = "$merge_branch" + then + dot_prefix= + break + fi + done + fi case "$remote" in '') remote=HEAD ;; refs/heads/* | refs/tags/* | refs/remotes/*) ;; @@ -120,7 +194,6 @@ canon_refs_list_for_fetch () { die "* refusing to create funny ref '$local_ref_name' locally" fi echo "${dot_prefix}${force}${remote}:${local}" - dot_prefix=. done } @@ -128,10 +201,10 @@ canon_refs_list_for_fetch () { get_remote_default_refs_for_fetch () { data_source=$(get_data_source "$1") case "$data_source" in - '' | config-partial | branches-partial) + '') echo "HEAD:" ;; config) - canon_refs_list_for_fetch \ + canon_refs_list_for_fetch -d "$1" \ $(git-repo-config --get-all "remote.$1.fetch") ;; branches) remote_branch=$(sed -ne '/#/s/.*#//p' "$GIT_DIR/branches/$1") @@ -139,10 +212,7 @@ get_remote_default_refs_for_fetch () { echo "refs/heads/${remote_branch}:refs/heads/$1" ;; remotes) - # This prefixes the second and later default refspecs - # with a '.', to signal git-fetch to mark them - # not-for-merge. - canon_refs_list_for_fetch $(sed -ne '/^Pull: */{ + canon_refs_list_for_fetch -d "$1" $(sed -ne '/^Pull: */{ s///p }' "$GIT_DIR/remotes/$1") ;; diff --git a/git-pull.sh b/git-pull.sh index f380437997..e9826fc4ce 100755 --- a/git-pull.sh +++ b/git-pull.sh @@ -7,6 +7,11 @@ USAGE='[-n | --no-summary] [--no-commit] [-s strategy]... [<fetch-options>] <repo> <head>...' LONG_USAGE='Fetch one or more remote refs and merge it/them into the current HEAD.' . git-sh-setup +set_reflog_action "pull $*" +require_work_tree + +test -z "$(git ls-files -u)" || + die "You are in a middle of conflicted merge." strategy_args= no_summary= no_commit= squash= while case "$#,$1" in 0) break ;; *,-*) ;; *) break ;; esac @@ -44,10 +49,10 @@ do shift done -orig_head=$(git-rev-parse --verify HEAD) || die "Pulling into a black hole?" -git-fetch --update-head-ok --reflog-action=pull "$@" || exit 1 +orig_head=$(git-rev-parse --verify HEAD 2>/dev/null) +git-fetch --update-head-ok "$@" || exit 1 -curr_head=$(git-rev-parse --verify HEAD) +curr_head=$(git-rev-parse --verify HEAD 2>/dev/null) if test "$curr_head" != "$orig_head" then # The fetch involved updating the current branch. @@ -58,7 +63,7 @@ then echo >&2 "Warning: fetch updated the current branch head." echo >&2 "Warning: fast forwarding your working tree from" - echo >&2 "Warning: $orig_head commit." + echo >&2 "Warning: commit $orig_head." git-update-index --refresh 2>/dev/null git-read-tree -u -m "$orig_head" "$curr_head" || die 'Cannot fast-forward your working tree. @@ -76,32 +81,29 @@ merge_head=$(sed -e '/ not-for-merge /d' \ case "$merge_head" in '') + curr_branch=$(git-symbolic-ref HEAD | \ + sed -e 's|^refs/heads/||') + echo >&2 "Warning: No merge candidate found because value of config option + \"branch.${curr_branch}.merge\" does not match any remote branch fetched." echo >&2 "No changes." exit 0 ;; ?*' '?*) - var=`git-repo-config --get pull.octopus` - if test -n "$var" + if test -z "$orig_head" then - strategy_default_args="-s $var" - fi - ;; -*) - var=`git-repo-config --get pull.twohead` - if test -n "$var" - then - strategy_default_args="-s $var" + echo >&2 "Cannot merge multiple branches into empty head" + exit 1 fi ;; esac -case "$strategy_args" in -'') - strategy_args=$strategy_default_args - ;; -esac +if test -z "$orig_head" +then + git-update-ref -m "initial pull" HEAD $merge_head "" && + git-read-tree --reset -u HEAD || exit 1 + exit +fi merge_name=$(git-fmt-merge-msg <"$GIT_DIR/FETCH_HEAD") || exit -git-merge "--reflog-action=pull $*" \ - $no_summary $no_commit $squash $strategy_args \ +exec git-merge $no_summary $no_commit $squash $strategy_args \ "$merge_name" HEAD $merge_head diff --git a/git-rebase.sh b/git-rebase.sh index 7d3a5d0e71..98f9558145 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -3,7 +3,7 @@ # Copyright (c) 2005 Junio C Hamano. # -USAGE='[--onto <newbase>] <upstream> [<branch>]' +USAGE='[-v] [--onto <newbase>] <upstream> [<branch>]' LONG_USAGE='git-rebase replaces <branch> with a new branch of the same name. When the --onto option is provided the new branch starts out with a HEAD equal to <newbase>, otherwise it is equal to <upstream> @@ -28,6 +28,8 @@ Example: git-rebase master~1 topic D---E---F---G master D---E---F---G master ' . git-sh-setup +set_reflog_action rebase +require_work_tree RESOLVEMSG=" When you have resolved this problem run \"git rebase --continue\". @@ -39,6 +41,7 @@ strategy=recursive do_merge= dotest=$GIT_DIR/.dotest-merge prec=4 +verbose= continue_merge () { test -n "$prev_head" || die "prev_head must be defined" @@ -79,10 +82,18 @@ continue_merge () { call_merge () { cmt="$(cat $dotest/cmt.$1)" echo "$cmt" > "$dotest/current" - git-merge-$strategy "$cmt^" -- HEAD "$cmt" + hd=$(git-rev-parse --verify HEAD) + cmt_name=$(git-symbolic-ref HEAD) + msgnum=$(cat $dotest/msgnum) + end=$(cat $dotest/end) + eval GITHEAD_$cmt='"${cmt_name##refs/heads/}~$(($end - $msgnum))"' + eval GITHEAD_$hd='"$(cat $dotest/onto_name)"' + export GITHEAD_$cmt GITHEAD_$hd + git-merge-$strategy "$cmt^" -- "$hd" "$cmt" rv=$? case "$rv" in 0) + unset GITHEAD_$cmt GITHEAD_$hd return ;; 1) @@ -131,13 +142,16 @@ do finish_rb_merge exit fi - git am --resolved --3way --resolvemsg="$RESOLVEMSG" \ - --reflog-action=rebase + git am --resolved --3way --resolvemsg="$RESOLVEMSG" exit ;; --skip) if test -d "$dotest" then + if test -d "$GIT_DIR/rr-cache" + then + git-rerere clear + fi prev_head="`cat $dotest/prev_head`" end="`cat $dotest/end`" msgnum="`cat $dotest/msgnum`" @@ -151,11 +165,14 @@ do finish_rb_merge exit fi - git am -3 --skip --resolvemsg="$RESOLVEMSG" \ - --reflog-action=rebase + git am -3 --skip --resolvemsg="$RESOLVEMSG" exit ;; --abort) + if test -d "$GIT_DIR/rr-cache" + then + git-rerere clear + fi if test -d "$dotest" then rm -r "$dotest" @@ -190,6 +207,9 @@ do esac do_merge=t ;; + -v|--verbose) + verbose=t + ;; -*) usage ;; @@ -273,7 +293,14 @@ then exit 0 fi +if test -n "$verbose" +then + echo "Changes from $mb to $onto:" + git-diff-tree --stat --summary "$mb" "$onto" +fi + # Rewind the head to "$onto"; this saves our current head in ORIG_HEAD. +echo "First, rewinding head to replay your work on top of it..." git-reset --hard "$onto" # If the $onto is a proper descendant of the tip of the branch, then @@ -286,26 +313,17 @@ fi if test -z "$do_merge" then - git-format-patch -k --stdout --full-index "$upstream"..ORIG_HEAD | - git am --binary -3 -k --resolvemsg="$RESOLVEMSG" \ - --reflog-action=rebase + git-format-patch -k --stdout --full-index --ignore-if-in-upstream "$upstream"..ORIG_HEAD | + git am --binary -3 -k --resolvemsg="$RESOLVEMSG" exit $? fi -if test "@@NO_PYTHON@@" && test "$strategy" = "recursive" -then - die 'The recursive merge strategy currently relies on Python, -which this installation of git was not configured with. Please consider -a different merge strategy (e.g. octopus, resolve, stupid, ours) -or install Python and git with Python support.' - -fi - # start doing a rebase with git-merge # this is rename-aware if the recursive (default) strategy is used mkdir -p "$dotest" echo "$onto" > "$dotest/onto" +echo "$onto_name" > "$dotest/onto_name" prev_head=`git-rev-parse HEAD^0` echo "$prev_head" > "$dotest/prev_head" diff --git a/git-remote.perl b/git-remote.perl new file mode 100755 index 0000000000..fc055b6d95 --- /dev/null +++ b/git-remote.perl @@ -0,0 +1,282 @@ +#!/usr/bin/perl -w + +use Git; +my $git = Git->repository(); + +sub add_remote_config { + my ($hash, $name, $what, $value) = @_; + if ($what eq 'url') { + if (exists $hash->{$name}{'URL'}) { + print STDERR "Warning: more than one remote.$name.url\n"; + } + $hash->{$name}{'URL'} = $value; + } + elsif ($what eq 'fetch') { + $hash->{$name}{'FETCH'} ||= []; + push @{$hash->{$name}{'FETCH'}}, $value; + } + if (!exists $hash->{$name}{'SOURCE'}) { + $hash->{$name}{'SOURCE'} = 'config'; + } +} + +sub add_remote_remotes { + my ($hash, $file, $name) = @_; + + if (exists $hash->{$name}) { + $hash->{$name}{'WARNING'} = 'ignored due to config'; + return; + } + + my $fh; + if (!open($fh, '<', $file)) { + print STDERR "Warning: cannot open $file\n"; + return; + } + my $it = { 'SOURCE' => 'remotes' }; + $hash->{$name} = $it; + while (<$fh>) { + chomp; + if (/^URL:\s*(.*)$/) { + # Having more than one is Ok -- it is used for push. + if (! exists $it->{'URL'}) { + $it->{'URL'} = $1; + } + } + elsif (/^Push:\s*(.*)$/) { + ; # later + } + elsif (/^Pull:\s*(.*)$/) { + $it->{'FETCH'} ||= []; + push @{$it->{'FETCH'}}, $1; + } + elsif (/^\#/) { + ; # ignore + } + else { + print STDERR "Warning: funny line in $file: $_\n"; + } + } + close($fh); +} + +sub list_remote { + my ($git) = @_; + my %seen = (); + my @remotes = eval { + $git->command(qw(repo-config --get-regexp), '^remote\.'); + }; + for (@remotes) { + if (/^remote\.([^.]*)\.(\S*)\s+(.*)$/) { + add_remote_config(\%seen, $1, $2, $3); + } + } + + my $dir = $git->repo_path() . "/remotes"; + if (opendir(my $dh, $dir)) { + local $_; + while ($_ = readdir($dh)) { + chomp; + next if (! -f "$dir/$_" || ! -r _); + add_remote_remotes(\%seen, "$dir/$_", $_); + } + } + + return \%seen; +} + +sub add_branch_config { + my ($hash, $name, $what, $value) = @_; + if ($what eq 'remote') { + if (exists $hash->{$name}{'REMOTE'}) { + print STDERR "Warning: more than one branch.$name.remote\n"; + } + $hash->{$name}{'REMOTE'} = $value; + } + elsif ($what eq 'merge') { + $hash->{$name}{'MERGE'} ||= []; + push @{$hash->{$name}{'MERGE'}}, $value; + } +} + +sub list_branch { + my ($git) = @_; + my %seen = (); + my @branches = eval { + $git->command(qw(repo-config --get-regexp), '^branch\.'); + }; + for (@branches) { + if (/^branch\.([^.]*)\.(\S*)\s+(.*)$/) { + add_branch_config(\%seen, $1, $2, $3); + } + } + + return \%seen; +} + +my $remote = list_remote($git); +my $branch = list_branch($git); + +sub update_ls_remote { + my ($harder, $info) = @_; + + return if (($harder == 0) || + (($harder == 1) && exists $info->{'LS_REMOTE'})); + + my @ref = map { + s|^[0-9a-f]{40}\s+refs/heads/||; + $_; + } $git->command(qw(ls-remote --heads), $info->{'URL'}); + $info->{'LS_REMOTE'} = \@ref; +} + +sub show_wildcard_mapping { + my ($forced, $ours, $ls) = @_; + my %refs; + for (@$ls) { + $refs{$_} = 01; # bit #0 to say "they have" + } + for ($git->command('for-each-ref', "refs/remotes/$ours")) { + chomp; + next unless (s|^[0-9a-f]{40}\s[a-z]+\srefs/remotes/$ours/||); + next if ($_ eq 'HEAD'); + $refs{$_} ||= 0; + $refs{$_} |= 02; # bit #1 to say "we have" + } + my (@new, @stale, @tracked); + for (sort keys %refs) { + my $have = $refs{$_}; + if ($have == 1) { + push @new, $_; + } + elsif ($have == 2) { + push @stale, $_; + } + elsif ($have == 3) { + push @tracked, $_; + } + } + if (@new) { + print " New remote branches (next fetch will store in remotes/$ours)\n"; + print " @new\n"; + } + if (@stale) { + print " Stale tracking branches in remotes/$ours (you'd better remove them)\n"; + print " @stale\n"; + } + if (@tracked) { + print " Tracked remote branches\n"; + print " @tracked\n"; + } +} + +sub show_mapping { + my ($name, $info) = @_; + my $fetch = $info->{'FETCH'}; + my $ls = $info->{'LS_REMOTE'}; + my (@stale, @tracked); + + for (@$fetch) { + next unless (/(\+)?([^:]+):(.*)/); + my ($forced, $theirs, $ours) = ($1, $2, $3); + if ($theirs eq 'refs/heads/*' && + $ours =~ /^refs\/remotes\/(.*)\/\*$/) { + # wildcard mapping + show_wildcard_mapping($forced, $1, $ls); + } + elsif ($theirs =~ /\*/ || $ours =~ /\*/) { + print STDERR "Warning: unrecognized mapping in remotes.$name.fetch: $_\n"; + } + elsif ($theirs =~ s|^refs/heads/||) { + if (!grep { $_ eq $theirs } @$ls) { + push @stale, $theirs; + } + elsif ($ours ne '') { + push @tracked, $theirs; + } + } + } + if (@stale) { + print " Stale tracking branches in remotes/$name (you'd better remove them)\n"; + print " @stale\n"; + } + if (@tracked) { + print " Tracked remote branches\n"; + print " @tracked\n"; + } +} + +sub show_remote { + my ($name, $ls_remote) = @_; + if (!exists $remote->{$name}) { + print STDERR "No such remote $name\n"; + return; + } + my $info = $remote->{$name}; + update_ls_remote($ls_remote, $info); + + print "* remote $name\n"; + print " URL: $info->{'URL'}\n"; + for my $branchname (sort keys %$branch) { + next if ($branch->{$branchname}{'REMOTE'} ne $name); + my @merged = map { + s|^refs/heads/||; + $_; + } split(' ',"@{$branch->{$branchname}{'MERGE'}}"); + next unless (@merged); + print " Remote branch(es) merged with 'git pull' while on branch $branchname\n"; + print " @merged\n"; + } + if ($info->{'LS_REMOTE'}) { + show_mapping($name, $info); + } +} + +sub add_remote { + my ($name, $url) = @_; + if (exists $remote->{$name}) { + print STDERR "remote $name already exists.\n"; + exit(1); + } + $git->command('repo-config', "remote.$name.url", $url); + $git->command('repo-config', "remote.$name.fetch", + "+refs/heads/*:refs/remotes/$name/*"); +} + +if (!@ARGV) { + for (sort keys %$remote) { + print "$_\n"; + } +} +elsif ($ARGV[0] eq 'show') { + my $ls_remote = 1; + my $i; + for ($i = 1; $i < @ARGV; $i++) { + if ($ARGV[$i] eq '-n') { + $ls_remote = 0; + } + else { + last; + } + } + if ($i >= @ARGV) { + print STDERR "Usage: git remote show <remote>\n"; + exit(1); + } + for (; $i < @ARGV; $i++) { + show_remote($ARGV[$i], $ls_remote); + } +} +elsif ($ARGV[0] eq 'add') { + if (@ARGV != 3) { + print STDERR "Usage: git remote add <name> <url>\n"; + exit(1); + } + add_remote($ARGV[1], $ARGV[2]); +} +else { + print STDERR "Usage: git remote\n"; + print STDERR " git remote add <name> <url>\n"; + print STDERR " git remote show <name>\n"; + exit(1); +} diff --git a/git-repack.sh b/git-repack.sh index 9da92fb061..da8e67f7a5 100755 --- a/git-repack.sh +++ b/git-repack.sh @@ -3,7 +3,8 @@ # Copyright (c) 2005 Linus Torvalds # -USAGE='[-a] [-d] [-f] [-l] [-n] [-q]' +USAGE='[-a] [-d] [-f] [-l] [-n] [-q] [--window=N] [--depth=N]' +SUBDIRECTORY_OK='Yes' . git-sh-setup no_update_info= all_into_one= remove_redundant= @@ -24,33 +25,50 @@ do shift done -rm -f .tmp-pack-* +# Later we will default repack.UseDeltaBaseOffset to true +default_dbo=false + +case "`git repo-config --bool repack.usedeltabaseoffset || + echo $default_dbo`" in +true) + extra="$extra --delta-base-offset" ;; +esac + PACKDIR="$GIT_OBJECT_DIRECTORY/pack" +PACKTMP="$GIT_DIR/.tmp-$$-pack" +rm -f "$PACKTMP"-* +trap 'rm -f "$PACKTMP"-*' 0 1 2 3 15 # There will be more repacking strategies to come... case ",$all_into_one," in ,,) - rev_list='--unpacked' - pack_objects='--incremental' + args='--unpacked --incremental' ;; ,t,) - rev_list= - pack_objects= - - # Redundancy check in all-into-one case is trivial. - existing=`cd "$PACKDIR" && \ - find . -type f \( -name '*.pack' -o -name '*.idx' \) -print` + if [ -d "$PACKDIR" ]; then + for e in `cd "$PACKDIR" && find . -type f -name '*.pack' \ + | sed -e 's/^\.\///' -e 's/\.pack$//'` + do + if [ -e "$PACKDIR/$e.keep" ]; then + : keep + else + args="$args --unpacked=$e.pack" + existing="$existing $e" + fi + done + fi + [ -z "$args" ] && args='--unpacked --incremental' ;; esac -pack_objects="$pack_objects $local $quiet $no_reuse_delta$extra" -name=$( { git-rev-list --objects --all $rev_list || - echo "git-rev-list died with exit code $?" - } | - git-pack-objects --non-empty $pack_objects .tmp-pack) || + +args="$args $local $quiet $no_reuse_delta$extra" +name=$(git-pack-objects --non-empty --all --reflog $args </dev/null "$PACKTMP") || exit 1 if [ -z "$name" ]; then echo Nothing new to pack. else + chmod a-w "$PACKTMP-$name.pack" + chmod a-w "$PACKTMP-$name.idx" if test "$quiet" != '-q'; then echo "Pack pack-$name created." fi @@ -64,8 +82,8 @@ else "$PACKDIR/old-pack-$name.$sfx" fi done && - mv -f .tmp-pack-$name.pack "$PACKDIR/pack-$name.pack" && - mv -f .tmp-pack-$name.idx "$PACKDIR/pack-$name.idx" && + mv -f "$PACKTMP-$name.pack" "$PACKDIR/pack-$name.pack" && + mv -f "$PACKTMP-$name.idx" "$PACKDIR/pack-$name.idx" && test -f "$PACKDIR/pack-$name.pack" && test -f "$PACKDIR/pack-$name.idx" || { echo >&2 "Couldn't replace the existing pack with updated one." @@ -78,22 +96,21 @@ fi if test "$remove_redundant" = t then - # We know $existing are all redundant only when - # all-into-one is used. - if test "$all_into_one" != '' && test "$existing" != '' + # We know $existing are all redundant. + if [ -n "$existing" ] then sync ( cd "$PACKDIR" && for e in $existing do case "$e" in - ./pack-$name.pack | ./pack-$name.idx) ;; - *) rm -f $e ;; + pack-$name) ;; + *) rm -f "$e.pack" "$e.idx" "$e.keep" ;; esac done ) fi - git-prune-packed + git-prune-packed $quiet fi case "$no_update_info" in diff --git a/git-request-pull.sh b/git-request-pull.sh index 4319e35c62..4eacc3a059 100755 --- a/git-request-pull.sh +++ b/git-request-pull.sh @@ -30,4 +30,4 @@ echo " $url" echo git log $baserev..$headrev | git-shortlog ; -git diff --stat --summary $baserev..$headrev +git diff -M --stat --summary $baserev..$headrev diff --git a/git-rerere.perl b/git-rerere.perl deleted file mode 100755 index d3664ff491..0000000000 --- a/git-rerere.perl +++ /dev/null @@ -1,227 +0,0 @@ -#!/usr/bin/perl -# -# REuse REcorded REsolve. This tool records a conflicted automerge -# result and its hand resolution, and helps to resolve future -# automerge that results in the same conflict. -# -# To enable this feature, create a directory 'rr-cache' under your -# .git/ directory. - -use Digest; -use File::Path; -use File::Copy; - -my $git_dir = $::ENV{GIT_DIR} || ".git"; -my $rr_dir = "$git_dir/rr-cache"; -my $merge_rr = "$git_dir/rr-cache/MERGE_RR"; - -my %merge_rr = (); - -sub read_rr { - if (!-f $merge_rr) { - %merge_rr = (); - return; - } - my $in; - local $/ = "\0"; - open $in, "<$merge_rr" or die "$!: $merge_rr"; - while (<$in>) { - chomp; - my ($name, $path) = /^([0-9a-f]{40})\t(.*)$/s; - $merge_rr{$path} = $name; - } - close $in; -} - -sub write_rr { - my $out; - open $out, ">$merge_rr" or die "$!: $merge_rr"; - for my $path (sort keys %merge_rr) { - my $name = $merge_rr{$path}; - print $out "$name\t$path\0"; - } - close $out; -} - -sub compute_conflict_name { - my ($path) = @_; - my @side = (); - my $in; - open $in, "<$path" or die "$!: $path"; - - my $sha1 = Digest->new("SHA-1"); - my $hunk = 0; - while (<$in>) { - if (/^<<<<<<< .*/) { - $hunk++; - @side = ([], undef); - } - elsif (/^=======$/) { - $side[1] = []; - } - elsif (/^>>>>>>> .*/) { - my ($one, $two); - $one = join('', @{$side[0]}); - $two = join('', @{$side[1]}); - if ($two le $one) { - ($one, $two) = ($two, $one); - } - $sha1->add($one); - $sha1->add("\0"); - $sha1->add($two); - $sha1->add("\0"); - @side = (); - } - elsif (@side == 0) { - next; - } - elsif (defined $side[1]) { - push @{$side[1]}, $_; - } - else { - push @{$side[0]}, $_; - } - } - close $in; - return ($sha1->hexdigest, $hunk); -} - -sub record_preimage { - my ($path, $name) = @_; - my @side = (); - my ($in, $out); - open $in, "<$path" or die "$!: $path"; - open $out, ">$name" or die "$!: $name"; - - while (<$in>) { - if (/^<<<<<<< .*/) { - @side = ([], undef); - } - elsif (/^=======$/) { - $side[1] = []; - } - elsif (/^>>>>>>> .*/) { - my ($one, $two); - $one = join('', @{$side[0]}); - $two = join('', @{$side[1]}); - if ($two le $one) { - ($one, $two) = ($two, $one); - } - print $out "<<<<<<<\n"; - print $out $one; - print $out "=======\n"; - print $out $two; - print $out ">>>>>>>\n"; - @side = (); - } - elsif (@side == 0) { - print $out $_; - } - elsif (defined $side[1]) { - push @{$side[1]}, $_; - } - else { - push @{$side[0]}, $_; - } - } - close $out; - close $in; -} - -sub find_conflict { - my $in; - local $/ = "\0"; - my $pid = open($in, '-|'); - die "$!" unless defined $pid; - if (!$pid) { - exec(qw(git ls-files -z -u)) or die "$!: ls-files"; - } - my %path = (); - my @path = (); - while (<$in>) { - chomp; - my ($mode, $sha1, $stage, $path) = - /^([0-7]+) ([0-9a-f]{40}) ([123])\t(.*)$/s; - $path{$path} |= (1 << $stage); - } - close $in; - while (my ($path, $status) = each %path) { - if ($status == 14) { push @path, $path; } - } - return @path; -} - -sub merge { - my ($name, $path) = @_; - record_preimage($path, "$rr_dir/$name/thisimage"); - unless (system('merge', map { "$rr_dir/$name/${_}image" } - qw(this pre post))) { - my $in; - open $in, "<$rr_dir/$name/thisimage" or - die "$!: $name/thisimage"; - my $out; - open $out, ">$path" or die "$!: $path"; - while (<$in>) { print $out $_; } - close $in; - close $out; - return 1; - } - return 0; -} - --d "$rr_dir" || exit(0); - -read_rr(); -my %conflict = map { $_ => 1 } find_conflict(); - -# MERGE_RR records paths with conflicts immediately after merge -# failed. Some of the conflicted paths might have been hand resolved -# in the working tree since then, but the initial run would catch all -# and register their preimages. - -for my $path (keys %conflict) { - # This path has conflict. If it is not recorded yet, - # record the pre-image. - if (!exists $merge_rr{$path}) { - my ($name, $hunk) = compute_conflict_name($path); - next unless ($hunk); - $merge_rr{$path} = $name; - if (! -d "$rr_dir/$name") { - mkpath("$rr_dir/$name", 0, 0777); - print STDERR "Recorded preimage for '$path'\n"; - record_preimage($path, "$rr_dir/$name/preimage"); - } - } -} - -# Now some of the paths that had conflicts earlier might have been -# hand resolved. Others may be similar to a conflict already that -# was resolved before. - -for my $path (keys %merge_rr) { - my $name = $merge_rr{$path}; - - # We could resolve this automatically if we have images. - if (-f "$rr_dir/$name/preimage" && - -f "$rr_dir/$name/postimage") { - if (merge($name, $path)) { - print STDERR "Resolved '$path' using previous resolution.\n"; - # Then we do not have to worry about this path - # anymore. - delete $merge_rr{$path}; - next; - } - } - - # Let's see if we have resolved it. - (undef, my $hunk) = compute_conflict_name($path); - next if ($hunk); - - print STDERR "Recorded resolution for '$path'.\n"; - copy($path, "$rr_dir/$name/postimage"); - # And we do not have to worry about this path anymore. - delete $merge_rr{$path}; -} - -# Write out the rest. -write_rr(); diff --git a/git-reset.sh b/git-reset.sh index 36fc8ce25b..b9045bc762 100755 --- a/git-reset.sh +++ b/git-reset.sh @@ -1,31 +1,64 @@ #!/bin/sh - -USAGE='[--mixed | --soft | --hard] [<commit-ish>]' +# +# Copyright (c) 2005, 2006 Linus Torvalds and Junio C Hamano +# +USAGE='[--mixed | --soft | --hard] [<commit-ish>] [ [--] <paths>...]' +SUBDIRECTORY_OK=Yes . git-sh-setup +set_reflog_action "reset $*" +require_work_tree -tmp=${GIT_DIR}/reset.$$ -trap 'rm -f $tmp-*' 0 1 2 3 15 +update= reset_type=--mixed +unset rev -update= -reset_type=--mixed -case "$1" in ---mixed | --soft | --hard) - reset_type="$1" +while case $# in 0) break ;; esac +do + case "$1" in + --mixed | --soft | --hard) + reset_type="$1" + ;; + --) + break + ;; + -*) + usage + ;; + *) + rev=$(git-rev-parse --verify "$1") || exit + shift + break + ;; + esac shift - ;; --*) - usage ;; -esac +done -case $# in -0) rev=HEAD ;; -1) rev=$(git-rev-parse --verify "$1") || exit ;; -*) usage ;; -esac +: ${rev=HEAD} rev=$(git-rev-parse --verify $rev^0) || exit -# We need to remember the set of paths that _could_ be left -# behind before a hard reset, so that we can remove them. +# Skip -- in "git reset HEAD -- foo" and "git reset -- foo". +case "$1" in --) shift ;; esac + +# git reset --mixed tree [--] paths... can be used to +# load chosen paths from the tree into the index without +# affecting the working tree nor HEAD. +if test $# != 0 +then + test "$reset_type" == "--mixed" || + die "Cannot do partial $reset_type reset." + + git-diff-index --cached $rev -- "$@" | + sed -e 's/^:\([0-7][0-7]*\) [0-7][0-7]* \([0-9a-f][0-9a-f]*\) [0-9a-f][0-9a-f]* [A-Z] \(.*\)$/\1 \2 \3/' | + git update-index --add --remove --index-info || exit + git update-index --refresh + exit +fi + +TOP=$(git-rev-parse --show-cdup) +if test ! -z "$TOP" +then + cd "$TOP" +fi + if test "$reset_type" = "--hard" then update=-u @@ -52,12 +85,17 @@ then else rm -f "$GIT_DIR/ORIG_HEAD" fi -git-update-ref -m "reset $reset_type $*" HEAD "$rev" +git-update-ref -m "$GIT_REFLOG_ACTION" HEAD "$rev" update_ref_status=$? case "$reset_type" in --hard ) - ;; # Nothing else to do + test $update_ref_status = 0 && { + echo -n "HEAD is now at " + GIT_PAGER= git log --max-count=1 --pretty=oneline \ + --abbrev-commit HEAD + } + ;; --soft ) ;; # Nothing else to do --mixed ) @@ -66,6 +104,7 @@ case "$reset_type" in ;; esac -rm -f "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/rr-cache/MERGE_RR" "$GIT_DIR/SQUASH_MSG" +rm -f "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/rr-cache/MERGE_RR" \ + "$GIT_DIR/SQUASH_MSG" "$GIT_DIR/MERGE_MSG" exit $update_ref_status diff --git a/git-resolve.sh b/git-resolve.sh index a7bc680d90..36b90e3849 100755 --- a/git-resolve.sh +++ b/git-resolve.sh @@ -5,6 +5,10 @@ # Resolve two trees. # +echo 'WARNING: This command is DEPRECATED and will be removed very soon.' >&2 +echo 'WARNING: Please use git-merge or git-pull instead.' >&2 +sleep 2 + USAGE='<head> <remote> <merge-message>' . git-sh-setup @@ -42,7 +46,7 @@ case "$common" in exit 0 ;; "$head") - echo "Updating from $head to $merge" + echo "Updating $(git-rev-parse --short $head)..$(git-rev-parse --short $merge)" git-read-tree -u -m $head $merge || exit 1 git-update-ref -m "resolve $merge_name: Fast forward" \ HEAD "$merge" "$head" diff --git a/git-revert.sh b/git-revert.sh index 2bf35d116c..fcca3ebb90 100755 --- a/git-revert.sh +++ b/git-revert.sh @@ -7,18 +7,22 @@ case "$0" in *-revert* ) test -t 0 && edit=-e + replay= me=revert USAGE='[--edit | --no-edit] [-n] <commit-ish>' ;; *-cherry-pick* ) + replay=t edit= me=cherry-pick - USAGE='[--edit] [-n] [-r] <commit-ish>' ;; + USAGE='[--edit] [-n] [-r] [-x] <commit-ish>' ;; * ) - die "What are you talking about?" ;; + echo >&2 "What are you talking about?" + exit 1 ;; esac . git-sh-setup +require_work_tree -no_commit= replay= +no_commit= while case "$#" in 0) break ;; esac do case "$1" in @@ -32,8 +36,10 @@ do --n|--no|--no-|--no-e|--no-ed|--no-edi|--no-edit) edit= ;; - -r|--r|--re|--rep|--repl|--repla|--replay) - replay=t + -r) + : no-op ;; + -x|--i-really-want-to-expose-my-private-commit-object-name) + replay= ;; -*) usage @@ -121,7 +127,7 @@ cherry-pick) git-cat-file commit $commit | sed -e '1,/^$/d' case "$replay" in '') - echo "(cherry picked from $commit commit)" + echo "(cherry picked from commit $commit)" test "$rev" = "$commit" || echo "(original 'git cherry-pick' arguments: $@)" ;; @@ -141,9 +147,18 @@ git-read-tree -m -u --aggressive $base $head $next && result=$(git-write-tree 2>/dev/null) || { echo >&2 "Simple $me fails; trying Automatic $me." git-merge-index -o git-merge-one-file -a || { + mv -f .msg "$GIT_DIR/MERGE_MSG" + { + echo ' +Conflicts: +' + git ls-files --unmerged | + sed -e 's/^[^ ]* / /' | + uniq + } >>"$GIT_DIR/MERGE_MSG" echo >&2 "Automatic $me failed. After resolving the conflicts," - echo >&2 "mark the corrected paths with 'git-update-index <paths>'" - echo >&2 "and commit with 'git commit -F .msg'" + echo >&2 "mark the corrected paths with 'git-add <paths>'" + echo >&2 "and commit the result." case "$me" in cherry-pick) echo >&2 "You may choose to use the following when making" diff --git a/git-send-email.perl b/git-send-email.perl index 746c525079..8dc2ee0cf7 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -21,6 +21,7 @@ use warnings; use Term::ReadLine; use Getopt::Long; use Data::Dumper; +use Git; package FakeTerm; sub new { @@ -82,16 +83,18 @@ sub cleanup_compose_files(); my $compose_filename = ".msg.$$"; # Variables we fill in automatically, or via prompting: -my (@to,@cc,@initial_cc,@bcclist, +my (@to,@cc,@initial_cc,@bcclist,@xh, $initial_reply_to,$initial_subject,@files,$from,$compose,$time); # Behavior modification variables -my ($chain_reply_to, $quiet, $suppress_from, $no_signed_off_cc) = (1, 0, 0, 0); +my ($chain_reply_to, $quiet, $suppress_from, $no_signed_off_cc, + $dry_run) = (1, 0, 0, 0, 0); my $smtp_server; # Example reply to: #$initial_reply_to = ''; #<20050203173208.GA23964@foobar.com>'; +my $repo = Git->repository(); my $term = eval { new Term::ReadLine 'git-send-email'; }; @@ -114,6 +117,7 @@ my $rc = GetOptions("from=s" => \$from, "quiet" => \$quiet, "suppress-from" => \$suppress_from, "no-signed-off-cc|no-signed-off-by-cc" => \$no_signed_off_cc, + "dry-run" => \$dry_run, ); # Verify the user input @@ -132,33 +136,12 @@ foreach my $entry (@bcclist) { # Now, let's fill any that aren't set in with defaults: -sub gitvar { - my ($var) = @_; - my $fh; - my $pid = open($fh, '-|'); - die "$!" unless defined $pid; - if (!$pid) { - exec('git-var', $var) or die "$!"; - } - my ($val) = <$fh>; - close $fh or die "$!"; - chomp($val); - return $val; -} - -sub gitvar_ident { - my ($name) = @_; - my $val = gitvar($name); - my @field = split(/\s+/, $val); - return join(' ', @field[0...(@field-3)]); -} - -my ($author) = gitvar_ident('GIT_AUTHOR_IDENT'); -my ($committer) = gitvar_ident('GIT_COMMITTER_IDENT'); +my ($author) = $repo->ident_person('author'); +my ($committer) = $repo->ident_person('committer'); my %aliases; -chomp(my @alias_files = `git-repo-config --get-all sendemail.aliasesfile`); -chomp(my $aliasfiletype = `git-repo-config sendemail.aliasfiletype`); +my @alias_files = $repo->config('sendemail.aliasesfile'); +my $aliasfiletype = $repo->config('sendemail.aliasfiletype'); my %parse_alias = ( # multiline formats can be supported in the future mutt => sub { my $fh = shift; while (<$fh>) { @@ -183,7 +166,7 @@ my %parse_alias = ( }}} ); -if (@alias_files && defined $parse_alias{$aliasfiletype}) { +if (@alias_files and $aliasfiletype and defined $parse_alias{$aliasfiletype}) { foreach my $file (@alias_files) { open my $fh, '<', $file or die "opening $file: $!\n"; $parse_alias{$aliasfiletype}->($fh); @@ -195,11 +178,10 @@ my $prompting = 0; if (!defined $from) { $from = $author || $committer; do { - $_ = $term->readline("Who should the emails appear to be from? ", - $from); + $_ = $term->readline("Who should the emails appear to be from? [$from] "); } while (!defined $_); - $from = $_; + $from = $_ if ($_); print "Emails will be sent from: ", $from, "\n"; $prompting++; } @@ -248,6 +230,9 @@ if (!defined $initial_reply_to && $prompting) { } if (!$smtp_server) { + $smtp_server = $repo->config('sendemail.smtpserver'); +} +if (!$smtp_server) { foreach (qw( /usr/sbin/sendmail /usr/lib/sendmail )) { if (-x $_) { $smtp_server = $_; @@ -417,6 +402,15 @@ sub make_message_id $cc = ""; $time = time - scalar $#files; +sub unquote_rfc2047 { + local ($_) = @_; + if (s/=\?utf-8\?q\?(.*)\?=/$1/g) { + s/_/ /g; + s/=([0-9A-F]{2})/chr(hex($1))/eg; + } + return "$_ - unquoted"; +} + sub send_message { my @recipients = unique_email_list(@to); @@ -425,12 +419,14 @@ sub send_message my $date = format_2822_time($time++); my $gitversion = '@@GIT_VERSION@@'; if ($gitversion =~ m/..GIT_VERSION../) { - $gitversion = `git --version`; - chomp $gitversion; - # keep only what's after the last space - $gitversion =~ s/^.* //; + $gitversion = Git::version(); } + my ($author_name) = ($from =~ /^(.*?)\s+</); + if ($author_name && $author_name =~ /\./ && $author_name !~ /^".*"$/) { + my ($name, $addr) = ($from =~ /^(.*?)(\s+<.*)/); + $from = "\"$name\"$addr"; + } my $header = "From: $from To: $to Cc: $cc @@ -444,8 +440,13 @@ X-Mailer: git-send-email $gitversion $header .= "In-Reply-To: $reply_to\n"; $header .= "References: $references\n"; } + if (@xh) { + $header .= join("\n", @xh) . "\n"; + } - if ($smtp_server =~ m#^/#) { + if ($dry_run) { + # We don't want to send the email. + } elsif ($smtp_server =~ m#^/#) { my $pid = open my $sm, '|-'; defined $pid or die $!; if (!$pid) { @@ -494,15 +495,22 @@ foreach my $t (@files) { my $author_not_sender = undef; @cc = @initial_cc; - my $found_mbox = 0; + @xh = (); + my $input_format = undef; my $header_done = 0; $message = ""; while(<F>) { if (!$header_done) { - $found_mbox = 1, next if (/^From /); + if (/^From /) { + $input_format = 'mbox'; + next; + } chomp; + if (!defined $input_format && /^[-A-Za-z]+:\s/) { + $input_format = 'mbox'; + } - if ($found_mbox) { + if (defined $input_format && $input_format eq 'mbox') { if (/^Subject:\s+(.*)$/) { $subject = $1; @@ -517,6 +525,9 @@ foreach my $t (@files) { $2, $_) unless $quiet; push @cc, $2; } + elsif (!/^Date:\s/ && /^[-A-Za-z]+:\s+\S/) { + push @xh, $_; + } } else { # In the traditional @@ -524,6 +535,7 @@ foreach my $t (@files) { # line 1 = cc # line 2 = subject # So let's support that, too. + $input_format = 'lots'; if (@cc == 0) { printf("(non-mbox) Adding cc: %s from line '%s'\n", $_, $_) unless $quiet; @@ -552,6 +564,7 @@ foreach my $t (@files) { } close F; if (defined $author_not_sender) { + $author_not_sender = unquote_rfc2047($author_not_sender); $message = "From: $author_not_sender\n\n$message"; } @@ -560,7 +573,7 @@ foreach my $t (@files) { send_message(); # set up for the next message - if ($chain_reply_to || length($reply_to) == 0) { + if ($chain_reply_to || !defined $reply_to || length($reply_to) == 0) { $reply_to = $message_id; if (length $references > 0) { $references .= " $message_id"; diff --git a/git-sh-setup.sh b/git-sh-setup.sh index 42f9b1c125..57f7f77776 100755 --- a/git-sh-setup.sh +++ b/git-sh-setup.sh @@ -20,6 +20,27 @@ usage() { die "Usage: $0 $USAGE" } +set_reflog_action() { + if [ -z "${GIT_REFLOG_ACTION:+set}" ] + then + GIT_REFLOG_ACTION="$*" + export GIT_REFLOG_ACTION + fi +} + +is_bare_repository () { + git-repo-config --bool --get core.bare || + case "$GIT_DIR" in + .git | */.git) echo false ;; + *) echo true ;; + esac +} + +require_work_tree () { + test $(is_bare_repository) = false || + die "fatal: $0 cannot be used without a working tree." +} + if [ -z "$LONG_USAGE" ] then LONG_USAGE="Usage: $0 $USAGE" @@ -39,7 +60,11 @@ esac if [ -z "$SUBDIRECTORY_OK" ] then : ${GIT_DIR=.git} - GIT_DIR=$(GIT_DIR="$GIT_DIR" git-rev-parse --git-dir) || exit + GIT_DIR=$(GIT_DIR="$GIT_DIR" git-rev-parse --git-dir) || { + exit=$? + echo >&2 "You need to run this command from the toplevel of the working tree." + exit $exit + } else GIT_DIR=$(git-rev-parse --git-dir) || exit fi diff --git a/git-shortlog.perl b/git-shortlog.perl deleted file mode 100755 index 0b14f833ee..0000000000 --- a/git-shortlog.perl +++ /dev/null @@ -1,200 +0,0 @@ -#!/usr/bin/perl -w - -use strict; - -my (%mailmap); -my (%email); -my (%map); -my $pstate = 1; -my $n_records = 0; -my $n_output = 0; - -sub shortlog_entry($$) { - my ($name, $desc) = @_; - my $key = $name; - - $desc =~ s#/pub/scm/linux/kernel/git/#/.../#g; - $desc =~ s#\[PATCH\] ##g; - - # store description in array, in email->{desc list} map - if (exists $map{$key}) { - # grab ref - my $obj = $map{$key}; - - # add desc to array - push(@$obj, $desc); - } else { - # create new array, containing 1 item - my @arr = ($desc); - - # store ref to array - $map{$key} = \@arr; - } -} - -# sort comparison function -sub by_name($$) { - my ($a, $b) = @_; - - uc($a) cmp uc($b); -} - -sub shortlog_output { - my ($obj, $key, $desc); - - foreach $key (sort by_name keys %map) { - # output author - printf "%s:\n", $key; - - # output author's 1-line summaries - $obj = $map{$key}; - foreach $desc (reverse @$obj) { - print " $desc\n"; - $n_output++; - } - - # blank line separating author from next author - print "\n"; - } -} - -sub changelog_input { - my ($author, $desc); - - while (<>) { - # get author and email - if ($pstate == 1) { - my ($email); - - next unless /^[Aa]uthor:?\s*(.*?)\s*<(.*)>/; - - $n_records++; - - $author = $1; - $email = $2; - $desc = undef; - - # cset author fixups - if (exists $mailmap{$email}) { - $author = $mailmap{$email}; - } elsif (exists $mailmap{$author}) { - $author = $mailmap{$author}; - } elsif (!$author) { - $author = $email; - } - $email{$author}{$email}++; - $pstate++; - } - - # skip to blank line - elsif ($pstate == 2) { - next unless /^\s*$/; - $pstate++; - } - - # skip to non-blank line - elsif ($pstate == 3) { - next unless /^\s*?(.*)/; - - # skip lines that are obviously not - # a 1-line cset description - next if /^\s*From: /; - - chomp; - $desc = $1; - - &shortlog_entry($author, $desc); - - $pstate = 1; - } - - else { - die "invalid parse state $pstate"; - } - } -} - -sub read_mailmap { - my ($fh, $mailmap) = @_; - while (<$fh>) { - chomp; - if (/^([^#].*?)\s*<(.*)>/) { - $mailmap->{$2} = $1; - } - } -} - -sub setup_mailmap { - read_mailmap(\*DATA, \%mailmap); - if (-f '.mailmap') { - my $fh = undef; - open $fh, '<', '.mailmap'; - read_mailmap($fh, \%mailmap); - close $fh; - } -} - -sub finalize { - #print "\n$n_records records parsed.\n"; - - if ($n_records != $n_output) { - die "parse error: input records != output records\n"; - } - if (0) { - for my $author (sort keys %email) { - my $e = $email{$author}; - for my $email (sort keys %$e) { - print STDERR "$author <$email>\n"; - } - } - } -} - -&setup_mailmap; -&changelog_input; -&shortlog_output; -&finalize; -exit(0); - - -__DATA__ -# -# Even with git, we don't always have name translations. -# So have an email->real name table to translate the -# (hopefully few) missing names -# -Adrian Bunk <bunk@stusta.de> -Andreas Herrmann <aherrman@de.ibm.com> -Andrew Morton <akpm@osdl.org> -Andrew Vasquez <andrew.vasquez@qlogic.com> -Christoph Hellwig <hch@lst.de> -Corey Minyard <minyard@acm.org> -David Woodhouse <dwmw2@shinybook.infradead.org> -Domen Puncer <domen@coderock.org> -Douglas Gilbert <dougg@torque.net> -Ed L Cashin <ecashin@coraid.com> -Evgeniy Polyakov <johnpol@2ka.mipt.ru> -Felix Moeller <felix@derklecks.de> -Frank Zago <fzago@systemfabricworks.com> -Greg Kroah-Hartman <gregkh@suse.de> -James Bottomley <jejb@mulgrave.(none)> -James Bottomley <jejb@titanic.il.steeleye.com> -Jeff Garzik <jgarzik@pretzel.yyz.us> -Jens Axboe <axboe@suse.de> -Kay Sievers <kay.sievers@vrfy.org> -Mitesh shah <mshah@teja.com> -Morten Welinder <terra@gnome.org> -Morten Welinder <welinder@anemone.rentec.com> -Morten Welinder <welinder@darter.rentec.com> -Morten Welinder <welinder@troll.com> -Nguyen Anh Quynh <aquynh@gmail.com> -Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> -Peter A Jonsson <pj@ludd.ltu.se> -Ralf Wildenhues <Ralf.Wildenhues@gmx.de> -Rudolf Marek <R.Marek@sh.cvut.cz> -Rui Saraiva <rmps@joel.ist.utl.pt> -Sachin P Sant <ssant@in.ibm.com> -Santtu Hyrkk,Av(B <santtu.hyrkko@gmail.com> -Simon Kelley <simon@thekelleys.org.uk> -Tejun Heo <htejun@gmail.com> -Tony Luck <tony.luck@intel.com> diff --git a/git-svn.perl b/git-svn.perl index 0d58bb9b37..9986a0c9bb 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -21,39 +21,58 @@ $ENV{TZ} = 'UTC'; $ENV{LC_ALL} = 'C'; $| = 1; # unbuffer STDOUT -# If SVN:: library support is added, please make the dependencies -# optional and preserve the capability to use the command-line client. -# use eval { require SVN::... } to make it lazy load -# We don't use any modules not in the standard Perl distribution: +# properties that we do not log: +my %SKIP = ( 'svn:wc:ra_dav:version-url' => 1, + 'svn:special' => 1, + 'svn:executable' => 1, + 'svn:entry:committed-rev' => 1, + 'svn:entry:last-author' => 1, + 'svn:entry:uuid' => 1, + 'svn:entry:committed-date' => 1, +); + +sub fatal (@) { print STDERR @_; exit 1 } +require SVN::Core; # use()-ing this causes segfaults for me... *shrug* +require SVN::Ra; +require SVN::Delta; +if ($SVN::Core::VERSION lt '1.1.0') { + fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)\n"; +} +push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; +push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor'; +*SVN::Git::Fetcher::process_rm = *process_rm; use Carp qw/croak/; use IO::File qw//; use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; -use File::Spec qw//; -use File::Copy qw/copy/; use POSIX qw/strftime/; use IPC::Open3; use Memoize; +use Git qw/command command_oneline command_noisy + command_output_pipe command_input_pipe command_close_pipe/; memoize('revisions_eq'); memoize('cmt_metadata'); memoize('get_commit_time'); -my ($SVN_PATH, $SVN, $SVN_LOG, $_use_lib); -$_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB}; -libsvn_load(); +my ($SVN); + my $_optimize_commits = 1 unless $ENV{GIT_SVN_NO_OPTIMIZE_COMMITS}; my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{4,40}/; +my $_esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_cp_similarity, $_cp_remote, $_repack, $_repack_nr, $_repack_flags, $_q, $_message, $_file, $_follow_parent, $_no_metadata, $_template, $_shared, $_no_default_regex, $_no_graft_copy, $_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit, - $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m); + $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m, + $_merge, $_strategy, $_dry_run, $_ignore_nodate, $_non_recursive, + $_username, $_config_dir, $_no_auth_cache, + $_pager, $_color, $_prefix); my (@_branch_from, %tree_map, %users, %rusers, %equiv); -my ($_svn_co_url_revs, $_svn_pg_peg_revs); +my ($_svn_can_do_switch); my @repo_path_split_cache; my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, @@ -64,6 +83,10 @@ my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'repack:i' => \$_repack, 'no-metadata' => \$_no_metadata, 'quiet|q' => \$_q, + 'username=s' => \$_username, + 'config-dir=s' => \$_config_dir, + 'no-auth-cache' => \$_no_auth_cache, + 'ignore-nodate' => \$_ignore_nodate, 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags); my ($_trunk, $_tags, $_branches); @@ -79,12 +102,17 @@ my %cmt_opts = ( 'edit|e' => \$_edit, ); my %cmd = ( - fetch => [ \&fetch, "Download new revisions from SVN", + fetch => [ \&cmd_fetch, "Download new revisions from SVN", { 'revision|r=s' => \$_revision, %fc_opts } ], init => [ \&init, "Initialize a repo for tracking" . " (requires URL argument)", \%init_opts ], - commit => [ \&commit, "Commit git revisions to SVN", + dcommit => [ \&dcommit, 'Commit several diffs to merge with upstream', + { 'merge|m|M' => \$_merge, + 'strategy|s=s' => \$_strategy, + 'dry-run|n' => \$_dry_run, + %cmt_opts, %fc_opts } ], + 'set-tree' => [ \&commit, "Set an SVN repository to a git tree-ish", { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ], 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", { 'revision|r=i' => \$_revision } ], @@ -101,7 +129,13 @@ my %cmd = ( 'no-graft-copy' => \$_no_graft_copy } ], 'multi-init' => [ \&multi_init, 'Initialize multiple trees (like git-svnimport)', - { %multi_opts, %fc_opts } ], + { %multi_opts, %init_opts, + 'revision|r=i' => \$_revision, + 'username=s' => \$_username, + 'config-dir=s' => \$_config_dir, + 'no-auth-cache' => \$_no_auth_cache, + 'prefix=s' => \$_prefix, + } ], 'multi-fetch' => [ \&multi_fetch, 'Fetch multiple trees (like git-svnimport)', \%fc_opts ], @@ -112,11 +146,15 @@ my %cmd = ( 'incremental' => \$_incremental, 'oneline' => \$_oneline, 'show-commit' => \$_show_commit, + 'non-recursive' => \$_non_recursive, 'authors-file|A=s' => \$_authors, + 'color' => \$_color, + 'pager=s' => \$_pager, } ], 'commit-diff' => [ \&commit_diff, 'Commit a diff between two trees', { 'message|m=s' => \$_message, 'file|F=s' => \$_file, + 'revision|r=s' => \$_revision, %cmt_opts } ], ); @@ -144,7 +182,6 @@ usage(1) unless defined $cmd; init_vars(); load_authors() if $_authors; load_all_refs() if $_branch_all_refs; -svn_compat_check() unless $_use_lib; migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init|commit-diff)$/; $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -161,11 +198,11 @@ Usage: $0 <command> [options] [arguments]\n foreach (sort keys %cmd) { next if $cmd && $cmd ne $_; - print $fd ' ',pack('A13',$_),$cmd{$_}->[1],"\n"; + print $fd ' ',pack('A17',$_),$cmd{$_}->[1],"\n"; foreach (keys %{$cmd{$_}->[2]}) { # prints out arguments as they should be passed: my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : ''; - print $fd ' ' x 17, join(', ', map { length $_ > 1 ? + print $fd ' ' x 21, join(', ', map { length $_ > 1 ? "--$_" : "-$_" } split /\|/,$_)," $x\n"; } @@ -180,36 +217,35 @@ information. } sub version { - print "git-svn version $VERSION\n"; + print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n"; exit 0; } sub rebuild { - if (quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0")) { + if (!verify_ref("refs/remotes/$GIT_SVN^0")) { copy_remote_ref(); } $SVN_URL = shift or undef; my $newest_rev = 0; if ($_upgrade) { - sys('git-update-ref',"refs/remotes/$GIT_SVN","$GIT_SVN-HEAD"); + command_noisy('update-ref',"refs/remotes/$GIT_SVN"," + $GIT_SVN-HEAD"); } else { check_upgrade_needed(); } - my $pid = open(my $rev_list,'-|'); - defined $pid or croak $!; - if ($pid == 0) { - exec("git-rev-list","refs/remotes/$GIT_SVN") or croak $!; - } + my ($rev_list, $ctx) = command_output_pipe("rev-list", + "refs/remotes/$GIT_SVN"); my $latest; while (<$rev_list>) { chomp; my $c = $_; croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o; - my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`); + my @commit = grep(/^git-svn-id: /, + command(qw/cat-file commit/, $c)); next if (!@commit); # skip merges my ($url, $rev, $uuid) = extract_metadata($commit[$#commit]); - if (!$rev || !$uuid) { + if (!defined $rev || !$uuid) { croak "Unable to extract revision or UUID from ", "$c, $commit[$#commit]\n"; } @@ -232,33 +268,7 @@ sub rebuild { print "r$rev = $c\n"; $newest_rev = $rev if ($rev > $newest_rev); } - close $rev_list or croak $?; - - goto out if $_use_lib; - if (!chdir $SVN_WC) { - svn_cmd_checkout($SVN_URL, $latest, $SVN_WC); - chdir $SVN_WC or croak $!; - } - - $pid = fork; - defined $pid or croak $!; - if ($pid == 0) { - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - sys(@svn_up,"-r$newest_rev"); - $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; - index_changes(); - exec('git-write-tree') or croak $!; - } - waitpid $pid, 0; - croak $? if $?; -out: - if ($_upgrade) { - print STDERR <<""; -Keeping deprecated refs/head/$GIT_SVN-HEAD for now. Please remove it -when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN - - } + command_close_pipe($rev_list, $ctx); } sub init { @@ -276,88 +286,32 @@ sub init { $SVN_URL = $url; unless (-d $GIT_DIR) { - my @init_db = ('git-init-db'); + my @init_db = ('init'); push @init_db, "--template=$_template" if defined $_template; push @init_db, "--shared" if defined $_shared; - sys(@init_db); + command_noisy(@init_db); } setup_git_svn(); } +sub cmd_fetch { + fetch_child_id($GIT_SVN, @_); +} + sub fetch { check_upgrade_needed(); $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - my $ret = $_use_lib ? fetch_lib(@_) : fetch_cmd(@_); - if ($ret->{commit} && quiet_run(qw(git-rev-parse --verify - refs/heads/master^0))) { - sys(qw(git-update-ref refs/heads/master),$ret->{commit}); + my $ret = fetch_lib(@_); + if ($ret->{commit} && !verify_ref('refs/heads/master^0')) { + command_noisy(qw(update-ref refs/heads/master),$ret->{commit}); } return $ret; } -sub fetch_cmd { - my (@parents) = @_; - my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL); - unless ($_revision) { - $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD'; - } - push @log_args, "-r$_revision"; - push @log_args, '--stop-on-copy' unless $_no_stop_copy; - - my $svn_log = svn_log_raw(@log_args); - - my $base = next_log_entry($svn_log) or croak "No base revision!\n"; - # don't need last_revision from grab_base_rev() because - # user could've specified a different revision to skip (they - # didn't want to import certain revisions into git for whatever - # reason, so trust $base->{revision} instead. - my (undef, $last_commit) = svn_grab_base_rev(); - unless (-d $SVN_WC) { - svn_cmd_checkout($SVN_URL,$base->{revision},$SVN_WC); - chdir $SVN_WC or croak $!; - read_uuid(); - $last_commit = git_commit($base, @parents); - assert_tree($last_commit); - } else { - chdir $SVN_WC or croak $!; - read_uuid(); - # looks like a user manually cp'd and svn switch'ed - unless ($last_commit) { - sys(qw/svn revert -R ./); - assert_svn_wc_clean($base->{revision}); - $last_commit = git_commit($base, @parents); - assert_tree($last_commit); - } - } - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - my $last = $base; - while (my $log_msg = next_log_entry($svn_log)) { - if ($last->{revision} >= $log_msg->{revision}) { - croak "Out of order: last >= current: ", - "$last->{revision} >= $log_msg->{revision}\n"; - } - # Revert is needed for cases like: - # https://svn.musicpd.org/Jamming/trunk (r166:167), but - # I can't seem to reproduce something like that on a test... - sys(qw/svn revert -R ./); - assert_svn_wc_clean($last->{revision}); - sys(@svn_up,"-r$log_msg->{revision}"); - $last_commit = git_commit($log_msg, $last_commit, @parents); - $last = $log_msg; - } - close $svn_log->{fh}; - $last->{commit} = $last_commit; - return $last; -} - sub fetch_lib { my (@parents) = @_; $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - my $repo; - ($repo, $SVN_PATH) = repo_path_split($SVN_URL); - $SVN_LOG ||= libsvn_connect($repo); - $SVN ||= libsvn_connect($repo); + $SVN ||= libsvn_connect($SVN_URL); my ($last_rev, $last_commit) = svn_grab_base_rev(); my ($base, $head) = libsvn_parse_revision($last_rev); if ($base > $head) { @@ -372,16 +326,16 @@ sub fetch_lib { read_uuid(); if (defined $last_commit) { unless (-e $GIT_SVN_INDEX) { - sys(qw/git-read-tree/, $last_commit); + command_noisy('read-tree', $last_commit); } - chomp (my $x = `git-write-tree`); - my ($y) = (`git-cat-file commit $last_commit` + my $x = command_oneline('write-tree'); + my ($y) = (command(qw/cat-file commit/, $last_commit) =~ /^tree ($sha1)/m); if ($y ne $x) { unlink $GIT_SVN_INDEX or croak $!; - sys(qw/git-read-tree/, $last_commit); + command_noisy('read-tree', $last_commit); } - chomp ($x = `git-write-tree`); + $x = command_oneline('write-tree'); if ($y ne $x) { print STDERR "trees ($last_commit) $y != $x\n", "Something is seriously wrong...\n"; @@ -399,7 +353,7 @@ sub fetch_lib { # performance sucks with it enabled, so it's much # faster to fetch revision ranges instead of relying # on the limiter. - libsvn_get_log($SVN_LOG, '/'.$SVN_PATH, + libsvn_get_log(libsvn_dup_ra($SVN), [''], $min, $max, 0, 1, 1, sub { my $log_msg; @@ -425,6 +379,7 @@ sub fetch_lib { $min = $max + 1; $max += $inc; $max = $head if ($max > $head); + $SVN = libsvn_connect($SVN_URL); } restore_index($index); return { revision => $last_rev, commit => $last_commit }; @@ -444,45 +399,19 @@ sub commit { } my @revs; foreach my $c (@commits) { - chomp(my @tmp = safe_qx('git-rev-parse',$c)); + my @tmp = command('rev-parse',$c); if (scalar @tmp == 1) { push @revs, $tmp[0]; } elsif (scalar @tmp > 1) { - push @revs, reverse (safe_qx('git-rev-list',@tmp)); + push @revs, reverse(command('rev-list',@tmp)); } else { die "Failed to rev-parse $c\n"; } } - chomp @revs; - $_use_lib ? commit_lib(@revs) : commit_cmd(@revs); + commit_lib(@revs); print "Done committing ",scalar @revs," revisions to SVN\n"; } -sub commit_cmd { - my (@revs) = @_; - - chdir $SVN_WC or croak "Unable to chdir $SVN_WC: $!\n"; - my $info = svn_info('.'); - my $fetched = fetch(); - if ($info->{Revision} != $fetched->{revision}) { - print STDERR "There are new revisions that were fetched ", - "and need to be merged (or acknowledged) ", - "before committing.\n"; - exit 1; - } - $info = svn_info('.'); - read_uuid($info); - my $last = $fetched; - foreach my $c (@revs) { - my $mods = svn_checkout_tree($last, $c); - if (scalar @$mods == 0) { - print "Skipping, no changes detected\n"; - next; - } - $last = svn_commit_tree($last, $c); - } -} - sub commit_lib { my (@revs) = @_; my ($r_last, $cmt_last) = svn_grab_base_rev(); @@ -500,6 +429,7 @@ sub commit_lib { my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; + my $repo; set_svn_commit_env(); foreach my $c (@revs) { my $log_msg = get_commit_message($c, $commit_msg); @@ -510,9 +440,9 @@ sub commit_lib { if (!$pid) { my $ed = SVN::Git::Editor->new( { r => $r_last, - ra => $SVN, + ra => libsvn_dup_ra($SVN), c => $c, - svn_path => $SVN_PATH + svn_path => $SVN->{svn_path}, }, $SVN->get_commit_editor( $log_msg->{msg}, @@ -544,7 +474,7 @@ sub commit_lib { $no = 1; } } - close $fh or croak $?; + close $fh or exit 1; if (! defined $r_new && ! defined $cmt_new) { unless ($no) { die "Failed to parse revision information\n"; @@ -557,39 +487,57 @@ sub commit_lib { unlink $commit_msg; } -sub show_ignore { - $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - $_use_lib ? show_ignore_lib() : show_ignore_cmd(); -} - -sub show_ignore_cmd { - require File::Find or die $!; - if (defined $_revision) { - die "-r/--revision option doesn't work unless the Perl SVN ", - "libraries are used\n"; - } - chdir $SVN_WC or croak $!; - my %ign; - File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ - s#^\./##; - @{$ign{$_}} = svn_propget_base('svn:ignore', $_); - }}, no_chdir=>1},'.'); - - print "\n# /\n"; - foreach (@{$ign{'.'}}) { print '/',$_ if /\S/ } - delete $ign{'.'}; - foreach my $i (sort keys %ign) { - print "\n# ",$i,"\n"; - foreach (@{$ign{$i}}) { print '/',$i,'/',$_ if /\S/ } +sub dcommit { + my $head = shift || 'HEAD'; + my $gs = "refs/remotes/$GIT_SVN"; + my @refs = command(qw/rev-list --no-merges/, "$gs..$head"); + my $last_rev; + foreach my $d (reverse @refs) { + if (!verify_ref("$d~1")) { + die "Commit $d\n", + "has no parent commit, and therefore ", + "nothing to diff against.\n", + "You should be working from a repository ", + "originally created by git-svn\n"; + } + unless (defined $last_rev) { + (undef, $last_rev, undef) = cmt_metadata("$d~1"); + unless (defined $last_rev) { + die "Unable to extract revision information ", + "from commit $d~1\n"; + } + } + if ($_dry_run) { + print "diff-tree $d~1 $d\n"; + } else { + if (my $r = commit_diff("$d~1", $d, undef, $last_rev)) { + $last_rev = $r; + } # else: no changes, same $last_rev + } + } + return if $_dry_run; + fetch(); + my @diff = command('diff-tree', 'HEAD', $gs, '--'); + my @finish; + if (@diff) { + @finish = qw/rebase/; + push @finish, qw/--merge/ if $_merge; + push @finish, "--strategy=$_strategy" if $_strategy; + print STDERR "W: HEAD and $gs differ, using @finish:\n", @diff; + } else { + print "No changes between current HEAD and $gs\n", + "Resetting to the latest $gs\n"; + @finish = qw/reset --mixed/; } + command_noisy(@finish, $gs); } -sub show_ignore_lib { +sub show_ignore { + $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); my $repo; - ($repo, $SVN_PATH) = repo_path_split($SVN_URL); - $SVN ||= libsvn_connect($repo); + $SVN ||= libsvn_connect($SVN_URL); my $r = defined $_revision ? $_revision : $SVN->get_latest_revnum; - libsvn_traverse_ignore(\*STDOUT, $SVN_PATH, $r); + libsvn_traverse_ignore(\*STDOUT, '', $r); } sub graft_branches { @@ -599,7 +547,7 @@ sub graft_branches { if (%$grafts) { # temporarily disable our grafts file to make this idempotent - chomp($gr_sha1 = safe_qx(qw/git-hash-object -w/,$gr_file)); + chomp($gr_sha1 = command(qw/hash-object -w/,$gr_file)); rename $gr_file, "$gr_file~$gr_sha1" or croak $!; } @@ -617,11 +565,7 @@ sub graft_branches { } } unless ($_no_graft_copy) { - if ($_use_lib) { - graft_file_copy_lib($grafts,$l_map,$u); - } else { - graft_file_copy_cmd($grafts,$l_map,$u); - } + graft_file_copy_lib($grafts,$l_map,$u); } } graft_tree_joins($grafts); @@ -632,26 +576,29 @@ sub graft_branches { sub multi_init { my $url = shift; - $_trunk ||= 'trunk'; - $_trunk =~ s#/+$##; - $url =~ s#/+$## if $url; - if ($_trunk !~ m#^[a-z\+]+://#) { - $_trunk = '/' . $_trunk if ($_trunk !~ m#^/#); - unless ($url) { - print STDERR "E: '$_trunk' is not a complete URL ", - "and a separate URL is not specified\n"; - exit 1; - } - $_trunk = $url . $_trunk; + unless (defined $_trunk || defined $_branches || defined $_tags) { + usage(1); } - if ($GIT_SVN eq 'git-svn') { - print "GIT_SVN_ID set to 'trunk' for $_trunk\n"; - $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; + if (defined $_trunk) { + my $trunk_url = complete_svn_url($url, $_trunk); + my $ch_id; + if ($GIT_SVN eq 'git-svn') { + $ch_id = 1; + $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; + } + init_vars(); + unless (-d $GIT_SVN_DIR) { + if ($ch_id) { + print "GIT_SVN_ID set to 'trunk' for ", + "$trunk_url ($_trunk)\n"; + } + init($trunk_url); + command_noisy('repo-config', 'svn.trunk', $trunk_url); + } } - init_vars(); - init($_trunk); - complete_url_ls_init($url, $_branches, '--branches/-b', ''); - complete_url_ls_init($url, $_tags, '--tags/-t', 'tags/'); + $_prefix = '' unless defined $_prefix; + complete_url_ls_init($url, $_branches, '--branches/-b', $_prefix); + complete_url_ls_init($url, $_tags, '--tags/-t', $_prefix . 'tags/'); } sub multi_fetch { @@ -685,16 +632,14 @@ sub show_log { } } - my $pid = open(my $log,'-|'); - defined $pid or croak $!; - if (!$pid) { - exec(git_svn_log_cmd($r_min,$r_max), @args) or croak $!; - } - setup_pager(); + config_pager(); + @args = (git_svn_log_cmd($r_min, $r_max), @args); + my $log = command_output_pipe(@args); + run_pager(); my (@k, $c, $d); while (<$log>) { - if (/^commit ($sha1_short)/o) { + if (/^${_esc_color}commit ($sha1_short)/o) { my $cmt = $1; if ($c && cmt_showable($c) && $c->{r} != $r_last) { $r_last = $c->{r}; @@ -703,20 +648,25 @@ sub show_log { } $d = undef; $c = { c => $cmt }; - } elsif (/^author (.+) (\d+) ([\-\+]?\d+)$/) { + } elsif (/^${_esc_color}author (.+) (\d+) ([\-\+]?\d+)$/) { get_author_info($c, $1, $2, $3); - } elsif (/^(?:tree|parent|committer) /) { + } elsif (/^${_esc_color}(?:tree|parent|committer) /) { # ignore - } elsif (/^:\d{6} \d{6} $sha1_short/o) { + } elsif (/^${_esc_color}:\d{6} \d{6} $sha1_short/o) { push @{$c->{raw}}, $_; - } elsif (/^diff /) { + } elsif (/^${_esc_color}[ACRMDT]\t/) { + # we could add $SVN->{svn_path} here, but that requires + # remote access at the moment (repo_path_split)... + s#^(${_esc_color})([ACRMDT])\t#$1 $2 #; + push @{$c->{changed}}, $_; + } elsif (/^${_esc_color}diff /) { $d = 1; push @{$c->{diff}}, $_; } elsif ($d) { push @{$c->{diff}}, $_; - } elsif (/^ (git-svn-id:.+)$/) { - (undef, $c->{r}, undef) = extract_metadata($1); - } elsif (s/^ //) { + } elsif (/^${_esc_color} (git-svn-id:.+)$/) { + ($c->{url}, $c->{r}, undef) = extract_metadata($1); + } elsif (s/^${_esc_color} //) { push @{$c->{l}}, $_; } } @@ -731,7 +681,7 @@ sub show_log { process_commit($_, $r_min, $r_max) foreach reverse @k; } out: - close $log; + eval { command_close_pipe($log) }; print '-' x72,"\n" unless $_incremental || $_oneline; } @@ -741,16 +691,20 @@ sub commit_diff_usage { } sub commit_diff { - if (!$_use_lib) { - print STDERR "commit-diff must be used with SVN libraries\n"; - exit 1; - } my $ta = shift or commit_diff_usage(); my $tb = shift or commit_diff_usage(); if (!eval { $SVN_URL = shift || file_to_s("$GIT_SVN_DIR/info/url") }) { print STDERR "Needed URL or usable git-svn id command-line\n"; commit_diff_usage(); } + my $r = shift; + unless (defined $r) { + if (defined $_revision) { + $r = $_revision + } else { + die "-r|--revision is a required argument\n"; + } + } if (defined $_message && defined $_file) { print STDERR "Both --message/-m and --file/-F specified ", "for the commit message.\n", @@ -763,25 +717,37 @@ sub commit_diff { $_message ||= get_commit_message($tb, "$GIT_DIR/.svn-commit.tmp.$$")->{msg}; } - my $repo; - ($repo, $SVN_PATH) = repo_path_split($SVN_URL); - $SVN_LOG ||= libsvn_connect($repo); - $SVN ||= libsvn_connect($repo); + $SVN ||= libsvn_connect($SVN_URL); + if ($r eq 'HEAD') { + $r = $SVN->get_latest_revnum; + } elsif ($r !~ /^\d+$/) { + die "revision argument: $r not understood by git-svn\n"; + } my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); - my $ed = SVN::Git::Editor->new({ r => $SVN->get_latest_revnum, - ra => $SVN, c => $tb, - svn_path => $SVN_PATH + my $rev_committed; + my $ed = SVN::Git::Editor->new({ r => $r, + ra => libsvn_dup_ra($SVN), + c => $tb, + svn_path => $SVN->{svn_path} }, $SVN->get_commit_editor($_message, - sub {print "Committed $_[0]\n"},@lock) + sub { + $rev_committed = $_[0]; + print "Committed $_[0]\n"; + }, @lock) ); - my $mods = libsvn_checkout_tree($ta, $tb, $ed); - if (@$mods == 0) { - print "No changes\n$ta == $tb\n"; - $ed->abort_edit; - } else { - $ed->close_edit; - } + eval { + my $mods = libsvn_checkout_tree($ta, $tb, $ed); + if (@$mods == 0) { + print "No changes\n$ta == $tb\n"; + $ed->abort_edit; + } else { + $ed->close_edit; + } + }; + fatal "$@\n" if $@; + $_message = $_file = undef; + return $rev_committed; } ########################### utility functions ######################### @@ -791,7 +757,7 @@ sub cmt_showable { return 1 if defined $c->{r}; if ($c->{l} && $c->{l}->[-1] eq "...\n" && $c->{a_raw} =~ /\@([a-f\d\-]+)>$/) { - my @msg = safe_qx(qw/git-cat-file commit/, $c->{c}); + my @msg = command(qw/cat-file commit/, $c->{c}); shift @msg while ($msg[0] ne "\n"); shift @msg; @{$c->{l}} = grep !/^git-svn-id: /, @msg; @@ -802,11 +768,49 @@ sub cmt_showable { return defined $c->{r}; } +sub log_use_color { + return 1 if $_color; + my ($dc, $dcvar); + $dcvar = 'color.diff'; + $dc = `git-repo-config --get $dcvar`; + if ($dc eq '') { + # nothing at all; fallback to "diff.color" + $dcvar = 'diff.color'; + $dc = `git-repo-config --get $dcvar`; + } + chomp($dc); + if ($dc eq 'auto') { + my $pc; + $pc = `git-repo-config --get color.pager`; + if ($pc eq '') { + # does not have it -- fallback to pager.color + $pc = `git-repo-config --bool --get pager.color`; + } + else { + $pc = `git-repo-config --bool --get color.pager`; + if ($?) { + $pc = 'false'; + } + } + chomp($pc); + if (-t *STDOUT || (defined $_pager && $pc eq 'true')) { + return ($ENV{TERM} && $ENV{TERM} ne 'dumb'); + } + return 0; + } + return 0 if $dc eq 'never'; + return 1 if $dc eq 'always'; + chomp($dc = `git-repo-config --bool --get $dcvar`); + return ($dc eq 'true'); +} + sub git_svn_log_cmd { my ($r_min, $r_max) = @_; - my @cmd = (qw/git-log --abbrev-commit --pretty=raw + my @cmd = (qw/log --abbrev-commit --pretty=raw --default/, "refs/remotes/$GIT_SVN"); - push @cmd, '--summary' if $_verbose; + push @cmd, '-r' unless $_non_recursive; + push @cmd, qw/--raw --name-status/ if $_verbose; + push @cmd, '--color' if log_use_color(); return @cmd unless defined $r_max; if ($r_max == $r_min) { push @cmd, '--max-count=1'; @@ -817,7 +821,7 @@ sub git_svn_log_cmd { my ($c_min, $c_max); $c_max = revdb_get($REVDB, $r_max); $c_min = revdb_get($REVDB, $r_min); - if ($c_min && $c_max) { + if (defined $c_min && defined $c_max) { if ($r_max > $r_max) { push @cmd, "$c_min..$c_max"; } else { @@ -838,7 +842,6 @@ sub fetch_child_id { my $ref = "$GIT_DIR/refs/remotes/$id"; defined(my $pid = open my $fh, '-|') or croak $!; if (!$pid) { - $_repack = undef; $GIT_SVN = $ENV{GIT_SVN_ID} = $id; init_vars(); fetch(@_); @@ -846,7 +849,7 @@ sub fetch_child_id { } while (<$fh>) { print $_; - check_repack() if (/^r\d+ = $sha1/); + check_repack() if (/^r\d+ = $sha1/o); } close $fh or croak $?; } @@ -871,43 +874,52 @@ sub rec_fetch { } } +sub complete_svn_url { + my ($url, $path) = @_; + $path =~ s#/+$##; + $url =~ s#/+$## if $url; + if ($path !~ m#^[a-z\+]+://#) { + $path = '/' . $path if ($path !~ m#^/#); + if (!defined $url || $url !~ m#^[a-z\+]+://#) { + fatal("E: '$path' is not a complete URL ", + "and a separate URL is not specified\n"); + } + $path = $url . $path; + } + return $path; +} + sub complete_url_ls_init { - my ($url, $var, $switch, $pfx) = @_; - unless ($var) { + my ($url, $path, $switch, $pfx) = @_; + unless ($path) { print STDERR "W: $switch not specified\n"; return; } - $var =~ s#/+$##; - if ($var !~ m#^[a-z\+]+://#) { - $var = '/' . $var if ($var !~ m#^/#); - unless ($url) { - print STDERR "E: '$var' is not a complete URL ", - "and a separate URL is not specified\n"; - exit 1; - } - $var = $url . $var; - } - chomp(my @ls = $_use_lib ? libsvn_ls_fullurl($var) - : safe_qx(qw/svn ls --non-interactive/, $var)); - my $old = $GIT_SVN; + my $full_url = complete_svn_url($url, $path); + my @ls = libsvn_ls_fullurl($full_url); defined(my $pid = fork) or croak $!; if (!$pid) { - foreach my $u (map { "$var/$_" } (grep m!/$!, @ls)) { + foreach my $u (map { "$full_url/$_" } (grep m!/$!, @ls)) { $u =~ s#/+$##; - if ($u !~ m!\Q$var\E/(.+)$!) { + if ($u !~ m!\Q$full_url\E/(.+)$!) { print STDERR "W: Unrecognized URL: $u\n"; die "This should never happen\n"; } + # don't try to init already existing refs my $id = $pfx.$1; - print "init $u => $id\n"; $GIT_SVN = $ENV{GIT_SVN_ID} = $id; init_vars(); - init($u); + unless (-d $GIT_SVN_DIR) { + print "init $u => $id\n"; + init($u); + } } exit 0; } waitpid $pid, 0; croak $? if $?; + my ($n) = ($switch =~ /^--(\w+)/); + command_noisy('repo-config', "svn.$n", $full_url); } sub common_prefix { @@ -939,11 +951,8 @@ sub graft_tree_joins { git_svn_each(sub { my $i = shift; - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - exec qw/git-rev-list --pretty=raw/, - "refs/remotes/$i" or croak $!; - } + my @args = (qw/rev-list --pretty=raw/, "refs/remotes/$i"); + my ($fh, $ctx) = command_output_pipe(@args); while (<$fh>) { next unless /^commit ($sha1)$/o; my $c = $1; @@ -966,9 +975,7 @@ sub graft_tree_joins { foreach my $p (@{$tree_map{$t}}) { next if $p eq $c; - my $mb = eval { - safe_qx('git-merge-base', $c, $p) - }; + my $mb = eval { command('merge-base', $c, $p) }; next unless ($@ || $?); if (defined $r_a) { # see if SVN says it's a relative @@ -997,48 +1004,16 @@ sub graft_tree_joins { # what should we do when $ct == $s ? } } - close $fh or croak $?; + command_close_pipe($fh, $ctx); }); } -# this isn't funky-filename safe, but good enough for now... -sub graft_file_copy_cmd { - my ($grafts, $l_map, $u) = @_; - my $paths = $l_map->{$u}; - my $pfx = common_prefix([keys %$paths]); - $SVN_URL ||= $u.$pfx; - my $pid = open my $fh, '-|'; - defined $pid or croak $!; - unless ($pid) { - my @exec = qw/svn log -v/; - push @exec, "-r$_revision" if defined $_revision; - exec @exec, $u.$pfx or croak $!; - } - my ($r, $mp) = (undef, undef); - while (<$fh>) { - chomp; - if (/^\-{72}$/) { - $mp = $r = undef; - } elsif (/^r(\d+) \| /) { - $r = $1 unless defined $r; - } elsif (/^Changed paths:/) { - $mp = 1; - } elsif ($mp && m#^ [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) { - my ($p1, $p0, $r0) = ($1, $2, $3); - my $c = find_graft_path_commit($paths, $p1, $r); - next unless $c; - find_graft_path_parents($grafts, $paths, $c, $p0, $r0); - } - } -} - sub graft_file_copy_lib { my ($grafts, $l_map, $u) = @_; my $tree_paths = $l_map->{$u}; my $pfx = common_prefix([keys %$tree_paths]); my ($repo, $path) = repo_path_split($u.$pfx); - $SVN_LOG ||= libsvn_connect($repo); - $SVN ||= libsvn_connect($repo); + $SVN = libsvn_connect($repo); my ($base, $head) = libsvn_parse_revision(); my $inc = 1000; @@ -1047,7 +1022,8 @@ sub graft_file_copy_lib { $SVN::Error::handler = \&libsvn_skip_unknown_revs; while (1) { my $pool = SVN::Pool->new; - libsvn_get_log($SVN_LOG, "/$path", $min, $max, 0, 1, 1, + libsvn_get_log(libsvn_dup_ra($SVN), [$path], + $min, $max, 0, 2, 1, sub { libsvn_graft_file_copies($grafts, $tree_paths, $path, @_); @@ -1110,7 +1086,7 @@ sub graft_merge_msg { my ($grafts, $l_map, $u, $p, @re) = @_; my $x = $l_map->{$u}->{$p}; - my $rl = rev_list_raw($x); + my $rl = rev_list_raw("refs/remotes/$x"); while (my $c = next_rev_list_entry($rl)) { foreach my $re (@re) { my (@br) = ($c->{m} =~ /$re/g); @@ -1122,28 +1098,15 @@ sub graft_merge_msg { sub read_uuid { return if $SVN_UUID; - if ($_use_lib) { - my $pool = SVN::Pool->new; - $SVN_UUID = $SVN->get_uuid($pool); - $pool->clear; - } else { - my $info = shift || svn_info('.'); - $SVN_UUID = $info->{'Repository UUID'} or - croak "Repository UUID unreadable\n"; - } + my $pool = SVN::Pool->new; + $SVN_UUID = $SVN->get_uuid($pool); + $pool->clear; } -sub quiet_run { - my $pid = fork; - defined $pid or croak $!; - if (!$pid) { - open my $null, '>', '/dev/null' or croak $!; - open STDERR, '>&', $null or croak $!; - open STDOUT, '>&', $null or croak $!; - exec @_ or croak $!; - } - waitpid $pid, 0; - return $?; +sub verify_ref { + my ($ref) = @_; + eval { command_oneline([ 'rev-parse', '--verify', $ref ], + { STDERR => 0 }); }; } sub repo_path_split { @@ -1157,25 +1120,8 @@ sub repo_path_split { return ($u, $full_url); } } - - if ($_use_lib) { - my $tmp = libsvn_connect($full_url); - my $url = $tmp->get_repos_root; - $full_url =~ s#^\Q$url\E/*##; - push @repo_path_split_cache, qr/^(\Q$url\E)/; - return ($url, $full_url); - } else { - my ($url, $path) = ($full_url =~ m!^([a-z\+]+://[^/]*)(.*)$!i); - $path =~ s#^/+##; - my @paths = split(m#/+#, $path); - while (quiet_run(qw/svn ls --non-interactive/, $url)) { - my $n = shift @paths || last; - $url .= "/$n"; - } - push @repo_path_split_cache, qr/^(\Q$url\E)/; - $path = join('/',@paths); - return ($url, $path); - } + my $tmp = libsvn_connect($full_url); + return ($tmp->{repos_root}, $tmp->{svn_path}); } sub setup_git_svn { @@ -1191,40 +1137,17 @@ sub setup_git_svn { } -sub assert_svn_wc_clean { - return if $_use_lib; - my ($svn_rev) = @_; - croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/); - my $lcr = svn_info('.')->{'Last Changed Rev'}; - if ($svn_rev != $lcr) { - print STDERR "Checking for copy-tree ... "; - my @diff = grep(/^Index: /,(safe_qx(qw(svn diff), - "-r$lcr:$svn_rev"))); - if (@diff) { - croak "Nope! Expected r$svn_rev, got r$lcr\n"; - } else { - print STDERR "OK!\n"; - } - } - my @status = grep(!/^Performing status on external/,(`svn status`)); - @status = grep(!/^\s*$/,@status); - if (scalar @status) { - print STDERR "Tree ($SVN_WC) is not clean:\n"; - print STDERR $_ foreach @status; - croak; - } -} - sub get_tree_from_treeish { my ($treeish) = @_; croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o; - chomp(my $type = `git-cat-file -t $treeish`); + my $type = command_oneline(qw/cat-file -t/, $treeish); my $expected; while ($type eq 'tag') { - chomp(($treeish, $type) = `git-cat-file tag $treeish`); + ($treeish, $type) = command(qw/cat-file tag/, $treeish); } if ($type eq 'commit') { - $expected = (grep /^tree /,`git-cat-file commit $treeish`)[0]; + $expected = (grep /^tree /, command(qw/cat-file commit/, + $treeish))[0]; ($expected) = ($expected =~ /^tree ($sha1)$/); die "Unable to get tree from $treeish\n" unless $expected; } elsif ($type eq 'tree') { @@ -1235,27 +1158,19 @@ sub get_tree_from_treeish { return $expected; } -sub assert_tree { - return if $_use_lib; - my ($treeish) = @_; - my $expected = get_tree_from_treeish($treeish); - - my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp'; - if (-e $tmpindex) { - unlink $tmpindex or croak $!; - } - my $old_index = set_index($tmpindex); - index_changes(1); - chomp(my $tree = `git-write-tree`); - restore_index($old_index); - if ($tree ne $expected) { - croak "Tree mismatch, Got: $tree, Expected: $expected\n"; +sub get_diff { + my ($from, $treeish) = @_; + print "diff-tree $from $treeish\n"; + my @diff_tree = qw(diff-tree -z -r); + if ($_cp_similarity) { + push @diff_tree, "-C$_cp_similarity"; + } else { + push @diff_tree, '-C'; } - unlink $tmpindex; -} - -sub parse_diff_tree { - my $diff_fh = shift; + push @diff_tree, '--find-copies-harder' if $_find_copies_harder; + push @diff_tree, "-l$_l" if defined $_l; + push @diff_tree, $from, $treeish; + my ($diff_fh, $ctx) = command_output_pipe(@diff_tree); local $/ = "\0"; my $state = 'meta'; my @mods; @@ -1291,167 +1206,10 @@ sub parse_diff_tree { croak "Error parsing $_\n"; } } - close $diff_fh or croak $?; - + command_close_pipe($diff_fh, $ctx); return \@mods; } -sub svn_check_prop_executable { - my $m = shift; - return if -l $m->{file_b}; - if ($m->{mode_b} =~ /755$/) { - chmod((0755 &~ umask),$m->{file_b}) or croak $!; - if ($m->{mode_a} !~ /755$/) { - sys(qw(svn propset svn:executable 1), $m->{file_b}); - } - -x $m->{file_b} or croak "$m->{file_b} is not executable!\n"; - } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { - sys(qw(svn propdel svn:executable), $m->{file_b}); - chmod((0644 &~ umask),$m->{file_b}) or croak $!; - -x $m->{file_b} and croak "$m->{file_b} is executable!\n"; - } -} - -sub svn_ensure_parent_path { - my $dir_b = dirname(shift); - svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir); - mkpath([$dir_b]) unless (-d $dir_b); - sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn"); -} - -sub precommit_check { - my $mods = shift; - my (%rm_file, %rmdir_check, %added_check); - - my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 ); - foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { - if ($m->{chg} eq 'R') { - if (-d $m->{file_b}) { - err_dir_to_file("$m->{file_a} => $m->{file_b}"); - } - # dir/$file => dir/file/$file - my $dirname = dirname($m->{file_b}); - while ($dirname ne File::Spec->curdir) { - if ($dirname ne $m->{file_a}) { - $dirname = dirname($dirname); - next; - } - err_file_to_dir("$m->{file_a} => $m->{file_b}"); - } - # baz/zzz => baz (baz is a file) - $dirname = dirname($m->{file_a}); - while ($dirname ne File::Spec->curdir) { - if ($dirname ne $m->{file_b}) { - $dirname = dirname($dirname); - next; - } - err_dir_to_file("$m->{file_a} => $m->{file_b}"); - } - } - if ($m->{chg} =~ /^(D|R)$/) { - my $t = $1 eq 'D' ? 'file_b' : 'file_a'; - $rm_file{ $m->{$t} } = 1; - my $dirname = dirname( $m->{$t} ); - my $basename = basename( $m->{$t} ); - $rmdir_check{$dirname}->{$basename} = 1; - } elsif ($m->{chg} =~ /^(?:A|C)$/) { - if (-d $m->{file_b}) { - err_dir_to_file($m->{file_b}); - } - my $dirname = dirname( $m->{file_b} ); - my $basename = basename( $m->{file_b} ); - $added_check{$dirname}->{$basename} = 1; - while ($dirname ne File::Spec->curdir) { - if ($rm_file{$dirname}) { - err_file_to_dir($m->{file_b}); - } - $dirname = dirname $dirname; - } - } - } - return (\%rmdir_check, \%added_check); - - sub err_dir_to_file { - my $file = shift; - print STDERR "Node change from directory to file ", - "is not supported by Subversion: ",$file,"\n"; - exit 1; - } - sub err_file_to_dir { - my $file = shift; - print STDERR "Node change from file to directory ", - "is not supported by Subversion: ",$file,"\n"; - exit 1; - } -} - - -sub get_diff { - my ($from, $treeish) = @_; - assert_tree($from); - print "diff-tree $from $treeish\n"; - my $pid = open my $diff_fh, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - my @diff_tree = qw(git-diff-tree -z -r); - if ($_cp_similarity) { - push @diff_tree, "-C$_cp_similarity"; - } else { - push @diff_tree, '-C'; - } - push @diff_tree, '--find-copies-harder' if $_find_copies_harder; - push @diff_tree, "-l$_l" if defined $_l; - exec(@diff_tree, $from, $treeish) or croak $!; - } - return parse_diff_tree($diff_fh); -} - -sub svn_checkout_tree { - my ($from, $treeish) = @_; - my $mods = get_diff($from->{commit}, $treeish); - return $mods unless (scalar @$mods); - my ($rm, $add) = precommit_check($mods); - - my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); - foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { - if ($m->{chg} eq 'C') { - svn_ensure_parent_path( $m->{file_b} ); - sys(qw(svn cp), $m->{file_a}, $m->{file_b}); - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'D') { - sys(qw(svn rm --force), $m->{file_b}); - } elsif ($m->{chg} eq 'R') { - svn_ensure_parent_path( $m->{file_b} ); - sys(qw(svn mv --force), $m->{file_a}, $m->{file_b}); - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'M') { - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'T') { - sys(qw(svn rm --force),$m->{file_b}); - apply_mod_line_blob($m); - sys(qw(svn add), $m->{file_b}); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'A') { - svn_ensure_parent_path( $m->{file_b} ); - apply_mod_line_blob($m); - sys(qw(svn add), $m->{file_b}); - svn_check_prop_executable($m); - } else { - croak "Invalid chg: $m->{chg}\n"; - } - } - - assert_tree($treeish); - if ($_rmdir) { # remove empty directories - handle_rmdir($rm, $add); - } - assert_tree($treeish); - return $mods; -} - sub libsvn_checkout_tree { my ($from, $treeish, $ed) = @_; my $mods = get_diff($from, $treeish); @@ -1469,57 +1227,15 @@ sub libsvn_checkout_tree { return $mods; } -# svn ls doesn't work with respect to the current working tree, but what's -# in the repository. There's not even an option for it... *sigh* -# (added files don't show up and removed files remain in the ls listing) -sub svn_ls_current { - my ($dir, $rm, $add) = @_; - chomp(my @ls = safe_qx('svn','ls',$dir)); - my @ret = (); - foreach (@ls) { - s#/$##; # trailing slashes are evil - push @ret, $_ unless $rm->{$dir}->{$_}; - } - if (exists $add->{$dir}) { - push @ret, keys %{$add->{$dir}}; - } - return \@ret; -} - -sub handle_rmdir { - my ($rm, $add) = @_; - - foreach my $dir (sort {length $b <=> length $a} keys %$rm) { - my $ls = svn_ls_current($dir, $rm, $add); - next if (scalar @$ls); - sys(qw(svn rm --force),$dir); - - my $dn = dirname $dir; - $rm->{ $dn }->{ basename $dir } = 1; - $ls = svn_ls_current($dn, $rm, $add); - while (scalar @$ls == 0 && $dn ne File::Spec->curdir) { - sys(qw(svn rm --force),$dn); - $dir = basename $dn; - $dn = dirname $dn; - $rm->{ $dn }->{ $dir } = 1; - $ls = svn_ls_current($dn, $rm, $add); - } - } -} - sub get_commit_message { my ($commit, $commit_msg) = (@_); my %log_msg = ( msg => '' ); open my $msg, '>', $commit_msg or croak $!; - chomp(my $type = `git-cat-file -t $commit`); + my $type = command_oneline(qw/cat-file -t/, $commit); if ($type eq 'commit' || $type eq 'tag') { - my $pid = open my $msg_fh, '-|'; - defined $pid or croak $!; - - if ($pid == 0) { - exec('git-cat-file', $type, $commit) or croak $!; - } + my ($msg_fh, $ctx) = command_output_pipe('cat-file', + $type, $commit); my $in_msg = 0; while (<$msg_fh>) { if (!$in_msg) { @@ -1531,7 +1247,7 @@ sub get_commit_message { print $msg $_ or croak $!; } } - close $msg_fh or croak $?; + command_close_pipe($msg_fh, $ctx); } close $msg or croak $!; @@ -1556,64 +1272,9 @@ sub set_svn_commit_env { } } -sub svn_commit_tree { - my ($last, $commit) = @_; - my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; - my $log_msg = get_commit_message($commit, $commit_msg); - my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/); - print "Committing $commit: $oneline\n"; - - set_svn_commit_env(); - my @ci_output = safe_qx(qw(svn commit -F),$commit_msg); - $ENV{LC_ALL} = 'C'; - unlink $commit_msg; - my ($committed) = ($ci_output[$#ci_output] =~ /(\d+)/); - if (!defined $committed) { - my $out = join("\n",@ci_output); - print STDERR "W: Trouble parsing \`svn commit' output:\n\n", - $out, "\n\nAssuming English locale..."; - ($committed) = ($out =~ /^Committed revision \d+\./sm); - defined $committed or die " FAILED!\n", - "Commit output failed to parse committed revision!\n", - print STDERR " OK\n"; - } - - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - if ($_optimize_commits && ($committed == ($last->{revision} + 1))) { - push @svn_up, "-r$committed"; - sys(@svn_up); - my $info = svn_info('.'); - my $date = $info->{'Last Changed Date'} or die "Missing date\n"; - if ($info->{'Last Changed Rev'} != $committed) { - croak "$info->{'Last Changed Rev'} != $committed\n" - } - my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ - /(\d{4})\-(\d\d)\-(\d\d)\s - (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) - or croak "Failed to parse date: $date\n"; - $log_msg->{date} = "$tz $Y-$m-$d $H:$M:$S"; - $log_msg->{author} = $info->{'Last Changed Author'}; - $log_msg->{revision} = $committed; - $log_msg->{msg} .= "\n"; - $log_msg->{parents} = [ $last->{commit} ]; - $log_msg->{commit} = git_commit($log_msg, $commit); - return $log_msg; - } - # resync immediately - push @svn_up, "-r$last->{revision}"; - sys(@svn_up); - return fetch("$committed=$commit"); -} - sub rev_list_raw { - my (@args) = @_; - my $pid = open my $fh, '-|'; - defined $pid or croak $!; - if (!$pid) { - exec(qw/git-rev-list --pretty=raw/, @args) or croak $!; - } - return { fh => $fh, t => { } }; + my ($fh, $c) = command_output_pipe(qw/rev-list --pretty=raw/, @_); + return { fh => $fh, ctx => $c, t => { } }; } sub next_rev_list_entry { @@ -1635,182 +1296,10 @@ sub next_rev_list_entry { $x->{m} .= $_; } } + command_close_pipe($fh, $rl->{ctx}); return ($x != $rl->{t}) ? $x : undef; } -# read the entire log into a temporary file (which is removed ASAP) -# and store the file handle + parser state -sub svn_log_raw { - my (@log_args) = @_; - my $log_fh = IO::File->new_tmpfile or croak $!; - my $pid = fork; - defined $pid or croak $!; - if (!$pid) { - open STDOUT, '>&', $log_fh or croak $!; - exec (qw(svn log), @log_args) or croak $! - } - waitpid $pid, 0; - croak $? if $?; - seek $log_fh, 0, 0 or croak $!; - return { state => 'sep', fh => $log_fh }; -} - -sub next_log_entry { - my $log = shift; # retval of svn_log_raw() - my $ret = undef; - my $fh = $log->{fh}; - - while (<$fh>) { - chomp; - if (/^\-{72}$/) { - if ($log->{state} eq 'msg') { - if ($ret->{lines}) { - $ret->{msg} .= $_."\n"; - unless(--$ret->{lines}) { - $log->{state} = 'sep'; - } - } else { - croak "Log parse error at: $_\n", - $ret->{revision}, - "\n"; - } - next; - } - if ($log->{state} ne 'sep') { - croak "Log parse error at: $_\n", - "state: $log->{state}\n", - $ret->{revision}, - "\n"; - } - $log->{state} = 'rev'; - - # if we have an empty log message, put something there: - if ($ret) { - $ret->{msg} ||= "\n"; - delete $ret->{lines}; - return $ret; - } - next; - } - if ($log->{state} eq 'rev' && s/^r(\d+)\s*\|\s*//) { - my $rev = $1; - my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3); - ($lines) = ($lines =~ /(\d+)/); - my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ - /(\d{4})\-(\d\d)\-(\d\d)\s - (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) - or croak "Failed to parse date: $date\n"; - $ret = { revision => $rev, - date => "$tz $Y-$m-$d $H:$M:$S", - author => $author, - lines => $lines, - msg => '' }; - if (defined $_authors && ! defined $users{$author}) { - die "Author: $author not defined in ", - "$_authors file\n"; - } - $log->{state} = 'msg_start'; - next; - } - # skip the first blank line of the message: - if ($log->{state} eq 'msg_start' && /^$/) { - $log->{state} = 'msg'; - } elsif ($log->{state} eq 'msg') { - if ($ret->{lines}) { - $ret->{msg} .= $_."\n"; - unless (--$ret->{lines}) { - $log->{state} = 'sep'; - } - } else { - croak "Log parse error at: $_\n", - $ret->{revision},"\n"; - } - } - } - return $ret; -} - -sub svn_info { - my $url = shift || $SVN_URL; - - my $pid = open my $info_fh, '-|'; - defined $pid or croak $!; - - if ($pid == 0) { - exec(qw(svn info),$url) or croak $!; - } - - my $ret = {}; - # only single-lines seem to exist in svn info output - while (<$info_fh>) { - chomp $_; - if (m#^([^:]+)\s*:\s*(\S.*)$#) { - $ret->{$1} = $2; - push @{$ret->{-order}}, $1; - } - } - close $info_fh or croak $?; - return $ret; -} - -sub sys { system(@_) == 0 or croak $? } - -sub do_update_index { - my ($z_cmd, $cmd, $no_text_base) = @_; - - my $z = open my $p, '-|'; - defined $z or croak $!; - unless ($z) { exec @$z_cmd or croak $! } - - my $pid = open my $ui, '|-'; - defined $pid or croak $!; - unless ($pid) { - exec('git-update-index',"--$cmd",'-z','--stdin') or croak $!; - } - local $/ = "\0"; - while (my $x = <$p>) { - chomp $x; - if (!$no_text_base && lstat $x && ! -l _ && - svn_propget_base('svn:keywords', $x)) { - my $mode = -x _ ? 0755 : 0644; - my ($v,$d,$f) = File::Spec->splitpath($x); - my $tb = File::Spec->catfile($d, '.svn', 'tmp', - 'text-base',"$f.svn-base"); - $tb =~ s#^/##; - unless (-f $tb) { - $tb = File::Spec->catfile($d, '.svn', - 'text-base',"$f.svn-base"); - $tb =~ s#^/##; - } - my @s = stat($x); - unlink $x or croak $!; - copy($tb, $x); - chmod(($mode &~ umask), $x) or croak $!; - utime $s[8], $s[9], $x; - } - print $ui $x,"\0"; - } - close $ui or croak $?; -} - -sub index_changes { - return if $_use_lib; - - if (!-f "$GIT_SVN_DIR/info/exclude") { - open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; - print $fd '.svn',"\n"; - close $fd or croak $!; - } - my $no_text_base = shift; - do_update_index([qw/git-diff-files --name-only -z/], - 'remove', - $no_text_base); - do_update_index([qw/git-ls-files -z --others/, - "--exclude-from=$GIT_SVN_DIR/info/exclude"], - 'add', - $no_text_base); -} - sub s_to_file { my ($str, $file, $mode) = @_; open my $fd,'>',$file or croak $!; @@ -1836,18 +1325,6 @@ sub assert_revision_unknown { } } -sub trees_eq { - my ($x, $y) = @_; - my @x = safe_qx('git-cat-file','commit',$x); - my @y = safe_qx('git-cat-file','commit',$y); - if (($y[0] ne $x[0]) || $x[0] !~ /^tree $sha1\n$/ - || $y[0] !~ /^tree $sha1\n$/) { - print STDERR "Trees not equal: $y[0] != $x[0]\n"; - return 0 - } - return 1; -} - sub git_commit { my ($log_msg, @parents) = @_; assert_revision_unknown($log_msg->{revision}); @@ -1872,15 +1349,14 @@ sub git_commit { my $tree = $log_msg->{tree}; if (!defined $tree) { my $index = set_index($GIT_SVN_INDEX); - index_changes(); - chomp($tree = `git-write-tree`); + $tree = command_oneline('write-tree'); croak $? if $?; restore_index($index); } - # just in case we clobber the existing ref, we still want that ref # as our parent: - if (my $cur = eval { file_to_s("$GIT_DIR/refs/remotes/$GIT_SVN") }) { + if (my $cur = verify_ref("refs/remotes/$GIT_SVN^0")) { + chomp $cur; push @tmp_parents, $cur; } @@ -1889,9 +1365,7 @@ sub git_commit { my $skip; foreach (@tmp_parents) { # see if a common parent is found - my $mb = eval { - safe_qx('git-merge-base', $_, $p) - }; + my $mb = eval { command('merge-base', $_, $p) }; next if ($@ || $?); $skip = 1; last; @@ -1933,19 +1407,19 @@ sub git_commit { if ($commit !~ /^$sha1$/o) { die "Failed to commit, invalid sha1: $commit\n"; } - sys('git-update-ref',"refs/remotes/$GIT_SVN",$commit); + command_noisy('update-ref',"refs/remotes/$GIT_SVN",$commit); revdb_set($REVDB, $log_msg->{revision}, $commit); # this output is read via pipe, do not change: print "r$log_msg->{revision} = $commit\n"; - check_repack(); return $commit; } sub check_repack { if ($_repack && (--$_repack_nr == 0)) { $_repack_nr = $_repack; - sys("git repack $_repack_flags"); + # repack doesn't use any arguments with spaces in them, does it? + command_noisy('repack', split(/\s+/, $_repack_flags)); } } @@ -1962,122 +1436,17 @@ sub set_commit_env { $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_msg->{date}; } -sub apply_mod_line_blob { - my $m = shift; - if ($m->{mode_b} =~ /^120/) { - blob_to_symlink($m->{sha1_b}, $m->{file_b}); - } else { - blob_to_file($m->{sha1_b}, $m->{file_b}); - } -} - -sub blob_to_symlink { - my ($blob, $link) = @_; - defined $link or croak "\$link not defined!\n"; - croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; - if (-l $link || -f _) { - unlink $link or croak $!; - } - - my $dest = `git-cat-file blob $blob`; # no newline, so no chomp - symlink $dest, $link or croak $!; -} - -sub blob_to_file { - my ($blob, $file) = @_; - defined $file or croak "\$file not defined!\n"; - croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; - if (-l $file || -f _) { - unlink $file or croak $!; - } - - open my $blob_fh, '>', $file or croak "$!: $file\n"; - my $pid = fork; - defined $pid or croak $!; - - if ($pid == 0) { - open STDOUT, '>&', $blob_fh or croak $!; - exec('git-cat-file','blob',$blob) or croak $!; - } - waitpid $pid, 0; - croak $? if $?; - - close $blob_fh or croak $!; -} - -sub safe_qx { - my $pid = open my $child, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - exec(@_) or croak $!; - } - my @ret = (<$child>); - close $child or croak $?; - die $? if $?; # just in case close didn't error out - return wantarray ? @ret : join('',@ret); -} - -sub svn_compat_check { - if ($_follow_parent) { - print STDERR 'E: --follow-parent functionality is only ', - "available when SVN libraries are used\n"; - exit 1; - } - my @co_help = safe_qx(qw(svn co -h)); - unless (grep /ignore-externals/,@co_help) { - print STDERR "W: Installed svn version does not support ", - "--ignore-externals\n"; - $_no_ignore_ext = 1; - } - if (grep /usage: checkout URL\[\@REV\]/,@co_help) { - $_svn_co_url_revs = 1; - } - if (grep /\[TARGET\[\@REV\]\.\.\.\]/, `svn propget -h`) { - $_svn_pg_peg_revs = 1; - } - - # I really, really hope nobody hits this... - unless (grep /stop-on-copy/, (safe_qx(qw(svn log -h)))) { - print STDERR <<''; -W: The installed svn version does not support the --stop-on-copy flag in - the log command. - Lets hope the directory you're tracking is not a branch or tag - and was never moved within the repository... - - $_no_stop_copy = 1; - } -} - -# *sigh*, new versions of svn won't honor -r<rev> without URL@<rev>, -# (and they won't honor URL@<rev> without -r<rev>, too!) -sub svn_cmd_checkout { - my ($url, $rev, $dir) = @_; - my @cmd = ('svn','co', "-r$rev"); - push @cmd, '--ignore-externals' unless $_no_ignore_ext; - $url .= "\@$rev" if $_svn_co_url_revs; - sys(@cmd, $url, $dir); -} - sub check_upgrade_needed { if (!-r $REVDB) { -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]); open my $fh, '>>',$REVDB or croak $!; close $fh; } - my $old = eval { - my $pid = open my $child, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - close STDERR; - exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $!; - } - my @ret = (<$child>); - close $child or croak $?; - die $? if $?; # just in case close didn't error out - return wantarray ? @ret : join('',@ret); + return unless eval { + command([qw/rev-parse --verify/,"$GIT_SVN-HEAD^0"], + {STDERR => 0}); }; - return unless $old; - my $head = eval { safe_qx('git-rev-parse',"refs/remotes/$GIT_SVN") }; + my $head = eval { command('rev-parse',"refs/remotes/$GIT_SVN") }; if ($@ || !$head) { print STDERR "Please run: $0 rebuild --upgrade\n"; exit 1; @@ -2089,12 +1458,8 @@ sub check_upgrade_needed { sub map_tree_joins { my %seen; foreach my $br (@_branch_from) { - my $pid = open my $pipe, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - exec(qw(git-rev-list --topo-order --pretty=raw), $br) - or croak $!; - } + my $pipe = command_output_pipe(qw/rev-list + --topo-order --pretty=raw/, $br); while (<$pipe>) { if (/^commit ($sha1)$/o) { my $commit = $1; @@ -2110,7 +1475,7 @@ sub map_tree_joins { $seen{$commit} = 1; } } - close $pipe; # we could be breaking the pipe early + eval { command_close_pipe($pipe) }; } } @@ -2122,7 +1487,7 @@ sub load_all_refs { # don't worry about rev-list on non-commit objects/tags, # it shouldn't blow up if a ref is a blob or tree... - chomp(@_branch_from = `git-rev-parse --symbolic --all`); + @_branch_from = command(qw/rev-parse --symbolic --all/); } # '<svn username> = real-name <email address>' mapping based on git-svnimport: @@ -2130,7 +1495,7 @@ sub load_authors { open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; while (<$authors>) { chomp; - next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; + next unless /^(\S+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/; my ($user, $name, $email) = ($1, $2, $3); $users{$user} = [$name, $email]; } @@ -2148,15 +1513,9 @@ sub rload_authors { close $authors or croak $!; } -sub svn_propget_base { - my ($p, $f) = @_; - $f .= '@BASE' if $_svn_pg_peg_revs; - return safe_qx(qw/svn propget/, $p, $f); -} - sub git_svn_each { my $sub = shift; - foreach (`git-rev-parse --symbolic --all`) { + foreach (command(qw/rev-parse --symbolic --all/)) { next unless s#^refs/remotes/##; chomp $_; next unless -f "$GIT_DIR/svn/$_/info/url"; @@ -2197,7 +1556,7 @@ sub migration_check { "$GIT_SVN_DIR\n\t(required for this version ", "($VERSION) of git-svn) does not.\n"; - foreach my $x (`git-rev-parse --symbolic --all`) { + foreach my $x (command(qw/rev-parse --symbolic --all/)) { next unless $x =~ s#^refs/remotes/##; chomp $x; next unless -f "$GIT_DIR/$x/info/url"; @@ -2302,11 +1661,7 @@ sub write_grafts { my $p = $grafts->{$c}; my %x; # real parents delete $p->{$c}; # commits are not self-reproducing... - my $pid = open my $ch, '-|'; - defined $pid or croak $!; - if (!$pid) { - exec(qw/git-cat-file commit/, $c) or croak $!; - } + my $ch = command_output_pipe(qw/cat-file commit/, $c); while (<$ch>) { if (/^parent ($sha1)/) { $x{$1} = $p->{$1} = 1; @@ -2314,7 +1669,7 @@ sub write_grafts { last unless /^\S/; } } - close $ch; # breaking the pipe + eval { command_close_pipe($ch) }; # breaking the pipe # if real parents are the only ones in the grafts, drop it next if join(' ',sort keys %$p) eq join(' ',sort keys %x); @@ -2326,7 +1681,7 @@ sub write_grafts { next if $del{$i} || $p->{$i} == 2; foreach my $j (@jp) { next if $i eq $j || $del{$j} || $p->{$j} == 2; - $mb = eval { safe_qx('git-merge-base',$i,$j) }; + $mb = eval { command('merge-base', $i, $j) }; next unless $mb; chomp $mb; next if $x{$mb}; @@ -2387,7 +1742,7 @@ sub extract_metadata { my $id = shift or return (undef, undef, undef); my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) \s([a-f\d\-]+)$/x); - if (!$rev || !$uuid || !$url) { + if (!defined $rev || !$uuid || !$url) { # some of the original repositories I made had # identifiers like this: ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/); @@ -2397,15 +1752,12 @@ sub extract_metadata { sub cmt_metadata { return extract_metadata((grep(/^git-svn-id: /, - safe_qx(qw/git-cat-file commit/, shift)))[-1]); + command(qw/cat-file commit/, shift)))[-1]); } sub get_commit_time { my $cmt = shift; - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - exec qw/git-rev-list --pretty=raw -n1/, $cmt or croak $!; - } + my $fh = command_output_pipe(qw/rev-list --pretty=raw -n1/, $cmt); while (<$fh>) { /^committer\s(?:.+) (\d+) ([\-\+]?\d+)$/ or next; my ($s, $tz) = ($1, $2); @@ -2414,7 +1766,7 @@ sub get_commit_time { } elsif ($tz =~ s/^\-//) { $s -= tz_to_s_offset($tz); } - close $fh; + eval { command_close_pipe($fh) }; return $s; } die "Can't get commit time for commit: $cmt\n"; @@ -2426,14 +1778,18 @@ sub tz_to_s_offset { return ($1 * 60) + ($tz * 3600); } -sub setup_pager { # translated to Perl from pager.c - return unless (-t *STDOUT); - my $pager = $ENV{PAGER}; - if (!defined $pager) { - $pager = 'less'; - } elsif (length $pager == 0 || $pager eq 'cat') { - return; +# adapted from pager.c +sub config_pager { + $_pager ||= $ENV{GIT_PAGER} || $ENV{PAGER}; + if (!defined $_pager) { + $_pager = 'less'; + } elsif (length $_pager == 0 || $_pager eq 'cat') { + $_pager = undef; } +} + +sub run_pager { + return unless -t *STDOUT; pipe my $rfd, my $wfd or return; defined(my $pid = fork) or croak $!; if (!$pid) { @@ -2441,8 +1797,8 @@ sub setup_pager { # translated to Perl from pager.c return; } open STDIN, '<&', $rfd or croak $!; - $ENV{LESS} ||= '-S'; - exec $pager or croak "Can't run pager: $!\n";; + $ENV{LESS} ||= 'FRSX'; + exec $_pager or croak "Can't run pager: $! ($_pager)\n"; } sub get_author_info { @@ -2509,6 +1865,12 @@ sub show_commit { } } +sub show_commit_changed_paths { + my ($c) = @_; + return unless $c->{changed}; + print "Changed paths:\n", @{$c->{changed}}; +} + sub show_commit_normal { my ($c) = @_; print '-' x72, "\nr$c->{r} | "; @@ -2518,7 +1880,8 @@ sub show_commit_normal { my $nr_line = 0; if (my $l = $c->{l}) { - while ($l->[$#$l] eq "\n" && $l->[($#$l - 1)] eq "\n") { + while ($l->[$#$l] eq "\n" && $#$l > 0 + && $l->[($#$l - 1)] eq "\n") { pop @$l; } $nr_line = scalar @$l; @@ -2530,11 +1893,15 @@ sub show_commit_normal { } else { $nr_line .= ' lines'; } - print $nr_line, "\n\n"; + print $nr_line, "\n"; + show_commit_changed_paths($c); + print "\n"; print $_ foreach @$l; } } else { - print "1 line\n\n"; + print "1 line\n"; + show_commit_changed_paths($c); + print "\n"; } foreach my $x (qw/raw diff/) { @@ -2545,160 +1912,302 @@ sub show_commit_normal { } } -sub libsvn_load { - return unless $_use_lib; - $_use_lib = eval { - require SVN::Core; - if ($SVN::Core::VERSION lt '1.1.0') { - die "Need SVN::Core 1.1.0 or better ", - "(got $SVN::Core::VERSION) ", - "Falling back to command-line svn\n"; +sub _simple_prompt { + my ($cred, $realm, $default_username, $may_save, $pool) = @_; + $may_save = undef if $_no_auth_cache; + $default_username = $_username if defined $_username; + if (defined $default_username && length $default_username) { + if (defined $realm && length $realm) { + print "Authentication realm: $realm\n"; } - require SVN::Ra; - require SVN::Delta; - push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; - my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file. - $SVN::Node::dir.$SVN::Node::unknown. - $SVN::Node::none.$SVN::Node::file. - $SVN::Node::dir.$SVN::Node::unknown; - 1; - }; + $cred->username($default_username); + } else { + _username_prompt($cred, $realm, $may_save, $pool); + } + $cred->password(_read_password("Password for '" . + $cred->username . "': ", $realm)); + $cred->may_save($may_save); + $SVN::_Core::SVN_NO_ERROR; +} + +sub _ssl_server_trust_prompt { + my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_; + $may_save = undef if $_no_auth_cache; + print "Error validating server certificate for '$realm':\n"; + if ($failures & $SVN::Auth::SSL::UNKNOWNCA) { + print " - The certificate is not issued by a trusted ", + "authority. Use the\n", + " fingerprint to validate the certificate manually!\n"; + } + if ($failures & $SVN::Auth::SSL::CNMISMATCH) { + print " - The certificate hostname does not match.\n"; + } + if ($failures & $SVN::Auth::SSL::NOTYETVALID) { + print " - The certificate is not yet valid.\n"; + } + if ($failures & $SVN::Auth::SSL::EXPIRED) { + print " - The certificate has expired.\n"; + } + if ($failures & $SVN::Auth::SSL::OTHER) { + print " - The certificate has an unknown error.\n"; + } + printf( "Certificate information:\n". + " - Hostname: %s\n". + " - Valid: from %s until %s\n". + " - Issuer: %s\n". + " - Fingerprint: %s\n", + map $cert_info->$_, qw(hostname valid_from valid_until + issuer_dname fingerprint) ); + my $choice; +prompt: + print $may_save ? + "(R)eject, accept (t)emporarily or accept (p)ermanently? " : + "(R)eject or accept (t)emporarily? "; + $choice = lc(substr(<STDIN> || 'R', 0, 1)); + if ($choice =~ /^t$/i) { + $cred->may_save(undef); + } elsif ($choice =~ /^r$/i) { + return -1; + } elsif ($may_save && $choice =~ /^p$/i) { + $cred->may_save($may_save); + } else { + goto prompt; + } + $cred->accepted_failures($failures); + $SVN::_Core::SVN_NO_ERROR; } -sub libsvn_connect { - my ($url) = @_; - my $auth = SVN::Core::auth_open([SVN::Client::get_simple_provider(), - SVN::Client::get_ssl_server_trust_file_provider(), - SVN::Client::get_username_provider()]); - my $s = eval { SVN::Ra->new(url => $url, auth => $auth) }; - return $s; +sub _ssl_client_cert_prompt { + my ($cred, $realm, $may_save, $pool) = @_; + $may_save = undef if $_no_auth_cache; + print "Client certificate filename: "; + chomp(my $filename = <STDIN>); + $cred->cert_file($filename); + $cred->may_save($may_save); + $SVN::_Core::SVN_NO_ERROR; } -sub libsvn_get_file { - my ($gui, $f, $rev) = @_; - my $p = $f; - if (length $SVN_PATH > 0) { - return unless ($p =~ s#^\Q$SVN_PATH\E/##); +sub _ssl_client_cert_pw_prompt { + my ($cred, $realm, $may_save, $pool) = @_; + $may_save = undef if $_no_auth_cache; + $cred->password(_read_password("Password: ", $realm)); + $cred->may_save($may_save); + $SVN::_Core::SVN_NO_ERROR; +} + +sub _username_prompt { + my ($cred, $realm, $may_save, $pool) = @_; + $may_save = undef if $_no_auth_cache; + if (defined $realm && length $realm) { + print "Authentication realm: $realm\n"; + } + my $username; + if (defined $_username) { + $username = $_username; + } else { + print "Username: "; + chomp($username = <STDIN>); } + $cred->username($username); + $cred->may_save($may_save); + $SVN::_Core::SVN_NO_ERROR; +} - my ($hash, $pid, $in, $out); - my $pool = SVN::Pool->new; - defined($pid = open3($in, $out, '>&STDERR', - qw/git-hash-object -w --stdin/)) or croak $!; - # redirect STDOUT for SVN 1.1.x compatibility - open my $stdout, '>&', \*STDOUT or croak $!; - open STDOUT, '>&', $in or croak $!; - my ($r, $props) = $SVN->get_file($f, $rev, \*STDOUT, $pool); - $in->flush == 0 or croak $!; - open STDOUT, '>&', $stdout or croak $!; - close $in or croak $!; - close $stdout or croak $!; - $pool->clear; - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - waitpid $pid, 0; - $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; - - my $mode = exists $props->{'svn:executable'} ? '100755' : '100644'; - if (exists $props->{'svn:special'}) { - $mode = '120000'; - my $link = `git-cat-file blob $hash`; - $link =~ s/^link // or die "svn:special file with contents: <", - $link, "> is not understood\n"; - defined($pid = open3($in, $out, '>&STDERR', - qw/git-hash-object -w --stdin/)) or croak $!; - print $in $link; - $in->flush == 0 or croak $!; - close $in or croak $!; - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - waitpid $pid, 0; - $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; +sub _read_password { + my ($prompt, $realm) = @_; + print $prompt; + require Term::ReadKey; + Term::ReadKey::ReadMode('noecho'); + my $password = ''; + while (defined(my $key = Term::ReadKey::ReadKey(0))) { + last if $key =~ /[\012\015]/; # \n\r + $password .= $key; + } + Term::ReadKey::ReadMode('restore'); + print "\n"; + $password; +} + +sub libsvn_connect { + my ($url) = @_; + SVN::_Core::svn_config_ensure($_config_dir, undef); + my ($baton, $callbacks) = SVN::Core::auth_open_helper([ + SVN::Client::get_simple_provider(), + SVN::Client::get_ssl_server_trust_file_provider(), + SVN::Client::get_simple_prompt_provider( + \&_simple_prompt, 2), + SVN::Client::get_ssl_client_cert_prompt_provider( + \&_ssl_client_cert_prompt, 2), + SVN::Client::get_ssl_client_cert_pw_prompt_provider( + \&_ssl_client_cert_pw_prompt, 2), + SVN::Client::get_username_provider(), + SVN::Client::get_ssl_server_trust_prompt_provider( + \&_ssl_server_trust_prompt), + SVN::Client::get_username_prompt_provider( + \&_username_prompt, 2), + ]); + my $config = SVN::Core::config_get_config($_config_dir); + my $ra = SVN::Ra->new(url => $url, auth => $baton, + config => $config, + pool => SVN::Pool->new, + auth_provider_callbacks => $callbacks); + $ra->{svn_path} = $url; + $ra->{repos_root} = $ra->get_repos_root; + $ra->{svn_path} =~ s#^\Q$ra->{repos_root}\E/*##; + push @repo_path_split_cache, qr/^(\Q$ra->{repos_root}\E)/; + return $ra; +} + +sub libsvn_can_do_switch { + unless (defined $_svn_can_do_switch) { + my $pool = SVN::Pool->new; + my $rep = eval { + $SVN->do_switch(1, '', 0, $SVN->{url}, + SVN::Delta::Editor->new, $pool); + }; + if ($@) { + $_svn_can_do_switch = 0; + } else { + $rep->abort_report($pool); + $_svn_can_do_switch = 1; + } + $pool->clear; } - print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!; + $_svn_can_do_switch; +} + +sub libsvn_dup_ra { + my ($ra) = @_; + SVN::Ra->new(map { $_ => $ra->{$_} } qw/config url + auth auth_provider_callbacks repos_root svn_path/); +} + +sub uri_encode { + my ($f) = @_; + $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg; + $f +} + +sub uri_decode { + my ($f) = @_; + $f =~ tr/+/ /; + $f =~ s/%([A-F0-9]{2})/chr hex($1)/ge; + $f } sub libsvn_log_entry { - my ($rev, $author, $date, $msg, $parents) = @_; + my ($rev, $author, $date, $msg, $parents, $untracked) = @_; my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) or die "Unable to parse date: $date\n"; - if (defined $_authors && ! defined $users{$author}) { + if (defined $author && length $author > 0 && + defined $_authors && ! defined $users{$author}) { die "Author: $author not defined in $_authors file\n"; } $msg = '' if ($rev == 0 && !defined $msg); - return { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S", - author => $author, msg => $msg."\n", parents => $parents || [] } + + open my $un, '>>', "$GIT_SVN_DIR/unhandled.log" or croak $!; + my $h; + print $un "r$rev\n" or croak $!; + $h = $untracked->{empty}; + foreach (sort keys %$h) { + my $act = $h->{$_} ? '+empty_dir' : '-empty_dir'; + print $un " $act: ", uri_encode($_), "\n" or croak $!; + warn "W: $act: $_\n"; + } + foreach my $t (qw/dir_prop file_prop/) { + $h = $untracked->{$t} or next; + foreach my $path (sort keys %$h) { + my $ppath = $path eq '' ? '.' : $path; + foreach my $prop (sort keys %{$h->{$path}}) { + next if $SKIP{$prop}; + my $v = $h->{$path}->{$prop}; + if (defined $v) { + print $un " +$t: ", + uri_encode($ppath), ' ', + uri_encode($prop), ' ', + uri_encode($v), "\n" + or croak $!; + } else { + print $un " -$t: ", + uri_encode($ppath), ' ', + uri_encode($prop), "\n" + or croak $!; + } + } + } + } + foreach my $t (qw/absent_file absent_directory/) { + $h = $untracked->{$t} or next; + foreach my $parent (sort keys %$h) { + foreach my $path (sort @{$h->{$parent}}) { + print $un " $t: ", + uri_encode("$parent/$path"), "\n" + or croak $!; + warn "W: $t: $parent/$path ", + "Insufficient permissions?\n"; + } + } + } + + # revprops (make this optional? it's an extra network trip...) + my $pool = SVN::Pool->new; + my $rp = $SVN->rev_proplist($rev, $pool); + foreach (sort keys %$rp) { + next if /^svn:(?:author|date|log)$/; + print $un " rev_prop: ", uri_encode($_), ' ', + uri_encode($rp->{$_}), "\n"; + } + $pool->clear; + close $un or croak $!; + + { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S", + author => $author, msg => $msg."\n", parents => $parents || [], + revprops => $rp } } sub process_rm { - my ($gui, $last_commit, $f) = @_; - $f =~ s#^\Q$SVN_PATH\E/?## or return; + my ($gui, $last_commit, $f, $q) = @_; # remove entire directories. - if (safe_qx('git-ls-tree',$last_commit,'--',$f) =~ /^040000 tree/) { - defined(my $pid = open my $ls, '-|') or croak $!; - if (!$pid) { - exec(qw/git-ls-tree -r --name-only -z/, - $last_commit,'--',$f) or croak $!; - } + if (command('ls-tree',$last_commit,'--',$f) =~ /^040000 tree/) { + my ($ls, $ctx) = command_output_pipe(qw/ls-tree + -r --name-only -z/, + $last_commit,'--',$f); local $/ = "\0"; while (<$ls>) { print $gui '0 ',0 x 40,"\t",$_ or croak $!; + print "\tD\t$_\n" unless $q; } - close $ls or croak $?; + print "\tD\t$f/\n" unless $q; + command_close_pipe($ls, $ctx); + return $SVN::Node::dir; } else { print $gui '0 ',0 x 40,"\t",$f,"\0" or croak $!; + print "\tD\t$f\n" unless $q; + return $SVN::Node::file; } } sub libsvn_fetch { my ($last_commit, $paths, $rev, $author, $date, $msg) = @_; - open my $gui, '| git-update-index -z --index-info' or croak $!; - my @amr; - foreach my $f (keys %$paths) { - my $m = $paths->{$f}->action(); - $f =~ s#^/+##; - if ($m =~ /^[DR]$/) { - print "\t$m\t$f\n" unless $_q; - process_rm($gui, $last_commit, $f); - next if $m eq 'D'; - # 'R' can be file replacements, too, right? - } - my $pool = SVN::Pool->new; - my $t = $SVN->check_path($f, $rev, $pool); - if ($t == $SVN::Node::file) { - if ($m =~ /^[AMR]$/) { - push @amr, [ $m, $f ]; - } else { - die "Unrecognized action: $m, ($f r$rev)\n"; - } - } elsif ($t == $SVN::Node::dir && $m =~ /^[AR]$/) { - my @traversed = (); - libsvn_traverse($gui, '', $f, $rev, \@traversed); - foreach (@traversed) { - push @amr, [ $m, $_ ] - } - } - $pool->clear; - } - foreach (@amr) { - print "\t$_->[0]\t$_->[1]\n" unless $_q; - libsvn_get_file($gui, $_->[1], $rev) + my $pool = SVN::Pool->new; + my $ed = SVN::Git::Fetcher->new({ c => $last_commit, q => $_q }); + my $reporter = $SVN->do_update($rev, '', 1, $ed, $pool); + my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); + my (undef, $last_rev, undef) = cmt_metadata($last_commit); + $reporter->set_path('', $last_rev, 0, @lock, $pool); + $reporter->finish_report($pool); + $pool->clear; + unless ($ed->{git_commit_ok}) { + die "SVN connection failed somewhere...\n"; } - close $gui or croak $?; - return libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]); + libsvn_log_entry($rev, $author, $date, $msg, [$last_commit], $ed); } sub svn_grab_base_rev { - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - open my $null, '>', '/dev/null' or croak $!; - open STDERR, '>&', $null or croak $!; - exec qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0" - or croak $!; - } - chomp(my $c = do { local $/; <$fh> }); - close $fh; + my $c = eval { command_oneline([qw/rev-parse --verify/, + "refs/remotes/$GIT_SVN^0"], + { STDERR => 0 }) }; if (defined $c && length $c) { my ($url, $rev, $uuid) = cmt_metadata($c); return ($rev, $c) if defined $rev; @@ -2746,36 +2255,13 @@ sub libsvn_parse_revision { "Try using the command-line svn client instead\n"; } -sub libsvn_traverse { - my ($gui, $pfx, $path, $rev, $files) = @_; - my $cwd = "$pfx/$path"; - my $pool = SVN::Pool->new; - $cwd =~ s#^/+##g; - my ($dirent, $r, $props) = $SVN->get_dir($cwd, $rev, $pool); - foreach my $d (keys %$dirent) { - my $t = $dirent->{$d}->kind; - if ($t == $SVN::Node::dir) { - libsvn_traverse($gui, $cwd, $d, $rev, $files); - } elsif ($t == $SVN::Node::file) { - my $file = "$cwd/$d"; - if (defined $files) { - push @$files, $file; - } else { - print "\tA\t$file\n" unless $_q; - libsvn_get_file($gui, $file, $rev); - } - } - } - $pool->clear; -} - sub libsvn_traverse_ignore { my ($fh, $path, $r) = @_; $path =~ s#^/+##g; my $pool = SVN::Pool->new; my ($dirent, undef, $props) = $SVN->get_dir($path, $r, $pool); my $p = $path; - $p =~ s#^\Q$SVN_PATH\E/?##; + $p =~ s#^\Q$SVN->{svn_path}\E/##; print $fh length $p ? "\n# $p\n" : "\n# /\n"; if (my $s = $props->{'svn:ignore'}) { $s =~ s/[\r\n]+/\n/g; @@ -2799,25 +2285,18 @@ sub revisions_eq { my ($path, $r0, $r1) = @_; return 1 if $r0 == $r1; my $nr = 0; - if ($_use_lib) { - # should be OK to use Pool here (r1 - r0) should be small - my $pool = SVN::Pool->new; - libsvn_get_log($SVN, "/$path", $r0, $r1, - 0, 1, 1, sub {$nr++}, $pool); - $pool->clear; - } else { - my ($url, undef) = repo_path_split($SVN_URL); - my $svn_log = svn_log_raw("$url/$path","-r$r0:$r1"); - while (next_log_entry($svn_log)) { $nr++ } - close $svn_log->{fh}; - } + # should be OK to use Pool here (r1 - r0) should be small + my $pool = SVN::Pool->new; + libsvn_get_log($SVN, [$path], $r0, $r1, + 0, 0, 1, sub {$nr++}, $pool); + $pool->clear; return 0 if ($nr > 1); return 1; } sub libsvn_find_parent_branch { my ($paths, $rev, $author, $date, $msg) = @_; - my $svn_path = '/'.$SVN_PATH; + my $svn_path = '/'.$SVN->{svn_path}; # look for a parent from another branch: my $i = $paths->{$svn_path} or return; @@ -2828,7 +2307,7 @@ sub libsvn_find_parent_branch { $branch_from =~ s#^/##; my $l_map = {}; read_url_paths_all($l_map, '', "$GIT_DIR/svn"); - my $url = $SVN->{url}; + my $url = $SVN->{repos_root}; defined $l_map->{$url} or return; my $id = $l_map->{$url}->{$branch_from}; if (!defined $id && $_follow_parent) { @@ -2850,7 +2329,7 @@ sub libsvn_find_parent_branch { $GIT_SVN = $ENV{GIT_SVN_ID} = $id; init_vars(); $SVN_URL = "$url/$branch_from"; - $SVN_LOG = $SVN = undef; + $SVN = undef; setup_git_svn(); # we can't assume SVN_URL exists at r+1: $_revision = "0:$r"; @@ -2865,9 +2344,27 @@ sub libsvn_find_parent_branch { if (revisions_eq($branch_from, $r0, $r)) { unlink $GIT_SVN_INDEX; print STDERR "Found branch parent: ($GIT_SVN) $parent\n"; - sys(qw/git-read-tree/, $parent); - return libsvn_fetch($parent, $paths, $rev, - $author, $date, $msg); + command_noisy('read-tree', $parent); + unless (libsvn_can_do_switch()) { + return _libsvn_new_tree($paths, $rev, $author, $date, + $msg, [$parent]); + } + # do_switch works with svn/trunk >= r22312, but that is not + # included with SVN 1.4.2 (the latest version at the moment), + # so we can't rely on it. + my $ra = libsvn_connect("$url/$branch_from"); + my $ed = SVN::Git::Fetcher->new({c => $parent, q => $_q }); + my $pool = SVN::Pool->new; + my $reporter = $ra->do_switch($rev, '', 1, $SVN->{url}, + $ed, $pool); + my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); + $reporter->set_path('', $r0, 0, @lock, $pool); + $reporter->finish_report($pool); + $pool->clear; + unless ($ed->{git_commit_ok}) { + die "SVN connection failed somewhere...\n"; + } + return libsvn_log_entry($rev, $author, $date, $msg, [$parent]); } print STDERR "Nope, branch point not imported or unknown\n"; return undef; @@ -2875,6 +2372,7 @@ sub libsvn_find_parent_branch { sub libsvn_get_log { my ($ra, @args) = @_; + $args[4]-- if $args[4] && ! $_follow_parent; if ($SVN::Core::VERSION le '1.2.0') { splice(@args, 3, 1); } @@ -2885,11 +2383,23 @@ sub libsvn_new_tree { if (my $log_entry = libsvn_find_parent_branch(@_)) { return $log_entry; } - my ($paths, $rev, $author, $date, $msg) = @_; - open my $gui, '| git-update-index -z --index-info' or croak $!; - libsvn_traverse($gui, '', $SVN_PATH, $rev); - close $gui or croak $?; - return libsvn_log_entry($rev, $author, $date, $msg); + my ($paths, $rev, $author, $date, $msg) = @_; # $pool is last + _libsvn_new_tree($paths, $rev, $author, $date, $msg, []); +} + +sub _libsvn_new_tree { + my ($paths, $rev, $author, $date, $msg, $parents) = @_; + my $pool = SVN::Pool->new; + my $ed = SVN::Git::Fetcher->new({q => $_q}); + my $reporter = $SVN->do_update($rev, '', 1, $ed, $pool); + my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); + $reporter->set_path('', $rev, 1, @lock, $pool); + $reporter->finish_report($pool); + $pool->clear; + unless ($ed->{git_commit_ok}) { + die "SVN connection failed somewhere...\n"; + } + libsvn_log_entry($rev, $author, $date, $msg, $parents, $ed); } sub find_graft_path_commit { @@ -2959,7 +2469,7 @@ sub libsvn_commit_cb { my $log = libsvn_log_entry($rev,$committer,$date,$msg); $log->{tree} = get_tree_from_treeish($c); my $cmt = git_commit($log, $cmt_last, $c); - my @diff = safe_qx('git-diff-tree', $cmt, $c); + my @diff = command('diff-tree', $cmt, $c); if (@diff) { print STDERR "Trees differ: $cmt $c\n", join('',@diff),"\n"; @@ -2972,13 +2482,12 @@ sub libsvn_commit_cb { sub libsvn_ls_fullurl { my $fullurl = shift; - my ($repo, $path) = repo_path_split($fullurl); - $SVN ||= libsvn_connect($repo); + my $ra = libsvn_connect($fullurl); my @ret; my $pool = SVN::Pool->new; - my ($dirent, undef, undef) = $SVN->get_dir($path, - $SVN->get_latest_revnum, $pool); - foreach my $d (keys %$dirent) { + my $r = defined $_revision ? $_revision : $ra->get_latest_revnum; + my ($dirent, undef, undef) = $ra->get_dir('', $r, $pool); + foreach my $d (sort keys %$dirent) { if ($dirent->{$d}->kind == $SVN::Node::dir) { push @ret, "$d/"; # add '/' for compat with cli svn } @@ -2998,8 +2507,9 @@ sub libsvn_skip_unknown_revs { # Wonderfully consistent library, eh? # 160013 - svn:// and file:// # 175002 - http(s):// + # 175007 - http(s):// (this repo required authorization, too...) # More codes may be discovered later... - if ($errno == 175002 || $errno == 160013) { + if ($errno == 175007 || $errno == 175002 || $errno == 160013) { return; } croak "Error from SVN, ($errno): ", $err->expanded_message,"\n"; @@ -3051,20 +2561,225 @@ sub revdb_get { sub copy_remote_ref { my $origin = $_cp_remote ? $_cp_remote : 'origin'; my $ref = "refs/remotes/$GIT_SVN"; - if (safe_qx('git-ls-remote', $origin, $ref)) { - sys(qw/git fetch/, $origin, "$ref:$ref"); - } else { + if (command('ls-remote', $origin, $ref)) { + command_noisy('fetch', $origin, "$ref:$ref"); + } elsif ($_cp_remote && !$_upgrade) { die "Unable to find remote reference: ", "refs/remotes/$GIT_SVN on $origin\n"; } } +{ + my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file. + $SVN::Node::dir.$SVN::Node::unknown. + $SVN::Node::none.$SVN::Node::file. + $SVN::Node::dir.$SVN::Node::unknown. + $SVN::Auth::SSL::CNMISMATCH. + $SVN::Auth::SSL::NOTYETVALID. + $SVN::Auth::SSL::EXPIRED. + $SVN::Auth::SSL::UNKNOWNCA. + $SVN::Auth::SSL::OTHER; +} + +package SVN::Git::Fetcher; +use vars qw/@ISA/; +use strict; +use warnings; +use Carp qw/croak/; +use IO::File qw//; +use Git qw/command command_oneline command_noisy + command_output_pipe command_input_pipe command_close_pipe/; + +# file baton members: path, mode_a, mode_b, pool, fh, blob, base +sub new { + my ($class, $git_svn) = @_; + my $self = SVN::Delta::Editor->new; + bless $self, $class; + $self->{c} = $git_svn->{c} if exists $git_svn->{c}; + $self->{q} = $git_svn->{q}; + $self->{empty} = {}; + $self->{dir_prop} = {}; + $self->{file_prop} = {}; + $self->{absent_dir} = {}; + $self->{absent_file} = {}; + ($self->{gui}, $self->{ctx}) = command_input_pipe( + qw/update-index -z --index-info/); + require Digest::MD5; + $self; +} + +sub open_root { + { path => '' }; +} + +sub open_directory { + my ($self, $path, $pb, $rev) = @_; + { path => $path }; +} + +sub delete_entry { + my ($self, $path, $rev, $pb) = @_; + my $t = process_rm($self->{gui}, $self->{c}, $path, $self->{q}); + $self->{empty}->{$path} = 0 if $t == $SVN::Node::dir; + undef; +} + +sub open_file { + my ($self, $path, $pb, $rev) = @_; + my ($mode, $blob) = (command('ls-tree', $self->{c}, '--',$path) + =~ /^(\d{6}) blob ([a-f\d]{40})\t/); + unless (defined $mode && defined $blob) { + die "$path was not found in commit $self->{c} (r$rev)\n"; + } + { path => $path, mode_a => $mode, mode_b => $mode, blob => $blob, + pool => SVN::Pool->new, action => 'M' }; +} + +sub add_file { + my ($self, $path, $pb, $cp_path, $cp_rev) = @_; + my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); + delete $self->{empty}->{$dir}; + { path => $path, mode_a => 100644, mode_b => 100644, + pool => SVN::Pool->new, action => 'A' }; +} + +sub add_directory { + my ($self, $path, $cp_path, $cp_rev) = @_; + my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); + delete $self->{empty}->{$dir}; + $self->{empty}->{$path} = 1; + { path => $path }; +} + +sub change_dir_prop { + my ($self, $db, $prop, $value) = @_; + $self->{dir_prop}->{$db->{path}} ||= {}; + $self->{dir_prop}->{$db->{path}}->{$prop} = $value; + undef; +} + +sub absent_directory { + my ($self, $path, $pb) = @_; + $self->{absent_dir}->{$pb->{path}} ||= []; + push @{$self->{absent_dir}->{$pb->{path}}}, $path; + undef; +} + +sub absent_file { + my ($self, $path, $pb) = @_; + $self->{absent_file}->{$pb->{path}} ||= []; + push @{$self->{absent_file}->{$pb->{path}}}, $path; + undef; +} + +sub change_file_prop { + my ($self, $fb, $prop, $value) = @_; + if ($prop eq 'svn:executable') { + if ($fb->{mode_b} != 120000) { + $fb->{mode_b} = defined $value ? 100755 : 100644; + } + } elsif ($prop eq 'svn:special') { + $fb->{mode_b} = defined $value ? 120000 : 100644; + } else { + $self->{file_prop}->{$fb->{path}} ||= {}; + $self->{file_prop}->{$fb->{path}}->{$prop} = $value; + } + undef; +} + +sub apply_textdelta { + my ($self, $fb, $exp) = @_; + my $fh = IO::File->new_tmpfile; + $fh->autoflush(1); + # $fh gets auto-closed() by SVN::TxDelta::apply(), + # (but $base does not,) so dup() it for reading in close_file + open my $dup, '<&', $fh or croak $!; + my $base = IO::File->new_tmpfile; + $base->autoflush(1); + if ($fb->{blob}) { + defined (my $pid = fork) or croak $!; + if (!$pid) { + open STDOUT, '>&', $base or croak $!; + print STDOUT 'link ' if ($fb->{mode_a} == 120000); + exec qw/git-cat-file blob/, $fb->{blob} or croak $!; + } + waitpid $pid, 0; + croak $? if $?; + + if (defined $exp) { + seek $base, 0, 0 or croak $!; + my $md5 = Digest::MD5->new; + $md5->addfile($base); + my $got = $md5->hexdigest; + die "Checksum mismatch: $fb->{path} $fb->{blob}\n", + "expected: $exp\n", + " got: $got\n" if ($got ne $exp); + } + } + seek $base, 0, 0 or croak $!; + $fb->{fh} = $dup; + $fb->{base} = $base; + [ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ]; +} + +sub close_file { + my ($self, $fb, $exp) = @_; + my $hash; + my $path = $fb->{path}; + if (my $fh = $fb->{fh}) { + seek($fh, 0, 0) or croak $!; + my $md5 = Digest::MD5->new; + $md5->addfile($fh); + my $got = $md5->hexdigest; + die "Checksum mismatch: $path\n", + "expected: $exp\n got: $got\n" if ($got ne $exp); + seek($fh, 0, 0) or croak $!; + if ($fb->{mode_b} == 120000) { + read($fh, my $buf, 5) == 5 or croak $!; + $buf eq 'link ' or die "$path has mode 120000", + "but is not a link\n"; + } + defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n"; + if (!$pid) { + open STDIN, '<&', $fh or croak $!; + exec qw/git-hash-object -w --stdin/ or croak $!; + } + chomp($hash = do { local $/; <$out> }); + close $out or croak $!; + close $fh or croak $!; + $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n"; + close $fb->{base} or croak $!; + } else { + $hash = $fb->{blob} or die "no blob information\n"; + } + $fb->{pool}->clear; + my $gui = $self->{gui}; + print $gui "$fb->{mode_b} $hash\t$path\0" or croak $!; + print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $self->{q}; + undef; +} + +sub abort_edit { + my $self = shift; + eval { command_close_pipe($self->{gui}, $self->{ctx}) }; + $self->SUPER::abort_edit(@_); +} + +sub close_edit { + my $self = shift; + command_close_pipe($self->{gui}, $self->{ctx}); + $self->{git_commit_ok} = 1; + $self->SUPER::close_edit(@_); +} + package SVN::Git::Editor; use vars qw/@ISA/; use strict; use warnings; use Carp qw/croak/; use IO::File; +use Git qw/command command_oneline command_noisy + command_output_pipe command_input_pipe command_close_pipe/; sub new { my $class = shift; @@ -3087,8 +2802,7 @@ sub split_path { } sub repo_path { - (defined $_[1] && length $_[1]) ? "$_[0]->{svn_path}/$_[1]" - : $_[0]->{svn_path} + (defined $_[1] && length $_[1]) ? $_[1] : '' } sub url_path { @@ -3115,24 +2829,21 @@ sub rmdirs { delete $rm->{''}; # we never delete the url we're tracking return unless %$rm; - defined(my $pid = open my $fh,'-|') or croak $!; - if (!$pid) { - exec qw/git-ls-tree --name-only -r -z/, $self->{c} or croak $!; - } + my ($fh, $ctx) = command_output_pipe( + qw/ls-tree --name-only -r -z/, $self->{c}); local $/ = "\0"; - my @svn_path = split m#/#, $self->{svn_path}; while (<$fh>) { chomp; - my @dn = (@svn_path, (split m#/#, $_)); + my @dn = split m#/#, $_; while (pop @dn) { delete $rm->{join '/', @dn}; } unless (%$rm) { - close $fh; + eval { command_close_pipe($fh) }; return; } } - close $fh; + command_close_pipe($fh, $ctx); my ($r, $p, $bat) = ($self->{r}, $self->{pool}, $self->{bat}); foreach my $d (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$rm) { @@ -3270,9 +2981,11 @@ sub chg_file { seek $fh, 0, 0 or croak $!; my $exp = $md5->hexdigest; - my $atd = $self->apply_textdelta($fbat, undef, $self->{pool}); - my $got = SVN::TxDelta::send_stream($fh, @$atd, $self->{pool}); + my $pool = SVN::Pool->new; + my $atd = $self->apply_textdelta($fbat, undef, $pool); + my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool); die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp); + $pool->clear; close $fh or croak $!; } @@ -3305,13 +3018,7 @@ __END__ Data structures: -$svn_log hashref (as returned by svn_log_raw) -{ - fh => file handle of the log file, - state => state of the log file parser (sep/msg/rev/msg_start...) -} - -$log_msg hashref as returned by next_log_entry($svn_log) +$log_msg hashref as returned by libsvn_log_entry() { msg => 'whitespace-formatted log entry ', # trailing newline is preserved @@ -3320,7 +3027,6 @@ $log_msg hashref as returned by next_log_entry($svn_log) author => 'committer name' }; - @mods = array of diff-index line hashes, each element represents one line of diff-index output diff --git a/git-svnimport.perl b/git-svnimport.perl index 26dc454795..3af8c7e110 100755 --- a/git-svnimport.perl +++ b/git-svnimport.perl @@ -31,25 +31,29 @@ $SIG{'PIPE'}="IGNORE"; $ENV{'TZ'}="UTC"; our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T, - $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D); + $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D,$opt_S,$opt_F, + $opt_P,$opt_R); sub usage() { print STDERR <<END; Usage: ${\basename $0} # fetch/update GIT from SVN - [-o branch-for-HEAD] [-h] [-v] [-l max_rev] + [-o branch-for-HEAD] [-h] [-v] [-l max_rev] [-R repack_each_revs] [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname] [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg] - [-m] [-M regex] [-A author_file] [SVN_URL] + [-m] [-M regex] [-A author_file] [-S] [-F] [-P project_name] [SVN_URL] END exit(1); } -getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage(); +getopts("A:b:C:dDFhiI:l:mM:o:rs:t:T:SP:R:uv") or usage(); usage if $opt_h; my $tag_name = $opt_t || "tags"; my $trunk_name = $opt_T || "trunk"; my $branch_name = $opt_b || "branches"; +my $project_name = $opt_P || ""; +$project_name = "/" . $project_name if ($project_name); +my $repack_after = $opt_R || 1000; @ARGV == 1 or @ARGV == 2 or usage(); @@ -144,6 +148,7 @@ sub file { print "... $rev $path ...\n" if $opt_v; my (undef, $properties); my $pool = SVN::Pool->new(); + $path =~ s#^/*##; eval { (undef, $properties) = $self->{'svn'}->get_file($path,$rev,$fh,$pool); }; $pool->clear; @@ -179,6 +184,7 @@ sub ignore { my($self,$path,$rev) = @_; print "... $rev $path ...\n" if $opt_v; + $path =~ s#^/*##; my (undef,undef,$properties) = $self->{'svn'}->get_dir($path,$rev,undef); if (exists $properties->{'svn:ignore'}) { @@ -193,6 +199,14 @@ sub ignore { } } +sub dir_list { + my($self,$path,$rev) = @_; + $path =~ s#^/*##; + my ($dirents,undef,$properties) + = $self->{'svn'}->get_dir($path,$rev,undef); + return $dirents; +} + package main; use URI; @@ -271,7 +285,7 @@ my $last_rev = ""; my $last_branch; my $current_rev = $opt_s || 1; unless(-d $git_dir) { - system("git-init-db"); + system("git-init"); die "Cannot init the GIT db at $git_tree: $?\n" if $?; system("git-read-tree"); die "Cannot init an empty tree: $?\n" if $?; @@ -342,35 +356,17 @@ if ($opt_A) { open BRANCHES,">>", "$git_dir/svn2git"; -sub node_kind($$$) { - my ($branch, $path, $revision) = @_; +sub node_kind($$) { + my ($svnpath, $revision) = @_; my $pool=SVN::Pool->new; - my $kind = $svn->{'svn'}->check_path(revert_split_path($branch,$path),$revision,$pool); + $svnpath =~ s#^/*##; + my $kind = $svn->{'svn'}->check_path($svnpath,$revision,$pool); $pool->clear; return $kind; } -sub revert_split_path($$) { - my($branch,$path) = @_; - - my $svnpath; - $path = "" if $path eq "/"; # this should not happen, but ... - if($branch eq "/") { - $svnpath = "$trunk_name/$path"; - } elsif($branch =~ m#^/#) { - $svnpath = "$tag_name$branch/$path"; - } else { - $svnpath = "$branch_name/$branch/$path"; - } - - $svnpath =~ s#/+$##; - return $svnpath; -} - sub get_file($$$) { - my($rev,$branch,$path) = @_; - - my $svnpath = revert_split_path($branch,$path); + my($svnpath,$rev,$path) = @_; # now get it my ($name,$mode); @@ -413,10 +409,9 @@ sub get_file($$$) { } sub get_ignore($$$$$) { - my($new,$old,$rev,$branch,$path) = @_; + my($new,$old,$rev,$path,$svnpath) = @_; return unless $opt_I; - my $svnpath = revert_split_path($branch,$path); my $name = $svn->ignore("$svnpath",$rev); if ($path eq '/') { $path = $opt_I; @@ -435,11 +430,25 @@ sub get_ignore($$$$$) { close $F; unlink $name; push(@$new,['0644',$sha,$path]); - } else { + } elsif (defined $old) { push(@$old,$path); } } +sub project_path($$) +{ + my ($path, $project) = @_; + + $path = "/".$path unless ($path =~ m#^\/#) ; + return $1 if ($path =~ m#^$project\/(.*)$#); + + $path =~ s#\.#\\\.#g; + $path =~ s#\+#\\\+#g; + return "/" if ($project =~ m#^$path.*$#); + + return undef; +} + sub split_path($$) { my($rev,$path) = @_; my $branch; @@ -459,7 +468,11 @@ sub split_path($$) { print STDERR "$rev: Unrecognized path: $path\n" unless (defined $no_error{$path}); return () } - $path = "/" if $path eq ""; + if ($path eq "") { + $path = "/"; + } elsif ($project_name) { + $path = project_path($path, $project_name); + } return ($branch,$path); } @@ -480,6 +493,27 @@ sub branch_rev($$) { return $therev; } +sub expand_svndir($$$); + +sub expand_svndir($$$) +{ + my ($svnpath, $rev, $path) = @_; + my @list; + get_ignore(\@list, undef, $rev, $path, $svnpath); + my $dirents = $svn->dir_list($svnpath, $rev); + foreach my $p(keys %$dirents) { + my $kind = node_kind($svnpath.'/'.$p, $rev); + if ($kind eq $SVN::Node::file) { + my $f = get_file($svnpath.'/'.$p, $rev, $path.'/'.$p); + push(@list, $f) if $f; + } elsif ($kind eq $SVN::Node::dir) { + push(@list, + expand_svndir($svnpath.'/'.$p, $rev, $path.'/'.$p)); + } + } + return @list; +} + sub copy_path($$$$$$$$) { # Somebody copied a whole subdirectory. # We need to find the index entries from the old version which the @@ -488,8 +522,11 @@ sub copy_path($$$$$$$$) { my($newrev,$newbranch,$path,$oldpath,$rev,$node_kind,$new,$parents) = @_; my($srcbranch,$srcpath) = split_path($rev,$oldpath); - unless(defined $srcbranch) { - print "Path not found when copying from $oldpath @ $rev\n"; + unless(defined $srcbranch && defined $srcpath) { + print "Path not found when copying from $oldpath @ $rev.\n". + "Will try to copy from original SVN location...\n" + if $opt_v; + push (@$new, expand_svndir($oldpath, $rev, $path)); return; } my $therev = branch_rev($srcbranch, $rev); @@ -503,7 +540,7 @@ sub copy_path($$$$$$$$) { } print "$newrev:$newbranch:$path: copying from $srcbranch:$srcpath @ $rev\n" if $opt_v; if ($node_kind eq $SVN::Node::dir) { - $srcpath =~ s#/*$#/#; + $srcpath =~ s#/*$#/#; } my $pid = open my $f,'-|'; @@ -531,21 +568,34 @@ sub copy_path($$$$$$$$) { sub commit { my($branch, $changed_paths, $revision, $author, $date, $message) = @_; - my($author_name,$author_email,$dest); + my($committer_name,$committer_email,$dest); + my($author_name,$author_email); my(@old,@new,@parents); if (not defined $author or $author eq "") { - $author_name = $author_email = "unknown"; + $committer_name = $committer_email = "unknown"; } elsif (defined $users_file) { die "User $author is not listed in $users_file\n" unless exists $users{$author}; - ($author_name,$author_email) = @{$users{$author}}; + ($committer_name,$committer_email) = @{$users{$author}}; } elsif ($author =~ /^(.*?)\s+<(.*)>$/) { - ($author_name, $author_email) = ($1, $2); + ($committer_name, $committer_email) = ($1, $2); } else { $author =~ s/^<(.*)>$/$1/; - $author_name = $author_email = $author; + $committer_name = $committer_email = $author; + } + + if ($opt_F && $message =~ /From:\s+(.*?)\s+<(.*)>\s*\n/) { + ($author_name, $author_email) = ($1, $2); + print "Author from From: $1 <$2>\n" if ($opt_v);; + } elsif ($opt_S && $message =~ /Signed-off-by:\s+(.*?)\s+<(.*)>\s*\n/) { + ($author_name, $author_email) = ($1, $2); + print "Author from Signed-off-by: $1 <$2>\n" if ($opt_v);; + } else { + $author_name = $committer_name; + $author_email = $committer_email; } + $date = pdate($date); my $tag; @@ -569,10 +619,12 @@ sub commit { if(defined $oldpath) { my $p; ($parent,$p) = split_path($revision,$oldpath); - if($parent eq "/") { - $parent = $opt_o; - } else { - $parent =~ s#^/##; # if it's a tag + if(defined $parent) { + if($parent eq "/") { + $parent = $opt_o; + } else { + $parent =~ s#^/##; # if it's a tag + } } } else { $parent = undef; @@ -638,9 +690,10 @@ sub commit { push(@old,$path); # remove any old stuff } if(($action->[0] eq "A") || ($action->[0] eq "R")) { - my $node_kind = node_kind($branch,$path,$revision); + my $node_kind = node_kind($action->[3], $revision); if ($node_kind eq $SVN::Node::file) { - my $f = get_file($revision,$branch,$path); + my $f = get_file($action->[3], + $revision, $path); if ($f) { push(@new,$f) if $f; } else { @@ -655,19 +708,20 @@ sub commit { \@new, \@parents); } else { get_ignore(\@new, \@old, $revision, - $branch, $path); + $path, $action->[3]); } } } elsif ($action->[0] eq "D") { push(@old,$path); } elsif ($action->[0] eq "M") { - my $node_kind = node_kind($branch,$path,$revision); + my $node_kind = node_kind($action->[3], $revision); if ($node_kind eq $SVN::Node::file) { - my $f = get_file($revision,$branch,$path); + my $f = get_file($action->[3], + $revision, $path); push(@new,$f) if $f; } elsif ($node_kind eq $SVN::Node::dir) { get_ignore(\@new, \@old, $revision, - $branch,$path); + $path, $action->[3]); } } else { die "$revision: unknown action '".$action->[0]."' for $path\n"; @@ -772,8 +826,8 @@ sub commit { "GIT_AUTHOR_NAME=$author_name", "GIT_AUTHOR_EMAIL=$author_email", "GIT_AUTHOR_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)), - "GIT_COMMITTER_NAME=$author_name", - "GIT_COMMITTER_EMAIL=$author_email", + "GIT_COMMITTER_NAME=$committer_name", + "GIT_COMMITTER_EMAIL=$committer_email", "GIT_COMMITTER_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)), "git-commit-tree", $tree,@par); die "Cannot exec git-commit-tree: $!\n"; @@ -825,7 +879,7 @@ sub commit { print $out ("object $cid\n". "type commit\n". "tag $dest\n". - "tagger $author_name <$author_email>\n") and + "tagger $committer_name <$committer_email> 0 +0000\n") and close($out) or die "Cannot create tag object $dest: $!\n"; @@ -870,6 +924,7 @@ sub commit_all { while(my($path,$action) = each %$changed_paths) { ($branch,$path) = split_path($revision,$path); next if not defined $branch; + next if not defined $path; $done{$branch}{$path} = $action; } while(($branch,$changed_paths) = each %done) { @@ -885,11 +940,27 @@ if ($opt_l < $current_rev) { exit; } -print "Fetching from $current_rev to $opt_l ...\n" if $opt_v; +print "Processing from $current_rev to $opt_l ...\n" if $opt_v; + +my $from_rev; +my $to_rev = $current_rev - 1; -my $pool=SVN::Pool->new; -$svn->{'svn'}->get_log("/",$current_rev,$opt_l,0,1,1,\&commit_all,$pool); -$pool->clear; +while ($to_rev < $opt_l) { + $from_rev = $to_rev + 1; + $to_rev = $from_rev + $repack_after; + $to_rev = $opt_l if $opt_l < $to_rev; + print "Fetching from $from_rev to $to_rev ...\n" if $opt_v; + my $pool=SVN::Pool->new; + $svn->{'svn'}->get_log("/",$from_rev,$to_rev,0,1,1,\&commit_all,$pool); + $pool->clear; + my $pid = fork(); + die "Fork: $!\n" unless defined $pid; + unless($pid) { + exec("git-repack", "-d") + or die "Cannot repack: $!\n"; + } + waitpid($pid, 0); +} unlink($git_index); diff --git a/git-tag.sh b/git-tag.sh index a0afa25821..ecb9100e4b 100755 --- a/git-tag.sh +++ b/git-tag.sh @@ -1,16 +1,18 @@ #!/bin/sh # Copyright (c) 2005 Linus Torvalds -USAGE='-l [<pattern>] | [-a | -s | -u <key-id>] [-f | -d] [-m <msg>] <tagname> [<head>]' +USAGE='-l [<pattern>] | [-a | -s | -u <key-id>] [-f | -d | -v] [-m <msg>] <tagname> [<head>]' SUBDIRECTORY_OK='Yes' . git-sh-setup +message_given= annotate= signed= force= message= username= list= +verify= while case "$#" in 0) break ;; esac do case "$1" in @@ -37,6 +39,21 @@ do annotate=1 shift message="$1" + if test "$#" = "0"; then + die "error: option -m needs an argument" + else + message_given=1 + fi + ;; + -F) + annotate=1 + shift + if test "$#" = "0"; then + die "error: option -F needs an argument" + else + message="$(cat "$1")" + message_given=1 + fi ;; -u) annotate=1 @@ -47,8 +64,18 @@ do -d) shift tag_name="$1" - rm "$GIT_DIR/refs/tags/$tag_name" && \ - echo "Deleted tag $tag_name." + tag=$(git-show-ref --verify --hash -- "refs/tags/$tag_name") || + die "Seriously, what tag are you talking about?" + git-update-ref -m 'tag: delete' -d "refs/tags/$tag_name" "$tag" && + echo "Deleted tag $tag_name." + exit $? + ;; + -v) + shift + tag_name="$1" + tag=$(git-show-ref --verify --hash -- "refs/tags/$tag_name") || + die "Seriously, what tag are you talking about?" + git-verify-tag -v "$tag" exit $? ;; -*) @@ -63,8 +90,11 @@ done name="$1" [ "$name" ] || usage -if [ -e "$GIT_DIR/refs/tags/$name" -a -z "$force" ]; then - die "tag '$name' already exists" +prev=0000000000000000000000000000000000000000 +if git-show-ref --verify --quiet -- "refs/tags/$name" +then + test -n "$force" || die "tag '$name' already exists" + prev=`git rev-parse "refs/tags/$name"` fi shift git-check-ref-format "tags/$name" || @@ -78,7 +108,7 @@ tagger=$(git-var GIT_COMMITTER_IDENT) || exit 1 trap 'rm -f "$GIT_DIR"/TAG_TMP* "$GIT_DIR"/TAG_FINALMSG "$GIT_DIR"/TAG_EDITMSG' 0 if [ "$annotate" ]; then - if [ -z "$message" ]; then + if [ -z "$message_given" ]; then ( echo "#" echo "# Write a tag message" echo "#" ) > "$GIT_DIR"/TAG_EDITMSG @@ -90,7 +120,7 @@ if [ "$annotate" ]; then grep -v '^#' <"$GIT_DIR"/TAG_EDITMSG | git-stripspace >"$GIT_DIR"/TAG_FINALMSG - [ -s "$GIT_DIR"/TAG_FINALMSG ] || { + [ -s "$GIT_DIR"/TAG_FINALMSG -o -n "$message_given" ] || { echo >&2 "No tag message?" exit 1 } @@ -107,6 +137,5 @@ if [ "$annotate" ]; then object=$(git-mktag < "$GIT_DIR"/TAG_TMP) fi -leading=`expr "refs/tags/$name" : '\(.*\)/'` && -mkdir -p "$GIT_DIR/$leading" && -echo $object > "$GIT_DIR/refs/tags/$name" +git update-ref "refs/tags/$name" "$object" "$prev" + diff --git a/git-verify-tag.sh b/git-verify-tag.sh index 36f171b302..8db7dd0b7d 100755 --- a/git-verify-tag.sh +++ b/git-verify-tag.sh @@ -34,7 +34,10 @@ t) ;; esac +trap 'rm -f "$GIT_DIR/.tmp-vtag"' 0 + git-cat-file tag "$1" >"$GIT_DIR/.tmp-vtag" || exit 1 + cat "$GIT_DIR/.tmp-vtag" | sed '/-----BEGIN PGP/Q' | gpg --verify "$GIT_DIR/.tmp-vtag" - || exit 1 @@ -1,22 +1,10 @@ -#include <stdio.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <dirent.h> -#include <unistd.h> -#include <stdlib.h> -#include <string.h> -#include <errno.h> -#include <limits.h> -#include <stdarg.h> -#include "git-compat-util.h" +#include "builtin.h" #include "exec_cmd.h" #include "cache.h" #include "quote.h" -#include "builtin.h" - const char git_usage_string[] = - "git [--version] [--exec-path[=GIT_EXEC_PATH]] [--help] COMMAND [ ARGS ]"; + "git [--version] [--exec-path[=GIT_EXEC_PATH]] [-p|--paginate] [--bare] [--git-dir=GIT_DIR] [--help] COMMAND [ARGS]"; static void prepend_to_path(const char *dir, int len) { @@ -29,13 +17,15 @@ static void prepend_to_path(const char *dir, int len) path_len = len + strlen(old_path) + 1; - path = malloc(path_len + 1); + path = xmalloc(path_len + 1); memcpy(path, dir, len); path[len] = ':'; memcpy(path + len + 1, old_path, path_len - len); setenv("PATH", path, 1); + + free(path); } static int handle_options(const char*** argv, int* argc) @@ -69,16 +59,18 @@ static int handle_options(const char*** argv, int* argc) } else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) { setup_pager(); } else if (!strcmp(cmd, "--git-dir")) { - if (*argc < 1) - return -1; - setenv("GIT_DIR", (*argv)[1], 1); + if (*argc < 2) { + fprintf(stderr, "No directory given for --git-dir.\n" ); + usage(git_usage_string); + } + setenv(GIT_DIR_ENVIRONMENT, (*argv)[1], 1); (*argv)++; (*argc)--; } else if (!strncmp(cmd, "--git-dir=", 10)) { - setenv("GIT_DIR", cmd + 10, 1); + setenv(GIT_DIR_ENVIRONMENT, cmd + 10, 1); } else if (!strcmp(cmd, "--bare")) { - static char git_dir[1024]; - setenv("GIT_DIR", getcwd(git_dir, 1024), 1); + static char git_dir[PATH_MAX+1]; + setenv(GIT_DIR_ENVIRONMENT, getcwd(git_dir, sizeof(git_dir)), 1); } else { fprintf(stderr, "Unknown option: %s\n", cmd); usage(git_usage_string); @@ -97,7 +89,7 @@ static char *alias_string; static int git_alias_config(const char *var, const char *value) { if (!strncmp(var, "alias.", 6) && !strcmp(var + 6, alias_command)) { - alias_string = strdup(value); + alias_string = xstrdup(value); } return 0; } @@ -120,7 +112,7 @@ static int split_cmdline(char *cmdline, const char ***argv) ; /* skip */ if (count >= size) { size += 16; - *argv = realloc(*argv, sizeof(char*) * size); + *argv = xrealloc(*argv, sizeof(char*) * size); } (*argv)[count++] = cmdline + dst; } else if(!quoted && (c == '\'' || c == '"')) { @@ -179,20 +171,12 @@ static int handle_alias(int *argcp, const char ***argv) if (!strcmp(alias_command, new_argv[0])) die("recursive alias: %s", alias_command); - if (getenv("GIT_TRACE")) { - int i; - fprintf(stderr, "trace: alias expansion: %s =>", - alias_command); - for (i = 0; i < count; ++i) { - fputc(' ', stderr); - sq_quote_print(stderr, new_argv[i]); - } - fputc('\n', stderr); - fflush(stderr); - } + trace_argv_printf(new_argv, count, + "trace: alias expansion: %s =>", + alias_command); - new_argv = realloc(new_argv, sizeof(char*) * - (count + *argcp + 1)); + new_argv = xrealloc(new_argv, sizeof(char*) * + (count + *argcp + 1)); /* insert after command name */ memcpy(new_argv + count, *argv + 1, sizeof(char*) * *argcp); new_argv[count+*argcp] = NULL; @@ -215,6 +199,11 @@ const char git_version_string[] = GIT_VERSION; #define RUN_SETUP (1<<0) #define USE_PAGER (1<<1) +/* + * require working tree to be present -- anything uses this needs + * RUN_SETUP for reading from the configuration file. + */ +#define NOT_BARE (1<<2) static void handle_internal_command(int argc, const char **argv, char **envp) { @@ -224,53 +213,69 @@ static void handle_internal_command(int argc, const char **argv, char **envp) int (*fn)(int, const char **, const char *); int option; } commands[] = { - { "add", cmd_add, RUN_SETUP }, + { "add", cmd_add, RUN_SETUP | NOT_BARE }, + { "annotate", cmd_annotate, }, { "apply", cmd_apply }, + { "archive", cmd_archive }, + { "blame", cmd_blame, RUN_SETUP | USE_PAGER }, + { "branch", cmd_branch, RUN_SETUP }, { "cat-file", cmd_cat_file, RUN_SETUP }, { "checkout-index", cmd_checkout_index, RUN_SETUP }, { "check-ref-format", cmd_check_ref_format }, + { "cherry", cmd_cherry, RUN_SETUP }, { "commit-tree", cmd_commit_tree, RUN_SETUP }, - { "count-objects", cmd_count_objects }, - { "diff", cmd_diff, RUN_SETUP }, + { "count-objects", cmd_count_objects, RUN_SETUP }, + { "describe", cmd_describe, RUN_SETUP }, + { "diff", cmd_diff, RUN_SETUP | USE_PAGER }, { "diff-files", cmd_diff_files, RUN_SETUP }, { "diff-index", cmd_diff_index, RUN_SETUP }, { "diff-stages", cmd_diff_stages, RUN_SETUP }, { "diff-tree", cmd_diff_tree, RUN_SETUP }, { "fmt-merge-msg", cmd_fmt_merge_msg, RUN_SETUP }, + { "for-each-ref", cmd_for_each_ref, RUN_SETUP }, { "format-patch", cmd_format_patch, RUN_SETUP }, { "get-tar-commit-id", cmd_get_tar_commit_id }, { "grep", cmd_grep, RUN_SETUP }, { "help", cmd_help }, + { "init", cmd_init_db }, { "init-db", cmd_init_db }, { "log", cmd_log, RUN_SETUP | USE_PAGER }, { "ls-files", cmd_ls_files, RUN_SETUP }, { "ls-tree", cmd_ls_tree, RUN_SETUP }, { "mailinfo", cmd_mailinfo }, { "mailsplit", cmd_mailsplit }, - { "mv", cmd_mv, RUN_SETUP }, + { "merge-file", cmd_merge_file }, + { "mv", cmd_mv, RUN_SETUP | NOT_BARE }, { "name-rev", cmd_name_rev, RUN_SETUP }, { "pack-objects", cmd_pack_objects, RUN_SETUP }, + { "pickaxe", cmd_blame, RUN_SETUP | USE_PAGER }, { "prune", cmd_prune, RUN_SETUP }, { "prune-packed", cmd_prune_packed, RUN_SETUP }, { "push", cmd_push, RUN_SETUP }, { "read-tree", cmd_read_tree, RUN_SETUP }, + { "reflog", cmd_reflog, RUN_SETUP }, { "repo-config", cmd_repo_config }, + { "rerere", cmd_rerere, RUN_SETUP }, { "rev-list", cmd_rev_list, RUN_SETUP }, { "rev-parse", cmd_rev_parse, RUN_SETUP }, - { "rm", cmd_rm, RUN_SETUP }, + { "rm", cmd_rm, RUN_SETUP | NOT_BARE }, + { "runstatus", cmd_runstatus, RUN_SETUP | NOT_BARE }, + { "shortlog", cmd_shortlog, RUN_SETUP | USE_PAGER }, { "show-branch", cmd_show_branch, RUN_SETUP }, { "show", cmd_show, RUN_SETUP | USE_PAGER }, { "stripspace", cmd_stripspace }, { "symbolic-ref", cmd_symbolic_ref, RUN_SETUP }, - { "tar-tree", cmd_tar_tree, RUN_SETUP }, + { "tar-tree", cmd_tar_tree }, { "unpack-objects", cmd_unpack_objects, RUN_SETUP }, { "update-index", cmd_update_index, RUN_SETUP }, { "update-ref", cmd_update_ref, RUN_SETUP }, - { "upload-tar", cmd_upload_tar }, + { "upload-archive", cmd_upload_archive }, { "version", cmd_version }, { "whatchanged", cmd_whatchanged, RUN_SETUP | USE_PAGER }, { "write-tree", cmd_write_tree, RUN_SETUP }, { "verify-pack", cmd_verify_pack }, + { "show-ref", cmd_show_ref, RUN_SETUP }, + { "pack-refs", cmd_pack_refs, RUN_SETUP }, }; int i; @@ -291,16 +296,9 @@ static void handle_internal_command(int argc, const char **argv, char **envp) prefix = setup_git_directory(); if (p->option & USE_PAGER) setup_pager(); - if (getenv("GIT_TRACE")) { - int i; - fprintf(stderr, "trace: built-in: git"); - for (i = 0; i < argc; ++i) { - fputc(' ', stderr); - sq_quote_print(stderr, argv[i]); - } - putc('\n', stderr); - fflush(stderr); - } + if ((p->option & NOT_BARE) && is_bare_repository()) + die("%s cannot be used in a bare git directory", cmd); + trace_argv_printf(argv, argc, "trace: built-in: git"); exit(p->fn(argc, argv, prefix)); } @@ -308,7 +306,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) int main(int argc, const char **argv, char **envp) { - const char *cmd = argv[0]; + const char *cmd = argv[0] ? argv[0] : "git-help"; char *slash = strrchr(cmd, '/'); const char *exec_path = NULL; int done_alias = 0; diff --git a/git.spec.in b/git.spec.in index 8ccd2564e7..fb95e37594 100644 --- a/git.spec.in +++ b/git.spec.in @@ -9,7 +9,7 @@ URL: http://kernel.org/pub/software/scm/git/ Source: http://kernel.org/pub/software/scm/git/%{name}-%{version}.tar.gz BuildRequires: zlib-devel >= 1.2, openssl-devel, curl-devel, expat-devel %{!?_without_docs:, xmlto, asciidoc > 6.0.3} BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root-%(%{__id_u} -n) -Requires: git-core, git-svn, git-cvs, git-arch, git-email, gitk +Requires: git-core, git-svn, git-cvs, git-arch, git-email, gitk, perl-Git %description This is a stupid (but extremely fast) directory content manager. It @@ -24,7 +24,7 @@ This is a dummy package which brings in all subpackages. %package core Summary: Core git tools Group: Development/Tools -Requires: zlib >= 1.2, rsync, rcs, curl, less, openssh-clients, python >= 2.3, expat +Requires: zlib >= 1.2, rsync, curl, less, openssh-clients, expat %description core This is a stupid (but extremely fast) directory content manager. It doesn't do a whole lot, but what it _does_ do is track directory @@ -70,6 +70,16 @@ Requires: git-core = %{version}-%{release}, tk >= 8.4 %description -n gitk Git revision tree visualiser ('gitk') +%package -n perl-Git +Summary: Perl interface to Git +Group: Development/Libraries +Requires: git-core = %{version}-%{release} +Requires: perl(:MODULE_COMPAT_%(eval "`%{__perl} -V:version`"; echo $version)) +BuildRequires: perl(Error) + +%description -n perl-Git +Perl interface to Git + %prep %setup -q @@ -80,12 +90,18 @@ make %{_smp_mflags} CFLAGS="$RPM_OPT_FLAGS" WITH_OWN_SUBPROCESS_PY=YesPlease \ %install rm -rf $RPM_BUILD_ROOT make %{_smp_mflags} DESTDIR=$RPM_BUILD_ROOT WITH_OWN_SUBPROCESS_PY=YesPlease \ - prefix=%{_prefix} mandir=%{_mandir} \ + prefix=%{_prefix} mandir=%{_mandir} INSTALLDIRS=vendor \ install %{!?_without_docs: install-doc} +find $RPM_BUILD_ROOT -type f -name .packlist -exec rm -f {} ';' +find $RPM_BUILD_ROOT -type f -name '*.bs' -empty -exec rm -f {} ';' +find $RPM_BUILD_ROOT -type f -name perllocal.pod -exec rm -f {} ';' -(find $RPM_BUILD_ROOT%{_bindir} -type f | grep -vE "arch|svn|cvs|email|gitk" | sed -e s@^$RPM_BUILD_ROOT@@) > bin-man-doc-files +(find $RPM_BUILD_ROOT%{_bindir} -type f | grep -vE "archimport|svn|cvs|email|gitk" | sed -e s@^$RPM_BUILD_ROOT@@) > bin-man-doc-files +(find $RPM_BUILD_ROOT%{perl_vendorlib} -type f | sed -e s@^$RPM_BUILD_ROOT@@) >> perl-files %if %{!?_without_docs:1}0 -(find $RPM_BUILD_ROOT%{_mandir} $RPM_BUILD_ROOT/Documentation -type f | grep -vE "arch|svn|git-cvs|email|gitk" | sed -e s@^$RPM_BUILD_ROOT@@ -e 's/$/*/' ) >> bin-man-doc-files +(find $RPM_BUILD_ROOT%{_mandir} $RPM_BUILD_ROOT/Documentation -type f | grep -vE "archimport|svn|git-cvs|email|gitk" | sed -e s@^$RPM_BUILD_ROOT@@ -e 's/$/*/' ) >> bin-man-doc-files +%else +rm -rf $RPM_BUILD_ROOT%{_mandir} %endif %clean @@ -110,10 +126,10 @@ rm -rf $RPM_BUILD_ROOT %files arch %defattr(-,root,root) -%doc Documentation/*arch*.txt -%{_bindir}/*arch* -%{!?_without_docs: %{_mandir}/man1/*arch*.1*} -%{!?_without_docs: %doc Documentation/*arch*.html } +%doc Documentation/git-archimport.txt +%{_bindir}/git-archimport +%{!?_without_docs: %{_mandir}/man1/git-archimport.1*} +%{!?_without_docs: %doc Documentation/git-archimport.html } %files email %defattr(-,root,root) @@ -129,6 +145,9 @@ rm -rf $RPM_BUILD_ROOT %{!?_without_docs: %{_mandir}/man1/*gitk*.1*} %{!?_without_docs: %doc Documentation/*gitk*.html } +%files -n perl-Git -f perl-files +%defattr(-,root,root) + %files core -f bin-man-doc-files %defattr(-,root,root) %{_datadir}/git-core/ diff --git a/gitMergeCommon.py b/gitMergeCommon.py deleted file mode 100644 index fdbf9e4778..0000000000 --- a/gitMergeCommon.py +++ /dev/null @@ -1,275 +0,0 @@ -# -# Copyright (C) 2005 Fredrik Kuivinen -# - -import sys, re, os, traceback -from sets import Set - -def die(*args): - printList(args, sys.stderr) - sys.exit(2) - -def printList(list, file=sys.stdout): - for x in list: - file.write(str(x)) - file.write(' ') - file.write('\n') - -import subprocess - -# Debugging machinery -# ------------------- - -DEBUG = 0 -functionsToDebug = Set() - -def addDebug(func): - if type(func) == str: - functionsToDebug.add(func) - else: - functionsToDebug.add(func.func_name) - -def debug(*args): - if DEBUG: - funcName = traceback.extract_stack()[-2][2] - if funcName in functionsToDebug: - printList(args) - -# Program execution -# ----------------- - -class ProgramError(Exception): - def __init__(self, progStr, error): - self.progStr = progStr - self.error = error - - def __str__(self): - return self.progStr + ': ' + self.error - -addDebug('runProgram') -def runProgram(prog, input=None, returnCode=False, env=None, pipeOutput=True): - debug('runProgram prog:', str(prog), 'input:', str(input)) - if type(prog) is str: - progStr = prog - else: - progStr = ' '.join(prog) - - try: - if pipeOutput: - stderr = subprocess.STDOUT - stdout = subprocess.PIPE - else: - stderr = None - stdout = None - pop = subprocess.Popen(prog, - shell = type(prog) is str, - stderr=stderr, - stdout=stdout, - stdin=subprocess.PIPE, - env=env) - except OSError, e: - debug('strerror:', e.strerror) - raise ProgramError(progStr, e.strerror) - - if input != None: - pop.stdin.write(input) - pop.stdin.close() - - if pipeOutput: - out = pop.stdout.read() - else: - out = '' - - code = pop.wait() - if returnCode: - ret = [out, code] - else: - ret = out - if code != 0 and not returnCode: - debug('error output:', out) - debug('prog:', prog) - raise ProgramError(progStr, out) -# debug('output:', out.replace('\0', '\n')) - return ret - -# Code for computing common ancestors -# ----------------------------------- - -currentId = 0 -def getUniqueId(): - global currentId - currentId += 1 - return currentId - -# The 'virtual' commit objects have SHAs which are integers -shaRE = re.compile('^[0-9a-f]{40}$') -def isSha(obj): - return (type(obj) is str and bool(shaRE.match(obj))) or \ - (type(obj) is int and obj >= 1) - -class Commit(object): - __slots__ = ['parents', 'firstLineMsg', 'children', '_tree', 'sha', - 'virtual'] - - def __init__(self, sha, parents, tree=None): - self.parents = parents - self.firstLineMsg = None - self.children = [] - - if tree: - tree = tree.rstrip() - assert(isSha(tree)) - self._tree = tree - - if not sha: - self.sha = getUniqueId() - self.virtual = True - self.firstLineMsg = 'virtual commit' - assert(isSha(tree)) - else: - self.virtual = False - self.sha = sha.rstrip() - assert(isSha(self.sha)) - - def tree(self): - self.getInfo() - assert(self._tree != None) - return self._tree - - def shortInfo(self): - self.getInfo() - return str(self.sha) + ' ' + self.firstLineMsg - - def __str__(self): - return self.shortInfo() - - def getInfo(self): - if self.virtual or self.firstLineMsg != None: - return - else: - info = runProgram(['git-cat-file', 'commit', self.sha]) - info = info.split('\n') - msg = False - for l in info: - if msg: - self.firstLineMsg = l - break - else: - if l.startswith('tree'): - self._tree = l[5:].rstrip() - elif l == '': - msg = True - -class Graph: - def __init__(self): - self.commits = [] - self.shaMap = {} - - def addNode(self, node): - assert(isinstance(node, Commit)) - self.shaMap[node.sha] = node - self.commits.append(node) - for p in node.parents: - p.children.append(node) - return node - - def reachableNodes(self, n1, n2): - res = {} - def traverse(n): - res[n] = True - for p in n.parents: - traverse(p) - - traverse(n1) - traverse(n2) - return res - - def fixParents(self, node): - for x in range(0, len(node.parents)): - node.parents[x] = self.shaMap[node.parents[x]] - -# addDebug('buildGraph') -def buildGraph(heads): - debug('buildGraph heads:', heads) - for h in heads: - assert(isSha(h)) - - g = Graph() - - out = runProgram(['git-rev-list', '--parents'] + heads) - for l in out.split('\n'): - if l == '': - continue - shas = l.split(' ') - - # This is a hack, we temporarily use the 'parents' attribute - # to contain a list of SHA1:s. They are later replaced by proper - # Commit objects. - c = Commit(shas[0], shas[1:]) - - g.commits.append(c) - g.shaMap[c.sha] = c - - for c in g.commits: - g.fixParents(c) - - for c in g.commits: - for p in c.parents: - p.children.append(c) - return g - -# Write the empty tree to the object database and return its SHA1 -def writeEmptyTree(): - tmpIndex = os.environ.get('GIT_DIR', '.git') + '/merge-tmp-index' - def delTmpIndex(): - try: - os.unlink(tmpIndex) - except OSError: - pass - delTmpIndex() - newEnv = os.environ.copy() - newEnv['GIT_INDEX_FILE'] = tmpIndex - res = runProgram(['git-write-tree'], env=newEnv).rstrip() - delTmpIndex() - return res - -def addCommonRoot(graph): - roots = [] - for c in graph.commits: - if len(c.parents) == 0: - roots.append(c) - - superRoot = Commit(sha=None, parents=[], tree=writeEmptyTree()) - graph.addNode(superRoot) - for r in roots: - r.parents = [superRoot] - superRoot.children = roots - return superRoot - -def getCommonAncestors(graph, commit1, commit2): - '''Find the common ancestors for commit1 and commit2''' - assert(isinstance(commit1, Commit) and isinstance(commit2, Commit)) - - def traverse(start, set): - stack = [start] - while len(stack) > 0: - el = stack.pop() - set.add(el) - for p in el.parents: - if p not in set: - stack.append(p) - h1Set = Set() - h2Set = Set() - traverse(commit1, h1Set) - traverse(commit2, h2Set) - shared = h1Set.intersection(h2Set) - - if len(shared) == 0: - shared = [addCommonRoot(graph)] - - res = Set() - - for s in shared: - if len([c for c in s.children if c in shared]) == 0: - res.add(s) - return list(res) @@ -2,7 +2,7 @@ # Tcl ignores the next line -*- tcl -*- \ exec wish "$0" -- "$@" -# Copyright (C) 2005 Paul Mackerras. All rights reserved. +# Copyright (C) 2005-2006 Paul Mackerras. All rights reserved. # This program is free software; it may be used, copied, modified # and distributed under the terms of the GNU General Public Licence, # either version 2, or (at your option) any later version. @@ -17,13 +17,12 @@ proc gitdir {} { } proc start_rev_list {view} { - global startmsecs nextupdate ncmupdate + global startmsecs nextupdate global commfd leftover tclencoding datemode global viewargs viewfiles commitidx set startmsecs [clock clicks -milliseconds] set nextupdate [expr {$startmsecs + 100}] - set ncmupdate 1 set commitidx($view) 0 set args $viewargs($view) if {$viewfiles($view) ne {}} { @@ -79,7 +78,7 @@ proc getcommitlines {fd view} { global parentlist childlist children curview hlview global vparentlist vchildlist vdisporder vcmitlisted - set stuff [read $fd] + set stuff [read $fd 500000] if {$stuff == {}} { if {![eof $fd]} return global viewname @@ -185,7 +184,7 @@ proc getcommitlines {fd view} { } if {$gotsome} { if {$view == $curview} { - layoutmore + while {[layoutmore $nextupdate]} doupdate } elseif {[info exists hlview] && $view == $hlview} { vhighlightmore } @@ -196,20 +195,13 @@ proc getcommitlines {fd view} { } proc doupdate {} { - global commfd nextupdate numcommits ncmupdate + global commfd nextupdate numcommits foreach v [array names commfd] { fileevent $commfd($v) readable {} } update set nextupdate [expr {[clock clicks -milliseconds] + 100}] - if {$numcommits < 100} { - set ncmupdate [expr {$numcommits + 1}] - } elseif {$numcommits < 10000} { - set ncmupdate [expr {$numcommits + 10}] - } else { - set ncmupdate [expr {$numcommits + 100}] - } foreach v [array names commfd] { set fd $commfd($v) fileevent $fd readable [list getcommitlines $fd $v] @@ -341,13 +333,13 @@ proc readrefs {} { set tag {} catch { set commit [exec git rev-parse "$id^0"] - if {"$commit" != "$id"} { + if {$commit != $id} { set tagids($name) $commit lappend idtags($commit) $name } } catch { - set tagcontents($name) [exec git cat-file tag "$id"] + set tagcontents($name) [exec git cat-file tag $id] } } elseif { $type == "heads" } { set headids($name) $id @@ -384,6 +376,23 @@ proc error_popup msg { show_error $w $w $msg } +proc confirm_popup msg { + global confirm_ok + set confirm_ok 0 + set w .confirm + toplevel $w + wm transient $w . + message $w.m -text $msg -justify center -aspect 400 + pack $w.m -side top -fill x -padx 20 -pady 20 + button $w.ok -text OK -command "set confirm_ok 1; destroy $w" + pack $w.ok -side left -fill x + button $w.cancel -text Cancel -command "destroy $w" + pack $w.cancel -side right -fill x + bind $w <Visibility> "grab $w; focus $w" + tkwait window $w + return $confirm_ok +} + proc makewindow {} { global canv canv2 canv3 linespc charspc ctext cflist global textfont mainfont uifont @@ -394,6 +403,7 @@ proc makewindow {} { global highlight_files gdttype global searchstring sstring global bgcolor fgcolor bglist fglist diffcolors + global headctxmenu menu .bar .bar add cascade -label "File" -menu .bar.file @@ -544,7 +554,7 @@ proc makewindow {} { pack .ctop.top.lbar.vlabel -side left -fill y global viewhlmenu selectedhlview set viewhlmenu [tk_optionMenu .ctop.top.lbar.vhl selectedhlview None] - $viewhlmenu entryconf 0 -command delvhighlight + $viewhlmenu entryconf None -command delvhighlight $viewhlmenu conf -font $uifont .ctop.top.lbar.vhl conf -font $uifont pack .ctop.top.lbar.vhl -side left -fill y @@ -711,6 +721,16 @@ proc makewindow {} { $rowctxmenu add command -label "Make patch" -command mkpatch $rowctxmenu add command -label "Create tag" -command mktag $rowctxmenu add command -label "Write commit to file" -command writecommit + $rowctxmenu add command -label "Create new branch" -command mkbranch + $rowctxmenu add command -label "Cherry-pick this commit" \ + -command cherrypick + + set headctxmenu .headctxmenu + menu $headctxmenu -tearoff 0 + $headctxmenu add command -label "Check out this branch" \ + -command cobranch + $headctxmenu add command -label "Remove this branch" \ + -command rmbranch } # mouse-2 makes all windows scan vertically, but only the one @@ -1454,7 +1474,7 @@ proc doviewmenu {m first cmd op argv} { proc allviewmenus {n op args} { global viewhlmenu - doviewmenu .bar.view 7 [list showview $n] $op $args + doviewmenu .bar.view 5 [list showview $n] $op $args doviewmenu $viewhlmenu 1 [list addvhighlight $n] $op $args } @@ -1496,7 +1516,7 @@ proc newviewok {top n} { set viewperm($n) $newviewperm($n) if {$newviewname($n) ne $viewname($n)} { set viewname($n) $newviewname($n) - doviewmenu .bar.view 7 [list showview $n] \ + doviewmenu .bar.view 5 [list showview $n] \ entryconf [list -label $viewname($n)] doviewmenu $viewhlmenu 1 [list addvhighlight $n] \ entryconf [list -label $viewname($n) -value $viewname($n)] @@ -1612,8 +1632,8 @@ proc showview {n} { set curview $n set selectedview $n - .bar.view entryconf 2 -state [expr {$n == 0? "disabled": "normal"}] - .bar.view entryconf 3 -state [expr {$n == 0? "disabled": "normal"}] + .bar.view entryconf Edit* -state [expr {$n == 0? "disabled": "normal"}] + .bar.view entryconf Delete* -state [expr {$n == 0? "disabled": "normal"}] if {![info exists viewdata($n)]} { set pending_select $selid @@ -1669,7 +1689,7 @@ proc showview {n} { show_status "Reading commits..." } if {[info exists commfd($n)]} { - layoutmore + layoutmore {} } else { finishcommits } @@ -2350,20 +2370,38 @@ proc visiblerows {} { return [list $r0 $r1] } -proc layoutmore {} { +proc layoutmore {tmax} { global rowlaidout rowoptim commitidx numcommits optim_delay global uparrowlen curview - set row $rowlaidout - set rowlaidout [layoutrows $row $commitidx($curview) 0] - set orow [expr {$rowlaidout - $uparrowlen - 1}] - if {$orow > $rowoptim} { - optimize_rows $rowoptim 0 $orow - set rowoptim $orow - } - set canshow [expr {$rowoptim - $optim_delay}] - if {$canshow > $numcommits} { - showstuff $canshow + while {1} { + if {$rowoptim - $optim_delay > $numcommits} { + showstuff [expr {$rowoptim - $optim_delay}] + } elseif {$rowlaidout - $uparrowlen - 1 > $rowoptim} { + set nr [expr {$rowlaidout - $uparrowlen - 1 - $rowoptim}] + if {$nr > 100} { + set nr 100 + } + optimize_rows $rowoptim 0 [expr {$rowoptim + $nr}] + incr rowoptim $nr + } elseif {$commitidx($curview) > $rowlaidout} { + set nr [expr {$commitidx($curview) - $rowlaidout}] + # may need to increase this threshold if uparrowlen or + # mingaplen are increased... + if {$nr > 150} { + set nr 150 + } + set row $rowlaidout + set rowlaidout [layoutrows $row [expr {$row + $nr}] 0] + if {$rowlaidout == $row} { + return 0 + } + } else { + return 0 + } + if {$tmax ne {} && [clock clicks -milliseconds] >= $tmax} { + return 1 + } } } @@ -3236,6 +3274,8 @@ proc drawtags {id x xt y1} { -font $font -tags [list tag.$id text]] if {$ntags >= 0} { $canv bind $t <1> [list showtag $tag 1] + } elseif {$nheads >= 0} { + $canv bind $t <Button-3> [list headmenu %X %Y $id $tag] } } return $xt @@ -3263,8 +3303,7 @@ proc show_status {msg} { proc finishcommits {} { global commitidx phase curview - global canv mainfont ctext maincursor textcursor - global findinprogress pending_select + global pending_select if {$commitidx($curview) > 0} { drawrest @@ -3275,6 +3314,108 @@ proc finishcommits {} { catch {unset pending_select} } +# Insert a new commit as the child of the commit on row $row. +# The new commit will be displayed on row $row and the commits +# on that row and below will move down one row. +proc insertrow {row newcmit} { + global displayorder parentlist childlist commitlisted + global commitrow curview rowidlist rowoffsets numcommits + global rowrangelist idrowranges rowlaidout rowoptim numcommits + global linesegends selectedline + + if {$row >= $numcommits} { + puts "oops, inserting new row $row but only have $numcommits rows" + return + } + set p [lindex $displayorder $row] + set displayorder [linsert $displayorder $row $newcmit] + set parentlist [linsert $parentlist $row $p] + set kids [lindex $childlist $row] + lappend kids $newcmit + lset childlist $row $kids + set childlist [linsert $childlist $row {}] + set commitlisted [linsert $commitlisted $row 1] + set l [llength $displayorder] + for {set r $row} {$r < $l} {incr r} { + set id [lindex $displayorder $r] + set commitrow($curview,$id) $r + } + + set idlist [lindex $rowidlist $row] + set offs [lindex $rowoffsets $row] + set newoffs {} + foreach x $idlist { + if {$x eq {} || ($x eq $p && [llength $kids] == 1)} { + lappend newoffs {} + } else { + lappend newoffs 0 + } + } + if {[llength $kids] == 1} { + set col [lsearch -exact $idlist $p] + lset idlist $col $newcmit + } else { + set col [llength $idlist] + lappend idlist $newcmit + lappend offs {} + lset rowoffsets $row $offs + } + set rowidlist [linsert $rowidlist $row $idlist] + set rowoffsets [linsert $rowoffsets [expr {$row+1}] $newoffs] + + set rowrangelist [linsert $rowrangelist $row {}] + set l [llength $rowrangelist] + for {set r 0} {$r < $l} {incr r} { + set ranges [lindex $rowrangelist $r] + if {$ranges ne {} && [lindex $ranges end] >= $row} { + set newranges {} + foreach x $ranges { + if {$x >= $row} { + lappend newranges [expr {$x + 1}] + } else { + lappend newranges $x + } + } + lset rowrangelist $r $newranges + } + } + if {[llength $kids] > 1} { + set rp1 [expr {$row + 1}] + set ranges [lindex $rowrangelist $rp1] + if {$ranges eq {}} { + set ranges [list $row $rp1] + } elseif {[lindex $ranges end-1] == $rp1} { + lset ranges end-1 $row + } + lset rowrangelist $rp1 $ranges + } + foreach id [array names idrowranges] { + set ranges $idrowranges($id) + if {$ranges ne {} && [lindex $ranges end] >= $row} { + set newranges {} + foreach x $ranges { + if {$x >= $row} { + lappend newranges [expr {$x + 1}] + } else { + lappend newranges $x + } + } + set idrowranges($id) $newranges + } + } + + set linesegends [linsert $linesegends $row {}] + + incr rowlaidout + incr rowoptim + incr numcommits + + if {[info exists selectedline] && $selectedline >= $row} { + incr selectedline + } + redisplay +} + # Don't change the text pane cursor if it is currently the hand cursor, # showing that we are over a sha1 ID link. proc settextcursor {c} { @@ -3307,9 +3448,7 @@ proc notbusy {what} { } proc drawrest {} { - global numcommits global startmsecs - global canvy0 numcommits linespc global rowlaidout commitidx curview global pending_select @@ -3323,6 +3462,7 @@ proc drawrest {} { } set drawmsecs [expr {[clock clicks -milliseconds] - $startmsecs}] + #global numcommits #puts "overall $drawmsecs ms for $numcommits commits" } @@ -3603,27 +3743,20 @@ proc viewnextline {dir} { # add a list of tag or branch names at position pos # returns the number of names inserted -proc appendrefs {pos l var} { - global ctext commitrow linknum curview idtags $var +proc appendrefs {pos tags var} { + global ctext commitrow linknum curview $var if {[catch {$ctext index $pos}]} { return 0 } - set tags {} - foreach id $l { - foreach tag [set $var\($id\)] { - lappend tags [concat $tag $id] - } - } - set tags [lsort -index 1 $tags] + set tags [lsort $tags] set sep {} foreach tag $tags { - set name [lindex $tag 0] - set id [lindex $tag 1] + set id [set $var\($tag\)] set lk link$linknum incr linknum $ctext insert $pos $sep - $ctext insert $pos $name $lk + $ctext insert $pos $tag $lk $ctext tag conf $lk -foreground blue if {[info exists commitrow($curview,$id)]} { $ctext tag bind $lk <1> \ @@ -3637,6 +3770,18 @@ proc appendrefs {pos l var} { return [llength $tags] } +proc taglist {ids} { + global idtags + + set tags {} + foreach id $ids { + foreach tag $idtags($id) { + lappend tags $tag + } + } + return $tags +} + # called when we have finished computing the nearby tags proc dispneartags {} { global selectedline currentid ctext anc_tags desc_tags showneartags @@ -3646,15 +3791,15 @@ proc dispneartags {} { set id $currentid $ctext conf -state normal if {[info exists desc_heads($id)]} { - if {[appendrefs branch $desc_heads($id) idheads] > 1} { + if {[appendrefs branch $desc_heads($id) headids] > 1} { $ctext insert "branch -2c" "es" } } if {[info exists anc_tags($id)]} { - appendrefs follows $anc_tags($id) idtags + appendrefs follows [taglist $anc_tags($id)] tagids } if {[info exists desc_tags($id)]} { - appendrefs precedes $desc_tags($id) idtags + appendrefs precedes [taglist $desc_tags($id)] tagids } $ctext conf -state disabled } @@ -3787,7 +3932,7 @@ proc selectline {l isnew} { $ctext mark set branch "end -1c" $ctext mark gravity branch left if {[info exists desc_heads($id)]} { - if {[appendrefs branch $desc_heads($id) idheads] > 1} { + if {[appendrefs branch $desc_heads($id) headids] > 1} { # turn "Branch" into "Branches" $ctext insert "branch -2c" "es" } @@ -3796,13 +3941,13 @@ proc selectline {l isnew} { $ctext mark set follows "end -1c" $ctext mark gravity follows left if {[info exists anc_tags($id)]} { - appendrefs follows $anc_tags($id) idtags + appendrefs follows [taglist $anc_tags($id)] tagids } $ctext insert end "\nPrecedes: " $ctext mark set precedes "end -1c" $ctext mark gravity precedes left if {[info exists desc_tags($id)]} { - appendrefs precedes $desc_tags($id) idtags + appendrefs precedes [taglist $desc_tags($id)] tagids } $ctext insert end "\n" } @@ -4295,12 +4440,27 @@ proc getblobdiffline {bdf ids} { } } +proc prevfile {} { + global difffilestart ctext + set prev [lindex $difffilestart 0] + set here [$ctext index @0,0] + foreach loc $difffilestart { + if {[$ctext compare $loc >= $here]} { + $ctext yview $prev + return + } + set prev $loc + } + $ctext yview $prev +} + proc nextfile {} { global difffilestart ctext set here [$ctext index @0,0] foreach loc $difffilestart { if {[$ctext compare $loc > $here]} { $ctext yview $loc + return } } } @@ -4463,6 +4623,7 @@ proc redisplay {} { drawvisible if {[info exists selectedline]} { selectline $selectedline 0 + allcanvs yview moveto [lindex $span 0] } } @@ -4738,9 +4899,9 @@ proc rowmenu {x y id} { } else { set state normal } - $rowctxmenu entryconfigure 0 -state $state - $rowctxmenu entryconfigure 1 -state $state - $rowctxmenu entryconfigure 2 -state $state + $rowctxmenu entryconfigure "Diff this*" -state $state + $rowctxmenu entryconfigure "Diff selected*" -state $state + $rowctxmenu entryconfigure "Make patch" -state $state set rowmenuid $id tk_popup $rowctxmenu $x $y } @@ -4930,6 +5091,7 @@ proc domktag {} { set tagids($tag) $id lappend idtags($id) $tag redrawtags $id + addedtag $id } proc redrawtags {id} { @@ -5020,10 +5182,164 @@ proc wrcomcan {} { unset wrcomtop } +proc mkbranch {} { + global rowmenuid mkbrtop + + set top .makebranch + catch {destroy $top} + toplevel $top + label $top.title -text "Create new branch" + grid $top.title - -pady 10 + label $top.id -text "ID:" + entry $top.sha1 -width 40 -relief flat + $top.sha1 insert 0 $rowmenuid + $top.sha1 conf -state readonly + grid $top.id $top.sha1 -sticky w + label $top.nlab -text "Name:" + entry $top.name -width 40 + grid $top.nlab $top.name -sticky w + frame $top.buts + button $top.buts.go -text "Create" -command [list mkbrgo $top] + button $top.buts.can -text "Cancel" -command "catch {destroy $top}" + grid $top.buts.go $top.buts.can + grid columnconfigure $top.buts 0 -weight 1 -uniform a + grid columnconfigure $top.buts 1 -weight 1 -uniform a + grid $top.buts - -pady 10 -sticky ew + focus $top.name +} + +proc mkbrgo {top} { + global headids idheads + + set name [$top.name get] + set id [$top.sha1 get] + if {$name eq {}} { + error_popup "Please specify a name for the new branch" + return + } + catch {destroy $top} + nowbusy newbranch + update + if {[catch { + exec git branch $name $id + } err]} { + notbusy newbranch + error_popup $err + } else { + addedhead $id $name + # XXX should update list of heads displayed for selected commit + notbusy newbranch + redrawtags $id + } +} + +proc cherrypick {} { + global rowmenuid curview commitrow + global mainhead desc_heads anc_tags desc_tags allparents allchildren + + if {[info exists desc_heads($rowmenuid)] + && [lsearch -exact $desc_heads($rowmenuid) $mainhead] >= 0} { + set ok [confirm_popup "Commit [string range $rowmenuid 0 7] is already\ + included in branch $mainhead -- really re-apply it?"] + if {!$ok} return + } + nowbusy cherrypick + update + set oldhead [exec git rev-parse HEAD] + # Unfortunately git-cherry-pick writes stuff to stderr even when + # no error occurs, and exec takes that as an indication of error... + if {[catch {exec sh -c "git cherry-pick -r $rowmenuid 2>&1"} err]} { + notbusy cherrypick + error_popup $err + return + } + set newhead [exec git rev-parse HEAD] + if {$newhead eq $oldhead} { + notbusy cherrypick + error_popup "No changes committed" + return + } + set allparents($newhead) $oldhead + lappend allchildren($oldhead) $newhead + set desc_heads($newhead) $mainhead + if {[info exists anc_tags($oldhead)]} { + set anc_tags($newhead) $anc_tags($oldhead) + } + set desc_tags($newhead) {} + if {[info exists commitrow($curview,$oldhead)]} { + insertrow $commitrow($curview,$oldhead) $newhead + if {$mainhead ne {}} { + movedhead $newhead $mainhead + } + redrawtags $oldhead + redrawtags $newhead + } + notbusy cherrypick +} + +# context menu for a head +proc headmenu {x y id head} { + global headmenuid headmenuhead headctxmenu + + set headmenuid $id + set headmenuhead $head + tk_popup $headctxmenu $x $y +} + +proc cobranch {} { + global headmenuid headmenuhead mainhead headids + + # check the tree is clean first?? + set oldmainhead $mainhead + nowbusy checkout + update + if {[catch { + exec git checkout $headmenuhead + } err]} { + notbusy checkout + error_popup $err + } else { + notbusy checkout + set mainhead $headmenuhead + if {[info exists headids($oldmainhead)]} { + redrawtags $headids($oldmainhead) + } + redrawtags $headmenuid + } +} + +proc rmbranch {} { + global desc_heads headmenuid headmenuhead mainhead + global headids idheads + + set head $headmenuhead + set id $headmenuid + if {$head eq $mainhead} { + error_popup "Cannot delete the currently checked-out branch" + return + } + if {$desc_heads($id) eq $head} { + # the stuff on this branch isn't on any other branch + if {![confirm_popup "The commits on branch $head aren't on any other\ + branch.\nReally delete branch $head?"]} return + } + nowbusy rmbranch + update + if {[catch {exec git branch -D $head} err]} { + notbusy rmbranch + error_popup $err + return + } + removedhead $id $head + redrawtags $id + notbusy rmbranch +} + # Stuff for finding nearby tags proc getallcommits {} { - global allcstart allcommits allcfd + global allcstart allcommits allcfd allids + set allids {} set fd [open [concat | git rev-list --all --topo-order --parents] r] set allcfd $fd fconfigure $fd -blocking 0 @@ -5107,10 +5423,52 @@ proc combine_atags {l1 l2} { return $res } +proc forward_pass {id children} { + global idtags desc_tags idheads desc_heads alldtags tagisdesc + + set dtags {} + set dheads {} + foreach child $children { + if {[info exists idtags($child)]} { + set ctags [list $child] + } else { + set ctags $desc_tags($child) + } + if {$dtags eq {}} { + set dtags $ctags + } elseif {$ctags ne $dtags} { + set dtags [combine_dtags $dtags $ctags] + } + set cheads $desc_heads($child) + if {$dheads eq {}} { + set dheads $cheads + } elseif {$cheads ne $dheads} { + set dheads [lsort -unique [concat $dheads $cheads]] + } + } + set desc_tags($id) $dtags + if {[info exists idtags($id)]} { + set adt $dtags + foreach tag $dtags { + set adt [concat $adt $alldtags($tag)] + } + set adt [lsort -unique $adt] + set alldtags($id) $adt + foreach tag $adt { + set tagisdesc($id,$tag) -1 + set tagisdesc($tag,$id) 1 + } + } + if {[info exists idheads($id)]} { + set dheads [concat $dheads $idheads($id)] + } + set desc_heads($id) $dheads +} + proc getallclines {fd} { global allparents allchildren allcommits allcstart - global desc_tags anc_tags idtags alldtags tagisdesc allids - global desc_heads idheads + global desc_tags anc_tags idtags tagisdesc allids + global idheads travindex while {[gets $fd line] >= 0} { set id [lindex $line 0] @@ -5125,43 +5483,7 @@ proc getallclines {fd} { } # compute nearest tagged descendents as we go # also compute descendent heads - set dtags {} - set dheads {} - foreach child $allchildren($id) { - if {[info exists idtags($child)]} { - set ctags [list $child] - } else { - set ctags $desc_tags($child) - } - if {$dtags eq {}} { - set dtags $ctags - } elseif {$ctags ne $dtags} { - set dtags [combine_dtags $dtags $ctags] - } - set cheads $desc_heads($child) - if {$dheads eq {}} { - set dheads $cheads - } elseif {$cheads ne $dheads} { - set dheads [lsort -unique [concat $dheads $cheads]] - } - } - set desc_tags($id) $dtags - if {[info exists idtags($id)]} { - set adt $dtags - foreach tag $dtags { - set adt [concat $adt $alldtags($tag)] - } - set adt [lsort -unique $adt] - set alldtags($id) $adt - foreach tag $adt { - set tagisdesc($id,$tag) -1 - set tagisdesc($tag,$id) 1 - } - } - if {[info exists idheads($id)]} { - lappend dheads $id - } - set desc_heads($id) $dheads + forward_pass $id $allchildren($id) if {[clock clicks -milliseconds] - $allcstart >= 50} { fileevent $fd readable {} after idle restartgetall $fd @@ -5169,7 +5491,9 @@ proc getallclines {fd} { } } if {[eof $fd]} { - after idle restartatags [llength $allids] + set travindex [llength $allids] + set allcommits "traversing" + after idle restartatags if {[catch {close $fd} err]} { error_popup "Error reading full commit graph: $err.\n\ Results may be incomplete." @@ -5178,10 +5502,11 @@ proc getallclines {fd} { } # walk backward through the tree and compute nearest tagged ancestors -proc restartatags {i} { - global allids allparents idtags anc_tags t0 +proc restartatags {} { + global allids allparents idtags anc_tags travindex set t0 [clock clicks -milliseconds] + set i $travindex while {[incr i -1] >= 0} { set id [lindex $allids $i] set atags {} @@ -5199,17 +5524,195 @@ proc restartatags {i} { } set anc_tags($id) $atags if {[clock clicks -milliseconds] - $t0 >= 50} { - after idle restartatags $i + set travindex $i + after idle restartatags return } } set allcommits "done" + set travindex 0 notbusy allcommits dispneartags } +# update the desc_tags and anc_tags arrays for a new tag just added +proc addedtag {id} { + global desc_tags anc_tags allparents allchildren allcommits + global idtags tagisdesc alldtags + + if {![info exists desc_tags($id)]} return + set adt $desc_tags($id) + foreach t $desc_tags($id) { + set adt [concat $adt $alldtags($t)] + } + set adt [lsort -unique $adt] + set alldtags($id) $adt + foreach t $adt { + set tagisdesc($id,$t) -1 + set tagisdesc($t,$id) 1 + } + if {[info exists anc_tags($id)]} { + set todo $anc_tags($id) + while {$todo ne {}} { + set do [lindex $todo 0] + set todo [lrange $todo 1 end] + if {[info exists tagisdesc($id,$do)]} continue + set tagisdesc($do,$id) -1 + set tagisdesc($id,$do) 1 + if {[info exists anc_tags($do)]} { + set todo [concat $todo $anc_tags($do)] + } + } + } + + set lastold $desc_tags($id) + set lastnew [list $id] + set nup 0 + set nch 0 + set todo $allparents($id) + while {$todo ne {}} { + set do [lindex $todo 0] + set todo [lrange $todo 1 end] + if {![info exists desc_tags($do)]} continue + if {$desc_tags($do) ne $lastold} { + set lastold $desc_tags($do) + set lastnew [combine_dtags $lastold [list $id]] + incr nch + } + if {$lastold eq $lastnew} continue + set desc_tags($do) $lastnew + incr nup + if {![info exists idtags($do)]} { + set todo [concat $todo $allparents($do)] + } + } + + if {![info exists anc_tags($id)]} return + set lastold $anc_tags($id) + set lastnew [list $id] + set nup 0 + set nch 0 + set todo $allchildren($id) + while {$todo ne {}} { + set do [lindex $todo 0] + set todo [lrange $todo 1 end] + if {![info exists anc_tags($do)]} continue + if {$anc_tags($do) ne $lastold} { + set lastold $anc_tags($do) + set lastnew [combine_atags $lastold [list $id]] + incr nch + } + if {$lastold eq $lastnew} continue + set anc_tags($do) $lastnew + incr nup + if {![info exists idtags($do)]} { + set todo [concat $todo $allchildren($do)] + } + } +} + +# update the desc_heads array for a new head just added +proc addedhead {hid head} { + global desc_heads allparents headids idheads + + set headids($head) $hid + lappend idheads($hid) $head + + set todo [list $hid] + while {$todo ne {}} { + set do [lindex $todo 0] + set todo [lrange $todo 1 end] + if {![info exists desc_heads($do)] || + [lsearch -exact $desc_heads($do) $head] >= 0} continue + set oldheads $desc_heads($do) + lappend desc_heads($do) $head + set heads $desc_heads($do) + while {1} { + set p $allparents($do) + if {[llength $p] != 1 || ![info exists desc_heads($p)] || + $desc_heads($p) ne $oldheads} break + set do $p + set desc_heads($do) $heads + } + set todo [concat $todo $p] + } +} + +# update the desc_heads array for a head just removed +proc removedhead {hid head} { + global desc_heads allparents headids idheads + + unset headids($head) + if {$idheads($hid) eq $head} { + unset idheads($hid) + } else { + set i [lsearch -exact $idheads($hid) $head] + if {$i >= 0} { + set idheads($hid) [lreplace $idheads($hid) $i $i] + } + } + + set todo [list $hid] + while {$todo ne {}} { + set do [lindex $todo 0] + set todo [lrange $todo 1 end] + if {![info exists desc_heads($do)]} continue + set i [lsearch -exact $desc_heads($do) $head] + if {$i < 0} continue + set oldheads $desc_heads($do) + set heads [lreplace $desc_heads($do) $i $i] + while {1} { + set desc_heads($do) $heads + set p $allparents($do) + if {[llength $p] != 1 || ![info exists desc_heads($p)] || + $desc_heads($p) ne $oldheads} break + set do $p + } + set todo [concat $todo $p] + } +} + +# update things for a head moved to a child of its previous location +proc movedhead {id name} { + global headids idheads + + set oldid $headids($name) + set headids($name) $id + if {$idheads($oldid) eq $name} { + unset idheads($oldid) + } else { + set i [lsearch -exact $idheads($oldid) $name] + if {$i >= 0} { + set idheads($oldid) [lreplace $idheads($oldid) $i $i] + } + } + lappend idheads($id) $name +} + +proc changedrefs {} { + global desc_heads desc_tags anc_tags allcommits allids + global allchildren allparents idtags travindex + + if {![info exists allcommits]} return + catch {unset desc_heads} + catch {unset desc_tags} + catch {unset anc_tags} + catch {unset alldtags} + catch {unset tagisdesc} + foreach id $allids { + forward_pass $id $allchildren($id) + } + if {$allcommits ne "reading"} { + set travindex [llength $allids] + if {$allcommits ne "traversing"} { + set allcommits "traversing" + after idle restartatags + } + } +} + proc rereadrefs {} { - global idtags idheads idotherrefs + global idtags idheads idotherrefs mainhead set refids [concat [array names idtags] \ [array names idheads] [array names idotherrefs]] @@ -5218,12 +5721,16 @@ proc rereadrefs {} { set ref($id) [listrefs $id] } } + set oldmainhead $mainhead readrefs + changedrefs set refids [lsort -unique [concat $refids [array names idtags] \ [array names idheads] [array names idotherrefs]]] foreach id $refids { set v [listrefs $id] - if {![info exists ref($id)] || $ref($id) != $v} { + if {![info exists ref($id)] || $ref($id) != $v || + ($id eq $oldmainhead && $id ne $mainhead) || + ($id eq $mainhead && $id ne $oldmainhead)} { redrawtags $id } } @@ -5798,8 +6305,8 @@ if {$cmdline_files ne {} || $revtreeargs ne {}} { set viewargs(1) $revtreeargs set viewperm(1) 0 addviewmenu 1 - .bar.view entryconf 2 -state normal - .bar.view entryconf 3 -state normal + .bar.view entryconf Edit* -state normal + .bar.view entryconf Delete* -state normal } if {[info exists permviews]} { diff --git a/gitweb/README b/gitweb/README index 27c6dac143..e02e90f042 100644 --- a/gitweb/README +++ b/gitweb/README @@ -1,4 +1,5 @@ GIT web Interface +================= The one working on: http://www.kernel.org/git/ @@ -6,7 +7,8 @@ The one working on: From the git version 1.4.0 gitweb is bundled with git. -How to configure gitweb for your local system: +How to configure gitweb for your local system +--------------------------------------------- You can specify the following configuration variables when building GIT: * GITWEB_SITENAME @@ -24,11 +26,54 @@ You can specify the following configuration variables when building GIT: * GITWEB_LOGO Points to the location where you put git-logo.png on your web server. * GITWEB_CONFIG - This file will be loaded using 'require'. If the environment + This file will be loaded using 'require' and can be used to override any + of the options above as well as some other options - see the top of + 'gitweb.cgi' for their full list and description. If the environment $GITWEB_CONFIG is set when gitweb.cgi is executed the file in the environment variable will be loaded instead of the file specified when gitweb.cgi was created. + +Runtime gitweb configuration +---------------------------- + +You can adjust gitweb behaviour using the file specified in `GITWEB_CONFIG` +(defaults to 'gitweb_config.perl' in the same directory as the CGI). +See the top of 'gitweb.cgi' for the list of variables and some description. +The most notable thing that is not configurable at compile time are the +optional features, stored in the '%features' variable. You can find further +description on how to reconfigure the default features setting in your +`GITWEB_CONFIG` or per-project in `project.git/config` inside 'gitweb.cgi'. + + +Webserver configuration +----------------------- + +If you want to have one URL for both gitweb and your http:// +repositories, you can configure apache like this: + +<VirtualHost www:80> + ServerName git.domain.org + DocumentRoot /pub/git + RewriteEngine on + RewriteRule ^/(.*\.git/(?!/?(info|objects|refs)).*)?$ /cgi-bin/gitweb.cgi%{REQUEST_URI} [L,PT] + SetEnv GITWEB_CONFIG /etc/gitweb.conf +</VirtualHost> + +The above configuration expects your public repositories to live under +/pub/git and will serve them as http://git.domain.org/dir-under-pub-git, +both as cloneable GIT URL and as browseable gitweb interface. +If you then start your git-daemon with --base-path=/pub/git --export-all +then you can even use the git:// URL with exactly the same path. + +Setting the environment variable GITWEB_CONFIG will tell gitweb to use +the named file (i.e. in this example /etc/gitweb.conf) as a +configuration for gitweb. Perl variables defined in here will +override the defaults given at the head of the gitweb.perl (or +gitweb.cgi). Look at the comments in that file for information on +which variables and what they mean. + + Originally written by: Kay Sievers <kay.sievers@vrfy.org> diff --git a/gitweb/git-favicon.png b/gitweb/git-favicon.png Binary files differnew file mode 100644 index 0000000000..de637c0608 --- /dev/null +++ b/gitweb/git-favicon.png diff --git a/gitweb/gitweb.css b/gitweb/gitweb.css index 9013895857..7177c6e86b 100644 --- a/gitweb/gitweb.css +++ b/gitweb/gitweb.css @@ -16,6 +16,18 @@ a:hover, a:visited, a:active { color: #880000; } +span.cntrl { + border: dashed #aaaaaa; + border-width: 1px; + padding: 0px 2px 0px 2px; + margin: 0px 2px 0px 2px; +} + +img.logo { + float: right; + border-width: 0px; +} + div.page_header { height: 25px; padding: 8px; @@ -42,6 +54,7 @@ div.page_nav a:visited { div.page_path { padding: 8px; + font-weight: bold; border: solid #d9d8d1; border-width: 0px 0px 1px; } @@ -115,13 +128,23 @@ div.list_head { font-style: italic; } +div.author_date { + padding: 8px; + border: solid #d9d8d1; + border-width: 0px 0px 1px 0px; + font-style: italic; +} + a.list { text-decoration: none; - font-weight: bold; color: #000000; } -table.tags a.list { +a.subject, a.name { + font-weight: bold; +} + +table.tags a.subject { font-weight: normal; } @@ -162,6 +185,12 @@ table.blame { border-collapse: collapse; } +table.blame td { + padding: 0px 5px; + font-size: 12px; + vertical-align: top; +} + th { padding: 2px 5px; font-size: 12px; @@ -269,25 +298,96 @@ td.mode { font-family: monospace; } +/* styling of diffs (patchsets): commitdiff and blobdiff views */ +div.diff.header, +div.diff.extended_header { + white-space: normal; +} + +div.diff.header { + font-weight: bold; + + background-color: #edece6; + + margin-top: 4px; + padding: 4px 0px 2px 0px; + border: solid #d9d8d1; + border-width: 1px 0px 1px 0px; +} + +div.diff.header a.path { + text-decoration: underline; +} + +div.diff.extended_header, +div.diff.extended_header a.path, +div.diff.extended_header a.hash { + color: #777777; +} + +div.diff.extended_header .info { + color: #b0b0b0; +} + +div.diff.extended_header { + background-color: #f6f5ee; + padding: 2px 0px 2px 0px; +} + +div.diff a.list, +div.diff a.path, +div.diff a.hash { + text-decoration: none; +} + +div.diff a.list:hover, +div.diff a.path:hover, +div.diff a.hash:hover { + text-decoration: underline; +} + +div.diff.to_file a.path, +div.diff.to_file { + color: #007000; +} + div.diff.add { color: #008800; } +div.diff.from_file a.path, +div.diff.from_file { + color: #aa0000; +} + div.diff.rem { color: #cc0000; } +div.diff.chunk_header a, div.diff.chunk_header { color: #990099; } -div.diff_info { - font-family: monospace; - color: #000099; - background-color: #edece6; - font-style: italic; +div.diff.chunk_header { + border: dotted #ffe0ff; + border-width: 1px 0px 0px 0px; + margin-top: 2px; +} + +div.diff.chunk_header span.chunk_info { + background-color: #ffeeff; } +div.diff.chunk_header span.section { + color: #aa22aa; +} + +div.diff.incomplete { + color: #cccccc; +} + + div.index_include { border: solid #d9d8d1; border-width: 0px 0px 1px; @@ -295,6 +395,8 @@ div.index_include { } div.search { + font-size: 12px; + font-weight: normal; margin: 4px 8px; position: absolute; top: 56px; diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 04282fa5e3..88af2e6380 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -15,8 +15,13 @@ use CGI::Carp qw(fatalsToBrowser); use Encode; use Fcntl ':mode'; use File::Find qw(); +use File::Basename qw(basename); binmode STDOUT, ':utf8'; +BEGIN { + CGI->compile() if $ENV{MOD_PERL}; +} + our $cgi = new CGI; our $version = "++GIT_VERSION++"; our $my_url = $cgi->url(); @@ -30,33 +35,52 @@ our $GIT = "++GIT_BINDIR++/git"; #our $projectroot = "/pub/scm"; our $projectroot = "++GITWEB_PROJECTROOT++"; -# location for temporary files needed for diffs -our $git_temp = "/tmp/gitweb"; - # target of the home link on top of all pages -our $home_link = $my_uri; +our $home_link = $my_uri || "/"; # string of the home link on top of all pages our $home_link_str = "++GITWEB_HOME_LINK_STR++"; # name of your site or organization to appear in page titles # replace this with something more descriptive for clearer bookmarks -our $site_name = "++GITWEB_SITENAME++" || $ENV{'SERVER_NAME'} || "Untitled"; +our $site_name = "++GITWEB_SITENAME++" + || ($ENV{'SERVER_NAME'} || "Untitled") . " Git"; +# filename of html text to include at top of each page +our $site_header = "++GITWEB_SITE_HEADER++"; # html text to include at home page our $home_text = "++GITWEB_HOMETEXT++"; - -# URI of default stylesheet -our $stylesheet = "++GITWEB_CSS++"; -# URI of GIT logo +# filename of html text to include at bottom of each page +our $site_footer = "++GITWEB_SITE_FOOTER++"; + +# URI of stylesheets +our @stylesheets = ("++GITWEB_CSS++"); +# URI of a single stylesheet, which can be overridden in GITWEB_CONFIG. +our $stylesheet = undef; +# URI of GIT logo (72x27 size) our $logo = "++GITWEB_LOGO++"; +# URI of GIT favicon, assumed to be image/png type +our $favicon = "++GITWEB_FAVICON++"; + +# URI and label (title) of GIT logo link +#our $logo_url = "http://www.kernel.org/pub/software/scm/git/docs/"; +#our $logo_label = "git documentation"; +our $logo_url = "http://git.or.cz/"; +our $logo_label = "git homepage"; # source of projects list our $projects_list = "++GITWEB_LIST++"; +# show repository only if this file exists +# (only effective if this variable evaluates to true) +our $export_ok = "++GITWEB_EXPORT_OK++"; + +# only allow viewing of repositories also shown on the overview page +our $strict_export = "++GITWEB_STRICT_EXPORT++"; + # list of git base URLs used for URL to where fetch project from, # i.e. full URL is "$git_base_url/$project" -our @git_base_url_list = ("++GITWEB_BASE_URL++"); +our @git_base_url_list = grep { $_ ne '' } ("++GITWEB_BASE_URL++"); # default blob_plain mimetype and default charset for text/plain blob our $default_blob_plain_mimetype = 'text/plain'; @@ -66,16 +90,198 @@ our $default_text_plain_charset = undef; # (relative to the current git repository) our $mimetypes_file = undef; +# You define site-wide feature defaults here; override them with +# $GITWEB_CONFIG as necessary. +our %feature = ( + # feature => { + # 'sub' => feature-sub (subroutine), + # 'override' => allow-override (boolean), + # 'default' => [ default options...] (array reference)} + # + # if feature is overridable (it means that allow-override has true value, + # then feature-sub will be called with default options as parameters; + # return value of feature-sub indicates if to enable specified feature + # + # use gitweb_check_feature(<feature>) to check if <feature> is enabled + + # Enable the 'blame' blob view, showing the last commit that modified + # each line in the file. This can be very CPU-intensive. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'blame'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'blame'}{'override'} = 1; + # and in project config gitweb.blame = 0|1; + 'blame' => { + 'sub' => \&feature_blame, + 'override' => 0, + 'default' => [0]}, + + # Enable the 'snapshot' link, providing a compressed tarball of any + # tree. This can potentially generate high traffic if you have large + # project. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'snapshot'}{'default'} = [undef]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'snapshot'}{'override'} = 1; + # and in project config gitweb.snapshot = none|gzip|bzip2; + 'snapshot' => { + 'sub' => \&feature_snapshot, + 'override' => 0, + # => [content-encoding, suffix, program] + 'default' => ['x-gzip', 'gz', 'gzip']}, + + # Enable text search, which will list the commits which match author, + # committer or commit text to a given string. Enabled by default. + 'search' => { + 'override' => 0, + 'default' => [1]}, + + # Enable the pickaxe search, which will list the commits that modified + # a given string in a file. This can be practical and quite faster + # alternative to 'blame', but still potentially CPU-intensive. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'pickaxe'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'pickaxe'}{'override'} = 1; + # and in project config gitweb.pickaxe = 0|1; + 'pickaxe' => { + 'sub' => \&feature_pickaxe, + 'override' => 0, + 'default' => [1]}, + + # Make gitweb use an alternative format of the URLs which can be + # more readable and natural-looking: project name is embedded + # directly in the path and the query string contains other + # auxiliary information. All gitweb installations recognize + # URL in either format; this configures in which formats gitweb + # generates links. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'pathinfo'}{'default'} = [1]; + # Project specific override is not supported. + + # Note that you will need to change the default location of CSS, + # favicon, logo and possibly other files to an absolute URL. Also, + # if gitweb.cgi serves as your indexfile, you will need to force + # $my_uri to contain the script name in your $GITWEB_CONFIG. + 'pathinfo' => { + 'override' => 0, + 'default' => [0]}, + + # Make gitweb consider projects in project root subdirectories + # to be forks of existing projects. Given project $projname.git, + # projects matching $projname/*.git will not be shown in the main + # projects list, instead a '+' mark will be added to $projname + # there and a 'forks' view will be enabled for the project, listing + # all the forks. This feature is supported only if project list + # is taken from a directory, not file. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'forks'}{'default'} = [1]; + # Project specific override is not supported. + 'forks' => { + 'override' => 0, + 'default' => [0]}, +); + +sub gitweb_check_feature { + my ($name) = @_; + return unless exists $feature{$name}; + my ($sub, $override, @defaults) = ( + $feature{$name}{'sub'}, + $feature{$name}{'override'}, + @{$feature{$name}{'default'}}); + if (!$override) { return @defaults; } + if (!defined $sub) { + warn "feature $name is not overrideable"; + return @defaults; + } + return $sub->(@defaults); +} + +sub feature_blame { + my ($val) = git_get_project_config('blame', '--bool'); + + if ($val eq 'true') { + return 1; + } elsif ($val eq 'false') { + return 0; + } + + return $_[0]; +} + +sub feature_snapshot { + my ($ctype, $suffix, $command) = @_; + + my ($val) = git_get_project_config('snapshot'); + + if ($val eq 'gzip') { + return ('x-gzip', 'gz', 'gzip'); + } elsif ($val eq 'bzip2') { + return ('x-bzip2', 'bz2', 'bzip2'); + } elsif ($val eq 'none') { + return (); + } + + return ($ctype, $suffix, $command); +} + +sub gitweb_have_snapshot { + my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); + my $have_snapshot = (defined $ctype && defined $suffix); + + return $have_snapshot; +} + +sub feature_pickaxe { + my ($val) = git_get_project_config('pickaxe', '--bool'); + + if ($val eq 'true') { + return (1); + } elsif ($val eq 'false') { + return (0); + } + + return ($_[0]); +} + +# checking HEAD file with -e is fragile if the repository was +# initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed +# and then pruned. +sub check_head_link { + my ($dir) = @_; + my $headfile = "$dir/HEAD"; + return ((-e $headfile) || + (-l $headfile && readlink($headfile) =~ /^refs\/heads\//)); +} + +sub check_export_ok { + my ($dir) = @_; + return (check_head_link($dir) && + (!$export_ok || -e "$dir/$export_ok")); +} + +# rename detection options for git-diff and git-diff-tree +# - default is '-M', with the cost proportional to +# (number of removed files) * (number of new files). +# - more costly is '-C' (or '-C', '-M'), with the cost proportional to +# (number of changed files + number of removed files) * (number of new files) +# - even more costly is '-C', '--find-copies-harder' with cost +# (number of files in the original tree) * (number of new files) +# - one might want to include '-B' option, e.g. '-B', '-M' +our @diff_opts = ('-M'); # taken from git_commit + our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -require $GITWEB_CONFIG if -e $GITWEB_CONFIG; +do $GITWEB_CONFIG if -e $GITWEB_CONFIG; # version of the core git binary our $git_version = qx($GIT --version) =~ m/git version (.*)$/ ? $1 : "unknown"; $projects_list ||= $projectroot; -if (! -d $git_temp) { - mkdir($git_temp, 0700) || die_error(undef, "Couldn't mkdir $git_temp"); -} # ====================================================================== # input validation and dispatch @@ -84,65 +290,68 @@ if (defined $action) { if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { die_error(undef, "Invalid action parameter"); } - # action which does not check rest of parameters - if ($action eq "opml") { - git_opml(); - exit; - } } -our $project = ($cgi->param('p') || $ENV{'PATH_INFO'}); +# parameters which are pathnames +our $project = $cgi->param('p'); if (defined $project) { - $project =~ s|^/||; - $project =~ s|/$||; -} -if (defined $project && $project) { - if (!validate_input($project)) { - die_error(undef, "Invalid project parameter"); - } - if (!(-d "$projectroot/$project")) { - die_error(undef, "No such directory"); - } - if (!(-e "$projectroot/$project/HEAD")) { + if (!validate_pathname($project) || + !(-d "$projectroot/$project") || + !check_head_link("$projectroot/$project") || + ($export_ok && !(-e "$projectroot/$project/$export_ok")) || + ($strict_export && !project_in_list($project))) { + undef $project; die_error(undef, "No such project"); } - $ENV{'GIT_DIR'} = "$projectroot/$project"; -} else { - git_project_list(); - exit; } our $file_name = $cgi->param('f'); if (defined $file_name) { - if (!validate_input($file_name)) { + if (!validate_pathname($file_name)) { die_error(undef, "Invalid file parameter"); } } +our $file_parent = $cgi->param('fp'); +if (defined $file_parent) { + if (!validate_pathname($file_parent)) { + die_error(undef, "Invalid file parent parameter"); + } +} + +# parameters which are refnames our $hash = $cgi->param('h'); if (defined $hash) { - if (!validate_input($hash)) { + if (!validate_refname($hash)) { die_error(undef, "Invalid hash parameter"); } } our $hash_parent = $cgi->param('hp'); if (defined $hash_parent) { - if (!validate_input($hash_parent)) { + if (!validate_refname($hash_parent)) { die_error(undef, "Invalid hash parent parameter"); } } our $hash_base = $cgi->param('hb'); if (defined $hash_base) { - if (!validate_input($hash_base)) { + if (!validate_refname($hash_base)) { die_error(undef, "Invalid hash base parameter"); } } +our $hash_parent_base = $cgi->param('hpb'); +if (defined $hash_parent_base) { + if (!validate_refname($hash_parent_base)) { + die_error(undef, "Invalid hash parent base parameter"); + } +} + +# other parameters our $page = $cgi->param('pg'); if (defined $page) { - if ($page =~ m/[^0-9]$/) { + if ($page =~ m/[^0-9]/) { die_error(undef, "Invalid page parameter"); } } @@ -152,9 +361,68 @@ if (defined $searchtext) { if ($searchtext =~ m/[^a-zA-Z0-9_\.\/\-\+\:\@ ]/) { die_error(undef, "Invalid search parameter"); } + if (length($searchtext) < 2) { + die_error(undef, "At least two characters are required for search parameter"); + } $searchtext = quotemeta $searchtext; } +our $searchtype = $cgi->param('st'); +if (defined $searchtype) { + if ($searchtype =~ m/[^a-z]/) { + die_error(undef, "Invalid searchtype parameter"); + } +} + +# now read PATH_INFO and use it as alternative to parameters +sub evaluate_path_info { + return if defined $project; + my $path_info = $ENV{"PATH_INFO"}; + return if !$path_info; + $path_info =~ s,^/+,,; + return if !$path_info; + # find which part of PATH_INFO is project + $project = $path_info; + $project =~ s,/+$,,; + while ($project && !check_head_link("$projectroot/$project")) { + $project =~ s,/*[^/]*$,,; + } + # validate project + $project = validate_pathname($project); + if (!$project || + ($export_ok && !-e "$projectroot/$project/$export_ok") || + ($strict_export && !project_in_list($project))) { + undef $project; + return; + } + # do not change any parameters if an action is given using the query string + return if $action; + $path_info =~ s,^$project/*,,; + my ($refname, $pathname) = split(/:/, $path_info, 2); + if (defined $pathname) { + # we got "project.git/branch:filename" or "project.git/branch:dir/" + # we could use git_get_type(branch:pathname), but it needs $git_dir + $pathname =~ s,^/+,,; + if (!$pathname || substr($pathname, -1) eq "/") { + $action ||= "tree"; + $pathname =~ s,/$,,; + } else { + $action ||= "blob_plain"; + } + $hash_base ||= validate_refname($refname); + $file_name ||= validate_pathname($pathname); + } elsif (defined $refname) { + # we got "project.git/branch" + $action ||= "shortlog"; + $hash ||= validate_refname($refname); + } +} +evaluate_path_info(); + +# path to the current git repository +our $git_dir; +$git_dir = "$projectroot/$project" if $project; + # dispatch my %actions = ( "blame" => \&git_blame2, @@ -165,22 +433,39 @@ my %actions = ( "commitdiff" => \&git_commitdiff, "commitdiff_plain" => \&git_commitdiff_plain, "commit" => \&git_commit, + "forks" => \&git_forks, "heads" => \&git_heads, "history" => \&git_history, "log" => \&git_log, "rss" => \&git_rss, + "atom" => \&git_atom, "search" => \&git_search, + "search_help" => \&git_search_help, "shortlog" => \&git_shortlog, "summary" => \&git_summary, "tag" => \&git_tag, "tags" => \&git_tags, "tree" => \&git_tree, + "snapshot" => \&git_snapshot, + "object" => \&git_object, + # those below don't need $project + "opml" => \&git_opml, + "project_list" => \&git_project_list, + "project_index" => \&git_project_index, ); -$action = 'summary' if (!defined($action)); +if (defined $project) { + $action ||= 'summary'; +} else { + $action ||= 'project_list'; +} if (!defined($actions{$action})) { die_error(undef, "Unknown action"); } +if ($action !~ m/^(opml|project_list|project_index)$/ && + !$project) { + die_error(undef, "Project needed"); +} $actions{$action}->(); exit; @@ -188,24 +473,52 @@ exit; ## action links sub href(%) { - my %mapping = ( - action => "a", + my %params = @_; + # default is to use -absolute url() i.e. $my_uri + my $href = $params{-full} ? $my_url : $my_uri; + + # XXX: Warning: If you touch this, check the search form for updating, + # too. + + my @mapping = ( project => "p", + action => "a", file_name => "f", + file_parent => "fp", hash => "h", hash_parent => "hp", hash_base => "hb", + hash_parent_base => "hpb", page => "pg", + order => "o", searchtext => "s", + searchtype => "st", ); + my %mapping = @mapping; - my %params = @_; - $params{"project"} ||= $project; + $params{'project'} = $project unless exists $params{'project'}; + + my ($use_pathinfo) = gitweb_check_feature('pathinfo'); + if ($use_pathinfo) { + # use PATH_INFO for project name + $href .= "/$params{'project'}" if defined $params{'project'}; + delete $params{'project'}; + + # Summary just uses the project path URL + if (defined $params{'action'} && $params{'action'} eq 'summary') { + delete $params{'action'}; + } + } - my $href = "$my_uri?"; - $href .= esc_param( join(";", - map { "$mapping{$_}=$params{$_}" } keys %params - ) ); + # now encode the parameters explicitly + my @result = (); + for (my $i = 0; $i < @mapping; $i += 2) { + my ($name, $symbol) = ($mapping[$i], $mapping[$i+1]); + if (defined $params{$name}) { + push @result, $symbol . "=" . esc_param($params{$name}); + } + } + $href .= "?" . join(';', @result) if scalar @result; return $href; } @@ -214,25 +527,58 @@ sub href(%) { ## ====================================================================== ## validation, quoting/unquoting and escaping -sub validate_input { - my $input = shift; +sub validate_pathname { + my $input = shift || return undef; - if ($input =~ m/^[0-9a-fA-F]{40}$/) { - return $input; + # no '.' or '..' as elements of path, i.e. no '.' nor '..' + # at the beginning, at the end, and between slashes. + # also this catches doubled slashes + if ($input =~ m!(^|/)(|\.|\.\.)(/|$)!) { + return undef; } - if ($input =~ m/(^|\/)(|\.|\.\.)($|\/)/) { + # no null characters + if ($input =~ m!\0!) { return undef; } - if ($input =~ m/[^a-zA-Z0-9_\x80-\xff\ \t\.\/\-\+\#\~\%]/) { + return $input; +} + +sub validate_refname { + my $input = shift || return undef; + + # textual hashes are O.K. + if ($input =~ m/^[0-9a-fA-F]{40}$/) { + return $input; + } + # it must be correct pathname + $input = validate_pathname($input) + or return undef; + # restrictions on ref name according to git-check-ref-format + if ($input =~ m!(/\.|\.\.|[\000-\040\177 ~^:?*\[]|/$)!) { return undef; } return $input; } +# very thin wrapper for decode("utf8", $str, Encode::FB_DEFAULT); +sub to_utf8 { + my $str = shift; + return decode("utf8", $str, Encode::FB_DEFAULT); +} + # quote unsafe chars, but keep the slash, even when it's not # correct, but quoted slashes look too horrible in bookmarks sub esc_param { my $str = shift; + $str =~ s/([^A-Za-z0-9\-_.~()\/:@])/sprintf("%%%02X", ord($1))/eg; + $str =~ s/\+/%2B/g; + $str =~ s/ /\+/g; + return $str; +} + +# quote unsafe chars in whole URL, so some charactrs cannot be quoted +sub esc_url { + my $str = shift; $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&=])/sprintf("%%%02X", ord($1))/eg; $str =~ s/\+/%2B/g; $str =~ s/ /\+/g; @@ -240,20 +586,93 @@ sub esc_param { } # replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html { +sub esc_html ($;%) { my $str = shift; - $str = decode("utf8", $str, Encode::FB_DEFAULT); + my %opts = @_; + + $str = to_utf8($str); $str = escapeHTML($str); - $str =~ s/\014/^L/g; # escape FORM FEED (FF) character (e.g. in COPYING file) + if ($opts{'-nbsp'}) { + $str =~ s/ / /g; + } + $str =~ s|([[:cntrl:]])|(($1 ne "\t") ? quot_cec($1) : $1)|eg; return $str; } +# quote control characters and escape filename to HTML +sub esc_path { + my $str = shift; + my %opts = @_; + + $str = to_utf8($str); + $str = escapeHTML($str); + if ($opts{'-nbsp'}) { + $str =~ s/ / /g; + } + $str =~ s|([[:cntrl:]])|quot_cec($1)|eg; + return $str; +} + +# Make control characters "printable", using character escape codes (CEC) +sub quot_cec { + my $cntrl = shift; + my %es = ( # character escape codes, aka escape sequences + "\t" => '\t', # tab (HT) + "\n" => '\n', # line feed (LF) + "\r" => '\r', # carrige return (CR) + "\f" => '\f', # form feed (FF) + "\b" => '\b', # backspace (BS) + "\a" => '\a', # alarm (bell) (BEL) + "\e" => '\e', # escape (ESC) + "\013" => '\v', # vertical tab (VT) + "\000" => '\0', # nul character (NUL) + ); + my $chr = ( (exists $es{$cntrl}) + ? $es{$cntrl} + : sprintf('\%03o', ord($cntrl)) ); + return "<span class=\"cntrl\">$chr</span>"; +} + +# Alternatively use unicode control pictures codepoints, +# Unicode "printable representation" (PR) +sub quot_upr { + my $cntrl = shift; + my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); + return "<span class=\"cntrl\">$chr</span>"; +} + # git may return quoted and escaped filenames sub unquote { my $str = shift; + + sub unq { + my $seq = shift; + my %es = ( # character escape codes, aka escape sequences + 't' => "\t", # tab (HT, TAB) + 'n' => "\n", # newline (NL) + 'r' => "\r", # return (CR) + 'f' => "\f", # form feed (FF) + 'b' => "\b", # backspace (BS) + 'a' => "\a", # alarm (bell) (BEL) + 'e' => "\e", # escape (ESC) + 'v' => "\013", # vertical tab (VT) + ); + + if ($seq =~ m/^[0-7]{1,3}$/) { + # octal char sequence + return chr(oct($seq)); + } elsif (exists $es{$seq}) { + # C escape sequence, aka character escape code + return $es{$seq} + } + # quoted ordinary character + return $seq; + } + if ($str =~ m/^"(.*)"$/) { + # needs unquoting $str = $1; - $str =~ s/\\([0-7]{1,3})/chr(oct($1))/eg; + $str =~ s/\\([^0-7]|[0-7]{1,3})/unq($1)/eg; } return $str; } @@ -272,6 +691,12 @@ sub untabify { return $line; } +sub project_in_list { + my $project = shift; + my @list = git_get_projects_list(); + return @list && scalar(grep { $_->{'path'} eq $project } @list); +} + ## ---------------------------------------------------------------------- ## HTML aware string manipulation @@ -362,7 +787,13 @@ sub mode_str { # convert file mode in octal to file type string sub file_type { - my $mode = oct shift; + my $mode = shift; + + if ($mode !~ m/^[0-7]+$/) { + return $mode; + } else { + $mode = oct $mode; + } if (S_ISDIR($mode & S_IFMT)) { return "directory"; @@ -375,22 +806,47 @@ sub file_type { } } +# convert file mode in octal to file type description string +sub file_type_long { + my $mode = shift; + + if ($mode !~ m/^[0-7]+$/) { + return $mode; + } else { + $mode = oct $mode; + } + + if (S_ISDIR($mode & S_IFMT)) { + return "directory"; + } elsif (S_ISLNK($mode)) { + return "symlink"; + } elsif (S_ISREG($mode)) { + if ($mode & S_IXUSR) { + return "executable"; + } else { + return "file"; + }; + } else { + return "unknown"; + } +} + + ## ---------------------------------------------------------------------- ## functions returning short HTML fragments, or transforming HTML fragments ## which don't beling to other sections -# format line of commit message or tag comment +# format line of commit message. sub format_log_line_html { my $line = shift; - $line = esc_html($line); - $line =~ s/ / /g; - if ($line =~ m/([0-9a-fA-F]{40})/) { + $line = esc_html($line, -nbsp=>1); + if ($line =~ m/([0-9a-fA-F]{8,40})/) { my $hash_text = $1; - if (git_get_type($hash_text) eq "commit") { - my $link = $cgi->a({-class => "text", -href => href(action=>"commit", hash=>$hash_text)}, $hash_text); - $line =~ s/$hash_text/$link/; - } + my $link = + $cgi->a({-href => href(action=>"object", hash=>$hash_text), + -class => "text"}, $hash_text); + $line =~ s/$hash_text/$link/; } return $line; } @@ -412,7 +868,8 @@ sub format_ref_marker { $name = $ref; } - $markers .= " <span class=\"$type\">" . esc_html($name) . "</span>"; + $markers .= " <span class=\"$type\" title=\"$ref\">" . + esc_html($name) . "</span>"; } } @@ -429,33 +886,84 @@ sub format_subject_html { $extra = '' unless defined($extra); if (length($short) < length($long)) { - return $cgi->a({-href => $href, -class => "list", - -title => $long}, + return $cgi->a({-href => $href, -class => "list subject", + -title => to_utf8($long)}, esc_html($short) . $extra); } else { - return $cgi->a({-href => $href, -class => "list"}, + return $cgi->a({-href => $href, -class => "list subject"}, esc_html($long) . $extra); } } +# format patch (diff) line (rather not to be used for diff headers) +sub format_diff_line { + my $line = shift; + my ($from, $to) = @_; + my $char = substr($line, 0, 1); + my $diff_class = ""; + + chomp $line; + + if ($char eq '+') { + $diff_class = " add"; + } elsif ($char eq "-") { + $diff_class = " rem"; + } elsif ($char eq "@") { + $diff_class = " chunk_header"; + } elsif ($char eq "\\") { + $diff_class = " incomplete"; + } + $line = untabify($line); + if ($from && $to && $line =~ m/^\@{2} /) { + my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = + $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; + + $from_lines = 0 unless defined $from_lines; + $to_lines = 0 unless defined $to_lines; + + if ($from->{'href'}) { + $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", + -class=>"list"}, $from_text); + } + if ($to->{'href'}) { + $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } + $line = "<span class=\"chunk_info\">@@ $from_text $to_text @@</span>" . + "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; + return "<div class=\"diff$diff_class\">$line</div>\n"; + } + return "<div class=\"diff$diff_class\">" . esc_html($line, -nbsp=>1) . "</div>\n"; +} + ## ---------------------------------------------------------------------- ## git utility subroutines, invoking git commands +# returns path to the core git executable and the --git-dir parameter as list +sub git_cmd { + return $GIT, '--git-dir='.$git_dir; +} + +# returns path to the core git executable and the --git-dir parameter as string +sub git_cmd_str { + return join(' ', git_cmd()); +} + # get HEAD ref of given project as hash sub git_get_head_hash { my $project = shift; - my $oENV = $ENV{'GIT_DIR'}; + my $o_git_dir = $git_dir; my $retval = undef; - $ENV{'GIT_DIR'} = "$projectroot/$project"; - if (open my $fd, "-|", $GIT, "rev-parse", "--verify", "HEAD") { + $git_dir = "$projectroot/$project"; + if (open my $fd, "-|", git_cmd(), "rev-parse", "--verify", "HEAD") { my $head = <$fd>; close $fd; if (defined $head && $head =~ /^([0-9a-fA-F]{40})$/) { $retval = $1; } } - if (defined $oENV) { - $ENV{'GIT_DIR'} = $oENV; + if (defined $o_git_dir) { + $git_dir = $o_git_dir; } return $retval; } @@ -464,7 +972,7 @@ sub git_get_head_hash { sub git_get_type { my $hash = shift; - open my $fd, "-|", $GIT, "cat-file", '-t', $hash or return; + open my $fd, "-|", git_cmd(), "cat-file", '-t', $hash or return; my $type = <$fd>; close $fd or return; chomp $type; @@ -472,57 +980,46 @@ sub git_get_type { } sub git_get_project_config { - my $key = shift; + my ($key, $type) = @_; return unless ($key); $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); - my $val = qx($GIT repo-config --get gitweb.$key); + my @x = (git_cmd(), 'repo-config'); + if (defined $type) { push @x, $type; } + push @x, "--get"; + push @x, "gitweb.$key"; + my $val = qx(@x); + chomp $val; return ($val); } -sub git_get_project_config_bool { - my $val = git_get_project_config (@_); - if ($val and $val =~ m/true|yes|on/) { - return (1); - } - return; # implicit false -} - # get hash of given path at given ref sub git_get_hash_by_path { my $base = shift; my $path = shift || return undef; + my $type = shift; - my $tree = $base; + $path =~ s,/+$,,; - open my $fd, "-|", $GIT, "ls-tree", $base, "--", $path + open my $fd, "-|", git_cmd(), "ls-tree", $base, "--", $path or die_error(undef, "Open git-ls-tree failed"); my $line = <$fd>; close $fd or return undef; #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/; + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/; + if (defined $type && $type ne $2) { + # type doesn't match + return undef; + } return $3; } ## ...................................................................... ## git utility functions, directly accessing git repository -# assumes that PATH is not symref -sub git_get_hash_by_ref { - my $path = shift; - - open my $fd, "$projectroot/$path" or return undef; - my $head = <$fd>; - close $fd; - chomp $head; - if ($head =~ m/^[0-9a-fA-F]{40}$/) { - return $head; - } -} - sub git_get_project_description { my $path = shift; @@ -536,7 +1033,7 @@ sub git_get_project_description { sub git_get_project_url_list { my $path = shift; - open my $fd, "$projectroot/$path/cloneurl" or return undef; + open my $fd, "$projectroot/$path/cloneurl" or return; my @git_project_url_list = map { chomp; $_ } <$fd>; close $fd; @@ -544,27 +1041,47 @@ sub git_get_project_url_list { } sub git_get_projects_list { + my ($filter) = @_; my @list; + $filter ||= ''; + $filter =~ s/\.git$//; + if (-d $projects_list) { # search in directory - my $dir = $projects_list; - opendir my ($dh), $dir or return undef; - while (my $dir = readdir($dh)) { - if (-e "$projectroot/$dir/HEAD") { - my $pr = { - path => $dir, - }; - push @list, $pr - } - } - closedir($dh); + my $dir = $projects_list . ($filter ? "/$filter" : ''); + # remove the trailing "/" + $dir =~ s!/+$!!; + my $pfxlen = length("$dir"); + + my ($check_forks) = gitweb_check_feature('forks'); + + File::Find::find({ + follow_fast => 1, # follow symbolic links + dangling_symlinks => 0, # ignore dangling symlinks, silently + wanted => sub { + # skip project-list toplevel, if we get it. + return if (m!^[/.]$!); + # only directories can be git repositories + return unless (-d $_); + + my $subdir = substr($File::Find::name, $pfxlen + 1); + # we check related file in $projectroot + if ($check_forks and $subdir =~ m#/.#) { + $File::Find::prune = 1; + } elsif (check_export_ok("$projectroot/$filter/$subdir")) { + push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + $File::Find::prune = 1; + } + }, + }, "$dir"); + } elsif (-f $projects_list) { # read from file(url-encoded): # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - open my ($fd), $projects_list or return undef; + open my ($fd), $projects_list or return; while (my $line = <$fd>) { chomp $line; my ($path, $owner) = split ' ', $line; @@ -573,10 +1090,21 @@ sub git_get_projects_list { if (!defined $path) { next; } - if (-e "$projectroot/$path/HEAD") { + if ($filter ne '') { + # looking for forks; + my $pfx = substr($path, 0, length($filter)); + if ($pfx ne $filter) { + next; + } + my $sfx = substr($path, length($filter)); + if ($sfx !~ /^\/.*\.git$/) { + next; + } + } + if (check_export_ok("$projectroot/$path")) { my $pr = { path => $path, - owner => decode("utf8", $owner, Encode::FB_DEFAULT), + owner => to_utf8($owner), }; push @list, $pr } @@ -605,7 +1133,7 @@ sub git_get_project_owner { $pr = unescape($pr); $ow = unescape($ow); if ($pr eq $project) { - $owner = decode("utf8", $ow, Encode::FB_DEFAULT); + $owner = to_utf8($ow); last; } } @@ -618,23 +1146,37 @@ sub git_get_project_owner { return $owner; } +sub git_get_last_activity { + my ($path) = @_; + my $fd; + + $git_dir = "$projectroot/$path"; + open($fd, "-|", git_cmd(), 'for-each-ref', + '--format=%(committer)', + '--sort=-committerdate', + '--count=1', + 'refs/heads') or return; + my $most_recent = <$fd>; + close $fd or return; + if ($most_recent =~ / (\d+) [-+][01]\d\d\d$/) { + my $timestamp = $1; + my $age = time - $timestamp; + return ($age, age_string($age)); + } +} + sub git_get_references { my $type = shift || ""; my %refs; - my $fd; - # 5dc01c595e6c6ec9ccda4f6f69c131c0dd945f8c refs/tags/v2.6.11 - # c39ae07f393806ccf406ef966e9a15afc43cc36a refs/tags/v2.6.11^{} - if (-f "$projectroot/$project/info/refs") { - open $fd, "$projectroot/$project/info/refs" - or return; - } else { - open $fd, "-|", $GIT, "ls-remote", "." - or return; - } + # 5dc01c595e6c6ec9ccda4f6f69c131c0dd945f8c refs/tags/v2.6.11 + # c39ae07f393806ccf406ef966e9a15afc43cc36a refs/tags/v2.6.11^{} + open my $fd, "-|", git_cmd(), "show-ref", "--dereference", + ($type ? ("--", "refs/$type") : ()) # use -- <pattern> if $type + or return; while (my $line = <$fd>) { chomp $line; - if ($line =~ m/^([0-9a-fA-F]{40})\trefs\/($type\/?[^\^]+)/) { + if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type/?[^^]+)!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -646,6 +1188,22 @@ sub git_get_references { return \%refs; } +sub git_get_rev_name_tags { + my $hash = shift || return undef; + + open my $fd, "-|", git_cmd(), "name-rev", "--tags", $hash + or return; + my $name_rev = <$fd>; + close $fd; + + if ($name_rev =~ m|^$hash tags/(.*)$|) { + return $1; + } else { + # catches also '$hash undefined' output + return undef; + } +} + ## ---------------------------------------------------------------------- ## parse to hash functions @@ -662,8 +1220,12 @@ sub parse_date { $date{'mday'} = $mday; $date{'day'} = $days[$wday]; $date{'month'} = $months[$mon]; - $date{'rfc2822'} = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000", $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec; - $date{'mday-time'} = sprintf "%d %s %02d:%02d", $mday, $months[$mon], $hour ,$min; + $date{'rfc2822'} = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000", + $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec; + $date{'mday-time'} = sprintf "%d %s %02d:%02d", + $mday, $months[$mon], $hour ,$min; + $date{'iso-8601'} = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ", + 1900+$year, $mon, $mday, $hour ,$min, $sec; $tz =~ m/^([+\-][0-9][0-9])([0-9][0-9])$/; my $local = $epoch + ((int $1 + ($2/60)) * 3600); @@ -671,6 +1233,9 @@ sub parse_date { $date{'hour_local'} = $hour; $date{'minute_local'} = $min; $date{'tz_local'} = $tz; + $date{'iso-tz'} = sprintf("%04d-%02d-%02d %02d:%02d:%02d %s", + 1900+$year, $mon+1, $mday, + $hour, $min, $sec, $tz); return %date; } @@ -679,7 +1244,7 @@ sub parse_tag { my %tag; my @comment; - open my $fd, "-|", $GIT, "cat-file", "tag", $tag_id or return; + open my $fd, "-|", git_cmd(), "cat-file", "tag", $tag_id or return; $tag{'id'} = $tag_id; while (my $line = <$fd>) { chomp $line; @@ -709,40 +1274,31 @@ sub parse_tag { return %tag } -sub parse_commit { - my $commit_id = shift; - my $commit_text = shift; - - my @commit_lines; +sub parse_commit_text { + my ($commit_text, $withparents) = @_; + my @commit_lines = split '\n', $commit_text; my %co; - if (defined $commit_text) { - @commit_lines = @$commit_text; - } else { - $/ = "\0"; - open my $fd, "-|", $GIT, "rev-list", "--header", "--parents", "--max-count=1", $commit_id or return; - @commit_lines = split '\n', <$fd>; - close $fd or return; - $/ = "\n"; - pop @commit_lines; - } + pop @commit_lines; # Remove '\0' + my $header = shift @commit_lines; if (!($header =~ m/^[0-9a-fA-F]{40}/)) { return; } ($co{'id'}, my @parents) = split ' ', $header; - $co{'parents'} = \@parents; - $co{'parent'} = $parents[0]; while (my $line = shift @commit_lines) { last if $line eq "\n"; if ($line =~ m/^tree ([0-9a-fA-F]{40})$/) { $co{'tree'} = $1; + } elsif ((!defined $withparents) && ($line =~ m/^parent ([0-9a-fA-F]{40})$/)) { + push @parents, $1; } elsif ($line =~ m/^author (.*) ([0-9]+) (.*)$/) { $co{'author'} = $1; $co{'author_epoch'} = $2; $co{'author_tz'} = $3; - if ($co{'author'} =~ m/^([^<]+) </) { - $co{'author_name'} = $1; + if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) { + $co{'author_name'} = $1; + $co{'author_email'} = $2; } else { $co{'author_name'} = $co{'author'}; } @@ -751,12 +1307,19 @@ sub parse_commit { $co{'committer_epoch'} = $2; $co{'committer_tz'} = $3; $co{'committer_name'} = $co{'committer'}; - $co{'committer_name'} =~ s/ <.*//; + if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) { + $co{'committer_name'} = $1; + $co{'committer_email'} = $2; + } else { + $co{'committer_name'} = $co{'committer'}; + } } } if (!defined $co{'tree'}) { return; }; + $co{'parents'} = \@parents; + $co{'parent'} = $parents[0]; foreach my $title (@commit_lines) { $title =~ s/^ //; @@ -783,6 +1346,9 @@ sub parse_commit { last; } } + if ($co{'title'} eq "") { + $co{'title'} = $co{'title_short'} = '(no commit message)'; + } # remove added spaces foreach my $line (@commit_lines) { $line =~ s/^ //; @@ -803,6 +1369,52 @@ sub parse_commit { return %co; } +sub parse_commit { + my ($commit_id) = @_; + my %co; + + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "rev-list", + "--parents", + "--header", + "--max-count=1", + $commit_id, + "--", + or die_error(undef, "Open git-rev-list failed"); + %co = parse_commit_text(<$fd>, 1); + close $fd; + + return %co; +} + +sub parse_commits { + my ($commit_id, $maxcount, $skip, $arg, $filename) = @_; + my @cos; + + $maxcount ||= 1; + $skip ||= 0; + + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "rev-list", + "--header", + ($arg ? ($arg) : ()), + ("--max-count=" . $maxcount), + ("--skip=" . $skip), + $commit_id, + "--", + ($filename ? ($filename) : ()) + or die_error(undef, "Open git-rev-list failed"); + while (my $line = <$fd>) { + my %co = parse_commit_text($line); + push @cos, \%co; + } + close $fd; + + return wantarray ? @cos : \@cos; +} + # parse ref from ref_file, given by ref_id, with given type sub parse_ref { my $ref_file = shift; @@ -846,32 +1458,140 @@ sub parse_ref { return %ref_item; } +# parse line of git-diff-tree "raw" output +sub parse_difftree_raw_line { + my $line = shift; + my %res; + + # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' + # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' + if ($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/) { + $res{'from_mode'} = $1; + $res{'to_mode'} = $2; + $res{'from_id'} = $3; + $res{'to_id'} = $4; + $res{'status'} = $5; + $res{'similarity'} = $6; + if ($res{'status'} eq 'R' || $res{'status'} eq 'C') { # renamed or copied + ($res{'from_file'}, $res{'to_file'}) = map { unquote($_) } split("\t", $7); + } else { + $res{'file'} = unquote($7); + } + } + # 'c512b523472485aef4fff9e57b229d9d243c967f' + elsif ($line =~ m/^([0-9a-fA-F]{40})$/) { + $res{'commit'} = $1; + } + + return wantarray ? %res : \%res; +} + +# parse line of git-ls-tree output +sub parse_ls_tree_line ($;%) { + my $line = shift; + my %opts = @_; + my %res; + + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + if ($opts{'-z'}) { + $res{'name'} = $4; + } else { + $res{'name'} = unquote($4); + } + + return wantarray ? %res : \%res; +} + ## ...................................................................... ## parse to array of hashes functions -sub git_get_refs_list { - my $ref_dir = shift; - my @reflist; +sub git_get_heads_list { + my $limit = shift; + my @headslist; - my @refs; - my $pfxlen = length("$projectroot/$project/$ref_dir"); - File::Find::find(sub { - return if (/^\./); - if (-f $_) { - push @refs, substr($File::Find::name, $pfxlen + 1); + open my $fd, '-|', git_cmd(), 'for-each-ref', + ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate', + '--format=%(objectname) %(refname) %(subject)%00%(committer)', + 'refs/heads' + or return; + while (my $line = <$fd>) { + my %ref_item; + + chomp $line; + my ($refinfo, $committerinfo) = split(/\0/, $line); + my ($hash, $name, $title) = split(' ', $refinfo, 3); + my ($committer, $epoch, $tz) = + ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); + $name =~ s!^refs/heads/!!; + + $ref_item{'name'} = $name; + $ref_item{'id'} = $hash; + $ref_item{'title'} = $title || '(no commit message)'; + $ref_item{'epoch'} = $epoch; + if ($epoch) { + $ref_item{'age'} = age_string(time - $ref_item{'epoch'}); + } else { + $ref_item{'age'} = "unknown"; } - }, "$projectroot/$project/$ref_dir"); - foreach my $ref_file (@refs) { - my $ref_id = git_get_hash_by_ref("$project/$ref_dir/$ref_file"); - my $type = git_get_type($ref_id) || next; - my %ref_item = parse_ref($ref_file, $ref_id, $type); + push @headslist, \%ref_item; + } + close $fd; + + return wantarray ? @headslist : \@headslist; +} + +sub git_get_tags_list { + my $limit = shift; + my @tagslist; - push @reflist, \%ref_item; + open my $fd, '-|', git_cmd(), 'for-each-ref', + ($limit ? '--count='.($limit+1) : ()), '--sort=-creatordate', + '--format=%(objectname) %(objecttype) %(refname) '. + '%(*objectname) %(*objecttype) %(subject)%00%(creator)', + 'refs/tags' + or return; + while (my $line = <$fd>) { + my %ref_item; + + chomp $line; + my ($refinfo, $creatorinfo) = split(/\0/, $line); + my ($id, $type, $name, $refid, $reftype, $title) = split(' ', $refinfo, 6); + my ($creator, $epoch, $tz) = + ($creatorinfo =~ /^(.*) ([0-9]+) (.*)$/); + $name =~ s!^refs/tags/!!; + + $ref_item{'type'} = $type; + $ref_item{'id'} = $id; + $ref_item{'name'} = $name; + if ($type eq "tag") { + $ref_item{'subject'} = $title; + $ref_item{'reftype'} = $reftype; + $ref_item{'refid'} = $refid; + } else { + $ref_item{'reftype'} = $type; + $ref_item{'refid'} = $id; + } + + if ($type eq "tag" || $type eq "commit") { + $ref_item{'epoch'} = $epoch; + if ($epoch) { + $ref_item{'age'} = age_string(time - $ref_item{'epoch'}); + } else { + $ref_item{'age'} = "unknown"; + } + } + + push @tagslist, \%ref_item; } - # sort refs by age - @reflist = sort {$b->{'epoch'} <=> $a->{'epoch'}} @reflist; - return \@reflist; + close $fd; + + return wantarray ? @tagslist : \@tagslist; } ## ---------------------------------------------------------------------- @@ -887,7 +1607,7 @@ sub get_file_owner { } my $owner = $gcos; $owner =~ s/[,;].*$//; - return decode("utf8", $owner, Encode::FB_DEFAULT); + return to_utf8($owner); } ## ...................................................................... @@ -912,7 +1632,7 @@ sub mimetype_guess_file { } close(MIME); - $filename =~ /\.(.*?)$/; + $filename =~ /\.([^.]*)$/; return $mimemap{$1}; } @@ -968,13 +1688,13 @@ sub git_header_html { my $status = shift || "200 OK"; my $expires = shift; - my $title = "$site_name git"; + my $title = "$site_name"; if (defined $project) { $title .= " - $project"; if (defined $action) { $title .= "/$action"; if (defined $file_name) { - $title .= " - $file_name"; + $title .= " - " . esc_path($file_name); if ($action eq "tree" && $file_name !~ m|/$|) { $title .= "/"; } @@ -986,12 +1706,16 @@ sub git_header_html { # 'application/xhtml+xml', otherwise send it as plain old 'text/html'. # we have to do this because MSIE sometimes globs '*/*', pretending to # support xhtml+xml but choking when it gets what it asked for. - if (defined $cgi->http('HTTP_ACCEPT') && $cgi->http('HTTP_ACCEPT') =~ m/(,|;|\s|^)application\/xhtml\+xml(,|;|\s|$)/ && $cgi->Accept('application/xhtml+xml') != 0) { + if (defined $cgi->http('HTTP_ACCEPT') && + $cgi->http('HTTP_ACCEPT') =~ m/(,|;|\s|^)application\/xhtml\+xml(,|;|\s|$)/ && + $cgi->Accept('application/xhtml+xml') != 0) { $content_type = 'application/xhtml+xml'; } else { $content_type = 'text/html'; } - print $cgi->header(-type=>$content_type, -charset => 'utf-8', -status=> $status, -expires => $expires); + print $cgi->header(-type=>$content_type, -charset => 'utf-8', + -status=> $status, -expires => $expires); + my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; print <<EOF; <?xml version="1.0" encoding="utf-8"?> <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> @@ -1000,30 +1724,62 @@ sub git_header_html { <!-- git core binaries version $git_version --> <head> <meta http-equiv="content-type" content="$content_type; charset=utf-8"/> -<meta name="generator" content="gitweb/$version git/$git_version"/> +<meta name="generator" content="gitweb/$version git/$git_version$mod_perl_version"/> <meta name="robots" content="index, nofollow"/> <title>$title</title> -<link rel="stylesheet" type="text/css" href="$stylesheet"/> EOF +# print out each stylesheet that exist + if (defined $stylesheet) { +#provides backwards capability for those people who define style sheet in a config file + print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n"; + } else { + foreach my $stylesheet (@stylesheets) { + next unless $stylesheet; + print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n"; + } + } if (defined $project) { - printf('<link rel="alternate" title="%s log" '. - 'href="%s" type="application/rss+xml"/>'."\n", + printf('<link rel="alternate" title="%s log RSS feed" '. + 'href="%s" type="application/rss+xml" />'."\n", esc_param($project), href(action=>"rss")); + printf('<link rel="alternate" title="%s log Atom feed" '. + 'href="%s" type="application/atom+xml" />'."\n", + esc_param($project), href(action=>"atom")); + } else { + printf('<link rel="alternate" title="%s projects list" '. + 'href="%s" type="text/plain; charset=utf-8"/>'."\n", + $site_name, href(project=>undef, action=>"project_index")); + printf('<link rel="alternate" title="%s projects feeds" '. + 'href="%s" type="text/x-opml"/>'."\n", + $site_name, href(project=>undef, action=>"opml")); + } + if (defined $favicon) { + print qq(<link rel="shortcut icon" href="$favicon" type="image/png"/>\n); } print "</head>\n" . - "<body>\n" . - "<div class=\"page_header\">\n" . - "<a href=\"http://www.kernel.org/pub/software/scm/git/docs/\" title=\"git documentation\">" . - "<img src=\"$logo\" width=\"72\" height=\"27\" alt=\"git\" style=\"float:right; border-width:0px;\"/>" . - "</a>\n"; - print $cgi->a({-href => esc_param($home_link)}, $home_link_str) . " / "; + "<body>\n"; + + if (-f $site_header) { + open (my $fd, $site_header); + print <$fd>; + close $fd; + } + + print "<div class=\"page_header\">\n" . + $cgi->a({-href => esc_url($logo_url), + -title => $logo_label}, + qq(<img src="$logo" width="72" height="27" alt="git" class="logo"/>)); + print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; if (defined $project) { print $cgi->a({-href => href(action=>"summary")}, esc_html($project)); if (defined $action) { print " / $action"; } print "\n"; + } + my ($have_search) = gitweb_check_feature('search'); + if ((defined $project) && ($have_search)) { if (!defined $searchtext) { $searchtext = ""; } @@ -1037,11 +1793,16 @@ EOF } $cgi->param("a", "search"); $cgi->param("h", $search_hash); + $cgi->param("p", $project); print $cgi->startform(-method => "get", -action => $my_uri) . "<div class=\"search\">\n" . $cgi->hidden(-name => "p") . "\n" . $cgi->hidden(-name => "a") . "\n" . $cgi->hidden(-name => "h") . "\n" . + $cgi->popup_menu(-name => 'st', -default => 'commit', + -values => ['commit', 'author', 'committer', 'pickaxe']) . + $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) . + " search:\n", $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . "</div>" . $cgi->end_form() . "\n"; @@ -1056,12 +1817,25 @@ sub git_footer_html { if (defined $descr) { print "<div class=\"page_footer_text\">" . esc_html($descr) . "</div>\n"; } - print $cgi->a({-href => href(action=>"rss"), -class => "rss_logo"}, "RSS") . "\n"; + print $cgi->a({-href => href(action=>"rss"), + -class => "rss_logo"}, "RSS") . " "; + print $cgi->a({-href => href(action=>"atom"), + -class => "rss_logo"}, "Atom") . "\n"; } else { - print $cgi->a({-href => "$my_uri?" . esc_param("a=opml"), -class => "rss_logo"}, "OPML") . "\n"; + print $cgi->a({-href => href(project=>undef, action=>"opml"), + -class => "rss_logo"}, "OPML") . " "; + print $cgi->a({-href => href(project=>undef, action=>"project_index"), + -class => "rss_logo"}, "TXT") . "\n"; } - print "</div>\n" . - "</body>\n" . + print "</div>\n" ; + + if (-f $site_footer) { + open (my $fd, $site_footer); + print <$fd>; + close $fd; + } + + print "</body>\n" . "</html>"; } @@ -1070,11 +1844,13 @@ sub die_error { my $error = shift || "Malformed query, file missing or permission denied"; git_header_html($status); - print "<div class=\"page_body\">\n" . - "<br/><br/>\n" . - "$status - $error\n" . - "<br/>\n" . - "</div>\n"; + print <<EOF; +<div class="page_body"> +<br /><br /> +$status - $error +<br /> +</div> +EOF git_footer_html(); exit; } @@ -1161,17 +1937,244 @@ sub git_print_header_div { "\n</div>\n"; } +#sub git_print_authorship (\%) { +sub git_print_authorship { + my $co = shift; + + my %ad = parse_date($co->{'author_epoch'}, $co->{'author_tz'}); + print "<div class=\"author_date\">" . + esc_html($co->{'author_name'}) . + " [$ad{'rfc2822'}"; + if ($ad{'hour_local'} < 6) { + printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", + $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + } else { + printf(" (%02d:%02d %s)", + $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + } + print "]</div>\n"; +} + sub git_print_page_path { my $name = shift; my $type = shift; + my $hb = shift; + + + print "<div class=\"page_path\">"; + print $cgi->a({-href => href(action=>"tree", hash_base=>$hb), + -title => 'tree root'}, "[$project]"); + print " / "; + if (defined $name) { + my @dirname = split '/', $name; + my $basename = pop @dirname; + my $fullname = ''; + + foreach my $dir (@dirname) { + $fullname .= ($fullname ? '/' : '') . $dir; + print $cgi->a({-href => href(action=>"tree", file_name=>$fullname, + hash_base=>$hb), + -title => esc_html($fullname)}, esc_path($dir)); + print " / "; + } + if (defined $type && $type eq 'blob') { + print $cgi->a({-href => href(action=>"blob_plain", file_name=>$file_name, + hash_base=>$hb), + -title => esc_html($name)}, esc_path($basename)); + } elsif (defined $type && $type eq 'tree') { + print $cgi->a({-href => href(action=>"tree", file_name=>$file_name, + hash_base=>$hb), + -title => esc_html($name)}, esc_path($basename)); + print " / "; + } else { + print esc_path($basename); + } + } + print "<br/></div>\n"; +} + +# sub git_print_log (\@;%) { +sub git_print_log ($;%) { + my $log = shift; + my %opts = @_; + + if ($opts{'-remove_title'}) { + # remove title, i.e. first line of log + shift @$log; + } + # remove leading empty lines + while (defined $log->[0] && $log->[0] eq "") { + shift @$log; + } + + # print log + my $signoff = 0; + my $empty = 0; + foreach my $line (@$log) { + if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { + $signoff = 1; + $empty = 0; + if (! $opts{'-remove_signoff'}) { + print "<span class=\"signoff\">" . esc_html($line) . "</span><br/>\n"; + next; + } else { + # remove signoff lines + next; + } + } else { + $signoff = 0; + } + + # print only one empty line + # do not print empty line after signoff + if ($line eq "") { + next if ($empty || $signoff); + $empty = 1; + } else { + $empty = 0; + } + + print format_log_line_html($line) . "<br/>\n"; + } + + if ($opts{'-final_empty_line'}) { + # end with single empty line + print "<br/>\n" unless $empty; + } +} - if (!defined $name) { - print "<div class=\"page_path\"><b>/</b></div>\n"; - } elsif (defined $type && $type eq 'blob') { - print "<div class=\"page_path\"><b>" . - $cgi->a({-href => href(action=>"blob_plain", file_name=>$file_name)}, esc_html($name)) . "</b><br/></div>\n"; +# return link target (what link points to) +sub git_get_link_target { + my $hash = shift; + my $link_target; + + # read link + open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash + or return; + { + local $/; + $link_target = <$fd>; + } + close $fd + or return; + + return $link_target; +} + +# given link target, and the directory (basedir) the link is in, +# return target of link relative to top directory (top tree); +# return undef if it is not possible (including absolute links). +sub normalize_link_target { + my ($link_target, $basedir, $hash_base) = @_; + + # we can normalize symlink target only if $hash_base is provided + return unless $hash_base; + + # absolute symlinks (beginning with '/') cannot be normalized + return if (substr($link_target, 0, 1) eq '/'); + + # normalize link target to path from top (root) tree (dir) + my $path; + if ($basedir) { + $path = $basedir . '/' . $link_target; } else { - print "<div class=\"page_path\"><b>" . esc_html($name) . "</b><br/></div>\n"; + # we are in top (root) tree (dir) + $path = $link_target; + } + + # remove //, /./, and /../ + my @path_parts; + foreach my $part (split('/', $path)) { + # discard '.' and '' + next if (!$part || $part eq '.'); + # handle '..' + if ($part eq '..') { + if (@path_parts) { + pop @path_parts; + } else { + # link leads outside repository (outside top dir) + return; + } + } else { + push @path_parts, $part; + } + } + $path = join('/', @path_parts); + + return $path; +} + +# print tree entry (row of git_tree), but without encompassing <tr> element +sub git_print_tree_entry { + my ($t, $basedir, $hash_base, $have_blame) = @_; + + my %base_key = (); + $base_key{'hash_base'} = $hash_base if defined $hash_base; + + # The format of a table row is: mode list link. Where mode is + # the mode of the entry, list is the name of the entry, an href, + # and link is the action links of the entry. + + print "<td class=\"mode\">" . mode_str($t->{'mode'}) . "</td>\n"; + if ($t->{'type'} eq "blob") { + print "<td class=\"list\">" . + $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, + file_name=>"$basedir$t->{'name'}", %base_key), + -class => "list"}, esc_path($t->{'name'})); + if (S_ISLNK(oct $t->{'mode'})) { + my $link_target = git_get_link_target($t->{'hash'}); + if ($link_target) { + my $norm_target = normalize_link_target($link_target, $basedir, $hash_base); + if (defined $norm_target) { + print " -> " . + $cgi->a({-href => href(action=>"object", hash_base=>$hash_base, + file_name=>$norm_target), + -title => $norm_target}, esc_path($link_target)); + } else { + print " -> " . esc_path($link_target); + } + } + } + print "</td>\n"; + print "<td class=\"link\">"; + print $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, + file_name=>"$basedir$t->{'name'}", %base_key)}, + "blob"); + if ($have_blame) { + print " | " . + $cgi->a({-href => href(action=>"blame", hash=>$t->{'hash'}, + file_name=>"$basedir$t->{'name'}", %base_key)}, + "blame"); + } + if (defined $hash_base) { + print " | " . + $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, + hash=>$t->{'hash'}, file_name=>"$basedir$t->{'name'}")}, + "history"); + } + print " | " . + $cgi->a({-href => href(action=>"blob_plain", hash_base=>$hash_base, + file_name=>"$basedir$t->{'name'}")}, + "raw"); + print "</td>\n"; + + } elsif ($t->{'type'} eq "tree") { + print "<td class=\"list\">"; + print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, + file_name=>"$basedir$t->{'name'}", %base_key)}, + esc_path($t->{'name'})); + print "</td>\n"; + print "<td class=\"link\">"; + print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, + file_name=>"$basedir$t->{'name'}", %base_key)}, + "tree"); + if (defined $hash_base) { + print " | " . + $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, + file_name=>"$basedir$t->{'name'}")}, + "history"); + } + print "</td>\n"; } } @@ -1179,8 +2182,8 @@ sub git_print_page_path { ## functions printing large fragments of HTML sub git_difftree_body { - my ($difftree, $parent) = @_; - + my ($difftree, $hash, $parent) = @_; + my ($have_blame) = gitweb_check_feature('blame'); print "<div class=\"list_head\">\n"; if ($#{$difftree} > 10) { print(($#{$difftree} + 1) . " files changed:\n"); @@ -1188,20 +2191,10 @@ sub git_difftree_body { print "</div>\n"; print "<table class=\"diff_tree\">\n"; - my $alternate = 0; + my $alternate = 1; + my $patchno = 0; foreach my $line (@{$difftree}) { - # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' - # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' - if ($line !~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/) { - next; - } - my $from_mode = $1; - my $to_mode = $2; - my $from_id = $3; - my $to_id = $4; - my $status = $5; - my $similarity = $6; # score - my $file = validate_input(unquote($7)); + my %diff = parse_difftree_raw_line($line); if ($alternate) { print "<tr class=\"dark\">\n"; @@ -1210,126 +2203,510 @@ sub git_difftree_body { } $alternate ^= 1; - if ($status eq "A") { # created - my $mode_chng = ""; - if (S_ISREG(oct $to_mode)) { - $mode_chng = sprintf(" with mode: %04o", (oct $to_mode) & 0777); + my ($to_mode_oct, $to_mode_str, $to_file_type); + my ($from_mode_oct, $from_mode_str, $from_file_type); + if ($diff{'to_mode'} ne ('0' x 6)) { + $to_mode_oct = oct $diff{'to_mode'}; + if (S_ISREG($to_mode_oct)) { # only for regular file + $to_mode_str = sprintf("%04o", $to_mode_oct & 0777); # permission bits } - print "<td>" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$file), - -class => "list"}, esc_html($file)) . - "</td>\n" . - "<td><span class=\"file_status new\">[new " . file_type($to_mode) . "$mode_chng]</span></td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$file)}, "blob") . - "</td>\n"; - - } elsif ($status eq "D") { # deleted - print "<td>" . - $cgi->a({-href => href(action=>"blob", hash=>$from_id, hash_base=>$parent, file_name=>$file), - -class => "list"}, esc_html($file)) . "</td>\n" . - "<td><span class=\"file_status deleted\">[deleted " . file_type($from_mode). "]</span></td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"blob", hash=>$from_id, hash_base=>$parent, file_name=>$file)}, "blob") . " | " . - $cgi->a({-href => href(action=>"history", hash_base=>$parent, file_name=>$file)}, "history") . - "</td>\n" - - } elsif ($status eq "M" || $status eq "T") { # modified, or type changed + $to_file_type = file_type($diff{'to_mode'}); + } + if ($diff{'from_mode'} ne ('0' x 6)) { + $from_mode_oct = oct $diff{'from_mode'}; + if (S_ISREG($to_mode_oct)) { # only for regular file + $from_mode_str = sprintf("%04o", $from_mode_oct & 0777); # permission bits + } + $from_file_type = file_type($diff{'from_mode'}); + } + + if ($diff{'status'} eq "A") { # created + my $mode_chng = "<span class=\"file_status new\">[new $to_file_type"; + $mode_chng .= " with mode: $to_mode_str" if $to_mode_str; + $mode_chng .= "]</span>"; + print "<td>"; + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, + hash_base=>$hash, file_name=>$diff{'file'}), + -class => "list"}, esc_path($diff{'file'})); + print "</td>\n"; + print "<td>$mode_chng</td>\n"; + print "<td class=\"link\">"; + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print $cgi->a({-href => "#patch$patchno"}, "patch"); + print " | "; + } + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, + hash_base=>$hash, file_name=>$diff{'file'})}, + "blob"); + print "</td>\n"; + + } elsif ($diff{'status'} eq "D") { # deleted + my $mode_chng = "<span class=\"file_status deleted\">[deleted $from_file_type]</span>"; + print "<td>"; + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, + hash_base=>$parent, file_name=>$diff{'file'}), + -class => "list"}, esc_path($diff{'file'})); + print "</td>\n"; + print "<td>$mode_chng</td>\n"; + print "<td class=\"link\">"; + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print $cgi->a({-href => "#patch$patchno"}, "patch"); + print " | "; + } + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, + hash_base=>$parent, file_name=>$diff{'file'})}, + "blob") . " | "; + if ($have_blame) { + print $cgi->a({-href => href(action=>"blame", hash_base=>$parent, + file_name=>$diff{'file'})}, + "blame") . " | "; + } + print $cgi->a({-href => href(action=>"history", hash_base=>$parent, + file_name=>$diff{'file'})}, + "history"); + print "</td>\n"; + + } elsif ($diff{'status'} eq "M" || $diff{'status'} eq "T") { # modified, or type changed my $mode_chnge = ""; - if ($from_mode != $to_mode) { - $mode_chnge = " <span class=\"file_status mode_chnge\">[changed"; - if (((oct $from_mode) & S_IFMT) != ((oct $to_mode) & S_IFMT)) { - $mode_chnge .= " from " . file_type($from_mode) . " to " . file_type($to_mode); + if ($diff{'from_mode'} != $diff{'to_mode'}) { + $mode_chnge = "<span class=\"file_status mode_chnge\">[changed"; + if ($from_file_type ne $to_file_type) { + $mode_chnge .= " from $from_file_type to $to_file_type"; } - if (((oct $from_mode) & 0777) != ((oct $to_mode) & 0777)) { - if (S_ISREG($from_mode) && S_ISREG($to_mode)) { - $mode_chnge .= sprintf(" mode: %04o->%04o", (oct $from_mode) & 0777, (oct $to_mode) & 0777); - } elsif (S_ISREG($to_mode)) { - $mode_chnge .= sprintf(" mode: %04o", (oct $to_mode) & 0777); + if (($from_mode_oct & 0777) != ($to_mode_oct & 0777)) { + if ($from_mode_str && $to_mode_str) { + $mode_chnge .= " mode: $from_mode_str->$to_mode_str"; + } elsif ($to_mode_str) { + $mode_chnge .= " mode: $to_mode_str"; } } $mode_chnge .= "]</span>\n"; } print "<td>"; - if ($to_id ne $from_id) { # modified - print $cgi->a({-href => href(action=>"blobdiff", hash=>$to_id, hash_parent=>$from_id, hash_base=>$hash, file_name=>$file), - -class => "list"}, esc_html($file)); - } else { # mode changed - print $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$file), - -class => "list"}, esc_html($file)); + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, + hash_base=>$hash, file_name=>$diff{'file'}), + -class => "list"}, esc_path($diff{'file'})); + print "</td>\n"; + print "<td>$mode_chnge</td>\n"; + print "<td class=\"link\">"; + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print $cgi->a({-href => "#patch$patchno"}, "patch") . + " | "; + } elsif ($diff{'to_id'} ne $diff{'from_id'}) { + # "commit" view and modified file (not onlu mode changed) + print $cgi->a({-href => href(action=>"blobdiff", + hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash_base=>$hash, hash_parent_base=>$parent, + file_name=>$diff{'file'})}, + "diff") . + " | "; } - print "</td>\n" . - "<td>$mode_chnge</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$file)}, "blob"); - if ($to_id ne $from_id) { # modified - print $cgi->a({-href => href(action=>"blobdiff", hash=>$to_id, hash_parent=>$from_id, hash_base=>$hash, file_name=>$file)}, "diff"); + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, + hash_base=>$hash, file_name=>$diff{'file'})}, + "blob") . " | "; + if ($have_blame) { + print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, + file_name=>$diff{'file'})}, + "blame") . " | "; } - print " | " . $cgi->a({-href => href(action=>"history", hash_base=>$hash, file_name=>$file)}, "history") . "\n"; + print $cgi->a({-href => href(action=>"history", hash_base=>$hash, + file_name=>$diff{'file'})}, + "history"); print "</td>\n"; - } elsif ($status eq "R") { # renamed - my ($from_file, $to_file) = split "\t", $file; + } elsif ($diff{'status'} eq "R" || $diff{'status'} eq "C") { # renamed or copied + my %status_name = ('R' => 'moved', 'C' => 'copied'); + my $nstatus = $status_name{$diff{'status'}}; my $mode_chng = ""; - if ($from_mode != $to_mode) { - $mode_chng = sprintf(", mode: %04o", (oct $to_mode) & 0777); + if ($diff{'from_mode'} != $diff{'to_mode'}) { + # mode also for directories, so we cannot use $to_mode_str + $mode_chng = sprintf(", mode: %04o", $to_mode_oct & 0777); } print "<td>" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$to_file), - -class => "list"}, esc_html($to_file)) . "</td>\n" . - "<td><span class=\"file_status moved\">[moved from " . - $cgi->a({-href => href(action=>"blob", hash=>$from_id, hash_base=>$parent, file_name=>$from_file), - -class => "list"}, esc_html($from_file)) . - " with " . (int $similarity) . "% similarity$mode_chng]</span></td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$to_file)}, "blob"); - if ($to_id ne $from_id) { - print " | " . - $cgi->a({-href => "$my_uri?" . - esc_param("p=$project;a=blobdiff;h=$to_id;hp=$from_id;hb=$hash;f=$to_file;fp=$from_file")}, "diff"); + $cgi->a({-href => href(action=>"blob", hash_base=>$hash, + hash=>$diff{'to_id'}, file_name=>$diff{'to_file'}), + -class => "list"}, esc_path($diff{'to_file'})) . "</td>\n" . + "<td><span class=\"file_status $nstatus\">[$nstatus from " . + $cgi->a({-href => href(action=>"blob", hash_base=>$parent, + hash=>$diff{'from_id'}, file_name=>$diff{'from_file'}), + -class => "list"}, esc_path($diff{'from_file'})) . + " with " . (int $diff{'similarity'}) . "% similarity$mode_chng]</span></td>\n" . + "<td class=\"link\">"; + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print $cgi->a({-href => "#patch$patchno"}, "patch") . + " | "; + } elsif ($diff{'to_id'} ne $diff{'from_id'}) { + # "commit" view and modified file (not only pure rename or copy) + print $cgi->a({-href => href(action=>"blobdiff", + hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash_base=>$hash, hash_parent_base=>$parent, + file_name=>$diff{'to_file'}, file_parent=>$diff{'from_file'})}, + "diff") . + " | "; + } + print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, + hash_base=>$parent, file_name=>$diff{'to_file'})}, + "blob") . " | "; + if ($have_blame) { + print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, + file_name=>$diff{'to_file'})}, + "blame") . " | "; } + print $cgi->a({-href => href(action=>"history", hash_base=>$hash, + file_name=>$diff{'to_file'})}, + "history"); print "</td>\n"; - } elsif ($status eq "C") { # copied - my ($from_file, $to_file) = split "\t", $file; - my $mode_chng = ""; - if ($from_mode != $to_mode) { - $mode_chng = sprintf(", mode: %04o", (oct $to_mode) & 0777); + } # we should not encounter Unmerged (U) or Unknown (X) status + print "</tr>\n"; + } + print "</table>\n"; +} + +sub git_patchset_body { + my ($fd, $difftree, $hash, $hash_parent) = @_; + + my $patch_idx = 0; + my $patch_line; + my $diffinfo; + my (%from, %to); + + print "<div class=\"patchset\">\n"; + + # skip to first patch + while ($patch_line = <$fd>) { + chomp $patch_line; + + last if ($patch_line =~ m/^diff /); + } + + PATCH: + while ($patch_line) { + my @diff_header; + my ($from_id, $to_id); + + # git diff header + #assert($patch_line =~ m/^diff /) if DEBUG; + #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed + push @diff_header, $patch_line; + + # extended diff header + EXTENDED_HEADER: + while ($patch_line = <$fd>) { + chomp $patch_line; + + last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); + + if ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) { + $from_id = $1; + $to_id = $2; } - print "<td>" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$to_file), - -class => "list"}, esc_html($to_file)) . "</td>\n" . - "<td><span class=\"file_status copied\">[copied from " . - $cgi->a({-href => href(action=>"blob", hash=>$from_id, hash_base=>$parent, file_name=>$from_file), - -class => "list"}, esc_html($from_file)) . - " with " . (int $similarity) . "% similarity$mode_chng]</span></td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"blob", hash=>$to_id, hash_base=>$hash, file_name=>$to_file)}, "blob"); - if ($to_id ne $from_id) { - print " | " . - $cgi->a({-href => "$my_uri?" . - esc_param("p=$project;a=blobdiff;h=$to_id;hp=$from_id;hb=$hash;f=$to_file;fp=$from_file")}, "diff"); + + push @diff_header, $patch_line; + } + my $last_patch_line = $patch_line; + + # check if current patch belong to current raw line + # and parse raw git-diff line if needed + if (defined $diffinfo && + $diffinfo->{'from_id'} eq $from_id && + $diffinfo->{'to_id'} eq $to_id) { + # this is split patch + print "<div class=\"patch cont\">\n"; + } else { + # advance raw git-diff output if needed + $patch_idx++ if defined $diffinfo; + + # read and prepare patch information + if (ref($difftree->[$patch_idx]) eq "HASH") { + # pre-parsed (or generated by hand) + $diffinfo = $difftree->[$patch_idx]; + } else { + $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]); + } + $from{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'}; + $to{'file'} = $diffinfo->{'to_file'} || $diffinfo->{'file'}; + if ($diffinfo->{'status'} ne "A") { # not new (added) file + $from{'href'} = href(action=>"blob", hash_base=>$hash_parent, + hash=>$diffinfo->{'from_id'}, + file_name=>$from{'file'}); + } else { + delete $from{'href'}; + } + if ($diffinfo->{'status'} ne "D") { # not deleted file + $to{'href'} = href(action=>"blob", hash_base=>$hash, + hash=>$diffinfo->{'to_id'}, + file_name=>$to{'file'}); + } else { + delete $to{'href'}; + } + # this is first patch for raw difftree line with $patch_idx index + # we index @$difftree array from 0, but number patches from 1 + print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n"; + } + + # print "git diff" header + $patch_line = shift @diff_header; + $patch_line =~ s!^(diff (.*?) )"?a/.*$!$1!; + if ($from{'href'}) { + $patch_line .= $cgi->a({-href => $from{'href'}, -class => "path"}, + 'a/' . esc_path($from{'file'})); + } else { # file was added + $patch_line .= 'a/' . esc_path($from{'file'}); + } + $patch_line .= ' '; + if ($to{'href'}) { + $patch_line .= $cgi->a({-href => $to{'href'}, -class => "path"}, + 'b/' . esc_path($to{'file'})); + } else { # file was deleted + $patch_line .= 'b/' . esc_path($to{'file'}); + } + print "<div class=\"diff header\">$patch_line</div>\n"; + + # print extended diff header + print "<div class=\"diff extended_header\">\n" if (@diff_header > 0); + EXTENDED_HEADER: + foreach $patch_line (@diff_header) { + # match <path> + if ($patch_line =~ s!^((copy|rename) from ).*$!$1! && $from{'href'}) { + $patch_line .= $cgi->a({-href=>$from{'href'}, -class=>"path"}, + esc_path($from{'file'})); + } + if ($patch_line =~ s!^((copy|rename) to ).*$!$1! && $to{'href'}) { + $patch_line .= $cgi->a({-href=>$to{'href'}, -class=>"path"}, + esc_path($to{'file'})); + } + # match <mode> + if ($patch_line =~ m/\s(\d{6})$/) { + $patch_line .= '<span class="info"> (' . + file_type_long($1) . + ')</span>'; + } + # match <hash> + if ($patch_line =~ m/^index/) { + my ($from_link, $to_link); + if ($from{'href'}) { + $from_link = $cgi->a({-href=>$from{'href'}, -class=>"hash"}, + substr($diffinfo->{'from_id'},0,7)); + } else { + $from_link = '0' x 7; + } + if ($to{'href'}) { + $to_link = $cgi->a({-href=>$to{'href'}, -class=>"hash"}, + substr($diffinfo->{'to_id'},0,7)); + } else { + $to_link = '0' x 7; + } + #affirm { + # my ($from_hash, $to_hash) = + # ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/); + # my ($from_id, $to_id) = + # ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); + # ($from_hash eq $from_id) && ($to_hash eq $to_id); + #} if DEBUG; + my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); + $patch_line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; + } + print $patch_line . "<br/>\n"; + } + print "</div>\n" if (@diff_header > 0); # class="diff extended_header" + + # from-file/to-file diff header + $patch_line = $last_patch_line; + if (! $patch_line) { + print "</div>\n"; # class="patch" + last PATCH; + } + next PATCH if ($patch_line =~ m/^diff /); + #assert($patch_line =~ m/^---/) if DEBUG; + if ($from{'href'} && $patch_line =~ m!^--- "?a/!) { + $patch_line = '--- a/' . + $cgi->a({-href=>$from{'href'}, -class=>"path"}, + esc_path($from{'file'})); + } + print "<div class=\"diff from_file\">$patch_line</div>\n"; + + $patch_line = <$fd>; + chomp $patch_line; + + #assert($patch_line =~ m/^+++/) if DEBUG; + if ($to{'href'} && $patch_line =~ m!^\+\+\+ "?b/!) { + $patch_line = '+++ b/' . + $cgi->a({-href=>$to{'href'}, -class=>"path"}, + esc_path($to{'file'})); + } + print "<div class=\"diff to_file\">$patch_line</div>\n"; + + # the patch itself + LINE: + while ($patch_line = <$fd>) { + chomp $patch_line; + + next PATCH if ($patch_line =~ m/^diff /); + + print format_diff_line($patch_line, \%from, \%to); + } + + } continue { + print "</div>\n"; # class="patch" + } + + print "</div>\n"; # class="patchset" +} + +# . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . + +sub git_project_list_body { + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + + my ($check_forks) = gitweb_check_feature('forks'); + + my @projects; + foreach my $pr (@$projlist) { + my (@aa) = git_get_last_activity($pr->{'path'}); + unless (@aa) { + next; + } + ($pr->{'age'}, $pr->{'age_string'}) = @aa; + if (!defined $pr->{'descr'}) { + my $descr = git_get_project_description($pr->{'path'}) || ""; + $pr->{'descr_long'} = to_utf8($descr); + $pr->{'descr'} = chop_str($descr, 25, 5); + } + if (!defined $pr->{'owner'}) { + $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}") || ""; + } + if ($check_forks) { + my $pname = $pr->{'path'}; + if (($pname =~ s/\.git$//) && + ($pname !~ /\/$/) && + (-d "$projectroot/$pname")) { + $pr->{'forks'} = "-d $projectroot/$pname"; + } + else { + $pr->{'forks'} = 0; + } + } + push @projects, $pr; + } + + $order ||= "project"; + $from = 0 unless defined $from; + $to = $#projects if (!defined $to || $#projects < $to); + + print "<table class=\"project_list\">\n"; + unless ($no_header) { + print "<tr>\n"; + if ($check_forks) { + print "<th></th>\n"; + } + if ($order eq "project") { + @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; + print "<th>Project</th>\n"; + } else { + print "<th>" . + $cgi->a({-href => href(project=>undef, order=>'project'), + -class => "header"}, "Project") . + "</th>\n"; + } + if ($order eq "descr") { + @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; + print "<th>Description</th>\n"; + } else { + print "<th>" . + $cgi->a({-href => href(project=>undef, order=>'descr'), + -class => "header"}, "Description") . + "</th>\n"; + } + if ($order eq "owner") { + @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; + print "<th>Owner</th>\n"; + } else { + print "<th>" . + $cgi->a({-href => href(project=>undef, order=>'owner'), + -class => "header"}, "Owner") . + "</th>\n"; + } + if ($order eq "age") { + @projects = sort {$a->{'age'} <=> $b->{'age'}} @projects; + print "<th>Last Change</th>\n"; + } else { + print "<th>" . + $cgi->a({-href => href(project=>undef, order=>'age'), + -class => "header"}, "Last Change") . + "</th>\n"; + } + print "<th></th>\n" . + "</tr>\n"; + } + my $alternate = 1; + for (my $i = $from; $i <= $to; $i++) { + my $pr = $projects[$i]; + if ($alternate) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $alternate ^= 1; + if ($check_forks) { + print "<td>"; + if ($pr->{'forks'}) { + print "<!-- $pr->{'forks'} -->\n"; + print $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks")}, "+"); } print "</td>\n"; - } # we should not encounter Unmerged (U) or Unknown (X) status - print "</tr>\n"; + } + print "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), + -class => "list"}, esc_html($pr->{'path'})) . "</td>\n" . + "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), + -class => "list", -title => $pr->{'descr_long'}}, + esc_html($pr->{'descr'})) . "</td>\n" . + "<td><i>" . chop_str($pr->{'owner'}, 15) . "</i></td>\n"; + print "<td class=\"". age_class($pr->{'age'}) . "\">" . + $pr->{'age_string'} . "</td>\n" . + "<td class=\"link\">" . + $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary")}, "summary") . " | " . + $cgi->a({-href => href(project=>$pr->{'path'}, action=>"shortlog")}, "shortlog") . " | " . + $cgi->a({-href => href(project=>$pr->{'path'}, action=>"log")}, "log") . " | " . + $cgi->a({-href => href(project=>$pr->{'path'}, action=>"tree")}, "tree") . + ($pr->{'forks'} ? " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks")}, "forks") : '') . + "</td>\n" . + "</tr>\n"; + } + if (defined $extra) { + print "<tr>\n"; + if ($check_forks) { + print "<td></td>\n"; + } + print "<td colspan=\"5\">$extra</td>\n" . + "</tr>\n"; } print "</table>\n"; } sub git_shortlog_body { # uses global variable $project - my ($revlist, $from, $to, $refs, $extra) = @_; + my ($commitlist, $from, $to, $refs, $extra) = @_; + + my $have_snapshot = gitweb_have_snapshot(); + $from = 0 unless defined $from; - $to = $#{$revlist} if (!defined $to || $#{$revlist} < $to); + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); print "<table class=\"shortlog\" cellspacing=\"0\">\n"; - my $alternate = 0; + my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - my $commit = $revlist->[$i]; - #my $ref = defined $refs ? format_ref_marker($refs, $commit) : ''; + my %co = %{$commitlist->[$i]}; + my $commit = $co{'id'}; my $ref = format_ref_marker($refs, $commit); - my %co = parse_commit($commit); if ($alternate) { print "<tr class=\"dark\">\n"; } else { @@ -1340,12 +2717,17 @@ sub git_shortlog_body { print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . "<td><i>" . esc_html(chop_str($co{'author_name'}, 10)) . "</i></td>\n" . "<td>"; - print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); + print format_subject_html($co{'title'}, $co{'title_short'}, + href(action=>"commit", hash=>$commit), $ref); print "</td>\n" . "<td class=\"link\">" . $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . " | " . - $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . - "</td>\n" . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . " | " . + $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree"); + if ($have_snapshot) { + print " | " . $cgi->a({-href => href(action=>"snapshot", hash=>$commit)}, "snapshot"); + } + print "</td>\n" . "</tr>\n"; } if (defined $extra) { @@ -1358,20 +2740,19 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($fd, $refs, $hash_base, $ftype, $extra) = @_; + my ($commitlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; - print "<table class=\"history\" cellspacing=\"0\">\n"; - my $alternate = 0; - while (my $line = <$fd>) { - if ($line !~ m/^([0-9a-fA-F]{40})/) { - next; - } + $from = 0 unless defined $from; + $to = $#{$commitlist} unless (defined $to && $to <= $#{$commitlist}); - my $commit = $1; - my %co = parse_commit($commit); + print "<table class=\"history\" cellspacing=\"0\">\n"; + my $alternate = 1; + for (my $i = $from; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; if (!%co) { next; } + my $commit = $co{'id'}; my $ref = format_ref_marker($refs, $commit); @@ -1386,12 +2767,12 @@ sub git_history_body { "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 3)) . "</i></td>\n" . "<td>"; # originally git_history used chop_str($co{'title'}, 50) - print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); + print format_subject_html($co{'title'}, $co{'title_short'}, + href(action=>"commit", hash=>$commit), $ref); print "</td>\n" . "<td class=\"link\">" . - $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . " | " . - $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . " | " . - $cgi->a({-href => href(action=>$ftype, hash_base=>$commit, file_name=>$file_name)}, $ftype); + $cgi->a({-href => href(action=>$ftype, hash_base=>$commit, file_name=>$file_name)}, $ftype) . " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff"); if ($ftype eq 'blob') { my $blob_current = git_get_hash_by_path($hash_base, $file_name); @@ -1399,7 +2780,10 @@ sub git_history_body { if (defined $blob_current && defined $blob_parent && $blob_current ne $blob_parent) { print " | " . - $cgi->a({-href => href(action=>"blobdiff", hash=>$blob_current, hash_parent=>$blob_parent, hash_base=>$commit, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blobdiff", + hash=>$blob_current, hash_parent=>$blob_parent, + hash_base=>$hash_base, hash_parent_base=>$commit, + file_name=>$file_name)}, "diff to current"); } } @@ -1421,12 +2805,11 @@ sub git_tags_body { $to = $#{$taglist} if (!defined $to || $#{$taglist} < $to); print "<table class=\"tags\" cellspacing=\"0\">\n"; - my $alternate = 0; + my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my $entry = $taglist->[$i]; my %tag = %$entry; - my $comment_lines = $tag{'comment'}; - my $comment = shift @$comment_lines; + my $comment = $tag{'subject'}; my $comment_short; if (defined $comment) { $comment_short = chop_str($comment, 30, 5); @@ -1437,14 +2820,19 @@ sub git_tags_body { print "<tr class=\"light\">\n"; } $alternate ^= 1; - print "<td><i>$tag{'age'}</i></td>\n" . - "<td>" . + if (defined $tag{'age'}) { + print "<td><i>$tag{'age'}</i></td>\n"; + } else { + print "<td></td>\n"; + } + print "<td>" . $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'}), - -class => "list"}, "<b>" . esc_html($tag{'name'}) . "</b>") . + -class => "list name"}, esc_html($tag{'name'})) . "</td>\n" . "<td>"; if (defined $comment) { - print format_subject_html($comment, $comment_short, href(action=>"tag", hash=>$tag{'id'})); + print format_subject_html($comment, $comment_short, + href(action=>"tag", hash=>$tag{'id'})); } print "</td>\n" . "<td class=\"selflink\">"; @@ -1458,7 +2846,7 @@ sub git_tags_body { $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'})}, $tag{'reftype'}); if ($tag{'reftype'} eq "commit") { print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") . - " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'refid'})}, "log"); + " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log"); } elsif ($tag{'reftype'} eq "blob") { print " | " . $cgi->a({-href => href(action=>"blob_plain", hash=>$tag{'refid'})}, "raw"); } @@ -1475,30 +2863,31 @@ sub git_tags_body { sub git_heads_body { # uses global variable $project - my ($taglist, $head, $from, $to, $extra) = @_; + my ($headlist, $head, $from, $to, $extra) = @_; $from = 0 unless defined $from; - $to = $#{$taglist} if (!defined $to || $#{$taglist} < $to); + $to = $#{$headlist} if (!defined $to || $#{$headlist} < $to); print "<table class=\"heads\" cellspacing=\"0\">\n"; - my $alternate = 0; + my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - my $entry = $taglist->[$i]; - my %tag = %$entry; - my $curr = $tag{'id'} eq $head; + my $entry = $headlist->[$i]; + my %ref = %$entry; + my $curr = $ref{'id'} eq $head; if ($alternate) { print "<tr class=\"dark\">\n"; } else { print "<tr class=\"light\">\n"; } $alternate ^= 1; - print "<td><i>$tag{'age'}</i></td>\n" . - ($tag{'id'} eq $head ? "<td class=\"current_head\">" : "<td>") . - $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'}), - -class => "list"}, "<b>" . esc_html($tag{'name'}) . "</b>") . + print "<td><i>$ref{'age'}</i></td>\n" . + ($curr ? "<td class=\"current_head\">" : "<td>") . + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'}), + -class => "list name"},esc_html($ref{'name'})) . "</td>\n" . "<td class=\"link\">" . - $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") . " | " . - $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log") . + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'})}, "shortlog") . " | " . + $cgi->a({-href => href(action=>"log", hash=>$ref{'name'})}, "log") . " | " . + $cgi->a({-href => href(action=>"tree", hash=>$ref{'name'}, hash_base=>$ref{'name'})}, "tree") . "</td>\n" . "</tr>"; } @@ -1510,77 +2899,58 @@ sub git_heads_body { print "</table>\n"; } -## ---------------------------------------------------------------------- -## functions printing large fragments, format as one of arguments - -sub git_diff_print { - my $from = shift; - my $from_name = shift; - my $to = shift; - my $to_name = shift; - my $format = shift || "html"; - - my $from_tmp = "/dev/null"; - my $to_tmp = "/dev/null"; - my $pid = $$; - - # create tmp from-file - if (defined $from) { - $from_tmp = "$git_temp/gitweb_" . $$ . "_from"; - open my $fd2, "> $from_tmp"; - open my $fd, "-|", $GIT, "cat-file", "blob", $from; - my @file = <$fd>; - print $fd2 @file; - close $fd2; - close $fd; - } - - # create tmp to-file - if (defined $to) { - $to_tmp = "$git_temp/gitweb_" . $$ . "_to"; - open my $fd2, "> $to_tmp"; - open my $fd, "-|", $GIT, "cat-file", "blob", $to; - my @file = <$fd>; - print $fd2 @file; - close $fd2; - close $fd; - } +sub git_search_grep_body { + my ($commitlist, $from, $to, $extra) = @_; + $from = 0 unless defined $from; + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - open my $fd, "-|", "/usr/bin/diff -u -p -L \'$from_name\' -L \'$to_name\' $from_tmp $to_tmp"; - if ($format eq "plain") { - undef $/; - print <$fd>; - $/ = "\n"; - } else { - while (my $line = <$fd>) { - chomp $line; - my $char = substr($line, 0, 1); - my $diff_class = ""; - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq "-") { - $diff_class = " rem"; - } elsif ($char eq "@") { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - # skip errors - next; + print "<table class=\"grep\" cellspacing=\"0\">\n"; + my $alternate = 1; + for (my $i = $from; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; + if (!%co) { + next; + } + my $commit = $co{'id'}; + if ($alternate) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $alternate ^= 1; + print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . + "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . + "<td>" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"}, + esc_html(chop_str($co{'title'}, 50)) . "<br/>"); + my $comment = $co{'comment'}; + foreach my $line (@$comment) { + if ($line =~ m/^(.*)($searchtext)(.*)$/i) { + my $lead = esc_html($1) || ""; + $lead = chop_str($lead, 30, 10); + my $match = esc_html($2) || ""; + my $trail = esc_html($3) || ""; + $trail = chop_str($trail, 30, 10); + my $text = "$lead<span class=\"match\">$match</span>$trail"; + print chop_str($text, 80, 5) . "<br/>\n"; } - $line = untabify($line); - print "<div class=\"diff$diff_class\">" . esc_html($line) . "</div>\n"; } + print "</td>\n" . + "<td class=\"link\">" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); + print "</td>\n" . + "</tr>\n"; } - close $fd; - - if (defined $from) { - unlink($from_tmp); - } - if (defined $to) { - unlink($to_tmp); + if (defined $extra) { + print "<tr>\n" . + "<td colspan=\"3\">$extra</td>\n" . + "</tr>\n"; } + print "</table>\n"; } - ## ====================================================================== ## ====================================================================== ## actions @@ -1592,30 +2962,9 @@ sub git_project_list { } my @list = git_get_projects_list(); - my @projects; if (!@list) { die_error(undef, "No projects found"); } - foreach my $pr (@list) { - my $head = git_get_head_hash($pr->{'path'}); - if (!defined $head) { - next; - } - $ENV{'GIT_DIR'} = "$projectroot/$pr->{'path'}"; - my %co = parse_commit($head); - if (!%co) { - next; - } - $pr->{'commit'} = \%co; - if (!defined $pr->{'descr'}) { - my $descr = git_get_project_description($pr->{'path'}) || ""; - $pr->{'descr'} = chop_str($descr, 25, 5); - } - if (!defined $pr->{'owner'}) { - $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}") || ""; - } - push @projects, $pr; - } git_header_html(); if (-f $home_text) { @@ -1625,81 +2974,72 @@ sub git_project_list { close $fd; print "</div>\n"; } - print "<table class=\"project_list\">\n" . - "<tr>\n"; - $order ||= "project"; - if ($order eq "project") { - @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; - print "<th>Project</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => "$my_uri?" . esc_param("o=project"), - -class => "header"}, "Project") . - "</th>\n"; - } - if ($order eq "descr") { - @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; - print "<th>Description</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => "$my_uri?" . esc_param("o=descr"), - -class => "header"}, "Description") . - "</th>\n"; - } - if ($order eq "owner") { - @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; - print "<th>Owner</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => "$my_uri?" . esc_param("o=owner"), - -class => "header"}, "Owner") . - "</th>\n"; - } - if ($order eq "age") { - @projects = sort {$a->{'commit'}{'age'} <=> $b->{'commit'}{'age'}} @projects; - print "<th>Last Change</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => "$my_uri?" . esc_param("o=age"), - -class => "header"}, "Last Change") . - "</th>\n"; + git_project_list_body(\@list, $order); + git_footer_html(); +} + +sub git_forks { + my $order = $cgi->param('o'); + if (defined $order && $order !~ m/project|descr|owner|age/) { + die_error(undef, "Unknown order parameter"); } - print "<th></th>\n" . - "</tr>\n"; - my $alternate = 0; + + my @list = git_get_projects_list($project); + if (!@list) { + die_error(undef, "No forks found"); + } + + git_header_html(); + git_print_page_nav('',''); + git_print_header_div('summary', "$project forks"); + git_project_list_body(\@list, $order); + git_footer_html(); +} + +sub git_project_index { + my @projects = git_get_projects_list($project); + + print $cgi->header( + -type => 'text/plain', + -charset => 'utf-8', + -content_disposition => 'inline; filename="index.aux"'); + foreach my $pr (@projects) { - if ($alternate) { - print "<tr class=\"dark\">\n"; - } else { - print "<tr class=\"light\">\n"; + if (!exists $pr->{'owner'}) { + $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}"); } - $alternate ^= 1; - print "<td>" . $cgi->a({-href => "$my_uri?" . esc_param("p=$pr->{'path'};a=summary"), - -class => "list"}, esc_html($pr->{'path'})) . "</td>\n" . - "<td>" . esc_html($pr->{'descr'}) . "</td>\n" . - "<td><i>" . chop_str($pr->{'owner'}, 15) . "</i></td>\n"; - print "<td class=\"". age_class($pr->{'commit'}{'age'}) . "\">" . - $pr->{'commit'}{'age_string'} . "</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$pr->{'path'};a=summary")}, "summary") . " | " . - $cgi->a({-href => "$my_uri?" . esc_param("p=$pr->{'path'};a=shortlog")}, "shortlog") . " | " . - $cgi->a({-href => "$my_uri?" . esc_param("p=$pr->{'path'};a=log")}, "log") . - "</td>\n" . - "</tr>\n"; + + my ($path, $owner) = ($pr->{'path'}, $pr->{'owner'}); + # quote as in CGI::Util::encode, but keep the slash, and use '+' for ' ' + $path =~ s/([^a-zA-Z0-9_.\-\/ ])/sprintf("%%%02X", ord($1))/eg; + $owner =~ s/([^a-zA-Z0-9_.\-\/ ])/sprintf("%%%02X", ord($1))/eg; + $path =~ s/ /\+/g; + $owner =~ s/ /\+/g; + + print "$path $owner\n"; } - print "</table>\n"; - git_footer_html(); } sub git_summary { my $descr = git_get_project_description($project) || "none"; - my $head = git_get_head_hash($project); - my %co = parse_commit($head); + my %co = parse_commit("HEAD"); my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my $head = $co{'id'}; my $owner = git_get_project_owner($project); my $refs = git_get_references(); + # These get_*_list functions return one more to allow us to see if + # there are more ... + my @taglist = git_get_tags_list(16); + my @headlist = git_get_heads_list(16); + my @forklist; + my ($check_forks) = gitweb_check_feature('forks'); + + if ($check_forks) { + @forklist = git_get_projects_list($project); + } + git_header_html(); git_print_page_nav('summary','', $head); @@ -1720,28 +3060,44 @@ sub git_summary { } print "</table>\n"; - open my $fd, "-|", $GIT, "rev-list", "--max-count=17", git_get_head_hash($project) - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; + if (-s "$projectroot/$project/README.html") { + if (open my $fd, "$projectroot/$project/README.html") { + print "<div class=\"title\">readme</div>\n"; + print $_ while (<$fd>); + close $fd; + } + } + + # we need to request one more than 16 (0..15) to check if + # those 16 are all + my @commitlist = parse_commits($head, 17); git_print_header_div('shortlog'); - git_shortlog_body(\@revlist, 0, 15, $refs, + git_shortlog_body(\@commitlist, 0, 15, $refs, + $#commitlist <= 15 ? undef : $cgi->a({-href => href(action=>"shortlog")}, "...")); - my $taglist = git_get_refs_list("refs/tags"); - if (defined @$taglist) { + if (@taglist) { git_print_header_div('tags'); - git_tags_body($taglist, 0, 15, + git_tags_body(\@taglist, 0, 15, + $#taglist <= 15 ? undef : $cgi->a({-href => href(action=>"tags")}, "...")); } - my $headlist = git_get_refs_list("refs/heads"); - if (defined @$headlist) { + if (@headlist) { git_print_header_div('heads'); - git_heads_body($headlist, $head, 0, 15, + git_heads_body(\@headlist, $head, 0, 15, + $#headlist <= 15 ? undef : $cgi->a({-href => href(action=>"heads")}, "...")); } + if (@forklist) { + git_print_header_div('forks'); + git_project_list_body(\@forklist, undef, 0, 15, + $#forklist <= 15 ? undef : + $cgi->a({-href => href(action=>"forks")}, "..."), + 'noheader'); + } + git_footer_html(); } @@ -1755,20 +3111,25 @@ sub git_tag { "<table cellspacing=\"0\">\n" . "<tr>\n" . "<td>object</td>\n" . - "<td>" . $cgi->a({-class => "list", -href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, $tag{'object'}) . "</td>\n" . - "<td class=\"link\">" . $cgi->a({-href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, $tag{'type'}) . "</td>\n" . + "<td>" . $cgi->a({-class => "list", -href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, + $tag{'object'}) . "</td>\n" . + "<td class=\"link\">" . $cgi->a({-href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, + $tag{'type'}) . "</td>\n" . "</tr>\n"; if (defined($tag{'author'})) { my %ad = parse_date($tag{'epoch'}, $tag{'tz'}); print "<tr><td>author</td><td>" . esc_html($tag{'author'}) . "</td></tr>\n"; - print "<tr><td></td><td>" . $ad{'rfc2822'} . sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . "</td></tr>\n"; + print "<tr><td></td><td>" . $ad{'rfc2822'} . + sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . + "</td></tr>\n"; } print "</table>\n\n" . "</div>\n"; print "<div class=\"page_body\">"; my $comment = $tag{'comment'}; foreach my $line (@$comment) { - print esc_html($line) . "<br/>\n"; + chomp $line; + print esc_html($line, -nbsp=>1) . "<br/>\n"; } print "</div>\n"; git_footer_html(); @@ -1777,7 +3138,11 @@ sub git_tag { sub git_blame2 { my $fd; my $ftype; - die_error(undef, "Permission denied") if (!git_get_project_config_bool ('blame')); + + my ($have_blame) = gitweb_check_feature('blame'); + if (!$have_blame) { + die_error('403 Permission denied', "Permission denied"); + } die_error('404 Not Found', "File name not defined") if (!$file_name); $hash_base ||= git_get_head_hash($project); die_error(undef, "Couldn't find base commit") unless ($hash_base); @@ -1791,51 +3156,100 @@ sub git_blame2 { if ($ftype !~ "blob") { die_error("400 Bad Request", "Object is not a blob"); } - open ($fd, "-|", $GIT, "blame", '-l', $file_name, $hash_base) + open ($fd, "-|", git_cmd(), "blame", '-p', '--', + $file_name, $hash_base) or die_error(undef, "Open git-blame failed"); git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blobl", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, "blob") . - " | " . $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, "head"); + $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + "blob") . + " | " . + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + "history") . + " | " . + $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, + "HEAD"); git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, $ftype); + git_print_page_path($file_name, $ftype, $hash_base); my @rev_color = (qw(light2 dark2)); my $num_colors = scalar(@rev_color); my $current_color = 0; my $last_rev; - print "<div class=\"page_body\">\n"; - print "<table class=\"blame\">\n"; - print "<tr><th>Commit</th><th>Line</th><th>Data</th></tr>\n"; - while (<$fd>) { - /^([0-9a-fA-F]{40}).*?(\d+)\)\s{1}(\s*.*)/; - my $full_rev = $1; + print <<HTML; +<div class="page_body"> +<table class="blame"> +<tr><th>Commit</th><th>Line</th><th>Data</th></tr> +HTML + my %metainfo = (); + while (1) { + $_ = <$fd>; + last unless defined $_; + my ($full_rev, $orig_lineno, $lineno, $group_size) = + /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/; + if (!exists $metainfo{$full_rev}) { + $metainfo{$full_rev} = {}; + } + my $meta = $metainfo{$full_rev}; + while (<$fd>) { + last if (s/^\t//); + if (/^(\S+) (.*)$/) { + $meta->{$1} = $2; + } + } + my $data = $_; + chomp $data; my $rev = substr($full_rev, 0, 8); - my $lineno = $2; - my $data = $3; - - if (!defined $last_rev) { - $last_rev = $full_rev; - } elsif ($last_rev ne $full_rev) { - $last_rev = $full_rev; + my $author = $meta->{'author'}; + my %date = parse_date($meta->{'author-time'}, + $meta->{'author-tz'}); + my $date = $date{'iso-tz'}; + if ($group_size) { $current_color = ++$current_color % $num_colors; } print "<tr class=\"$rev_color[$current_color]\">\n"; - print "<td class=\"sha1\">" . - $cgi->a({-href => href(action=>"commit", hash=>$full_rev, file_name=>$file_name)}, esc_html($rev)) . "</td>\n"; - print "<td class=\"linenr\"><a id=\"l$lineno\" href=\"#l$lineno\" class=\"linenr\">" . esc_html($lineno) . "</a></td>\n"; + if ($group_size) { + print "<td class=\"sha1\""; + print " title=\"". esc_html($author) . ", $date\""; + print " rowspan=\"$group_size\"" if ($group_size > 1); + print ">"; + print $cgi->a({-href => href(action=>"commit", + hash=>$full_rev, + file_name=>$file_name)}, + esc_html($rev)); + print "</td>\n"; + } + open (my $dd, "-|", git_cmd(), "rev-parse", "$full_rev^") + or die_error("could not open git-rev-parse"); + my $parent_commit = <$dd>; + close $dd; + chomp($parent_commit); + my $blamed = href(action => 'blame', + file_name => $meta->{'filename'}, + hash_base => $parent_commit); + print "<td class=\"linenr\">"; + print $cgi->a({ -href => "$blamed#l$orig_lineno", + -id => "l$lineno", + -class => "linenr" }, + esc_html($lineno)); + print "</td>"; print "<td class=\"pre\">" . esc_html($data) . "</td>\n"; print "</tr>\n"; } print "</table>\n"; print "</div>"; - close $fd or print "Reading blob failed\n"; + close $fd + or print "Reading blob failed\n"; git_footer_html(); } sub git_blame { my $fd; - die_error('403 Permission denied', "Permission denied") if (!git_get_project_config_bool ('blame')); + + my ($have_blame) = gitweb_check_feature('blame'); + if (!$have_blame) { + die_error('403 Permission denied', "Permission denied"); + } die_error('404 Not Found', "File name not defined") if (!$file_name); $hash_base ||= git_get_head_hash($project); die_error(undef, "Couldn't find base commit") unless ($hash_base); @@ -1845,15 +3259,21 @@ sub git_blame { $hash = git_get_hash_by_path($hash_base, $file_name, "blob") or die_error(undef, "Error lookup file"); } - open ($fd, "-|", $GIT, "annotate", '-l', '-t', '-r', $file_name, $hash_base) + open ($fd, "-|", git_cmd(), "annotate", '-l', '-t', '-r', $file_name, $hash_base) or die_error(undef, "Open git-annotate failed"); git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blobl", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, "blob") . - " | " . $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, "head"); + $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + "blob") . + " | " . + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + "history") . + " | " . + $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, + "HEAD"); git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, 'blob'); + git_print_page_path($file_name, 'blob', $hash_base); print "<div class=\"page_body\">\n"; print <<HTML; <table class="blame"> @@ -1882,7 +3302,7 @@ HTML chomp $line; $line_class_num = ($line_class_num + 1) % $line_class_len; - if ($line =~ m/^([0-9a-fA-F]{40})\t\(\s*([^\t]+)\t(\d+) \+\d\d\d\d\t(\d+)\)(.*)$/) { + if ($line =~ m/^([0-9a-fA-F]{40})\t\(\s*([^\t]+)\t(\d+) [+-]\d\d\d\d\t(\d+)\)(.*)$/) { $long_rev = $1; $author = $2; $time = $3; @@ -1914,7 +3334,8 @@ HTML HTML } # while (my $line = <$fd>) print "</table>\n\n"; - close $fd or print "Reading blob failed.\n"; + close $fd + or print "Reading blob failed.\n"; print "</div>"; git_footer_html(); } @@ -1925,9 +3346,9 @@ sub git_tags { git_print_page_nav('','', $head,undef,$head); git_print_header_div('summary', $project); - my $taglist = git_get_refs_list("refs/tags"); - if (defined @$taglist) { - git_tags_body($taglist); + my @tagslist = git_get_tags_list(); + if (@tagslist) { + git_tags_body(\@tagslist); } git_footer_html(); } @@ -1938,14 +3359,16 @@ sub git_heads { git_print_page_nav('','', $head,undef,$head); git_print_header_div('summary', $project); - my $taglist = git_get_refs_list("refs/heads"); - if (defined @$taglist) { - git_heads_body($taglist, $head); + my @headslist = git_get_heads_list(); + if (@headslist) { + git_heads_body(\@headslist, $head); } git_footer_html(); } sub git_blob_plain { + my $expires; + if (!defined $hash) { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); @@ -1954,9 +3377,13 @@ sub git_blob_plain { } else { die_error(undef, "No file name defined"); } + } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + # blobs defined by non-textual hash id's can be cached + $expires = "+1d"; } + my $type = shift; - open my $fd, "-|", $GIT, "cat-file", "blob", $hash + open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or die_error(undef, "Couldn't cat $file_name, $hash"); $type ||= blob_mimetype($fd, $file_name); @@ -1969,7 +3396,10 @@ sub git_blob_plain { $save_as .= '.txt'; } - print $cgi->header(-type => "$type", '-content-disposition' => "inline; filename=\"$save_as\""); + print $cgi->header( + -type => "$type", + -expires=>$expires, + -content_disposition => 'inline; filename="' . "$save_as" . '"'); undef $/; binmode STDOUT, ':raw'; print <$fd>; @@ -1979,6 +3409,8 @@ sub git_blob_plain { } sub git_blob { + my $expires; + if (!defined $hash) { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); @@ -1987,27 +3419,48 @@ sub git_blob { } else { die_error(undef, "No file name defined"); } + } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + # blobs defined by non-textual hash id's can be cached + $expires = "+1d"; } - my $have_blame = git_get_project_config_bool ('blame'); - open my $fd, "-|", $GIT, "cat-file", "blob", $hash + + my ($have_blame) = gitweb_check_feature('blame'); + open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or die_error(undef, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); - if ($mimetype !~ m/^text\//) { + if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)!) { close $fd; return git_blob_plain($mimetype); } - git_header_html(); + # we can have blame only for text/* mimetype + $have_blame &&= ($mimetype =~ m!^text/!); + + git_header_html(undef, $expires); my $formats_nav = ''; if (defined $hash_base && (my %co = parse_commit($hash_base))) { if (defined $file_name) { if ($have_blame) { - $formats_nav .= $cgi->a({-href => href(action=>"blame", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, "blame") . " | "; + $formats_nav .= + $cgi->a({-href => href(action=>"blame", hash_base=>$hash_base, + hash=>$hash, file_name=>$file_name)}, + "blame") . + " | "; } $formats_nav .= - $cgi->a({-href => href(action=>"blob_plain", hash=>$hash, file_name=>$file_name)}, "plain") . - " | " . $cgi->a({-href => href(action=>"blob", hash_base=>"HEAD", file_name=>$file_name)}, "head"); + $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, + hash=>$hash, file_name=>$file_name)}, + "history") . + " | " . + $cgi->a({-href => href(action=>"blob_plain", + hash=>$hash, file_name=>$file_name)}, + "raw") . + " | " . + $cgi->a({-href => href(action=>"blob", + hash_base=>"HEAD", file_name=>$file_name)}, + "HEAD"); } else { - $formats_nav .= $cgi->a({-href => href(action=>"blob_plain", hash=>$hash)}, "plain"); + $formats_nav .= + $cgi->a({-href => href(action=>"blob_plain", hash=>$hash)}, "raw"); } git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); @@ -2016,33 +3469,48 @@ sub git_blob { "<br/><br/></div>\n" . "<div class=\"title\">$hash</div>\n"; } - git_print_page_path($file_name, "blob"); + git_print_page_path($file_name, "blob", $hash_base); print "<div class=\"page_body\">\n"; - my $nr; - while (my $line = <$fd>) { - chomp $line; - $nr++; - $line = untabify($line); - printf "<div class=\"pre\"><a id=\"l%i\" href=\"#l%i\" class=\"linenr\">%4i</a> %s</div>\n", $nr, $nr, $nr, esc_html($line); + if ($mimetype =~ m!^text/!) { + my $nr; + while (my $line = <$fd>) { + chomp $line; + $nr++; + $line = untabify($line); + printf "<div class=\"pre\"><a id=\"l%i\" href=\"#l%i\" class=\"linenr\">%4i</a> %s</div>\n", + $nr, $nr, $nr, esc_html($line, -nbsp=>1); + } + } elsif ($mimetype =~ m!^image/!) { + print qq!<img type="$mimetype"!; + if ($file_name) { + print qq! alt="$file_name" title="$file_name"!; + } + print qq! src="! . + href(action=>"blob_plain", hash=>$hash, + hash_base=>$hash_base, file_name=>$file_name) . + qq!" />\n!; } - close $fd or print "Reading blob failed.\n"; + close $fd + or print "Reading blob failed.\n"; print "</div>"; git_footer_html(); } sub git_tree { + my $have_snapshot = gitweb_have_snapshot(); + + if (!defined $hash_base) { + $hash_base = "HEAD"; + } if (!defined $hash) { - $hash = git_get_head_hash($project); if (defined $file_name) { - my $base = $hash_base || $hash; - $hash = git_get_hash_by_path($base, $file_name, "tree"); - } - if (!defined $hash_base) { - $hash_base = $hash; + $hash = git_get_hash_by_path($hash_base, $file_name, "tree"); + } else { + $hash = $hash_base; } } $/ = "\0"; - open my $fd, "-|", $GIT, "ls-tree", '-z', $hash + open my $fd, "-|", git_cmd(), "ls-tree", '-z', $hash or die_error(undef, "Open git-ls-tree failed"); my @entries = map { chomp; $_ } <$fd>; close $fd or die_error(undef, "Reading tree failed"); @@ -2051,60 +3519,79 @@ sub git_tree { my $refs = git_get_references(); my $ref = format_ref_marker($refs, $hash_base); git_header_html(); - my $base_key = ""; - my $base = ""; - my $have_blame = git_get_project_config_bool ('blame'); + my $basedir = ''; + my ($have_blame) = gitweb_check_feature('blame'); if (defined $hash_base && (my %co = parse_commit($hash_base))) { - $base_key = ";hb=$hash_base"; - git_print_page_nav('tree','', $hash_base); + my @views_nav = (); + if (defined $file_name) { + push @views_nav, + $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, + hash=>$hash, file_name=>$file_name)}, + "history"), + $cgi->a({-href => href(action=>"tree", + hash_base=>"HEAD", file_name=>$file_name)}, + "HEAD"), + } + if ($have_snapshot) { + # FIXME: Should be available when we have no hash base as well. + push @views_nav, + $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, + "snapshot"); + } + git_print_page_nav('tree','', $hash_base, undef, undef, join(' | ', @views_nav)); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash_base); } else { + undef $hash_base; print "<div class=\"page_nav\">\n"; print "<br/><br/></div>\n"; print "<div class=\"title\">$hash</div>\n"; } if (defined $file_name) { - $base = esc_html("$file_name/"); + $basedir = $file_name; + if ($basedir ne '' && substr($basedir, -1) ne '/') { + $basedir .= '/'; + } } - git_print_page_path($file_name, 'tree'); + git_print_page_path($file_name, 'tree', $hash_base); print "<div class=\"page_body\">\n"; print "<table cellspacing=\"0\">\n"; - my $alternate = 0; - foreach my $line (@entries) { - #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/; - my $t_mode = $1; - my $t_type = $2; - my $t_hash = $3; - my $t_name = validate_input($4); + my $alternate = 1; + # '..' (top directory) link if possible + if (defined $hash_base && + defined $file_name && $file_name =~ m![^/]+$!) { if ($alternate) { print "<tr class=\"dark\">\n"; } else { print "<tr class=\"light\">\n"; } $alternate ^= 1; - print "<td class=\"mode\">" . mode_str($t_mode) . "</td>\n"; - if ($t_type eq "blob") { - print "<td class=\"list\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$t_hash$base_key;f=$base$t_name"), -class => "list"}, esc_html($t_name)) . - "</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$t_hash$base_key;f=$base$t_name")}, "blob"); - if ($have_blame) { - print " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blame;h=$t_hash$base_key;f=$base$t_name")}, "blame"); - } - print " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=history;h=$t_hash;hb=$hash_base;f=$base$t_name")}, "history") . - " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob_plain;h=$t_hash;f=$base$t_name")}, "raw") . - "</td>\n"; - } elsif ($t_type eq "tree") { - print "<td class=\"list\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=tree;h=$t_hash$base_key;f=$base$t_name")}, esc_html($t_name)) . - "</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=tree;h=$t_hash$base_key;f=$base$t_name")}, "tree") . - " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=history;hb=$hash_base;f=$base$t_name")}, "history") . - "</td>\n"; + + my $up = $file_name; + $up =~ s!/?[^/]+$!!; + undef $up unless $up; + # based on git_print_tree_entry + print '<td class="mode">' . mode_str('040000') . "</td>\n"; + print '<td class="list">'; + print $cgi->a({-href => href(action=>"tree", hash_base=>$hash_base, + file_name=>$up)}, + ".."); + print "</td>\n"; + print "<td class=\"link\"></td>\n"; + + print "</tr>\n"; + } + foreach my $line (@entries) { + my %t = parse_ls_tree_line($line, -z => 1); + + if ($alternate) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; } + $alternate ^= 1; + + git_print_tree_entry(\%t, $basedir, $hash_base, $have_blame); + print "</tr>\n"; } print "</table>\n" . @@ -2112,6 +3599,37 @@ sub git_tree { git_footer_html(); } +sub git_snapshot { + my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); + my $have_snapshot = (defined $ctype && defined $suffix); + if (!$have_snapshot) { + die_error('403 Permission denied', "Permission denied"); + } + + if (!defined $hash) { + $hash = git_get_head_hash($project); + } + + my $filename = basename($project) . "-$hash.tar.$suffix"; + + print $cgi->header( + -type => "application/$ctype", + -content_disposition => 'inline; filename="' . "$filename" . '"', + -status => '200 OK'); + + my $git = git_cmd_str(); + my $name = $project; + $name =~ s/\047/\047\\\047\047/g; + open my $fd, "-|", + "$git archive --format=tar --prefix=\'$name\'/ $hash | $command" + or die_error(undef, "Execute git-tar-tree failed."); + binmode STDOUT, ':raw'; + print <$fd>; + binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi + close $fd; + +} + sub git_log { my $head = git_get_head_hash($project); if (!defined $hash) { @@ -2122,28 +3640,25 @@ sub git_log { } my $refs = git_get_references(); - my $limit = sprintf("--max-count=%i", (100 * ($page+1))); - open my $fd, "-|", $GIT, "rev-list", $limit, $hash - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; + my @commitlist = parse_commits($hash, 101, (100 * $page)); - my $paging_nav = format_paging_nav('log', $hash, $head, $page, $#revlist); + my $paging_nav = format_paging_nav('log', $hash, $head, $page, (100 * ($page+1))); git_header_html(); git_print_page_nav('log','', $hash,undef,undef, $paging_nav); - if (!@revlist) { + if (!@commitlist) { my %co = parse_commit($hash); git_print_header_div('summary', $project); print "<div class=\"page_body\"> Last change $co{'age_string'}.<br/><br/></div>\n"; } - for (my $i = ($page * 100); $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my $ref = format_ref_marker($refs, $commit); - my %co = parse_commit($commit); + my $to = ($#commitlist >= 99) ? (99) : ($#commitlist); + for (my $i = 0; $i <= $to; $i++) { + my %co = %{$commitlist[$i]}; next if !%co; + my $commit = $co{'id'}; + my $ref = format_ref_marker($refs, $commit); my %ad = parse_date($co{'author_epoch'}); git_print_header_div('commit', "<span class=\"age\">$co{'age_string'}</span>" . @@ -2152,37 +3667,30 @@ sub git_log { print "<div class=\"title_text\">\n" . "<div class=\"log_link\">\n" . $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . - " | " . $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . "<br/>\n" . "</div>\n" . "<i>" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]</i><br/>\n" . - "</div>\n" . - "<div class=\"log_body\">\n"; - my $comment = $co{'comment'}; - my $empty = 0; - foreach my $line (@$comment) { - if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { - next; - } - if ($line eq "") { - if ($empty) { - next; - } - $empty = 1; - } else { - $empty = 0; - } - print format_log_line_html($line) . "<br/>\n"; - } - if (!$empty) { - print "<br/>\n"; - } + "</div>\n"; + + print "<div class=\"log_body\">\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1); + print "</div>\n"; + } + if ($#commitlist >= 100) { + print "<div class=\"page_nav\">\n"; + print $cgi->a({-href => href(action=>"log", hash=>$hash, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); print "</div>\n"; } git_footer_html(); } sub git_commit { + $hash ||= $hash_base || "HEAD"; my %co = parse_commit($hash); if (!%co) { die_error(undef, "Unknown commit object"); @@ -2190,14 +3698,46 @@ sub git_commit { my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); - my $parent = $co{'parent'}; + my $parent = $co{'parent'}; + my $parents = $co{'parents'}; # listref + + # we need to prepare $formats_nav before any parameter munging + my $formats_nav; + if (!defined $parent) { + # --root commitdiff + $formats_nav .= '(initial)'; + } elsif (@$parents == 1) { + # single parent commit + $formats_nav .= + '(parent: ' . + $cgi->a({-href => href(action=>"commit", + hash=>$parent)}, + esc_html(substr($parent, 0, 7))) . + ')'; + } else { + # merge commit + $formats_nav .= + '(merge: ' . + join(' ', map { + $cgi->a({-href => href(action=>"commitdiff", + hash=>$_)}, + esc_html(substr($_, 0, 7))); + } @$parents ) . + ')'; + } + if (!defined $parent) { $parent = "--root"; } - open my $fd, "-|", $GIT, "diff-tree", '-r', '-M', $parent, $hash - or die_error(undef, "Open git-diff-tree failed"); - my @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); + my @difftree; + if (@$parents <= 1) { + # difftree output is not printed for merges + open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", + @diff_opts, $parent, $hash, "--" + or die_error(undef, "Open git-diff-tree failed"); + @difftree = map { chomp; $_ } <$fd>; + close $fd or die_error(undef, "Reading git-diff-tree failed"); + } # non-textual hash id's can be cached my $expires; @@ -2206,15 +3746,13 @@ sub git_commit { } my $refs = git_get_references(); my $ref = format_ref_marker($refs, $co{'id'}); - my $formats_nav = ''; - if (defined $file_name && defined $co{'parent'}) { - my $parent = $co{'parent'}; - $formats_nav .= $cgi->a({-href => href(action=>"blame", hash_parent=>$parent, file_name=>$file_name)}, "blame"); - } + + my $have_snapshot = gitweb_have_snapshot(); + git_header_html(undef, $expires); - git_print_page_nav('commit', defined $co{'parent'} ? '' : 'commitdiff', - $hash, $co{'tree'}, $hash, - $formats_nav); + git_print_page_nav('commit', '', + $hash, $co{'tree'}, $hash, + $formats_nav); if (defined $co{'parent'}) { git_print_header_div('commitdiff', esc_html($co{'title'}) . $ref, $hash); @@ -2227,281 +3765,503 @@ sub git_commit { "<tr>" . "<td></td><td> $ad{'rfc2822'}"; if ($ad{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", + $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); } else { - printf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + printf(" (%02d:%02d %s)", + $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); } print "</td>" . "</tr>\n"; print "<tr><td>committer</td><td>" . esc_html($co{'committer'}) . "</td></tr>\n"; - print "<tr><td></td><td> $cd{'rfc2822'}" . sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . "</td></tr>\n"; + print "<tr><td></td><td> $cd{'rfc2822'}" . + sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . + "</td></tr>\n"; print "<tr><td>commit</td><td class=\"sha1\">$co{'id'}</td></tr>\n"; print "<tr>" . "<td>tree</td>" . "<td class=\"sha1\">" . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash), class => "list"}, $co{'tree'}) . - "</td>" . - "<td class=\"link\">" . $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash)}, "tree") . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash), + class => "list"}, $co{'tree'}) . "</td>" . + "<td class=\"link\">" . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash)}, + "tree"); + if ($have_snapshot) { + print " | " . + $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, "snapshot"); + } + print "</td>" . "</tr>\n"; - my $parents = $co{'parents'}; + foreach my $par (@$parents) { print "<tr>" . "<td>parent</td>" . - "<td class=\"sha1\">" . $cgi->a({-href => href(action=>"commit", hash=>$par), class => "list"}, $par) . "</td>" . + "<td class=\"sha1\">" . + $cgi->a({-href => href(action=>"commit", hash=>$par), + class => "list"}, $par) . + "</td>" . "<td class=\"link\">" . $cgi->a({-href => href(action=>"commit", hash=>$par)}, "commit") . - " | " . $cgi->a({-href => href(action=>"commitdiff", hash=>$hash, hash_parent=>$par)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$hash, hash_parent=>$par)}, "diff") . "</td>" . "</tr>\n"; } print "</table>". "</div>\n"; + print "<div class=\"page_body\">\n"; - my $comment = $co{'comment'}; - my $empty = 0; - my $signed = 0; - foreach my $line (@$comment) { - # print only one empty line - if ($line eq "") { - if ($empty || $signed) { - next; + git_print_log($co{'comment'}); + print "</div>\n"; + + if (@$parents <= 1) { + # do not output difftree/whatchanged for merges + git_difftree_body(\@difftree, $hash, $parent); + } + + git_footer_html(); +} + +sub git_object { + # object is defined by: + # - hash or hash_base alone + # - hash_base and file_name + my $type; + + # - hash or hash_base alone + if ($hash || ($hash_base && !defined $file_name)) { + my $object_id = $hash || $hash_base; + + my $git_command = git_cmd_str(); + open my $fd, "-|", "$git_command cat-file -t $object_id 2>/dev/null" + or die_error('404 Not Found', "Object does not exist"); + $type = <$fd>; + chomp $type; + close $fd + or die_error('404 Not Found', "Object does not exist"); + + # - hash_base and file_name + } elsif ($hash_base && defined $file_name) { + $file_name =~ s,/+$,,; + + system(git_cmd(), "cat-file", '-e', $hash_base) == 0 + or die_error('404 Not Found', "Base object does not exist"); + + # here errors should not hapen + open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name + or die_error(undef, "Open git-ls-tree failed"); + my $line = <$fd>; + close $fd; + + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' + unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { + die_error('404 Not Found', "File or directory for given base does not exist"); + } + $type = $2; + $hash = $3; + } else { + die_error('404 Not Found', "Not enough information to find object"); + } + + print $cgi->redirect(-uri => href(action=>$type, -full=>1, + hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name), + -status => '302 Found'); +} + +sub git_blobdiff { + my $format = shift || 'html'; + + my $fd; + my @difftree; + my %diffinfo; + my $expires; + + # preparing $fd and %diffinfo for git_patchset_body + # new style URI + if (defined $hash_base && defined $hash_parent_base) { + if (defined $file_name) { + # read raw output + open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + $hash_parent_base, $hash_base, + "--", $file_name + or die_error(undef, "Open git-diff-tree failed"); + @difftree = map { chomp; $_ } <$fd>; + close $fd + or die_error(undef, "Reading git-diff-tree failed"); + @difftree + or die_error('404 Not Found', "Blob diff not found"); + + } elsif (defined $hash && + $hash =~ /[0-9a-fA-F]{40}/) { + # try to find filename from $hash + + # read filtered raw output + open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + $hash_parent_base, $hash_base, "--" + or die_error(undef, "Open git-diff-tree failed"); + @difftree = + # ':100644 100644 03b21826... 3b93d5e7... M ls-files.c' + # $hash == to_id + grep { /^:[0-7]{6} [0-7]{6} [0-9a-fA-F]{40} $hash/ } + map { chomp; $_ } <$fd>; + close $fd + or die_error(undef, "Reading git-diff-tree failed"); + @difftree + or die_error('404 Not Found', "Blob diff not found"); + + } else { + die_error('404 Not Found', "Missing one of the blob diff parameters"); + } + + if (@difftree > 1) { + die_error('404 Not Found', "Ambiguous blob diff specification"); + } + + %diffinfo = parse_difftree_raw_line($difftree[0]); + $file_parent ||= $diffinfo{'from_file'} || $file_name || $diffinfo{'file'}; + $file_name ||= $diffinfo{'to_file'} || $diffinfo{'file'}; + + $hash_parent ||= $diffinfo{'from_id'}; + $hash ||= $diffinfo{'to_id'}; + + # non-textual hash id's can be cached + if ($hash_base =~ m/^[0-9a-fA-F]{40}$/ && + $hash_parent_base =~ m/^[0-9a-fA-F]{40}$/) { + $expires = '+1d'; + } + + # open patch output + open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + '-p', $hash_parent_base, $hash_base, + "--", $file_name + or die_error(undef, "Open git-diff-tree failed"); + } + + # old/legacy style URI + if (!%diffinfo && # if new style URI failed + defined $hash && defined $hash_parent) { + # fake git-diff-tree raw output + $diffinfo{'from_mode'} = $diffinfo{'to_mode'} = "blob"; + $diffinfo{'from_id'} = $hash_parent; + $diffinfo{'to_id'} = $hash; + if (defined $file_name) { + if (defined $file_parent) { + $diffinfo{'status'} = '2'; + $diffinfo{'from_file'} = $file_parent; + $diffinfo{'to_file'} = $file_name; + } else { # assume not renamed + $diffinfo{'status'} = '1'; + $diffinfo{'from_file'} = $file_name; + $diffinfo{'to_file'} = $file_name; } - $empty = 1; + } else { # no filename given + $diffinfo{'status'} = '2'; + $diffinfo{'from_file'} = $hash_parent; + $diffinfo{'to_file'} = $hash; + } + + # non-textual hash id's can be cached + if ($hash =~ m/^[0-9a-fA-F]{40}$/ && + $hash_parent =~ m/^[0-9a-fA-F]{40}$/) { + $expires = '+1d'; + } + + # open patch output + open $fd, "-|", git_cmd(), "diff", '-p', @diff_opts, + $hash_parent, $hash, "--" + or die_error(undef, "Open git-diff failed"); + } else { + die_error('404 Not Found', "Missing one of the blob diff parameters") + unless %diffinfo; + } + + # header + if ($format eq 'html') { + my $formats_nav = + $cgi->a({-href => href(action=>"blobdiff_plain", + hash=>$hash, hash_parent=>$hash_parent, + hash_base=>$hash_base, hash_parent_base=>$hash_parent_base, + file_name=>$file_name, file_parent=>$file_parent)}, + "raw"); + git_header_html(undef, $expires); + if (defined $hash_base && (my %co = parse_commit($hash_base))) { + git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); + git_print_header_div('commit', esc_html($co{'title'}), $hash_base); } else { - $empty = 0; + print "<div class=\"page_nav\"><br/>$formats_nav<br/></div>\n"; + print "<div class=\"title\">$hash vs $hash_parent</div>\n"; } - if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { - $signed = 1; - print "<span class=\"signoff\">" . esc_html($line) . "</span><br/>\n"; + if (defined $file_name) { + git_print_page_path($file_name, "blob", $hash_base); } else { - $signed = 0; - print format_log_line_html($line) . "<br/>\n"; + print "<div class=\"page_path\"></div>\n"; } + + } elsif ($format eq 'plain') { + print $cgi->header( + -type => 'text/plain', + -charset => 'utf-8', + -expires => $expires, + -content_disposition => 'inline; filename="' . "$file_name" . '.patch"'); + + print "X-Git-Url: " . $cgi->self_url() . "\n\n"; + + } else { + die_error(undef, "Unknown blobdiff format"); } - print "</div>\n"; - git_difftree_body(\@difftree, $parent); + # patch + if ($format eq 'html') { + print "<div class=\"page_body\">\n"; - git_footer_html(); -} + git_patchset_body($fd, [ \%diffinfo ], $hash_base, $hash_parent_base); + close $fd; + + print "</div>\n"; # class="page_body" + git_footer_html(); -sub git_blobdiff { - mkdir($git_temp, 0700); - git_header_html(); - if (defined $hash_base && (my %co = parse_commit($hash_base))) { - my $formats_nav = - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blobdiff_plain;h=$hash;hp=$hash_parent")}, "plain"); - git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); } else { - print "<div class=\"page_nav\">\n" . - "<br/><br/></div>\n" . - "<div class=\"title\">$hash vs $hash_parent</div>\n"; - } - git_print_page_path($file_name, "blob"); - print "<div class=\"page_body\">\n" . - "<div class=\"diff_info\">blob:" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$hash_parent;hb=$hash_base;f=$file_name")}, $hash_parent) . - " -> blob:" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$hash;hb=$hash_base;f=$file_name")}, $hash) . - "</div>\n"; - git_diff_print($hash_parent, $file_name || $hash_parent, $hash, $file_name || $hash); - print "</div>"; - git_footer_html(); + while (my $line = <$fd>) { + $line =~ s!a/($hash|$hash_parent)!'a/'.esc_path($diffinfo{'from_file'})!eg; + $line =~ s!b/($hash|$hash_parent)!'b/'.esc_path($diffinfo{'to_file'})!eg; + + print $line; + + last if $line =~ m!^\+\+\+!; + } + local $/ = undef; + print <$fd>; + close $fd; + } } sub git_blobdiff_plain { - mkdir($git_temp, 0700); - print $cgi->header(-type => "text/plain", -charset => 'utf-8'); - git_diff_print($hash_parent, $file_name || $hash_parent, $hash, $file_name || $hash, "plain"); + git_blobdiff('plain'); } sub git_commitdiff { - mkdir($git_temp, 0700); + my $format = shift || 'html'; + $hash ||= $hash_base || "HEAD"; my %co = parse_commit($hash); if (!%co) { die_error(undef, "Unknown commit object"); } - if (!defined $hash_parent) { - $hash_parent = $co{'parent'} || '--root'; - } - open my $fd, "-|", $GIT, "diff-tree", '-r', $hash_parent, $hash - or die_error(undef, "Open git-diff-tree failed"); - my @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); - # non-textual hash id's can be cached - my $expires; - if ($hash =~ m/^[0-9a-fA-F]{40}$/) { - $expires = "+1d"; - } - my $refs = git_get_references(); - my $ref = format_ref_marker($refs, $co{'id'}); - my $formats_nav = - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=commitdiff_plain;h=$hash;hp=$hash_parent")}, "plain"); - git_header_html(undef, $expires); - git_print_page_nav('commitdiff','', $hash,$co{'tree'},$hash, $formats_nav); - git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash); - print "<div class=\"page_body\">\n"; - my $comment = $co{'comment'}; - my $empty = 0; - my $signed = 0; - my @log = @$comment; - # remove first and empty lines after that - shift @log; - while (defined $log[0] && $log[0] eq "") { - shift @log; - } - foreach my $line (@log) { - if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { - next; - } - if ($line eq "") { - if ($empty) { - next; + # we need to prepare $formats_nav before any parameter munging + my $formats_nav; + if ($format eq 'html') { + $formats_nav = + $cgi->a({-href => href(action=>"commitdiff_plain", + hash=>$hash, hash_parent=>$hash_parent)}, + "raw"); + + if (defined $hash_parent) { + # commitdiff with two commits given + my $hash_parent_short = $hash_parent; + if ($hash_parent =~ m/^[0-9a-fA-F]{40}$/) { + $hash_parent_short = substr($hash_parent, 0, 7); } - $empty = 1; + $formats_nav .= + ' (from: ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash_parent)}, + esc_html($hash_parent_short)) . + ')'; + } elsif (!$co{'parent'}) { + # --root commitdiff + $formats_nav .= ' (initial)'; + } elsif (scalar @{$co{'parents'}} == 1) { + # single parent commit + $formats_nav .= + ' (parent: ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$co{'parent'})}, + esc_html(substr($co{'parent'}, 0, 7))) . + ')'; } else { - $empty = 0; - } - print format_log_line_html($line) . "<br/>\n"; - } - print "<br/>\n"; - foreach my $line (@difftree) { - # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' - # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' - if ($line !~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)\t(.*)$/) { - next; - } - my $from_mode = $1; - my $to_mode = $2; - my $from_id = $3; - my $to_id = $4; - my $status = $5; - my $file = validate_input(unquote($6)); - if ($status eq "A") { - print "<div class=\"diff_info\">" . file_type($to_mode) . ":" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$to_id;hb=$hash;f=$file")}, $to_id) . "(new)" . - "</div>\n"; - git_diff_print(undef, "/dev/null", $to_id, "b/$file"); - } elsif ($status eq "D") { - print "<div class=\"diff_info\">" . file_type($from_mode) . ":" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$from_id;hb=$hash_parent;f=$file")}, $from_id) . "(deleted)" . - "</div>\n"; - git_diff_print($from_id, "a/$file", undef, "/dev/null"); - } elsif ($status eq "M") { - if ($from_id ne $to_id) { - print "<div class=\"diff_info\">" . - file_type($from_mode) . ":" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$from_id;hb=$hash_parent;f=$file")}, $from_id) . - " -> " . - file_type($to_mode) . ":" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$to_id;hb=$hash;f=$file")}, $to_id); - print "</div>\n"; - git_diff_print($from_id, "a/$file", $to_id, "b/$file"); - } + # merge commit + $formats_nav .= + ' (merge: ' . + join(' ', map { + $cgi->a({-href => href(action=>"commitdiff", + hash=>$_)}, + esc_html(substr($_, 0, 7))); + } @{$co{'parents'}} ) . + ')'; } } - print "<br/>\n" . - "</div>"; - git_footer_html(); -} -sub git_commitdiff_plain { - mkdir($git_temp, 0700); - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); - } if (!defined $hash_parent) { $hash_parent = $co{'parent'} || '--root'; } - open my $fd, "-|", $GIT, "diff-tree", '-r', $hash_parent, $hash - or die_error(undef, "Open git-diff-tree failed"); - my @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading diff-tree failed"); - # try to figure out the next tag after this commit - my $tagname; - my $refs = git_get_references("tags"); - open $fd, "-|", $GIT, "rev-list", "HEAD"; - my @commits = map { chomp; $_ } <$fd>; - close $fd; - foreach my $commit (@commits) { - if (defined $refs->{$commit}) { - $tagname = $refs->{$commit} - } - if ($commit eq $hash) { - last; + # read commitdiff + my $fd; + my @difftree; + if ($format eq 'html') { + open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + "--no-commit-id", "--patch-with-raw", "--full-index", + $hash_parent, $hash, "--" + or die_error(undef, "Open git-diff-tree failed"); + + while (my $line = <$fd>) { + chomp $line; + # empty line ends raw part of diff-tree output + last unless $line; + push @difftree, $line; } - } - print $cgi->header(-type => "text/plain", -charset => 'utf-8', '-content-disposition' => "inline; filename=\"git-$hash.patch\""); - my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - my $comment = $co{'comment'}; - print "From: $co{'author'}\n" . - "Date: $ad{'rfc2822'} ($ad{'tz_local'})\n". - "Subject: $co{'title'}\n"; - if (defined $tagname) { - print "X-Git-Tag: $tagname\n"; + } elsif ($format eq 'plain') { + open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + '-p', $hash_parent, $hash, "--" + or die_error(undef, "Open git-diff-tree failed"); + + } else { + die_error(undef, "Unknown commitdiff format"); } - print "X-Git-Url: $my_url?p=$project;a=commitdiff;h=$hash\n" . - "\n"; - foreach my $line (@$comment) {; - print "$line\n"; + # non-textual hash id's can be cached + my $expires; + if ($hash =~ m/^[0-9a-fA-F]{40}$/) { + $expires = "+1d"; } - print "---\n\n"; - foreach my $line (@difftree) { - if ($line !~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)\t(.*)$/) { - next; + # write commit message + if ($format eq 'html') { + my $refs = git_get_references(); + my $ref = format_ref_marker($refs, $co{'id'}); + + git_header_html(undef, $expires); + git_print_page_nav('commitdiff','', $hash,$co{'tree'},$hash, $formats_nav); + git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash); + git_print_authorship(\%co); + print "<div class=\"page_body\">\n"; + if (@{$co{'comment'}} > 1) { + print "<div class=\"log\">\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1, -remove_title => 1); + print "</div>\n"; # class="log" } - my $from_id = $3; - my $to_id = $4; - my $status = $5; - my $file = $6; - if ($status eq "A") { - git_diff_print(undef, "/dev/null", $to_id, "b/$file", "plain"); - } elsif ($status eq "D") { - git_diff_print($from_id, "a/$file", undef, "/dev/null", "plain"); - } elsif ($status eq "M") { - git_diff_print($from_id, "a/$file", $to_id, "b/$file", "plain"); + + } elsif ($format eq 'plain') { + my $refs = git_get_references("tags"); + my $tagname = git_get_rev_name_tags($hash); + my $filename = basename($project) . "-$hash.patch"; + + print $cgi->header( + -type => 'text/plain', + -charset => 'utf-8', + -expires => $expires, + -content_disposition => 'inline; filename="' . "$filename" . '"'); + my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); + print <<TEXT; +From: $co{'author'} +Date: $ad{'rfc2822'} ($ad{'tz_local'}) +Subject: $co{'title'} +TEXT + print "X-Git-Tag: $tagname\n" if $tagname; + print "X-Git-Url: " . $cgi->self_url() . "\n\n"; + + foreach my $line (@{$co{'comment'}}) { + print "$line\n"; } + print "---\n\n"; + } + + # write patch + if ($format eq 'html') { + git_difftree_body(\@difftree, $hash, $hash_parent); + print "<br/>\n"; + + git_patchset_body($fd, \@difftree, $hash, $hash_parent); + close $fd; + print "</div>\n"; # class="page_body" + git_footer_html(); + + } elsif ($format eq 'plain') { + local $/ = undef; + print <$fd>; + close $fd + or print "Reading git-diff-tree failed\n"; } } +sub git_commitdiff_plain { + git_commitdiff('plain'); +} + sub git_history { if (!defined $hash_base) { $hash_base = git_get_head_hash($project); } + if (!defined $page) { + $page = 0; + } my $ftype; my %co = parse_commit($hash_base); if (!%co) { die_error(undef, "Unknown commit object"); } + my $refs = git_get_references(); - git_header_html(); - git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); + my $limit = sprintf("--max-count=%i", (100 * ($page+1))); + if (!defined $hash && defined $file_name) { $hash = git_get_hash_by_path($hash_base, $file_name); } if (defined $hash) { $ftype = git_get_type($hash); } - git_print_page_path($file_name, $ftype); - open my $fd, "-|", - $GIT, "rev-list", "--full-history", $hash_base, "--", $file_name; - git_history_body($fd, $refs, $hash_base, $ftype); + my @commitlist = parse_commits($hash_base, 101, (100 * $page), "--full-history", $file_name); + + my $paging_nav = ''; + if ($page > 0) { + $paging_nav .= + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name)}, + "first"); + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name, page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); + } else { + $paging_nav .= "first"; + $paging_nav .= " ⋅ prev"; + } + if ($#commitlist >= 100) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + } else { + $paging_nav .= " ⋅ next"; + } + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + } + + git_header_html(); + git_print_page_nav('history','', $hash_base,$co{'tree'},$hash_base, $paging_nav); + git_print_header_div('commit', esc_html($co{'title'}), $hash_base); + git_print_page_path($file_name, $ftype, $hash_base); + + git_history_body(\@commitlist, 0, 99, + $refs, $hash_base, $ftype, $next_link); - close $fd; git_footer_html(); } sub git_search { + my ($have_search) = gitweb_check_feature('search'); + if (!$have_search) { + die_error('403 Permission denied', "Permission denied"); + } if (!defined $searchtext) { die_error(undef, "Text field empty"); } @@ -2512,79 +4272,82 @@ sub git_search { if (!%co) { die_error(undef, "Unknown commit object"); } - # pickaxe may take all resources of your box and run for several minutes - # with every query - so decide by yourself how public you make this feature :) - my $commit_search = 1; - my $author_search = 0; - my $committer_search = 0; - my $pickaxe_search = 0; - if ($searchtext =~ s/^author\\://i) { - $author_search = 1; - } elsif ($searchtext =~ s/^committer\\://i) { - $committer_search = 1; - } elsif ($searchtext =~ s/^pickaxe\\://i) { - $commit_search = 0; - $pickaxe_search = 1; + if (!defined $page) { + $page = 0; + } + + $searchtype ||= 'commit'; + if ($searchtype eq 'pickaxe') { + # pickaxe may take all resources of your box and run for several minutes + # with every query - so decide by yourself how public you make this feature + my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + if (!$have_pickaxe) { + die_error('403 Permission denied', "Permission denied"); + } } + git_header_html(); - git_print_page_nav('','', $hash,$co{'tree'},$hash); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - print "<table cellspacing=\"0\">\n"; - my $alternate = 0; - if ($commit_search) { - $/ = "\0"; - open my $fd, "-|", $GIT, "rev-list", "--header", "--parents", $hash or next; - while (my $commit_text = <$fd>) { - if (!grep m/$searchtext/i, $commit_text) { - next; - } - if ($author_search && !grep m/\nauthor .*$searchtext/i, $commit_text) { - next; - } - if ($committer_search && !grep m/\ncommitter .*$searchtext/i, $commit_text) { - next; - } - my @commit_lines = split "\n", $commit_text; - my %co = parse_commit(undef, \@commit_lines); - if (!%co) { - next; - } - if ($alternate) { - print "<tr class=\"dark\">\n"; - } else { - print "<tr class=\"light\">\n"; - } - $alternate ^= 1; - print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . - "<td>" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=commit;h=$co{'id'}"), -class => "list"}, "<b>" . esc_html(chop_str($co{'title'}, 50)) . "</b><br/>"); - my $comment = $co{'comment'}; - foreach my $line (@$comment) { - if ($line =~ m/^(.*)($searchtext)(.*)$/i) { - my $lead = esc_html($1) || ""; - $lead = chop_str($lead, 30, 10); - my $match = esc_html($2) || ""; - my $trail = esc_html($3) || ""; - $trail = chop_str($trail, 30, 10); - my $text = "$lead<span class=\"match\">$match</span>$trail"; - print chop_str($text, 80, 5) . "<br/>\n"; - } - } - print "</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=commit;h=$co{'id'}")}, "commit") . - " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=tree;h=$co{'tree'};hb=$co{'id'}")}, "tree"); - print "</td>\n" . - "</tr>\n"; + if ($searchtype eq 'commit' or $searchtype eq 'author' or $searchtype eq 'committer') { + my $greptype; + if ($searchtype eq 'commit') { + $greptype = "--grep="; + } elsif ($searchtype eq 'author') { + $greptype = "--author="; + } elsif ($searchtype eq 'committer') { + $greptype = "--committer="; } - close $fd; + $greptype .= $searchtext; + my @commitlist = parse_commits($hash, 101, (100 * $page), $greptype); + + my $paging_nav = ''; + if ($page > 0) { + $paging_nav .= + $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$searchtext, searchtype=>$searchtype)}, + "first"); + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$searchtext, searchtype=>$searchtype, + page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); + } else { + $paging_nav .= "first"; + $paging_nav .= " ⋅ prev"; + } + if ($#commitlist >= 100) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$searchtext, searchtype=>$searchtype, + page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + } else { + $paging_nav .= " ⋅ next"; + } + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$searchtext, searchtype=>$searchtype, + page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + } + + git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + git_search_grep_body(\@commitlist, 0, 99, $next_link); } - if ($pickaxe_search) { + if ($searchtype eq 'pickaxe') { + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "<table cellspacing=\"0\">\n"; + my $alternate = 1; $/ = "\n"; - open my $fd, "-|", "$GIT rev-list $hash | $GIT diff-tree -r --stdin -S\'$searchtext\'"; + my $git_command = git_cmd_str(); + open my $fd, "-|", "$git_command rev-list $hash | " . + "$git_command diff-tree -r --stdin -S\'$searchtext\'"; undef %co; my @files; while (my $line = <$fd>) { @@ -2612,18 +4375,22 @@ sub git_search { print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . "<td>" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=commit;h=$co{'id'}"), -class => "list"}, "<b>" . - esc_html(chop_str($co{'title'}, 50)) . "</b><br/>"); + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + esc_html(chop_str($co{'title'}, 50)) . "<br/>"); while (my $setref = shift @files) { my %set = %$setref; - print $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=blob;h=$set{'id'};hb=$co{'id'};f=$set{'file'}"), class => "list"}, - "<span class=\"match\">" . esc_html($set{'file'}) . "</span>") . + print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, + hash=>$set{'id'}, file_name=>$set{'file'}), + -class => "list"}, + "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") . "<br/>\n"; } print "</td>\n" . "<td class=\"link\">" . - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=commit;h=$co{'id'}")}, "commit") . - " | " . $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=tree;h=$co{'tree'};hb=$co{'id'}")}, "tree"); + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); print "</td>\n" . "</tr>\n"; } @@ -2631,8 +4398,34 @@ sub git_search { } } close $fd; + + print "</table>\n"; } - print "</table>\n"; + git_footer_html(); +} + +sub git_search_help { + git_header_html(); + git_print_page_nav('','', $hash,$hash,$hash); + print <<EOT; +<dl> +<dt><b>commit</b></dt> +<dd>The commit messages and authorship information will be scanned for the given string.</dd> +<dt><b>author</b></dt> +<dd>Name and e-mail of the change author and date of birth of the patch will be scanned for the given string.</dd> +<dt><b>committer</b></dt> +<dd>Name and e-mail of the committer and date of commit will be scanned for the given string.</dd> +EOT + my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + if ($have_pickaxe) { + print <<EOT; +<dt><b>pickaxe</b></dt> +<dd>All commits that caused the string to appear or disappear from any file (changes that +added, removed or "modified" the string) will be listed. This search can take a while and +takes a lot of strain on the server, so please use it wisely.</dd> +EOT + } + print "</dl>\n"; git_footer_html(); } @@ -2646,102 +4439,268 @@ sub git_shortlog { } my $refs = git_get_references(); - my $limit = sprintf("--max-count=%i", (100 * ($page+1))); - open my $fd, "-|", $GIT, "rev-list", $limit, $hash - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; + my @commitlist = parse_commits($hash, 101, (100 * $page)); - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, $#revlist); + my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, (100 * ($page+1))); my $next_link = ''; - if ($#revlist >= (100 * ($page+1)-1)) { + if ($#commitlist >= 100) { $next_link = - $cgi->a({-href => "$my_uri?" . esc_param("p=$project;a=shortlog;h=$hash;pg=" . ($page+1)), - -title => "Alt-n"}, "next"); + $cgi->a({-href => href(action=>"shortlog", hash=>$hash, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); } - git_header_html(); git_print_page_nav('shortlog','', $hash,$hash,$hash, $paging_nav); git_print_header_div('summary', $project); - git_shortlog_body(\@revlist, ($page * 100), $#revlist, $refs, $next_link); + git_shortlog_body(\@commitlist, 0, 99, $refs, $next_link); git_footer_html(); } ## ...................................................................... -## feeds (RSS, OPML) +## feeds (RSS, Atom; OPML) + +sub git_feed { + my $format = shift || 'atom'; + my ($have_blame) = gitweb_check_feature('blame'); + + # Atom: http://www.atomenabled.org/developers/syndication/ + # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ + if ($format ne 'rss' && $format ne 'atom') { + die_error(undef, "Unknown web feed format"); + } + + # log/feed of current (HEAD) branch, log of given branch, history of file/directory + my $head = $hash || 'HEAD'; + my @commitlist = parse_commits($head, 150); + + my %latest_commit; + my %latest_date; + my $content_type = "application/$format+xml"; + if (defined $cgi->http('HTTP_ACCEPT') && + $cgi->Accept('text/xml') > $cgi->Accept($content_type)) { + # browser (feed reader) prefers text/xml + $content_type = 'text/xml'; + } + if (defined($commitlist[0])) { + %latest_commit = %{$commitlist[0]}; + %latest_date = parse_date($latest_commit{'author_epoch'}); + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + -last_modified => $latest_date{'rfc2822'}); + } else { + print $cgi->header( + -type => $content_type, + -charset => 'utf-8'); + } -sub git_rss { - # http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ - open my $fd, "-|", $GIT, "rev-list", "--max-count=150", git_get_head_hash($project) - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-rev-list failed"); - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); - print "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n". - "<rss version=\"2.0\" xmlns:content=\"http://purl.org/rss/1.0/modules/content/\">\n"; - print "<channel>\n"; - print "<title>$project</title>\n". - "<link>" . esc_html("$my_url?p=$project;a=summary") . "</link>\n". - "<description>$project log</description>\n". - "<language>en</language>\n"; - - for (my $i = 0; $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my %co = parse_commit($commit); + # Optimization: skip generating the body if client asks only + # for Last-Modified date. + return if ($cgi->request_method() eq 'HEAD'); + + # header variables + my $title = "$site_name - $project/$action"; + my $feed_type = 'log'; + if (defined $hash) { + $title .= " - '$hash'"; + $feed_type = 'branch log'; + if (defined $file_name) { + $title .= " :: $file_name"; + $feed_type = 'history'; + } + } elsif (defined $file_name) { + $title .= " - $file_name"; + $feed_type = 'history'; + } + $title .= " $feed_type"; + my $descr = git_get_project_description($project); + if (defined $descr) { + $descr = esc_html($descr); + } else { + $descr = "$project " . + ($format eq 'rss' ? 'RSS' : 'Atom') . + " feed"; + } + my $owner = git_get_project_owner($project); + $owner = esc_html($owner); + + #header + my $alt_url; + if (defined $file_name) { + $alt_url = href(-full=>1, action=>"history", hash=>$hash, file_name=>$file_name); + } elsif (defined $hash) { + $alt_url = href(-full=>1, action=>"log", hash=>$hash); + } else { + $alt_url = href(-full=>1, action=>"summary"); + } + print qq!<?xml version="1.0" encoding="utf-8"?>\n!; + if ($format eq 'rss') { + print <<XML; +<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/"> +<channel> +XML + print "<title>$title</title>\n" . + "<link>$alt_url</link>\n" . + "<description>$descr</description>\n" . + "<language>en</language>\n"; + } elsif ($format eq 'atom') { + print <<XML; +<feed xmlns="http://www.w3.org/2005/Atom"> +XML + print "<title>$title</title>\n" . + "<subtitle>$descr</subtitle>\n" . + '<link rel="alternate" type="text/html" href="' . + $alt_url . '" />' . "\n" . + '<link rel="self" type="' . $content_type . '" href="' . + $cgi->self_url() . '" />' . "\n" . + "<id>" . href(-full=>1) . "</id>\n" . + # use project owner for feed author + "<author><name>$owner</name></author>\n"; + if (defined $favicon) { + print "<icon>" . esc_url($favicon) . "</icon>\n"; + } + if (defined $logo_url) { + # not twice as wide as tall: 72 x 27 pixels + print "<logo>" . esc_url($logo) . "</logo>\n"; + } + if (! %latest_date) { + # dummy date to keep the feed valid until commits trickle in: + print "<updated>1970-01-01T00:00:00Z</updated>\n"; + } else { + print "<updated>$latest_date{'iso-8601'}</updated>\n"; + } + } + + # contents + for (my $i = 0; $i <= $#commitlist; $i++) { + my %co = %{$commitlist[$i]}; + my $commit = $co{'id'}; # we read 150, we always show 30 and the ones more recent than 48 hours - if (($i >= 20) && ((time - $co{'committer_epoch'}) > 48*60*60)) { + if (($i >= 20) && ((time - $co{'author_epoch'}) > 48*60*60)) { last; } - my %cd = parse_date($co{'committer_epoch'}); - open $fd, "-|", $GIT, "diff-tree", '-r', $co{'parent'}, $co{'id'} or next; + my %cd = parse_date($co{'author_epoch'}); + + # get list of changed files + open my $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + $co{'parent'}, $co{'id'}, "--", (defined $file_name ? $file_name : ()) + or next; my @difftree = map { chomp; $_ } <$fd>; - close $fd or next; - print "<item>\n" . - "<title>" . - sprintf("%d %s %02d:%02d", $cd{'mday'}, $cd{'month'}, $cd{'hour'}, $cd{'minute'}) . " - " . esc_html($co{'title'}) . - "</title>\n" . - "<author>" . esc_html($co{'author'}) . "</author>\n" . - "<pubDate>$cd{'rfc2822'}</pubDate>\n" . - "<guid isPermaLink=\"true\">" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "</guid>\n" . - "<link>" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "</link>\n" . - "<description>" . esc_html($co{'title'}) . "</description>\n" . - "<content:encoded>" . - "<![CDATA[\n"; + close $fd + or next; + + # print element (entry, item) + my $co_url = href(-full=>1, action=>"commit", hash=>$commit); + if ($format eq 'rss') { + print "<item>\n" . + "<title>" . esc_html($co{'title'}) . "</title>\n" . + "<author>" . esc_html($co{'author'}) . "</author>\n" . + "<pubDate>$cd{'rfc2822'}</pubDate>\n" . + "<guid isPermaLink=\"true\">$co_url</guid>\n" . + "<link>$co_url</link>\n" . + "<description>" . esc_html($co{'title'}) . "</description>\n" . + "<content:encoded>" . + "<![CDATA[\n"; + } elsif ($format eq 'atom') { + print "<entry>\n" . + "<title type=\"html\">" . esc_html($co{'title'}) . "</title>\n" . + "<updated>$cd{'iso-8601'}</updated>\n" . + "<author>\n" . + " <name>" . esc_html($co{'author_name'}) . "</name>\n"; + if ($co{'author_email'}) { + print " <email>" . esc_html($co{'author_email'}) . "</email>\n"; + } + print "</author>\n" . + # use committer for contributor + "<contributor>\n" . + " <name>" . esc_html($co{'committer_name'}) . "</name>\n"; + if ($co{'committer_email'}) { + print " <email>" . esc_html($co{'committer_email'}) . "</email>\n"; + } + print "</contributor>\n" . + "<published>$cd{'iso-8601'}</published>\n" . + "<link rel=\"alternate\" type=\"text/html\" href=\"$co_url\" />\n" . + "<id>$co_url</id>\n" . + "<content type=\"xhtml\" xml:base=\"" . esc_url($my_url) . "\">\n" . + "<div xmlns=\"http://www.w3.org/1999/xhtml\">\n"; + } my $comment = $co{'comment'}; + print "<pre>\n"; foreach my $line (@$comment) { - $line = decode("utf8", $line, Encode::FB_DEFAULT); - print "$line<br/>\n"; + $line = esc_html($line); + print "$line\n"; } - print "<br/>\n"; - foreach my $line (@difftree) { - if (!($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/)) { - next; + print "</pre><ul>\n"; + foreach my $difftree_line (@difftree) { + my %difftree = parse_difftree_raw_line($difftree_line); + next if !$difftree{'from_id'}; + + my $file = $difftree{'file'} || $difftree{'to_file'}; + + print "<li>" . + "[" . + $cgi->a({-href => href(-full=>1, action=>"blobdiff", + hash=>$difftree{'to_id'}, hash_parent=>$difftree{'from_id'}, + hash_base=>$co{'id'}, hash_parent_base=>$co{'parent'}, + file_name=>$file, file_parent=>$difftree{'from_file'}), + -title => "diff"}, 'D'); + if ($have_blame) { + print $cgi->a({-href => href(-full=>1, action=>"blame", + file_name=>$file, hash_base=>$commit), + -title => "blame"}, 'B'); } - my $file = validate_input(unquote($7)); - $file = decode("utf8", $file, Encode::FB_DEFAULT); - print "$file<br/>\n"; + # if this is not a feed of a file history + if (!defined $file_name || $file_name ne $file) { + print $cgi->a({-href => href(-full=>1, action=>"history", + file_name=>$file, hash=>$commit), + -title => "history"}, 'H'); + } + $file = esc_path($file); + print "] ". + "$file</li>\n"; + } + if ($format eq 'rss') { + print "</ul>]]>\n" . + "</content:encoded>\n" . + "</item>\n"; + } elsif ($format eq 'atom') { + print "</ul>\n</div>\n" . + "</content>\n" . + "</entry>\n"; } - print "]]>\n" . - "</content:encoded>\n" . - "</item>\n"; } - print "</channel></rss>"; + + # end of feed + if ($format eq 'rss') { + print "</channel>\n</rss>\n"; + } elsif ($format eq 'atom') { + print "</feed>\n"; + } +} + +sub git_rss { + git_feed('rss'); +} + +sub git_atom { + git_feed('atom'); } sub git_opml { my @list = git_get_projects_list(); print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); - print "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n". - "<opml version=\"1.0\">\n". - "<head>". - " <title>$site_name Git OPML Export</title>\n". - "</head>\n". - "<body>\n". - "<outline text=\"git RSS feeds\">\n"; + print <<XML; +<?xml version="1.0" encoding="utf-8"?> +<opml version="1.0"> +<head> + <title>$site_name OPML Export</title> +</head> +<body> +<outline text="git RSS feeds"> +XML foreach my $pr (@list) { my %proj = %$pr; @@ -2749,7 +4708,7 @@ sub git_opml { if (!defined $head) { next; } - $ENV{'GIT_DIR'} = "$projectroot/$proj{'path'}"; + $git_dir = "$projectroot/$proj{'path'}"; my %co = parse_commit($head); if (!%co) { next; @@ -2760,7 +4719,9 @@ sub git_opml { my $html = "$my_url?p=$proj{'path'};a=summary"; print "<outline type=\"rss\" text=\"$path\" title=\"$path\" xmlUrl=\"$rss\" htmlUrl=\"$html\"/>\n"; } - print "</outline>\n". - "</body>\n". - "</opml>\n"; + print <<XML; +</outline> +</body> +</opml> +XML } diff --git a/grep.c b/grep.c new file mode 100644 index 0000000000..fcc6762302 --- /dev/null +++ b/grep.c @@ -0,0 +1,575 @@ +#include "cache.h" +#include "grep.h" + +void append_grep_pattern(struct grep_opt *opt, const char *pat, + const char *origin, int no, enum grep_pat_token t) +{ + struct grep_pat *p = xcalloc(1, sizeof(*p)); + p->pattern = pat; + p->origin = origin; + p->no = no; + p->token = t; + *opt->pattern_tail = p; + opt->pattern_tail = &p->next; + p->next = NULL; +} + +static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) +{ + int err = regcomp(&p->regexp, p->pattern, opt->regflags); + if (err) { + char errbuf[1024]; + char where[1024]; + if (p->no) + sprintf(where, "In '%s' at %d, ", + p->origin, p->no); + else if (p->origin) + sprintf(where, "%s, ", p->origin); + else + where[0] = 0; + regerror(err, &p->regexp, errbuf, 1024); + regfree(&p->regexp); + die("%s'%s': %s", where, p->pattern, errbuf); + } +} + +static struct grep_expr *compile_pattern_or(struct grep_pat **); +static struct grep_expr *compile_pattern_atom(struct grep_pat **list) +{ + struct grep_pat *p; + struct grep_expr *x; + + p = *list; + switch (p->token) { + case GREP_PATTERN: /* atom */ + case GREP_PATTERN_HEAD: + case GREP_PATTERN_BODY: + x = xcalloc(1, sizeof (struct grep_expr)); + x->node = GREP_NODE_ATOM; + x->u.atom = p; + *list = p->next; + return x; + case GREP_OPEN_PAREN: + *list = p->next; + x = compile_pattern_or(list); + if (!x) + return NULL; + if (!*list || (*list)->token != GREP_CLOSE_PAREN) + die("unmatched parenthesis"); + *list = (*list)->next; + return x; + default: + return NULL; + } +} + +static struct grep_expr *compile_pattern_not(struct grep_pat **list) +{ + struct grep_pat *p; + struct grep_expr *x; + + p = *list; + switch (p->token) { + case GREP_NOT: + if (!p->next) + die("--not not followed by pattern expression"); + *list = p->next; + x = xcalloc(1, sizeof (struct grep_expr)); + x->node = GREP_NODE_NOT; + x->u.unary = compile_pattern_not(list); + if (!x->u.unary) + die("--not followed by non pattern expression"); + return x; + default: + return compile_pattern_atom(list); + } +} + +static struct grep_expr *compile_pattern_and(struct grep_pat **list) +{ + struct grep_pat *p; + struct grep_expr *x, *y, *z; + + x = compile_pattern_not(list); + p = *list; + if (p && p->token == GREP_AND) { + if (!p->next) + die("--and not followed by pattern expression"); + *list = p->next; + y = compile_pattern_and(list); + if (!y) + die("--and not followed by pattern expression"); + z = xcalloc(1, sizeof (struct grep_expr)); + z->node = GREP_NODE_AND; + z->u.binary.left = x; + z->u.binary.right = y; + return z; + } + return x; +} + +static struct grep_expr *compile_pattern_or(struct grep_pat **list) +{ + struct grep_pat *p; + struct grep_expr *x, *y, *z; + + x = compile_pattern_and(list); + p = *list; + if (x && p && p->token != GREP_CLOSE_PAREN) { + y = compile_pattern_or(list); + if (!y) + die("not a pattern expression %s", p->pattern); + z = xcalloc(1, sizeof (struct grep_expr)); + z->node = GREP_NODE_OR; + z->u.binary.left = x; + z->u.binary.right = y; + return z; + } + return x; +} + +static struct grep_expr *compile_pattern_expr(struct grep_pat **list) +{ + return compile_pattern_or(list); +} + +void compile_grep_patterns(struct grep_opt *opt) +{ + struct grep_pat *p; + + if (opt->all_match) + opt->extended = 1; + + for (p = opt->pattern_list; p; p = p->next) { + switch (p->token) { + case GREP_PATTERN: /* atom */ + case GREP_PATTERN_HEAD: + case GREP_PATTERN_BODY: + if (!opt->fixed) + compile_regexp(p, opt); + break; + default: + opt->extended = 1; + break; + } + } + + if (!opt->extended) + return; + + /* Then bundle them up in an expression. + * A classic recursive descent parser would do. + */ + p = opt->pattern_list; + opt->pattern_expression = compile_pattern_expr(&p); + if (p) + die("incomplete pattern expression: %s", p->pattern); +} + +static void free_pattern_expr(struct grep_expr *x) +{ + switch (x->node) { + case GREP_NODE_ATOM: + break; + case GREP_NODE_NOT: + free_pattern_expr(x->u.unary); + break; + case GREP_NODE_AND: + case GREP_NODE_OR: + free_pattern_expr(x->u.binary.left); + free_pattern_expr(x->u.binary.right); + break; + } + free(x); +} + +void free_grep_patterns(struct grep_opt *opt) +{ + struct grep_pat *p, *n; + + for (p = opt->pattern_list; p; p = n) { + n = p->next; + switch (p->token) { + case GREP_PATTERN: /* atom */ + case GREP_PATTERN_HEAD: + case GREP_PATTERN_BODY: + regfree(&p->regexp); + break; + default: + break; + } + free(p); + } + + if (!opt->extended) + return; + free_pattern_expr(opt->pattern_expression); +} + +static char *end_of_line(char *cp, unsigned long *left) +{ + unsigned long l = *left; + while (l && *cp != '\n') { + l--; + cp++; + } + *left = l; + return cp; +} + +static int word_char(char ch) +{ + return isalnum(ch) || ch == '_'; +} + +static void show_line(struct grep_opt *opt, const char *bol, const char *eol, + const char *name, unsigned lno, char sign) +{ + if (opt->pathname) + printf("%s%c", name, sign); + if (opt->linenum) + printf("%d%c", lno, sign); + printf("%.*s\n", (int)(eol-bol), bol); +} + +/* + * NEEDSWORK: share code with diff.c + */ +#define FIRST_FEW_BYTES 8000 +static int buffer_is_binary(const char *ptr, unsigned long size) +{ + if (FIRST_FEW_BYTES < size) + size = FIRST_FEW_BYTES; + return !!memchr(ptr, 0, size); +} + +static int fixmatch(const char *pattern, char *line, regmatch_t *match) +{ + char *hit = strstr(line, pattern); + if (!hit) { + match->rm_so = match->rm_eo = -1; + return REG_NOMATCH; + } + else { + match->rm_so = hit - line; + match->rm_eo = match->rm_so + strlen(pattern); + return 0; + } +} + +static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol, enum grep_context ctx) +{ + int hit = 0; + int at_true_bol = 1; + regmatch_t pmatch[10]; + + if ((p->token != GREP_PATTERN) && + ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD))) + return 0; + + again: + if (!opt->fixed) { + regex_t *exp = &p->regexp; + hit = !regexec(exp, bol, ARRAY_SIZE(pmatch), + pmatch, 0); + } + else { + hit = !fixmatch(p->pattern, bol, pmatch); + } + + if (hit && opt->word_regexp) { + if ((pmatch[0].rm_so < 0) || + (eol - bol) <= pmatch[0].rm_so || + (pmatch[0].rm_eo < 0) || + (eol - bol) < pmatch[0].rm_eo) + die("regexp returned nonsense"); + + /* Match beginning must be either beginning of the + * line, or at word boundary (i.e. the last char must + * not be a word char). Similarly, match end must be + * either end of the line, or at word boundary + * (i.e. the next char must not be a word char). + */ + if ( ((pmatch[0].rm_so == 0 && at_true_bol) || + !word_char(bol[pmatch[0].rm_so-1])) && + ((pmatch[0].rm_eo == (eol-bol)) || + !word_char(bol[pmatch[0].rm_eo])) ) + ; + else + hit = 0; + + if (!hit && pmatch[0].rm_so + bol + 1 < eol) { + /* There could be more than one match on the + * line, and the first match might not be + * strict word match. But later ones could be! + */ + bol = pmatch[0].rm_so + bol + 1; + at_true_bol = 0; + goto again; + } + } + return hit; +} + +static int match_expr_eval(struct grep_opt *o, + struct grep_expr *x, + char *bol, char *eol, + enum grep_context ctx, + int collect_hits) +{ + int h = 0; + + switch (x->node) { + case GREP_NODE_ATOM: + h = match_one_pattern(o, x->u.atom, bol, eol, ctx); + break; + case GREP_NODE_NOT: + h = !match_expr_eval(o, x->u.unary, bol, eol, ctx, 0); + break; + case GREP_NODE_AND: + if (!collect_hits) + return (match_expr_eval(o, x->u.binary.left, + bol, eol, ctx, 0) && + match_expr_eval(o, x->u.binary.right, + bol, eol, ctx, 0)); + h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0); + h &= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 0); + break; + case GREP_NODE_OR: + if (!collect_hits) + return (match_expr_eval(o, x->u.binary.left, + bol, eol, ctx, 0) || + match_expr_eval(o, x->u.binary.right, + bol, eol, ctx, 0)); + h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0); + x->u.binary.left->hit |= h; + h |= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 1); + break; + default: + die("Unexpected node type (internal error) %d\n", x->node); + } + if (collect_hits) + x->hit |= h; + return h; +} + +static int match_expr(struct grep_opt *opt, char *bol, char *eol, + enum grep_context ctx, int collect_hits) +{ + struct grep_expr *x = opt->pattern_expression; + return match_expr_eval(opt, x, bol, eol, ctx, collect_hits); +} + +static int match_line(struct grep_opt *opt, char *bol, char *eol, + enum grep_context ctx, int collect_hits) +{ + struct grep_pat *p; + if (opt->extended) + return match_expr(opt, bol, eol, ctx, collect_hits); + + /* we do not call with collect_hits without being extended */ + for (p = opt->pattern_list; p; p = p->next) { + if (match_one_pattern(opt, p, bol, eol, ctx)) + return 1; + } + return 0; +} + +static int grep_buffer_1(struct grep_opt *opt, const char *name, + char *buf, unsigned long size, int collect_hits) +{ + char *bol = buf; + unsigned long left = size; + unsigned lno = 1; + struct pre_context_line { + char *bol; + char *eol; + } *prev = NULL, *pcl; + unsigned last_hit = 0; + unsigned last_shown = 0; + int binary_match_only = 0; + const char *hunk_mark = ""; + unsigned count = 0; + enum grep_context ctx = GREP_CONTEXT_HEAD; + + if (buffer_is_binary(buf, size)) { + switch (opt->binary) { + case GREP_BINARY_DEFAULT: + binary_match_only = 1; + break; + case GREP_BINARY_NOMATCH: + return 0; /* Assume unmatch */ + break; + default: + break; + } + } + + if (opt->pre_context) + prev = xcalloc(opt->pre_context, sizeof(*prev)); + if (opt->pre_context || opt->post_context) + hunk_mark = "--\n"; + + while (left) { + char *eol, ch; + int hit; + + eol = end_of_line(bol, &left); + ch = *eol; + *eol = 0; + + if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol)) + ctx = GREP_CONTEXT_BODY; + + hit = match_line(opt, bol, eol, ctx, collect_hits); + *eol = ch; + + if (collect_hits) + goto next_line; + + /* "grep -v -e foo -e bla" should list lines + * that do not have either, so inversion should + * be done outside. + */ + if (opt->invert) + hit = !hit; + if (opt->unmatch_name_only) { + if (hit) + return 0; + goto next_line; + } + if (hit) { + count++; + if (opt->status_only) + return 1; + if (binary_match_only) { + printf("Binary file %s matches\n", name); + return 1; + } + if (opt->name_only) { + printf("%s\n", name); + return 1; + } + /* Hit at this line. If we haven't shown the + * pre-context lines, we would need to show them. + * When asked to do "count", this still show + * the context which is nonsense, but the user + * deserves to get that ;-). + */ + if (opt->pre_context) { + unsigned from; + if (opt->pre_context < lno) + from = lno - opt->pre_context; + else + from = 1; + if (from <= last_shown) + from = last_shown + 1; + if (last_shown && from != last_shown + 1) + printf(hunk_mark); + while (from < lno) { + pcl = &prev[lno-from-1]; + show_line(opt, pcl->bol, pcl->eol, + name, from, '-'); + from++; + } + last_shown = lno-1; + } + if (last_shown && lno != last_shown + 1) + printf(hunk_mark); + if (!opt->count) + show_line(opt, bol, eol, name, lno, ':'); + last_shown = last_hit = lno; + } + else if (last_hit && + lno <= last_hit + opt->post_context) { + /* If the last hit is within the post context, + * we need to show this line. + */ + if (last_shown && lno != last_shown + 1) + printf(hunk_mark); + show_line(opt, bol, eol, name, lno, '-'); + last_shown = lno; + } + if (opt->pre_context) { + memmove(prev+1, prev, + (opt->pre_context-1) * sizeof(*prev)); + prev->bol = bol; + prev->eol = eol; + } + + next_line: + bol = eol + 1; + if (!left) + break; + left--; + lno++; + } + + free(prev); + if (collect_hits) + return 0; + + if (opt->status_only) + return 0; + if (opt->unmatch_name_only) { + /* We did not see any hit, so we want to show this */ + printf("%s\n", name); + return 1; + } + + /* NEEDSWORK: + * The real "grep -c foo *.c" gives many "bar.c:0" lines, + * which feels mostly useless but sometimes useful. Maybe + * make it another option? For now suppress them. + */ + if (opt->count && count) + printf("%s:%u\n", name, count); + return !!last_hit; +} + +static void clr_hit_marker(struct grep_expr *x) +{ + /* All-hit markers are meaningful only at the very top level + * OR node. + */ + while (1) { + x->hit = 0; + if (x->node != GREP_NODE_OR) + return; + x->u.binary.left->hit = 0; + x = x->u.binary.right; + } +} + +static int chk_hit_marker(struct grep_expr *x) +{ + /* Top level nodes have hit markers. See if they all are hits */ + while (1) { + if (x->node != GREP_NODE_OR) + return x->hit; + if (!x->u.binary.left->hit) + return 0; + x = x->u.binary.right; + } +} + +int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size) +{ + /* + * we do not have to do the two-pass grep when we do not check + * buffer-wide "all-match". + */ + if (!opt->all_match) + return grep_buffer_1(opt, name, buf, size, 0); + + /* Otherwise the toplevel "or" terms hit a bit differently. + * We first clear hit markers from them. + */ + clr_hit_marker(opt->pattern_expression); + grep_buffer_1(opt, name, buf, size, 1); + + if (!chk_hit_marker(opt->pattern_expression)) + return 0; + + return grep_buffer_1(opt, name, buf, size, 0); +} diff --git a/grep.h b/grep.h new file mode 100644 index 0000000000..d252dd25f8 --- /dev/null +++ b/grep.h @@ -0,0 +1,81 @@ +#ifndef GREP_H +#define GREP_H + +enum grep_pat_token { + GREP_PATTERN, + GREP_PATTERN_HEAD, + GREP_PATTERN_BODY, + GREP_AND, + GREP_OPEN_PAREN, + GREP_CLOSE_PAREN, + GREP_NOT, + GREP_OR, +}; + +enum grep_context { + GREP_CONTEXT_HEAD, + GREP_CONTEXT_BODY, +}; + +struct grep_pat { + struct grep_pat *next; + const char *origin; + int no; + enum grep_pat_token token; + const char *pattern; + regex_t regexp; +}; + +enum grep_expr_node { + GREP_NODE_ATOM, + GREP_NODE_NOT, + GREP_NODE_AND, + GREP_NODE_OR, +}; + +struct grep_expr { + enum grep_expr_node node; + unsigned hit; + union { + struct grep_pat *atom; + struct grep_expr *unary; + struct { + struct grep_expr *left; + struct grep_expr *right; + } binary; + } u; +}; + +struct grep_opt { + struct grep_pat *pattern_list; + struct grep_pat **pattern_tail; + struct grep_expr *pattern_expression; + int prefix_length; + regex_t regexp; + unsigned linenum:1; + unsigned invert:1; + unsigned status_only:1; + unsigned name_only:1; + unsigned unmatch_name_only:1; + unsigned count:1; + unsigned word_regexp:1; + unsigned fixed:1; + unsigned all_match:1; +#define GREP_BINARY_DEFAULT 0 +#define GREP_BINARY_NOMATCH 1 +#define GREP_BINARY_TEXT 2 + unsigned binary:2; + unsigned extended:1; + unsigned relative:1; + unsigned pathname:1; + int regflags; + unsigned pre_context; + unsigned post_context; +}; + +extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t); +extern void compile_grep_patterns(struct grep_opt *opt); +extern void free_grep_patterns(struct grep_opt *opt); +extern int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size); + +#endif @@ -3,12 +3,11 @@ * * Builtin help-related commands (help, usage, version) */ -#include <sys/ioctl.h> #include "cache.h" #include "builtin.h" #include "exec_cmd.h" #include "common-cmds.h" - +#include <sys/ioctl.h> /* most GUI terminals set COLUMNS (although some don't export it) */ static int term_columns(void) @@ -184,7 +183,7 @@ static void show_man_page(const char *git_cmd) page = git_cmd; else { int page_len = strlen(git_cmd) + 4; - char *p = malloc(page_len + 1); + char *p = xmalloc(page_len + 1); strcpy(p, "git-"); strcpy(p + 4, git_cmd); p[page_len] = 0; diff --git a/http-fetch.c b/http-fetch.c index 7619b338fe..67dfb0a033 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -4,35 +4,6 @@ #include "fetch.h" #include "http.h" -#ifndef NO_EXPAT -#include <expat.h> - -/* Definitions for DAV requests */ -#define DAV_PROPFIND "PROPFIND" -#define DAV_PROPFIND_RESP ".multistatus.response" -#define DAV_PROPFIND_NAME ".multistatus.response.href" -#define DAV_PROPFIND_COLLECTION ".multistatus.response.propstat.prop.resourcetype.collection" -#define PROPFIND_ALL_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:propfind xmlns:D=\"DAV:\">\n<D:allprop/>\n</D:propfind>" - -/* Definitions for processing XML DAV responses */ -#ifndef XML_STATUS_OK -enum XML_Status { - XML_STATUS_OK = 1, - XML_STATUS_ERROR = 0 -}; -#define XML_STATUS_OK 1 -#define XML_STATUS_ERROR 0 -#endif - -/* Flags that control remote_ls processing */ -#define PROCESS_FILES (1u << 0) -#define PROCESS_DIRS (1u << 1) -#define RECURSIVE (1u << 2) - -/* Flags that remote_ls passes to callback functions */ -#define IS_DIR (1u << 0) -#endif - #define PREV_BUF_SIZE 4096 #define RANGE_HEADER_SIZE 30 @@ -90,30 +61,6 @@ struct alternates_request { int http_specific; }; -#ifndef NO_EXPAT -struct xml_ctx -{ - char *name; - int len; - char *cdata; - void (*userFunc)(struct xml_ctx *ctx, int tag_closed); - void *userData; -}; - -struct remote_ls_ctx -{ - struct alt_base *repo; - char *path; - void (*userFunc)(struct remote_ls_ctx *ls); - void *userData; - int flags; - char *dentry_name; - int dentry_flags; - int rc; - struct remote_ls_ctx *parent; -}; -#endif - static struct object_request *object_queue_head; static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, @@ -124,7 +71,7 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, int posn = 0; struct object_request *obj_req = (struct object_request *)data; do { - ssize_t retval = write(obj_req->local, + ssize_t retval = xwrite(obj_req->local, (char *) ptr + posn, size - posn); if (retval < 0) return posn; @@ -144,6 +91,19 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, return size; } +static int missing__target(int code, int result) +{ + return /* file:// URL -- do we ever use one??? */ + (result == CURLE_FILE_COULDNT_READ_FILE) || + /* http:// and https:// URL */ + (code == 404 && result == CURLE_HTTP_RETURNED_ERROR) || + /* ftp:// URL */ + (code == 550 && result == CURLE_FTP_COULDNT_RETR_FILE) + ; +} + +#define missing_target(a) missing__target((a)->http_code, (a)->curl_result) + static void fetch_alternates(const char *base); static void process_object_response(void *callback_data); @@ -215,7 +175,7 @@ static void start_object_request(struct object_request *obj_req) prevlocal = open(prevfile, O_RDONLY); if (prevlocal != -1) { do { - prev_read = read(prevlocal, prev_buf, PREV_BUF_SIZE); + prev_read = xread(prevlocal, prev_buf, PREV_BUF_SIZE); if (prev_read>0) { if (fwrite_sha1_file(prev_buf, 1, @@ -323,8 +283,7 @@ static void process_object_response(void *callback_data) obj_req->state = COMPLETE; /* Use alternates if necessary */ - if (obj_req->http_code == 404 || - obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE) { + if (missing_target(obj_req)) { fetch_alternates(alt->base); if (obj_req->repo->next != NULL) { obj_req->repo = @@ -537,8 +496,7 @@ static void process_alternates_response(void *callback_data) return; } } else if (slot->curl_result != CURLE_OK) { - if (slot->http_code != 404 && - slot->curl_result != CURLE_FILE_COULDNT_READ_FILE) { + if (!missing_target(slot)) { got_alternates = -1; return; } @@ -559,9 +517,36 @@ static void process_alternates_response(void *callback_data) char *target = NULL; char *path; if (data[i] == '/') { - serverlen = strchr(base + 8, '/') - base; - okay = 1; + /* This counts + * http://git.host/pub/scm/linux.git/ + * -----------here^ + * so memcpy(dst, base, serverlen) will + * copy up to "...git.host". + */ + const char *colon_ss = strstr(base,"://"); + if (colon_ss) { + serverlen = (strchr(colon_ss + 3, '/') + - base); + okay = 1; + } } else if (!memcmp(data + i, "../", 3)) { + /* Relative URL; chop the corresponding + * number of subpath from base (and ../ + * from data), and concatenate the result. + * + * The code first drops ../ from data, and + * then drops one ../ from data and one path + * from base. IOW, one extra ../ is dropped + * from data than path is dropped from base. + * + * This is not wrong. The alternate in + * http://git.host/pub/scm/linux.git/ + * to borrow from + * http://git.host/pub/scm/linus.git/ + * is ../../linus.git/objects/. You need + * two ../../ to borrow from your direct + * neighbour. + */ i += 3; serverlen = strlen(base); while (i + 2 < posn && @@ -583,11 +568,13 @@ static void process_alternates_response(void *callback_data) okay = 1; } } - /* skip 'objects' at end */ + /* skip "objects\n" at end */ if (okay) { target = xmalloc(serverlen + posn - i - 6); - strlcpy(target, base, serverlen); - strlcpy(target + serverlen, data + i, posn - i - 6); + memcpy(target, base, serverlen); + memcpy(target + serverlen, data + i, + posn - i - 7); + target[serverlen + posn - i - 7] = 0; if (get_verbosely) fprintf(stderr, "Also look at %s\n", target); @@ -674,209 +661,6 @@ static void fetch_alternates(const char *base) free(url); } -#ifndef NO_EXPAT -static void -xml_start_tag(void *userData, const char *name, const char **atts) -{ - struct xml_ctx *ctx = (struct xml_ctx *)userData; - const char *c = strchr(name, ':'); - int new_len; - - if (c == NULL) - c = name; - else - c++; - - new_len = strlen(ctx->name) + strlen(c) + 2; - - if (new_len > ctx->len) { - ctx->name = xrealloc(ctx->name, new_len); - ctx->len = new_len; - } - strcat(ctx->name, "."); - strcat(ctx->name, c); - - if (ctx->cdata) { - free(ctx->cdata); - ctx->cdata = NULL; - } - - ctx->userFunc(ctx, 0); -} - -static void -xml_end_tag(void *userData, const char *name) -{ - struct xml_ctx *ctx = (struct xml_ctx *)userData; - const char *c = strchr(name, ':'); - char *ep; - - ctx->userFunc(ctx, 1); - - if (c == NULL) - c = name; - else - c++; - - ep = ctx->name + strlen(ctx->name) - strlen(c) - 1; - *ep = 0; -} - -static void -xml_cdata(void *userData, const XML_Char *s, int len) -{ - struct xml_ctx *ctx = (struct xml_ctx *)userData; - if (ctx->cdata) - free(ctx->cdata); - ctx->cdata = xmalloc(len + 1); - strlcpy(ctx->cdata, s, len + 1); -} - -static int remote_ls(struct alt_base *repo, const char *path, int flags, - void (*userFunc)(struct remote_ls_ctx *ls), - void *userData); - -static void handle_remote_ls_ctx(struct xml_ctx *ctx, int tag_closed) -{ - struct remote_ls_ctx *ls = (struct remote_ls_ctx *)ctx->userData; - - if (tag_closed) { - if (!strcmp(ctx->name, DAV_PROPFIND_RESP) && ls->dentry_name) { - if (ls->dentry_flags & IS_DIR) { - if (ls->flags & PROCESS_DIRS) { - ls->userFunc(ls); - } - if (strcmp(ls->dentry_name, ls->path) && - ls->flags & RECURSIVE) { - ls->rc = remote_ls(ls->repo, - ls->dentry_name, - ls->flags, - ls->userFunc, - ls->userData); - } - } else if (ls->flags & PROCESS_FILES) { - ls->userFunc(ls); - } - } else if (!strcmp(ctx->name, DAV_PROPFIND_NAME) && ctx->cdata) { - ls->dentry_name = xmalloc(strlen(ctx->cdata) - - ls->repo->path_len + 1); - strcpy(ls->dentry_name, ctx->cdata + ls->repo->path_len); - } else if (!strcmp(ctx->name, DAV_PROPFIND_COLLECTION)) { - ls->dentry_flags |= IS_DIR; - } - } else if (!strcmp(ctx->name, DAV_PROPFIND_RESP)) { - if (ls->dentry_name) { - free(ls->dentry_name); - } - ls->dentry_name = NULL; - ls->dentry_flags = 0; - } -} - -static int remote_ls(struct alt_base *repo, const char *path, int flags, - void (*userFunc)(struct remote_ls_ctx *ls), - void *userData) -{ - char *url = xmalloc(strlen(repo->base) + strlen(path) + 1); - struct active_request_slot *slot; - struct slot_results results; - struct buffer in_buffer; - struct buffer out_buffer; - char *in_data; - char *out_data; - XML_Parser parser = XML_ParserCreate(NULL); - enum XML_Status result; - struct curl_slist *dav_headers = NULL; - struct xml_ctx ctx; - struct remote_ls_ctx ls; - - ls.flags = flags; - ls.repo = repo; - ls.path = strdup(path); - ls.dentry_name = NULL; - ls.dentry_flags = 0; - ls.userData = userData; - ls.userFunc = userFunc; - ls.rc = 0; - - sprintf(url, "%s%s", repo->base, path); - - out_buffer.size = strlen(PROPFIND_ALL_REQUEST); - out_data = xmalloc(out_buffer.size + 1); - snprintf(out_data, out_buffer.size + 1, PROPFIND_ALL_REQUEST); - out_buffer.posn = 0; - out_buffer.buffer = out_data; - - in_buffer.size = 4096; - in_data = xmalloc(in_buffer.size); - in_buffer.posn = 0; - in_buffer.buffer = in_data; - - dav_headers = curl_slist_append(dav_headers, "Depth: 1"); - dav_headers = curl_slist_append(dav_headers, "Content-Type: text/xml"); - - slot = get_active_slot(); - slot->results = &results; - curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer); - curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size); - curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); - curl_easy_setopt(slot->curl, CURLOPT_FILE, &in_buffer); - curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); - curl_easy_setopt(slot->curl, CURLOPT_URL, url); - curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 1); - curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_PROPFIND); - curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, dav_headers); - - if (start_active_slot(slot)) { - run_active_slot(slot); - if (results.curl_result == CURLE_OK) { - ctx.name = xcalloc(10, 1); - ctx.len = 0; - ctx.cdata = NULL; - ctx.userFunc = handle_remote_ls_ctx; - ctx.userData = &ls; - XML_SetUserData(parser, &ctx); - XML_SetElementHandler(parser, xml_start_tag, - xml_end_tag); - XML_SetCharacterDataHandler(parser, xml_cdata); - result = XML_Parse(parser, in_buffer.buffer, - in_buffer.posn, 1); - free(ctx.name); - - if (result != XML_STATUS_OK) { - ls.rc = error("XML error: %s", - XML_ErrorString( - XML_GetErrorCode(parser))); - } - } else { - ls.rc = -1; - } - } else { - ls.rc = error("Unable to start PROPFIND request"); - } - - free(ls.path); - free(url); - free(out_data); - free(in_buffer.buffer); - curl_slist_free_all(dav_headers); - - return ls.rc; -} - -static void process_ls_pack(struct remote_ls_ctx *ls) -{ - unsigned char sha1[20]; - - if (strlen(ls->dentry_name) == 63 && - !strncmp(ls->dentry_name, "objects/pack/pack-", 18) && - has_extension(ls->dentry_name, ".pack")) { - get_sha1_hex(ls->dentry_name + 18, sha1); - setup_index(ls->repo, sha1); - } -} -#endif - static int fetch_indices(struct alt_base *repo) { unsigned char sha1[20]; @@ -899,12 +683,6 @@ static int fetch_indices(struct alt_base *repo) if (get_verbosely) fprintf(stderr, "Getting pack list for %s\n", repo->base); -#ifndef NO_EXPAT - if (remote_ls(repo, "objects/pack/", PROCESS_FILES, - process_ls_pack, NULL) == 0) - return 0; -#endif - url = xmalloc(strlen(repo->base) + 21); sprintf(url, "%s/objects/info/packs", repo->base); @@ -917,8 +695,7 @@ static int fetch_indices(struct alt_base *repo) if (start_active_slot(slot)) { run_active_slot(slot); if (results.curl_result != CURLE_OK) { - if (results.http_code == 404 || - results.curl_result == CURLE_FILE_COULDNT_READ_FILE) { + if (missing_target(&results)) { repo->got_indices = 1; free(buffer.buffer); return 0; @@ -1032,6 +809,7 @@ static int fetch_pack(struct alt_base *repo, unsigned char *sha1) return error("Unable to start request"); } + target->pack_size = ftell(packfile); fclose(packfile); ret = move_temp_to_file(tmpfile, filename); @@ -1099,8 +877,7 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) ret = error("Request for %s aborted", hex); } else if (obj_req->curl_result != CURLE_OK && obj_req->http_code != 416) { - if (obj_req->http_code == 404 || - obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE) + if (missing_target(obj_req)) ret = -1; /* Be silent, it is probably in a pack. */ else ret = error("%s (curl_result = %d, http_code = %ld, sha1 = %s)", diff --git a/http-push.c b/http-push.c index 8df7a0d576..0a15f53782 100644 --- a/http-push.c +++ b/http-push.c @@ -195,7 +195,7 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, int posn = 0; struct transfer_request *request = (struct transfer_request *)data; do { - ssize_t retval = write(request->local_fileno, + ssize_t retval = xwrite(request->local_fileno, (char *) ptr + posn, size - posn); if (retval < 0) return posn; @@ -288,7 +288,7 @@ static void start_fetch_loose(struct transfer_request *request) prevlocal = open(prevfile, O_RDONLY); if (prevlocal != -1) { do { - prev_read = read(prevlocal, prev_buf, PREV_BUF_SIZE); + prev_read = xread(prevlocal, prev_buf, PREV_BUF_SIZE); if (prev_read>0) { if (fwrite_sha1_file(prev_buf, 1, @@ -770,11 +770,14 @@ static void finish_request(struct transfer_request *request) request->url, curl_errorstr); remote->can_update_info_refs = 0; } else { + off_t pack_size = ftell(request->local_stream); + fclose(request->local_stream); request->local_stream = NULL; if (!move_temp_to_file(request->tmpfile, request->filename)) { target = (struct packed_git *)request->userData; + target->pack_size = pack_size; lst = &remote->packs; while (*lst != target) lst = &((*lst)->next); @@ -1238,10 +1241,8 @@ xml_start_tag(void *userData, const char *name, const char **atts) strcat(ctx->name, "."); strcat(ctx->name, c); - if (ctx->cdata) { - free(ctx->cdata); - ctx->cdata = NULL; - } + free(ctx->cdata); + ctx->cdata = NULL; ctx->userFunc(ctx, 0); } @@ -1268,8 +1269,7 @@ static void xml_cdata(void *userData, const XML_Char *s, int len) { struct xml_ctx *ctx = (struct xml_ctx *)userData; - if (ctx->cdata) - free(ctx->cdata); + free(ctx->cdata); ctx->cdata = xmalloc(len + 1); strlcpy(ctx->cdata, s, len + 1); } @@ -1518,9 +1518,7 @@ static void handle_remote_ls_ctx(struct xml_ctx *ctx, int tag_closed) ls->dentry_flags |= IS_DIR; } } else if (!strcmp(ctx->name, DAV_PROPFIND_RESP)) { - if (ls->dentry_name) { - free(ls->dentry_name); - } + free(ls->dentry_name); ls->dentry_name = NULL; ls->dentry_flags = 0; } @@ -1544,7 +1542,7 @@ static void remote_ls(const char *path, int flags, struct remote_ls_ctx ls; ls.flags = flags; - ls.path = strdup(path); + ls.path = xstrdup(path); ls.dentry_name = NULL; ls.dentry_flags = 0; ls.userData = userData; @@ -1700,7 +1698,7 @@ static int locking_available(void) return lock_flags; } -struct object_list **add_one_object(struct object *obj, struct object_list **p) +static struct object_list **add_one_object(struct object *obj, struct object_list **p) { struct object_list *entry = xmalloc(sizeof(struct object_list)); entry->item = obj; @@ -1743,7 +1741,7 @@ static struct object_list **process_tree(struct tree *tree, die("bad tree object %s", sha1_to_hex(obj->sha1)); obj->flags |= SEEN; - name = strdup(name); + name = xstrdup(name); p = add_one_object(obj, p); me.up = path; me.elem = name; @@ -1869,7 +1867,7 @@ static int update_remote(unsigned char *sha1, struct remote_lock *lock) static struct ref *local_refs, **local_tail; static struct ref *remote_refs, **remote_tail; -static int one_local_ref(const char *refname, const unsigned char *sha1) +static int one_local_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { struct ref *ref; int len = strlen(refname) + 1; @@ -1918,7 +1916,7 @@ static void one_remote_ref(char *refname) static void get_local_heads(void) { local_tail = &local_refs; - for_each_ref(one_local_ref); + for_each_ref(one_local_ref, NULL); } static void get_dav_remote_heads(void) @@ -2472,7 +2470,7 @@ int main(int argc, char **argv) /* Set up revision info for this refspec */ commit_argc = 3; - new_sha1_hex = strdup(sha1_to_hex(ref->new_sha1)); + new_sha1_hex = xstrdup(sha1_to_hex(ref->new_sha1)); old_sha1_hex = NULL; commit_argv[1] = "--objects"; commit_argv[2] = new_sha1_hex; @@ -23,6 +23,7 @@ char *ssl_capath = NULL; char *ssl_cainfo = NULL; long curl_low_speed_limit = -1; long curl_low_speed_time = -1; +int curl_ftp_no_epsv = 0; struct curl_slist *pragma_header; @@ -155,6 +156,11 @@ static int http_options(const char *var, const char *value) return 0; } + if (!strcmp("http.noepsv", var)) { + curl_ftp_no_epsv = git_config_bool(var, value); + return 0; + } + /* Fall back on the default ones */ return git_default_config(var, value); } @@ -196,6 +202,9 @@ static CURL* get_curl_handle(void) curl_easy_setopt(result, CURLOPT_USERAGENT, GIT_USER_AGENT); + if (curl_ftp_no_epsv) + curl_easy_setopt(result, CURLOPT_FTP_USE_EPSV, 0); + return result; } @@ -251,6 +260,9 @@ void http_init(void) max_requests = DEFAULT_MAX_REQUESTS; #endif + if (getenv("GIT_CURL_FTP_NO_EPSV")) + curl_ftp_no_epsv = 1; + #ifndef NO_CURL_EASY_DUPHANDLE curl_default = get_curl_handle(); #endif @@ -18,10 +18,14 @@ #define curl_global_init(a) do { /* nothing */ } while(0) #endif -#if LIBCURL_VERSION_NUM < 0x070c04 +#if (LIBCURL_VERSION_NUM < 0x070c04) || (LIBCURL_VERSION_NUM == 0x071000) #define NO_CURL_EASY_DUPHANDLE #endif +#if LIBCURL_VERSION_NUM < 0x070a03 +#define CURLE_HTTP_RETURNED_ERROR CURLE_HTTP_NOT_FOUND +#endif + struct slot_results { CURLcode curl_result; @@ -7,9 +7,6 @@ */ #include "cache.h" -#include <pwd.h> -#include <netdb.h> - static char git_default_date[50]; static void copy_gecos(struct passwd *w, char *name, int sz) @@ -158,12 +155,17 @@ static int copy(char *buf, int size, int offset, const char *src) static const char au_env[] = "GIT_AUTHOR_NAME"; static const char co_env[] = "GIT_COMMITTER_NAME"; static const char *env_hint = -"\n*** Environment problem:\n" +"\n" "*** Your name cannot be determined from your system services (gecos).\n" -"*** You would need to set %s and %s\n" -"*** environment variables; otherwise you won't be able to perform\n" -"*** certain operations because of \"empty ident\" errors.\n" -"*** Alternatively, you can use user.name configuration variable.\n\n"; +"\n" +"Run\n" +"\n" +" git repo-config user.email \"you@email.com\"\n" +" git repo-config user.name \"Your Name\"\n" +"\n" +"To set the identity in this repository.\n" +"Add --global to set your account\'s default\n" +"\n"; static const char *get_ident(const char *name, const char *email, const char *date_str, int error_on_no_name) @@ -216,3 +218,18 @@ const char *git_committer_info(int error_on_no_name) getenv("GIT_COMMITTER_DATE"), error_on_no_name); } + +void ignore_missing_committer_name() +{ + /* If we did not get a name from the user's gecos entry then + * git_default_name is empty; so instead load the username + * into it as a 'good enough for now' approximation of who + * this user is. + */ + if (!*git_default_name) { + struct passwd *pw = getpwuid(getuid()); + if (!pw) + die("You don't exist. Go away!"); + strlcpy(git_default_name, pw->pw_name, sizeof(git_default_name)); + } +} diff --git a/imap-send.c b/imap-send.c index 65c71c602d..3eaf025720 100644 --- a/imap-send.c +++ b/imap-send.c @@ -24,13 +24,6 @@ #include "cache.h" -#include <assert.h> -#include <netinet/in.h> -#include <netinet/tcp.h> -#include <arpa/inet.h> -#include <sys/socket.h> -#include <netdb.h> - typedef struct store_conf { char *name; const char *path; /* should this be here? its interpretation is driver-specific */ @@ -103,14 +96,13 @@ typedef struct { static int Verbose, Quiet; -static void info( const char *, ... ); -static void warn( const char *, ... ); +static void imap_info( const char *, ... ); +static void imap_warn( const char *, ... ); static char *next_arg( char ** ); static void free_generic_messages( message_t * ); -static int nfvasprintf( char **str, const char *fmt, va_list va ); static int nfsnprintf( char *buf, int blen, const char *fmt, ... ); @@ -232,7 +224,7 @@ socket_perror( const char *func, Socket_t *sock, int ret ) static int socket_read( Socket_t *sock, char *buf, int len ) { - int n = read( sock->fd, buf, len ); + int n = xread( sock->fd, buf, len ); if (n <= 0) { socket_perror( "read", sock, n ); close( sock->fd ); @@ -244,7 +236,7 @@ socket_read( Socket_t *sock, char *buf, int len ) static int socket_write( Socket_t *sock, const char *buf, int len ) { - int n = write( sock->fd, buf, len ); + int n = write_in_full( sock->fd, buf, len ); if (n != len) { socket_perror( "write", sock, n ); close( sock->fd ); @@ -273,7 +265,7 @@ buffer_gets( buffer_t * b, char **s ) n = b->bytes - start; if (n) - memcpy( b->buf, b->buf + start, n ); + memmove(b->buf, b->buf + start, n); b->offset -= start; b->bytes = n; start = 0; @@ -305,7 +297,7 @@ buffer_gets( buffer_t * b, char **s ) } static void -info( const char *msg, ... ) +imap_info( const char *msg, ... ) { va_list va; @@ -318,7 +310,7 @@ info( const char *msg, ... ) } static void -warn( const char *msg, ... ) +imap_warn( const char *msg, ... ) { va_list va; @@ -372,21 +364,6 @@ free_generic_messages( message_t *msgs ) } static int -git_vasprintf( char **strp, const char *fmt, va_list ap ) -{ - int len; - char tmp[1024]; - - if ((len = vsnprintf( tmp, sizeof(tmp), fmt, ap )) < 0 || !(*strp = xmalloc( len + 1 ))) - return -1; - if (len >= (int)sizeof(tmp)) - vsprintf( *strp, fmt, ap ); - else - memcpy( *strp, tmp, len + 1 ); - return len; -} - -static int nfsnprintf( char *buf, int blen, const char *fmt, ... ) { int ret; @@ -399,15 +376,6 @@ nfsnprintf( char *buf, int blen, const char *fmt, ... ) return ret; } -static int -nfvasprintf( char **str, const char *fmt, va_list va ) -{ - int ret = git_vasprintf( str, fmt, va ); - if (ret < 0) - die( "Fatal: Out of memory\n"); - return ret; -} - static struct { unsigned char i, j, s[256]; } rs; @@ -422,7 +390,7 @@ arc4_init( void ) fprintf( stderr, "Fatal: no random number source available.\n" ); exit( 3 ); } - if (read( fd, dat, 128 ) != 128) { + if (read_in_full( fd, dat, 128 ) != 128) { fprintf( stderr, "Fatal: cannot read random number source.\n" ); exit( 3 ); } @@ -935,7 +903,7 @@ imap_open_store( imap_server_conf_t *srvc ) /* open connection to IMAP server */ if (srvc->tunnel) { - info( "Starting tunnel '%s'... ", srvc->tunnel ); + imap_info( "Starting tunnel '%s'... ", srvc->tunnel ); if (socketpair( PF_UNIX, SOCK_STREAM, 0, a )) { perror( "socketpair" ); @@ -958,31 +926,31 @@ imap_open_store( imap_server_conf_t *srvc ) imap->buf.sock.fd = a[1]; - info( "ok\n" ); + imap_info( "ok\n" ); } else { memset( &addr, 0, sizeof(addr) ); addr.sin_port = htons( srvc->port ); addr.sin_family = AF_INET; - info( "Resolving %s... ", srvc->host ); + imap_info( "Resolving %s... ", srvc->host ); he = gethostbyname( srvc->host ); if (!he) { perror( "gethostbyname" ); goto bail; } - info( "ok\n" ); + imap_info( "ok\n" ); addr.sin_addr.s_addr = *((int *) he->h_addr_list[0]); s = socket( PF_INET, SOCK_STREAM, 0 ); - info( "Connecting to %s:%hu... ", inet_ntoa( addr.sin_addr ), ntohs( addr.sin_port ) ); + imap_info( "Connecting to %s:%hu... ", inet_ntoa( addr.sin_addr ), ntohs( addr.sin_port ) ); if (connect( s, (struct sockaddr *)&addr, sizeof(addr) )) { close( s ); perror( "connect" ); goto bail; } - info( "ok\n" ); + imap_info( "ok\n" ); imap->buf.sock.fd = s; @@ -1011,7 +979,7 @@ imap_open_store( imap_server_conf_t *srvc ) if (!preauth) { - info ("Logging in...\n"); + imap_info ("Logging in...\n"); if (!srvc->user) { fprintf( stderr, "Skipping server %s, no user\n", srvc->host ); goto bail; @@ -1032,13 +1000,13 @@ imap_open_store( imap_server_conf_t *srvc ) * getpass() returns a pointer to a static buffer. make a copy * for long term storage. */ - srvc->pass = strdup( arg ); + srvc->pass = xstrdup( arg ); } if (CAP(NOLOGIN)) { fprintf( stderr, "Skipping account %s@%s, server forbids LOGIN\n", srvc->user, srvc->host ); goto bail; } - warn( "*** IMAP Warning *** Password is being sent in the clear\n" ); + imap_warn( "*** IMAP Warning *** Password is being sent in the clear\n" ); if (imap_exec( ctx, NULL, "LOGIN \"%s\" \"%s\"", srvc->user, srvc->pass ) != RESP_OK) { fprintf( stderr, "IMAP error: LOGIN failed\n" ); goto bail; @@ -1251,6 +1219,14 @@ split_msg( msg_data_t *all_msgs, msg_data_t *msg, int *ofs ) if (msg->len < 5 || strncmp( data, "From ", 5 )) return 0; + p = strchr( data, '\n' ); + if (p) { + p = &p[1]; + msg->len -= p-data; + *ofs += p-data; + data = p; + } + p = strstr( data, "\nFrom " ); if (p) msg->len = &p[1] - data; @@ -1288,7 +1264,7 @@ git_imap_config(const char *key, const char *val) key += sizeof imap_key - 1; if (!strcmp( "folder", key )) { - imap_folder = strdup( val ); + imap_folder = xstrdup( val ); } else if (!strcmp( "host", key )) { { if (!strncmp( "imap:", val, 5 )) @@ -1298,16 +1274,16 @@ git_imap_config(const char *key, const char *val) } if (!strncmp( "//", val, 2 )) val += 2; - server.host = strdup( val ); + server.host = xstrdup( val ); } else if (!strcmp( "user", key )) - server.user = strdup( val ); + server.user = xstrdup( val ); else if (!strcmp( "pass", key )) - server.pass = strdup( val ); + server.pass = xstrdup( val ); else if (!strcmp( "port", key )) server.port = git_config_int( key, val ); else if (!strcmp( "tunnel", key )) - server.tunnel = strdup( val ); + server.tunnel = xstrdup( val ); return 0; } diff --git a/index-pack.c b/index-pack.c index 80bc6cb45b..72e0962415 100644 --- a/index-pack.c +++ b/index-pack.c @@ -8,82 +8,169 @@ #include "tree.h" static const char index_pack_usage[] = -"git-index-pack [-o index-file] pack-file"; +"git-index-pack [-v] [-o <index-file>] [{ ---keep | --keep=<msg> }] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }"; struct object_entry { unsigned long offset; + unsigned long size; + unsigned int hdr_size; enum object_type type; enum object_type real_type; unsigned char sha1[20]; }; +union delta_base { + unsigned char sha1[20]; + unsigned long offset; +}; + +/* + * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want + * to memcmp() only the first 20 bytes. + */ +#define UNION_BASE_SZ 20 + struct delta_entry { - struct object_entry *obj; - unsigned char base_sha1[20]; + union delta_base base; + int obj_no; }; -static const char *pack_name; -static unsigned char *pack_base; -static unsigned long pack_size; static struct object_entry *objects; static struct delta_entry *deltas; static int nr_objects; static int nr_deltas; +static int nr_resolved_deltas; + +static int from_stdin; +static int verbose; + +static volatile sig_atomic_t progress_update; -static void open_pack_file(void) +static void progress_interval(int signum) { - int fd; - struct stat st; + progress_update = 1; +} - fd = open(pack_name, O_RDONLY); - if (fd < 0) - die("cannot open packfile '%s': %s", pack_name, - strerror(errno)); - if (fstat(fd, &st)) { - int err = errno; - close(fd); - die("cannot fstat packfile '%s': %s", pack_name, - strerror(err)); +static void setup_progress_signal(void) +{ + struct sigaction sa; + struct itimerval v; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = progress_interval; + sigemptyset(&sa.sa_mask); + sa.sa_flags = SA_RESTART; + sigaction(SIGALRM, &sa, NULL); + + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + setitimer(ITIMER_REAL, &v, NULL); + +} + +static unsigned display_progress(unsigned n, unsigned total, unsigned last_pc) +{ + unsigned percent = n * 100 / total; + if (percent != last_pc || progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", percent, n, total); + progress_update = 0; } - pack_size = st.st_size; - pack_base = mmap(NULL, pack_size, PROT_READ, MAP_PRIVATE, fd, 0); - if (pack_base == MAP_FAILED) { - int err = errno; - close(fd); - die("cannot mmap packfile '%s': %s", pack_name, - strerror(err)); + return percent; +} + +/* We always read in 4kB chunks. */ +static unsigned char input_buffer[4096]; +static unsigned long input_offset, input_len, consumed_bytes; +static SHA_CTX input_ctx; +static int input_fd, output_fd, pack_fd; + +/* Discard current buffer used content. */ +static void flush(void) +{ + if (input_offset) { + if (output_fd >= 0) + write_or_die(output_fd, input_buffer, input_offset); + SHA1_Update(&input_ctx, input_buffer, input_offset); + memmove(input_buffer, input_buffer + input_offset, input_len); + input_offset = 0; } - close(fd); } -static void parse_pack_header(void) +/* + * Make sure at least "min" bytes are available in the buffer, and + * return the pointer to the buffer. + */ +static void *fill(int min) { - const struct pack_header *hdr; - unsigned char sha1[20]; - SHA_CTX ctx; + if (min <= input_len) + return input_buffer + input_offset; + if (min > sizeof(input_buffer)) + die("cannot fill %d bytes", min); + flush(); + do { + int ret = xread(input_fd, input_buffer + input_len, + sizeof(input_buffer) - input_len); + if (ret <= 0) { + if (!ret) + die("early EOF"); + die("read error on input: %s", strerror(errno)); + } + input_len += ret; + } while (input_len < min); + return input_buffer; +} + +static void use(int bytes) +{ + if (bytes > input_len) + die("used more bytes than were available"); + input_len -= bytes; + input_offset += bytes; + consumed_bytes += bytes; +} + +static const char *open_pack_file(const char *pack_name) +{ + if (from_stdin) { + input_fd = 0; + if (!pack_name) { + static char tmpfile[PATH_MAX]; + snprintf(tmpfile, sizeof(tmpfile), + "%s/pack_XXXXXX", get_object_directory()); + output_fd = mkstemp(tmpfile); + pack_name = xstrdup(tmpfile); + } else + output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600); + if (output_fd < 0) + die("unable to create %s: %s\n", pack_name, strerror(errno)); + pack_fd = output_fd; + } else { + input_fd = open(pack_name, O_RDONLY); + if (input_fd < 0) + die("cannot open packfile '%s': %s", + pack_name, strerror(errno)); + output_fd = -1; + pack_fd = input_fd; + } + SHA1_Init(&input_ctx); + return pack_name; +} - /* Ensure there are enough bytes for the header and final SHA1 */ - if (pack_size < sizeof(struct pack_header) + 20) - die("packfile '%s' is too small", pack_name); +static void parse_pack_header(void) +{ + struct pack_header *hdr = fill(sizeof(struct pack_header)); /* Header consistency check */ - hdr = (void *)pack_base; if (hdr->hdr_signature != htonl(PACK_SIGNATURE)) - die("packfile '%s' signature mismatch", pack_name); + die("pack signature mismatch"); if (!pack_version_ok(hdr->hdr_version)) - die("packfile '%s' version %d unsupported", - pack_name, ntohl(hdr->hdr_version)); + die("pack version %d unsupported", ntohl(hdr->hdr_version)); nr_objects = ntohl(hdr->hdr_entries); - - /* Check packfile integrity */ - SHA1_Init(&ctx); - SHA1_Update(&ctx, pack_base, pack_size - 20); - SHA1_Final(sha1, &ctx); - if (hashcmp(sha1, pack_base + pack_size - 20)) - die("packfile '%s' SHA1 mismatch", pack_name); + use(sizeof(struct pack_header)); } static void bad_object(unsigned long offset, const char *format, @@ -97,90 +184,122 @@ static void bad_object(unsigned long offset, const char *format, ...) va_start(params, format); vsnprintf(buf, sizeof(buf), format, params); va_end(params); - die("packfile '%s': bad object at offset %lu: %s", - pack_name, offset, buf); + die("pack has bad object at offset %lu: %s", offset, buf); } -static void *unpack_entry_data(unsigned long offset, - unsigned long *current_pos, unsigned long size) +static void *unpack_entry_data(unsigned long offset, unsigned long size) { - unsigned long pack_limit = pack_size - 20; - unsigned long pos = *current_pos; z_stream stream; void *buf = xmalloc(size); memset(&stream, 0, sizeof(stream)); stream.next_out = buf; stream.avail_out = size; - stream.next_in = pack_base + pos; - stream.avail_in = pack_limit - pos; + stream.next_in = fill(1); + stream.avail_in = input_len; inflateInit(&stream); for (;;) { int ret = inflate(&stream, 0); - if (ret == Z_STREAM_END) + use(input_len - stream.avail_in); + if (stream.total_out == size && ret == Z_STREAM_END) break; if (ret != Z_OK) bad_object(offset, "inflate returned %d", ret); + stream.next_in = fill(1); + stream.avail_in = input_len; } inflateEnd(&stream); - if (stream.total_out != size) - bad_object(offset, "size mismatch (expected %lu, got %lu)", - size, stream.total_out); - *current_pos = pack_limit - stream.avail_in; return buf; } -static void *unpack_raw_entry(unsigned long offset, - enum object_type *obj_type, - unsigned long *obj_size, - unsigned char *delta_base, - unsigned long *next_obj_offset) +static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base) { - unsigned long pack_limit = pack_size - 20; - unsigned long pos = offset; - unsigned char c; - unsigned long size; + unsigned char *p, c; + unsigned long size, base_offset; unsigned shift; - enum object_type type; - void *data; - c = pack_base[pos++]; - type = (c >> 4) & 7; + obj->offset = consumed_bytes; + + p = fill(1); + c = *p; + use(1); + obj->type = (c >> 4) & 7; size = (c & 15); shift = 4; while (c & 0x80) { - if (pos >= pack_limit) - bad_object(offset, "object extends past end of pack"); - c = pack_base[pos++]; + p = fill(1); + c = *p; + use(1); size += (c & 0x7fUL) << shift; shift += 7; } + obj->size = size; - switch (type) { - case OBJ_DELTA: - if (pos + 20 >= pack_limit) - bad_object(offset, "object extends past end of pack"); - hashcpy(delta_base, pack_base + pos); - pos += 20; - /* fallthru */ + switch (obj->type) { + case OBJ_REF_DELTA: + hashcpy(delta_base->sha1, fill(20)); + use(20); + break; + case OBJ_OFS_DELTA: + memset(delta_base, 0, sizeof(*delta_base)); + p = fill(1); + c = *p; + use(1); + base_offset = c & 127; + while (c & 128) { + base_offset += 1; + if (!base_offset || base_offset & ~(~0UL >> 7)) + bad_object(obj->offset, "offset value overflow for delta base object"); + p = fill(1); + c = *p; + use(1); + base_offset = (base_offset << 7) + (c & 127); + } + delta_base->offset = obj->offset - base_offset; + if (delta_base->offset >= obj->offset) + bad_object(obj->offset, "delta base offset is out of bound"); + break; case OBJ_COMMIT: case OBJ_TREE: case OBJ_BLOB: case OBJ_TAG: - data = unpack_entry_data(offset, &pos, size); break; default: - bad_object(offset, "bad object type %d", type); + bad_object(obj->offset, "unknown object type %d", obj->type); } + obj->hdr_size = consumed_bytes - obj->offset; - *obj_type = type; - *obj_size = size; - *next_obj_offset = pos; + return unpack_entry_data(obj->offset, obj->size); +} + +static void *get_data_from_pack(struct object_entry *obj) +{ + unsigned long from = obj[0].offset + obj[0].hdr_size; + unsigned long len = obj[1].offset - from; + unsigned char *src, *data; + z_stream stream; + int st; + + src = xmalloc(len); + if (pread(pack_fd, src, len, from) != len) + die("cannot pread pack file: %s", strerror(errno)); + data = xmalloc(obj->size); + memset(&stream, 0, sizeof(stream)); + stream.next_out = data; + stream.avail_out = obj->size; + stream.next_in = src; + stream.avail_in = len; + inflateInit(&stream); + while ((st = inflate(&stream, Z_FINISH)) == Z_OK); + inflateEnd(&stream); + if (st != Z_STREAM_END || stream.total_out != obj->size) + die("serious inflate inconsistency"); + free(src); return data; } -static int find_delta(const unsigned char *base_sha1) +static int find_delta(const union delta_base *base) { int first = 0, last = nr_deltas; @@ -189,7 +308,7 @@ static int find_delta(const unsigned char *base_sha1) struct delta_entry *delta = &deltas[next]; int cmp; - cmp = hashcmp(base_sha1, delta->base_sha1); + cmp = memcmp(base, &delta->base, UNION_BASE_SZ); if (!cmp) return next; if (cmp < 0) { @@ -201,18 +320,18 @@ static int find_delta(const unsigned char *base_sha1) return -first-1; } -static int find_deltas_based_on_sha1(const unsigned char *base_sha1, - int *first_index, int *last_index) +static int find_delta_children(const union delta_base *base, + int *first_index, int *last_index) { - int first = find_delta(base_sha1); + int first = find_delta(base); int last = first; int end = nr_deltas - 1; if (first < 0) return -1; - while (first > 0 && !hashcmp(deltas[first - 1].base_sha1, base_sha1)) + while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ)) --first; - while (last < end && !hashcmp(deltas[last + 1].base_sha1, base_sha1)) + while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ)) ++last; *first_index = first; *last_index = last; @@ -244,33 +363,46 @@ static void sha1_object(const void *data, unsigned long size, SHA1_Final(sha1, &ctx); } -static void resolve_delta(struct delta_entry *delta, void *base_data, +static void resolve_delta(struct object_entry *delta_obj, void *base_data, unsigned long base_size, enum object_type type) { - struct object_entry *obj = delta->obj; void *delta_data; unsigned long delta_size; void *result; unsigned long result_size; - enum object_type delta_type; - unsigned char base_sha1[20]; - unsigned long next_obj_offset; + union delta_base delta_base; int j, first, last; - obj->real_type = type; - delta_data = unpack_raw_entry(obj->offset, &delta_type, - &delta_size, base_sha1, - &next_obj_offset); + delta_obj->real_type = type; + delta_data = get_data_from_pack(delta_obj); + delta_size = delta_obj->size; result = patch_delta(base_data, base_size, delta_data, delta_size, &result_size); free(delta_data); if (!result) - bad_object(obj->offset, "failed to apply delta"); - sha1_object(result, result_size, type, obj->sha1); - if (!find_deltas_based_on_sha1(obj->sha1, &first, &last)) { - for (j = first; j <= last; j++) - resolve_delta(&deltas[j], result, result_size, type); + bad_object(delta_obj->offset, "failed to apply delta"); + sha1_object(result, result_size, type, delta_obj->sha1); + nr_resolved_deltas++; + + hashcpy(delta_base.sha1, delta_obj->sha1); + if (!find_delta_children(&delta_base, &first, &last)) { + for (j = first; j <= last; j++) { + struct object_entry *child = objects + deltas[j].obj_no; + if (child->real_type == OBJ_REF_DELTA) + resolve_delta(child, result, result_size, type); + } + } + + memset(&delta_base, 0, sizeof(delta_base)); + delta_base.offset = delta_obj->offset; + if (!find_delta_children(&delta_base, &first, &last)) { + for (j = first; j <= last; j++) { + struct object_entry *child = objects + deltas[j].obj_no; + if (child->real_type == OBJ_OFS_DELTA) + resolve_delta(child, result, result_size, type); + } } + free(result); } @@ -278,41 +410,60 @@ static int compare_delta_entry(const void *a, const void *b) { const struct delta_entry *delta_a = a; const struct delta_entry *delta_b = b; - return hashcmp(delta_a->base_sha1, delta_b->base_sha1); + return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ); } -static void parse_pack_objects(void) +/* Parse all objects and return the pack content SHA1 hash */ +static void parse_pack_objects(unsigned char *sha1) { - int i; - unsigned long offset = sizeof(struct pack_header); - unsigned char base_sha1[20]; + int i, percent = -1; + struct delta_entry *delta = deltas; void *data; - unsigned long data_size; + struct stat st; /* * First pass: * - find locations of all objects; * - calculate SHA1 of all non-delta objects; - * - remember base SHA1 for all deltas. + * - remember base (SHA1 or offset) for all deltas. */ + if (verbose) + fprintf(stderr, "Indexing %d objects.\n", nr_objects); for (i = 0; i < nr_objects; i++) { struct object_entry *obj = &objects[i]; - obj->offset = offset; - data = unpack_raw_entry(offset, &obj->type, &data_size, - base_sha1, &offset); + data = unpack_raw_entry(obj, &delta->base); obj->real_type = obj->type; - if (obj->type == OBJ_DELTA) { - struct delta_entry *delta = &deltas[nr_deltas++]; - delta->obj = obj; - hashcpy(delta->base_sha1, base_sha1); + if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) { + nr_deltas++; + delta->obj_no = i; + delta++; } else - sha1_object(data, data_size, obj->type, obj->sha1); + sha1_object(data, obj->size, obj->type, obj->sha1); free(data); + if (verbose) + percent = display_progress(i+1, nr_objects, percent); } - if (offset != pack_size - 20) - die("packfile '%s' has junk at the end", pack_name); - - /* Sort deltas by base SHA1 for fast searching */ + objects[i].offset = consumed_bytes; + if (verbose) + fputc('\n', stderr); + + /* Check pack integrity */ + flush(); + SHA1_Final(sha1, &input_ctx); + if (hashcmp(fill(20), sha1)) + die("pack is corrupted (SHA1 mismatch)"); + use(20); + + /* If input_fd is a file, we should have reached its end now. */ + if (fstat(input_fd, &st)) + die("cannot fstat packfile: %s", strerror(errno)); + if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes) + die("pack has junk at the end"); + + if (!nr_deltas) + return; + + /* Sort deltas by base SHA1/offset for fast searching */ qsort(deltas, nr_deltas, sizeof(struct delta_entry), compare_delta_entry); @@ -324,26 +475,189 @@ static void parse_pack_objects(void) * recursively checking if the resulting object is used as a base * for some more deltas. */ + if (verbose) + fprintf(stderr, "Resolving %d deltas.\n", nr_deltas); for (i = 0; i < nr_objects; i++) { struct object_entry *obj = &objects[i]; - int j, first, last; + union delta_base base; + int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last; - if (obj->type == OBJ_DELTA) + if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) continue; - if (find_deltas_based_on_sha1(obj->sha1, &first, &last)) + hashcpy(base.sha1, obj->sha1); + ref = !find_delta_children(&base, &ref_first, &ref_last); + memset(&base, 0, sizeof(base)); + base.offset = obj->offset; + ofs = !find_delta_children(&base, &ofs_first, &ofs_last); + if (!ref && !ofs) continue; - data = unpack_raw_entry(obj->offset, &obj->type, &data_size, - base_sha1, &offset); - for (j = first; j <= last; j++) - resolve_delta(&deltas[j], data, data_size, obj->type); + data = get_data_from_pack(obj); + if (ref) + for (j = ref_first; j <= ref_last; j++) { + struct object_entry *child = objects + deltas[j].obj_no; + if (child->real_type == OBJ_REF_DELTA) + resolve_delta(child, data, + obj->size, obj->type); + } + if (ofs) + for (j = ofs_first; j <= ofs_last; j++) { + struct object_entry *child = objects + deltas[j].obj_no; + if (child->real_type == OBJ_OFS_DELTA) + resolve_delta(child, data, + obj->size, obj->type); + } free(data); + if (verbose) + percent = display_progress(nr_resolved_deltas, + nr_deltas, percent); } + if (verbose && nr_resolved_deltas == nr_deltas) + fputc('\n', stderr); +} + +static int write_compressed(int fd, void *in, unsigned int size) +{ + z_stream stream; + unsigned long maxsize; + void *out; + + memset(&stream, 0, sizeof(stream)); + deflateInit(&stream, zlib_compression_level); + maxsize = deflateBound(&stream, size); + out = xmalloc(maxsize); + + /* Compress it */ + stream.next_in = in; + stream.avail_in = size; + stream.next_out = out; + stream.avail_out = maxsize; + while (deflate(&stream, Z_FINISH) == Z_OK); + deflateEnd(&stream); + + size = stream.total_out; + write_or_die(fd, out, size); + free(out); + return size; +} + +static void append_obj_to_pack(void *buf, + unsigned long size, enum object_type type) +{ + struct object_entry *obj = &objects[nr_objects++]; + unsigned char header[10]; + unsigned long s = size; + int n = 0; + unsigned char c = (type << 4) | (s & 15); + s >>= 4; + while (s) { + header[n++] = c | 0x80; + c = s & 0x7f; + s >>= 7; + } + header[n++] = c; + write_or_die(output_fd, header, n); + obj[1].offset = obj[0].offset + n; + obj[1].offset += write_compressed(output_fd, buf, size); + sha1_object(buf, size, type, obj->sha1); +} + +static int delta_pos_compare(const void *_a, const void *_b) +{ + struct delta_entry *a = *(struct delta_entry **)_a; + struct delta_entry *b = *(struct delta_entry **)_b; + return a->obj_no - b->obj_no; +} + +static void fix_unresolved_deltas(int nr_unresolved) +{ + struct delta_entry **sorted_by_pos; + int i, n = 0, percent = -1; - /* Check for unresolved deltas */ + /* + * Since many unresolved deltas may well be themselves base objects + * for more unresolved deltas, we really want to include the + * smallest number of base objects that would cover as much delta + * as possible by picking the + * trunc deltas first, allowing for other deltas to resolve without + * additional base objects. Since most base objects are to be found + * before deltas depending on them, a good heuristic is to start + * resolving deltas in the same order as their position in the pack. + */ + sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos)); for (i = 0; i < nr_deltas; i++) { - if (deltas[i].obj->real_type == OBJ_DELTA) - die("packfile '%s' has unresolved deltas", pack_name); + if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA) + continue; + sorted_by_pos[n++] = &deltas[i]; + } + qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare); + + for (i = 0; i < n; i++) { + struct delta_entry *d = sorted_by_pos[i]; + void *data; + unsigned long size; + char type[10]; + enum object_type obj_type; + int j, first, last; + + if (objects[d->obj_no].real_type != OBJ_REF_DELTA) + continue; + data = read_sha1_file(d->base.sha1, type, &size); + if (!data) + continue; + if (!strcmp(type, blob_type)) obj_type = OBJ_BLOB; + else if (!strcmp(type, tree_type)) obj_type = OBJ_TREE; + else if (!strcmp(type, commit_type)) obj_type = OBJ_COMMIT; + else if (!strcmp(type, tag_type)) obj_type = OBJ_TAG; + else die("base object %s is of type '%s'", + sha1_to_hex(d->base.sha1), type); + + find_delta_children(&d->base, &first, &last); + for (j = first; j <= last; j++) { + struct object_entry *child = objects + deltas[j].obj_no; + if (child->real_type == OBJ_REF_DELTA) + resolve_delta(child, data, size, obj_type); + } + + append_obj_to_pack(data, size, obj_type); + free(data); + if (verbose) + percent = display_progress(nr_resolved_deltas, + nr_deltas, percent); } + free(sorted_by_pos); + if (verbose) + fputc('\n', stderr); +} + +static void readjust_pack_header_and_sha1(unsigned char *sha1) +{ + struct pack_header hdr; + SHA_CTX ctx; + int size; + + /* Rewrite pack header with updated object number */ + if (lseek(output_fd, 0, SEEK_SET) != 0) + die("cannot seek back: %s", strerror(errno)); + if (read_in_full(output_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) + die("cannot read pack header back: %s", strerror(errno)); + hdr.hdr_entries = htonl(nr_objects); + if (lseek(output_fd, 0, SEEK_SET) != 0) + die("cannot seek back: %s", strerror(errno)); + write_or_die(output_fd, &hdr, sizeof(hdr)); + if (lseek(output_fd, 0, SEEK_SET) != 0) + die("cannot seek back: %s", strerror(errno)); + + /* Recompute and store the new pack's SHA1 */ + SHA1_Init(&ctx); + do { + unsigned char *buf[4096]; + size = xread(output_fd, buf, sizeof(buf)); + if (size < 0) + die("cannot read pack data back: %s", strerror(errno)); + SHA1_Update(&ctx, buf, size); + } while (size > 0); + SHA1_Final(sha1, &ctx); + write_or_die(output_fd, sha1, 20); } static int sha1_compare(const void *_a, const void *_b) @@ -353,12 +667,16 @@ static int sha1_compare(const void *_a, const void *_b) return hashcmp(a->sha1, b->sha1); } -static void write_index_file(const char *index_name, unsigned char *sha1) +/* + * On entry *sha1 contains the pack content SHA1 hash, on exit it is + * the SHA1 hash of sorted object names. + */ +static const char *write_index_file(const char *index_name, unsigned char *sha1) { struct sha1file *f; struct object_entry **sorted_by_sha, **list, **last; unsigned int array[256]; - int i; + int i, fd; SHA_CTX ctx; if (nr_objects) { @@ -375,8 +693,19 @@ static void write_index_file(const char *index_name, unsigned char *sha1) else sorted_by_sha = list = last = NULL; - unlink(index_name); - f = sha1create("%s", index_name); + if (!index_name) { + static char tmpfile[PATH_MAX]; + snprintf(tmpfile, sizeof(tmpfile), + "%s/index_XXXXXX", get_object_directory()); + fd = mkstemp(tmpfile); + index_name = xstrdup(tmpfile); + } else { + unlink(index_name); + fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600); + } + if (fd < 0) + die("unable to create %s: %s", index_name, strerror(errno)); + f = sha1fd(fd, index_name); /* * Write the first-level table (the list is sorted, @@ -412,24 +741,132 @@ static void write_index_file(const char *index_name, unsigned char *sha1) sha1write(f, obj->sha1, 20); SHA1_Update(&ctx, obj->sha1, 20); } - sha1write(f, pack_base + pack_size - 20, 20); + sha1write(f, sha1, 20); sha1close(f, NULL, 1); free(sorted_by_sha); SHA1_Final(sha1, &ctx); + return index_name; +} + +static void final(const char *final_pack_name, const char *curr_pack_name, + const char *final_index_name, const char *curr_index_name, + const char *keep_name, const char *keep_msg, + unsigned char *sha1) +{ + char *report = "pack"; + char name[PATH_MAX]; + int err; + + if (!from_stdin) { + close(input_fd); + } else { + err = close(output_fd); + if (err) + die("error while closing pack file: %s", strerror(errno)); + chmod(curr_pack_name, 0444); + } + + if (keep_msg) { + int keep_fd, keep_msg_len = strlen(keep_msg); + if (!keep_name) { + snprintf(name, sizeof(name), "%s/pack/pack-%s.keep", + get_object_directory(), sha1_to_hex(sha1)); + keep_name = name; + } + keep_fd = open(keep_name, O_RDWR|O_CREAT|O_EXCL, 0600); + if (keep_fd < 0) { + if (errno != EEXIST) + die("cannot write keep file"); + } else { + if (keep_msg_len > 0) { + write_or_die(keep_fd, keep_msg, keep_msg_len); + write_or_die(keep_fd, "\n", 1); + } + close(keep_fd); + report = "keep"; + } + } + + if (final_pack_name != curr_pack_name) { + if (!final_pack_name) { + snprintf(name, sizeof(name), "%s/pack/pack-%s.pack", + get_object_directory(), sha1_to_hex(sha1)); + final_pack_name = name; + } + if (move_temp_to_file(curr_pack_name, final_pack_name)) + die("cannot store pack file"); + } + + chmod(curr_index_name, 0444); + if (final_index_name != curr_index_name) { + if (!final_index_name) { + snprintf(name, sizeof(name), "%s/pack/pack-%s.idx", + get_object_directory(), sha1_to_hex(sha1)); + final_index_name = name; + } + if (move_temp_to_file(curr_index_name, final_index_name)) + die("cannot store index file"); + } + + if (!from_stdin) { + printf("%s\n", sha1_to_hex(sha1)); + } else { + char buf[48]; + int len = snprintf(buf, sizeof(buf), "%s\t%s\n", + report, sha1_to_hex(sha1)); + write_or_die(1, buf, len); + + /* + * Let's just mimic git-unpack-objects here and write + * the last part of the input buffer to stdout. + */ + while (input_len) { + err = xwrite(1, input_buffer + input_offset, input_len); + if (err <= 0) + break; + input_len -= err; + input_offset += err; + } + } } int main(int argc, char **argv) { - int i; - char *index_name = NULL; - char *index_name_buf = NULL; + int i, fix_thin_pack = 0; + const char *curr_pack, *pack_name = NULL; + const char *curr_index, *index_name = NULL; + const char *keep_name = NULL, *keep_msg = NULL; + char *index_name_buf = NULL, *keep_name_buf = NULL; unsigned char sha1[20]; for (i = 1; i < argc; i++) { const char *arg = argv[i]; if (*arg == '-') { - if (!strcmp(arg, "-o")) { + if (!strcmp(arg, "--stdin")) { + from_stdin = 1; + } else if (!strcmp(arg, "--fix-thin")) { + fix_thin_pack = 1; + } else if (!strcmp(arg, "--keep")) { + keep_msg = ""; + } else if (!strncmp(arg, "--keep=", 7)) { + keep_msg = arg + 7; + } else if (!strncmp(arg, "--pack_header=", 14)) { + struct pack_header *hdr; + char *c; + + hdr = (struct pack_header *)input_buffer; + hdr->hdr_signature = htonl(PACK_SIGNATURE); + hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10)); + if (*c != ',') + die("bad %s", arg); + hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10)); + if (*c) + die("bad %s", arg); + input_len = sizeof(*hdr); + } else if (!strcmp(arg, "-v")) { + verbose = 1; + } else if (!strcmp(arg, "-o")) { if (index_name || (i+1) >= argc) usage(index_pack_usage); index_name = argv[++i]; @@ -443,9 +880,11 @@ int main(int argc, char **argv) pack_name = arg; } - if (!pack_name) + if (!pack_name && !from_stdin) usage(index_pack_usage); - if (!index_name) { + if (fix_thin_pack && !from_stdin) + die("--fix-thin cannot be used without --stdin"); + if (!index_name && pack_name) { int len = strlen(pack_name); if (!has_extension(pack_name, ".pack")) die("packfile name '%s' does not end with '.pack'", @@ -455,18 +894,55 @@ int main(int argc, char **argv) strcpy(index_name_buf + len - 5, ".idx"); index_name = index_name_buf; } + if (keep_msg && !keep_name && pack_name) { + int len = strlen(pack_name); + if (!has_extension(pack_name, ".pack")) + die("packfile name '%s' does not end with '.pack'", + pack_name); + keep_name_buf = xmalloc(len); + memcpy(keep_name_buf, pack_name, len - 5); + strcpy(keep_name_buf + len - 5, ".keep"); + keep_name = keep_name_buf; + } - open_pack_file(); + curr_pack = open_pack_file(pack_name); parse_pack_header(); - objects = xcalloc(nr_objects, sizeof(struct object_entry)); - deltas = xcalloc(nr_objects, sizeof(struct delta_entry)); - parse_pack_objects(); + objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry)); + deltas = xmalloc(nr_objects * sizeof(struct delta_entry)); + if (verbose) + setup_progress_signal(); + parse_pack_objects(sha1); + if (nr_deltas != nr_resolved_deltas) { + if (fix_thin_pack) { + int nr_unresolved = nr_deltas - nr_resolved_deltas; + int nr_objects_initial = nr_objects; + if (nr_unresolved <= 0) + die("confusion beyond insanity"); + objects = xrealloc(objects, + (nr_objects + nr_unresolved + 1) + * sizeof(*objects)); + fix_unresolved_deltas(nr_unresolved); + if (verbose) + fprintf(stderr, "%d objects were added to complete this thin pack.\n", + nr_objects - nr_objects_initial); + readjust_pack_header_and_sha1(sha1); + } + if (nr_deltas != nr_resolved_deltas) + die("pack has %d unresolved deltas", + nr_deltas - nr_resolved_deltas); + } else { + /* Flush remaining pack final 20-byte SHA1. */ + flush(); + } free(deltas); - write_index_file(index_name, sha1); + curr_index = write_index_file(index_name, sha1); + final(pack_name, curr_pack, + index_name, curr_index, + keep_name, keep_msg, + sha1); free(objects); free(index_name_buf); - - printf("%s\n", sha1_to_hex(sha1)); + free(keep_name_buf); return 0; } diff --git a/interpolate.c b/interpolate.c new file mode 100644 index 0000000000..f992ef7753 --- /dev/null +++ b/interpolate.c @@ -0,0 +1,106 @@ +/* + * Copyright 2006 Jon Loeliger + */ + +#include "git-compat-util.h" +#include "interpolate.h" + + +void interp_set_entry(struct interp *table, int slot, const char *value) +{ + char *oldval = table[slot].value; + char *newval = NULL; + + if (oldval) + free(oldval); + + if (value) + newval = xstrdup(value); + + table[slot].value = newval; +} + + +void interp_clear_table(struct interp *table, int ninterps) +{ + int i; + + for (i = 0; i < ninterps; i++) { + interp_set_entry(table, i, NULL); + } +} + + +/* + * Convert a NUL-terminated string in buffer orig + * into the supplied buffer, result, whose length is reslen, + * performing substitutions on %-named sub-strings from + * the table, interps, with ninterps entries. + * + * Example interps: + * { + * { "%H", "example.org"}, + * { "%port", "123"}, + * { "%%", "%"}, + * } + * + * Returns 1 on a successful substitution pass that fits in result, + * Returns 0 on a failed or overflowing substitution pass. + */ + +int interpolate(char *result, int reslen, + const char *orig, + const struct interp *interps, int ninterps) +{ + const char *src = orig; + char *dest = result; + int newlen = 0; + char *name, *value; + int namelen, valuelen; + int i; + char c; + + memset(result, 0, reslen); + + while ((c = *src) && newlen < reslen - 1) { + if (c == '%') { + /* Try to match an interpolation string. */ + for (i = 0; i < ninterps; i++) { + name = interps[i].name; + namelen = strlen(name); + if (strncmp(src, name, namelen) == 0) { + break; + } + } + + /* Check for valid interpolation. */ + if (i < ninterps) { + value = interps[i].value; + valuelen = strlen(value); + + if (newlen + valuelen < reslen - 1) { + /* Substitute. */ + strncpy(dest, value, valuelen); + newlen += valuelen; + dest += valuelen; + src += namelen; + } else { + /* Something's not fitting. */ + return 0; + } + + } else { + /* Skip bogus interpolation. */ + *dest++ = *src++; + newlen++; + } + + } else { + /* Straight copy one non-interpolation character. */ + *dest++ = *src++; + newlen++; + } + } + + return newlen < reslen - 1; +} diff --git a/interpolate.h b/interpolate.h new file mode 100644 index 0000000000..190a180b58 --- /dev/null +++ b/interpolate.h @@ -0,0 +1,26 @@ +/* + * Copyright 2006 Jon Loeliger + */ + +#ifndef INTERPOLATE_H +#define INTERPOLATE_H + +/* + * Convert a NUL-terminated string in buffer orig, + * performing substitutions on %-named sub-strings from + * the interpretation table. + */ + +struct interp { + char *name; + char *value; +}; + +extern void interp_set_entry(struct interp *table, int slot, const char *value); +extern void interp_clear_table(struct interp *table, int ninterps); + +extern int interpolate(char *result, int reslen, + const char *orig, + const struct interp *interps, int ninterps); + +#endif /* INTERPOLATE_H */ diff --git a/list-objects.c b/list-objects.c new file mode 100644 index 0000000000..f1fa21c397 --- /dev/null +++ b/list-objects.c @@ -0,0 +1,140 @@ +#include "cache.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "diff.h" +#include "tree-walk.h" +#include "revision.h" +#include "list-objects.h" + +static void process_blob(struct rev_info *revs, + struct blob *blob, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &blob->object; + + if (!revs->blob_objects) + return; + if (obj->flags & (UNINTERESTING | SEEN)) + return; + obj->flags |= SEEN; + name = xstrdup(name); + add_object(obj, p, path, name); +} + +static void process_tree(struct rev_info *revs, + struct tree *tree, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &tree->object; + struct tree_desc desc; + struct name_entry entry; + struct name_path me; + + if (!revs->tree_objects) + return; + if (obj->flags & (UNINTERESTING | SEEN)) + return; + if (parse_tree(tree) < 0) + die("bad tree object %s", sha1_to_hex(obj->sha1)); + obj->flags |= SEEN; + name = xstrdup(name); + add_object(obj, p, path, name); + me.up = path; + me.elem = name; + me.elem_len = strlen(name); + + desc.buf = tree->buffer; + desc.size = tree->size; + + while (tree_entry(&desc, &entry)) { + if (S_ISDIR(entry.mode)) + process_tree(revs, + lookup_tree(entry.sha1), + p, &me, entry.path); + else + process_blob(revs, + lookup_blob(entry.sha1), + p, &me, entry.path); + } + free(tree->buffer); + tree->buffer = NULL; +} + +static void mark_edge_parents_uninteresting(struct commit *commit, + struct rev_info *revs, + show_edge_fn show_edge) +{ + struct commit_list *parents; + + for (parents = commit->parents; parents; parents = parents->next) { + struct commit *parent = parents->item; + if (!(parent->object.flags & UNINTERESTING)) + continue; + mark_tree_uninteresting(parent->tree); + if (revs->edge_hint && !(parent->object.flags & SHOWN)) { + parent->object.flags |= SHOWN; + show_edge(parent); + } + } +} + +void mark_edges_uninteresting(struct commit_list *list, + struct rev_info *revs, + show_edge_fn show_edge) +{ + for ( ; list; list = list->next) { + struct commit *commit = list->item; + + if (commit->object.flags & UNINTERESTING) { + mark_tree_uninteresting(commit->tree); + continue; + } + mark_edge_parents_uninteresting(commit, revs, show_edge); + } +} + +void traverse_commit_list(struct rev_info *revs, + void (*show_commit)(struct commit *), + void (*show_object)(struct object_array_entry *)) +{ + int i; + struct commit *commit; + struct object_array objects = { 0, 0, NULL }; + + while ((commit = get_revision(revs)) != NULL) { + process_tree(revs, commit->tree, &objects, NULL, ""); + show_commit(commit); + } + for (i = 0; i < revs->pending.nr; i++) { + struct object_array_entry *pending = revs->pending.objects + i; + struct object *obj = pending->item; + const char *name = pending->name; + if (obj->flags & (UNINTERESTING | SEEN)) + continue; + if (obj->type == OBJ_TAG) { + obj->flags |= SEEN; + add_object_array(obj, name, &objects); + continue; + } + if (obj->type == OBJ_TREE) { + process_tree(revs, (struct tree *)obj, &objects, + NULL, name); + continue; + } + if (obj->type == OBJ_BLOB) { + process_blob(revs, (struct blob *)obj, &objects, + NULL, name); + continue; + } + die("unknown pending object %s (%s)", + sha1_to_hex(obj->sha1), name); + } + for (i = 0; i < objects.nr; i++) + show_object(&objects.objects[i]); +} diff --git a/list-objects.h b/list-objects.h new file mode 100644 index 0000000000..0f41391ecc --- /dev/null +++ b/list-objects.h @@ -0,0 +1,12 @@ +#ifndef LIST_OBJECTS_H +#define LIST_OBJECTS_H + +typedef void (*show_commit_fn)(struct commit *); +typedef void (*show_object_fn)(struct object_array_entry *); +typedef void (*show_edge_fn)(struct commit *); + +void traverse_commit_list(struct rev_info *revs, show_commit_fn, show_object_fn); + +void mark_edges_uninteresting(struct commit_list *, struct rev_info *, show_edge_fn); + +#endif diff --git a/local-fetch.c b/local-fetch.c index 7b6875cce6..cf99cb72dd 100644 --- a/local-fetch.c +++ b/local-fetch.c @@ -184,7 +184,7 @@ int fetch_ref(char *ref, unsigned char *sha1) fprintf(stderr, "cannot open %s\n", filename); return -1; } - if (read(ifd, hex, 40) != 40 || get_sha1_hex(hex, sha1)) { + if (read_in_full(ifd, hex, 40) != 40 || get_sha1_hex(hex, sha1)) { close(ifd); fprintf(stderr, "cannot read from %s\n", filename); return -1; diff --git a/lockfile.c b/lockfile.c index 2a2fea3cb6..4824f4dc02 100644 --- a/lockfile.c +++ b/lockfile.c @@ -1,7 +1,6 @@ /* * Copyright (c) 2005, Junio C Hamano */ -#include <signal.h> #include "cache.h" static struct lock_file *lock_file_list; @@ -28,9 +27,12 @@ static int lock_file(struct lock_file *lk, const char *path) sprintf(lk->filename, "%s.lock", path); fd = open(lk->filename, O_RDWR | O_CREAT | O_EXCL, 0666); if (0 <= fd) { - if (!lk->next) { + if (!lk->on_list) { lk->next = lock_file_list; lock_file_list = lk; + lk->on_list = 1; + } + if (lock_file_list) { signal(SIGINT, remove_lock_file_on_signal); atexit(remove_lock_file); } @@ -38,6 +40,8 @@ static int lock_file(struct lock_file *lk, const char *path) return error("cannot fix permission bits on %s", lk->filename); } + else + lk->filename[0] = 0; return fd; } @@ -45,7 +49,7 @@ int hold_lock_file_for_update(struct lock_file *lk, const char *path, int die_on { int fd = lock_file(lk, path); if (fd < 0 && die_on_error) - die("unable to create '%s': %s", path, strerror(errno)); + die("unable to create '%s.lock': %s", path, strerror(errno)); return fd; } diff --git a/log-tree.c b/log-tree.c index 031af88933..35be33aaf7 100644 --- a/log-tree.c +++ b/log-tree.c @@ -12,10 +12,58 @@ static void show_parents(struct commit *commit, int abbrev) } } +/* + * Search for "^[-A-Za-z]+: [^@]+@" pattern. It usually matches + * Signed-off-by: and Acked-by: lines. + */ +static int detect_any_signoff(char *letter, int size) +{ + char ch, *cp; + int seen_colon = 0; + int seen_at = 0; + int seen_name = 0; + int seen_head = 0; + + cp = letter + size; + while (letter <= --cp && (ch = *cp) == '\n') + continue; + + while (letter <= cp) { + ch = *cp--; + if (ch == '\n') + break; + + if (!seen_at) { + if (ch == '@') + seen_at = 1; + continue; + } + if (!seen_colon) { + if (ch == '@') + return 0; + else if (ch == ':') + seen_colon = 1; + else + seen_name = 1; + continue; + } + if (('A' <= ch && ch <= 'Z') || + ('a' <= ch && ch <= 'z') || + ch == '-') { + seen_head = 1; + continue; + } + /* no empty last line doesn't match */ + return 0; + } + return seen_head && seen_name; +} + static int append_signoff(char *buf, int buf_sz, int at, const char *signoff) { - int signoff_len = strlen(signoff); static const char signed_off_by[] = "Signed-off-by: "; + int signoff_len = strlen(signoff); + int has_signoff = 0; char *cp = buf; /* Do we have enough space to add it? */ @@ -23,58 +71,26 @@ static int append_signoff(char *buf, int buf_sz, int at, const char *signoff) return at; /* First see if we already have the sign-off by the signer */ - while (1) { - cp = strstr(cp, signed_off_by); - if (!cp) - break; + while ((cp = strstr(cp, signed_off_by))) { + + has_signoff = 1; + cp += strlen(signed_off_by); - if ((cp + signoff_len < buf + at) && - !strncmp(cp, signoff, signoff_len) && - isspace(cp[signoff_len])) - return at; /* we already have him */ + if (cp + signoff_len >= buf + at) + break; + if (strncmp(cp, signoff, signoff_len)) + continue; + if (!isspace(cp[signoff_len])) + continue; + /* we already have him */ + return at; } - /* Does the last line already end with "^[-A-Za-z]+: [^@]+@"? - * If not, add a blank line to separate the message from - * the run of Signed-off-by: and Acked-by: lines. - */ - { - char ch; - int seen_colon, seen_at, seen_name, seen_head, not_signoff; - seen_colon = 0; - seen_at = 0; - seen_name = 0; - seen_head = 0; - not_signoff = 0; - cp = buf + at; - while (buf <= --cp && (ch = *cp) == '\n') - ; - while (!not_signoff && buf <= cp && (ch = *cp--) != '\n') { - if (!seen_at) { - if (ch == '@') - seen_at = 1; - continue; - } - if (!seen_colon) { - if (ch == '@') - not_signoff = 1; - else if (ch == ':') - seen_colon = 1; - else - seen_name = 1; - continue; - } - if (('A' <= ch && ch <= 'Z') || - ('a' <= ch && ch <= 'z') || - ch == '-') { - seen_head = 1; - continue; - } - not_signoff = 1; - } - if (not_signoff || !seen_head || !seen_name) - buf[at++] = '\n'; - } + if (!has_signoff) + has_signoff = detect_any_signoff(buf, at); + + if (!has_signoff) + buf[at++] = '\n'; strcpy(buf + at, signed_off_by); at += strlen(signed_off_by); @@ -98,6 +114,14 @@ void show_log(struct rev_info *opt, const char *sep) opt->loginfo = NULL; if (!opt->verbose_header) { + if (opt->left_right) { + if (commit->object.flags & BOUNDARY) + putchar('-'); + else if (commit->object.flags & SYMMETRIC_LEFT) + putchar('<'); + else + putchar('>'); + } fputs(diff_unique_abbrev(commit->object.sha1, abbrev_commit), stdout); if (opt->parents) show_parents(commit, abbrev_commit); @@ -176,10 +200,20 @@ void show_log(struct rev_info *opt, const char *sep) opt->diffopt.stat_sep = buffer; } } else { - printf("%s%s%s", - diff_get_color(opt->diffopt.color_diff, DIFF_COMMIT), - opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ", - diff_unique_abbrev(commit->object.sha1, abbrev_commit)); + fputs(diff_get_color(opt->diffopt.color_diff, DIFF_COMMIT), + stdout); + if (opt->commit_format != CMIT_FMT_ONELINE) + fputs("commit ", stdout); + if (opt->left_right) { + if (commit->object.flags & BOUNDARY) + putchar('-'); + else if (commit->object.flags & SYMMETRIC_LEFT) + putchar('<'); + else + putchar('>'); + } + fputs(diff_unique_abbrev(commit->object.sha1, abbrev_commit), + stdout); if (opt->parents) show_parents(commit, abbrev_commit); if (parent) @@ -194,7 +228,9 @@ void show_log(struct rev_info *opt, const char *sep) /* * And then the pretty-printed message itself */ - len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, sizeof(this_header), abbrev, subject, extra_headers); + len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, + sizeof(this_header), abbrev, subject, + extra_headers, opt->relative_date); if (opt->add_signoff) len = append_signoff(this_header, sizeof(this_header), len, @@ -234,26 +270,6 @@ int log_tree_diff_flush(struct rev_info *opt) return 1; } -static int diff_root_tree(struct rev_info *opt, - const unsigned char *new, const char *base) -{ - int retval; - void *tree; - struct tree_desc empty, real; - - tree = read_object_with_reference(new, tree_type, &real.size, NULL); - if (!tree) - die("unable to read root tree (%s)", sha1_to_hex(new)); - real.buf = tree; - - empty.buf = ""; - empty.size = 0; - retval = diff_tree(&empty, &real, base, &opt->diffopt); - free(tree); - log_tree_diff_flush(opt); - return retval; -} - static int do_diff_combined(struct rev_info *opt, struct commit *commit) { unsigned const char *sha1 = commit->object.sha1; @@ -279,8 +295,10 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log /* Root commit? */ parents = commit->parents; if (!parents) { - if (opt->show_root_diff) - diff_root_tree(opt, sha1, ""); + if (opt->show_root_diff) { + diff_root_tree_sha1(sha1, "", &opt->diffopt); + log_tree_diff_flush(opt); + } return !opt->loginfo; } diff --git a/merge-base.c b/merge-base.c index 009caf804b..385f4ba386 100644 --- a/merge-base.c +++ b/merge-base.c @@ -1,4 +1,3 @@ -#include <stdlib.h> #include "cache.h" #include "commit.h" diff --git a/merge-file.c b/merge-file.c index f32c653825..69dc1ebbf7 100644 --- a/merge-file.c +++ b/merge-file.c @@ -3,52 +3,6 @@ #include "xdiff-interface.h" #include "blob.h" -static void rm_temp_file(const char *filename) -{ - unlink(filename); - free((void *)filename); -} - -static const char *write_temp_file(mmfile_t *f) -{ - int fd; - const char *tmp = getenv("TMPDIR"); - char *filename; - - if (!tmp) - tmp = "/tmp"; - filename = mkpath("%s/%s", tmp, "git-tmp-XXXXXX"); - fd = mkstemp(filename); - if (fd < 0) - return NULL; - filename = strdup(filename); - if (f->size != xwrite(fd, f->ptr, f->size)) { - rm_temp_file(filename); - return NULL; - } - close(fd); - return filename; -} - -static void *read_temp_file(const char *filename, unsigned long *size) -{ - struct stat st; - char *buf = NULL; - int fd = open(filename, O_RDONLY); - if (fd < 0) - return NULL; - if (!fstat(fd, &st)) { - *size = st.st_size; - buf = xmalloc(st.st_size); - if (st.st_size != xread(fd, buf, st.st_size)) { - free(buf); - buf = NULL; - } - } - close(fd); - return buf; -} - static int fill_mmfile_blob(mmfile_t *f, struct blob *obj) { void *buf; @@ -72,22 +26,19 @@ static void free_mmfile(mmfile_t *f) static void *three_way_filemerge(mmfile_t *base, mmfile_t *our, mmfile_t *their, unsigned long *size) { - void *res; - const char *t1, *t2, *t3; - - t1 = write_temp_file(base); - t2 = write_temp_file(our); - t3 = write_temp_file(their); - res = NULL; - if (t1 && t2 && t3) { - int code = run_command("merge", t2, t1, t3, NULL); - if (!code || code == -1) - res = read_temp_file(t2, size); - } - rm_temp_file(t1); - rm_temp_file(t2); - rm_temp_file(t3); - return res; + mmbuffer_t res; + xpparam_t xpp; + int merge_status; + + memset(&xpp, 0, sizeof(xpp)); + merge_status = xdl_merge(base, our, ".our", their, ".their", + &xpp, XDL_MERGE_ZEALOUS, &res); + + if (merge_status < 0) + return NULL; + + *size = res.size; + return res.ptr; } static int common_outf(void *priv_, mmbuffer_t *mb, int nbuf) diff --git a/merge-index.c b/merge-index.c index 646d090c58..a9983dd78a 100644 --- a/merge-index.c +++ b/merge-index.c @@ -1,7 +1,3 @@ -#include <sys/types.h> -#include <sys/wait.h> -#include <signal.h> - #include "cache.h" static const char *pgm; diff --git a/merge-recursive.c b/merge-recursive.c new file mode 100644 index 0000000000..b4acbb7408 --- /dev/null +++ b/merge-recursive.c @@ -0,0 +1,1250 @@ +/* + * Recursive Merge algorithm stolen from git-merge-recursive.py by + * Fredrik Kuivinen. + * The thieves were Alex Riesen and Johannes Schindelin, in June/July 2006 + */ +#include "cache.h" +#include "cache-tree.h" +#include "commit.h" +#include "blob.h" +#include "tree-walk.h" +#include "diff.h" +#include "diffcore.h" +#include "run-command.h" +#include "tag.h" +#include "unpack-trees.h" +#include "path-list.h" +#include "xdiff-interface.h" + +/* + * A virtual commit has + * - (const char *)commit->util set to the name, and + * - *(int *)commit->object.sha1 set to the virtual id. + */ + +static unsigned commit_list_count(const struct commit_list *l) +{ + unsigned c = 0; + for (; l; l = l->next ) + c++; + return c; +} + +static struct commit *make_virtual_commit(struct tree *tree, const char *comment) +{ + struct commit *commit = xcalloc(1, sizeof(struct commit)); + static unsigned virtual_id = 1; + commit->tree = tree; + commit->util = (void*)comment; + *(int*)commit->object.sha1 = virtual_id++; + /* avoid warnings */ + commit->object.parsed = 1; + return commit; +} + +/* + * Since we use get_tree_entry(), which does not put the read object into + * the object pool, we cannot rely on a == b. + */ +static int sha_eq(const unsigned char *a, const unsigned char *b) +{ + if (!a && !b) + return 2; + return a && b && hashcmp(a, b) == 0; +} + +/* + * Since we want to write the index eventually, we cannot reuse the index + * for these (temporary) data. + */ +struct stage_data +{ + struct + { + unsigned mode; + unsigned char sha[20]; + } stages[4]; + unsigned processed:1; +}; + +static struct path_list current_file_set = {NULL, 0, 0, 1}; +static struct path_list current_directory_set = {NULL, 0, 0, 1}; + +static int output_indent = 0; + +static void output(const char *fmt, ...) +{ + va_list args; + int i; + for (i = output_indent; i--;) + fputs(" ", stdout); + va_start(args, fmt); + vfprintf(stdout, fmt, args); + va_end(args); + fputc('\n', stdout); +} + +static void output_commit_title(struct commit *commit) +{ + int i; + for (i = output_indent; i--;) + fputs(" ", stdout); + if (commit->util) + printf("virtual %s\n", (char *)commit->util); + else { + printf("%s ", find_unique_abbrev(commit->object.sha1, DEFAULT_ABBREV)); + if (parse_commit(commit) != 0) + printf("(bad commit)\n"); + else { + const char *s; + int len; + for (s = commit->buffer; *s; s++) + if (*s == '\n' && s[1] == '\n') { + s += 2; + break; + } + for (len = 0; s[len] && '\n' != s[len]; len++) + ; /* do nothing */ + printf("%.*s\n", len, s); + } + } +} + +static struct cache_entry *make_cache_entry(unsigned int mode, + const unsigned char *sha1, const char *path, int stage, int refresh) +{ + int size, len; + struct cache_entry *ce; + + if (!verify_path(path)) + return NULL; + + len = strlen(path); + size = cache_entry_size(len); + ce = xcalloc(1, size); + + hashcpy(ce->sha1, sha1); + memcpy(ce->name, path, len); + ce->ce_flags = create_ce_flags(len, stage); + ce->ce_mode = create_ce_mode(mode); + + if (refresh) + return refresh_cache_entry(ce, 0); + + return ce; +} + +static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, + const char *path, int stage, int refresh, int options) +{ + struct cache_entry *ce; + ce = make_cache_entry(mode, sha1 ? sha1 : null_sha1, path, stage, refresh); + if (!ce) + return error("cache_addinfo failed: %s", strerror(cache_errno)); + return add_cache_entry(ce, options); +} + +/* + * This is a global variable which is used in a number of places but + * only written to in the 'merge' function. + * + * index_only == 1 => Don't leave any non-stage 0 entries in the cache and + * don't update the working directory. + * 0 => Leave unmerged entries in the cache and update + * the working directory. + */ +static int index_only = 0; + +static int git_merge_trees(int index_only, + struct tree *common, + struct tree *head, + struct tree *merge) +{ + int rc; + struct object_list *trees = NULL; + struct unpack_trees_options opts; + + memset(&opts, 0, sizeof(opts)); + if (index_only) + opts.index_only = 1; + else + opts.update = 1; + opts.merge = 1; + opts.head_idx = 2; + opts.fn = threeway_merge; + + object_list_append(&common->object, &trees); + object_list_append(&head->object, &trees); + object_list_append(&merge->object, &trees); + + rc = unpack_trees(trees, &opts); + cache_tree_free(&active_cache_tree); + return rc; +} + +static int unmerged_index(void) +{ + int i; + for (i = 0; i < active_nr; i++) { + struct cache_entry *ce = active_cache[i]; + if (ce_stage(ce)) + return 1; + } + return 0; +} + +static struct tree *git_write_tree(void) +{ + struct tree *result = NULL; + + if (unmerged_index()) + return NULL; + + if (!active_cache_tree) + active_cache_tree = cache_tree(); + + if (!cache_tree_fully_valid(active_cache_tree) && + cache_tree_update(active_cache_tree, + active_cache, active_nr, 0, 0) < 0) + die("error building trees"); + + result = lookup_tree(active_cache_tree->sha1); + + return result; +} + +static int save_files_dirs(const unsigned char *sha1, + const char *base, int baselen, const char *path, + unsigned int mode, int stage) +{ + int len = strlen(path); + char *newpath = xmalloc(baselen + len + 1); + memcpy(newpath, base, baselen); + memcpy(newpath + baselen, path, len); + newpath[baselen + len] = '\0'; + + if (S_ISDIR(mode)) + path_list_insert(newpath, ¤t_directory_set); + else + path_list_insert(newpath, ¤t_file_set); + free(newpath); + + return READ_TREE_RECURSIVE; +} + +static int get_files_dirs(struct tree *tree) +{ + int n; + if (read_tree_recursive(tree, "", 0, 0, NULL, save_files_dirs) != 0) + return 0; + n = current_file_set.nr + current_directory_set.nr; + return n; +} + +/* + * Returns a index_entry instance which doesn't have to correspond to + * a real cache entry in Git's index. + */ +static struct stage_data *insert_stage_data(const char *path, + struct tree *o, struct tree *a, struct tree *b, + struct path_list *entries) +{ + struct path_list_item *item; + struct stage_data *e = xcalloc(1, sizeof(struct stage_data)); + get_tree_entry(o->object.sha1, path, + e->stages[1].sha, &e->stages[1].mode); + get_tree_entry(a->object.sha1, path, + e->stages[2].sha, &e->stages[2].mode); + get_tree_entry(b->object.sha1, path, + e->stages[3].sha, &e->stages[3].mode); + item = path_list_insert(path, entries); + item->util = e; + return e; +} + +/* + * Create a dictionary mapping file names to stage_data objects. The + * dictionary contains one entry for every path with a non-zero stage entry. + */ +static struct path_list *get_unmerged(void) +{ + struct path_list *unmerged = xcalloc(1, sizeof(struct path_list)); + int i; + + unmerged->strdup_paths = 1; + + for (i = 0; i < active_nr; i++) { + struct path_list_item *item; + struct stage_data *e; + struct cache_entry *ce = active_cache[i]; + if (!ce_stage(ce)) + continue; + + item = path_list_lookup(ce->name, unmerged); + if (!item) { + item = path_list_insert(ce->name, unmerged); + item->util = xcalloc(1, sizeof(struct stage_data)); + } + e = item->util; + e->stages[ce_stage(ce)].mode = ntohl(ce->ce_mode); + hashcpy(e->stages[ce_stage(ce)].sha, ce->sha1); + } + + return unmerged; +} + +struct rename +{ + struct diff_filepair *pair; + struct stage_data *src_entry; + struct stage_data *dst_entry; + unsigned processed:1; +}; + +/* + * Get information of all renames which occured between 'o_tree' and + * 'tree'. We need the three trees in the merge ('o_tree', 'a_tree' and + * 'b_tree') to be able to associate the correct cache entries with + * the rename information. 'tree' is always equal to either a_tree or b_tree. + */ +static struct path_list *get_renames(struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct path_list *entries) +{ + int i; + struct path_list *renames; + struct diff_options opts; + + renames = xcalloc(1, sizeof(struct path_list)); + diff_setup(&opts); + opts.recursive = 1; + opts.detect_rename = DIFF_DETECT_RENAME; + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + if (diff_setup_done(&opts) < 0) + die("diff setup failed"); + diff_tree_sha1(o_tree->object.sha1, tree->object.sha1, "", &opts); + diffcore_std(&opts); + for (i = 0; i < diff_queued_diff.nr; ++i) { + struct path_list_item *item; + struct rename *re; + struct diff_filepair *pair = diff_queued_diff.queue[i]; + if (pair->status != 'R') { + diff_free_filepair(pair); + continue; + } + re = xmalloc(sizeof(*re)); + re->processed = 0; + re->pair = pair; + item = path_list_lookup(re->pair->one->path, entries); + if (!item) + re->src_entry = insert_stage_data(re->pair->one->path, + o_tree, a_tree, b_tree, entries); + else + re->src_entry = item->util; + + item = path_list_lookup(re->pair->two->path, entries); + if (!item) + re->dst_entry = insert_stage_data(re->pair->two->path, + o_tree, a_tree, b_tree, entries); + else + re->dst_entry = item->util; + item = path_list_insert(pair->one->path, renames); + item->util = re; + } + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_flush(&opts); + return renames; +} + +static int update_stages(const char *path, struct diff_filespec *o, + struct diff_filespec *a, struct diff_filespec *b, + int clear) +{ + int options = ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE; + if (clear) + if (remove_file_from_cache(path)) + return -1; + if (o) + if (add_cacheinfo(o->mode, o->sha1, path, 1, 0, options)) + return -1; + if (a) + if (add_cacheinfo(a->mode, a->sha1, path, 2, 0, options)) + return -1; + if (b) + if (add_cacheinfo(b->mode, b->sha1, path, 3, 0, options)) + return -1; + return 0; +} + +static int remove_path(const char *name) +{ + int ret, len; + char *slash, *dirs; + + ret = unlink(name); + if (ret) + return ret; + len = strlen(name); + dirs = xmalloc(len+1); + memcpy(dirs, name, len); + dirs[len] = '\0'; + while ((slash = strrchr(name, '/'))) { + *slash = '\0'; + len = slash - name; + if (rmdir(name) != 0) + break; + } + free(dirs); + return ret; +} + +static int remove_file(int clean, const char *path, int no_wd) +{ + int update_cache = index_only || clean; + int update_working_directory = !index_only && !no_wd; + + if (update_cache) { + if (remove_file_from_cache(path)) + return -1; + } + if (update_working_directory) { + unlink(path); + if (errno != ENOENT || errno != EISDIR) + return -1; + remove_path(path); + } + return 0; +} + +static char *unique_path(const char *path, const char *branch) +{ + char *newpath = xmalloc(strlen(path) + 1 + strlen(branch) + 8 + 1); + int suffix = 0; + struct stat st; + char *p = newpath + strlen(path); + strcpy(newpath, path); + *(p++) = '~'; + strcpy(p, branch); + for (; *p; ++p) + if ('/' == *p) + *p = '_'; + while (path_list_has_path(¤t_file_set, newpath) || + path_list_has_path(¤t_directory_set, newpath) || + lstat(newpath, &st) == 0) + sprintf(p, "_%d", suffix++); + + path_list_insert(newpath, ¤t_file_set); + return newpath; +} + +static int mkdir_p(const char *path, unsigned long mode) +{ + /* path points to cache entries, so xstrdup before messing with it */ + char *buf = xstrdup(path); + int result = safe_create_leading_directories(buf); + free(buf); + return result; +} + +static void flush_buffer(int fd, const char *buf, unsigned long size) +{ + while (size > 0) { + long ret = write_in_full(fd, buf, size); + if (ret < 0) { + /* Ignore epipe */ + if (errno == EPIPE) + break; + die("merge-recursive: %s", strerror(errno)); + } else if (!ret) { + die("merge-recursive: disk full?"); + } + size -= ret; + buf += ret; + } +} + +static void update_file_flags(const unsigned char *sha, + unsigned mode, + const char *path, + int update_cache, + int update_wd) +{ + if (index_only) + update_wd = 0; + + if (update_wd) { + char type[20]; + void *buf; + unsigned long size; + + buf = read_sha1_file(sha, type, &size); + if (!buf) + die("cannot read object %s '%s'", sha1_to_hex(sha), path); + if (strcmp(type, blob_type) != 0) + die("blob expected for %s '%s'", sha1_to_hex(sha), path); + + if (S_ISREG(mode)) { + int fd; + if (mkdir_p(path, 0777)) + die("failed to create path %s: %s", path, strerror(errno)); + unlink(path); + if (mode & 0100) + mode = 0777; + else + mode = 0666; + fd = open(path, O_WRONLY | O_TRUNC | O_CREAT, mode); + if (fd < 0) + die("failed to open %s: %s", path, strerror(errno)); + flush_buffer(fd, buf, size); + close(fd); + } else if (S_ISLNK(mode)) { + char *lnk = xmalloc(size + 1); + memcpy(lnk, buf, size); + lnk[size] = '\0'; + mkdir_p(path, 0777); + unlink(lnk); + symlink(lnk, path); + } else + die("do not know what to do with %06o %s '%s'", + mode, sha1_to_hex(sha), path); + } + if (update_cache) + add_cacheinfo(mode, sha, path, 0, update_wd, ADD_CACHE_OK_TO_ADD); +} + +static void update_file(int clean, + const unsigned char *sha, + unsigned mode, + const char *path) +{ + update_file_flags(sha, mode, path, index_only || clean, !index_only); +} + +/* Low level file merging, update and removal */ + +struct merge_file_info +{ + unsigned char sha[20]; + unsigned mode; + unsigned clean:1, + merge:1; +}; + +static void fill_mm(const unsigned char *sha1, mmfile_t *mm) +{ + unsigned long size; + char type[20]; + + if (!hashcmp(sha1, null_sha1)) { + mm->ptr = xstrdup(""); + mm->size = 0; + return; + } + + mm->ptr = read_sha1_file(sha1, type, &size); + if (!mm->ptr || strcmp(type, blob_type)) + die("unable to read blob object %s", sha1_to_hex(sha1)); + mm->size = size; +} + +static struct merge_file_info merge_file(struct diff_filespec *o, + struct diff_filespec *a, struct diff_filespec *b, + const char *branch1, const char *branch2) +{ + struct merge_file_info result; + result.merge = 0; + result.clean = 1; + + if ((S_IFMT & a->mode) != (S_IFMT & b->mode)) { + result.clean = 0; + if (S_ISREG(a->mode)) { + result.mode = a->mode; + hashcpy(result.sha, a->sha1); + } else { + result.mode = b->mode; + hashcpy(result.sha, b->sha1); + } + } else { + if (!sha_eq(a->sha1, o->sha1) && !sha_eq(b->sha1, o->sha1)) + result.merge = 1; + + result.mode = a->mode == o->mode ? b->mode: a->mode; + + if (sha_eq(a->sha1, o->sha1)) + hashcpy(result.sha, b->sha1); + else if (sha_eq(b->sha1, o->sha1)) + hashcpy(result.sha, a->sha1); + else if (S_ISREG(a->mode)) { + mmfile_t orig, src1, src2; + mmbuffer_t result_buf; + xpparam_t xpp; + char *name1, *name2; + int merge_status; + + name1 = xstrdup(mkpath("%s:%s", branch1, a->path)); + name2 = xstrdup(mkpath("%s:%s", branch2, b->path)); + + fill_mm(o->sha1, &orig); + fill_mm(a->sha1, &src1); + fill_mm(b->sha1, &src2); + + memset(&xpp, 0, sizeof(xpp)); + merge_status = xdl_merge(&orig, + &src1, name1, + &src2, name2, + &xpp, XDL_MERGE_ZEALOUS, + &result_buf); + free(name1); + free(name2); + free(orig.ptr); + free(src1.ptr); + free(src2.ptr); + + if ((merge_status < 0) || !result_buf.ptr) + die("Failed to execute internal merge"); + + if (write_sha1_file(result_buf.ptr, result_buf.size, + blob_type, result.sha)) + die("Unable to add %s to database", + a->path); + + free(result_buf.ptr); + result.clean = (merge_status == 0); + } else { + if (!(S_ISLNK(a->mode) || S_ISLNK(b->mode))) + die("cannot merge modes?"); + + hashcpy(result.sha, a->sha1); + + if (!sha_eq(a->sha1, b->sha1)) + result.clean = 0; + } + } + + return result; +} + +static void conflict_rename_rename(struct rename *ren1, + const char *branch1, + struct rename *ren2, + const char *branch2) +{ + char *del[2]; + int delp = 0; + const char *ren1_dst = ren1->pair->two->path; + const char *ren2_dst = ren2->pair->two->path; + const char *dst_name1 = ren1_dst; + const char *dst_name2 = ren2_dst; + if (path_list_has_path(¤t_directory_set, ren1_dst)) { + dst_name1 = del[delp++] = unique_path(ren1_dst, branch1); + output("%s is a directory in %s adding as %s instead", + ren1_dst, branch2, dst_name1); + remove_file(0, ren1_dst, 0); + } + if (path_list_has_path(¤t_directory_set, ren2_dst)) { + dst_name2 = del[delp++] = unique_path(ren2_dst, branch2); + output("%s is a directory in %s adding as %s instead", + ren2_dst, branch1, dst_name2); + remove_file(0, ren2_dst, 0); + } + update_stages(dst_name1, NULL, ren1->pair->two, NULL, 1); + update_stages(dst_name2, NULL, NULL, ren2->pair->two, 1); + while (delp--) + free(del[delp]); +} + +static void conflict_rename_dir(struct rename *ren1, + const char *branch1) +{ + char *new_path = unique_path(ren1->pair->two->path, branch1); + output("Renaming %s to %s instead", ren1->pair->one->path, new_path); + remove_file(0, ren1->pair->two->path, 0); + update_file(0, ren1->pair->two->sha1, ren1->pair->two->mode, new_path); + free(new_path); +} + +static void conflict_rename_rename_2(struct rename *ren1, + const char *branch1, + struct rename *ren2, + const char *branch2) +{ + char *new_path1 = unique_path(ren1->pair->two->path, branch1); + char *new_path2 = unique_path(ren2->pair->two->path, branch2); + output("Renaming %s to %s and %s to %s instead", + ren1->pair->one->path, new_path1, + ren2->pair->one->path, new_path2); + remove_file(0, ren1->pair->two->path, 0); + update_file(0, ren1->pair->two->sha1, ren1->pair->two->mode, new_path1); + update_file(0, ren2->pair->two->sha1, ren2->pair->two->mode, new_path2); + free(new_path2); + free(new_path1); +} + +static int process_renames(struct path_list *a_renames, + struct path_list *b_renames, + const char *a_branch, + const char *b_branch) +{ + int clean_merge = 1, i, j; + struct path_list a_by_dst = {NULL, 0, 0, 0}, b_by_dst = {NULL, 0, 0, 0}; + const struct rename *sre; + + for (i = 0; i < a_renames->nr; i++) { + sre = a_renames->items[i].util; + path_list_insert(sre->pair->two->path, &a_by_dst)->util + = sre->dst_entry; + } + for (i = 0; i < b_renames->nr; i++) { + sre = b_renames->items[i].util; + path_list_insert(sre->pair->two->path, &b_by_dst)->util + = sre->dst_entry; + } + + for (i = 0, j = 0; i < a_renames->nr || j < b_renames->nr;) { + int compare; + char *src; + struct path_list *renames1, *renames2, *renames2Dst; + struct rename *ren1 = NULL, *ren2 = NULL; + const char *branch1, *branch2; + const char *ren1_src, *ren1_dst; + + if (i >= a_renames->nr) { + compare = 1; + ren2 = b_renames->items[j++].util; + } else if (j >= b_renames->nr) { + compare = -1; + ren1 = a_renames->items[i++].util; + } else { + compare = strcmp(a_renames->items[i].path, + b_renames->items[j].path); + if (compare <= 0) + ren1 = a_renames->items[i++].util; + if (compare >= 0) + ren2 = b_renames->items[j++].util; + } + + /* TODO: refactor, so that 1/2 are not needed */ + if (ren1) { + renames1 = a_renames; + renames2 = b_renames; + renames2Dst = &b_by_dst; + branch1 = a_branch; + branch2 = b_branch; + } else { + struct rename *tmp; + renames1 = b_renames; + renames2 = a_renames; + renames2Dst = &a_by_dst; + branch1 = b_branch; + branch2 = a_branch; + tmp = ren2; + ren2 = ren1; + ren1 = tmp; + } + src = ren1->pair->one->path; + + ren1->dst_entry->processed = 1; + ren1->src_entry->processed = 1; + + if (ren1->processed) + continue; + ren1->processed = 1; + + ren1_src = ren1->pair->one->path; + ren1_dst = ren1->pair->two->path; + + if (ren2) { + const char *ren2_src = ren2->pair->one->path; + const char *ren2_dst = ren2->pair->two->path; + /* Renamed in 1 and renamed in 2 */ + if (strcmp(ren1_src, ren2_src) != 0) + die("ren1.src != ren2.src"); + ren2->dst_entry->processed = 1; + ren2->processed = 1; + if (strcmp(ren1_dst, ren2_dst) != 0) { + clean_merge = 0; + output("CONFLICT (rename/rename): " + "Rename %s->%s in branch %s " + "rename %s->%s in %s", + src, ren1_dst, branch1, + src, ren2_dst, branch2); + conflict_rename_rename(ren1, branch1, ren2, branch2); + } else { + struct merge_file_info mfi; + remove_file(1, ren1_src, 1); + mfi = merge_file(ren1->pair->one, + ren1->pair->two, + ren2->pair->two, + branch1, + branch2); + if (mfi.merge || !mfi.clean) + output("Renaming %s->%s", src, ren1_dst); + + if (mfi.merge) + output("Auto-merging %s", ren1_dst); + + if (!mfi.clean) { + output("CONFLICT (content): merge conflict in %s", + ren1_dst); + clean_merge = 0; + + if (!index_only) + update_stages(ren1_dst, + ren1->pair->one, + ren1->pair->two, + ren2->pair->two, + 1 /* clear */); + } + update_file(mfi.clean, mfi.sha, mfi.mode, ren1_dst); + } + } else { + /* Renamed in 1, maybe changed in 2 */ + struct path_list_item *item; + /* we only use sha1 and mode of these */ + struct diff_filespec src_other, dst_other; + int try_merge, stage = a_renames == renames1 ? 3: 2; + + remove_file(1, ren1_src, index_only); + + hashcpy(src_other.sha1, ren1->src_entry->stages[stage].sha); + src_other.mode = ren1->src_entry->stages[stage].mode; + hashcpy(dst_other.sha1, ren1->dst_entry->stages[stage].sha); + dst_other.mode = ren1->dst_entry->stages[stage].mode; + + try_merge = 0; + + if (path_list_has_path(¤t_directory_set, ren1_dst)) { + clean_merge = 0; + output("CONFLICT (rename/directory): Rename %s->%s in %s " + " directory %s added in %s", + ren1_src, ren1_dst, branch1, + ren1_dst, branch2); + conflict_rename_dir(ren1, branch1); + } else if (sha_eq(src_other.sha1, null_sha1)) { + clean_merge = 0; + output("CONFLICT (rename/delete): Rename %s->%s in %s " + "and deleted in %s", + ren1_src, ren1_dst, branch1, + branch2); + update_file(0, ren1->pair->two->sha1, ren1->pair->two->mode, ren1_dst); + } else if (!sha_eq(dst_other.sha1, null_sha1)) { + const char *new_path; + clean_merge = 0; + try_merge = 1; + output("CONFLICT (rename/add): Rename %s->%s in %s. " + "%s added in %s", + ren1_src, ren1_dst, branch1, + ren1_dst, branch2); + new_path = unique_path(ren1_dst, branch2); + output("Adding as %s instead", new_path); + update_file(0, dst_other.sha1, dst_other.mode, new_path); + } else if ((item = path_list_lookup(ren1_dst, renames2Dst))) { + ren2 = item->util; + clean_merge = 0; + ren2->processed = 1; + output("CONFLICT (rename/rename): Rename %s->%s in %s. " + "Rename %s->%s in %s", + ren1_src, ren1_dst, branch1, + ren2->pair->one->path, ren2->pair->two->path, branch2); + conflict_rename_rename_2(ren1, branch1, ren2, branch2); + } else + try_merge = 1; + + if (try_merge) { + struct diff_filespec *o, *a, *b; + struct merge_file_info mfi; + src_other.path = (char *)ren1_src; + + o = ren1->pair->one; + if (a_renames == renames1) { + a = ren1->pair->two; + b = &src_other; + } else { + b = ren1->pair->two; + a = &src_other; + } + mfi = merge_file(o, a, b, + a_branch, b_branch); + + if (mfi.merge || !mfi.clean) + output("Renaming %s => %s", ren1_src, ren1_dst); + if (mfi.merge) + output("Auto-merging %s", ren1_dst); + if (!mfi.clean) { + output("CONFLICT (rename/modify): Merge conflict in %s", + ren1_dst); + clean_merge = 0; + + if (!index_only) + update_stages(ren1_dst, + o, a, b, 1); + } + update_file(mfi.clean, mfi.sha, mfi.mode, ren1_dst); + } + } + } + path_list_clear(&a_by_dst, 0); + path_list_clear(&b_by_dst, 0); + + return clean_merge; +} + +static unsigned char *has_sha(const unsigned char *sha) +{ + return is_null_sha1(sha) ? NULL: (unsigned char *)sha; +} + +/* Per entry merge function */ +static int process_entry(const char *path, struct stage_data *entry, + const char *branch1, + const char *branch2) +{ + /* + printf("processing entry, clean cache: %s\n", index_only ? "yes": "no"); + print_index_entry("\tpath: ", entry); + */ + int clean_merge = 1; + unsigned char *o_sha = has_sha(entry->stages[1].sha); + unsigned char *a_sha = has_sha(entry->stages[2].sha); + unsigned char *b_sha = has_sha(entry->stages[3].sha); + unsigned o_mode = entry->stages[1].mode; + unsigned a_mode = entry->stages[2].mode; + unsigned b_mode = entry->stages[3].mode; + + if (o_sha && (!a_sha || !b_sha)) { + /* Case A: Deleted in one */ + if ((!a_sha && !b_sha) || + (sha_eq(a_sha, o_sha) && !b_sha) || + (!a_sha && sha_eq(b_sha, o_sha))) { + /* Deleted in both or deleted in one and + * unchanged in the other */ + if (a_sha) + output("Removing %s", path); + /* do not touch working file if it did not exist */ + remove_file(1, path, !a_sha); + } else { + /* Deleted in one and changed in the other */ + clean_merge = 0; + if (!a_sha) { + output("CONFLICT (delete/modify): %s deleted in %s " + "and modified in %s. Version %s of %s left in tree.", + path, branch1, + branch2, branch2, path); + update_file(0, b_sha, b_mode, path); + } else { + output("CONFLICT (delete/modify): %s deleted in %s " + "and modified in %s. Version %s of %s left in tree.", + path, branch2, + branch1, branch1, path); + update_file(0, a_sha, a_mode, path); + } + } + + } else if ((!o_sha && a_sha && !b_sha) || + (!o_sha && !a_sha && b_sha)) { + /* Case B: Added in one. */ + const char *add_branch; + const char *other_branch; + unsigned mode; + const unsigned char *sha; + const char *conf; + + if (a_sha) { + add_branch = branch1; + other_branch = branch2; + mode = a_mode; + sha = a_sha; + conf = "file/directory"; + } else { + add_branch = branch2; + other_branch = branch1; + mode = b_mode; + sha = b_sha; + conf = "directory/file"; + } + if (path_list_has_path(¤t_directory_set, path)) { + const char *new_path = unique_path(path, add_branch); + clean_merge = 0; + output("CONFLICT (%s): There is a directory with name %s in %s. " + "Adding %s as %s", + conf, path, other_branch, path, new_path); + remove_file(0, path, 0); + update_file(0, sha, mode, new_path); + } else { + output("Adding %s", path); + update_file(1, sha, mode, path); + } + } else if (a_sha && b_sha) { + /* Case C: Added in both (check for same permissions) and */ + /* case D: Modified in both, but differently. */ + const char *reason = "content"; + struct merge_file_info mfi; + struct diff_filespec o, a, b; + + if (!o_sha) { + reason = "add/add"; + o_sha = (unsigned char *)null_sha1; + } + output("Auto-merging %s", path); + o.path = a.path = b.path = (char *)path; + hashcpy(o.sha1, o_sha); + o.mode = o_mode; + hashcpy(a.sha1, a_sha); + a.mode = a_mode; + hashcpy(b.sha1, b_sha); + b.mode = b_mode; + + mfi = merge_file(&o, &a, &b, + branch1, branch2); + + if (mfi.clean) + update_file(1, mfi.sha, mfi.mode, path); + else { + clean_merge = 0; + output("CONFLICT (%s): Merge conflict in %s", + reason, path); + + if (index_only) + update_file(0, mfi.sha, mfi.mode, path); + else + update_file_flags(mfi.sha, mfi.mode, path, + 0 /* update_cache */, 1 /* update_working_directory */); + } + } else + die("Fatal merge failure, shouldn't happen."); + + return clean_merge; +} + +static int merge_trees(struct tree *head, + struct tree *merge, + struct tree *common, + const char *branch1, + const char *branch2, + struct tree **result) +{ + int code, clean; + if (sha_eq(common->object.sha1, merge->object.sha1)) { + output("Already uptodate!"); + *result = head; + return 1; + } + + code = git_merge_trees(index_only, common, head, merge); + + if (code != 0) + die("merging of trees %s and %s failed", + sha1_to_hex(head->object.sha1), + sha1_to_hex(merge->object.sha1)); + + if (unmerged_index()) { + struct path_list *entries, *re_head, *re_merge; + int i; + path_list_clear(¤t_file_set, 1); + path_list_clear(¤t_directory_set, 1); + get_files_dirs(head); + get_files_dirs(merge); + + entries = get_unmerged(); + re_head = get_renames(head, common, head, merge, entries); + re_merge = get_renames(merge, common, head, merge, entries); + clean = process_renames(re_head, re_merge, + branch1, branch2); + for (i = 0; i < entries->nr; i++) { + const char *path = entries->items[i].path; + struct stage_data *e = entries->items[i].util; + if (e->processed) + continue; + if (!process_entry(path, e, branch1, branch2)) + clean = 0; + } + + path_list_clear(re_merge, 0); + path_list_clear(re_head, 0); + path_list_clear(entries, 1); + + } + else + clean = 1; + + if (index_only) + *result = git_write_tree(); + + return clean; +} + +static struct commit_list *reverse_commit_list(struct commit_list *list) +{ + struct commit_list *next = NULL, *current, *backup; + for (current = list; current; current = backup) { + backup = current->next; + current->next = next; + next = current; + } + return next; +} + +/* + * Merge the commits h1 and h2, return the resulting virtual + * commit object and a flag indicating the cleaness of the merge. + */ +static int merge(struct commit *h1, + struct commit *h2, + const char *branch1, + const char *branch2, + int call_depth /* =0 */, + struct commit_list *ca, + struct commit **result) +{ + struct commit_list *iter; + struct commit *merged_common_ancestors; + struct tree *mrtree; + int clean; + + output("Merging:"); + output_commit_title(h1); + output_commit_title(h2); + + if (!ca) { + ca = get_merge_bases(h1, h2, 1); + ca = reverse_commit_list(ca); + } + + output("found %u common ancestor(s):", commit_list_count(ca)); + for (iter = ca; iter; iter = iter->next) + output_commit_title(iter->item); + + merged_common_ancestors = pop_commit(&ca); + if (merged_common_ancestors == NULL) { + /* if there is no common ancestor, make an empty tree */ + struct tree *tree = xcalloc(1, sizeof(struct tree)); + + tree->object.parsed = 1; + tree->object.type = OBJ_TREE; + write_sha1_file(NULL, 0, tree_type, tree->object.sha1); + merged_common_ancestors = make_virtual_commit(tree, "ancestor"); + } + + for (iter = ca; iter; iter = iter->next) { + output_indent = call_depth + 1; + /* + * When the merge fails, the result contains files + * with conflict markers. The cleanness flag is + * ignored, it was never acutally used, as result of + * merge_trees has always overwritten it: the commited + * "conflicts" were already resolved. + */ + discard_cache(); + merge(merged_common_ancestors, iter->item, + "Temporary merge branch 1", + "Temporary merge branch 2", + call_depth + 1, + NULL, + &merged_common_ancestors); + output_indent = call_depth; + + if (!merged_common_ancestors) + die("merge returned no commit"); + } + + discard_cache(); + if (call_depth == 0) { + read_cache(); + index_only = 0; + } else + index_only = 1; + + clean = merge_trees(h1->tree, h2->tree, merged_common_ancestors->tree, + branch1, branch2, &mrtree); + + if (index_only) { + *result = make_virtual_commit(mrtree, "merged tree"); + commit_list_insert(h1, &(*result)->parents); + commit_list_insert(h2, &(*result)->parents->next); + } + return clean; +} + +static const char *better_branch_name(const char *branch) +{ + static char githead_env[8 + 40 + 1]; + char *name; + + if (strlen(branch) != 40) + return branch; + sprintf(githead_env, "GITHEAD_%s", branch); + name = getenv(githead_env); + return name ? name : branch; +} + +static struct commit *get_ref(const char *ref) +{ + unsigned char sha1[20]; + struct object *object; + + if (get_sha1(ref, sha1)) + die("Could not resolve ref '%s'", ref); + object = deref_tag(parse_object(sha1), ref, strlen(ref)); + if (object->type == OBJ_TREE) + return make_virtual_commit((struct tree*)object, + better_branch_name(ref)); + if (object->type != OBJ_COMMIT) + return NULL; + if (parse_commit((struct commit *)object)) + die("Could not parse commit '%s'", sha1_to_hex(object->sha1)); + return (struct commit *)object; +} + +int main(int argc, char *argv[]) +{ + static const char *bases[20]; + static unsigned bases_count = 0; + int i, clean; + const char *branch1, *branch2; + struct commit *result, *h1, *h2; + struct commit_list *ca = NULL; + struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); + int index_fd; + + git_config(git_default_config); /* core.filemode */ + + if (argc < 4) + die("Usage: %s <base>... -- <head> <remote> ...\n", argv[0]); + + for (i = 1; i < argc; ++i) { + if (!strcmp(argv[i], "--")) + break; + if (bases_count < sizeof(bases)/sizeof(*bases)) + bases[bases_count++] = argv[i]; + } + if (argc - i != 3) /* "--" "<head>" "<remote>" */ + die("Not handling anything other than two heads merge."); + + branch1 = argv[++i]; + branch2 = argv[++i]; + + h1 = get_ref(branch1); + h2 = get_ref(branch2); + + branch1 = better_branch_name(branch1); + branch2 = better_branch_name(branch2); + printf("Merging %s with %s\n", branch1, branch2); + + index_fd = hold_lock_file_for_update(lock, get_index_file(), 1); + + for (i = 0; i < bases_count; i++) { + struct commit *ancestor = get_ref(bases[i]); + ca = commit_list_insert(ancestor, &ca); + } + clean = merge(h1, h2, branch1, branch2, 0, ca, &result); + + if (active_cache_changed && + (write_cache(index_fd, active_cache, active_nr) || + close(index_fd) || commit_lock_file(lock))) + die ("unable to write %s", get_index_file()); + + return clean ? 0: 1; +} diff --git a/merge-tree.c b/merge-tree.c index c2e9a867ed..692ede0e3d 100644 --- a/merge-tree.c +++ b/merge-tree.c @@ -177,7 +177,7 @@ static void resolve(const char *base, struct name_entry *branch1, struct name_en if (!branch1) return; - path = strdup(mkpath("%s%s", base, result->path)); + path = xstrdup(mkpath("%s%s", base, result->path)); orig = create_entry(2, branch1->mode, branch1->sha1, path); final = create_entry(0, result->mode, result->sha1, path); @@ -233,7 +233,7 @@ static struct merge_list *link_entry(unsigned stage, const char *base, struct na if (entry) path = entry->path; else - path = strdup(mkpath("%s%s", base, n->path)); + path = xstrdup(mkpath("%s%s", base, n->path)); link = create_entry(stage, n->mode, n->sha1, path); link->link = entry; return link; @@ -337,9 +337,11 @@ int main(int argc, char **argv) struct tree_desc t[3]; void *buf1, *buf2, *buf3; - if (argc < 4) + if (argc != 4) usage(merge_tree_usage); + setup_git_directory(); + buf1 = get_tree_descriptor(t+0, argv[1]); buf2 = get_tree_descriptor(t+1, argv[2]); buf3 = get_tree_descriptor(t+2, argv[3]); @@ -119,7 +119,7 @@ static int verify_tag(char *buffer, unsigned long size) int main(int argc, char **argv) { unsigned long size = 4096; - char *buffer = malloc(size); + char *buffer = xmalloc(size); unsigned char result_sha1[20]; if (argc != 1) diff --git a/object-refs.c b/object-refs.c index b1b8065851..98ea10005a 100644 --- a/object-refs.c +++ b/object-refs.c @@ -30,7 +30,7 @@ static void grow_refs_hash(void) int new_hash_size = (refs_hash_size + 1000) * 3 / 2; struct object_refs **new_hash; - new_hash = calloc(new_hash_size, sizeof(struct object_refs *)); + new_hash = xcalloc(new_hash_size, sizeof(struct object_refs *)); for (i = 0; i < refs_hash_size; i++) { struct object_refs *ref = refs_hash[i]; if (!ref) @@ -55,9 +55,13 @@ static void add_object_refs(struct object *obj, struct object_refs *ref) struct object_refs *lookup_object_refs(struct object *obj) { - int j = hash_obj(obj, refs_hash_size); struct object_refs *ref; + int j; + /* nothing to lookup */ + if (!refs_hash_size) + return NULL; + j = hash_obj(obj, refs_hash_size); while ((ref = refs_hash[j]) != NULL) { if (ref->base == obj) break; @@ -125,9 +129,6 @@ void mark_reachable(struct object *obj, unsigned int mask) if (!track_object_refs) die("cannot do reachability with object refs turned off"); - /* nothing to lookup */ - if (!refs_hash_size) - return; /* If we've been here already, don't bother */ if (obj->flags & mask) return; @@ -73,7 +73,7 @@ static void grow_object_hash(void) int new_hash_size = obj_hash_size < 32 ? 32 : 2 * obj_hash_size; struct object **new_hash; - new_hash = calloc(new_hash_size, sizeof(struct object *)); + new_hash = xcalloc(new_hash_size, sizeof(struct object *)); for (i = 0; i < obj_hash_size; i++) { struct object *obj = obj_hash[i]; if (!obj) @@ -138,42 +138,56 @@ struct object *lookup_unknown_object(const unsigned char *sha1) return obj; } +struct object *parse_object_buffer(const unsigned char *sha1, const char *type, unsigned long size, void *buffer, int *eaten_p) +{ + struct object *obj; + int eaten = 0; + + if (!strcmp(type, blob_type)) { + struct blob *blob = lookup_blob(sha1); + parse_blob_buffer(blob, buffer, size); + obj = &blob->object; + } else if (!strcmp(type, tree_type)) { + struct tree *tree = lookup_tree(sha1); + obj = &tree->object; + if (!tree->object.parsed) { + parse_tree_buffer(tree, buffer, size); + eaten = 1; + } + } else if (!strcmp(type, commit_type)) { + struct commit *commit = lookup_commit(sha1); + parse_commit_buffer(commit, buffer, size); + if (!commit->buffer) { + commit->buffer = buffer; + eaten = 1; + } + obj = &commit->object; + } else if (!strcmp(type, tag_type)) { + struct tag *tag = lookup_tag(sha1); + parse_tag_buffer(tag, buffer, size); + obj = &tag->object; + } else { + obj = NULL; + } + *eaten_p = eaten; + return obj; +} + struct object *parse_object(const unsigned char *sha1) { unsigned long size; char type[20]; + int eaten; void *buffer = read_sha1_file(sha1, type, &size); + if (buffer) { struct object *obj; if (check_sha1_signature(sha1, buffer, size, type) < 0) printf("sha1 mismatch %s\n", sha1_to_hex(sha1)); - if (!strcmp(type, blob_type)) { - struct blob *blob = lookup_blob(sha1); - parse_blob_buffer(blob, buffer, size); - obj = &blob->object; - } else if (!strcmp(type, tree_type)) { - struct tree *tree = lookup_tree(sha1); - obj = &tree->object; - if (!tree->object.parsed) { - parse_tree_buffer(tree, buffer, size); - buffer = NULL; - } - } else if (!strcmp(type, commit_type)) { - struct commit *commit = lookup_commit(sha1); - parse_commit_buffer(commit, buffer, size); - if (!commit->buffer) { - commit->buffer = buffer; - buffer = NULL; - } - obj = &commit->object; - } else if (!strcmp(type, tag_type)) { - struct tag *tag = lookup_tag(sha1); - parse_tag_buffer(tag, buffer, size); - obj = &tag->object; - } else { - obj = NULL; - } - free(buffer); + + obj = parse_object_buffer(sha1, type, size, buffer, &eaten); + if (!eaten) + free(buffer); return obj; } return NULL; @@ -27,17 +27,6 @@ struct object_array { /* * The object type is stored in 3 bits. */ -enum object_type { - OBJ_NONE = 0, - OBJ_COMMIT = 1, - OBJ_TREE = 2, - OBJ_BLOB = 3, - OBJ_TAG = 4, - /* 5/6 for future expansion */ - OBJ_DELTA = 7, - OBJ_BAD, -}; - struct object { unsigned parsed : 1; unsigned used : 1; @@ -70,6 +59,12 @@ void created_object(const unsigned char *sha1, struct object *obj); /** Returns the object, having parsed it to find out what it is. **/ struct object *parse_object(const unsigned char *sha1); +/* Given the result of read_sha1_file(), returns the object after + * parsing it. eaten_p indicates if the object has a borrowed copy + * of buffer and the caller should not free() it. + */ +struct object *parse_object_buffer(const unsigned char *sha1, const char *type, unsigned long size, void *buffer, int *eaten_p); + /** Returns the object, with potentially excess memory allocated. **/ struct object *lookup_unknown_object(const unsigned char *sha1); diff --git a/pack-check.c b/pack-check.c index 04c6c00821..08a9fd8dc0 100644 --- a/pack-check.c +++ b/pack-check.c @@ -1,57 +1,57 @@ #include "cache.h" #include "pack.h" -static int verify_packfile(struct packed_git *p) +static int verify_packfile(struct packed_git *p, + struct pack_window **w_curs) { unsigned long index_size = p->index_size; void *index_base = p->index_base; SHA_CTX ctx; unsigned char sha1[20]; - unsigned long pack_size = p->pack_size; - void *pack_base; - struct pack_header *hdr; + unsigned long offset = 0, pack_sig = p->pack_size - 20; int nr_objects, err, i; - /* Header consistency check */ - hdr = p->pack_base; - if (hdr->hdr_signature != htonl(PACK_SIGNATURE)) - return error("Packfile %s signature mismatch", p->pack_name); - if (!pack_version_ok(hdr->hdr_version)) - return error("Packfile version %d unsupported", - ntohl(hdr->hdr_version)); - nr_objects = ntohl(hdr->hdr_entries); - if (num_packed_objects(p) != nr_objects) - return error("Packfile claims to have %d objects, " - "while idx size expects %d", nr_objects, - num_packed_objects(p)); + /* Note that the pack header checks are actually performed by + * use_pack when it first opens the pack file. If anything + * goes wrong during those checks then the call will die out + * immediately. + */ SHA1_Init(&ctx); - pack_base = p->pack_base; - SHA1_Update(&ctx, pack_base, pack_size - 20); + while (offset < pack_sig) { + unsigned int remaining; + unsigned char *in = use_pack(p, w_curs, offset, &remaining); + offset += remaining; + if (offset > pack_sig) + remaining -= offset - pack_sig; + SHA1_Update(&ctx, in, remaining); + } SHA1_Final(sha1, &ctx); - if (hashcmp(sha1, (unsigned char *)pack_base + pack_size - 20)) + if (hashcmp(sha1, use_pack(p, w_curs, pack_sig, NULL))) return error("Packfile %s SHA1 mismatch with itself", p->pack_name); if (hashcmp(sha1, (unsigned char *)index_base + index_size - 40)) return error("Packfile %s SHA1 mismatch with idx", p->pack_name); + unuse_pack(w_curs); /* Make sure everything reachable from idx is valid. Since we * have verified that nr_objects matches between idx and pack, * we do not do scan-streaming check on the pack file. */ + nr_objects = num_packed_objects(p); for (i = err = 0; i < nr_objects; i++) { unsigned char sha1[20]; - struct pack_entry e; void *data; char type[20]; - unsigned long size; + unsigned long size, offset; if (nth_packed_object_sha1(p, i, sha1)) die("internal error pack-check nth-packed-object"); - if (!find_pack_entry_one(sha1, &e, p)) + offset = find_pack_entry_one(sha1, p); + if (!offset) die("internal error pack-check find-pack-entry-one"); - data = unpack_entry_gently(&e, type, &size); + data = unpack_entry(p, offset, type, &size); if (!data) { err = error("cannot unpack %s from %s", sha1_to_hex(sha1), p->pack_name); @@ -74,35 +74,34 @@ static int verify_packfile(struct packed_git *p) static void show_pack_info(struct packed_git *p) { - struct pack_header *hdr; int nr_objects, i; unsigned int chain_histogram[MAX_CHAIN]; - hdr = p->pack_base; - nr_objects = ntohl(hdr->hdr_entries); + nr_objects = num_packed_objects(p); memset(chain_histogram, 0, sizeof(chain_histogram)); for (i = 0; i < nr_objects; i++) { unsigned char sha1[20], base_sha1[20]; - struct pack_entry e; char type[20]; unsigned long size; unsigned long store_size; + unsigned long offset; unsigned int delta_chain_length; if (nth_packed_object_sha1(p, i, sha1)) die("internal error pack-check nth-packed-object"); - if (!find_pack_entry_one(sha1, &e, p)) + offset = find_pack_entry_one(sha1, p); + if (!offset) die("internal error pack-check find-pack-entry-one"); - packed_object_info_detail(&e, type, &size, &store_size, + packed_object_info_detail(p, offset, type, &size, &store_size, &delta_chain_length, base_sha1); printf("%s ", sha1_to_hex(sha1)); if (!delta_chain_length) - printf("%-6s %lu %u\n", type, size, e.offset); + printf("%-6s %lu %lu\n", type, size, offset); else { - printf("%-6s %lu %u %u %s\n", type, size, e.offset, + printf("%-6s %lu %lu %u %s\n", type, size, offset, delta_chain_length, sha1_to_hex(base_sha1)); if (delta_chain_length < MAX_CHAIN) chain_histogram[delta_chain_length]++; @@ -141,18 +140,16 @@ int verify_pack(struct packed_git *p, int verbose) if (!ret) { /* Verify pack file */ - use_packed_git(p); - ret = verify_packfile(p); - unuse_packed_git(p); + struct pack_window *w_curs = NULL; + ret = verify_packfile(p, &w_curs); + unuse_pack(&w_curs); } if (verbose) { if (ret) printf("%s: bad\n", p->pack_name); else { - use_packed_git(p); show_pack_info(p); - unuse_packed_git(p); printf("%s: ok\n", p->pack_name); } } @@ -16,7 +16,4 @@ struct pack_header { }; extern int verify_pack(struct packed_git *, int); -extern int check_reuse_pack_delta(struct packed_git *, unsigned long, - unsigned char *, unsigned long *, - enum object_type *); #endif @@ -50,7 +50,7 @@ void setup_pager(void) close(fd[0]); close(fd[1]); - setenv("LESS", "-RS", 0); + setenv("LESS", "FRSX", 0); run_pager(pager); die("unable to execute pager '%s'", pager); exit(255); diff --git a/patch-delta.c b/patch-delta.c index e3a1d425ee..ed9db81fa8 100644 --- a/patch-delta.c +++ b/patch-delta.c @@ -9,8 +9,7 @@ * published by the Free Software Foundation. */ -#include <stdlib.h> -#include <string.h> +#include "git-compat-util.h" #include "delta.h" void *patch_delta(const void *src_buf, unsigned long src_size, @@ -34,9 +33,7 @@ void *patch_delta(const void *src_buf, unsigned long src_size, /* now the result size */ size = get_delta_hdr_size(&data, top); - dst_buf = malloc(size + 1); - if (!dst_buf) - return NULL; + dst_buf = xmalloc(size + 1); dst_buf[size] = 0; out = dst_buf; @@ -55,13 +52,13 @@ void *patch_delta(const void *src_buf, unsigned long src_size, if (cp_off + cp_size < cp_size || cp_off + cp_size > src_size || cp_size > size) - goto bad; + break; memcpy(out, (char *) src_buf + cp_off, cp_size); out += cp_size; size -= cp_size; } else if (cmd) { if (cmd > size) - goto bad; + break; memcpy(out, data, cmd); out += cmd; data += cmd; @@ -72,12 +69,14 @@ void *patch_delta(const void *src_buf, unsigned long src_size, * extensions. In the mean time we must fail when * encountering them (might be data corruption). */ + error("unexpected delta opcode 0"); goto bad; } } /* sanity check */ if (data != top || size != 0) { + error("delta replay has gone wild"); bad: free(dst_buf); return NULL; diff --git a/path-list.c b/path-list.c index f15a10de37..caaa5cc57b 100644 --- a/path-list.c +++ b/path-list.c @@ -1,4 +1,3 @@ -#include <stdio.h> #include "cache.h" #include "path-list.h" @@ -45,7 +44,7 @@ static int add_entry(struct path_list *list, const char *path) (list->nr - index) * sizeof(struct path_list_item)); list->items[index].path = list->strdup_paths ? - strdup(path) : (char *)path; + xstrdup(path) : (char *)path; list->items[index].util = NULL; list->nr++; @@ -57,7 +56,7 @@ struct path_list_item *path_list_insert(const char *path, struct path_list *list int index = add_entry(list, path); if (index < 0) - index = 1 - index; + index = -1 - index; return list->items + index; } @@ -85,8 +84,7 @@ void path_list_clear(struct path_list *list, int free_items) for (i = 0; i < list->nr; i++) { if (list->strdup_paths) free(list->items[i].path); - if (list->items[i].util) - free(list->items[i].util); + free(list->items[i].util); } free(list->items); } @@ -11,11 +11,16 @@ * which is what it's designed for. */ #include "cache.h" -#include <pwd.h> -static char pathname[PATH_MAX]; static char bad_path[] = "/bad-path/"; +static char *get_pathname(void) +{ + static char pathname_array[4][PATH_MAX]; + static int index; + return pathname_array[3 & ++index]; +} + static char *cleanup_path(char *path) { /* Clean it up */ @@ -31,6 +36,7 @@ char *mkpath(const char *fmt, ...) { va_list args; unsigned len; + char *pathname = get_pathname(); va_start(args, fmt); len = vsnprintf(pathname, PATH_MAX, fmt, args); @@ -43,6 +49,7 @@ char *mkpath(const char *fmt, ...) char *git_path(const char *fmt, ...) { const char *git_dir = get_git_dir(); + char *pathname = get_pathname(); va_list args; unsigned len; @@ -83,10 +90,11 @@ int git_mkstemp(char *path, size_t len, const char *template) } -int validate_symref(const char *path) +int validate_headref(const char *path) { struct stat st; char *buf, buffer[256]; + unsigned char sha1[20]; int len, fd; if (lstat(path, &st) < 0) @@ -106,20 +114,29 @@ int validate_symref(const char *path) fd = open(path, O_RDONLY); if (fd < 0) return -1; - len = read(fd, buffer, sizeof(buffer)-1); + len = read_in_full(fd, buffer, sizeof(buffer)-1); close(fd); /* * Is it a symbolic ref? */ - if (len < 4 || memcmp("ref:", buffer, 4)) + if (len < 4) return -1; - buf = buffer + 4; - len -= 4; - while (len && isspace(*buf)) - buf++, len--; - if (len >= 5 && !memcmp("refs/", buf, 5)) + if (!memcmp("ref:", buffer, 4)) { + buf = buffer + 4; + len -= 4; + while (len && isspace(*buf)) + buf++, len--; + if (len >= 5 && !memcmp("refs/", buf, 5)) + return 0; + } + + /* + * Is this a detached HEAD? + */ + if (!get_sha1_hex(buffer, sha1)) return 0; + return -1; } @@ -234,7 +251,7 @@ char *enter_repo(char *path, int strict) return NULL; if (access("objects", X_OK) == 0 && access("refs", X_OK) == 0 && - validate_symref("HEAD") == 0) { + validate_headref("HEAD") == 0) { putenv("GIT_DIR=."); check_repository_format(); return path; @@ -271,7 +288,7 @@ int adjust_shared_perm(const char *path) : 0)); if (S_ISDIR(mode)) mode |= S_ISGID; - if (chmod(path, mode) < 0) + if ((mode & st.st_mode) != mode && chmod(path, mode) < 0) return -2; return 0; } diff --git a/peek-remote.c b/peek-remote.c index 2b30980b04..353da002b4 100644 --- a/peek-remote.c +++ b/peek-remote.c @@ -1,7 +1,6 @@ #include "cache.h" #include "refs.h" #include "pkt-line.h" -#include <sys/wait.h> static const char peek_remote_usage[] = "git-peek-remote [--exec=upload-pack] [host:]directory"; @@ -67,6 +66,6 @@ int main(int argc, char **argv) ret = peek_remote(fd, flags); close(fd[0]); close(fd[1]); - finish_connect(pid); - return ret; + ret |= finish_connect(pid); + return !!ret; } diff --git a/perl/.gitignore b/perl/.gitignore new file mode 100644 index 0000000000..98b24772c7 --- /dev/null +++ b/perl/.gitignore @@ -0,0 +1,5 @@ +perl.mak +perl.mak.old +blib +blibdirs +pm_to_blib diff --git a/perl/Git.pm b/perl/Git.pm new file mode 100644 index 0000000000..3474ad320f --- /dev/null +++ b/perl/Git.pm @@ -0,0 +1,837 @@ +=head1 NAME + +Git - Perl interface to the Git version control system + +=cut + + +package Git; + +use strict; + + +BEGIN { + +our ($VERSION, @ISA, @EXPORT, @EXPORT_OK); + +# Totally unstable API. +$VERSION = '0.01'; + + +=head1 SYNOPSIS + + use Git; + + my $version = Git::command_oneline('version'); + + git_cmd_try { Git::command_noisy('update-server-info') } + '%s failed w/ code %d'; + + my $repo = Git->repository (Directory => '/srv/git/cogito.git'); + + + my @revs = $repo->command('rev-list', '--since=last monday', '--all'); + + my ($fh, $c) = $repo->command_output_pipe('rev-list', '--since=last monday', '--all'); + my $lastrev = <$fh>; chomp $lastrev; + $repo->command_close_pipe($fh, $c); + + my $lastrev = $repo->command_oneline( [ 'rev-list', '--all' ], + STDERR => 0 ); + +=cut + + +require Exporter; + +@ISA = qw(Exporter); + +@EXPORT = qw(git_cmd_try); + +# Methods which can be called as standalone functions as well: +@EXPORT_OK = qw(command command_oneline command_noisy + command_output_pipe command_input_pipe command_close_pipe + version exec_path hash_object git_cmd_try); + + +=head1 DESCRIPTION + +This module provides Perl scripts easy way to interface the Git version control +system. The modules have an easy and well-tested way to call arbitrary Git +commands; in the future, the interface will also provide specialized methods +for doing easily operations which are not totally trivial to do over +the generic command interface. + +While some commands can be executed outside of any context (e.g. 'version' +or 'init'), most operations require a repository context, which in practice +means getting an instance of the Git object using the repository() constructor. +(In the future, we will also get a new_repository() constructor.) All commands +called as methods of the object are then executed in the context of the +repository. + +Part of the "repository state" is also information about path to the attached +working copy (unless you work with a bare repository). You can also navigate +inside of the working copy using the C<wc_chdir()> method. (Note that +the repository object is self-contained and will not change working directory +of your process.) + +TODO: In the future, we might also do + + my $remoterepo = $repo->remote_repository (Name => 'cogito', Branch => 'master'); + $remoterepo ||= Git->remote_repository ('http://git.or.cz/cogito.git/'); + my @refs = $remoterepo->refs(); + +Currently, the module merely wraps calls to external Git tools. In the future, +it will provide a much faster way to interact with Git by linking directly +to libgit. This should be completely opaque to the user, though (performance +increate nonwithstanding). + +=cut + + +use Carp qw(carp croak); # but croak is bad - throw instead +use Error qw(:try); +use Cwd qw(abs_path); + +} + + +=head1 CONSTRUCTORS + +=over 4 + +=item repository ( OPTIONS ) + +=item repository ( DIRECTORY ) + +=item repository () + +Construct a new repository object. +C<OPTIONS> are passed in a hash like fashion, using key and value pairs. +Possible options are: + +B<Repository> - Path to the Git repository. + +B<WorkingCopy> - Path to the associated working copy; not strictly required +as many commands will happily crunch on a bare repository. + +B<WorkingSubdir> - Subdirectory in the working copy to work inside. +Just left undefined if you do not want to limit the scope of operations. + +B<Directory> - Path to the Git working directory in its usual setup. +The C<.git> directory is searched in the directory and all the parent +directories; if found, C<WorkingCopy> is set to the directory containing +it and C<Repository> to the C<.git> directory itself. If no C<.git> +directory was found, the C<Directory> is assumed to be a bare repository, +C<Repository> is set to point at it and C<WorkingCopy> is left undefined. +If the C<$GIT_DIR> environment variable is set, things behave as expected +as well. + +You should not use both C<Directory> and either of C<Repository> and +C<WorkingCopy> - the results of that are undefined. + +Alternatively, a directory path may be passed as a single scalar argument +to the constructor; it is equivalent to setting only the C<Directory> option +field. + +Calling the constructor with no options whatsoever is equivalent to +calling it with C<< Directory => '.' >>. In general, if you are building +a standard porcelain command, simply doing C<< Git->repository() >> should +do the right thing and setup the object to reflect exactly where the user +is right now. + +=cut + +sub repository { + my $class = shift; + my @args = @_; + my %opts = (); + my $self; + + if (defined $args[0]) { + if ($#args % 2 != 1) { + # Not a hash. + $#args == 0 or throw Error::Simple("bad usage"); + %opts = ( Directory => $args[0] ); + } else { + %opts = @args; + } + } + + if (not defined $opts{Repository} and not defined $opts{WorkingCopy}) { + $opts{Directory} ||= '.'; + } + + if ($opts{Directory}) { + -d $opts{Directory} or throw Error::Simple("Directory not found: $!"); + + my $search = Git->repository(WorkingCopy => $opts{Directory}); + my $dir; + try { + $dir = $search->command_oneline(['rev-parse', '--git-dir'], + STDERR => 0); + } catch Git::Error::Command with { + $dir = undef; + }; + + if ($dir) { + $dir =~ m#^/# or $dir = $opts{Directory} . '/' . $dir; + $opts{Repository} = $dir; + + # If --git-dir went ok, this shouldn't die either. + my $prefix = $search->command_oneline('rev-parse', '--show-prefix'); + $dir = abs_path($opts{Directory}) . '/'; + if ($prefix) { + if (substr($dir, -length($prefix)) ne $prefix) { + throw Error::Simple("rev-parse confused me - $dir does not have trailing $prefix"); + } + substr($dir, -length($prefix)) = ''; + } + $opts{WorkingCopy} = $dir; + $opts{WorkingSubdir} = $prefix; + + } else { + # A bare repository? Let's see... + $dir = $opts{Directory}; + + unless (-d "$dir/refs" and -d "$dir/objects" and -e "$dir/HEAD") { + # Mimick git-rev-parse --git-dir error message: + throw Error::Simple('fatal: Not a git repository'); + } + my $search = Git->repository(Repository => $dir); + try { + $search->command('symbolic-ref', 'HEAD'); + } catch Git::Error::Command with { + # Mimick git-rev-parse --git-dir error message: + throw Error::Simple('fatal: Not a git repository'); + } + + $opts{Repository} = abs_path($dir); + } + + delete $opts{Directory}; + } + + $self = { opts => \%opts }; + bless $self, $class; +} + + +=back + +=head1 METHODS + +=over 4 + +=item command ( COMMAND [, ARGUMENTS... ] ) + +=item command ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + +Execute the given Git C<COMMAND> (specify it without the 'git-' +prefix), optionally with the specified extra C<ARGUMENTS>. + +The second more elaborate form can be used if you want to further adjust +the command execution. Currently, only one option is supported: + +B<STDERR> - How to deal with the command's error output. By default (C<undef>) +it is delivered to the caller's C<STDERR>. A false value (0 or '') will cause +it to be thrown away. If you want to process it, you can get it in a filehandle +you specify, but you must be extremely careful; if the error output is not +very short and you want to read it in the same process as where you called +C<command()>, you are set up for a nice deadlock! + +The method can be called without any instance or on a specified Git repository +(in that case the command will be run in the repository context). + +In scalar context, it returns all the command output in a single string +(verbatim). + +In array context, it returns an array containing lines printed to the +command's stdout (without trailing newlines). + +In both cases, the command's stdin and stderr are the same as the caller's. + +=cut + +sub command { + my ($fh, $ctx) = command_output_pipe(@_); + + if (not defined wantarray) { + # Nothing to pepper the possible exception with. + _cmd_close($fh, $ctx); + + } elsif (not wantarray) { + local $/; + my $text = <$fh>; + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + # Pepper with the output: + my $E = shift; + $E->{'-outputref'} = \$text; + throw $E; + }; + return $text; + + } else { + my @lines = <$fh>; + chomp @lines; + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + my $E = shift; + $E->{'-outputref'} = \@lines; + throw $E; + }; + return @lines; + } +} + + +=item command_oneline ( COMMAND [, ARGUMENTS... ] ) + +=item command_oneline ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + +Execute the given C<COMMAND> in the same way as command() +does but always return a scalar string containing the first line +of the command's standard output. + +=cut + +sub command_oneline { + my ($fh, $ctx) = command_output_pipe(@_); + + my $line = <$fh>; + defined $line and chomp $line; + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + # Pepper with the output: + my $E = shift; + $E->{'-outputref'} = \$line; + throw $E; + }; + return $line; +} + + +=item command_output_pipe ( COMMAND [, ARGUMENTS... ] ) + +=item command_output_pipe ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + +Execute the given C<COMMAND> in the same way as command() +does but return a pipe filehandle from which the command output can be +read. + +The function can return C<($pipe, $ctx)> in array context. +See C<command_close_pipe()> for details. + +=cut + +sub command_output_pipe { + _command_common_pipe('-|', @_); +} + + +=item command_input_pipe ( COMMAND [, ARGUMENTS... ] ) + +=item command_input_pipe ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + +Execute the given C<COMMAND> in the same way as command_output_pipe() +does but return an input pipe filehandle instead; the command output +is not captured. + +The function can return C<($pipe, $ctx)> in array context. +See C<command_close_pipe()> for details. + +=cut + +sub command_input_pipe { + _command_common_pipe('|-', @_); +} + + +=item command_close_pipe ( PIPE [, CTX ] ) + +Close the C<PIPE> as returned from C<command_*_pipe()>, checking +whether the command finished successfuly. The optional C<CTX> argument +is required if you want to see the command name in the error message, +and it is the second value returned by C<command_*_pipe()> when +called in array context. The call idiom is: + + my ($fh, $ctx) = $r->command_output_pipe('status'); + while (<$fh>) { ... } + $r->command_close_pipe($fh, $ctx); + +Note that you should not rely on whatever actually is in C<CTX>; +currently it is simply the command name but in future the context might +have more complicated structure. + +=cut + +sub command_close_pipe { + my ($self, $fh, $ctx) = _maybe_self(@_); + $ctx ||= '<unknown>'; + _cmd_close($fh, $ctx); +} + + +=item command_noisy ( COMMAND [, ARGUMENTS... ] ) + +Execute the given C<COMMAND> in the same way as command() does but do not +capture the command output - the standard output is not redirected and goes +to the standard output of the caller application. + +While the method is called command_noisy(), you might want to as well use +it for the most silent Git commands which you know will never pollute your +stdout but you want to avoid the overhead of the pipe setup when calling them. + +The function returns only after the command has finished running. + +=cut + +sub command_noisy { + my ($self, $cmd, @args) = _maybe_self(@_); + _check_valid_cmd($cmd); + + my $pid = fork; + if (not defined $pid) { + throw Error::Simple("fork failed: $!"); + } elsif ($pid == 0) { + _cmd_exec($self, $cmd, @args); + } + if (waitpid($pid, 0) > 0 and $?>>8 != 0) { + throw Git::Error::Command(join(' ', $cmd, @args), $? >> 8); + } +} + + +=item version () + +Return the Git version in use. + +=cut + +sub version { + my $verstr = command_oneline('--version'); + $verstr =~ s/^git version //; + $verstr; +} + + +=item exec_path () + +Return path to the Git sub-command executables (the same as +C<git --exec-path>). Useful mostly only internally. + +=cut + +sub exec_path { command_oneline('--exec-path') } + + +=item repo_path () + +Return path to the git repository. Must be called on a repository instance. + +=cut + +sub repo_path { $_[0]->{opts}->{Repository} } + + +=item wc_path () + +Return path to the working copy. Must be called on a repository instance. + +=cut + +sub wc_path { $_[0]->{opts}->{WorkingCopy} } + + +=item wc_subdir () + +Return path to the subdirectory inside of a working copy. Must be called +on a repository instance. + +=cut + +sub wc_subdir { $_[0]->{opts}->{WorkingSubdir} ||= '' } + + +=item wc_chdir ( SUBDIR ) + +Change the working copy subdirectory to work within. The C<SUBDIR> is +relative to the working copy root directory (not the current subdirectory). +Must be called on a repository instance attached to a working copy +and the directory must exist. + +=cut + +sub wc_chdir { + my ($self, $subdir) = @_; + $self->wc_path() + or throw Error::Simple("bare repository"); + + -d $self->wc_path().'/'.$subdir + or throw Error::Simple("subdir not found: $!"); + # Of course we will not "hold" the subdirectory so anyone + # can delete it now and we will never know. But at least we tried. + + $self->{opts}->{WorkingSubdir} = $subdir; +} + + +=item config ( VARIABLE ) + +Retrieve the configuration C<VARIABLE> in the same manner as C<repo-config> +does. In scalar context requires the variable to be set only one time +(exception is thrown otherwise), in array context returns allows the +variable to be set multiple times and returns all the values. + +Must be called on a repository instance. + +This currently wraps command('repo-config') so it is not so fast. + +=cut + +sub config { + my ($self, $var) = @_; + $self->repo_path() + or throw Error::Simple("not a repository"); + + try { + if (wantarray) { + return $self->command('repo-config', '--get-all', $var); + } else { + return $self->command_oneline('repo-config', '--get', $var); + } + } catch Git::Error::Command with { + my $E = shift; + if ($E->value() == 1) { + # Key not found. + return undef; + } else { + throw $E; + } + }; +} + + +=item ident ( TYPE | IDENTSTR ) + +=item ident_person ( TYPE | IDENTSTR | IDENTARRAY ) + +This suite of functions retrieves and parses ident information, as stored +in the commit and tag objects or produced by C<var GIT_type_IDENT> (thus +C<TYPE> can be either I<author> or I<committer>; case is insignificant). + +The C<ident> method retrieves the ident information from C<git-var> +and either returns it as a scalar string or as an array with the fields parsed. +Alternatively, it can take a prepared ident string (e.g. from the commit +object) and just parse it. + +C<ident_person> returns the person part of the ident - name and email; +it can take the same arguments as C<ident> or the array returned by C<ident>. + +The synopsis is like: + + my ($name, $email, $time_tz) = ident('author'); + "$name <$email>" eq ident_person('author'); + "$name <$email>" eq ident_person($name); + $time_tz =~ /^\d+ [+-]\d{4}$/; + +Both methods must be called on a repository instance. + +=cut + +sub ident { + my ($self, $type) = @_; + my $identstr; + if (lc $type eq lc 'committer' or lc $type eq lc 'author') { + $identstr = $self->command_oneline('var', 'GIT_'.uc($type).'_IDENT'); + } else { + $identstr = $type; + } + if (wantarray) { + return $identstr =~ /^(.*) <(.*)> (\d+ [+-]\d{4})$/; + } else { + return $identstr; + } +} + +sub ident_person { + my ($self, @ident) = @_; + $#ident == 0 and @ident = $self->ident($ident[0]); + return "$ident[0] <$ident[1]>"; +} + + +=item hash_object ( TYPE, FILENAME ) + +Compute the SHA1 object id of the given C<FILENAME> (or data waiting in +C<FILEHANDLE>) considering it is of the C<TYPE> object type (C<blob>, +C<commit>, C<tree>). + +The method can be called without any instance or on a specified Git repository, +it makes zero difference. + +The function returns the SHA1 hash. + +=cut + +# TODO: Support for passing FILEHANDLE instead of FILENAME +sub hash_object { + my ($self, $type, $file) = _maybe_self(@_); + command_oneline('hash-object', '-t', $type, $file); +} + + + +=back + +=head1 ERROR HANDLING + +All functions are supposed to throw Perl exceptions in case of errors. +See the L<Error> module on how to catch those. Most exceptions are mere +L<Error::Simple> instances. + +However, the C<command()>, C<command_oneline()> and C<command_noisy()> +functions suite can throw C<Git::Error::Command> exceptions as well: those are +thrown when the external command returns an error code and contain the error +code as well as access to the captured command's output. The exception class +provides the usual C<stringify> and C<value> (command's exit code) methods and +in addition also a C<cmd_output> method that returns either an array or a +string with the captured command output (depending on the original function +call context; C<command_noisy()> returns C<undef>) and $<cmdline> which +returns the command and its arguments (but without proper quoting). + +Note that the C<command_*_pipe()> functions cannot throw this exception since +it has no idea whether the command failed or not. You will only find out +at the time you C<close> the pipe; if you want to have that automated, +use C<command_close_pipe()>, which can throw the exception. + +=cut + +{ + package Git::Error::Command; + + @Git::Error::Command::ISA = qw(Error); + + sub new { + my $self = shift; + my $cmdline = '' . shift; + my $value = 0 + shift; + my $outputref = shift; + my(@args) = (); + + local $Error::Depth = $Error::Depth + 1; + + push(@args, '-cmdline', $cmdline); + push(@args, '-value', $value); + push(@args, '-outputref', $outputref); + + $self->SUPER::new(-text => 'command returned error', @args); + } + + sub stringify { + my $self = shift; + my $text = $self->SUPER::stringify; + $self->cmdline() . ': ' . $text . ': ' . $self->value() . "\n"; + } + + sub cmdline { + my $self = shift; + $self->{'-cmdline'}; + } + + sub cmd_output { + my $self = shift; + my $ref = $self->{'-outputref'}; + defined $ref or undef; + if (ref $ref eq 'ARRAY') { + return @$ref; + } else { # SCALAR + return $$ref; + } + } +} + +=over 4 + +=item git_cmd_try { CODE } ERRMSG + +This magical statement will automatically catch any C<Git::Error::Command> +exceptions thrown by C<CODE> and make your program die with C<ERRMSG> +on its lips; the message will have %s substituted for the command line +and %d for the exit status. This statement is useful mostly for producing +more user-friendly error messages. + +In case of no exception caught the statement returns C<CODE>'s return value. + +Note that this is the only auto-exported function. + +=cut + +sub git_cmd_try(&$) { + my ($code, $errmsg) = @_; + my @result; + my $err; + my $array = wantarray; + try { + if ($array) { + @result = &$code; + } else { + $result[0] = &$code; + } + } catch Git::Error::Command with { + my $E = shift; + $err = $errmsg; + $err =~ s/\%s/$E->cmdline()/ge; + $err =~ s/\%d/$E->value()/ge; + # We can't croak here since Error.pm would mangle + # that to Error::Simple. + }; + $err and croak $err; + return $array ? @result : $result[0]; +} + + +=back + +=head1 COPYRIGHT + +Copyright 2006 by Petr Baudis E<lt>pasky@suse.czE<gt>. + +This module is free software; it may be used, copied, modified +and distributed under the terms of the GNU General Public Licence, +either version 2, or (at your option) any later version. + +=cut + + +# Take raw method argument list and return ($obj, @args) in case +# the method was called upon an instance and (undef, @args) if +# it was called directly. +sub _maybe_self { + # This breaks inheritance. Oh well. + ref $_[0] eq 'Git' ? @_ : (undef, @_); +} + +# Check if the command id is something reasonable. +sub _check_valid_cmd { + my ($cmd) = @_; + $cmd =~ /^[a-z0-9A-Z_-]+$/ or throw Error::Simple("bad command: $cmd"); +} + +# Common backend for the pipe creators. +sub _command_common_pipe { + my $direction = shift; + my ($self, @p) = _maybe_self(@_); + my (%opts, $cmd, @args); + if (ref $p[0]) { + ($cmd, @args) = @{shift @p}; + %opts = ref $p[0] ? %{$p[0]} : @p; + } else { + ($cmd, @args) = @p; + } + _check_valid_cmd($cmd); + + my $fh; + if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { + # ActiveState Perl + #defined $opts{STDERR} and + # warn 'ignoring STDERR option - running w/ ActiveState'; + $direction eq '-|' or + die 'input pipe for ActiveState not implemented'; + tie ($fh, 'Git::activestate_pipe', $cmd, @args); + + } else { + my $pid = open($fh, $direction); + if (not defined $pid) { + throw Error::Simple("open failed: $!"); + } elsif ($pid == 0) { + if (defined $opts{STDERR}) { + close STDERR; + } + if ($opts{STDERR}) { + open (STDERR, '>&', $opts{STDERR}) + or die "dup failed: $!"; + } + _cmd_exec($self, $cmd, @args); + } + } + return wantarray ? ($fh, join(' ', $cmd, @args)) : $fh; +} + +# When already in the subprocess, set up the appropriate state +# for the given repository and execute the git command. +sub _cmd_exec { + my ($self, @args) = @_; + if ($self) { + $self->repo_path() and $ENV{'GIT_DIR'} = $self->repo_path(); + $self->wc_path() and chdir($self->wc_path()); + $self->wc_subdir() and chdir($self->wc_subdir()); + } + _execv_git_cmd(@args); + die "exec failed: $!"; +} + +# Execute the given Git command ($_[0]) with arguments ($_[1..]) +# by searching for it at proper places. +sub _execv_git_cmd { exec('git', @_); } + +# Close pipe to a subprocess. +sub _cmd_close { + my ($fh, $ctx) = @_; + if (not close $fh) { + if ($!) { + # It's just close, no point in fatalities + carp "error closing pipe: $!"; + } elsif ($? >> 8) { + # The caller should pepper this. + throw Git::Error::Command($ctx, $? >> 8); + } + # else we might e.g. closed a live stream; the command + # dying of SIGPIPE would drive us here. + } +} + + +sub DESTROY { } + + +# Pipe implementation for ActiveState Perl. + +package Git::activestate_pipe; +use strict; + +sub TIEHANDLE { + my ($class, @params) = @_; + # FIXME: This is probably horrible idea and the thing will explode + # at the moment you give it arguments that require some quoting, + # but I have no ActiveState clue... --pasky + my $cmdline = join " ", @params; + my @data = qx{$cmdline}; + bless { i => 0, data => \@data }, $class; +} + +sub READLINE { + my $self = shift; + if ($self->{i} >= scalar @{$self->{data}}) { + return undef; + } + return $self->{'data'}->[ $self->{i}++ ]; +} + +sub CLOSE { + my $self = shift; + delete $self->{data}; + delete $self->{i}; +} + +sub EOF { + my $self = shift; + return ($self->{i} >= scalar @{$self->{data}}); +} + + +1; # Famous last words diff --git a/perl/Makefile b/perl/Makefile new file mode 100644 index 0000000000..099beda873 --- /dev/null +++ b/perl/Makefile @@ -0,0 +1,39 @@ +# +# Makefile for perl support modules and routine +# +makfile:=perl.mak + +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +prefix_SQ = $(subst ','\'',$(prefix)) + +all install instlibdir: $(makfile) + $(MAKE) -f $(makfile) $@ + +clean: + test -f $(makfile) && $(MAKE) -f $(makfile) $@ || exit 0 + $(RM) ppport.h + $(RM) $(makfile) + $(RM) $(makfile).old + +ifdef NO_PERL_MAKEMAKER +instdir_SQ = $(subst ','\'',$(prefix)/lib) +$(makfile): ../GIT-CFLAGS Makefile + echo all: > $@ + echo ' :' >> $@ + echo install: >> $@ + echo ' mkdir -p $(instdir_SQ)' >> $@ + echo ' $(RM) $(instdir_SQ)/Git.pm; cp Git.pm $(instdir_SQ)' >> $@ + echo ' $(RM) $(instdir_SQ)/Error.pm; \ + cp private-Error.pm $(instdir_SQ)/Error.pm' >> $@ + echo instlibdir: >> $@ + echo ' echo $(instdir_SQ)' >> $@ +else +$(makfile): Makefile.PL ../GIT-CFLAGS + '$(PERL_PATH_SQ)' $< PREFIX='$(prefix_SQ)' +endif + +# this is just added comfort for calling make directly in perl dir +# (even though GIT-CFLAGS aren't used yet. If ever) +../GIT-CFLAGS: + $(MAKE) -C .. GIT-CFLAGS + diff --git a/perl/Makefile.PL b/perl/Makefile.PL new file mode 100644 index 0000000000..41687757a7 --- /dev/null +++ b/perl/Makefile.PL @@ -0,0 +1,29 @@ +use ExtUtils::MakeMaker; + +sub MY::postamble { + return <<'MAKE_FRAG'; +instlibdir: + @echo '$(INSTALLSITELIB)' + +MAKE_FRAG +} + +my %pm = ('Git.pm' => '$(INST_LIBDIR)/Git.pm'); + +# We come with our own bundled Error.pm. It's not in the set of default +# Perl modules so install it if it's not available on the system yet. +eval { require Error }; +if ($@) { + $pm{'private-Error.pm'} = '$(INST_LIBDIR)/Error.pm'; +} + +my %extra; +$extra{DESTDIR} = $ENV{DESTDIR} if $ENV{DESTDIR}; + +WriteMakefile( + NAME => 'Git', + VERSION_FROM => 'Git.pm', + PM => \%pm, + MAKEFILE => 'perl.mak', + %extra +); diff --git a/perl/private-Error.pm b/perl/private-Error.pm new file mode 100644 index 0000000000..8fff86699f --- /dev/null +++ b/perl/private-Error.pm @@ -0,0 +1,827 @@ +# Error.pm +# +# Copyright (c) 1997-8 Graham Barr <gbarr@ti.com>. All rights reserved. +# This program is free software; you can redistribute it and/or +# modify it under the same terms as Perl itself. +# +# Based on my original Error.pm, and Exceptions.pm by Peter Seibel +# <peter@weblogic.com> and adapted by Jesse Glick <jglick@sig.bsh.com>. +# +# but modified ***significantly*** + +package Error; + +use strict; +use vars qw($VERSION); +use 5.004; + +$VERSION = "0.15009"; + +use overload ( + '""' => 'stringify', + '0+' => 'value', + 'bool' => sub { return 1; }, + 'fallback' => 1 +); + +$Error::Depth = 0; # Depth to pass to caller() +$Error::Debug = 0; # Generate verbose stack traces +@Error::STACK = (); # Clause stack for try +$Error::THROWN = undef; # last error thrown, a workaround until die $ref works + +my $LAST; # Last error created +my %ERROR; # Last error associated with package + +sub throw_Error_Simple +{ + my $args = shift; + return Error::Simple->new($args->{'text'}); +} + +$Error::ObjectifyCallback = \&throw_Error_Simple; + + +# Exported subs are defined in Error::subs + +sub import { + shift; + local $Exporter::ExportLevel = $Exporter::ExportLevel + 1; + Error::subs->import(@_); +} + +# I really want to use last for the name of this method, but it is a keyword +# which prevent the syntax last Error + +sub prior { + shift; # ignore + + return $LAST unless @_; + + my $pkg = shift; + return exists $ERROR{$pkg} ? $ERROR{$pkg} : undef + unless ref($pkg); + + my $obj = $pkg; + my $err = undef; + if($obj->isa('HASH')) { + $err = $obj->{'__Error__'} + if exists $obj->{'__Error__'}; + } + elsif($obj->isa('GLOB')) { + $err = ${*$obj}{'__Error__'} + if exists ${*$obj}{'__Error__'}; + } + + $err; +} + +sub flush { + shift; #ignore + + unless (@_) { + $LAST = undef; + return; + } + + my $pkg = shift; + return unless ref($pkg); + + undef $ERROR{$pkg} if defined $ERROR{$pkg}; +} + +# Return as much information as possible about where the error +# happened. The -stacktrace element only exists if $Error::DEBUG +# was set when the error was created + +sub stacktrace { + my $self = shift; + + return $self->{'-stacktrace'} + if exists $self->{'-stacktrace'}; + + my $text = exists $self->{'-text'} ? $self->{'-text'} : "Died"; + + $text .= sprintf(" at %s line %d.\n", $self->file, $self->line) + unless($text =~ /\n$/s); + + $text; +} + +# Allow error propagation, ie +# +# $ber->encode(...) or +# return Error->prior($ber)->associate($ldap); + +sub associate { + my $err = shift; + my $obj = shift; + + return unless ref($obj); + + if($obj->isa('HASH')) { + $obj->{'__Error__'} = $err; + } + elsif($obj->isa('GLOB')) { + ${*$obj}{'__Error__'} = $err; + } + $obj = ref($obj); + $ERROR{ ref($obj) } = $err; + + return; +} + +sub new { + my $self = shift; + my($pkg,$file,$line) = caller($Error::Depth); + + my $err = bless { + '-package' => $pkg, + '-file' => $file, + '-line' => $line, + @_ + }, $self; + + $err->associate($err->{'-object'}) + if(exists $err->{'-object'}); + + # To always create a stacktrace would be very inefficient, so + # we only do it if $Error::Debug is set + + if($Error::Debug) { + require Carp; + local $Carp::CarpLevel = $Error::Depth; + my $text = defined($err->{'-text'}) ? $err->{'-text'} : "Error"; + my $trace = Carp::longmess($text); + # Remove try calls from the trace + $trace =~ s/(\n\s+\S+__ANON__[^\n]+)?\n\s+eval[^\n]+\n\s+Error::subs::try[^\n]+(?=\n)//sog; + $trace =~ s/(\n\s+\S+__ANON__[^\n]+)?\n\s+eval[^\n]+\n\s+Error::subs::run_clauses[^\n]+\n\s+Error::subs::try[^\n]+(?=\n)//sog; + $err->{'-stacktrace'} = $trace + } + + $@ = $LAST = $ERROR{$pkg} = $err; +} + +# Throw an error. this contains some very gory code. + +sub throw { + my $self = shift; + local $Error::Depth = $Error::Depth + 1; + + # if we are not rethrow-ing then create the object to throw + $self = $self->new(@_) unless ref($self); + + die $Error::THROWN = $self; +} + +# syntactic sugar for +# +# die with Error( ... ); + +sub with { + my $self = shift; + local $Error::Depth = $Error::Depth + 1; + + $self->new(@_); +} + +# syntactic sugar for +# +# record Error( ... ) and return; + +sub record { + my $self = shift; + local $Error::Depth = $Error::Depth + 1; + + $self->new(@_); +} + +# catch clause for +# +# try { ... } catch CLASS with { ... } + +sub catch { + my $pkg = shift; + my $code = shift; + my $clauses = shift || {}; + my $catch = $clauses->{'catch'} ||= []; + + unshift @$catch, $pkg, $code; + + $clauses; +} + +# Object query methods + +sub object { + my $self = shift; + exists $self->{'-object'} ? $self->{'-object'} : undef; +} + +sub file { + my $self = shift; + exists $self->{'-file'} ? $self->{'-file'} : undef; +} + +sub line { + my $self = shift; + exists $self->{'-line'} ? $self->{'-line'} : undef; +} + +sub text { + my $self = shift; + exists $self->{'-text'} ? $self->{'-text'} : undef; +} + +# overload methods + +sub stringify { + my $self = shift; + defined $self->{'-text'} ? $self->{'-text'} : "Died"; +} + +sub value { + my $self = shift; + exists $self->{'-value'} ? $self->{'-value'} : undef; +} + +package Error::Simple; + +@Error::Simple::ISA = qw(Error); + +sub new { + my $self = shift; + my $text = "" . shift; + my $value = shift; + my(@args) = (); + + local $Error::Depth = $Error::Depth + 1; + + @args = ( -file => $1, -line => $2) + if($text =~ s/\s+at\s+(\S+)\s+line\s+(\d+)(?:,\s*<[^>]*>\s+line\s+\d+)?\.?\n?$//s); + push(@args, '-value', 0 + $value) + if defined($value); + + $self->SUPER::new(-text => $text, @args); +} + +sub stringify { + my $self = shift; + my $text = $self->SUPER::stringify; + $text .= sprintf(" at %s line %d.\n", $self->file, $self->line) + unless($text =~ /\n$/s); + $text; +} + +########################################################################## +########################################################################## + +# Inspired by code from Jesse Glick <jglick@sig.bsh.com> and +# Peter Seibel <peter@weblogic.com> + +package Error::subs; + +use Exporter (); +use vars qw(@EXPORT_OK @ISA %EXPORT_TAGS); + +@EXPORT_OK = qw(try with finally except otherwise); +%EXPORT_TAGS = (try => \@EXPORT_OK); + +@ISA = qw(Exporter); + + +sub blessed { + my $item = shift; + local $@; # don't kill an outer $@ + ref $item and eval { $item->can('can') }; +} + + +sub run_clauses ($$$\@) { + my($clauses,$err,$wantarray,$result) = @_; + my $code = undef; + + $err = $Error::ObjectifyCallback->({'text' =>$err}) unless ref($err); + + CATCH: { + + # catch + my $catch; + if(defined($catch = $clauses->{'catch'})) { + my $i = 0; + + CATCHLOOP: + for( ; $i < @$catch ; $i += 2) { + my $pkg = $catch->[$i]; + unless(defined $pkg) { + #except + splice(@$catch,$i,2,$catch->[$i+1]->()); + $i -= 2; + next CATCHLOOP; + } + elsif(blessed($err) && $err->isa($pkg)) { + $code = $catch->[$i+1]; + while(1) { + my $more = 0; + local($Error::THROWN); + my $ok = eval { + if($wantarray) { + @{$result} = $code->($err,\$more); + } + elsif(defined($wantarray)) { + @{$result} = (); + $result->[0] = $code->($err,\$more); + } + else { + $code->($err,\$more); + } + 1; + }; + if( $ok ) { + next CATCHLOOP if $more; + undef $err; + } + else { + $err = defined($Error::THROWN) + ? $Error::THROWN : $@; + $err = $Error::ObjectifyCallback->({'text' =>$err}) + unless ref($err); + } + last CATCH; + }; + } + } + } + + # otherwise + my $owise; + if(defined($owise = $clauses->{'otherwise'})) { + my $code = $clauses->{'otherwise'}; + my $more = 0; + my $ok = eval { + if($wantarray) { + @{$result} = $code->($err,\$more); + } + elsif(defined($wantarray)) { + @{$result} = (); + $result->[0] = $code->($err,\$more); + } + else { + $code->($err,\$more); + } + 1; + }; + if( $ok ) { + undef $err; + } + else { + $err = defined($Error::THROWN) + ? $Error::THROWN : $@; + + $err = $Error::ObjectifyCallback->({'text' =>$err}) + unless ref($err); + } + } + } + $err; +} + +sub try (&;$) { + my $try = shift; + my $clauses = @_ ? shift : {}; + my $ok = 0; + my $err = undef; + my @result = (); + + unshift @Error::STACK, $clauses; + + my $wantarray = wantarray(); + + do { + local $Error::THROWN = undef; + local $@ = undef; + + $ok = eval { + if($wantarray) { + @result = $try->(); + } + elsif(defined $wantarray) { + $result[0] = $try->(); + } + else { + $try->(); + } + 1; + }; + + $err = defined($Error::THROWN) ? $Error::THROWN : $@ + unless $ok; + }; + + shift @Error::STACK; + + $err = run_clauses($clauses,$err,wantarray,@result) + unless($ok); + + $clauses->{'finally'}->() + if(defined($clauses->{'finally'})); + + if (defined($err)) + { + if (blessed($err) && $err->can('throw')) + { + throw $err; + } + else + { + die $err; + } + } + + wantarray ? @result : $result[0]; +} + +# Each clause adds a sub to the list of clauses. The finally clause is +# always the last, and the otherwise clause is always added just before +# the finally clause. +# +# All clauses, except the finally clause, add a sub which takes one argument +# this argument will be the error being thrown. The sub will return a code ref +# if that clause can handle that error, otherwise undef is returned. +# +# The otherwise clause adds a sub which unconditionally returns the users +# code reference, this is why it is forced to be last. +# +# The catch clause is defined in Error.pm, as the syntax causes it to +# be called as a method + +sub with (&;$) { + @_ +} + +sub finally (&) { + my $code = shift; + my $clauses = { 'finally' => $code }; + $clauses; +} + +# The except clause is a block which returns a hashref or a list of +# key-value pairs, where the keys are the classes and the values are subs. + +sub except (&;$) { + my $code = shift; + my $clauses = shift || {}; + my $catch = $clauses->{'catch'} ||= []; + + my $sub = sub { + my $ref; + my(@array) = $code->($_[0]); + if(@array == 1 && ref($array[0])) { + $ref = $array[0]; + $ref = [ %$ref ] + if(UNIVERSAL::isa($ref,'HASH')); + } + else { + $ref = \@array; + } + @$ref + }; + + unshift @{$catch}, undef, $sub; + + $clauses; +} + +sub otherwise (&;$) { + my $code = shift; + my $clauses = shift || {}; + + if(exists $clauses->{'otherwise'}) { + require Carp; + Carp::croak("Multiple otherwise clauses"); + } + + $clauses->{'otherwise'} = $code; + + $clauses; +} + +1; +__END__ + +=head1 NAME + +Error - Error/exception handling in an OO-ish way + +=head1 SYNOPSIS + + use Error qw(:try); + + throw Error::Simple( "A simple error"); + + sub xyz { + ... + record Error::Simple("A simple error") + and return; + } + + unlink($file) or throw Error::Simple("$file: $!",$!); + + try { + do_some_stuff(); + die "error!" if $condition; + throw Error::Simple -text => "Oops!" if $other_condition; + } + catch Error::IO with { + my $E = shift; + print STDERR "File ", $E->{'-file'}, " had a problem\n"; + } + except { + my $E = shift; + my $general_handler=sub {send_message $E->{-description}}; + return { + UserException1 => $general_handler, + UserException2 => $general_handler + }; + } + otherwise { + print STDERR "Well I don't know what to say\n"; + } + finally { + close_the_garage_door_already(); # Should be reliable + }; # Don't forget the trailing ; or you might be surprised + +=head1 DESCRIPTION + +The C<Error> package provides two interfaces. Firstly C<Error> provides +a procedural interface to exception handling. Secondly C<Error> is a +base class for errors/exceptions that can either be thrown, for +subsequent catch, or can simply be recorded. + +Errors in the class C<Error> should not be thrown directly, but the +user should throw errors from a sub-class of C<Error>. + +=head1 PROCEDURAL INTERFACE + +C<Error> exports subroutines to perform exception handling. These will +be exported if the C<:try> tag is used in the C<use> line. + +=over 4 + +=item try BLOCK CLAUSES + +C<try> is the main subroutine called by the user. All other subroutines +exported are clauses to the try subroutine. + +The BLOCK will be evaluated and, if no error is throw, try will return +the result of the block. + +C<CLAUSES> are the subroutines below, which describe what to do in the +event of an error being thrown within BLOCK. + +=item catch CLASS with BLOCK + +This clauses will cause all errors that satisfy C<$err-E<gt>isa(CLASS)> +to be caught and handled by evaluating C<BLOCK>. + +C<BLOCK> will be passed two arguments. The first will be the error +being thrown. The second is a reference to a scalar variable. If this +variable is set by the catch block then, on return from the catch +block, try will continue processing as if the catch block was never +found. + +To propagate the error the catch block may call C<$err-E<gt>throw> + +If the scalar reference by the second argument is not set, and the +error is not thrown. Then the current try block will return with the +result from the catch block. + +=item except BLOCK + +When C<try> is looking for a handler, if an except clause is found +C<BLOCK> is evaluated. The return value from this block should be a +HASHREF or a list of key-value pairs, where the keys are class names +and the values are CODE references for the handler of errors of that +type. + +=item otherwise BLOCK + +Catch any error by executing the code in C<BLOCK> + +When evaluated C<BLOCK> will be passed one argument, which will be the +error being processed. + +Only one otherwise block may be specified per try block + +=item finally BLOCK + +Execute the code in C<BLOCK> either after the code in the try block has +successfully completed, or if the try block throws an error then +C<BLOCK> will be executed after the handler has completed. + +If the handler throws an error then the error will be caught, the +finally block will be executed and the error will be re-thrown. + +Only one finally block may be specified per try block + +=back + +=head1 CLASS INTERFACE + +=head2 CONSTRUCTORS + +The C<Error> object is implemented as a HASH. This HASH is initialized +with the arguments that are passed to it's constructor. The elements +that are used by, or are retrievable by the C<Error> class are listed +below, other classes may add to these. + + -file + -line + -text + -value + -object + +If C<-file> or C<-line> are not specified in the constructor arguments +then these will be initialized with the file name and line number where +the constructor was called from. + +If the error is associated with an object then the object should be +passed as the C<-object> argument. This will allow the C<Error> package +to associate the error with the object. + +The C<Error> package remembers the last error created, and also the +last error associated with a package. This could either be the last +error created by a sub in that package, or the last error which passed +an object blessed into that package as the C<-object> argument. + +=over 4 + +=item throw ( [ ARGS ] ) + +Create a new C<Error> object and throw an error, which will be caught +by a surrounding C<try> block, if there is one. Otherwise it will cause +the program to exit. + +C<throw> may also be called on an existing error to re-throw it. + +=item with ( [ ARGS ] ) + +Create a new C<Error> object and returns it. This is defined for +syntactic sugar, eg + + die with Some::Error ( ... ); + +=item record ( [ ARGS ] ) + +Create a new C<Error> object and returns it. This is defined for +syntactic sugar, eg + + record Some::Error ( ... ) + and return; + +=back + +=head2 STATIC METHODS + +=over 4 + +=item prior ( [ PACKAGE ] ) + +Return the last error created, or the last error associated with +C<PACKAGE> + +=item flush ( [ PACKAGE ] ) + +Flush the last error created, or the last error associated with +C<PACKAGE>.It is necessary to clear the error stack before exiting the +package or uncaught errors generated using C<record> will be reported. + + $Error->flush; + +=cut + +=back + +=head2 OBJECT METHODS + +=over 4 + +=item stacktrace + +If the variable C<$Error::Debug> was non-zero when the error was +created, then C<stacktrace> returns a string created by calling +C<Carp::longmess>. If the variable was zero the C<stacktrace> returns +the text of the error appended with the filename and line number of +where the error was created, providing the text does not end with a +newline. + +=item object + +The object this error was associated with + +=item file + +The file where the constructor of this error was called from + +=item line + +The line where the constructor of this error was called from + +=item text + +The text of the error + +=back + +=head2 OVERLOAD METHODS + +=over 4 + +=item stringify + +A method that converts the object into a string. This method may simply +return the same as the C<text> method, or it may append more +information. For example the file name and line number. + +By default this method returns the C<-text> argument that was passed to +the constructor, or the string C<"Died"> if none was given. + +=item value + +A method that will return a value that can be associated with the +error. For example if an error was created due to the failure of a +system call, then this may return the numeric value of C<$!> at the +time. + +By default this method returns the C<-value> argument that was passed +to the constructor. + +=back + +=head1 PRE-DEFINED ERROR CLASSES + +=over 4 + +=item Error::Simple + +This class can be used to hold simple error strings and values. It's +constructor takes two arguments. The first is a text value, the second +is a numeric value. These values are what will be returned by the +overload methods. + +If the text value ends with C<at file line 1> as $@ strings do, then +this infomation will be used to set the C<-file> and C<-line> arguments +of the error object. + +This class is used internally if an eval'd block die's with an error +that is a plain string. (Unless C<$Error::ObjectifyCallback> is modified) + +=back + +=head1 $Error::ObjectifyCallback + +This variable holds a reference to a subroutine that converts errors that +are plain strings to objects. It is used by Error.pm to convert textual +errors to objects, and can be overrided by the user. + +It accepts a single argument which is a hash reference to named parameters. +Currently the only named parameter passed is C<'text'> which is the text +of the error, but others may be available in the future. + +For example the following code will cause Error.pm to throw objects of the +class MyError::Bar by default: + + sub throw_MyError_Bar + { + my $args = shift; + my $err = MyError::Bar->new(); + $err->{'MyBarText'} = $args->{'text'}; + return $err; + } + + { + local $Error::ObjectifyCallback = \&throw_MyError_Bar; + + # Error handling here. + } + +=head1 KNOWN BUGS + +None, but that does not mean there are not any. + +=head1 AUTHORS + +Graham Barr <gbarr@pobox.com> + +The code that inspired me to write this was originally written by +Peter Seibel <peter@weblogic.com> and adapted by Jesse Glick +<jglick@sig.bsh.com>. + +=head1 MAINTAINER + +Shlomi Fish <shlomif@iglu.org.il> + +=head1 PAST MAINTAINERS + +Arun Kumar U <u_arunkumar@yahoo.com> + +=cut diff --git a/pkt-line.c b/pkt-line.c index c1e81f976f..b4cb7e2756 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -72,7 +72,7 @@ static void safe_read(int fd, void *buffer, unsigned size) if (ret < 0) die("read error (%s)", strerror(errno)); if (!ret) - die("unexpected EOF"); + die("The remote end hung up unexpectedly"); n += ret; } } @@ -74,6 +74,67 @@ char *sq_quote(const char *src) return buf; } +char *sq_quote_argv(const char** argv, int count) +{ + char *buf, *to; + int i; + size_t len = 0; + + /* Count argv if needed. */ + if (count < 0) { + for (count = 0; argv[count]; count++) + ; /* just counting */ + } + + /* Special case: no argv. */ + if (!count) + return xcalloc(1,1); + + /* Get destination buffer length. */ + for (i = 0; i < count; i++) + len += sq_quote_buf(NULL, 0, argv[i]) + 1; + + /* Alloc destination buffer. */ + to = buf = xmalloc(len + 1); + + /* Copy into destination buffer. */ + for (i = 0; i < count; ++i) { + *to++ = ' '; + to += sq_quote_buf(to, len, argv[i]); + } + + return buf; +} + +/* + * Append a string to a string buffer, with or without shell quoting. + * Return true if the buffer overflowed. + */ +int add_to_string(char **ptrp, int *sizep, const char *str, int quote) +{ + char *p = *ptrp; + int size = *sizep; + int oc; + int err = 0; + + if (quote) + oc = sq_quote_buf(p, size, str); + else { + oc = strlen(str); + memcpy(p, str, (size <= oc) ? size - 1 : oc); + } + + if (size <= oc) { + err = 1; + oc = size - 1; + } + + *ptrp += oc; + **ptrp = '\0'; + *sizep -= oc; + return err; +} + char *sq_dequote(char *arg) { char *dst = arg; @@ -148,7 +209,7 @@ static int quote_c_style_counted(const char *name, int namelen, if (!ch) break; if ((ch < ' ') || (ch == '"') || (ch == '\\') || - (ch == 0177)) { + (ch >= 0177)) { needquote = 1; switch (ch) { case '\a': EMITQ(); ch = 'a'; break; @@ -288,3 +349,41 @@ void write_name_quoted(const char *prefix, int prefix_len, else goto no_quote; } + +/* quoting as a string literal for other languages */ + +void perl_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} + +void python_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + const char nl = '\n'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == nl) { + fputc(bq, stream); + fputc('n', stream); + continue; + } + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} @@ -31,6 +31,13 @@ extern char *sq_quote(const char *src); extern void sq_quote_print(FILE *stream, const char *src); extern size_t sq_quote_buf(char *dst, size_t n, const char *src); +extern char *sq_quote_argv(const char** argv, int count); + +/* + * Append a string to a string buffer, with or without shell quoting. + * Return true if the buffer overflowed. + */ +extern int add_to_string(char **ptrp, int *sizep, const char *str, int quote); /* This unwraps what sq_quote() produces in place, but returns * NULL if the input does not look like what sq_quote would have @@ -45,4 +52,8 @@ extern char *unquote_c_style(const char *quoted, const char **endp); extern void write_name_quoted(const char *prefix, int prefix_len, const char *name, int quote, FILE *out); +/* quoting as a string literal for other languages */ +extern void perl_quote_print(FILE *stream, const char *src); +extern void python_quote_print(FILE *stream, const char *src); + #endif diff --git a/reachable.c b/reachable.c new file mode 100644 index 0000000000..a6a334822a --- /dev/null +++ b/reachable.c @@ -0,0 +1,201 @@ +#include "cache.h" +#include "refs.h" +#include "tag.h" +#include "commit.h" +#include "blob.h" +#include "diff.h" +#include "revision.h" +#include "reachable.h" +#include "cache-tree.h" + +static void process_blob(struct blob *blob, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &blob->object; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + /* Nothing to do, really .. The blob lookup was the important part */ +} + +static void process_tree(struct tree *tree, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &tree->object; + struct tree_desc desc; + struct name_entry entry; + struct name_path me; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + if (parse_tree(tree) < 0) + die("bad tree object %s", sha1_to_hex(obj->sha1)); + name = xstrdup(name); + add_object(obj, p, path, name); + me.up = path; + me.elem = name; + me.elem_len = strlen(name); + + desc.buf = tree->buffer; + desc.size = tree->size; + + while (tree_entry(&desc, &entry)) { + if (S_ISDIR(entry.mode)) + process_tree(lookup_tree(entry.sha1), p, &me, entry.path); + else + process_blob(lookup_blob(entry.sha1), p, &me, entry.path); + } + free(tree->buffer); + tree->buffer = NULL; +} + +static void process_tag(struct tag *tag, struct object_array *p, const char *name) +{ + struct object *obj = &tag->object; + struct name_path me; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + + me.up = NULL; + me.elem = "tag:/"; + me.elem_len = 5; + + if (parse_tag(tag) < 0) + die("bad tag object %s", sha1_to_hex(obj->sha1)); + add_object(tag->tagged, p, NULL, name); +} + +static void walk_commit_list(struct rev_info *revs) +{ + int i; + struct commit *commit; + struct object_array objects = { 0, 0, NULL }; + + /* Walk all commits, process their trees */ + while ((commit = get_revision(revs)) != NULL) + process_tree(commit->tree, &objects, NULL, ""); + + /* Then walk all the pending objects, recursively processing them too */ + for (i = 0; i < revs->pending.nr; i++) { + struct object_array_entry *pending = revs->pending.objects + i; + struct object *obj = pending->item; + const char *name = pending->name; + if (obj->type == OBJ_TAG) { + process_tag((struct tag *) obj, &objects, name); + continue; + } + if (obj->type == OBJ_TREE) { + process_tree((struct tree *)obj, &objects, NULL, name); + continue; + } + if (obj->type == OBJ_BLOB) { + process_blob((struct blob *)obj, &objects, NULL, name); + continue; + } + die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); + } +} + +static int add_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, + const char *email, unsigned long timestamp, int tz, + const char *message, void *cb_data) +{ + struct object *object; + struct rev_info *revs = (struct rev_info *)cb_data; + + object = parse_object(osha1); + if (object) + add_pending_object(revs, object, ""); + object = parse_object(nsha1); + if (object) + add_pending_object(revs, object, ""); + return 0; +} + +static int add_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) +{ + struct object *object = parse_object(sha1); + struct rev_info *revs = (struct rev_info *)cb_data; + + if (!object) + die("bad object ref: %s:%s", path, sha1_to_hex(sha1)); + add_pending_object(revs, object, ""); + + return 0; +} + +static int add_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data) +{ + for_each_reflog_ent(path, add_one_reflog_ent, cb_data); + return 0; +} + +static void add_one_tree(const unsigned char *sha1, struct rev_info *revs) +{ + struct tree *tree = lookup_tree(sha1); + add_pending_object(revs, &tree->object, ""); +} + +static void add_cache_tree(struct cache_tree *it, struct rev_info *revs) +{ + int i; + + if (it->entry_count >= 0) + add_one_tree(it->sha1, revs); + for (i = 0; i < it->subtree_nr; i++) + add_cache_tree(it->down[i]->cache_tree, revs); +} + +static void add_cache_refs(struct rev_info *revs) +{ + int i; + + read_cache(); + for (i = 0; i < active_nr; i++) { + lookup_blob(active_cache[i]->sha1); + /* + * We could add the blobs to the pending list, but quite + * frankly, we don't care. Once we've looked them up, and + * added them as objects, we've really done everything + * there is to do for a blob + */ + } + if (active_cache_tree) + add_cache_tree(active_cache_tree, revs); +} + +void mark_reachable_objects(struct rev_info *revs, int mark_reflog) +{ + /* + * Set up revision parsing, and mark us as being interested + * in all object types, not just commits. + */ + revs->tag_objects = 1; + revs->blob_objects = 1; + revs->tree_objects = 1; + + /* Add all refs from the index file */ + add_cache_refs(revs); + + /* Add all external refs */ + for_each_ref(add_one_ref, revs); + + /* Add all reflog info from refs */ + if (mark_reflog) + for_each_ref(add_one_reflog, revs); + + /* + * Set up the revision walk - this will move all commits + * from the pending list to the commit walking list. + */ + prepare_revision_walk(revs); + walk_commit_list(revs); +} diff --git a/reachable.h b/reachable.h new file mode 100644 index 0000000000..40751810b6 --- /dev/null +++ b/reachable.h @@ -0,0 +1,6 @@ +#ifndef REACHEABLE_H +#define REACHEABLE_H + +extern void mark_reachable_objects(struct rev_info *revs, int mark_reflog); + +#endif diff --git a/read-cache.c b/read-cache.c index b6982eac41..c54a611877 100644 --- a/read-cache.c +++ b/read-cache.c @@ -347,16 +347,18 @@ int add_file_to_index(const char *path, int verbose) ce->ce_mode = create_ce_mode(st.st_mode); if (!trust_executable_bit) { /* If there is an existing entry, pick the mode bits - * from it. + * from it, otherwise assume unexecutable. */ int pos = cache_name_pos(path, namelen); if (pos >= 0) ce->ce_mode = active_cache[pos]->ce_mode; + else if (S_ISREG(st.st_mode)) + ce->ce_mode = create_ce_mode(S_IFREG | 0666); } if (index_path(ce->sha1, path, &st, 1)) die("unable to index file %s", path); - if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD)) + if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE)) die("unable to add %s to index",path); if (verbose) printf("add '%s'\n", path); @@ -515,7 +517,7 @@ static int has_dir_name(const struct cache_entry *ce, int pos, int ok_to_replace pos = cache_name_pos(name, ntohs(create_ce_flags(len, stage))); if (pos >= 0) { retval = -1; - if (ok_to_replace) + if (!ok_to_replace) break; remove_cache_entry_at(pos); continue; @@ -607,7 +609,7 @@ int add_cache_entry(struct cache_entry *ce, int option) if (!skip_df_check && check_file_directory_conflict(ce, pos, ok_to_replace)) { if (!ok_to_replace) - return -1; + return error("'%s' appears as both a file and as a directory", ce->name); pos = cache_name_pos(ce->name, ntohs(ce->ce_flags)); pos = -pos-1; } @@ -791,16 +793,16 @@ int read_cache_from(const char *path) die("index file open failed (%s)", strerror(errno)); } - cache_mmap = MAP_FAILED; if (!fstat(fd, &st)) { cache_mmap_size = st.st_size; errno = EINVAL; if (cache_mmap_size >= sizeof(struct cache_header) + 20) - cache_mmap = mmap(NULL, cache_mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); - } + cache_mmap = xmmap(NULL, cache_mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + else + die("index file smaller than expected"); + } else + die("cannot stat the open index (%s)", strerror(errno)); close(fd); - if (cache_mmap == MAP_FAILED) - die("index file mmap failed (%s)", strerror(errno)); hdr = cache_mmap; if (verify_hdr(hdr, cache_mmap_size) < 0) @@ -842,6 +844,23 @@ unmap: die("index file corrupt"); } +int discard_cache(void) +{ + int ret; + + active_nr = active_cache_changed = 0; + index_file_timestamp = 0; + cache_tree_free(&active_cache_tree); + if (cache_mmap == NULL) + return 0; + ret = munmap(cache_mmap, cache_mmap_size); + cache_mmap = NULL; + cache_mmap_size = 0; + + /* no need to throw away allocated active_cache */ + return ret; +} + #define WRITE_BUFFER_SIZE 8192 static unsigned char write_buffer[WRITE_BUFFER_SIZE]; static unsigned long write_buffer_len; @@ -851,7 +870,7 @@ static int ce_write_flush(SHA_CTX *context, int fd) unsigned int buffered = write_buffer_len; if (buffered) { SHA1_Update(context, write_buffer, buffered); - if (write(fd, write_buffer, buffered) != buffered) + if (write_in_full(fd, write_buffer, buffered) != buffered) return -1; write_buffer_len = 0; } @@ -900,7 +919,7 @@ static int ce_flush(SHA_CTX *context, int fd) /* Flush first if not enough space for SHA1 signature */ if (left + 20 > WRITE_BUFFER_SIZE) { - if (write(fd, write_buffer, left) != left) + if (write_in_full(fd, write_buffer, left) != left) return -1; left = 0; } @@ -908,7 +927,7 @@ static int ce_flush(SHA_CTX *context, int fd) /* Append the SHA1 signature at the end */ SHA1_Final(write_buffer + left, context); left += 20; - return (write(fd, write_buffer, left) != left) ? -1 : 0; + return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0; } static void ce_smudge_racily_clean_entry(struct cache_entry *ce) @@ -991,7 +1010,7 @@ int write_cache(int newfd, struct cache_entry **cache, int entries) if (data && !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) && !ce_write(&c, newfd, data, sz)) - ; + free(data); else { free(data); return -1; diff --git a/receive-pack.c b/receive-pack.c index 201531626c..c176d8fd00 100644 --- a/receive-pack.c +++ b/receive-pack.c @@ -1,19 +1,41 @@ #include "cache.h" +#include "pack.h" #include "refs.h" #include "pkt-line.h" #include "run-command.h" -#include <sys/wait.h> +#include "exec_cmd.h" +#include "commit.h" +#include "object.h" static const char receive_pack_usage[] = "git-receive-pack <git-dir>"; -static const char *unpacker[] = { "unpack-objects", NULL }; - +static int deny_non_fast_forwards = 0; +static int unpack_limit = 100; static int report_status; -static char capabilities[] = "report-status"; +static char capabilities[] = " report-status delete-refs "; static int capabilities_sent; -static int show_ref(const char *path, const unsigned char *sha1) +static int receive_pack_config(const char *var, const char *value) +{ + git_default_config(var, value); + + if (strcmp(var, "receive.denynonfastforwards") == 0) + { + deny_non_fast_forwards = git_config_bool(var, value); + return 0; + } + + if (strcmp(var, "receive.unpacklimit") == 0) + { + unpack_limit = git_config_int(var, value); + return 0; + } + + return 0; +} + +static int show_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) { if (capabilities_sent) packet_write(1, "%s %s\n", sha1_to_hex(sha1), path); @@ -26,9 +48,9 @@ static int show_ref(const char *path, const unsigned char *sha1) static void write_head_info(void) { - for_each_ref(show_ref); + for_each_ref(show_ref, NULL); if (!capabilities_sent) - show_ref("capabilities^{}", null_sha1); + show_ref("capabilities^{}", null_sha1, 0, NULL); } @@ -42,34 +64,6 @@ struct command { static struct command *commands; -static int is_all_zeroes(const char *hex) -{ - int i; - for (i = 0; i < 40; i++) - if (*hex++ != '0') - return 0; - return 1; -} - -static int verify_old_ref(const char *name, char *hex_contents) -{ - int fd, ret; - char buffer[60]; - - if (is_all_zeroes(hex_contents)) - return 0; - fd = open(name, O_RDONLY); - if (fd < 0) - return -1; - ret = read(fd, buffer, 40); - close(fd); - if (ret != 40) - return -1; - if (memcmp(buffer, hex_contents, 40)) - return -1; - return 0; -} - static char update_hook[] = "hooks/update"; static int run_update_hook(const char *refname, @@ -79,7 +73,9 @@ static int run_update_hook(const char *refname, if (access(update_hook, X_OK) < 0) return 0; - code = run_command(update_hook, refname, old_hex, new_hex, NULL); + code = run_command_opt(RUN_COMMAND_NO_STDIN + | RUN_COMMAND_STDOUT_TO_STDERR, + update_hook, refname, old_hex, new_hex, NULL); switch (code) { case 0: return 0; @@ -106,8 +102,8 @@ static int update(struct command *cmd) const char *name = cmd->ref_name; unsigned char *old_sha1 = cmd->old_sha1; unsigned char *new_sha1 = cmd->new_sha1; - char new_hex[60], *old_hex, *lock_name; - int newfd, namelen, written; + char new_hex[41], old_hex[41]; + struct ref_lock *lock; cmd->error_string = NULL; if (!strncmp(name, "refs/", 5) && check_ref_format(name + 5)) { @@ -116,59 +112,53 @@ static int update(struct command *cmd) name); } - namelen = strlen(name); - lock_name = xmalloc(namelen + 10); - memcpy(lock_name, name, namelen); - memcpy(lock_name + namelen, ".lock", 6); - strcpy(new_hex, sha1_to_hex(new_sha1)); - old_hex = sha1_to_hex(old_sha1); - if (!has_sha1_file(new_sha1)) { + strcpy(old_hex, sha1_to_hex(old_sha1)); + + if (!is_null_sha1(new_sha1) && !has_sha1_file(new_sha1)) { cmd->error_string = "bad pack"; return error("unpack should have generated %s, " "but I can't find it!", new_hex); } - safe_create_leading_directories(lock_name); - - newfd = open(lock_name, O_CREAT | O_EXCL | O_WRONLY, 0666); - if (newfd < 0) { - cmd->error_string = "can't lock"; - return error("unable to create %s (%s)", - lock_name, strerror(errno)); - } - - /* Write the ref with an ending '\n' */ - new_hex[40] = '\n'; - new_hex[41] = 0; - written = write(newfd, new_hex, 41); - /* Remove the '\n' again */ - new_hex[40] = 0; - - close(newfd); - if (written != 41) { - unlink(lock_name); - cmd->error_string = "can't write"; - return error("unable to write %s", lock_name); - } - if (verify_old_ref(name, old_hex) < 0) { - unlink(lock_name); - cmd->error_string = "raced"; - return error("%s changed during push", name); + if (deny_non_fast_forwards && !is_null_sha1(new_sha1) && + !is_null_sha1(old_sha1) && + !strncmp(name, "refs/heads/", 11)) { + struct commit *old_commit, *new_commit; + struct commit_list *bases, *ent; + + old_commit = (struct commit *)parse_object(old_sha1); + new_commit = (struct commit *)parse_object(new_sha1); + bases = get_merge_bases(old_commit, new_commit, 1); + for (ent = bases; ent; ent = ent->next) + if (!hashcmp(old_sha1, ent->item->object.sha1)) + break; + free_commit_list(bases); + if (!ent) + return error("denying non-fast forward;" + " you should pull first"); } if (run_update_hook(name, old_hex, new_hex)) { - unlink(lock_name); cmd->error_string = "hook declined"; return error("hook declined to update %s", name); } - else if (rename(lock_name, name) < 0) { - unlink(lock_name); - cmd->error_string = "can't rename"; - return error("unable to replace %s", name); + + if (is_null_sha1(new_sha1)) { + if (delete_ref(name, old_sha1)) { + cmd->error_string = "failed to delete"; + return error("failed to delete %s", name); + } + fprintf(stderr, "%s: %s -> deleted\n", name, old_hex); } else { + lock = lock_any_ref_for_update(name, old_sha1); + if (!lock) { + cmd->error_string = "failed to lock"; + return error("failed to lock %s", name); + } + write_ref_sha1(lock, new_sha1, "push"); fprintf(stderr, "%s: %s -> %s\n", name, old_hex, new_hex); - return 0; } + return 0; } static char update_post_hook[] = "hooks/post-update"; @@ -199,7 +189,8 @@ static void run_update_post_hook(struct command *cmd) argc++; } argv[argc] = NULL; - run_command_v_opt(argc, argv, RUN_COMMAND_NO_STDIO); + run_command_v_opt(argv, RUN_COMMAND_NO_STDIN + | RUN_COMMAND_STDOUT_TO_STDERR); } /* @@ -257,29 +248,127 @@ static void read_head_info(void) } } -static const char *unpack(int *error_code) +static const char *parse_pack_header(struct pack_header *hdr) { - int code = run_command_v_opt(1, unpacker, RUN_GIT_CMD); + char *c = (char*)hdr; + ssize_t remaining = sizeof(struct pack_header); + do { + ssize_t r = xread(0, c, remaining); + if (r <= 0) + return "eof before pack header was fully read"; + remaining -= r; + c += r; + } while (remaining > 0); + if (hdr->hdr_signature != htonl(PACK_SIGNATURE)) + return "protocol error (pack signature mismatch detected)"; + if (!pack_version_ok(hdr->hdr_version)) + return "protocol error (pack version unsupported)"; + return NULL; +} - *error_code = 0; - switch (code) { - case 0: - return NULL; - case -ERR_RUN_COMMAND_FORK: - return "unpack fork failed"; - case -ERR_RUN_COMMAND_EXEC: - return "unpack execute failed"; - case -ERR_RUN_COMMAND_WAITPID: - return "waitpid failed"; - case -ERR_RUN_COMMAND_WAITPID_WRONG_PID: - return "waitpid is confused"; - case -ERR_RUN_COMMAND_WAITPID_SIGNAL: - return "unpacker died of signal"; - case -ERR_RUN_COMMAND_WAITPID_NOEXIT: - return "unpacker died strangely"; - default: - *error_code = -code; - return "unpacker exited with error code"; +static const char *pack_lockfile; + +static const char *unpack(void) +{ + struct pack_header hdr; + const char *hdr_err; + char hdr_arg[38]; + + hdr_err = parse_pack_header(&hdr); + if (hdr_err) + return hdr_err; + snprintf(hdr_arg, sizeof(hdr_arg), "--pack_header=%u,%u", + ntohl(hdr.hdr_version), ntohl(hdr.hdr_entries)); + + if (ntohl(hdr.hdr_entries) < unpack_limit) { + int code; + const char *unpacker[3]; + unpacker[0] = "unpack-objects"; + unpacker[1] = hdr_arg; + unpacker[2] = NULL; + code = run_command_v_opt(unpacker, RUN_GIT_CMD); + switch (code) { + case 0: + return NULL; + case -ERR_RUN_COMMAND_FORK: + return "unpack fork failed"; + case -ERR_RUN_COMMAND_EXEC: + return "unpack execute failed"; + case -ERR_RUN_COMMAND_WAITPID: + return "waitpid failed"; + case -ERR_RUN_COMMAND_WAITPID_WRONG_PID: + return "waitpid is confused"; + case -ERR_RUN_COMMAND_WAITPID_SIGNAL: + return "unpacker died of signal"; + case -ERR_RUN_COMMAND_WAITPID_NOEXIT: + return "unpacker died strangely"; + default: + return "unpacker exited with error code"; + } + } else { + const char *keeper[6]; + int fd[2], s, len, status; + pid_t pid; + char keep_arg[256]; + char packname[46]; + + s = sprintf(keep_arg, "--keep=receive-pack %i on ", getpid()); + if (gethostname(keep_arg + s, sizeof(keep_arg) - s)) + strcpy(keep_arg + s, "localhost"); + + keeper[0] = "index-pack"; + keeper[1] = "--stdin"; + keeper[2] = "--fix-thin"; + keeper[3] = hdr_arg; + keeper[4] = keep_arg; + keeper[5] = NULL; + + if (pipe(fd) < 0) + return "index-pack pipe failed"; + pid = fork(); + if (pid < 0) + return "index-pack fork failed"; + if (!pid) { + dup2(fd[1], 1); + close(fd[1]); + close(fd[0]); + execv_git_cmd(keeper); + die("execv of index-pack failed"); + } + close(fd[1]); + + /* + * The first thing we expects from index-pack's output + * is "pack\t%40s\n" or "keep\t%40s\n" (46 bytes) where + * %40s is the newly created pack SHA1 name. In the "keep" + * case, we need it to remove the corresponding .keep file + * later on. If we don't get that then tough luck with it. + */ + for (len = 0; + len < 46 && (s = xread(fd[0], packname+len, 46-len)) > 0; + len += s); + close(fd[0]); + if (len == 46 && packname[45] == '\n' && + memcmp(packname, "keep\t", 5) == 0) { + char path[PATH_MAX]; + packname[45] = 0; + snprintf(path, sizeof(path), "%s/pack/pack-%s.keep", + get_object_directory(), packname + 5); + pack_lockfile = xstrdup(path); + } + + /* Then wrap our index-pack process. */ + while (waitpid(pid, &status, 0) < 0) + if (errno != EINTR) + return "waitpid failed"; + if (WIFEXITED(status)) { + int code = WEXITSTATUS(status); + if (code) + return "index-pack exited with error code"; + reprepare_packed_git(); + return NULL; + } + return "index-pack abnormal exit"; } } @@ -299,6 +388,16 @@ static void report(const char *unpack_status) packet_flush(1); } +static int delete_only(struct command *cmd) +{ + while (cmd) { + if (!is_null_sha1(cmd->new_sha1)) + return 0; + cmd = cmd->next; + } + return 1; +} + int main(int argc, char **argv) { int i; @@ -319,9 +418,14 @@ int main(int argc, char **argv) if (!dir) usage(receive_pack_usage); - if(!enter_repo(dir, 0)) + if (!enter_repo(dir, 0)) die("'%s': unable to chdir or not a git archive", dir); + setup_ident(); + /* don't die if gecos is empty */ + ignore_missing_committer_name(); + git_config(receive_pack_config); + write_head_info(); /* EOF */ @@ -329,10 +433,14 @@ int main(int argc, char **argv) read_head_info(); if (commands) { - int code; - const char *unpack_status = unpack(&code); + const char *unpack_status = NULL; + + if (!delete_only(commands)) + unpack_status = unpack(); if (!unpack_status) execute_commands(); + if (pack_lockfile) + unlink(pack_lockfile); if (report_status) report(unpack_status); } @@ -1,17 +1,232 @@ -#include "refs.h" #include "cache.h" +#include "refs.h" +#include "object.h" +#include "tag.h" + +/* ISSYMREF=01 and ISPACKED=02 are public interfaces */ +#define REF_KNOWS_PEELED 04 + +struct ref_list { + struct ref_list *next; + unsigned char flag; /* ISSYMREF? ISPACKED? */ + unsigned char sha1[20]; + unsigned char peeled[20]; + char name[FLEX_ARRAY]; +}; + +static const char *parse_ref_line(char *line, unsigned char *sha1) +{ + /* + * 42: the answer to everything. + * + * In this case, it happens to be the answer to + * 40 (length of sha1 hex representation) + * +1 (space in between hex and name) + * +1 (newline at the end of the line) + */ + int len = strlen(line) - 42; + + if (len <= 0) + return NULL; + if (get_sha1_hex(line, sha1) < 0) + return NULL; + if (!isspace(line[40])) + return NULL; + line += 41; + if (isspace(*line)) + return NULL; + if (line[len] != '\n') + return NULL; + line[len] = 0; + + return line; +} + +static struct ref_list *add_ref(const char *name, const unsigned char *sha1, + int flag, struct ref_list *list, + struct ref_list **new_entry) +{ + int len; + struct ref_list **p = &list, *entry; + + /* Find the place to insert the ref into.. */ + while ((entry = *p) != NULL) { + int cmp = strcmp(entry->name, name); + if (cmp > 0) + break; + + /* Same as existing entry? */ + if (!cmp) { + if (new_entry) + *new_entry = entry; + return list; + } + p = &entry->next; + } + + /* Allocate it and add it in.. */ + len = strlen(name) + 1; + entry = xmalloc(sizeof(struct ref_list) + len); + hashcpy(entry->sha1, sha1); + hashclr(entry->peeled); + memcpy(entry->name, name, len); + entry->flag = flag; + entry->next = *p; + *p = entry; + if (new_entry) + *new_entry = entry; + return list; +} + +/* + * Future: need to be in "struct repository" + * when doing a full libification. + */ +struct cached_refs { + char did_loose; + char did_packed; + struct ref_list *loose; + struct ref_list *packed; +} cached_refs; + +static void free_ref_list(struct ref_list *list) +{ + struct ref_list *next; + for ( ; list; list = next) { + next = list->next; + free(list); + } +} + +static void invalidate_cached_refs(void) +{ + struct cached_refs *ca = &cached_refs; + + if (ca->did_loose && ca->loose) + free_ref_list(ca->loose); + if (ca->did_packed && ca->packed) + free_ref_list(ca->packed); + ca->loose = ca->packed = NULL; + ca->did_loose = ca->did_packed = 0; +} + +static void read_packed_refs(FILE *f, struct cached_refs *cached_refs) +{ + struct ref_list *list = NULL; + struct ref_list *last = NULL; + char refline[PATH_MAX]; + int flag = REF_ISPACKED; + + while (fgets(refline, sizeof(refline), f)) { + unsigned char sha1[20]; + const char *name; + static const char header[] = "# pack-refs with:"; + + if (!strncmp(refline, header, sizeof(header)-1)) { + const char *traits = refline + sizeof(header) - 1; + if (strstr(traits, " peeled ")) + flag |= REF_KNOWS_PEELED; + /* perhaps other traits later as well */ + continue; + } + + name = parse_ref_line(refline, sha1); + if (name) { + list = add_ref(name, sha1, flag, list, &last); + continue; + } + if (last && + refline[0] == '^' && + strlen(refline) == 42 && + refline[41] == '\n' && + !get_sha1_hex(refline + 1, sha1)) + hashcpy(last->peeled, sha1); + } + cached_refs->packed = list; +} + +static struct ref_list *get_packed_refs(void) +{ + if (!cached_refs.did_packed) { + FILE *f = fopen(git_path("packed-refs"), "r"); + cached_refs.packed = NULL; + if (f) { + read_packed_refs(f, &cached_refs); + fclose(f); + } + cached_refs.did_packed = 1; + } + return cached_refs.packed; +} + +static struct ref_list *get_ref_dir(const char *base, struct ref_list *list) +{ + DIR *dir = opendir(git_path("%s", base)); + + if (dir) { + struct dirent *de; + int baselen = strlen(base); + char *ref = xmalloc(baselen + 257); + + memcpy(ref, base, baselen); + if (baselen && base[baselen-1] != '/') + ref[baselen++] = '/'; + + while ((de = readdir(dir)) != NULL) { + unsigned char sha1[20]; + struct stat st; + int flag; + int namelen; + + if (de->d_name[0] == '.') + continue; + namelen = strlen(de->d_name); + if (namelen > 255) + continue; + if (has_extension(de->d_name, ".lock")) + continue; + memcpy(ref + baselen, de->d_name, namelen+1); + if (stat(git_path("%s", ref), &st) < 0) + continue; + if (S_ISDIR(st.st_mode)) { + list = get_ref_dir(ref, list); + continue; + } + if (!resolve_ref(ref, sha1, 1, &flag)) { + error("%s points nowhere!", ref); + continue; + } + list = add_ref(ref, sha1, flag, list, NULL); + } + free(ref); + closedir(dir); + } + return list; +} -#include <errno.h> +static struct ref_list *get_loose_refs(void) +{ + if (!cached_refs.did_loose) { + cached_refs.loose = get_ref_dir("refs", NULL); + cached_refs.did_loose = 1; + } + return cached_refs.loose; +} /* We allow "recursive" symbolic refs. Only within reason, though */ #define MAXDEPTH 5 -const char *resolve_ref(const char *path, unsigned char *sha1, int reading) +const char *resolve_ref(const char *ref, unsigned char *sha1, int reading, int *flag) { int depth = MAXDEPTH, len; char buffer[256]; + static char ref_buffer[256]; + + if (flag) + *flag = 0; for (;;) { + const char *path = git_path("%s", ref); struct stat st; char *buf; int fd; @@ -27,21 +242,41 @@ const char *resolve_ref(const char *path, unsigned char *sha1, int reading) * reading. */ if (lstat(path, &st) < 0) { + struct ref_list *list = get_packed_refs(); + while (list) { + if (!strcmp(ref, list->name)) { + hashcpy(sha1, list->sha1); + if (flag) + *flag |= REF_ISPACKED; + return ref; + } + list = list->next; + } if (reading || errno != ENOENT) return NULL; hashclr(sha1); - return path; + return ref; } /* Follow "normalized" - ie "refs/.." symlinks by hand */ if (S_ISLNK(st.st_mode)) { len = readlink(path, buffer, sizeof(buffer)-1); if (len >= 5 && !memcmp("refs/", buffer, 5)) { - path = git_path("%.*s", len, buffer); + buffer[len] = 0; + strcpy(ref_buffer, buffer); + ref = ref_buffer; + if (flag) + *flag |= REF_ISSYMREF; continue; } } + /* Is it a directory? */ + if (S_ISDIR(st.st_mode)) { + errno = EISDIR; + return NULL; + } + /* * Anything else, just open it and try to use it as * a ref @@ -49,7 +284,7 @@ const char *resolve_ref(const char *path, unsigned char *sha1, int reading) fd = open(path, O_RDONLY); if (fd < 0) return NULL; - len = read(fd, buffer, sizeof(buffer)-1); + len = read_in_full(fd, buffer, sizeof(buffer)-1); close(fd); /* @@ -62,19 +297,24 @@ const char *resolve_ref(const char *path, unsigned char *sha1, int reading) while (len && isspace(*buf)) buf++, len--; while (len && isspace(buf[len-1])) - buf[--len] = 0; - path = git_path("%.*s", len, buf); + len--; + buf[len] = 0; + memcpy(ref_buffer, buf, len + 1); + ref = ref_buffer; + if (flag) + *flag |= REF_ISSYMREF; } if (len < 40 || get_sha1_hex(buffer, sha1)) return NULL; - return path; + return ref; } -int create_symref(const char *git_HEAD, const char *refs_heads_master) +int create_symref(const char *ref_target, const char *refs_heads_master) { const char *lockpath; char ref[1000]; int fd, len, written; + const char *git_HEAD = git_path("%s", ref_target); #ifndef NO_SYMLINK_HEAD if (prefer_symlink_refs) { @@ -92,7 +332,7 @@ int create_symref(const char *git_HEAD, const char *refs_heads_master) } lockpath = mkpath("%s.lock", git_HEAD); fd = open(lockpath, O_CREAT | O_EXCL | O_WRONLY, 0666); - written = write(fd, ref, len); + written = write_in_full(fd, ref, len); close(fd); if (written != len) { unlink(lockpath); @@ -112,104 +352,138 @@ int create_symref(const char *git_HEAD, const char *refs_heads_master) return 0; } -int read_ref(const char *filename, unsigned char *sha1) +int read_ref(const char *ref, unsigned char *sha1) { - if (resolve_ref(filename, sha1, 1)) + if (resolve_ref(ref, sha1, 1, NULL)) return 0; return -1; } -static int do_for_each_ref(const char *base, int (*fn)(const char *path, const unsigned char *sha1), int trim) +static int do_one_ref(const char *base, each_ref_fn fn, int trim, + void *cb_data, struct ref_list *entry) { - int retval = 0; - DIR *dir = opendir(git_path("%s", base)); + if (strncmp(base, entry->name, trim)) + return 0; + if (is_null_sha1(entry->sha1)) + return 0; + if (!has_sha1_file(entry->sha1)) { + error("%s does not point to a valid object!", entry->name); + return 0; + } + return fn(entry->name + trim, entry->sha1, entry->flag, cb_data); +} - if (dir) { - struct dirent *de; - int baselen = strlen(base); - char *path = xmalloc(baselen + 257); +int peel_ref(const char *ref, unsigned char *sha1) +{ + int flag; + unsigned char base[20]; + struct object *o; - if (!strncmp(base, "./", 2)) { - base += 2; - baselen -= 2; - } - memcpy(path, base, baselen); - if (baselen && base[baselen-1] != '/') - path[baselen++] = '/'; + if (!resolve_ref(ref, base, 1, &flag)) + return -1; - while ((de = readdir(dir)) != NULL) { - unsigned char sha1[20]; - struct stat st; - int namelen; + if ((flag & REF_ISPACKED)) { + struct ref_list *list = get_packed_refs(); - if (de->d_name[0] == '.') - continue; - namelen = strlen(de->d_name); - if (namelen > 255) - continue; - if (has_extension(de->d_name, ".lock")) - continue; - memcpy(path + baselen, de->d_name, namelen+1); - if (stat(git_path("%s", path), &st) < 0) - continue; - if (S_ISDIR(st.st_mode)) { - retval = do_for_each_ref(path, fn, trim); - if (retval) - break; - continue; - } - if (read_ref(git_path("%s", path), sha1) < 0) { - error("%s points nowhere!", path); - continue; - } - if (!has_sha1_file(sha1)) { - error("%s does not point to a valid " - "commit object!", path); - continue; - } - retval = fn(path + trim, sha1); - if (retval) + while (list) { + if (!strcmp(list->name, ref)) { + if (list->flag & REF_KNOWS_PEELED) { + hashcpy(sha1, list->peeled); + return 0; + } + /* older pack-refs did not leave peeled ones */ break; + } + list = list->next; } - free(path); - closedir(dir); } - return retval; + + /* fallback - callers should not call this for unpacked refs */ + o = parse_object(base); + if (o->type == OBJ_TAG) { + o = deref_tag(o, ref, 0); + if (o) { + hashcpy(sha1, o->sha1); + return 0; + } + } + return -1; +} + +static int do_for_each_ref(const char *base, each_ref_fn fn, int trim, + void *cb_data) +{ + int retval; + struct ref_list *packed = get_packed_refs(); + struct ref_list *loose = get_loose_refs(); + + while (packed && loose) { + struct ref_list *entry; + int cmp = strcmp(packed->name, loose->name); + if (!cmp) { + packed = packed->next; + continue; + } + if (cmp > 0) { + entry = loose; + loose = loose->next; + } else { + entry = packed; + packed = packed->next; + } + retval = do_one_ref(base, fn, trim, cb_data, entry); + if (retval) + return retval; + } + + for (packed = packed ? packed : loose; packed; packed = packed->next) { + retval = do_one_ref(base, fn, trim, cb_data, packed); + if (retval) + return retval; + } + return 0; } -int head_ref(int (*fn)(const char *path, const unsigned char *sha1)) +int head_ref(each_ref_fn fn, void *cb_data) { unsigned char sha1[20]; - if (!read_ref(git_path("HEAD"), sha1)) - return fn("HEAD", sha1); + int flag; + + if (resolve_ref("HEAD", sha1, 1, &flag)) + return fn("HEAD", sha1, flag, cb_data); return 0; } -int for_each_ref(int (*fn)(const char *path, const unsigned char *sha1)) +int for_each_ref(each_ref_fn fn, void *cb_data) { - return do_for_each_ref("refs", fn, 0); + return do_for_each_ref("refs/", fn, 0, cb_data); } -int for_each_tag_ref(int (*fn)(const char *path, const unsigned char *sha1)) +int for_each_tag_ref(each_ref_fn fn, void *cb_data) { - return do_for_each_ref("refs/tags", fn, 10); + return do_for_each_ref("refs/tags/", fn, 10, cb_data); } -int for_each_branch_ref(int (*fn)(const char *path, const unsigned char *sha1)) +int for_each_branch_ref(each_ref_fn fn, void *cb_data) { - return do_for_each_ref("refs/heads", fn, 11); + return do_for_each_ref("refs/heads/", fn, 11, cb_data); } -int for_each_remote_ref(int (*fn)(const char *path, const unsigned char *sha1)) +int for_each_remote_ref(each_ref_fn fn, void *cb_data) { - return do_for_each_ref("refs/remotes", fn, 13); + return do_for_each_ref("refs/remotes/", fn, 13, cb_data); } +/* NEEDSWORK: This is only used by ssh-upload and it should go; the + * caller should do resolve_ref or read_ref like everybody else. Or + * maybe everybody else should use get_ref_sha1() instead of doing + * read_ref(). + */ int get_ref_sha1(const char *ref, unsigned char *sha1) { if (check_ref_format(ref)) return -1; - return read_ref(git_path("refs/%s", ref), sha1); + return read_ref(mkpath("refs/%s", ref), sha1); } /* @@ -258,7 +532,7 @@ int check_ref_format(const char *ref) level++; if (!ch) { if (level < 2) - return -1; /* at least of form "heads/blah" */ + return -2; /* at least of form "heads/blah" */ return 0; } } @@ -267,22 +541,13 @@ int check_ref_format(const char *ref) static struct ref_lock *verify_lock(struct ref_lock *lock, const unsigned char *old_sha1, int mustexist) { - char buf[40]; - int nr, fd = open(lock->ref_file, O_RDONLY); - if (fd < 0 && (mustexist || errno != ENOENT)) { - error("Can't verify ref %s", lock->ref_file); - unlock_ref(lock); - return NULL; - } - nr = read(fd, buf, 40); - close(fd); - if (nr != 40 || get_sha1_hex(buf, lock->old_sha1) < 0) { - error("Can't verify ref %s", lock->ref_file); + if (!resolve_ref(lock->ref_name, lock->old_sha1, mustexist, NULL)) { + error("Can't verify ref %s", lock->ref_name); unlock_ref(lock); return NULL; } if (hashcmp(lock->old_sha1, old_sha1)) { - error("Ref %s is at %s but expected %s", lock->ref_file, + error("Ref %s is at %s but expected %s", lock->ref_name, sha1_to_hex(lock->old_sha1), sha1_to_hex(old_sha1)); unlock_ref(lock); return NULL; @@ -290,54 +555,351 @@ static struct ref_lock *verify_lock(struct ref_lock *lock, return lock; } -static struct ref_lock *lock_ref_sha1_basic(const char *path, - int plen, - const unsigned char *old_sha1, int mustexist) +static int remove_empty_dir_recursive(char *path, int len) +{ + DIR *dir = opendir(path); + struct dirent *e; + int ret = 0; + + if (!dir) + return -1; + if (path[len-1] != '/') + path[len++] = '/'; + while ((e = readdir(dir)) != NULL) { + struct stat st; + int namlen; + if ((e->d_name[0] == '.') && + ((e->d_name[1] == 0) || + ((e->d_name[1] == '.') && e->d_name[2] == 0))) + continue; /* "." and ".." */ + + namlen = strlen(e->d_name); + if ((len + namlen < PATH_MAX) && + strcpy(path + len, e->d_name) && + !lstat(path, &st) && + S_ISDIR(st.st_mode) && + !remove_empty_dir_recursive(path, len + namlen)) + continue; /* happy */ + + /* path too long, stat fails, or non-directory still exists */ + ret = -1; + break; + } + closedir(dir); + if (!ret) { + path[len] = 0; + ret = rmdir(path); + } + return ret; +} + +static int remove_empty_directories(char *file) +{ + /* we want to create a file but there is a directory there; + * if that is an empty directory (or a directory that contains + * only empty directories), remove them. + */ + char path[PATH_MAX]; + int len = strlen(file); + + if (len >= PATH_MAX) /* path too long ;-) */ + return -1; + strcpy(path, file); + return remove_empty_dir_recursive(path, len); +} + +static int is_refname_available(const char *ref, const char *oldref, + struct ref_list *list, int quiet) +{ + int namlen = strlen(ref); /* e.g. 'foo/bar' */ + while (list) { + /* list->name could be 'foo' or 'foo/bar/baz' */ + if (!oldref || strcmp(oldref, list->name)) { + int len = strlen(list->name); + int cmplen = (namlen < len) ? namlen : len; + const char *lead = (namlen < len) ? list->name : ref; + if (!strncmp(ref, list->name, cmplen) && + lead[cmplen] == '/') { + if (!quiet) + error("'%s' exists; cannot create '%s'", + list->name, ref); + return 0; + } + } + list = list->next; + } + return 1; +} + +static struct ref_lock *lock_ref_sha1_basic(const char *ref, const unsigned char *old_sha1, int *flag) { - const char *orig_path = path; + char *ref_file; + const char *orig_ref = ref; struct ref_lock *lock; struct stat st; + int last_errno = 0; + int mustexist = (old_sha1 && !is_null_sha1(old_sha1)); lock = xcalloc(1, sizeof(struct ref_lock)); lock->lock_fd = -1; - plen = strlen(path) - plen; - path = resolve_ref(path, lock->old_sha1, mustexist); - if (!path) { - int last_errno = errno; + ref = resolve_ref(ref, lock->old_sha1, mustexist, flag); + if (!ref && errno == EISDIR) { + /* we are trying to lock foo but we used to + * have foo/bar which now does not exist; + * it is normal for the empty directory 'foo' + * to remain. + */ + ref_file = git_path("%s", orig_ref); + if (remove_empty_directories(ref_file)) { + last_errno = errno; + error("there are still refs under '%s'", orig_ref); + goto error_return; + } + ref = resolve_ref(orig_ref, lock->old_sha1, mustexist, flag); + } + if (!ref) { + last_errno = errno; error("unable to resolve reference %s: %s", - orig_path, strerror(errno)); - unlock_ref(lock); - errno = last_errno; - return NULL; + orig_ref, strerror(errno)); + goto error_return; } + /* When the ref did not exist and we are creating it, + * make sure there is no existing ref that is packed + * whose name begins with our refname, nor a ref whose + * name is a proper prefix of our refname. + */ + if (is_null_sha1(lock->old_sha1) && + !is_refname_available(ref, NULL, get_packed_refs(), 0)) + goto error_return; + lock->lk = xcalloc(1, sizeof(struct lock_file)); - lock->ref_file = strdup(path); - lock->log_file = strdup(git_path("logs/%s", lock->ref_file + plen)); - lock->force_write = lstat(lock->ref_file, &st) && errno == ENOENT; + lock->ref_name = xstrdup(ref); + lock->log_file = xstrdup(git_path("logs/%s", ref)); + ref_file = git_path("%s", ref); + lock->force_write = lstat(ref_file, &st) && errno == ENOENT; - if (safe_create_leading_directories(lock->ref_file)) - die("unable to create directory for %s", lock->ref_file); - lock->lock_fd = hold_lock_file_for_update(lock->lk, lock->ref_file, 1); + if (safe_create_leading_directories(ref_file)) { + last_errno = errno; + error("unable to create directory for %s", ref_file); + goto error_return; + } + lock->lock_fd = hold_lock_file_for_update(lock->lk, ref_file, 1); return old_sha1 ? verify_lock(lock, old_sha1, mustexist) : lock; + + error_return: + unlock_ref(lock); + errno = last_errno; + return NULL; } -struct ref_lock *lock_ref_sha1(const char *ref, - const unsigned char *old_sha1, int mustexist) +struct ref_lock *lock_ref_sha1(const char *ref, const unsigned char *old_sha1) { + char refpath[PATH_MAX]; if (check_ref_format(ref)) return NULL; - return lock_ref_sha1_basic(git_path("refs/%s", ref), - 5 + strlen(ref), old_sha1, mustexist); + strcpy(refpath, mkpath("refs/%s", ref)); + return lock_ref_sha1_basic(refpath, old_sha1, NULL); } -struct ref_lock *lock_any_ref_for_update(const char *ref, - const unsigned char *old_sha1, int mustexist) +struct ref_lock *lock_any_ref_for_update(const char *ref, const unsigned char *old_sha1) +{ + return lock_ref_sha1_basic(ref, old_sha1, NULL); +} + +static struct lock_file packlock; + +static int repack_without_ref(const char *refname) { - return lock_ref_sha1_basic(git_path("%s", ref), - strlen(ref), old_sha1, mustexist); + struct ref_list *list, *packed_ref_list; + int fd; + int found = 0; + + packed_ref_list = get_packed_refs(); + for (list = packed_ref_list; list; list = list->next) { + if (!strcmp(refname, list->name)) { + found = 1; + break; + } + } + if (!found) + return 0; + fd = hold_lock_file_for_update(&packlock, git_path("packed-refs"), 0); + if (fd < 0) + return error("cannot delete '%s' from packed refs", refname); + + for (list = packed_ref_list; list; list = list->next) { + char line[PATH_MAX + 100]; + int len; + + if (!strcmp(refname, list->name)) + continue; + len = snprintf(line, sizeof(line), "%s %s\n", + sha1_to_hex(list->sha1), list->name); + /* this should not happen but just being defensive */ + if (len > sizeof(line)) + die("too long a refname '%s'", list->name); + write_or_die(fd, line, len); + } + return commit_lock_file(&packlock); +} + +int delete_ref(const char *refname, unsigned char *sha1) +{ + struct ref_lock *lock; + int err, i, ret = 0, flag = 0; + + lock = lock_ref_sha1_basic(refname, sha1, &flag); + if (!lock) + return 1; + if (!(flag & REF_ISPACKED)) { + /* loose */ + i = strlen(lock->lk->filename) - 5; /* .lock */ + lock->lk->filename[i] = 0; + err = unlink(lock->lk->filename); + if (err) { + ret = 1; + error("unlink(%s) failed: %s", + lock->lk->filename, strerror(errno)); + } + lock->lk->filename[i] = '.'; + } + /* removing the loose one could have resurrected an earlier + * packed one. Also, if it was not loose we need to repack + * without it. + */ + ret |= repack_without_ref(refname); + + err = unlink(lock->log_file); + if (err && errno != ENOENT) + fprintf(stderr, "warning: unlink(%s) failed: %s", + lock->log_file, strerror(errno)); + invalidate_cached_refs(); + unlock_ref(lock); + return ret; +} + +int rename_ref(const char *oldref, const char *newref, const char *logmsg) +{ + static const char renamed_ref[] = "RENAMED-REF"; + unsigned char sha1[20], orig_sha1[20]; + int flag = 0, logmoved = 0; + struct ref_lock *lock; + struct stat loginfo; + int log = !lstat(git_path("logs/%s", oldref), &loginfo); + + if (S_ISLNK(loginfo.st_mode)) + return error("reflog for %s is a symlink", oldref); + + if (!resolve_ref(oldref, orig_sha1, 1, &flag)) + return error("refname %s not found", oldref); + + if (!is_refname_available(newref, oldref, get_packed_refs(), 0)) + return 1; + + if (!is_refname_available(newref, oldref, get_loose_refs(), 0)) + return 1; + + lock = lock_ref_sha1_basic(renamed_ref, NULL, NULL); + if (!lock) + return error("unable to lock %s", renamed_ref); + lock->force_write = 1; + if (write_ref_sha1(lock, orig_sha1, logmsg)) + return error("unable to save current sha1 in %s", renamed_ref); + + if (log && rename(git_path("logs/%s", oldref), git_path("tmp-renamed-log"))) + return error("unable to move logfile logs/%s to tmp-renamed-log: %s", + oldref, strerror(errno)); + + if (delete_ref(oldref, orig_sha1)) { + error("unable to delete old %s", oldref); + goto rollback; + } + + if (resolve_ref(newref, sha1, 1, &flag) && delete_ref(newref, sha1)) { + if (errno==EISDIR) { + if (remove_empty_directories(git_path("%s", newref))) { + error("Directory not empty: %s", newref); + goto rollback; + } + } else { + error("unable to delete existing %s", newref); + goto rollback; + } + } + + if (log && safe_create_leading_directories(git_path("logs/%s", newref))) { + error("unable to create directory for %s", newref); + goto rollback; + } + + retry: + if (log && rename(git_path("tmp-renamed-log"), git_path("logs/%s", newref))) { + if (errno==EISDIR) { + if (remove_empty_directories(git_path("logs/%s", newref))) { + error("Directory not empty: logs/%s", newref); + goto rollback; + } + goto retry; + } else { + error("unable to move logfile tmp-renamed-log to logs/%s: %s", + newref, strerror(errno)); + goto rollback; + } + } + logmoved = log; + + lock = lock_ref_sha1_basic(newref, NULL, NULL); + if (!lock) { + error("unable to lock %s for update", newref); + goto rollback; + } + + lock->force_write = 1; + hashcpy(lock->old_sha1, orig_sha1); + if (write_ref_sha1(lock, orig_sha1, logmsg)) { + error("unable to write current sha1 into %s", newref); + goto rollback; + } + + if (!strncmp(oldref, "refs/heads/", 11) && + !strncmp(newref, "refs/heads/", 11)) { + char oldsection[1024], newsection[1024]; + + snprintf(oldsection, 1024, "branch.%s", oldref + 11); + snprintf(newsection, 1024, "branch.%s", newref + 11); + if (git_config_rename_section(oldsection, newsection) < 0) + return 1; + } + + return 0; + + rollback: + lock = lock_ref_sha1_basic(oldref, NULL, NULL); + if (!lock) { + error("unable to lock %s for rollback", oldref); + goto rollbacklog; + } + + lock->force_write = 1; + flag = log_all_ref_updates; + log_all_ref_updates = 0; + if (write_ref_sha1(lock, orig_sha1, NULL)) + error("unable to write current sha1 into %s", oldref); + log_all_ref_updates = flag; + + rollbacklog: + if (logmoved && rename(git_path("logs/%s", newref), git_path("logs/%s", oldref))) + error("unable to restore logfile %s from %s: %s", + oldref, newref, strerror(errno)); + if (!logmoved && log && + rename(git_path("tmp-renamed-log"), git_path("logs/%s", oldref))) + error("unable to restore logfile %s from tmp-renamed-log: %s", + oldref, strerror(errno)); + + return 1; } void unlock_ref(struct ref_lock *lock) @@ -348,10 +910,8 @@ void unlock_ref(struct ref_lock *lock) if (lock->lk) rollback_lock_file(lock->lk); } - if (lock->ref_file) - free(lock->ref_file); - if (lock->log_file) - free(lock->log_file); + free(lock->ref_name); + free(lock->log_file); free(lock); } @@ -363,7 +923,12 @@ static int log_ref_write(struct ref_lock *lock, char *logrec; const char *committer; - if (log_all_ref_updates) { + if (log_all_ref_updates < 0) + log_all_ref_updates = !is_bare_repository(); + + if (log_all_ref_updates && + (!strncmp(lock->ref_name, "refs/heads/", 11) || + !strncmp(lock->ref_name, "refs/remotes/", 13))) { if (safe_create_leading_directories(lock->log_file) < 0) return error("unable to create directory for %s", lock->log_file); @@ -372,10 +937,20 @@ static int log_ref_write(struct ref_lock *lock, logfd = open(lock->log_file, oflags, 0666); if (logfd < 0) { - if (!log_all_ref_updates && errno == ENOENT) + if (!(oflags & O_CREAT) && errno == ENOENT) return 0; - return error("Unable to append to %s: %s", - lock->log_file, strerror(errno)); + + if ((oflags & O_CREAT) && errno == EISDIR) { + if (remove_empty_directories(lock->log_file)) { + return error("There are still logs under '%s'", + lock->log_file); + } + logfd = open(lock->log_file, oflags, 0666); + } + + if (logfd < 0) + return error("Unable to append to %s: %s", + lock->log_file, strerror(errno)); } committer = git_committer_info(1); @@ -396,7 +971,7 @@ static int log_ref_write(struct ref_lock *lock, sha1_to_hex(sha1), committer); } - written = len <= maxlen ? write(logfd, logrec, len) : -1; + written = len <= maxlen ? write_in_full(logfd, logrec, len) : -1; free(logrec); close(logfd); if (written != len) @@ -415,19 +990,20 @@ int write_ref_sha1(struct ref_lock *lock, unlock_ref(lock); return 0; } - if (write(lock->lock_fd, sha1_to_hex(sha1), 40) != 40 || - write(lock->lock_fd, &term, 1) != 1 + if (write_in_full(lock->lock_fd, sha1_to_hex(sha1), 40) != 40 || + write_in_full(lock->lock_fd, &term, 1) != 1 || close(lock->lock_fd) < 0) { error("Couldn't write %s", lock->lk->filename); unlock_ref(lock); return -1; } + invalidate_cached_refs(); if (log_ref_write(lock, sha1, logmsg) < 0) { unlock_ref(lock); return -1; } if (commit_lock_file(lock->lk)) { - error("Couldn't set %s", lock->ref_file); + error("Couldn't set %s", lock->ref_name); unlock_ref(lock); return -1; } @@ -436,11 +1012,11 @@ int write_ref_sha1(struct ref_lock *lock, return 0; } -int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1) +int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *sha1) { const char *logfile, *logdata, *logend, *rec, *lastgt, *lastrec; char *tz_c; - int logfd, tz; + int logfd, tz, reccnt = 0; struct stat st; unsigned long date; unsigned char logged_sha1[20]; @@ -452,12 +1028,13 @@ int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1) fstat(logfd, &st); if (!st.st_size) die("Log %s is empty.", logfile); - logdata = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, logfd, 0); + logdata = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, logfd, 0); close(logfd); lastrec = NULL; rec = logend = logdata + st.st_size; while (logdata < rec) { + reccnt++; if (logdata < rec && *(rec-1) == '\n') rec--; lastgt = NULL; @@ -469,7 +1046,7 @@ int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1) if (!lastgt) die("Log %s is corrupt.", logfile); date = strtoul(lastgt + 1, &tz_c, 10); - if (date <= at_time) { + if (date <= at_time || cnt == 0) { if (lastrec) { if (get_sha1_hex(lastrec, logged_sha1)) die("Log %s is corrupt.", logfile); @@ -500,6 +1077,8 @@ int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1) return 0; } lastrec = rec; + if (cnt > 0) + cnt--; } rec = logdata; @@ -512,7 +1091,53 @@ int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1) if (get_sha1_hex(logdata, sha1)) die("Log %s is corrupt.", logfile); munmap((void*)logdata, st.st_size); - fprintf(stderr, "warning: Log %s only goes back to %s.\n", - logfile, show_rfc2822_date(date, tz)); + if (at_time) + fprintf(stderr, "warning: Log %s only goes back to %s.\n", + logfile, show_rfc2822_date(date, tz)); + else + fprintf(stderr, "warning: Log %s only has %d entries.\n", + logfile, reccnt); return 0; } + +int for_each_reflog_ent(const char *ref, each_reflog_ent_fn fn, void *cb_data) +{ + const char *logfile; + FILE *logfp; + char buf[1024]; + + logfile = git_path("logs/%s", ref); + logfp = fopen(logfile, "r"); + if (!logfp) + return -1; + while (fgets(buf, sizeof(buf), logfp)) { + unsigned char osha1[20], nsha1[20]; + char *email_end, *message; + unsigned long timestamp; + int len, ret, tz; + + /* old SP new SP name <email> SP time TAB msg LF */ + len = strlen(buf); + if (len < 83 || buf[len-1] != '\n' || + get_sha1_hex(buf, osha1) || buf[40] != ' ' || + get_sha1_hex(buf + 41, nsha1) || buf[81] != ' ' || + !(email_end = strchr(buf + 82, '>')) || + email_end[1] != ' ' || + !(timestamp = strtoul(email_end + 2, &message, 10)) || + !message || message[0] != ' ' || + (message[1] != '+' && message[1] != '-') || + !isdigit(message[2]) || !isdigit(message[3]) || + !isdigit(message[4]) || !isdigit(message[5]) || + message[6] != '\t') + continue; /* corrupt? */ + email_end[1] = '\0'; + tz = strtol(message + 1, NULL, 10); + message += 7; + ret = fn(osha1, nsha1, buf+82, timestamp, tz, message, cb_data); + if (ret) + return ret; + } + fclose(logfp); + return 0; +} + @@ -2,7 +2,7 @@ #define REFS_H struct ref_lock { - char *ref_file; + char *ref_name; char *log_file; struct lock_file *lk; unsigned char old_sha1[20]; @@ -10,24 +10,30 @@ struct ref_lock { int force_write; }; +#define REF_ISSYMREF 01 +#define REF_ISPACKED 02 + /* * Calls the specified function for each ref file until it returns nonzero, * and returns the value */ -extern int head_ref(int (*fn)(const char *path, const unsigned char *sha1)); -extern int for_each_ref(int (*fn)(const char *path, const unsigned char *sha1)); -extern int for_each_tag_ref(int (*fn)(const char *path, const unsigned char *sha1)); -extern int for_each_branch_ref(int (*fn)(const char *path, const unsigned char *sha1)); -extern int for_each_remote_ref(int (*fn)(const char *path, const unsigned char *sha1)); +typedef int each_ref_fn(const char *refname, const unsigned char *sha1, int flags, void *cb_data); +extern int head_ref(each_ref_fn, void *); +extern int for_each_ref(each_ref_fn, void *); +extern int for_each_tag_ref(each_ref_fn, void *); +extern int for_each_branch_ref(each_ref_fn, void *); +extern int for_each_remote_ref(each_ref_fn, void *); + +extern int peel_ref(const char *, unsigned char *); /** Reads the refs file specified into sha1 **/ extern int get_ref_sha1(const char *ref, unsigned char *sha1); /** Locks a "refs/" ref returning the lock on success and NULL on failure. **/ -extern struct ref_lock *lock_ref_sha1(const char *ref, const unsigned char *old_sha1, int mustexist); +extern struct ref_lock *lock_ref_sha1(const char *ref, const unsigned char *old_sha1); /** Locks any ref (for 'HEAD' type refs). */ -extern struct ref_lock *lock_any_ref_for_update(const char *ref, const unsigned char *old_sha1, int mustexist); +extern struct ref_lock *lock_any_ref_for_update(const char *ref, const unsigned char *old_sha1); /** Release any lock taken but not written. **/ extern void unlock_ref(struct ref_lock *lock); @@ -36,9 +42,16 @@ extern void unlock_ref(struct ref_lock *lock); extern int write_ref_sha1(struct ref_lock *lock, const unsigned char *sha1, const char *msg); /** Reads log for the value of ref during at_time. **/ -extern int read_ref_at(const char *ref, unsigned long at_time, unsigned char *sha1); +extern int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *sha1); + +/* iterate over reflog entries */ +typedef int each_reflog_ent_fn(unsigned char *osha1, unsigned char *nsha1, const char *, unsigned long, int, const char *, void *); +int for_each_reflog_ent(const char *ref, each_reflog_ent_fn fn, void *cb_data); /** Returns 0 if target has the right format for a ref. **/ extern int check_ref_format(const char *target); +/** rename ref, return 0 on success **/ +extern int rename_ref(const char *oldref, const char *newref, const char *logmsg); + #endif /* REFS_H */ diff --git a/revision.c b/revision.c index 1d89d72738..f2ddd95e29 100644 --- a/revision.c +++ b/revision.c @@ -6,6 +6,7 @@ #include "diff.h" #include "refs.h" #include "revision.h" +#include "grep.h" static char *path_name(struct name_path *path, const char *name) { @@ -342,6 +343,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) static void add_parents_to_list(struct rev_info *revs, struct commit *commit, struct commit_list **list) { struct commit_list *parent = commit->parents; + unsigned left_flag; if (commit->object.flags & ADDED) return; @@ -386,6 +388,7 @@ static void add_parents_to_list(struct rev_info *revs, struct commit *commit, st if (revs->no_walk) return; + left_flag = (commit->object.flags & SYMMETRIC_LEFT); parent = commit->parents; while (parent) { struct commit *p = parent->item; @@ -393,6 +396,7 @@ static void add_parents_to_list(struct rev_info *revs, struct commit *commit, st parent = parent->next; parse_commit(p); + p->object.flags |= left_flag; if (p->object.flags & SEEN) continue; p->object.flags |= SEEN; @@ -416,8 +420,6 @@ static void limit_list(struct rev_info *revs) if (revs->max_age != -1 && (commit->date < revs->max_age)) obj->flags |= UNINTERESTING; - if (revs->unpacked && has_sha1_pack(obj->sha1)) - obj->flags |= UNINTERESTING; add_parents_to_list(revs, commit, &list); if (obj->flags & UNINTERESTING) { mark_parents_uninteresting(commit); @@ -462,21 +464,71 @@ static void limit_list(struct rev_info *revs) revs->commits = newlist; } -static int all_flags; -static struct rev_info *all_revs; +struct all_refs_cb { + int all_flags; + int warned_bad_reflog; + struct rev_info *all_revs; + const char *name_for_errormsg; +}; -static int handle_one_ref(const char *path, const unsigned char *sha1) +static int handle_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) { - struct object *object = get_reference(all_revs, path, sha1, all_flags); - add_pending_object(all_revs, object, ""); + struct all_refs_cb *cb = cb_data; + struct object *object = get_reference(cb->all_revs, path, sha1, + cb->all_flags); + add_pending_object(cb->all_revs, object, ""); return 0; } static void handle_all(struct rev_info *revs, unsigned flags) { - all_revs = revs; - all_flags = flags; - for_each_ref(handle_one_ref); + struct all_refs_cb cb; + cb.all_revs = revs; + cb.all_flags = flags; + for_each_ref(handle_one_ref, &cb); +} + +static void handle_one_reflog_commit(unsigned char *sha1, void *cb_data) +{ + struct all_refs_cb *cb = cb_data; + if (!is_null_sha1(sha1)) { + struct object *o = parse_object(sha1); + if (o) { + o->flags |= cb->all_flags; + add_pending_object(cb->all_revs, o, ""); + } + else if (!cb->warned_bad_reflog) { + warn("reflog of '%s' references pruned commits", + cb->name_for_errormsg); + cb->warned_bad_reflog = 1; + } + } +} + +static int handle_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, + const char *email, unsigned long timestamp, int tz, + const char *message, void *cb_data) +{ + handle_one_reflog_commit(osha1, cb_data); + handle_one_reflog_commit(nsha1, cb_data); + return 0; +} + +static int handle_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data) +{ + struct all_refs_cb *cb = cb_data; + cb->warned_bad_reflog = 0; + cb->name_for_errormsg = path; + for_each_reflog_ent(path, handle_one_reflog_ent, cb_data); + return 0; +} + +static void handle_reflog(struct rev_info *revs, unsigned flags) +{ + struct all_refs_cb cb; + cb.all_revs = revs; + cb.all_flags = flags; + for_each_ref(handle_one_reflog, &cb); } static int add_parents_only(struct rev_info *revs, const char *arg, int flags) @@ -524,6 +576,7 @@ void init_revisions(struct rev_info *revs, const char *prefix) revs->prefix = prefix; revs->max_age = -1; revs->min_age = -1; + revs->skip_count = -1; revs->max_count = -1; revs->prune_fn = NULL; @@ -592,6 +645,138 @@ static void prepare_show_merge(struct rev_info *revs) revs->prune_data = prune; } +int handle_revision_arg(const char *arg, struct rev_info *revs, + int flags, + int cant_be_filename) +{ + char *dotdot; + struct object *object; + unsigned char sha1[20]; + int local_flags; + + dotdot = strstr(arg, ".."); + if (dotdot) { + unsigned char from_sha1[20]; + const char *next = dotdot + 2; + const char *this = arg; + int symmetric = *next == '.'; + unsigned int flags_exclude = flags ^ UNINTERESTING; + + *dotdot = 0; + next += symmetric; + + if (!*next) + next = "HEAD"; + if (dotdot == arg) + this = "HEAD"; + if (!get_sha1(this, from_sha1) && + !get_sha1(next, sha1)) { + struct commit *a, *b; + struct commit_list *exclude; + + a = lookup_commit_reference(from_sha1); + b = lookup_commit_reference(sha1); + if (!a || !b) { + die(symmetric ? + "Invalid symmetric difference expression %s...%s" : + "Invalid revision range %s..%s", + arg, next); + } + + if (!cant_be_filename) { + *dotdot = '.'; + verify_non_filename(revs->prefix, arg); + } + + if (symmetric) { + exclude = get_merge_bases(a, b, 1); + add_pending_commit_list(revs, exclude, + flags_exclude); + free_commit_list(exclude); + a->object.flags |= flags | SYMMETRIC_LEFT; + } else + a->object.flags |= flags_exclude; + b->object.flags |= flags; + add_pending_object(revs, &a->object, this); + add_pending_object(revs, &b->object, next); + return 0; + } + *dotdot = '.'; + } + dotdot = strstr(arg, "^@"); + if (dotdot && !dotdot[2]) { + *dotdot = 0; + if (add_parents_only(revs, arg, flags)) + return 0; + *dotdot = '^'; + } + dotdot = strstr(arg, "^!"); + if (dotdot && !dotdot[2]) { + *dotdot = 0; + if (!add_parents_only(revs, arg, flags ^ UNINTERESTING)) + *dotdot = '^'; + } + + local_flags = 0; + if (*arg == '^') { + local_flags = UNINTERESTING; + arg++; + } + if (get_sha1(arg, sha1)) + return -1; + if (!cant_be_filename) + verify_non_filename(revs->prefix, arg); + object = get_reference(revs, arg, sha1, flags ^ local_flags); + add_pending_object(revs, object, arg); + return 0; +} + +static void add_grep(struct rev_info *revs, const char *ptn, enum grep_pat_token what) +{ + if (!revs->grep_filter) { + struct grep_opt *opt = xcalloc(1, sizeof(*opt)); + opt->status_only = 1; + opt->pattern_tail = &(opt->pattern_list); + opt->regflags = REG_NEWLINE; + revs->grep_filter = opt; + } + append_grep_pattern(revs->grep_filter, ptn, + "command line", 0, what); +} + +static void add_header_grep(struct rev_info *revs, const char *field, const char *pattern) +{ + char *pat; + const char *prefix; + int patlen, fldlen; + + fldlen = strlen(field); + patlen = strlen(pattern); + pat = xmalloc(patlen + fldlen + 10); + prefix = ".*"; + if (*pattern == '^') { + prefix = ""; + pattern++; + } + sprintf(pat, "^%s %s%s", field, prefix, pattern); + add_grep(revs, pat, GREP_PATTERN_HEAD); +} + +static void add_message_grep(struct rev_info *revs, const char *pattern) +{ + add_grep(revs, pattern, GREP_PATTERN_BODY); +} + +static void add_ignore_packed(struct rev_info *revs, const char *name) +{ + int num = ++revs->num_ignore_packed; + + revs->ignore_packed = xrealloc(revs->ignore_packed, + sizeof(const char **) * (num + 1)); + revs->ignore_packed[num-1] = name; + revs->ignore_packed[num] = NULL; +} + /* * Parse revision information, filling in the "rev_info" structure, * and removing the used arguments from the argument list. @@ -604,6 +789,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch int i, flags, seen_dashdash, show_merge; const char **unrecognized = argv + 1; int left = 1; + int all_match = 0; /* First, search for "--" */ seen_dashdash = 0; @@ -620,18 +806,17 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch flags = show_merge = 0; for (i = 1; i < argc; i++) { - struct object *object; const char *arg = argv[i]; - unsigned char sha1[20]; - char *dotdot; - int local_flags; - if (*arg == '-') { int opts; if (!strncmp(arg, "--max-count=", 12)) { revs->max_count = atoi(arg + 12); continue; } + if (!strncmp(arg, "--skip=", 7)) { + revs->skip_count = atoi(arg + 7); + continue; + } /* accept -<digit>, like traditional "head" */ if ((*arg == '-') && isdigit(arg[1])) { revs->max_count = atoi(arg + 1); @@ -675,6 +860,10 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch handle_all(revs, flags); continue; } + if (!strcmp(arg, "--reflog")) { + handle_reflog(revs, flags); + continue; + } if (!strcmp(arg, "--not")) { flags ^= UNINTERESTING; continue; @@ -722,6 +911,10 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch revs->boundary = 1; continue; } + if (!strcmp(arg, "--left-right")) { + revs->left_right = 1; + continue; + } if (!strcmp(arg, "--objects")) { revs->tag_objects = 1; revs->tree_objects = 1; @@ -737,6 +930,14 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch } if (!strcmp(arg, "--unpacked")) { revs->unpacked = 1; + free(revs->ignore_packed); + revs->ignore_packed = NULL; + revs->num_ignore_packed = 0; + continue; + } + if (!strncmp(arg, "--unpacked=", 11)) { + revs->unpacked = 1; + add_ignore_packed(revs, arg+11); continue; } if (!strcmp(arg, "-r")) { @@ -816,6 +1017,39 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch revs->simplify_history = 0; continue; } + if (!strcmp(arg, "--relative-date")) { + revs->relative_date = 1; + continue; + } + + /* + * Grepping the commit log + */ + if (!strncmp(arg, "--author=", 9)) { + add_header_grep(revs, "author", arg+9); + continue; + } + if (!strncmp(arg, "--committer=", 12)) { + add_header_grep(revs, "committer", arg+12); + continue; + } + if (!strncmp(arg, "--grep=", 7)) { + add_message_grep(revs, arg+7); + continue; + } + if (!strcmp(arg, "--all-match")) { + all_match = 1; + continue; + } + if (!strncmp(arg, "--encoding=", 11)) { + arg += 11; + if (strcmp(arg, "none")) + git_log_output_encoding = strdup(arg); + else + git_log_output_encoding = ""; + continue; + } + opts = diff_opt_parse(&revs->diffopt, argv+i, argc-i); if (opts > 0) { revs->diff = 1; @@ -826,71 +1060,10 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch left++; continue; } - dotdot = strstr(arg, ".."); - if (dotdot) { - unsigned char from_sha1[20]; - const char *next = dotdot + 2; - const char *this = arg; - int symmetric = *next == '.'; - unsigned int flags_exclude = flags ^ UNINTERESTING; - - *dotdot = 0; - next += symmetric; - - if (!*next) - next = "HEAD"; - if (dotdot == arg) - this = "HEAD"; - if (!get_sha1(this, from_sha1) && - !get_sha1(next, sha1)) { - struct commit *a, *b; - struct commit_list *exclude; - - a = lookup_commit_reference(from_sha1); - b = lookup_commit_reference(sha1); - if (!a || !b) { - die(symmetric ? - "Invalid symmetric difference expression %s...%s" : - "Invalid revision range %s..%s", - arg, next); - } - - if (!seen_dashdash) { - *dotdot = '.'; - verify_non_filename(revs->prefix, arg); - } - - if (symmetric) { - exclude = get_merge_bases(a, b, 1); - add_pending_commit_list(revs, exclude, - flags_exclude); - free_commit_list(exclude); - a->object.flags |= flags; - } else - a->object.flags |= flags_exclude; - b->object.flags |= flags; - add_pending_object(revs, &a->object, this); - add_pending_object(revs, &b->object, next); - continue; - } - *dotdot = '.'; - } - dotdot = strstr(arg, "^@"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; - if (add_parents_only(revs, arg, flags)) - continue; - *dotdot = '^'; - } - local_flags = 0; - if (*arg == '^') { - local_flags = UNINTERESTING; - arg++; - } - if (get_sha1(arg, sha1)) { - int j; - if (seen_dashdash || local_flags) + if (handle_revision_arg(arg, revs, flags, seen_dashdash)) { + int j; + if (seen_dashdash || *arg == '^') die("bad revision '%s'", arg); /* If we didn't have a "--": @@ -902,14 +1075,12 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch for (j = i; j < argc; j++) verify_filename(revs->prefix, argv[j]); - revs->prune_data = get_pathspec(revs->prefix, argv + i); + revs->prune_data = get_pathspec(revs->prefix, + argv + i); break; } - if (!seen_dashdash) - verify_non_filename(revs->prefix, arg); - object = get_reference(revs, arg, sha1, flags ^ local_flags); - add_pending_object(revs, object, arg); } + if (show_merge) prepare_show_merge(revs); if (def && !revs->pending.nr) { @@ -921,7 +1092,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch add_pending_object(revs, object, def); } - if (revs->topo_order || revs->unpacked) + if (revs->topo_order) revs->limited = 1; if (revs->prune_data) { @@ -939,27 +1110,34 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch if (diff_setup_done(&revs->diffopt) < 0) die("diff_setup_done failed"); + if (revs->grep_filter) { + revs->grep_filter->all_match = all_match; + compile_grep_patterns(revs->grep_filter); + } + return left; } void prepare_revision_walk(struct rev_info *revs) { int nr = revs->pending.nr; - struct object_array_entry *list = revs->pending.objects; + struct object_array_entry *e, *list; + e = list = revs->pending.objects; revs->pending.nr = 0; revs->pending.alloc = 0; revs->pending.objects = NULL; while (--nr >= 0) { - struct commit *commit = handle_commit(revs, list->item, list->name); + struct commit *commit = handle_commit(revs, e->item, e->name); if (commit) { if (!(commit->object.flags & SEEN)) { commit->object.flags |= SEEN; insert_by_date(commit, &revs->commits); } } - list++; + e++; } + free(list); if (revs->no_walk) return; @@ -1011,22 +1189,19 @@ static void mark_boundary_to_show(struct commit *commit) } } -struct commit *get_revision(struct rev_info *revs) +static int commit_match(struct commit *commit, struct rev_info *opt) { - struct commit_list *list = revs->commits; - - if (!list) - return NULL; + if (!opt->grep_filter) + return 1; + return grep_buffer(opt->grep_filter, + NULL, /* we say nothing, not even filename */ + commit->buffer, strlen(commit->buffer)); +} - /* Check the max_count ... */ - switch (revs->max_count) { - case -1: - break; - case 0: +static struct commit *get_revision_1(struct rev_info *revs) +{ + if (!revs->commits) return NULL; - default: - revs->max_count--; - } do { struct commit_list *entry = revs->commits; @@ -1041,16 +1216,18 @@ struct commit *get_revision(struct rev_info *revs) * that we'd otherwise have done in limit_list(). */ if (!revs->limited) { - if ((revs->unpacked && - has_sha1_pack(commit->object.sha1)) || - (revs->max_age != -1 && - (commit->date < revs->max_age))) + if (revs->max_age != -1 && + (commit->date < revs->max_age)) continue; add_parents_to_list(revs, commit, &revs->commits); } if (commit->object.flags & SHOWN) continue; + if (revs->unpacked && has_sha1_pack(commit->object.sha1, + revs->ignore_packed)) + continue; + /* We want to show boundary commits only when their * children are shown. When path-limiter is in effect, * rewrite_parents() drops some commits from getting shown, @@ -1070,6 +1247,8 @@ struct commit *get_revision(struct rev_info *revs) if (revs->no_merges && commit->parents && commit->parents->next) continue; + if (!commit_match(commit, revs)) + continue; if (revs->prune_fn && revs->dense) { /* Commit without changes? */ if (!(commit->object.flags & TREECHANGE)) { @@ -1090,3 +1269,28 @@ struct commit *get_revision(struct rev_info *revs) } while (revs->commits); return NULL; } + +struct commit *get_revision(struct rev_info *revs) +{ + struct commit *c = NULL; + + if (0 < revs->skip_count) { + while ((c = get_revision_1(revs)) != NULL) { + if (revs->skip_count-- <= 0) + break; + } + } + + /* Check the max_count ... */ + switch (revs->max_count) { + case -1: + break; + case 0: + return NULL; + default: + revs->max_count--; + } + if (c) + return c; + return get_revision_1(revs); +} diff --git a/revision.h b/revision.h index 0c3b8d9905..8f7907d7ab 100644 --- a/revision.h +++ b/revision.h @@ -9,6 +9,7 @@ #define BOUNDARY (1u<<5) #define BOUNDARY_SHOW (1u<<6) #define ADDED (1u<<7) /* Parents already parsed and added? */ +#define SYMMETRIC_LEFT (1u<<8) struct rev_info; struct log_info; @@ -38,8 +39,9 @@ struct rev_info { blob_objects:1, edge_hint:1, limited:1, - unpacked:1, + unpacked:1, /* see also ignore_packed below */ boundary:1, + left_right:1, parents:1; /* Diff flags */ @@ -55,7 +57,12 @@ struct rev_info { /* Format info */ unsigned int shown_one:1, - abbrev_commit:1; + abbrev_commit:1, + relative_date:1; + + const char **ignore_packed; /* pretend objects in these are unpacked */ + int num_ignore_packed; + unsigned int abbrev; enum cmit_fmt commit_format; struct log_info *loginfo; @@ -65,8 +72,13 @@ struct rev_info { const char *ref_message_id; const char *add_signoff; const char *extra_headers; + const char *log_reencode; + + /* Filter by commit log message */ + struct grep_opt *grep_filter; /* special limits */ + int skip_count; int max_count; unsigned long max_age; unsigned long min_age; @@ -89,6 +101,8 @@ extern int rev_compare_tree(struct rev_info *, struct tree *t1, struct tree *t2) extern void init_revisions(struct rev_info *revs, const char *prefix); extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def); +extern int handle_revision_arg(const char *arg, struct rev_info *revs,int flags,int cant_be_filename); + extern void prepare_revision_walk(struct rev_info *revs); extern struct commit *get_revision(struct rev_info *revs); @@ -1,43 +1,10 @@ -#include <string.h> -#include <sys/types.h> -#include <sys/socket.h> - +#include "cache.h" #include "rsh.h" #include "quote.h" -#include "cache.h" #define COMMAND_SIZE 4096 -/* - * Append a string to a string buffer, with or without shell quoting. - * Return true if the buffer overflowed. - */ -static int add_to_string(char **ptrp, int *sizep, const char *str, int quote) -{ - char *p = *ptrp; - int size = *sizep; - int oc; - int err = 0; - - if ( quote ) { - oc = sq_quote_buf(p, size, str); - } else { - oc = strlen(str); - memcpy(p, str, (oc >= size) ? size-1 : oc); - } - - if ( oc >= size ) { - err = 1; - oc = size-1; - } - - *ptrp += oc; - **ptrp = '\0'; - *sizep -= oc; - return err; -} - -int setup_connection(int *fd_in, int *fd_out, const char *remote_prog, +int setup_connection(int *fd_in, int *fd_out, const char *remote_prog, char *url, int rmt_argc, char **rmt_argv) { char *host; diff --git a/run-command.c b/run-command.c index 61908682b9..cfbad74d14 100644 --- a/run-command.c +++ b/run-command.c @@ -1,21 +1,21 @@ #include "cache.h" #include "run-command.h" -#include <sys/wait.h> #include "exec_cmd.h" -int run_command_v_opt(int argc, const char **argv, int flags) +int run_command_v_opt(const char **argv, int flags) { pid_t pid = fork(); if (pid < 0) return -ERR_RUN_COMMAND_FORK; if (!pid) { - if (flags & RUN_COMMAND_NO_STDIO) { + if (flags & RUN_COMMAND_NO_STDIN) { int fd = open("/dev/null", O_RDWR); dup2(fd, 0); - dup2(fd, 1); close(fd); } + if (flags & RUN_COMMAND_STDOUT_TO_STDERR) + dup2(2, 1); if (flags & RUN_GIT_CMD) { execv_git_cmd(argv); } else { @@ -47,19 +47,17 @@ int run_command_v_opt(int argc, const char **argv, int flags) } } -int run_command_v(int argc, const char **argv) +int run_command_v(const char **argv) { - return run_command_v_opt(argc, argv, 0); + return run_command_v_opt(argv, 0); } -int run_command(const char *cmd, ...) +static int run_command_va_opt(int opt, const char *cmd, va_list param) { int argc; const char *argv[MAX_RUN_COMMAND_ARGS]; const char *arg; - va_list param; - va_start(param, cmd); argv[0] = (char*) cmd; argc = 1; while (argc < MAX_RUN_COMMAND_ARGS) { @@ -67,8 +65,29 @@ int run_command(const char *cmd, ...) if (!arg) break; } - va_end(param); if (MAX_RUN_COMMAND_ARGS <= argc) return error("too many args to run %s", cmd); - return run_command_v_opt(argc, argv, 0); + return run_command_v_opt(argv, opt); +} + +int run_command_opt(int opt, const char *cmd, ...) +{ + va_list params; + int r; + + va_start(params, cmd); + r = run_command_va_opt(opt, cmd, params); + va_end(params); + return r; +} + +int run_command(const char *cmd, ...) +{ + va_list params; + int r; + + va_start(params, cmd); + r = run_command_va_opt(0, cmd, params); + va_end(params); + return r; } diff --git a/run-command.h b/run-command.h index 70b477a748..59c4476ced 100644 --- a/run-command.h +++ b/run-command.h @@ -11,10 +11,12 @@ enum { ERR_RUN_COMMAND_WAITPID_NOEXIT, }; -#define RUN_COMMAND_NO_STDIO 1 +#define RUN_COMMAND_NO_STDIN 1 #define RUN_GIT_CMD 2 /*If this is to be git sub-command */ -int run_command_v_opt(int argc, const char **argv, int opt); -int run_command_v(int argc, const char **argv); +#define RUN_COMMAND_STDOUT_TO_STDERR 4 +int run_command_v_opt(const char **argv, int opt); +int run_command_v(const char **argv); +int run_command_opt(int opt, const char *cmd, ...); int run_command(const char *cmd, ...); #endif diff --git a/send-pack.c b/send-pack.c index fd79a61923..6756264b29 100644 --- a/send-pack.c +++ b/send-pack.c @@ -14,118 +14,89 @@ static int send_all; static int force_update; static int use_thin_pack; -static int is_zero_sha1(const unsigned char *sha1) -{ - int i; - - for (i = 0; i < 20; i++) { - if (*sha1++) - return 0; - } - return 1; -} - -static void exec_pack_objects(void) -{ - static const char *args[] = { - "pack-objects", - "--stdout", - NULL - }; - execv_git_cmd(args); - die("git-pack-objects exec failed (%s)", strerror(errno)); -} - -static void exec_rev_list(struct ref *refs) -{ - struct ref *ref; - static const char *args[1000]; - int i = 0, j; - - args[i++] = "rev-list"; /* 0 */ - if (use_thin_pack) /* 1 */ - args[i++] = "--objects-edge"; - else - args[i++] = "--objects"; - - /* First send the ones we care about most */ - for (ref = refs; ref; ref = ref->next) { - if (900 < i) - die("git-rev-list environment overflow"); - if (!is_zero_sha1(ref->new_sha1)) { - char *buf = malloc(100); - args[i++] = buf; - snprintf(buf, 50, "%s", sha1_to_hex(ref->new_sha1)); - buf += 50; - if (!is_zero_sha1(ref->old_sha1) && - has_sha1_file(ref->old_sha1)) { - args[i++] = buf; - snprintf(buf, 50, "^%s", - sha1_to_hex(ref->old_sha1)); - } - } - } - - /* Then a handful of the remainder - * NEEDSWORK: we would be better off if used the newer ones first. - */ - for (ref = refs, j = i + 16; - i < 900 && i < j && ref; - ref = ref->next) { - if (is_zero_sha1(ref->new_sha1) && - !is_zero_sha1(ref->old_sha1) && - has_sha1_file(ref->old_sha1)) { - char *buf = malloc(42); - args[i++] = buf; - snprintf(buf, 42, "^%s", sha1_to_hex(ref->old_sha1)); - } - } - args[i] = NULL; - execv_git_cmd(args); - die("git-rev-list exec failed (%s)", strerror(errno)); -} - -static void rev_list(int fd, struct ref *refs) +/* + * Make a pack stream and spit it out into file descriptor fd + */ +static int pack_objects(int fd, struct ref *refs) { int pipe_fd[2]; - pid_t pack_objects_pid; + pid_t pid; if (pipe(pipe_fd) < 0) - die("rev-list setup: pipe failed"); - pack_objects_pid = fork(); - if (!pack_objects_pid) { + return error("send-pack: pipe failed"); + pid = fork(); + if (!pid) { + /* + * The child becomes pack-objects --revs; we feed + * the revision parameters to it via its stdin and + * let its stdout go back to the other end. + */ + static const char *args[] = { + "pack-objects", + "--all-progress", + "--revs", + "--stdout", + NULL, + NULL, + }; + if (use_thin_pack) + args[4] = "--thin"; dup2(pipe_fd[0], 0); dup2(fd, 1); close(pipe_fd[0]); close(pipe_fd[1]); close(fd); - exec_pack_objects(); - die("pack-objects setup failed"); + execv_git_cmd(args); + die("git-pack-objects exec failed (%s)", strerror(errno)); } - if (pack_objects_pid < 0) - die("pack-objects fork failed"); - dup2(pipe_fd[1], 1); + + /* + * We feed the pack-objects we just spawned with revision + * parameters by writing to the pipe. + */ close(pipe_fd[0]); - close(pipe_fd[1]); close(fd); - exec_rev_list(refs); -} -static void pack_objects(int fd, struct ref *refs) -{ - pid_t rev_list_pid; + while (refs) { + char buf[42]; + + if (!is_null_sha1(refs->old_sha1) && + has_sha1_file(refs->old_sha1)) { + memcpy(buf + 1, sha1_to_hex(refs->old_sha1), 40); + buf[0] = '^'; + buf[41] = '\n'; + if (!write_or_whine(pipe_fd[1], buf, 42, + "send-pack: send refs")) + break; + } + if (!is_null_sha1(refs->new_sha1)) { + memcpy(buf, sha1_to_hex(refs->new_sha1), 40); + buf[40] = '\n'; + if (!write_or_whine(pipe_fd[1], buf, 41, + "send-pack: send refs")) + break; + } + refs = refs->next; + } + close(pipe_fd[1]); - rev_list_pid = fork(); - if (!rev_list_pid) { - rev_list(fd, refs); - die("rev-list setup failed"); + for (;;) { + int status, code; + pid_t waiting = waitpid(pid, &status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + return error("waitpid failed (%s)", strerror(errno)); + } + if ((waiting != pid) || WIFSIGNALED(status) || + !WIFEXITED(status)) + return error("pack-objects died with strange error"); + code = WEXITSTATUS(status); + if (code) + return -code; + return 0; } - if (rev_list_pid < 0) - die("rev-list fork failed"); - /* - * We don't wait for the rev-list pipeline in the parent: - * we end up waiting for the other end instead - */ } static void unmark_and_free(struct commit_list *list, unsigned int mark) @@ -180,7 +151,7 @@ static int ref_newer(const unsigned char *new_sha1, static struct ref *local_refs, **local_tail; static struct ref *remote_refs, **remote_tail; -static int one_local_ref(const char *refname, const unsigned char *sha1) +static int one_local_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { struct ref *ref; int len = strlen(refname) + 1; @@ -195,7 +166,7 @@ static int one_local_ref(const char *refname, const unsigned char *sha1) static void get_local_heads(void) { local_tail = &local_refs; - for_each_ref(one_local_ref); + for_each_ref(one_local_ref, NULL); } static int receive_status(int in) @@ -235,6 +206,7 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) int new_refs; int ret = 0; int ask_for_status_report = 0; + int allow_deleting_refs = 0; int expect_status_report = 0; /* No funny business with the matcher */ @@ -244,6 +216,8 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) /* Does the other end support the reporting? */ if (server_supports("report-status")) ask_for_status_report = 1; + if (server_supports("delete-refs")) + allow_deleting_refs = 1; /* match them up */ if (!remote_tail) @@ -263,9 +237,19 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) new_refs = 0; for (ref = remote_refs; ref; ref = ref->next) { char old_hex[60], *new_hex; + int delete_ref; + if (!ref->peer_ref) continue; - if (!hashcmp(ref->old_sha1, ref->peer_ref->new_sha1)) { + + delete_ref = is_null_sha1(ref->peer_ref->new_sha1); + if (delete_ref && !allow_deleting_refs) { + error("remote does not support deleting refs"); + ret = -2; + continue; + } + if (!delete_ref && + !hashcmp(ref->old_sha1, ref->peer_ref->new_sha1)) { if (verbose) fprintf(stderr, "'%s': up-to-date\n", ref->name); continue; @@ -285,10 +269,14 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) * * (3) if both new and old are commit-ish, and new is a * descendant of old, it is OK. + * + * (4) regardless of all of the above, removing :B is + * always allowed. */ if (!force_update && - !is_zero_sha1(ref->old_sha1) && + !delete_ref && + !is_null_sha1(ref->old_sha1) && !ref->force) { if (!has_sha1_file(ref->old_sha1) || !ref_newer(ref->peer_ref->new_sha1, @@ -311,12 +299,8 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) } } hashcpy(ref->new_sha1, ref->peer_ref->new_sha1); - if (is_zero_sha1(ref->new_sha1)) { - error("cannot happen anymore"); - ret = -3; - continue; - } - new_refs++; + if (!delete_ref) + new_refs++; strcpy(old_hex, sha1_to_hex(ref->old_sha1)); new_hex = sha1_to_hex(ref->new_sha1); @@ -330,15 +314,21 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) else packet_write(out, "%s %s %s", old_hex, new_hex, ref->name); - fprintf(stderr, "updating '%s'", ref->name); - if (strcmp(ref->name, ref->peer_ref->name)) - fprintf(stderr, " using '%s'", ref->peer_ref->name); - fprintf(stderr, "\n from %s\n to %s\n", old_hex, new_hex); + if (delete_ref) + fprintf(stderr, "deleting '%s'\n", ref->name); + else { + fprintf(stderr, "updating '%s'", ref->name); + if (strcmp(ref->name, ref->peer_ref->name)) + fprintf(stderr, " using '%s'", + ref->peer_ref->name); + fprintf(stderr, "\n from %s\n to %s\n", + old_hex, new_hex); + } } packet_flush(out); if (new_refs) - pack_objects(out, remote_refs); + ret = pack_objects(out, remote_refs); close(out); if (expect_status_report) { @@ -351,6 +341,25 @@ static int send_pack(int in, int out, int nr_refspec, char **refspec) return ret; } +static void verify_remote_names(int nr_heads, char **heads) +{ + int i; + + for (i = 0; i < nr_heads; i++) { + const char *remote = strchr(heads[i], ':'); + + remote = remote ? (remote + 1) : heads[i]; + switch (check_ref_format(remote)) { + case 0: /* ok */ + case -2: /* ok but a single level -- that is fine for + * a match pattern. + */ + continue; + } + die("remote part of refspec is not a valid name in %s", + heads[i]); + } +} int main(int argc, char **argv) { @@ -402,12 +411,14 @@ int main(int argc, char **argv) usage(send_pack_usage); if (heads && send_all) usage(send_pack_usage); + verify_remote_names(nr_heads, heads); + pid = git_connect(fd, dest, exec); if (pid < 0) return 1; ret = send_pack(fd[0], fd[1], nr_heads, heads); close(fd[0]); close(fd[1]); - finish_connect(pid); - return ret; + ret |= finish_connect(pid); + return !!ret; } diff --git a/server-info.c b/server-info.c index 7df628f2b2..6cd38be329 100644 --- a/server-info.c +++ b/server-info.c @@ -7,7 +7,7 @@ /* refs */ static FILE *info_ref_fp; -static int add_info_ref(const char *path, const unsigned char *sha1) +static int add_info_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) { struct object *o = parse_object(sha1); @@ -23,7 +23,7 @@ static int add_info_ref(const char *path, const unsigned char *sha1) static int update_info_refs(int force) { - char *path0 = strdup(git_path("info/refs")); + char *path0 = xstrdup(git_path("info/refs")); int len = strlen(path0); char *path1 = xmalloc(len + 2); @@ -34,7 +34,7 @@ static int update_info_refs(int force) info_ref_fp = fopen(path1, "w"); if (!info_ref_fp) return error("unable to update %s", path0); - for_each_ref(add_info_ref); + for_each_ref(add_info_ref, NULL); fclose(info_ref_fp); rename(path1, path0); free(path0); @@ -131,28 +131,47 @@ const char **get_pathspec(const char *prefix, const char **pathspec) } /* - * Test if it looks like we're at the top level git directory. + * Test if it looks like we're at a git directory. * We want to see: * - * - either a .git/objects/ directory _or_ the proper + * - either a objects/ directory _or_ the proper * GIT_OBJECT_DIRECTORY environment variable - * - a refs/ directory under ".git" + * - a refs/ directory * - either a HEAD symlink or a HEAD file that is formatted as - * a proper "ref:". + * a proper "ref:", or a regular file HEAD that has a properly + * formatted sha1 object name. */ -static int is_toplevel_directory(void) +static int is_git_directory(const char *suspect) { - if (access(".git/refs/", X_OK) || - access(getenv(DB_ENVIRONMENT) ? - getenv(DB_ENVIRONMENT) : ".git/objects/", X_OK) || - validate_symref(".git/HEAD")) + char path[PATH_MAX]; + size_t len = strlen(suspect); + + strcpy(path, suspect); + if (getenv(DB_ENVIRONMENT)) { + if (access(getenv(DB_ENVIRONMENT), X_OK)) + return 0; + } + else { + strcpy(path + len, "/objects"); + if (access(path, X_OK)) + return 0; + } + + strcpy(path + len, "/refs"); + if (access(path, X_OK)) return 0; + + strcpy(path + len, "/HEAD"); + if (validate_headref(path)) + return 0; + return 1; } const char *setup_git_directory_gently(int *nongit_ok) { static char cwd[PATH_MAX+1]; + const char *gitdirenv; int len, offset; /* @@ -160,36 +179,17 @@ const char *setup_git_directory_gently(int *nongit_ok) * to do any discovery, but we still do repository * validation. */ - if (getenv(GIT_DIR_ENVIRONMENT)) { - char path[PATH_MAX]; - int len = strlen(getenv(GIT_DIR_ENVIRONMENT)); - if (sizeof(path) - 40 < len) + gitdirenv = getenv(GIT_DIR_ENVIRONMENT); + if (gitdirenv) { + if (PATH_MAX - 40 < strlen(gitdirenv)) die("'$%s' too big", GIT_DIR_ENVIRONMENT); - memcpy(path, getenv(GIT_DIR_ENVIRONMENT), len); - - strcpy(path + len, "/refs"); - if (access(path, X_OK)) - goto bad_dir_environ; - strcpy(path + len, "/HEAD"); - if (validate_symref(path)) - goto bad_dir_environ; - if (getenv(DB_ENVIRONMENT)) { - if (access(getenv(DB_ENVIRONMENT), X_OK)) - goto bad_dir_environ; - } - else { - strcpy(path + len, "/objects"); - if (access(path, X_OK)) - goto bad_dir_environ; - } - return NULL; - bad_dir_environ: + if (is_git_directory(gitdirenv)) + return NULL; if (nongit_ok) { *nongit_ok = 1; return NULL; } - path[len] = 0; - die("Not a git repository: '%s'", path); + die("Not a git repository: '%s'", gitdirenv); } if (!getcwd(cwd, sizeof(cwd)) || cwd[0] != '/') @@ -197,11 +197,17 @@ const char *setup_git_directory_gently(int *nongit_ok) offset = len = strlen(cwd); for (;;) { - if (is_toplevel_directory()) + if (is_git_directory(".git")) break; chdir(".."); do { if (!offset) { + if (is_git_directory(cwd)) { + if (chdir(cwd)) + die("Cannot come back to cwd"); + setenv(GIT_DIR_ENVIRONMENT, cwd, 1); + return NULL; + } if (nongit_ok) { if (chdir(cwd)) die("Cannot come back to cwd"); diff --git a/sha1_file.c b/sha1_file.c index 769a80984d..2a5be53fac 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -22,20 +22,50 @@ #endif #endif +#ifdef NO_C99_FORMAT +#define SZ_FMT "lu" +#else +#define SZ_FMT "zu" +#endif + const unsigned char null_sha1[20]; static unsigned int sha1_file_open_flag = O_NOATIME; -static unsigned hexval(char c) -{ - if (c >= '0' && c <= '9') - return c - '0'; - if (c >= 'a' && c <= 'f') - return c - 'a' + 10; - if (c >= 'A' && c <= 'F') - return c - 'A' + 10; - return ~0; -} +signed char hexval_table[256] = { + -1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */ + 0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */ + 8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */ +}; int get_sha1_hex(const char *hex, unsigned char *sha1) { @@ -115,7 +145,7 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) /* * NOTE! This returns a statically allocated buffer, so you have to be - * careful about using it. Do a "strdup()" if you need to save the + * careful about using it. Do a "xstrdup()" if you need to save the * filename. * * Also note that this returns the location for creating. Reading @@ -331,10 +361,8 @@ static void read_info_alternates(const char * relative_base, int depth) close(fd); return; } - map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + map = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (map == MAP_FAILED) - return; link_alt_odb_entries(map, map + st.st_size, '\n', relative_base, depth); @@ -373,11 +401,36 @@ static char *find_sha1_file(const unsigned char *sha1, struct stat *st) return NULL; } -#define PACK_MAX_SZ (1<<26) -static int pack_used_ctr; -static unsigned long pack_mapped; +static unsigned int pack_used_ctr; +static unsigned int pack_mmap_calls; +static unsigned int peak_pack_open_windows; +static unsigned int pack_open_windows; +static size_t peak_pack_mapped; +static size_t pack_mapped; +static size_t page_size; struct packed_git *packed_git; +void pack_report() +{ + fprintf(stderr, + "pack_report: getpagesize() = %10" SZ_FMT "\n" + "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" + "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", + page_size, + packed_git_window_size, + packed_git_limit); + fprintf(stderr, + "pack_report: pack_used_ctr = %10u\n" + "pack_report: pack_mmap_calls = %10u\n" + "pack_report: pack_open_windows = %10u / %10u\n" + "pack_report: pack_mapped = " + "%10" SZ_FMT " / %10" SZ_FMT "\n", + pack_used_ctr, + pack_mmap_calls, + pack_open_windows, peak_pack_open_windows, + pack_mapped, peak_pack_mapped); +} + static int check_packed_git_idx(const char *path, unsigned long *idx_size_, void **idx_map_) { @@ -394,10 +447,8 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_, return -1; } idx_size = st.st_size; - idx_map = mmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); + idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (idx_map == MAP_FAILED) - return -1; index = idx_map; *idx_map_ = idx_map; @@ -427,86 +478,198 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_, return 0; } -static int unuse_one_packed_git(void) +static void scan_windows(struct packed_git *p, + struct packed_git **lru_p, + struct pack_window **lru_w, + struct pack_window **lru_l) { - struct packed_git *p, *lru = NULL; + struct pack_window *w, *w_l; - for (p = packed_git; p; p = p->next) { - if (p->pack_use_cnt || !p->pack_base) - continue; - if (!lru || p->pack_last_used < lru->pack_last_used) - lru = p; + for (w_l = NULL, w = p->windows; w; w = w->next) { + if (!w->inuse_cnt) { + if (!*lru_w || w->last_used < (*lru_w)->last_used) { + *lru_p = p; + *lru_w = w; + *lru_l = w_l; + } + } + w_l = w; } - if (!lru) - return 0; - munmap(lru->pack_base, lru->pack_size); - lru->pack_base = NULL; - return 1; } -void unuse_packed_git(struct packed_git *p) +static int unuse_one_window(struct packed_git *current) +{ + struct packed_git *p, *lru_p = NULL; + struct pack_window *lru_w = NULL, *lru_l = NULL; + + if (current) + scan_windows(current, &lru_p, &lru_w, &lru_l); + for (p = packed_git; p; p = p->next) + scan_windows(p, &lru_p, &lru_w, &lru_l); + if (lru_p) { + munmap(lru_w->base, lru_w->len); + pack_mapped -= lru_w->len; + if (lru_l) + lru_l->next = lru_w->next; + else { + lru_p->windows = lru_w->next; + if (!lru_p->windows && lru_p != current) { + close(lru_p->pack_fd); + lru_p->pack_fd = -1; + } + } + free(lru_w); + pack_open_windows--; + return 1; + } + return 0; +} + +void release_pack_memory(size_t need) +{ + size_t cur = pack_mapped; + while (need >= (cur - pack_mapped) && unuse_one_window(NULL)) + ; /* nothing */ +} + +void unuse_pack(struct pack_window **w_cursor) { - p->pack_use_cnt--; + struct pack_window *w = *w_cursor; + if (w) { + w->inuse_cnt--; + *w_cursor = NULL; + } } -int use_packed_git(struct packed_git *p) +static void open_packed_git(struct packed_git *p) { + struct stat st; + struct pack_header hdr; + unsigned char sha1[20]; + unsigned char *idx_sha1; + long fd_flag; + + p->pack_fd = open(p->pack_name, O_RDONLY); + if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) + die("packfile %s cannot be opened", p->pack_name); + + /* If we created the struct before we had the pack we lack size. */ if (!p->pack_size) { - struct stat st; - /* We created the struct before we had the pack */ - stat(p->pack_name, &st); if (!S_ISREG(st.st_mode)) die("packfile %s not a regular file", p->pack_name); p->pack_size = st.st_size; - } - if (!p->pack_base) { - int fd; - struct stat st; - void *map; - struct pack_header *hdr; - - pack_mapped += p->pack_size; - while (PACK_MAX_SZ < pack_mapped && unuse_one_packed_git()) - ; /* nothing */ - fd = open(p->pack_name, O_RDONLY); - if (fd < 0) - die("packfile %s cannot be opened", p->pack_name); - if (fstat(fd, &st)) { - close(fd); - die("packfile %s cannot be opened", p->pack_name); - } - if (st.st_size != p->pack_size) - die("packfile %s size mismatch.", p->pack_name); - map = mmap(NULL, p->pack_size, PROT_READ, MAP_PRIVATE, fd, 0); - close(fd); - if (map == MAP_FAILED) - die("packfile %s cannot be mapped.", p->pack_name); - p->pack_base = map; + } else if (p->pack_size != st.st_size) + die("packfile %s size changed", p->pack_name); - /* Check if we understand this pack file. If we don't we're - * likely too old to handle it. - */ - hdr = map; - if (hdr->hdr_signature != htonl(PACK_SIGNATURE)) - die("packfile %s isn't actually a pack.", p->pack_name); - if (!pack_version_ok(hdr->hdr_version)) - die("packfile %s is version %i and not supported" - " (try upgrading GIT to a newer version)", - p->pack_name, ntohl(hdr->hdr_version)); - - /* Check if the pack file matches with the index file. - * this is cheap. - */ - if (hashcmp((unsigned char *)(p->index_base) + - p->index_size - 40, - (unsigned char *)p->pack_base + - p->pack_size - 20)) { - die("packfile %s does not match index.", p->pack_name); + /* We leave these file descriptors open with sliding mmap; + * there is no point keeping them open across exec(), though. + */ + fd_flag = fcntl(p->pack_fd, F_GETFD, 0); + if (fd_flag < 0) + die("cannot determine file descriptor flags"); + fd_flag |= FD_CLOEXEC; + if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) + die("cannot set FD_CLOEXEC"); + + /* Verify we recognize this pack file format. */ + read_or_die(p->pack_fd, &hdr, sizeof(hdr)); + if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) + die("file %s is not a GIT packfile", p->pack_name); + if (!pack_version_ok(hdr.hdr_version)) + die("packfile %s is version %u and not supported" + " (try upgrading GIT to a newer version)", + p->pack_name, ntohl(hdr.hdr_version)); + + /* Verify the pack matches its index. */ + if (num_packed_objects(p) != ntohl(hdr.hdr_entries)) + die("packfile %s claims to have %u objects" + " while index size indicates %u objects", + p->pack_name, ntohl(hdr.hdr_entries), + num_packed_objects(p)); + if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) + die("end of packfile %s is unavailable", p->pack_name); + read_or_die(p->pack_fd, sha1, sizeof(sha1)); + idx_sha1 = ((unsigned char *)p->index_base) + p->index_size - 40; + if (hashcmp(sha1, idx_sha1)) + die("packfile %s does not match index", p->pack_name); +} + +static int in_window(struct pack_window *win, unsigned long offset) +{ + /* We must promise at least 20 bytes (one hash) after the + * offset is available from this window, otherwise the offset + * is not actually in this window and a different window (which + * has that one hash excess) must be used. This is to support + * the object header and delta base parsing routines below. + */ + off_t win_off = win->offset; + return win_off <= offset + && (offset + 20) <= (win_off + win->len); +} + +unsigned char* use_pack(struct packed_git *p, + struct pack_window **w_cursor, + unsigned long offset, + unsigned int *left) +{ + struct pack_window *win = *w_cursor; + + if (p->pack_fd == -1) + open_packed_git(p); + + /* Since packfiles end in a hash of their content and its + * pointless to ask for an offset into the middle of that + * hash, and the in_window function above wouldn't match + * don't allow an offset too close to the end of the file. + */ + if (offset > (p->pack_size - 20)) + die("offset beyond end of packfile (truncated pack?)"); + + if (!win || !in_window(win, offset)) { + if (win) + win->inuse_cnt--; + for (win = p->windows; win; win = win->next) { + if (in_window(win, offset)) + break; + } + if (!win) { + if (!page_size) + page_size = getpagesize(); + win = xcalloc(1, sizeof(*win)); + win->offset = (offset / page_size) * page_size; + win->len = p->pack_size - win->offset; + if (win->len > packed_git_window_size) + win->len = packed_git_window_size; + pack_mapped += win->len; + while (packed_git_limit < pack_mapped + && unuse_one_window(p)) + ; /* nothing */ + win->base = xmmap(NULL, win->len, + PROT_READ, MAP_PRIVATE, + p->pack_fd, win->offset); + if (win->base == MAP_FAILED) + die("packfile %s cannot be mapped: %s", + p->pack_name, + strerror(errno)); + pack_mmap_calls++; + pack_open_windows++; + if (pack_mapped > peak_pack_mapped) + peak_pack_mapped = pack_mapped; + if (pack_open_windows > peak_pack_open_windows) + peak_pack_open_windows = pack_open_windows; + win->next = p->windows; + p->windows = win; } } - p->pack_last_used = pack_used_ctr++; - p->pack_use_cnt++; - return 0; + if (win != *w_cursor) { + win->last_used = pack_used_ctr++; + win->inuse_cnt++; + *w_cursor = win; + } + offset -= win->offset; + if (left) + *left = win->len - offset; + return win->base + offset; } struct packed_git *add_packed_git(char *path, int path_len, int local) @@ -535,9 +698,8 @@ struct packed_git *add_packed_git(char *path, int path_len, int local) p->pack_size = st.st_size; p->index_base = idx_map; p->next = NULL; - p->pack_base = NULL; - p->pack_last_used = 0; - p->pack_use_cnt = 0; + p->windows = NULL; + p->pack_fd = -1; p->pack_local = local; if ((path_len > 44) && !get_sha1_hex(path + path_len - 44, sha1)) hashcpy(p->sha1, sha1); @@ -568,9 +730,8 @@ struct packed_git *parse_pack_index_file(const unsigned char *sha1, char *idx_pa p->pack_size = 0; p->index_base = idx_map; p->next = NULL; - p->pack_base = NULL; - p->pack_last_used = 0; - p->pack_use_cnt = 0; + p->windows = NULL; + p->pack_fd = -1; hashcpy(p->sha1, sha1); return p; } @@ -639,7 +800,7 @@ void prepare_packed_git(void) prepare_packed_git_run_once = 1; } -static void reprepare_packed_git(void) +void reprepare_packed_git(void) { prepare_packed_git_run_once = 0; prepare_packed_git(); @@ -647,14 +808,8 @@ static void reprepare_packed_git(void) int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) { - char header[100]; unsigned char real_sha1[20]; - SHA_CTX c; - - SHA1_Init(&c); - SHA1_Update(&c, header, 1+sprintf(header, "%s %lu", type, size)); - SHA1_Update(&c, map, size); - SHA1_Final(real_sha1, &c); + hash_sha1_file(map, size, type, real_sha1); return hashcmp(sha1, real_sha1) ? -1 : 0; } @@ -687,10 +842,8 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) */ sha1_file_open_flag = 0; } - map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + map = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (map == MAP_FAILED) - return NULL; *size = st.st_size; return map; } @@ -711,17 +864,39 @@ int legacy_loose_object(unsigned char *map) return 0; } -static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) +unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) { + unsigned shift; unsigned char c; - unsigned int bits; unsigned long size; - static const char *typename[8] = { - NULL, /* OBJ_EXT */ - "commit", "tree", "blob", "tag", - NULL, NULL, NULL + unsigned long used = 0; + + c = buf[used++]; + *type = (c >> 4) & 7; + size = c & 15; + shift = 4; + while (c & 0x80) { + if (len <= used) + return 0; + if (sizeof(long) * 8 <= shift) + return 0; + c = buf[used++]; + size += (c & 0x7f) << shift; + shift += 7; + } + *sizep = size; + return used; +} + +static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) +{ + unsigned long size, used; + static const char valid_loose_object_type[8] = { + 0, /* OBJ_EXT */ + 1, 1, 1, 1, /* "commit", "tree", "blob", "tag" */ + 0, /* "delta" and others are invalid in a loose object */ }; - const char *type; + enum object_type type; /* Get the data stream */ memset(stream, 0, sizeof(*stream)); @@ -735,22 +910,11 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon return inflate(stream, 0); } - c = *map++; - mapsize--; - type = typename[(c >> 4) & 7]; - if (!type) + used = unpack_object_header_gently(map, mapsize, &type, &size); + if (!used || !valid_loose_object_type[type]) return -1; - - bits = 4; - size = c & 0xf; - while ((c & 0x80)) { - if (bits >= 8*sizeof(long)) - return -1; - c = *map++; - size += (c & 0x7f) << bits; - bits += 7; - mapsize--; - } + map += used; + mapsize -= used; /* Set up the stream for the rest.. */ stream->next_in = map; @@ -758,7 +922,8 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon inflateInit(stream); /* And generate the fake traditional header */ - stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", type, size); + stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", + type_names[type], size); return 0; } @@ -847,52 +1012,94 @@ void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned l return unpack_sha1_rest(&stream, hdr, *size); } +static unsigned long get_delta_base(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + enum object_type kind, + unsigned long delta_obj_offset, + unsigned long *base_obj_offset) +{ + unsigned char *base_info = use_pack(p, w_curs, offset, NULL); + unsigned long base_offset; + + /* use_pack() assured us we have [base_info, base_info + 20) + * as a range that we can look at without walking off the + * end of the mapped window. Its actually the hash size + * that is assured. An OFS_DELTA longer than the hash size + * is stupid, as then a REF_DELTA would be smaller to store. + */ + if (kind == OBJ_OFS_DELTA) { + unsigned used = 0; + unsigned char c = base_info[used++]; + base_offset = c & 127; + while (c & 128) { + base_offset += 1; + if (!base_offset || base_offset & ~(~0UL >> 7)) + die("offset value overflow for delta base object"); + c = base_info[used++]; + base_offset = (base_offset << 7) + (c & 127); + } + base_offset = delta_obj_offset - base_offset; + if (base_offset >= delta_obj_offset) + die("delta base offset out of bound"); + offset += used; + } else if (kind == OBJ_REF_DELTA) { + /* The base entry _must_ be in the same pack */ + base_offset = find_pack_entry_one(base_info, p); + if (!base_offset) + die("failed to find delta-pack base object %s", + sha1_to_hex(base_info)); + offset += 20; + } else + die("I am totally screwed"); + *base_obj_offset = base_offset; + return offset; +} + /* forward declaration for a mutually recursive function */ -static int packed_object_info(struct pack_entry *entry, +static int packed_object_info(struct packed_git *p, unsigned long offset, char *type, unsigned long *sizep); -static int packed_delta_info(unsigned char *base_sha1, - unsigned long delta_size, - unsigned long left, +static int packed_delta_info(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + enum object_type kind, + unsigned long obj_offset, char *type, - unsigned long *sizep, - struct packed_git *p) + unsigned long *sizep) { - struct pack_entry base_ent; - - if (left < 20) - die("truncated pack file"); + unsigned long base_offset; - /* The base entry _must_ be in the same pack */ - if (!find_pack_entry_one(base_sha1, &base_ent, p)) - die("failed to find delta-pack base object %s", - sha1_to_hex(base_sha1)); + offset = get_delta_base(p, w_curs, offset, kind, + obj_offset, &base_offset); /* We choose to only get the type of the base object and * ignore potentially corrupt pack file that expects the delta * based on a base with a wrong size. This saves tons of * inflate() calls. */ - - if (packed_object_info(&base_ent, type, NULL)) + if (packed_object_info(p, base_offset, type, NULL)) die("cannot get info for delta-pack base"); if (sizep) { const unsigned char *data; - unsigned char delta_head[64]; + unsigned char delta_head[20], *in; unsigned long result_size; z_stream stream; int st; memset(&stream, 0, sizeof(stream)); - - data = stream.next_in = base_sha1 + 20; - stream.avail_in = left - 20; stream.next_out = delta_head; stream.avail_out = sizeof(delta_head); inflateInit(&stream); - st = inflate(&stream, Z_FINISH); + do { + in = use_pack(p, w_curs, offset, &stream.avail_in); + stream.next_in = in; + st = inflate(&stream, Z_FINISH); + offset += stream.next_in - in; + } while ((st == Z_OK || st == Z_BUF_ERROR) + && stream.total_out < sizeof(delta_head)); inflateEnd(&stream); if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) @@ -913,221 +1120,135 @@ static int packed_delta_info(unsigned char *base_sha1, return 0; } -static unsigned long unpack_object_header(struct packed_git *p, unsigned long offset, - enum object_type *type, unsigned long *sizep) +static unsigned long unpack_object_header(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + enum object_type *type, + unsigned long *sizep) { - unsigned shift; - unsigned char *pack, c; - unsigned long size; + unsigned char *base; + unsigned int left; + unsigned long used; - if (offset >= p->pack_size) + /* use_pack() assures us we have [base, base + 20) available + * as a range that we can look at at. (Its actually the hash + * size that is assurred.) With our object header encoding + * the maximum deflated object size is 2^137, which is just + * insane, so we know won't exceed what we have been given. + */ + base = use_pack(p, w_curs, offset, &left); + used = unpack_object_header_gently(base, left, type, sizep); + if (!used) die("object offset outside of pack file"); - pack = (unsigned char *) p->pack_base + offset; - c = *pack++; - offset++; - *type = (c >> 4) & 7; - size = c & 15; - shift = 4; - while (c & 0x80) { - if (offset >= p->pack_size) - die("object offset outside of pack file"); - c = *pack++; - offset++; - size += (c & 0x7f) << shift; - shift += 7; - } - *sizep = size; - return offset; -} - -int check_reuse_pack_delta(struct packed_git *p, unsigned long offset, - unsigned char *base, unsigned long *sizep, - enum object_type *kindp) -{ - unsigned long ptr; - int status = -1; - - use_packed_git(p); - ptr = offset; - ptr = unpack_object_header(p, ptr, kindp, sizep); - if (*kindp != OBJ_DELTA) - goto done; - hashcpy(base, (unsigned char *) p->pack_base + ptr); - status = 0; - done: - unuse_packed_git(p); - return status; + return offset + used; } -void packed_object_info_detail(struct pack_entry *e, +void packed_object_info_detail(struct packed_git *p, + unsigned long offset, char *type, unsigned long *size, unsigned long *store_size, unsigned int *delta_chain_length, unsigned char *base_sha1) { - struct packed_git *p = e->p; - unsigned long offset; - unsigned char *pack; + struct pack_window *w_curs = NULL; + unsigned long obj_offset, val; + unsigned char *next_sha1; enum object_type kind; - offset = unpack_object_header(p, e->offset, &kind, size); - pack = (unsigned char *) p->pack_base + offset; - if (kind != OBJ_DELTA) - *delta_chain_length = 0; - else { - unsigned int chain_length = 0; - if (p->pack_size <= offset + 20) - die("pack file %s records an incomplete delta base", - p->pack_name); - hashcpy(base_sha1, pack); - do { - struct pack_entry base_ent; - unsigned long junk; - - find_pack_entry_one(pack, &base_ent, p); - offset = unpack_object_header(p, base_ent.offset, - &kind, &junk); - pack = (unsigned char *) p->pack_base + offset; - chain_length++; - } while (kind == OBJ_DELTA); - *delta_chain_length = chain_length; - } - switch (kind) { - case OBJ_COMMIT: - strcpy(type, commit_type); - break; - case OBJ_TREE: - strcpy(type, tree_type); - break; - case OBJ_BLOB: - strcpy(type, blob_type); - break; - case OBJ_TAG: - strcpy(type, tag_type); - break; - default: - die("corrupted pack file %s containing object of kind %d", - p->pack_name, kind); + *delta_chain_length = 0; + obj_offset = offset; + offset = unpack_object_header(p, &w_curs, offset, &kind, size); + + for (;;) { + switch (kind) { + default: + die("pack %s contains unknown object type %d", + p->pack_name, kind); + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + strcpy(type, type_names[kind]); + *store_size = 0; /* notyet */ + unuse_pack(&w_curs); + return; + case OBJ_OFS_DELTA: + get_delta_base(p, &w_curs, offset, kind, + obj_offset, &offset); + if (*delta_chain_length == 0) { + /* TODO: find base_sha1 as pointed by offset */ + } + break; + case OBJ_REF_DELTA: + next_sha1 = use_pack(p, &w_curs, offset, NULL); + if (*delta_chain_length == 0) + hashcpy(base_sha1, next_sha1); + offset = find_pack_entry_one(next_sha1, p); + break; + } + obj_offset = offset; + offset = unpack_object_header(p, &w_curs, offset, &kind, &val); + (*delta_chain_length)++; } - *store_size = 0; /* notyet */ } -static int packed_object_info(struct pack_entry *entry, +static int packed_object_info(struct packed_git *p, unsigned long offset, char *type, unsigned long *sizep) { - struct packed_git *p = entry->p; - unsigned long offset, size, left; - unsigned char *pack; + struct pack_window *w_curs = NULL; + unsigned long size, obj_offset = offset; enum object_type kind; - int retval; - - if (use_packed_git(p)) - die("cannot map packed file"); + int r; - offset = unpack_object_header(p, entry->offset, &kind, &size); - pack = (unsigned char *) p->pack_base + offset; - left = p->pack_size - offset; + offset = unpack_object_header(p, &w_curs, offset, &kind, &size); switch (kind) { - case OBJ_DELTA: - retval = packed_delta_info(pack, size, left, type, sizep, p); - unuse_packed_git(p); - return retval; + case OBJ_OFS_DELTA: + case OBJ_REF_DELTA: + r = packed_delta_info(p, &w_curs, offset, kind, + obj_offset, type, sizep); + unuse_pack(&w_curs); + return r; case OBJ_COMMIT: - strcpy(type, commit_type); - break; case OBJ_TREE: - strcpy(type, tree_type); - break; case OBJ_BLOB: - strcpy(type, blob_type); - break; case OBJ_TAG: - strcpy(type, tag_type); + strcpy(type, type_names[kind]); + unuse_pack(&w_curs); break; default: - die("corrupted pack file %s containing object of kind %d", + die("pack %s contains unknown object type %d", p->pack_name, kind); } if (sizep) *sizep = size; - unuse_packed_git(p); return 0; } -static void *unpack_delta_entry(unsigned char *base_sha1, - unsigned long delta_size, - unsigned long left, - char *type, - unsigned long *sizep, - struct packed_git *p) -{ - struct pack_entry base_ent; - void *data, *delta_data, *result, *base; - unsigned long data_size, result_size, base_size; - z_stream stream; - int st; - - if (left < 20) - die("truncated pack file"); - - /* The base entry _must_ be in the same pack */ - if (!find_pack_entry_one(base_sha1, &base_ent, p)) - die("failed to find delta-pack base object %s", - sha1_to_hex(base_sha1)); - base = unpack_entry_gently(&base_ent, type, &base_size); - if (!base) - die("failed to read delta-pack base object %s", - sha1_to_hex(base_sha1)); - - data = base_sha1 + 20; - data_size = left - 20; - delta_data = xmalloc(delta_size); - - memset(&stream, 0, sizeof(stream)); - - stream.next_in = data; - stream.avail_in = data_size; - stream.next_out = delta_data; - stream.avail_out = delta_size; - - inflateInit(&stream); - st = inflate(&stream, Z_FINISH); - inflateEnd(&stream); - if ((st != Z_STREAM_END) || stream.total_out != delta_size) - die("delta data unpack failed"); - - result = patch_delta(base, base_size, - delta_data, delta_size, - &result_size); - if (!result) - die("failed to apply delta"); - free(delta_data); - free(base); - *sizep = result_size; - return result; -} - -static void *unpack_non_delta_entry(unsigned char *data, - unsigned long size, - unsigned long left) +static void *unpack_compressed_entry(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + unsigned long size) { int st; z_stream stream; - unsigned char *buffer; + unsigned char *buffer, *in; buffer = xmalloc(size + 1); buffer[size] = 0; memset(&stream, 0, sizeof(stream)); - stream.next_in = data; - stream.avail_in = left; stream.next_out = buffer; stream.avail_out = size; inflateInit(&stream); - st = inflate(&stream, Z_FINISH); + do { + in = use_pack(p, w_curs, offset, &stream.avail_in); + stream.next_in = in; + st = inflate(&stream, Z_FINISH); + offset += stream.next_in - in; + } while (st == Z_OK || st == Z_BUF_ERROR); inflateEnd(&stream); if ((st != Z_STREAM_END) || stream.total_out != size) { free(buffer); @@ -1137,55 +1258,64 @@ static void *unpack_non_delta_entry(unsigned char *data, return buffer; } -static void *unpack_entry(struct pack_entry *entry, - char *type, unsigned long *sizep) +static void *unpack_delta_entry(struct packed_git *p, + struct pack_window **w_curs, + unsigned long offset, + unsigned long delta_size, + enum object_type kind, + unsigned long obj_offset, + char *type, + unsigned long *sizep) { - struct packed_git *p = entry->p; - void *retval; + void *delta_data, *result, *base; + unsigned long result_size, base_size, base_offset; - if (use_packed_git(p)) - die("cannot map packed file"); - retval = unpack_entry_gently(entry, type, sizep); - unuse_packed_git(p); - if (!retval) - die("corrupted pack file %s", p->pack_name); - return retval; + offset = get_delta_base(p, w_curs, offset, kind, + obj_offset, &base_offset); + base = unpack_entry(p, base_offset, type, &base_size); + if (!base) + die("failed to read delta base object at %lu from %s", + base_offset, p->pack_name); + + delta_data = unpack_compressed_entry(p, w_curs, offset, delta_size); + result = patch_delta(base, base_size, + delta_data, delta_size, + &result_size); + if (!result) + die("failed to apply delta"); + free(delta_data); + free(base); + *sizep = result_size; + return result; } -/* The caller is responsible for use_packed_git()/unuse_packed_git() pair */ -void *unpack_entry_gently(struct pack_entry *entry, +void *unpack_entry(struct packed_git *p, unsigned long offset, char *type, unsigned long *sizep) { - struct packed_git *p = entry->p; - unsigned long offset, size, left; - unsigned char *pack; + struct pack_window *w_curs = NULL; + unsigned long size, obj_offset = offset; enum object_type kind; void *retval; - offset = unpack_object_header(p, entry->offset, &kind, &size); - pack = (unsigned char *) p->pack_base + offset; - left = p->pack_size - offset; + offset = unpack_object_header(p, &w_curs, offset, &kind, &size); switch (kind) { - case OBJ_DELTA: - retval = unpack_delta_entry(pack, size, left, type, sizep, p); - return retval; - case OBJ_COMMIT: - strcpy(type, commit_type); + case OBJ_OFS_DELTA: + case OBJ_REF_DELTA: + retval = unpack_delta_entry(p, &w_curs, offset, size, + kind, obj_offset, type, sizep); break; + case OBJ_COMMIT: case OBJ_TREE: - strcpy(type, tree_type); - break; case OBJ_BLOB: - strcpy(type, blob_type); - break; case OBJ_TAG: - strcpy(type, tag_type); + strcpy(type, type_names[kind]); + *sizep = size; + retval = unpack_compressed_entry(p, &w_curs, offset, size); break; default: - return NULL; + die("unknown object type %i in %s", kind, p->pack_name); } - *sizep = size; - retval = unpack_non_delta_entry(pack, size, left); + unuse_pack(&w_curs); return retval; } @@ -1205,8 +1335,8 @@ int nth_packed_object_sha1(const struct packed_git *p, int n, return 0; } -int find_pack_entry_one(const unsigned char *sha1, - struct pack_entry *e, struct packed_git *p) +unsigned long find_pack_entry_one(const unsigned char *sha1, + struct packed_git *p) { unsigned int *level1_ofs = p->index_base; int hi = ntohl(level1_ofs[*sha1]); @@ -1216,12 +1346,8 @@ int find_pack_entry_one(const unsigned char *sha1, do { int mi = (lo + hi) / 2; int cmp = hashcmp((unsigned char *)index + (24 * mi) + 4, sha1); - if (!cmp) { - e->offset = ntohl(*((unsigned int *) ((char *) index + (24 * mi)))); - hashcpy(e->sha1, sha1); - e->p = p; - return 1; - } + if (!cmp) + return ntohl(*((unsigned int *) ((char *) index + (24 * mi)))); if (cmp > 0) hi = mi; else @@ -1230,14 +1356,47 @@ int find_pack_entry_one(const unsigned char *sha1, return 0; } -static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) +static int matches_pack_name(struct packed_git *p, const char *ig) +{ + const char *last_c, *c; + + if (!strcmp(p->pack_name, ig)) + return 0; + + for (c = p->pack_name, last_c = c; *c;) + if (*c == '/') + last_c = ++c; + else + ++c; + if (!strcmp(last_c, ig)) + return 0; + + return 1; +} + +static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed) { struct packed_git *p; + unsigned long offset; + prepare_packed_git(); for (p = packed_git; p; p = p->next) { - if (find_pack_entry_one(sha1, e, p)) + if (ignore_packed) { + const char **ig; + for (ig = ignore_packed; *ig; ig++) + if (!matches_pack_name(p, *ig)) + break; + if (*ig) + continue; + } + offset = find_pack_entry_one(sha1, p); + if (offset) { + e->offset = offset; + e->p = p; + hashcpy(e->sha1, sha1); return 1; + } } return 0; } @@ -1246,17 +1405,16 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1, struct packed_git *packs) { struct packed_git *p; - struct pack_entry e; for (p = packs; p; p = p->next) { - if (find_pack_entry_one(sha1, &e, p)) + if (find_pack_entry_one(sha1, p)) return p; } return NULL; } -int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep) +static int sha1_loose_object_info(const unsigned char *sha1, char *type, unsigned long *sizep) { int status; unsigned long mapsize, size; @@ -1265,16 +1423,8 @@ int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep char hdr[128]; map = map_sha1_file(sha1, &mapsize); - if (!map) { - struct pack_entry e; - - if (find_pack_entry(sha1, &e)) - return packed_object_info(&e, type, sizep); - reprepare_packed_git(); - if (find_pack_entry(sha1, &e)) - return packed_object_info(&e, type, sizep); + if (!map) return error("unable to find %s", sha1_to_hex(sha1)); - } if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) status = error("unable to unpack %s header", sha1_to_hex(sha1)); @@ -1290,15 +1440,27 @@ int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep return status; } +int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep) +{ + struct pack_entry e; + + if (!find_pack_entry(sha1, &e, NULL)) { + reprepare_packed_git(); + if (!find_pack_entry(sha1, &e, NULL)) + return sha1_loose_object_info(sha1, type, sizep); + } + return packed_object_info(e.p, e.offset, type, sizep); +} + static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned long *size) { struct pack_entry e; - if (!find_pack_entry(sha1, &e)) { + if (!find_pack_entry(sha1, &e, NULL)) { error("cannot read sha1_file for %s", sha1_to_hex(sha1)); return NULL; } - return unpack_entry(&e, type, size); + return unpack_entry(e.p, e.offset, type, size); } void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size) @@ -1307,7 +1469,7 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size void *map, *buf; struct pack_entry e; - if (find_pack_entry(sha1, &e)) + if (find_pack_entry(sha1, &e, NULL)) return read_packed_sha1(sha1, type, size); map = map_sha1_file(sha1, &mapsize); if (map) { @@ -1316,7 +1478,7 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size return buf; } reprepare_packed_git(); - if (find_pack_entry(sha1, &e)) + if (find_pack_entry(sha1, &e, NULL)) return read_packed_sha1(sha1, type, size); return NULL; } @@ -1367,12 +1529,9 @@ void *read_object_with_reference(const unsigned char *sha1, } } -char *write_sha1_file_prepare(void *buf, - unsigned long len, - const char *type, - unsigned char *sha1, - unsigned char *hdr, - int *hdrlen) +static void write_sha1_file_prepare(void *buf, unsigned long len, + const char *type, unsigned char *sha1, + unsigned char *hdr, int *hdrlen) { SHA_CTX c; @@ -1384,8 +1543,6 @@ char *write_sha1_file_prepare(void *buf, SHA1_Update(&c, hdr, *hdrlen); SHA1_Update(&c, buf, len); SHA1_Final(sha1, &c); - - return sha1_file_name(sha1); } /* @@ -1394,7 +1551,7 @@ char *write_sha1_file_prepare(void *buf, * * Returns the errno on failure, 0 on success. */ -static int link_temp_to_file(const char *tmpfile, char *filename) +static int link_temp_to_file(const char *tmpfile, const char *filename) { int ret; char *dir; @@ -1413,9 +1570,10 @@ static int link_temp_to_file(const char *tmpfile, char *filename) dir = strrchr(filename, '/'); if (dir) { *dir = 0; - mkdir(filename, 0777); - if (adjust_shared_perm(filename)) + if (!mkdir(filename, 0777) && adjust_shared_perm(filename)) { + *dir = '/'; return -2; + } *dir = '/'; if (!link(tmpfile, filename)) return 0; @@ -1427,7 +1585,7 @@ static int link_temp_to_file(const char *tmpfile, char *filename) /* * Move the just written object into its final resting place */ -int move_temp_to_file(const char *tmpfile, char *filename) +int move_temp_to_file(const char *tmpfile, const char *filename) { int ret = link_temp_to_file(tmpfile, filename); @@ -1450,8 +1608,7 @@ int move_temp_to_file(const char *tmpfile, char *filename) unlink(tmpfile); if (ret) { if (ret != EEXIST) { - fprintf(stderr, "unable to write sha1 filename %s: %s\n", filename, strerror(ret)); - return -1; + return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret)); } /* FIXME!!! Collision check here ? */ } @@ -1461,20 +1618,8 @@ int move_temp_to_file(const char *tmpfile, char *filename) static int write_buffer(int fd, const void *buf, size_t len) { - while (len) { - ssize_t size; - - size = write(fd, buf, len); - if (!size) - return error("file write: disk full"); - if (size < 0) { - if (errno == EINTR || errno == EAGAIN) - continue; - return error("file write error (%s)", strerror(errno)); - } - len -= size; - buf = (char *) buf + size; - } + if (write_in_full(fd, buf, len) < 0) + return error("file write error (%s)", strerror(errno)); return 0; } @@ -1521,6 +1666,15 @@ static void setup_object_header(z_stream *stream, const char *type, unsigned lon stream->avail_out -= hdr; } +int hash_sha1_file(void *buf, unsigned long len, const char *type, + unsigned char *sha1) +{ + unsigned char hdr[50]; + int hdrlen; + write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); + return 0; +} + int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1) { int size; @@ -1535,7 +1689,8 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. */ - filename = write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); + write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); + filename = sha1_file_name(sha1); if (returnsha1) hashcpy(returnsha1, sha1); if (has_sha1_file(sha1)) @@ -1551,16 +1706,17 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha } if (errno != ENOENT) { - fprintf(stderr, "sha1 file %s: %s\n", filename, strerror(errno)); - return -1; + return error("sha1 file %s: %s\n", filename, strerror(errno)); } snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory()); fd = mkstemp(tmpfile); if (fd < 0) { - fprintf(stderr, "unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno)); - return -1; + if (errno == EPERM) + return error("insufficient permission for adding an object to repository database %s\n", get_object_directory()); + else + return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno)); } /* Set it up */ @@ -1675,9 +1831,12 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory()); local = mkstemp(tmpfile); - if (local < 0) - return error("Couldn't open %s for %s", - tmpfile, sha1_to_hex(sha1)); + if (local < 0) { + if (errno == EPERM) + return error("insufficient permission for adding an object to repository database %s\n", get_object_directory()); + else + return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno)); + } memset(&stream, 0, sizeof(stream)); @@ -1705,7 +1864,7 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, if (ret != Z_OK) break; } - size = read(fd, buffer + *bufposn, bufsize - *bufposn); + size = xread(fd, buffer + *bufposn, bufsize - *bufposn); if (size <= 0) { close(local); unlink(tmpfile); @@ -1748,10 +1907,10 @@ int has_pack_file(const unsigned char *sha1) return 1; } -int has_sha1_pack(const unsigned char *sha1) +int has_sha1_pack(const unsigned char *sha1, const char **ignore_packed) { struct pack_entry e; - return find_pack_entry(sha1, &e); + return find_pack_entry(sha1, &e, ignore_packed); } int has_sha1_file(const unsigned char *sha1) @@ -1759,7 +1918,7 @@ int has_sha1_file(const unsigned char *sha1) struct stat st; struct pack_entry e; - if (find_pack_entry(sha1, &e)) + if (find_pack_entry(sha1, &e, NULL)) return 1; return find_sha1_file(sha1, &st) ? 1 : 0; } @@ -1786,7 +1945,7 @@ int read_pipe(int fd, char** return_buf, unsigned long* return_size) off += iret; if (off == size) { size *= 2; - buf = realloc(buf, size); + buf = xrealloc(buf, size); } } } while (iret > 0); @@ -1802,10 +1961,8 @@ int read_pipe(int fd, char** return_buf, unsigned long* return_size) int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) { unsigned long size = 4096; - char *buf = malloc(size); + char *buf = xmalloc(size); int ret; - unsigned char hdr[50]; - int hdrlen; if (read_pipe(fd, &buf, &size)) { free(buf); @@ -1816,10 +1973,8 @@ int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) type = blob_type; if (write_object) ret = write_sha1_file(buf, size, type, sha1); - else { - write_sha1_file_prepare(buf, size, type, sha1, hdr, &hdrlen); - ret = 0; - } + else + ret = hash_sha1_file(buf, size, type, sha1); free(buf); return ret; } @@ -1829,24 +1984,18 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, con unsigned long size = st->st_size; void *buf; int ret; - unsigned char hdr[50]; - int hdrlen; buf = ""; if (size) - buf = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (buf == MAP_FAILED) - return -1; if (!type) type = blob_type; if (write_object) ret = write_sha1_file(buf, size, type, sha1); - else { - write_sha1_file_prepare(buf, size, type, sha1, hdr, &hdrlen); - ret = 0; - } + else + ret = hash_sha1_file(buf, size, type, sha1); if (size) munmap(buf, size); return ret; @@ -1875,12 +2024,9 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write return error("readlink(\"%s\"): %s", path, errstr); } - if (!write_object) { - unsigned char hdr[50]; - int hdrlen; - write_sha1_file_prepare(target, st->st_size, blob_type, - sha1, hdr, &hdrlen); - } else if (write_sha1_file(target, st->st_size, blob_type, sha1)) + if (!write_object) + hash_sha1_file(target, st->st_size, blob_type, sha1); + else if (write_sha1_file(target, st->st_size, blob_type, sha1)) return error("%s: failed to insert into database", path); free(target); diff --git a/sha1_name.c b/sha1_name.c index 3f6b77ccfa..6d7cd78381 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -157,7 +157,7 @@ static int get_short_sha1(const char *name, int len, unsigned char *sha1, char canonical[40]; unsigned char res[20]; - if (len < MINIMUM_ABBREV) + if (len < MINIMUM_ABBREV || len > 40) return -1; hashclr(res); memset(canonical, 'x', 40); @@ -247,26 +247,25 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) NULL }; static const char *warning = "warning: refname '%.*s' is ambiguous.\n"; - const char **p, *pathname; - char *real_path = NULL; - int refs_found = 0, am; - unsigned long at_time = (unsigned long)-1; + const char **p, *ref; + char *real_ref = NULL; + int refs_found = 0; + int at, reflog_len; unsigned char *this_result; unsigned char sha1_from_ref[20]; if (len == 40 && !get_sha1_hex(str, sha1)) return 0; - /* At a given period of time? "@{2 hours ago}" */ - for (am = 1; am < len - 1; am++) { - if (str[am] == '@' && str[am+1] == '{' && str[len-1] == '}') { - int date_len = len - am - 3; - char *date_spec = xmalloc(date_len + 1); - strlcpy(date_spec, str + am + 2, date_len + 1); - at_time = approxidate(date_spec); - free(date_spec); - len = am; - break; + /* basic@{time or number} format to query ref-log */ + reflog_len = at = 0; + if (str[len-1] == '}') { + for (at = 1; at < len - 1; at++) { + if (str[at] == '@' && str[at+1] == '{') { + reflog_len = (len-1) - (at+2); + len = at; + break; + } } } @@ -276,10 +275,10 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) for (p = fmt; *p; p++) { this_result = refs_found ? sha1_from_ref : sha1; - pathname = resolve_ref(git_path(*p, len, str), this_result, 1); - if (pathname) { + ref = resolve_ref(mkpath(*p, len, str), this_result, 1, NULL); + if (ref) { if (!refs_found++) - real_path = strdup(pathname); + real_ref = xstrdup(ref); if (!warn_ambiguous_refs) break; } @@ -291,14 +290,25 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) if (warn_ambiguous_refs && refs_found > 1) fprintf(stderr, warning, len, str); - if (at_time != (unsigned long)-1) { - read_ref_at( - real_path + strlen(git_path(".")) - 1, - at_time, - sha1); + if (reflog_len) { + /* Is it asking for N-th entry, or approxidate? */ + int nth, i; + unsigned long at_time; + for (i = nth = 0; 0 <= nth && i < reflog_len; i++) { + char ch = str[at+2+i]; + if ('0' <= ch && ch <= '9') + nth = nth * 10 + ch - '0'; + else + nth = -1; + } + if (0 <= nth) + at_time = 0; + else + at_time = approxidate(str + at + 2); + read_ref_at(real_ref, at_time, nth, sha1); } - free(real_path); + free(real_ref); return 0; } @@ -431,6 +441,26 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) return 0; } +static int get_describe_name(const char *name, int len, unsigned char *sha1) +{ + const char *cp; + + for (cp = name + len - 1; name + 2 <= cp; cp--) { + char ch = *cp; + if (hexval(ch) & ~0377) { + /* We must be looking at g in "SOMETHING-g" + * for it to be describe output. + */ + if (ch == 'g' && cp[-1] == '-') { + cp++; + len -= cp - name; + return get_short_sha1(cp, len, sha1, 1); + } + } + } + return -1; +} + static int get_sha1_1(const char *name, int len, unsigned char *sha1) { int ret, has_suffix; @@ -472,6 +502,12 @@ static int get_sha1_1(const char *name, int len, unsigned char *sha1) ret = get_sha1_basic(name, len, sha1); if (!ret) return 0; + + /* It could be describe output that is "SOMETHING-gXXXX" */ + ret = get_describe_name(name, len, sha1); + if (!ret) + return 0; + return get_short_sha1(name, len, sha1, 0); } diff --git a/shallow.c b/shallow.c new file mode 100644 index 0000000000..3d53d17423 --- /dev/null +++ b/shallow.c @@ -0,0 +1,104 @@ +#include "cache.h" +#include "commit.h" +#include "tag.h" + +static int is_shallow = -1; + +int register_shallow(const unsigned char *sha1) +{ + struct commit_graft *graft = + xmalloc(sizeof(struct commit_graft)); + struct commit *commit = lookup_commit(sha1); + + hashcpy(graft->sha1, sha1); + graft->nr_parent = -1; + if (commit && commit->object.parsed) + commit->parents = NULL; + return register_commit_graft(graft, 0); +} + +int is_repository_shallow() +{ + FILE *fp; + char buf[1024]; + + if (is_shallow >= 0) + return is_shallow; + + fp = fopen(git_path("shallow"), "r"); + if (!fp) { + is_shallow = 0; + return is_shallow; + } + is_shallow = 1; + + while (fgets(buf, sizeof(buf), fp)) { + unsigned char sha1[20]; + if (get_sha1_hex(buf, sha1)) + die("bad shallow line: %s", buf); + register_shallow(sha1); + } + fclose(fp); + return is_shallow; +} + +struct commit_list *get_shallow_commits(struct object_array *heads, int depth, + int shallow_flag, int not_shallow_flag) +{ + int i = 0, cur_depth = 0; + struct commit_list *result = NULL; + struct object_array stack = {0, 0, NULL}; + struct commit *commit = NULL; + + while (commit || i < heads->nr || stack.nr) { + struct commit_list *p; + if (!commit) { + if (i < heads->nr) { + commit = (struct commit *) + deref_tag(heads->objects[i++].item, NULL, 0); + if (commit->object.type != OBJ_COMMIT) { + commit = NULL; + continue; + } + if (!commit->util) + commit->util = xmalloc(sizeof(int)); + *(int *)commit->util = 0; + cur_depth = 0; + } else { + commit = (struct commit *) + stack.objects[--stack.nr].item; + cur_depth = *(int *)commit->util; + } + } + parse_commit(commit); + commit->object.flags |= not_shallow_flag; + cur_depth++; + for (p = commit->parents, commit = NULL; p; p = p->next) { + if (!p->item->util) { + int *pointer = xmalloc(sizeof(int)); + p->item->util = pointer; + *pointer = cur_depth; + } else { + int *pointer = p->item->util; + if (cur_depth >= *pointer) + continue; + *pointer = cur_depth; + } + if (cur_depth < depth) { + if (p->next) + add_object_array(&p->item->object, + NULL, &stack); + else { + commit = p->item; + cur_depth = *(int *)commit->util; + } + } else { + commit_list_insert(p->item, &result); + p->item->object.flags |= shallow_flag; + } + } + } + + return result; +} + diff --git a/show-index.c b/show-index.c index c21d660b62..a30a2de5d1 100644 --- a/show-index.c +++ b/show-index.c @@ -8,7 +8,7 @@ int main(int argc, char **argv) static unsigned int top_index[256]; if (fread(top_index, sizeof(top_index), 1, stdin) != 1) - die("unable to read idex"); + die("unable to read index"); nr = 0; for (i = 0; i < 256; i++) { unsigned n = ntohl(top_index[i]); diff --git a/sideband.c b/sideband.c new file mode 100644 index 0000000000..277fa3c10d --- /dev/null +++ b/sideband.c @@ -0,0 +1,78 @@ +#include "pkt-line.h" +#include "sideband.h" + +/* + * Receive multiplexed output stream over git native protocol. + * in_stream is the input stream from the remote, which carries data + * in pkt_line format with band designator. Demultiplex it into out + * and err and return error appropriately. Band #1 carries the + * primary payload. Things coming over band #2 is not necessarily + * error; they are usually informative message on the standard error + * stream, aka "verbose"). A message over band #3 is a signal that + * the remote died unexpectedly. A flush() concludes the stream. + */ +int recv_sideband(const char *me, int in_stream, int out, int err) +{ + char buf[7 + LARGE_PACKET_MAX + 1]; + strcpy(buf, "remote:"); + while (1) { + int band, len; + len = packet_read_line(in_stream, buf+7, LARGE_PACKET_MAX); + if (len == 0) + break; + if (len < 1) { + len = sprintf(buf, "%s: protocol error: no band designator\n", me); + safe_write(err, buf, len); + return SIDEBAND_PROTOCOL_ERROR; + } + band = buf[7] & 0xff; + len--; + switch (band) { + case 3: + buf[7] = ' '; + buf[8+len] = '\n'; + safe_write(err, buf, 8+len+1); + return SIDEBAND_REMOTE_ERROR; + case 2: + buf[7] = ' '; + safe_write(err, buf, 8+len); + continue; + case 1: + safe_write(out, buf+8, len); + continue; + default: + len = sprintf(buf, + "%s: protocol error: bad band #%d\n", + me, band); + safe_write(err, buf, len); + return SIDEBAND_PROTOCOL_ERROR; + } + } + return 0; +} + +/* + * fd is connected to the remote side; send the sideband data + * over multiplexed packet stream. + */ +ssize_t send_sideband(int fd, int band, const char *data, ssize_t sz, int packet_max) +{ + ssize_t ssz = sz; + const char *p = data; + + while (sz) { + unsigned n; + char hdr[5]; + + n = sz; + if (packet_max - 5 < n) + n = packet_max - 5; + sprintf(hdr, "%04x", n + 5); + hdr[4] = band; + safe_write(fd, hdr, 5); + safe_write(fd, p, n); + p += n; + sz -= n; + } + return ssz; +} diff --git a/sideband.h b/sideband.h new file mode 100644 index 0000000000..a84b6917c7 --- /dev/null +++ b/sideband.h @@ -0,0 +1,13 @@ +#ifndef SIDEBAND_H +#define SIDEBAND_H + +#define SIDEBAND_PROTOCOL_ERROR -2 +#define SIDEBAND_REMOTE_ERROR -1 + +#define DEFAULT_PACKET_MAX 1000 +#define LARGE_PACKET_MAX 65520 + +int recv_sideband(const char *me, int in_stream, int out, int err); +ssize_t send_sideband(int fd, int band, const char *data, ssize_t sz, int packet_max); + +#endif diff --git a/ssh-fetch.c b/ssh-fetch.c index b006c5c980..4c172b6824 100644 --- a/ssh-fetch.c +++ b/ssh-fetch.c @@ -20,22 +20,6 @@ static int fd_out; static unsigned char remote_version; static unsigned char local_version = 1; -static ssize_t force_write(int fd, void *buffer, size_t length) -{ - ssize_t ret = 0; - while (ret < length) { - ssize_t size = write(fd, (char *) buffer + ret, length - ret); - if (size < 0) { - return size; - } - if (size == 0) { - return ret; - } - ret += size; - } - return ret; -} - static int prefetches; static struct object_list *in_transit; @@ -53,8 +37,9 @@ void prefetch(unsigned char *sha1) node->item = lookup_unknown_object(sha1); *end_of_transit = node; end_of_transit = &node->next; - force_write(fd_out, &type, 1); - force_write(fd_out, sha1, 20); + /* XXX: what if these writes fail? */ + write_in_full(fd_out, &type, 1); + write_in_full(fd_out, sha1, 20); prefetches++; } @@ -82,7 +67,7 @@ int fetch(unsigned char *sha1) remote = conn_buf[0]; memmove(conn_buf, conn_buf + 1, --conn_buf_posn); } else { - if (read(fd_in, &remote, 1) < 1) + if (xread(fd_in, &remote, 1) < 1) return -1; } /* fprintf(stderr, "Got %d\n", remote); */ @@ -97,9 +82,11 @@ int fetch(unsigned char *sha1) static int get_version(void) { char type = 'v'; - write(fd_out, &type, 1); - write(fd_out, &local_version, 1); - if (read(fd_in, &remote_version, 1) < 1) { + if (write_in_full(fd_out, &type, 1) != 1 || + write_in_full(fd_out, &local_version, 1)) { + return error("Couldn't request version from remote end"); + } + if (xread(fd_in, &remote_version, 1) < 1) { return error("Couldn't read version from remote end"); } return 0; @@ -109,12 +96,17 @@ int fetch_ref(char *ref, unsigned char *sha1) { signed char remote; char type = 'r'; - write(fd_out, &type, 1); - write(fd_out, ref, strlen(ref) + 1); - read(fd_in, &remote, 1); + int length = strlen(ref) + 1; + if (write_in_full(fd_out, &type, 1) != 1 || + write_in_full(fd_out, ref, length) != length) + return -1; + + if (read_in_full(fd_in, &remote, 1) != 1) + return -1; if (remote < 0) return remote; - read(fd_in, sha1, 20); + if (read_in_full(fd_in, sha1, 20) != 20) + return -1; return 0; } diff --git a/ssh-upload.c b/ssh-upload.c index 20b15eab57..2f04572787 100644 --- a/ssh-upload.c +++ b/ssh-upload.c @@ -12,8 +12,6 @@ #include "rsh.h" #include "refs.h" -#include <string.h> - static unsigned char local_version = 1; static unsigned char remote_version; @@ -23,17 +21,14 @@ static int serve_object(int fd_in, int fd_out) { ssize_t size; unsigned char sha1[20]; signed char remote; - int posn = 0; - do { - size = read(fd_in, sha1 + posn, 20 - posn); - if (size < 0) { - perror("git-ssh-upload: read "); - return -1; - } - if (!size) - return -1; - posn += size; - } while (posn < 20); + + size = read_in_full(fd_in, sha1, 20); + if (size < 0) { + perror("git-ssh-upload: read "); + return -1; + } + if (!size) + return -1; if (verbose) fprintf(stderr, "Serving %s\n", sha1_to_hex(sha1)); @@ -46,7 +41,8 @@ static int serve_object(int fd_in, int fd_out) { remote = -1; } - write(fd_out, &remote, 1); + if (write_in_full(fd_out, &remote, 1) != 1) + return 0; if (remote < 0) return 0; @@ -56,9 +52,9 @@ static int serve_object(int fd_in, int fd_out) { static int serve_version(int fd_in, int fd_out) { - if (read(fd_in, &remote_version, 1) < 1) + if (xread(fd_in, &remote_version, 1) < 1) return -1; - write(fd_out, &local_version, 1); + write_in_full(fd_out, &local_version, 1); return 0; } @@ -69,7 +65,7 @@ static int serve_ref(int fd_in, int fd_out) int posn = 0; signed char remote = 0; do { - if (read(fd_in, ref + posn, 1) < 1) + if (posn >= PATH_MAX || xread(fd_in, ref + posn, 1) < 1) return -1; posn++; } while (ref[posn - 1]); @@ -79,10 +75,11 @@ static int serve_ref(int fd_in, int fd_out) if (get_ref_sha1(ref, sha1)) remote = -1; - write(fd_out, &remote, 1); + if (write_in_full(fd_out, &remote, 1) != 1) + return 0; if (remote) return 0; - write(fd_out, sha1, 20); + write_in_full(fd_out, sha1, 20); return 0; } @@ -91,7 +88,7 @@ static void service(int fd_in, int fd_out) { char type; int retval; do { - retval = read(fd_in, &type, 1); + retval = xread(fd_in, &type, 1); if (retval < 1) { if (retval < 0) perror("git-ssh-upload: read "); @@ -1,7 +1,5 @@ -#include <stdio.h> -#include <stdlib.h> -#include "strbuf.h" #include "cache.h" +#include "strbuf.h" void strbuf_init(struct strbuf *sb) { sb->buf = NULL; diff --git a/t/Makefile b/t/Makefile index 89835093fb..19e38508a7 100644 --- a/t/Makefile +++ b/t/Makefile @@ -13,10 +13,6 @@ SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) TSVN = $(wildcard t91[0-9][0-9]-*.sh) -ifdef NO_PYTHON - GIT_TEST_OPTS += --no-python -endif - all: $(T) clean $(T): @@ -27,12 +23,8 @@ clean: # we can test NO_OPTIMIZE_COMMITS independently of LC_ALL full-svn-test: - $(MAKE) $(TSVN) GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C - $(MAKE) $(TSVN) GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C - $(MAKE) $(TSVN) GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ - LC_ALL=en_US.UTF-8 - $(MAKE) $(TSVN) GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ - LC_ALL=en_US.UTF-8 + $(MAKE) $(TSVN) GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C + $(MAKE) $(TSVN) GIT_SVN_NO_OPTIMIZE_COMMITS=0 LC_ALL=en_US.UTF-8 .PHONY: $(T) clean .NOTPARALLEL: @@ -18,7 +18,7 @@ The easiest way to run tests is to say "make". This runs all the tests. *** t0000-basic.sh *** - * ok 1: .git/objects should be empty after git-init-db in an empty repo. + * ok 1: .git/objects should be empty after git-init in an empty repo. * ok 2: .git/objects should have 256 subdirectories. * ok 3: git-update-index without --add should fail adding. ... @@ -74,6 +74,8 @@ First digit tells the family: 5 - the pull and exporting commands 6 - the revision tree commands (even e.g. merge-base) 7 - the porcelainish commands concerning the working tree + 8 - the porcelainish commands concerning forensics + 9 - the git tools Second digit tells the particular command we are testing. diff --git a/t/annotate-tests.sh b/t/annotate-tests.sh index 8baf2fef69..b5ceba4acf 100644 --- a/t/annotate-tests.sh +++ b/t/annotate-tests.sh @@ -4,6 +4,7 @@ check_count () { head= case "$1" in -h) head="$2"; shift; shift ;; esac + echo "$PROG file $head" >&4 $PROG file $head >.result || return 1 cat .result | perl -e ' my %expect = (@ARGV); diff --git a/t/lib-git-svn.sh b/t/lib-git-svn.sh index 29a1e72c61..a0f2814083 100644 --- a/t/lib-git-svn.sh +++ b/t/lib-git-svn.sh @@ -11,21 +11,6 @@ GIT_DIR=$PWD/.git GIT_SVN_DIR=$GIT_DIR/svn/git-svn SVN_TREE=$GIT_SVN_DIR/svn-tree -perl -e 'use SVN::Core' >/dev/null 2>&1 -if test $? -ne 0 -then - echo 'Perl SVN libraries not found, tests requiring those will be skipped' - GIT_SVN_NO_LIB=1 -fi - -svnadmin >/dev/null 2>&1 -if test $? -ne 1 -then - test_expect_success 'skipping git-svn tests, svnadmin not found' : - test_done - exit -fi - svn >/dev/null 2>&1 if test $? -ne 1 then @@ -36,15 +21,27 @@ fi svnrepo=$PWD/svnrepo -set -e - -if svnadmin create --help | grep fs-type >/dev/null +perl -w -e " +use SVN::Core; +use SVN::Repos; +\$SVN::Core::VERSION gt '1.1.0' or exit(42); +system(qw/svnadmin create --fs-type fsfs/, '$svnrepo') == 0 or exit(41); +" +x=$? +if test $x -ne 0 then - svnadmin create --fs-type fsfs "$svnrepo" -else - svnadmin create "$svnrepo" + if test $x -eq 42; then + err='Perl SVN libraries must be >= 1.1.0' + elif test $x -eq 41; then + err='svnadmin failed to create fsfs repository' + else + err='Perl SVN libraries not found or unusable, skipping test' + fi + test_expect_success "$err" : + test_done + exit fi -svnrepo="file://$svnrepo/test-git-svn" +svnrepo="file://$svnrepo" diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index 2c9bbb59b0..186de70243 100755 --- a/t/t0000-basic.sh +++ b/t/t0000-basic.sh @@ -19,11 +19,7 @@ modification *should* take notice and update the test vectors here. ' ################################################################ -# It appears that people are getting bitten by not installing -# 'merge' (usually part of RCS package in binary distributions) -# or have too old python without subprocess. Check them and error -# out before running any tests. Also catch the bogosity of trying -# to run tests without building while we are at it. +# It appears that people try to run tests without building... ../git >/dev/null if test $? != 1 @@ -32,29 +28,15 @@ then exit 1 fi -merge >/dev/null 2>/dev/null -if test $? = 127 -then - echo >&2 'You do not seem to have "merge" installed. -Please check INSTALL document.' - exit 1 -fi - . ./test-lib.sh -test "$no_python" || "$PYTHON" -c 'import subprocess' || { - echo >&2 'Your python seem to lack "subprocess" module. -Please check INSTALL document.' - exit 1 -} - ################################################################ -# init-db has been done in an empty repository. +# git-init has been done in an empty repository. # make sure it is empty. find .git/objects -type f -print >should-be-empty test_expect_success \ - '.git/objects should be empty after git-init-db in an empty repo.' \ + '.git/objects should be empty after git-init in an empty repo.' \ 'cmp -s /dev/null should-be-empty' # also it should have 2 subdirectories; no fan-out anymore, pack, and info. @@ -209,6 +191,28 @@ test_expect_success \ 'validate object ID for a known tree.' \ 'test "$ptree" = 3c5e5399f3a333eddecce7a9b9465b63f65f51e2' +cat >badobjects <<EOF +100644 blob 1000000000000000000000000000000000000000 dir/file1 +100644 blob 2000000000000000000000000000000000000000 dir/file2 +100644 blob 3000000000000000000000000000000000000000 dir/file3 +100644 blob 4000000000000000000000000000000000000000 dir/file4 +100644 blob 5000000000000000000000000000000000000000 dir/file5 +EOF + +rm .git/index +test_expect_success \ + 'put invalid objects into the index.' \ + 'git-update-index --index-info < badobjects' + +test_expect_failure \ + 'writing this tree without --missing-ok.' \ + 'git-write-tree' + +test_expect_success \ + 'writing this tree with --missing-ok.' \ + 'git-write-tree --missing-ok' + + ################################################################ rm .git/index test_expect_success \ @@ -268,4 +272,13 @@ test_expect_success \ wc -l) && test $numparent = 1' +test_expect_success 'update-index D/F conflict' ' + mv path0 tmp && + mv path2 path0 && + mv tmp path2 && + git update-index --add --replace path2 path0/file2 && + numpath0=$(git ls-files path0 | wc -l) && + test $numpath0 = 1 +' + test_done diff --git a/t/t1004-read-tree-m-u-wf.sh b/t/t1004-read-tree-m-u-wf.sh new file mode 100755 index 0000000000..4f664f6adf --- /dev/null +++ b/t/t1004-read-tree-m-u-wf.sh @@ -0,0 +1,119 @@ +#!/bin/sh + +test_description='read-tree -m -u checks working tree files' + +. ./test-lib.sh + +# two-tree test + +test_expect_success 'two-way setup' ' + + mkdir subdir && + echo >file1 file one && + echo >file2 file two && + echo >subdir/file1 file one in subdirectory && + echo >subdir/file2 file two in subdirectory && + git update-index --add file1 file2 subdir/file1 subdir/file2 && + git commit -m initial && + + git branch side && + git tag -f branch-point && + + echo file2 is not tracked on the master anymore && + rm -f file2 subdir/file2 && + git update-index --remove file2 subdir/file2 && + git commit -a -m "master removes file2 and subdir/file2" +' + +test_expect_success 'two-way not clobbering' ' + + echo >file2 master creates untracked file2 && + echo >subdir/file2 master creates untracked subdir/file2 && + if err=`git read-tree -m -u master side 2>&1` + then + echo should have complained + false + else + echo "happy to see $err" + fi +' + +echo file2 >.gitignore + +test_expect_success 'two-way with incorrect --exclude-per-directory (1)' ' + + if err=`git read-tree -m --exclude-per-directory=.gitignore master side 2>&1` + then + echo should have complained + false + else + echo "happy to see $err" + fi +' + +test_expect_success 'two-way with incorrect --exclude-per-directory (2)' ' + + if err=`git read-tree -m -u --exclude-per-directory=foo --exclude-per-directory=.gitignore master side 2>&1` + then + echo should have complained + false + else + echo "happy to see $err" + fi +' + +test_expect_success 'two-way clobbering a ignored file' ' + + git read-tree -m -u --exclude-per-directory=.gitignore master side +' + +rm -f .gitignore + +# three-tree test + +test_expect_success 'three-way not complaining on an untracked path in both' ' + + rm -f file2 subdir/file2 && + git checkout side && + echo >file3 file three && + echo >subdir/file3 file three && + git update-index --add file3 subdir/file3 && + git commit -a -m "side adds file3 and removes file2" && + + git checkout master && + echo >file2 file two is untracked on the master side && + echo >subdir/file2 file two is untracked on the master side && + + git-read-tree -m -u branch-point master side +' + +test_expect_success 'three-way not cloberring a working tree file' ' + + git reset --hard && + rm -f file2 subdir/file2 file3 subdir/file3 && + git checkout master && + echo >file3 file three created in master, untracked && + echo >subdir/file3 file three created in master, untracked && + if err=`git read-tree -m -u branch-point master side 2>&1` + then + echo should have complained + false + else + echo "happy to see $err" + fi +' + +echo >.gitignore file3 + +test_expect_success 'three-way not complaining on an untracked file' ' + + git reset --hard && + rm -f file2 subdir/file2 file3 subdir/file3 && + git checkout master && + echo >file3 file three created in master, untracked && + echo >subdir/file3 file three created in master, untracked && + + git read-tree -m -u --exclude-per-directory=.gitignore branch-point master side +' + +test_done diff --git a/t/t1200-tutorial.sh b/t/t1200-tutorial.sh index c7db20e7f3..eebe643bda 100755 --- a/t/t1200-tutorial.sh +++ b/t/t1200-tutorial.sh @@ -3,7 +3,7 @@ # Copyright (c) 2005 Johannes Schindelin # -test_description='Test git-rev-parse with different parent options' +test_description='A simple turial in the form of a test case' . ./test-lib.sh @@ -37,8 +37,6 @@ test_expect_success 'tree' "test 8988da15d077d4829fc51d8544c097def6644dbb = $tre output="$(echo "Initial commit" | git-commit-tree $(git-write-tree) 2>&1 > .git/refs/heads/master)" -test_expect_success 'commit' "test 'Committing initial tree 8988da15d077d4829fc51d8544c097def6644dbb' = \"$output\"" - git-diff-index -p HEAD > diff.output test_expect_success 'git-diff-index -p HEAD' 'cmp diff.expect diff.output' diff --git a/t/t1300-repo-config.sh b/t/t1300-repo-config.sh index 0de2497746..60acdd368b 100755 --- a/t/t1300-repo-config.sh +++ b/t/t1300-repo-config.sh @@ -265,6 +265,16 @@ EOF test_expect_success '--get-regexp' \ 'git-repo-config --get-regexp in > output && cmp output expect' +git-repo-config --add nextsection.nonewline "wow4 for you" + +cat > expect << EOF +wow2 for me +wow4 for you +EOF + +test_expect_success '--add' \ + 'git-repo-config --get-all nextsection.nonewline > output && cmp output expect' + cat > .git/config << EOF [novalue] variable @@ -333,5 +343,80 @@ EOF test_expect_success '--set in alternative GIT_CONFIG' 'cmp other-config expect' +cat > .git/config << EOF +# Hallo + #Bello +[branch "eins"] + x = 1 +[branch.eins] + y = 1 + [branch "1 234 blabl/a"] +weird +EOF + +test_expect_success "rename section" \ + "git-repo-config --rename-section branch.eins branch.zwei" + +cat > expect << EOF +# Hallo + #Bello +[branch "zwei"] + x = 1 +[branch "zwei"] + y = 1 + [branch "1 234 blabl/a"] +weird +EOF + +test_expect_success "rename succeeded" "diff -u expect .git/config" + +test_expect_failure "rename non-existing section" \ + 'git-repo-config --rename-section branch."world domination" branch.drei' + +test_expect_success "rename succeeded" "diff -u expect .git/config" + +test_expect_success "rename another section" \ + 'git-repo-config --rename-section branch."1 234 blabl/a" branch.drei' + +cat > expect << EOF +# Hallo + #Bello +[branch "zwei"] + x = 1 +[branch "zwei"] + y = 1 +[branch "drei"] +weird +EOF + +test_expect_success "rename succeeded" "diff -u expect .git/config" + +test_expect_success numbers ' + + git-repo-config kilo.gram 1k && + git-repo-config mega.ton 1m && + k=$(git-repo-config --int --get kilo.gram) && + test z1024 = "z$k" && + m=$(git-repo-config --int --get mega.ton) && + test z1048576 = "z$m" +' + +rm .git/config + +git-repo-config quote.leading " test" +git-repo-config quote.ending "test " +git-repo-config quote.semicolon "test;test" +git-repo-config quote.hash "test#test" + +cat > expect << EOF +[quote] + leading = " test" + ending = "test " + semicolon = "test;test" + hash = "test#test" +EOF + +test_expect_success 'quoting' 'cmp .git/config expect' + test_done diff --git a/t/t1400-update-ref.sh b/t/t1400-update-ref.sh index ddc80bbeae..5637cb5eac 100755 --- a/t/t1400-update-ref.sh +++ b/t/t1400-update-ref.sh @@ -19,70 +19,67 @@ n=$n_dir/fixes test_expect_success \ "create $m" \ - 'git-update-ref $m $A && - test $A = $(cat .git/$m)' + "git-update-ref $m $A && + test $A"' = $(cat .git/'"$m"')' test_expect_success \ "create $m" \ - 'git-update-ref $m $B $A && - test $B = $(cat .git/$m)' + "git-update-ref $m $B $A && + test $B"' = $(cat .git/'"$m"')' rm -f .git/$m test_expect_success \ "fail to create $n" \ - 'touch .git/$n_dir - git-update-ref $n $A >out 2>err - test $? = 1 && - test "" = "$(cat out)" && - grep "error: unable to resolve reference" err && - grep $n err' + "touch .git/$n_dir + git-update-ref $n $A >out 2>err"' + test $? != 0' rm -f .git/$n_dir out err test_expect_success \ "create $m (by HEAD)" \ - 'git-update-ref HEAD $A && - test $A = $(cat .git/$m)' + "git-update-ref HEAD $A && + test $A"' = $(cat .git/'"$m"')' test_expect_success \ "create $m (by HEAD)" \ - 'git-update-ref HEAD $B $A && - test $B = $(cat .git/$m)' + "git-update-ref HEAD $B $A && + test $B"' = $(cat .git/'"$m"')' rm -f .git/$m test_expect_failure \ '(not) create HEAD with old sha1' \ - 'git-update-ref HEAD $A $B' + "git-update-ref HEAD $A $B" test_expect_failure \ "(not) prior created .git/$m" \ - 'test -f .git/$m' + "test -f .git/$m" rm -f .git/$m test_expect_success \ "create HEAD" \ - 'git-update-ref HEAD $A' + "git-update-ref HEAD $A" test_expect_failure \ '(not) change HEAD with wrong SHA1' \ - 'git-update-ref HEAD $B $Z' + "git-update-ref HEAD $B $Z" test_expect_failure \ "(not) changed .git/$m" \ - 'test $B = $(cat .git/$m)' + "test $B"' = $(cat .git/'"$m"')' rm -f .git/$m -mkdir -p .git/logs/refs/heads -touch .git/logs/refs/heads/master +: a repository with working tree always has reflog these days... +: >.git/logs/refs/heads/master test_expect_success \ "create $m (logged by touch)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:30" \ - git-update-ref HEAD $A -m "Initial Creation" && - test $A = $(cat .git/$m)' + git-update-ref HEAD '"$A"' -m "Initial Creation" && + test '"$A"' = $(cat .git/'"$m"')' test_expect_success \ "update $m (logged by touch)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:31" \ - git-update-ref HEAD $B $A -m "Switch" && - test $B = $(cat .git/$m)' + git-update-ref HEAD'" $B $A "'-m "Switch" && + test '"$B"' = $(cat .git/'"$m"')' test_expect_success \ "set $m (logged by touch)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:41" \ - git-update-ref HEAD $A && - test $A = $(cat .git/$m)' + git-update-ref HEAD'" $A && + test $A"' = $(cat .git/'"$m"')' cat >expect <<EOF $Z $A $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000 Initial Creation @@ -91,7 +88,7 @@ $B $A $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150860 +0000 EOF test_expect_success \ "verifying $m's log" \ - 'diff expect .git/logs/$m' + "diff expect .git/logs/$m" rm -rf .git/$m .git/logs expect test_expect_success \ @@ -102,18 +99,18 @@ test_expect_success \ test_expect_success \ "create $m (logged by config)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:32" \ - git-update-ref HEAD $A -m "Initial Creation" && - test $A = $(cat .git/$m)' + git-update-ref HEAD'" $A "'-m "Initial Creation" && + test '"$A"' = $(cat .git/'"$m"')' test_expect_success \ "update $m (logged by config)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:33" \ - git-update-ref HEAD $B $A -m "Switch" && - test $B = $(cat .git/$m)' + git-update-ref HEAD'" $B $A "'-m "Switch" && + test '"$B"' = $(cat .git/'"$m"')' test_expect_success \ "set $m (logged by config)" \ 'GIT_COMMITTER_DATE="2005-05-26 23:43" \ - git-update-ref HEAD $A && - test $A = $(cat .git/$m)' + git-update-ref HEAD '"$A && + test $A"' = $(cat .git/'"$m"')' cat >expect <<EOF $Z $A $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150320 +0000 Initial Creation @@ -140,50 +137,50 @@ test_expect_success \ 'Query "master@{May 25 2005}" (before history)' \ 'rm -f o e git-rev-parse --verify "master@{May 25 2005}" >o 2>e && - test $C = $(cat o) && - test "warning: Log .git/logs/$m only goes back to $ed." = "$(cat e)"' + test '"$C"' = $(cat o) && + test "warning: Log .git/logs/'"$m only goes back to $ed"'." = "$(cat e)"' test_expect_success \ "Query master@{2005-05-25} (before history)" \ 'rm -f o e git-rev-parse --verify master@{2005-05-25} >o 2>e && - test $C = $(cat o) && - echo test "warning: Log .git/logs/$m only goes back to $ed." = "$(cat e)"' + test '"$C"' = $(cat o) && + echo test "warning: Log .git/logs/'"$m only goes back to $ed"'." = "$(cat e)"' test_expect_success \ 'Query "master@{May 26 2005 23:31:59}" (1 second before history)' \ 'rm -f o e git-rev-parse --verify "master@{May 26 2005 23:31:59}" >o 2>e && - test $C = $(cat o) && - test "warning: Log .git/logs/$m only goes back to $ed." = "$(cat e)"' + test '"$C"' = $(cat o) && + test "warning: Log .git/logs/'"$m only goes back to $ed"'." = "$(cat e)"' test_expect_success \ 'Query "master@{May 26 2005 23:32:00}" (exactly history start)' \ 'rm -f o e git-rev-parse --verify "master@{May 26 2005 23:32:00}" >o 2>e && - test $A = $(cat o) && + test '"$A"' = $(cat o) && test "" = "$(cat e)"' test_expect_success \ 'Query "master@{2005-05-26 23:33:01}" (middle of history with gap)' \ 'rm -f o e git-rev-parse --verify "master@{2005-05-26 23:33:01}" >o 2>e && - test $B = $(cat o) && - test "warning: Log .git/logs/$m has gap after $gd." = "$(cat e)"' + test '"$B"' = $(cat o) && + test "warning: Log .git/logs/'"$m has gap after $gd"'." = "$(cat e)"' test_expect_success \ 'Query "master@{2005-05-26 23:38:00}" (middle of history)' \ 'rm -f o e git-rev-parse --verify "master@{2005-05-26 23:38:00}" >o 2>e && - test $Z = $(cat o) && + test '"$Z"' = $(cat o) && test "" = "$(cat e)"' test_expect_success \ 'Query "master@{2005-05-26 23:43:00}" (exact end of history)' \ 'rm -f o e git-rev-parse --verify "master@{2005-05-26 23:43:00}" >o 2>e && - test $E = $(cat o) && + test '"$E"' = $(cat o) && test "" = "$(cat e)"' test_expect_success \ 'Query "master@{2005-05-28}" (past end of history)' \ 'rm -f o e git-rev-parse --verify "master@{2005-05-28}" >o 2>e && - test $D = $(cat o) && - test "warning: Log .git/logs/$m unexpectedly ended on $ld." = "$(cat e)"' + test '"$D"' = $(cat o) && + test "warning: Log .git/logs/'"$m unexpectedly ended on $ld"'." = "$(cat e)"' rm -f .git/$m .git/logs/$m expect @@ -221,7 +218,7 @@ $h_FIXED $h_MERGED $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117151100 +0000 c EOF test_expect_success \ 'git-commit logged updates' \ - 'diff expect .git/logs/$m' + "diff expect .git/logs/$m" unset h_TEST h_OTHER h_FIXED h_MERGED test_expect_success \ diff --git a/t/t1410-reflog.sh b/t/t1410-reflog.sh new file mode 100755 index 0000000000..8e8d526ef2 --- /dev/null +++ b/t/t1410-reflog.sh @@ -0,0 +1,178 @@ +#!/bin/sh +# +# Copyright (c) 2007 Junio C Hamano +# + +test_description='Test prune and reflog expiration' +. ./test-lib.sh + +check_have () { + gaah= && + for N in "$@" + do + eval "o=\$$N" && git cat-file -t $o || { + echo Gaah $N + gaah=$N + break + } + done && + test -z "$gaah" +} + +check_fsck () { + output=$(git fsck-objects --full) + case "$1" in + '') + test -z "$output" ;; + *) + echo "$output" | grep "$1" ;; + esac +} + +corrupt () { + aa=${1%??????????????????????????????????????} zz=${1#??} + mv .git/objects/$aa/$zz .git/$aa$zz +} + +recover () { + aa=${1%??????????????????????????????????????} zz=${1#??} + mkdir -p .git/objects/$aa + mv .git/$aa$zz .git/objects/$aa/$zz +} + +check_dont_have () { + gaah= && + for N in "$@" + do + eval "o=\$$N" + git cat-file -t $o && { + echo Gaah $N + gaah=$N + break + } + done + test -z "$gaah" +} + +test_expect_success setup ' + mkdir -p A/B && + echo rat >C && + echo ox >A/D && + echo tiger >A/B/E && + git add . && + + test_tick && git commit -m rabbit && + H=`git rev-parse --verify HEAD` && + A=`git rev-parse --verify HEAD:A` && + B=`git rev-parse --verify HEAD:A/B` && + C=`git rev-parse --verify HEAD:C` && + D=`git rev-parse --verify HEAD:A/D` && + E=`git rev-parse --verify HEAD:A/B/E` && + check_fsck && + + chmod +x C && + ( test "`git repo-config --bool core.filemode`" != false || + echo executable >>C ) && + git add C && + test_tick && git commit -m dragon && + L=`git rev-parse --verify HEAD` && + check_fsck && + + rm -f C A/B/E && + echo snake >F && + echo horse >A/G && + git add F A/G && + test_tick && git commit -a -m sheep && + F=`git rev-parse --verify HEAD:F` && + G=`git rev-parse --verify HEAD:A/G` && + I=`git rev-parse --verify HEAD:A` && + J=`git rev-parse --verify HEAD` && + check_fsck && + + rm -f A/G && + test_tick && git commit -a -m monkey && + K=`git rev-parse --verify HEAD` && + check_fsck && + + check_have A B C D E F G H I J K L && + + git prune && + + check_have A B C D E F G H I J K L && + + check_fsck && + + loglen=$(wc -l <.git/logs/refs/heads/master) && + test $loglen = 4 +' + +test_expect_success rewind ' + test_tick && git reset --hard HEAD~2 && + test -f C && + test -f A/B/E && + ! test -f F && + ! test -f A/G && + + check_have A B C D E F G H I J K L && + + git prune && + + check_have A B C D E F G H I J K L && + + loglen=$(wc -l <.git/logs/refs/heads/master) && + test $loglen = 5 +' + +test_expect_success 'corrupt and check' ' + + corrupt $F && + check_fsck "missing blob $F" + +' + +test_expect_success 'reflog expire --dry-run should not touch reflog' ' + + git reflog expire --dry-run \ + --expire=$(($test_tick - 10000)) \ + --expire-unreachable=$(($test_tick - 10000)) \ + --stale-fix \ + --all && + + loglen=$(wc -l <.git/logs/refs/heads/master) && + test $loglen = 5 && + + check_fsck "missing blob $F" +' + +test_expect_success 'reflog expire' ' + + git reflog expire --verbose \ + --expire=$(($test_tick - 10000)) \ + --expire-unreachable=$(($test_tick - 10000)) \ + --stale-fix \ + --all && + + loglen=$(wc -l <.git/logs/refs/heads/master) && + test $loglen = 2 && + + check_fsck "dangling commit $K" +' + +test_expect_success 'prune and fsck' ' + + git prune && + check_fsck && + + check_have A B C D E H L && + check_dont_have F G I J K + +' + +test_expect_success 'recover and check' ' + + recover $F && + check_fsck "dangling blob $F" + +' + +test_done diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh index 5b04efc89d..bb80e4286a 100755 --- a/t/t3200-branch.sh +++ b/t/t3200-branch.sh @@ -17,13 +17,10 @@ test_expect_success \ git-commit -m "Initial commit." && HEAD=$(git-rev-parse --verify HEAD)' -test_expect_success \ - 'git branch --help should return success now.' \ - 'git-branch --help' - test_expect_failure \ 'git branch --help should not have created a bogus branch' \ - 'test -f .git/refs/heads/--help' + 'git-branch --help </dev/null >/dev/null 2>/dev/null || : + test -f .git/refs/heads/--help' test_expect_success \ 'git branch abc should create a branch' \ @@ -34,7 +31,7 @@ test_expect_success \ 'git-branch a/b/c && test -f .git/refs/heads/a/b/c' cat >expect <<EOF -0000000000000000000000000000000000000000 $HEAD $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000 branch: Created from HEAD +0000000000000000000000000000000000000000 $HEAD $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000 branch: Created from master EOF test_expect_success \ 'git branch -l d/e/f should create a branch and a log' \ @@ -51,7 +48,7 @@ test_expect_success \ test ! -f .git/logs/refs/heads/d/e/f' cat >expect <<EOF -0000000000000000000000000000000000000000 $HEAD $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000 checkout: Created from master^0 +0000000000000000000000000000000000000000 $HEAD $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000 checkout: Created from master EOF test_expect_success \ 'git checkout -b g/h/i -l should create a branch and a log' \ @@ -61,4 +58,63 @@ test_expect_success \ test -f .git/logs/refs/heads/g/h/i && diff expect .git/logs/refs/heads/g/h/i' +test_expect_success \ + 'git branch j/k should work after branch j has been deleted' \ + 'git-branch j && + git-branch -d j && + git-branch j/k' + +test_expect_success \ + 'git branch l should work after branch l/m has been deleted' \ + 'git-branch l/m && + git-branch -d l/m && + git-branch l' + +test_expect_success \ + 'git branch -m m m/m should work' \ + 'git-branch -l m && + git-branch -m m m/m && + test -f .git/logs/refs/heads/m/m' + +test_expect_success \ + 'git branch -m n/n n should work' \ + 'git-branch -l n/n && + git-branch -m n/n n + test -f .git/logs/refs/heads/n' + +test_expect_failure \ + 'git branch -m o/o o should fail when o/p exists' \ + 'git-branch o/o && + git-branch o/p && + git-branch -m o/o o' + +test_expect_failure \ + 'git branch -m q r/q should fail when r exists' \ + 'git-branch q && + git-branch r && + git-branch -m q r/q' + +git-repo-config branch.s/s.dummy Hello + +test_expect_success \ + 'git branch -m s/s s should work when s/t is deleted' \ + 'git-branch -l s/s && + test -f .git/logs/refs/heads/s/s && + git-branch -l s/t && + test -f .git/logs/refs/heads/s/t && + git-branch -d s/t && + git-branch -m s/s s && + test -f .git/logs/refs/heads/s' + +test_expect_success 'config information was renamed, too' \ + "test $(git-repo-config branch.s.dummy) = Hello && + ! git-repo-config branch.s/s/dummy" + +test_expect_failure \ + 'git-branch -m u v should fail when the reflog for u is a symlink' \ + 'git-branch -l u && + mv .git/logs/refs/heads/u real-u && + ln -s real-u .git/logs/refs/heads/u && + git-branch -m u v' + test_done diff --git a/t/t3210-pack-refs.sh b/t/t3210-pack-refs.sh new file mode 100755 index 0000000000..16bdae4f23 --- /dev/null +++ b/t/t3210-pack-refs.sh @@ -0,0 +1,99 @@ +#!/bin/sh +# +# Copyright (c) 2005 Amos Waterland +# Copyright (c) 2006 Christian Couder +# + +test_description='git pack-refs should not change the branch semantic + +This test runs git pack-refs and git show-ref and checks that the branch +semantic is still the same. +' +. ./test-lib.sh + +echo '[core] logallrefupdates = true' >>.git/config + +test_expect_success \ + 'prepare a trivial repository' \ + 'echo Hello > A && + git-update-index --add A && + git-commit -m "Initial commit." && + HEAD=$(git-rev-parse --verify HEAD)' + +SHA1= + +test_expect_success \ + 'see if git show-ref works as expected' \ + 'git-branch a && + SHA1=`cat .git/refs/heads/a` && + echo "$SHA1 refs/heads/a" >expect && + git-show-ref a >result && + diff expect result' + +test_expect_success \ + 'see if a branch still exists when packed' \ + 'git-branch b && + git-pack-refs --all && + rm -f .git/refs/heads/b && + echo "$SHA1 refs/heads/b" >expect && + git-show-ref b >result && + diff expect result' + +test_expect_failure \ + 'git branch c/d should barf if branch c exists' \ + 'git-branch c && + git-pack-refs --all && + rm .git/refs/heads/c && + git-branch c/d' + +test_expect_success \ + 'see if a branch still exists after git pack-refs --prune' \ + 'git-branch e && + git-pack-refs --all --prune && + echo "$SHA1 refs/heads/e" >expect && + git-show-ref e >result && + diff expect result' + +test_expect_failure \ + 'see if git pack-refs --prune remove ref files' \ + 'git-branch f && + git-pack-refs --all --prune && + ls .git/refs/heads/f' + +test_expect_success \ + 'git branch g should work when git branch g/h has been deleted' \ + 'git-branch g/h && + git-pack-refs --all --prune && + git-branch -d g/h && + git-branch g && + git-pack-refs --all && + git-branch -d g' + +test_expect_failure \ + 'git branch i/j/k should barf if branch i exists' \ + 'git-branch i && + git-pack-refs --all --prune && + git-branch i/j/k' + +test_expect_success \ + 'test git branch k after branch k/l/m and k/lm have been deleted' \ + 'git-branch k/l && + git-branch k/lm && + git-branch -d k/l && + git-branch k/l/m && + git-branch -d k/l/m && + git-branch -d k/lm && + git-branch k' + +test_expect_success \ + 'test git branch n after some branch deletion and pruning' \ + 'git-branch n/o && + git-branch n/op && + git-branch -d n/o && + git-branch n/o/p && + git-branch -d n/op && + git-pack-refs --all --prune && + git-branch -d n/o/p && + git-branch n' + +test_done diff --git a/t/t3401-rebase-partial.sh b/t/t3401-rebase-partial.sh index 360a67060e..8b19d3ccea 100755 --- a/t/t3401-rebase-partial.sh +++ b/t/t3401-rebase-partial.sh @@ -52,13 +52,10 @@ test_expect_success \ 'rebase topic branch against new master and check git-am did not get halted' \ 'git-rebase master && test ! -d .dotest' -if test -z "$no_python" -then - test_expect_success \ +test_expect_success \ 'rebase --merge topic branch that was partially merged upstream' \ 'git-checkout -f my-topic-branch-merge && git-rebase --merge master-merge && test ! -d .git/.dotest-merge' -fi test_done diff --git a/t/t3402-rebase-merge.sh b/t/t3402-rebase-merge.sh index d34c6cf6f3..0779aaa9ab 100755 --- a/t/t3402-rebase-merge.sh +++ b/t/t3402-rebase-merge.sh @@ -7,12 +7,6 @@ test_description='git rebase --merge test' . ./test-lib.sh -if test "$no_python"; then - echo "Skipping: no python => no recursive merge" - test_done - exit 0 -fi - T="A quick brown fox jumps over the lazy dog." for i in 1 2 3 4 5 6 7 8 9 10 diff --git a/t/t3403-rebase-skip.sh b/t/t3403-rebase-skip.sh index 8ab63c5276..977c498f00 100755 --- a/t/t3403-rebase-skip.sh +++ b/t/t3403-rebase-skip.sh @@ -10,12 +10,6 @@ test_description='git rebase --merge --skip tests' # we assume the default git-am -3 --skip strategy is tested independently # and always works :) -if test "$no_python"; then - echo "Skipping: no python => no recursive merge" - test_done - exit 0 -fi - test_expect_success setup ' echo hello > hello && git add hello && @@ -37,7 +31,9 @@ test_expect_success setup ' git branch skip-merge skip-reference ' -test_expect_failure 'rebase with git am -3 (default)' 'git rebase master' +test_expect_failure 'rebase with git am -3 (default)' ' + git rebase master +' test_expect_success 'rebase --skip with am -3' ' git reset --hard HEAD && diff --git a/t/t3600-rm.sh b/t/t3600-rm.sh index 201d1642da..e31cf93a00 100755 --- a/t/t3600-rm.sh +++ b/t/t3600-rm.sh @@ -43,19 +43,19 @@ test_expect_success \ test_expect_success \ 'Test that git-rm foo succeeds' \ - 'git-rm foo' + 'git-rm --cached foo' test_expect_success \ 'Post-check that foo exists but is not in index after git-rm foo' \ '[ -f foo ] && ! git-ls-files --error-unmatch foo' test_expect_success \ - 'Pre-check that bar exists and is in index before "git-rm -f bar"' \ + 'Pre-check that bar exists and is in index before "git-rm bar"' \ '[ -f bar ] && git-ls-files --error-unmatch bar' test_expect_success \ - 'Test that "git-rm -f bar" succeeds' \ - 'git-rm -f bar' + 'Test that "git-rm bar" succeeds' \ + 'git-rm bar' test_expect_success \ 'Post-check that bar does not exist and is not in index after "git-rm -f bar"' \ @@ -84,4 +84,74 @@ test_expect_success \ 'When the rm in "git-rm -f" fails, it should not remove the file from the index' \ 'git-ls-files --error-unmatch baz' +# Now, failure cases. +test_expect_success 'Re-add foo and baz' ' + git add foo baz && + git ls-files --error-unmatch foo baz +' + +test_expect_success 'Modify foo -- rm should refuse' ' + echo >>foo && + ! git rm foo baz && + test -f foo && + test -f baz && + git ls-files --error-unmatch foo baz +' + +test_expect_success 'Modified foo -- rm -f should work' ' + git rm -f foo baz && + test ! -f foo && + test ! -f baz && + ! git ls-files --error-unmatch foo && + ! git ls-files --error-unmatch bar +' + +test_expect_success 'Re-add foo and baz for HEAD tests' ' + echo frotz >foo && + git checkout HEAD -- baz && + git add foo baz && + git ls-files --error-unmatch foo baz +' + +test_expect_success 'foo is different in index from HEAD -- rm should refuse' ' + ! git rm foo baz && + test -f foo && + test -f baz && + git ls-files --error-unmatch foo baz +' + +test_expect_success 'but with -f it should work.' ' + git rm -f foo baz && + test ! -f foo && + test ! -f baz && + ! git ls-files --error-unmatch foo + ! git ls-files --error-unmatch baz +' + +test_expect_success 'Recursive test setup' ' + mkdir -p frotz && + echo qfwfq >frotz/nitfol && + git add frotz && + git commit -m "subdir test" +' + +test_expect_success 'Recursive without -r fails' ' + ! git rm frotz && + test -d frotz && + test -f frotz/nitfol +' + +test_expect_success 'Recursive with -r but dirty' ' + echo qfwfq >>frotz/nitfol + ! git rm -r frotz && + test -d frotz && + test -f frotz/nitfol +' + +test_expect_success 'Recursive with -r -f' ' + git rm -f -r frotz && + ! test -f frotz/nitfol && + ! test -d frotz +' + test_done diff --git a/t/t3700-add.sh b/t/t3700-add.sh index 6cd05c3d90..e98786de32 100755 --- a/t/t3700-add.sh +++ b/t/t3700-add.sh @@ -19,4 +19,69 @@ test_expect_success \ 'Test that "git-add -- -q" works' \ 'touch -- -q && git-add -- -q' +test_expect_success \ + 'git-add: Test that executable bit is not used if core.filemode=0' \ + 'git repo-config core.filemode 0 && + echo foo >xfoo1 && + chmod 755 xfoo1 && + git-add xfoo1 && + case "`git-ls-files --stage xfoo1`" in + 100644" "*xfoo1) echo ok;; + *) echo fail; git-ls-files --stage xfoo1; (exit 1);; + esac' + +test_expect_success \ + 'git-update-index --add: Test that executable bit is not used...' \ + 'git repo-config core.filemode 0 && + echo foo >xfoo2 && + chmod 755 xfoo2 && + git-update-index --add xfoo2 && + case "`git-ls-files --stage xfoo2`" in + 100644" "*xfoo2) echo ok;; + *) echo fail; git-ls-files --stage xfoo2; (exit 1);; + esac' + +test_expect_success \ + 'git-update-index --add: Test that executable bit is not used...' \ + 'git repo-config core.filemode 0 && + ln -s xfoo2 xfoo3 && + git-update-index --add xfoo3 && + case "`git-ls-files --stage xfoo3`" in + 120000" "*xfoo3) echo ok;; + *) echo fail; git-ls-files --stage xfoo3; (exit 1);; + esac' + +test_expect_success '.gitignore test setup' ' + echo "*.ig" >.gitignore && + mkdir c.if d.ig && + >a.ig && >b.if && + >c.if/c.if && >c.if/c.ig && + >d.ig/d.if && >d.ig/d.ig +' + +test_expect_success '.gitignore is honored' ' + git-add . && + ! git-ls-files | grep "\\.ig" +' + +test_expect_success 'error out when attempting to add ignored ones without -f' ' + ! git-add a.?? && + ! git-ls-files | grep "\\.ig" +' + +test_expect_success 'error out when attempting to add ignored ones without -f' ' + ! git-add d.?? && + ! git-ls-files | grep "\\.ig" +' + +test_expect_success 'add ignored ones with -f' ' + git-add -f a.?? && + git-ls-files --error-unmatch a.ig +' + +test_expect_success 'add ignored ones with -f' ' + git-add -f d.??/* && + git-ls-files --error-unmatch d.ig/d.if d.ig/d.ig +' + test_done diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh new file mode 100755 index 0000000000..6714b0dd6e --- /dev/null +++ b/t/t3900-i18n-commit.sh @@ -0,0 +1,122 @@ +#!/bin/sh +# +# Copyright (c) 2006 Junio C Hamano +# + +test_description='commit and log output encodings' + +. ./test-lib.sh + +compare_with () { + git-show -s $1 | sed -e '1,/^$/d' -e 's/^ //' -e '$d' >current && + diff -u current "$2" +} + +test_expect_success setup ' + : >F && + git-add F && + T=$(git-write-tree) && + C=$(git-commit-tree $T <../t3900/1-UTF-8.txt) && + git-update-ref HEAD $C && + git-tag C0 +' + +test_expect_success 'no encoding header for base case' ' + E=$(git-cat-file commit C0 | sed -ne "s/^encoding //p") && + test z = "z$E" +' + +for H in ISO-8859-1 EUCJP ISO-2022-JP +do + test_expect_success "$H setup" ' + git-repo-config i18n.commitencoding $H && + git-checkout -b $H C0 && + echo $H >F && + git-commit -a -F ../t3900/$H.txt + ' +done + +for H in ISO-8859-1 EUCJP ISO-2022-JP +do + test_expect_success "check encoding header for $H" ' + E=$(git-cat-file commit '$H' | sed -ne "s/^encoding //p") && + test "z$E" = "z'$H'" + ' +done + +test_expect_success 'repo-config to remove customization' ' + git-repo-config --unset-all i18n.commitencoding && + if Z=$(git-repo-config --get-all i18n.commitencoding) + then + echo Oops, should have failed. + false + else + test z = "z$Z" + fi && + git-repo-config i18n.commitencoding utf-8 +' + +test_expect_success 'ISO-8859-1 should be shown in UTF-8 now' ' + compare_with ISO-8859-1 ../t3900/1-UTF-8.txt +' + +for H in EUCJP ISO-2022-JP +do + test_expect_success "$H should be shown in UTF-8 now" ' + compare_with '$H' ../t3900/2-UTF-8.txt + ' +done + +test_expect_success 'repo-config to add customization' ' + git-repo-config --unset-all i18n.commitencoding && + if Z=$(git-repo-config --get-all i18n.commitencoding) + then + echo Oops, should have failed. + false + else + test z = "z$Z" + fi +' + +for H in ISO-8859-1 EUCJP ISO-2022-JP +do + test_expect_success "$H should be shown in itself now" ' + git-repo-config i18n.commitencoding '$H' && + compare_with '$H' ../t3900/'$H'.txt + ' +done + +test_expect_success 'repo-config to tweak customization' ' + git-repo-config i18n.logoutputencoding utf-8 +' + +test_expect_success 'ISO-8859-1 should be shown in UTF-8 now' ' + compare_with ISO-8859-1 ../t3900/1-UTF-8.txt +' + +for H in EUCJP ISO-2022-JP +do + test_expect_success "$H should be shown in UTF-8 now" ' + compare_with '$H' ../t3900/2-UTF-8.txt + ' +done + +for J in EUCJP ISO-2022-JP +do + git-repo-config i18n.logoutputencoding $J + for H in EUCJP ISO-2022-JP + do + test_expect_success "$H should be shown in $J now" ' + compare_with '$H' ../t3900/'$J'.txt + ' + done +done + +for H in ISO-8859-1 EUCJP ISO-2022-JP +do + test_expect_success "No conversion with $H" ' + compare_with "--encoding=none '$H'" ../t3900/'$H'.txt + ' +done + +test_done diff --git a/t/t3900/1-UTF-8.txt b/t/t3900/1-UTF-8.txt new file mode 100644 index 0000000000..ee31e19738 --- /dev/null +++ b/t/t3900/1-UTF-8.txt @@ -0,0 +1,3 @@ +ÄËÑÃÖ + +Ãbçdèfg diff --git a/t/t3900/2-UTF-8.txt b/t/t3900/2-UTF-8.txt new file mode 100644 index 0000000000..63f4f8f121 --- /dev/null +++ b/t/t3900/2-UTF-8.txt @@ -0,0 +1,4 @@ +ã¯ã‚Œã²ã»ãµ + +ã—ã¦ã„ã‚‹ã®ãŒã€ã„ã‚‹ã®ã§ã€‚ +濱浜ã»ã‚Œã·ã‚Šã½ã‚Œã¾ã³ãã‚Šã‚ã¸ã€‚ diff --git a/t/t3900/EUCJP.txt b/t/t3900/EUCJP.txt new file mode 100644 index 0000000000..546f2aac01 --- /dev/null +++ b/t/t3900/EUCJP.txt @@ -0,0 +1,4 @@ +¤Ï¤ì¤Ò¤Û¤Õ + +¤·¤Æ¤¤¤ë¤Î¤¬¡¢¤¤¤ë¤Î¤Ç¡£ +ßÀÉͤۤì¤×¤ê¤Ý¤ì¤Þ¤Ó¤°¤ê¤í¤Ø¡£ diff --git a/t/t3900/ISO-2022-JP.txt b/t/t3900/ISO-2022-JP.txt new file mode 100644 index 0000000000..74b533042f --- /dev/null +++ b/t/t3900/ISO-2022-JP.txt @@ -0,0 +1,4 @@ +$B$O$l$R$[$U(B + +$B$7$F$$$k$N$,!"$$$k$N$G!#(B +$B_@IM$[$l$W$j$]$l$^$S$0$j$m$X!#(B diff --git a/t/t3900/ISO-8859-1.txt b/t/t3900/ISO-8859-1.txt new file mode 100644 index 0000000000..7cbef0ee6f --- /dev/null +++ b/t/t3900/ISO-8859-1.txt @@ -0,0 +1,3 @@ +ÄËÑÏÖ + +Ábçdèfg diff --git a/t/t4013-diff-various.sh b/t/t4013-diff-various.sh index 71c454356f..ed37141b6e 100755 --- a/t/t4013-diff-various.sh +++ b/t/t4013-diff-various.sh @@ -73,6 +73,7 @@ test_expect_success setup ' for i in 1 2; do echo $i; done >>dir/sub && git update-index file0 dir/sub && + git repo-config log.showroot false && git commit --amend && git show-branch ' diff --git a/t/t4013/diff.diff-tree_--pretty_--root_--summary_initial b/t/t4013/diff.diff-tree_--pretty_--root_--summary_initial index ea48205537..58e5f74aea 100644 --- a/t/t4013/diff.diff-tree_--pretty_--root_--summary_initial +++ b/t/t4013/diff.diff-tree_--pretty_--root_--summary_initial @@ -5,7 +5,7 @@ Date: Mon Jun 26 00:00:00 2006 +0000 Initial - create mode 040000 dir + create mode 100644 dir/sub create mode 100644 file0 create mode 100644 file2 $ diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh new file mode 100755 index 0000000000..adf4993bac --- /dev/null +++ b/t/t4015-diff-whitespace.sh @@ -0,0 +1,120 @@ +#!/bin/sh +# +# Copyright (c) 2006 Johannes E. Schindelin +# + +test_description='Test special whitespace in diff engine. + +' +. ./test-lib.sh +. ../diff-lib.sh + +# Ray Lehtiniemi's example + +cat << EOF > x +do { + nothing; +} while (0); +EOF + +git-update-index --add x + +cat << EOF > x +do +{ + nothing; +} +while (0); +EOF + +cat << EOF > expect +diff --git a/x b/x +index adf3937..6edc172 100644 +--- a/x ++++ b/x +@@ -1,3 +1,5 @@ +-do { ++do ++{ + nothing; +-} while (0); ++} ++while (0); +EOF + +git-diff > out +test_expect_success "Ray's example without options" 'diff -u expect out' + +git-diff -w > out +test_expect_success "Ray's example with -w" 'diff -u expect out' + +git-diff -b > out +test_expect_success "Ray's example with -b" 'diff -u expect out' + +tr 'Q' '\015' << EOF > x +whitespace at beginning +whitespace change +whitespace in the middle +whitespace at end +unchanged line +CR at endQ +EOF + +git-update-index x + +cat << EOF > x + whitespace at beginning +whitespace change +white space in the middle +whitespace at end +unchanged line +CR at end +EOF + +tr 'Q' '\015' << EOF > expect +diff --git a/x b/x +index d99af23..8b32fb5 100644 +--- a/x ++++ b/x +@@ -1,6 +1,6 @@ +-whitespace at beginning +-whitespace change +-whitespace in the middle +-whitespace at end ++ whitespace at beginning ++whitespace change ++white space in the middle ++whitespace at end + unchanged line +-CR at endQ ++CR at end +EOF +git-diff > out +test_expect_success 'another test, without options' 'diff -u expect out' + +cat << EOF > expect +diff --git a/x b/x +index d99af23..8b32fb5 100644 +EOF +git-diff -w > out +test_expect_success 'another test, with -w' 'diff -u expect out' + +tr 'Q' '\015' << EOF > expect +diff --git a/x b/x +index d99af23..8b32fb5 100644 +--- a/x ++++ b/x +@@ -1,6 +1,6 @@ +-whitespace at beginning ++ whitespace at beginning + whitespace change +-whitespace in the middle ++white space in the middle + whitespace at end + unchanged line + CR at endQ +EOF +git-diff -b > out +test_expect_success 'another test, with -b' 'diff -u expect out' + +test_done diff --git a/t/t4103-apply-binary.sh b/t/t4103-apply-binary.sh index ff052699a2..e2b1124c78 100755 --- a/t/t4103-apply-binary.sh +++ b/t/t4103-apply-binary.sh @@ -94,11 +94,11 @@ test_expect_failure 'apply binary diff (copy) -- should fail.' \ 'do_reset git-apply --index C.diff' -test_expect_failure 'apply binary diff without replacement -- should fail.' \ +test_expect_success 'apply binary diff without replacement.' \ 'do_reset git-apply BF.diff' -test_expect_failure 'apply binary diff without replacement (copy) -- should fail.' \ +test_expect_success 'apply binary diff without replacement (copy).' \ 'do_reset git-apply CF.diff' diff --git a/t/t4104-apply-boundary.sh b/t/t4104-apply-boundary.sh new file mode 100755 index 0000000000..2ff800c23f --- /dev/null +++ b/t/t4104-apply-boundary.sh @@ -0,0 +1,115 @@ +#!/bin/sh +# +# Copyright (c) 2005 Junio C Hamano +# + +test_description='git-apply boundary tests + +' +. ./test-lib.sh + +L="c d e f g h i j k l m n o p q r s t u v w x" + +test_expect_success setup ' + for i in b '"$L"' y + do + echo $i + done >victim && + cat victim >original && + git update-index --add victim && + + : add to the head + for i in a b '"$L"' y + do + echo $i + done >victim && + cat victim >add-a-expect && + git diff victim >add-a-patch.with && + git diff --unified=0 >add-a-patch.without && + + : modify at the head + for i in a '"$L"' y + do + echo $i + done >victim && + cat victim >mod-a-expect && + git diff victim >mod-a-patch.with && + git diff --unified=0 >mod-a-patch.without && + + : remove from the head + for i in '"$L"' y + do + echo $i + done >victim && + cat victim >del-a-expect && + git diff victim >del-a-patch.with + git diff --unified=0 >del-a-patch.without && + + : add to the tail + for i in b '"$L"' y z + do + echo $i + done >victim && + cat victim >add-z-expect && + git diff victim >add-z-patch.with && + git diff --unified=0 >add-z-patch.without && + + : modify at the tail + for i in a '"$L"' y + do + echo $i + done >victim && + cat victim >mod-z-expect && + git diff victim >mod-z-patch.with && + git diff --unified=0 >mod-z-patch.without && + + : remove from the tail + for i in b '"$L"' + do + echo $i + done >victim && + cat victim >del-z-expect && + git diff victim >del-z-patch.with + git diff --unified=0 >del-z-patch.without && + + : done +' + +for with in with without +do + case "$with" in + with) u= ;; + without) u='--unidiff-zero ' ;; + esac + for kind in add-a add-z mod-a mod-z del-a del-z + do + test_expect_success "apply $kind-patch $with context" ' + cat original >victim && + git update-index victim && + git apply --index '"$u$kind-patch.$with"' || { + cat '"$kind-patch.$with"' + (exit 1) + } && + diff -u '"$kind"'-expect victim + ' + done +done + +for kind in add-a add-z mod-a mod-z del-a del-z +do + rm -f $kind-ng.without + sed -e "s/^diff --git /diff /" \ + -e '/^index /d' \ + <$kind-patch.without >$kind-ng.without + test_expect_success "apply non-git $kind-patch without context" ' + cat original >victim && + git update-index victim && + git apply --unidiff-zero --index '"$kind-ng.without"' || { + cat '"$kind-ng.without"' + (exit 1) + } && + diff -u '"$kind"'-expect victim + ' +done + +test_done diff --git a/t/t4116-apply-reverse.sh b/t/t4116-apply-reverse.sh index 69aebe6005..aa2c869e0e 100755 --- a/t/t4116-apply-reverse.sh +++ b/t/t4116-apply-reverse.sh @@ -22,25 +22,64 @@ test_expect_success setup ' tr "[mon]" '\''[\0\1\2]'\'' <file1 >file2 && git commit -a -m second && + git tag second && - git diff --binary -R initial >patch + git diff --binary initial second >patch ' test_expect_success 'apply in forward' ' + T0=`git rev-parse "second^{tree}"` && + git reset --hard initial && git apply --index --binary patch && - git diff initial >diff && - diff -u /dev/null diff - + T1=`git write-tree` && + test "$T0" = "$T1" ' test_expect_success 'apply in reverse' ' + git reset --hard second && git apply --reverse --binary --index patch && git diff >diff && diff -u /dev/null diff ' +test_expect_success 'setup separate repository lacking postimage' ' + + git tar-tree initial initial | tar xf - && + ( + cd initial && git init && git add . + ) && + + git tar-tree second second | tar xf - && + ( + cd second && git init && git add . + ) + +' + +test_expect_success 'apply in forward without postimage' ' + + T0=`git rev-parse "second^{tree}"` && + ( + cd initial && + git apply --index --binary ../patch && + T1=`git write-tree` && + test "$T0" = "$T1" + ) +' + +test_expect_success 'apply in reverse without postimage' ' + + T0=`git rev-parse "initial^{tree}"` && + ( + cd second && + git apply --index --binary --reverse ../patch && + T1=`git write-tree` && + test "$T0" = "$T1" + ) +' + test_done diff --git a/t/t4117-apply-reject.sh b/t/t4117-apply-reject.sh new file mode 100755 index 0000000000..b4de075a3e --- /dev/null +++ b/t/t4117-apply-reject.sh @@ -0,0 +1,157 @@ +#!/bin/sh +# +# Copyright (c) 2005 Junio C Hamano +# + +test_description='git-apply with rejects + +' + +. ./test-lib.sh + +test_expect_success setup ' + for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 + do + echo $i + done >file1 && + cat file1 >saved.file1 && + git update-index --add file1 && + git commit -m initial && + + for i in 1 2 A B 4 5 6 7 8 9 10 11 12 C 13 14 15 16 17 18 19 20 D 21 + do + echo $i + done >file1 && + git diff >patch.1 && + cat file1 >clean && + + for i in 1 E 2 3 4 5 6 7 8 9 10 11 12 C 13 14 15 16 17 18 19 20 F 21 + do + echo $i + done >expected && + + mv file1 file2 && + git update-index --add --remove file1 file2 && + git diff -M HEAD >patch.2 && + + rm -f file1 file2 && + mv saved.file1 file1 && + git update-index --add --remove file1 file2 && + + for i in 1 E 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 F 21 + do + echo $i + done >file1 && + + cat file1 >saved.file1 +' + +test_expect_success 'apply without --reject should fail' ' + + if git apply patch.1 + then + echo "Eh? Why?" + exit 1 + fi + + diff -u file1 saved.file1 +' + +test_expect_success 'apply without --reject should fail' ' + + if git apply --verbose patch.1 + then + echo "Eh? Why?" + exit 1 + fi + + diff -u file1 saved.file1 +' + +test_expect_success 'apply with --reject should fail but update the file' ' + + cat saved.file1 >file1 && + rm -f file1.rej file2.rej && + + if git apply --reject patch.1 + then + echo "succeeds with --reject?" + exit 1 + fi + + diff -u file1 expected && + + cat file1.rej && + + if test -f file2.rej + then + echo "file2 should not have been touched" + exit 1 + fi +' + +test_expect_success 'apply with --reject should fail but update the file' ' + + cat saved.file1 >file1 && + rm -f file1.rej file2.rej file2 && + + if git apply --reject patch.2 >rejects + then + echo "succeeds with --reject?" + exit 1 + fi + + test -f file1 && { + echo "file1 still exists?" + exit 1 + } + diff -u file2 expected && + + cat file2.rej && + + if test -f file1.rej + then + echo "file2 should not have been touched" + exit 1 + fi + +' + +test_expect_success 'the same test with --verbose' ' + + cat saved.file1 >file1 && + rm -f file1.rej file2.rej file2 && + + if git apply --reject --verbose patch.2 >rejects + then + echo "succeeds with --reject?" + exit 1 + fi + + test -f file1 && { + echo "file1 still exists?" + exit 1 + } + diff -u file2 expected && + + cat file2.rej && + + if test -f file1.rej + then + echo "file2 should not have been touched" + exit 1 + fi + +' + +test_expect_success 'apply cleanly with --verbose' ' + + git cat-file -p HEAD:file1 >file1 && + rm -f file?.rej file2 && + + git apply --verbose patch.1 && + + diff -u file1 clean +' + +test_done diff --git a/t/t4118-apply-empty-context.sh b/t/t4118-apply-empty-context.sh new file mode 100755 index 0000000000..7309422fe5 --- /dev/null +++ b/t/t4118-apply-empty-context.sh @@ -0,0 +1,55 @@ +#!/bin/sh +# +# Copyright (c) 2006 Junio C Hamano +# + +test_description='git-apply with new style GNU diff with empty context + +' + +. ./test-lib.sh + +test_expect_success setup ' + { + echo; echo; + echo A; echo B; echo C; + echo; + } >file1 && + cat file1 >file1.orig && + { + cat file1 && + echo Q | tr -d "\\012" + } >file2 && + cat file2 >file2.orig + git add file1 file2 && + sed -e "/^B/d" <file1.orig >file1 && + sed -e "/^B/d" <file2.orig >file2 && + cat file1 >file1.mods && + cat file2 >file2.mods && + git diff | + sed -e "s/^ \$//" >diff.output +' + +test_expect_success 'apply --numstat' ' + + git apply --numstat diff.output >actual && + { + echo "0 1 file1" && + echo "0 1 file2" + } >expect && + diff -u expect actual + +' + +test_expect_success 'apply --apply' ' + + cat file1.orig >file1 && + cat file2.orig >file2 && + git update-index file1 file2 && + git apply --index diff.output && + diff -u file1.mods file1 && + diff -u file2.mods file2 +' + +test_done + diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh new file mode 100755 index 0000000000..5ee5b23095 --- /dev/null +++ b/t/t4200-rerere.sh @@ -0,0 +1,154 @@ +#!/bin/sh +# +# Copyright (c) 2006 Johannes E. Schindelin +# + +test_description='git-rerere +' + +. ./test-lib.sh + +cat > a1 << EOF +Whether 'tis nobler in the mind to suffer +The slings and arrows of outrageous fortune, +Or to take arms against a sea of troubles, +And by opposing end them? To die: to sleep; +No more; and by a sleep to say we end +The heart-ache and the thousand natural shocks +That flesh is heir to, 'tis a consummation +Devoutly to be wish'd. +EOF + +git add a1 +git commit -q -a -m initial + +git checkout -b first +cat >> a1 << EOF +To die, to sleep; +To sleep: perchance to dream: ay, there's the rub; +For in that sleep of death what dreams may come +When we have shuffled off this mortal coil, +Must give us pause: there's the respect +That makes calamity of so long life; +EOF +git commit -q -a -m first + +git checkout -b second master +git show first:a1 | sed 's/To die, t/To die! T/' > a1 +git commit -q -a -m second + +# activate rerere +mkdir .git/rr-cache + +test_expect_failure 'conflicting merge' 'git pull . first' + +sha1=4f58849a60b4f969a2848966b6d02893b783e8fb +rr=.git/rr-cache/$sha1 +test_expect_success 'recorded preimage' "grep ======= $rr/preimage" + +test_expect_success 'no postimage or thisimage yet' \ + "test ! -f $rr/postimage -a ! -f $rr/thisimage" + +git show first:a1 > a1 + +cat > expect << EOF +--- a/a1 ++++ b/a1 +@@ -6,11 +6,7 @@ + The heart-ache and the thousand natural shocks + That flesh is heir to, 'tis a consummation + Devoutly to be wish'd. +-<<<<<<< +-To die! To sleep; +-======= + To die, to sleep; +->>>>>>> + To sleep: perchance to dream: ay, there's the rub; + For in that sleep of death what dreams may come + When we have shuffled off this mortal coil, +EOF + +git rerere diff > out + +test_expect_success 'rerere diff' 'diff -u expect out' + +cat > expect << EOF +a1 +EOF + +git rerere status > out + +test_expect_success 'rerere status' 'diff -u expect out' + +test_expect_success 'commit succeeds' \ + "git commit -q -a -m 'prefer first over second'" + +test_expect_success 'recorded postimage' "test -f $rr/postimage" + +git checkout -b third master +git show second^:a1 | sed 's/To die: t/To die! T/' > a1 +git commit -q -a -m third + +test_expect_failure 'another conflicting merge' 'git pull . first' + +git show first:a1 | sed 's/To die: t/To die! T/' > expect +test_expect_success 'rerere kicked in' "! grep ======= a1" + +test_expect_success 'rerere prefers first change' 'diff -u a1 expect' + +rm $rr/postimage +echo "$sha1 a1" | tr '\012' '\0' > .git/rr-cache/MERGE_RR + +test_expect_success 'rerere clear' 'git rerere clear' + +test_expect_success 'clear removed the directory' "test ! -d $rr" + +mkdir $rr +echo Hello > $rr/preimage +echo World > $rr/postimage + +sha2=4000000000000000000000000000000000000000 +rr2=.git/rr-cache/$sha2 +mkdir $rr2 +echo Hello > $rr2/preimage + +case "$(date -d @11111111 +%s 2>/dev/null)" in +[1-9]*) + # it is a recent GNU date. good. + now=$(date +%s) + almost_15_days_ago=$(($now+60-15*86400)) + just_over_15_days_ago=$(($now-1-15*86400)) + almost_60_days_ago=$(($now+60-60*86400)) + just_over_60_days_ago=$(($now-1-60*86400)) + predate1="$(date -d "@$almost_60_days_ago" +%c)" + predate2="$(date -d "@$almost_15_days_ago" +%c)" + postdate1="$(date -d "@$just_over_60_days_ago" +%c)" + postdate2="$(date -d "@$just_over_15_days_ago" +%c)" + ;; +*) + # it is not GNU date. oh, well. + predate1="$(date)" + predate2="$(date)" + postdate1='1 Oct 2006 00:00:00' + postdate2='1 Dec 2006 00:00:00' +esac + +touch -m -d "$predate1" $rr/preimage +touch -m -d "$predate2" $rr2/preimage + +test_expect_success 'garbage collection (part1)' 'git rerere gc' + +test_expect_success 'young records still live' \ + "test -f $rr/preimage -a -f $rr2/preimage" + +touch -m -d "$postdate1" $rr/preimage +touch -m -d "$postdate2" $rr2/preimage + +test_expect_success 'garbage collection (part2)' 'git rerere gc' + +test_expect_success 'old records rest in peace' \ + "test ! -f $rr/preimage -a ! -f $rr2/preimage" + +test_done + + diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh index 278eb66701..cf08e9279c 100755 --- a/t/t5000-tar-tree.sh +++ b/t/t5000-tar-tree.sh @@ -26,6 +26,7 @@ commit id embedding: . ./test-lib.sh TAR=${TAR:-tar} +UNZIP=${UNZIP:-unzip} test_expect_success \ 'populate workdir' \ @@ -95,4 +96,38 @@ test_expect_success \ 'validate file contents with prefix' \ 'diff -r a c/prefix/a' +test_expect_success \ + 'git-archive --format=zip' \ + 'git-archive --format=zip HEAD >d.zip' + +test_expect_success \ + 'extract ZIP archive' \ + '(mkdir d && cd d && $UNZIP ../d.zip)' + +test_expect_success \ + 'validate filenames' \ + '(cd d/a && find .) | sort >d.lst && + diff a.lst d.lst' + +test_expect_success \ + 'validate file contents' \ + 'diff -r a d/a' + +test_expect_success \ + 'git-archive --format=zip with prefix' \ + 'git-archive --format=zip --prefix=prefix/ HEAD >e.zip' + +test_expect_success \ + 'extract ZIP archive with prefix' \ + '(mkdir e && cd e && $UNZIP ../e.zip)' + +test_expect_success \ + 'validate filenames with prefix' \ + '(cd e/prefix/a && find .) | sort >e.lst && + diff a.lst e.lst' + +test_expect_success \ + 'validate file contents with prefix' \ + 'diff -r a e/prefix/a' + test_done diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh index de45ac4e0f..f511547455 100755 --- a/t/t5300-pack-object.sh +++ b/t/t5300-pack-object.sh @@ -44,7 +44,7 @@ test_expect_success \ 'unpack without delta' \ "GIT_OBJECT_DIRECTORY=.git2/objects && export GIT_OBJECT_DIRECTORY && - git-init-db && + git-init && git-unpack-objects -n <test-1-${packname_1}.pack && git-unpack-objects <test-1-${packname_1}.pack" @@ -75,7 +75,7 @@ test_expect_success \ 'unpack with delta' \ 'GIT_OBJECT_DIRECTORY=.git2/objects && export GIT_OBJECT_DIRECTORY && - git-init-db && + git-init && git-unpack-objects -n <test-2-${packname_2}.pack && git-unpack-objects <test-2-${packname_2}.pack' @@ -100,7 +100,7 @@ test_expect_success \ 'use packed objects' \ 'GIT_OBJECT_DIRECTORY=.git2/objects && export GIT_OBJECT_DIRECTORY && - git-init-db && + git-init && cp test-1-${packname_1}.pack test-1-${packname_1}.idx .git2/objects/pack && { git-diff-tree --root -p $commit && while read object diff --git a/t/t5301-sliding-window.sh b/t/t5301-sliding-window.sh new file mode 100755 index 0000000000..5a7232a577 --- /dev/null +++ b/t/t5301-sliding-window.sh @@ -0,0 +1,60 @@ +#!/bin/sh +# +# Copyright (c) 2006 Shawn Pearce +# + +test_description='mmap sliding window tests' +. ./test-lib.sh + +test_expect_success \ + 'setup' \ + 'rm -f .git/index* + for i in a b c + do + echo $i >$i && + dd if=/dev/urandom bs=32k count=1 >>$i && + git-update-index --add $i || return 1 + done && + echo d >d && cat c >>d && git-update-index --add d && + tree=`git-write-tree` && + commit1=`git-commit-tree $tree </dev/null` && + git-update-ref HEAD $commit1 && + git-repack -a -d && + test "`git-count-objects`" = "0 objects, 0 kilobytes" && + pack1=`ls .git/objects/pack/*.pack` && + test -f "$pack1"' + +test_expect_success \ + 'verify-pack -v, defaults' \ + 'git-verify-pack -v "$pack1"' + +test_expect_success \ + 'verify-pack -v, packedGitWindowSize == 1 page' \ + 'git-repo-config core.packedGitWindowSize 512 && + git-verify-pack -v "$pack1"' + +test_expect_success \ + 'verify-pack -v, packedGit{WindowSize,Limit} == 1 page' \ + 'git-repo-config core.packedGitWindowSize 512 && + git-repo-config core.packedGitLimit 512 && + git-verify-pack -v "$pack1"' + +test_expect_success \ + 'repack -a -d, packedGit{WindowSize,Limit} == 1 page' \ + 'git-repo-config core.packedGitWindowSize 512 && + git-repo-config core.packedGitLimit 512 && + commit2=`git-commit-tree $tree -p $commit1 </dev/null` && + git-update-ref HEAD $commit2 && + git-repack -a -d && + test "`git-count-objects`" = "0 objects, 0 kilobytes" && + pack2=`ls .git/objects/pack/*.pack` && + test -f "$pack2" + test "$pack1" \!= "$pack2"' + +test_expect_success \ + 'verify-pack -v, defaults' \ + 'git-repo-config --unset core.packedGitWindowSize && + git-repo-config --unset core.packedGitLimit && + git-verify-pack -v "$pack2"' + +test_done diff --git a/t/t5400-send-pack.sh b/t/t5400-send-pack.sh index f3694ac3c7..2c151912a3 100755 --- a/t/t5400-send-pack.sh +++ b/t/t5400-send-pack.sh @@ -8,38 +8,63 @@ test_description='See why rewinding head breaks send-pack ' . ./test-lib.sh -touch cpio-test -test_expect_success 'working cpio' 'echo cpio-test | cpio -o > /dev/null' - -cnt='1' +cnt=64 test_expect_success setup ' + test_tick && + mkdir mozart mozart/is && + echo "Commit #0" >mozart/is/pink && + git-update-index --add mozart/is/pink && tree=$(git-write-tree) && commit=$(echo "Commit #0" | git-commit-tree $tree) && zero=$commit && parent=$zero && - for i in $cnt + i=0 && + while test $i -le $cnt do - sleep 1 && + i=$(($i+1)) && + test_tick && + echo "Commit #$i" >mozart/is/pink && + git-update-index --add mozart/is/pink && + tree=$(git-write-tree) && commit=$(echo "Commit #$i" | git-commit-tree $tree -p $parent) && + git-update-ref refs/tags/commit$i $commit && parent=$commit || return 1 done && git-update-ref HEAD "$commit" && - git-clone -l ./. victim && + git-clone ./. victim && cd victim && git-log && cd .. && git-update-ref HEAD "$zero" && parent=$zero && - for i in $cnt + i=0 && + while test $i -le $cnt do - sleep 1 && + i=$(($i+1)) && + test_tick && + echo "Rebase #$i" >mozart/is/pink && + git-update-index --add mozart/is/pink && + tree=$(git-write-tree) && commit=$(echo "Rebase #$i" | git-commit-tree $tree -p $parent) && + git-update-ref refs/tags/rebase$i $commit && parent=$commit || return 1 done && git-update-ref HEAD "$commit" && echo Rebase && git-log' +test_expect_success 'pack the source repository' ' + git repack -a -d && + git prune +' + +test_expect_success 'pack the destination repository' ' + cd victim && + git repack -a -d && + git prune && + cd .. +' + test_expect_success \ 'pushing rewound head should not barf but require --force' ' # should not fail but refuse to update. @@ -64,4 +89,28 @@ test_expect_success \ cmp victim/.git/refs/heads/master .git/refs/heads/master ' +test_expect_success \ + 'push can be used to delete a ref' ' + cd victim && + git branch extra master && + cd .. && + test -f victim/.git/refs/heads/extra && + git-send-pack ./victim/.git/ :extra master && + ! test -f victim/.git/refs/heads/extra +' + +unset GIT_CONFIG GIT_CONFIG_LOCAL +HOME=`pwd`/no-such-directory +export HOME ;# this way we force the victim/.git/config to be used. + +test_expect_success \ + 'pushing with --force should be denied with denyNonFastforwards' ' + cd victim && + git-repo-config receive.denyNonFastforwards true && + cd .. && + git-update-ref refs/heads/master master^ && + git-send-pack --force ./victim/.git/ master && + ! diff -u .git/refs/heads/master victim/.git/refs/heads/master +' + test_done diff --git a/t/t5401-update-hooks.sh b/t/t5401-update-hooks.sh new file mode 100755 index 0000000000..cd8cee6ae8 --- /dev/null +++ b/t/t5401-update-hooks.sh @@ -0,0 +1,81 @@ +#!/bin/sh +# +# Copyright (c) 2006 Shawn O. Pearce +# + +test_description='Test the update hook infrastructure.' +. ./test-lib.sh + +test_expect_success setup ' + echo This is a test. >a && + git-update-index --add a && + tree0=$(git-write-tree) && + commit0=$(echo setup | git-commit-tree $tree0) && + git-update-ref HEAD $commit0 && + git-clone ./. victim && + echo We hope it works. >a && + git-update-index a && + tree1=$(git-write-tree) && + commit1=$(echo modify | git-commit-tree $tree1 -p $commit0) && + git-update-ref HEAD $commit1 +' + +cat >victim/.git/hooks/update <<'EOF' +#!/bin/sh +echo "$@" >$GIT_DIR/update.args +read x; echo -n "$x" >$GIT_DIR/update.stdin +echo STDOUT update +echo STDERR update >&2 +EOF +chmod u+x victim/.git/hooks/update + +cat >victim/.git/hooks/post-update <<'EOF' +#!/bin/sh +echo "$@" >$GIT_DIR/post-update.args +read x; echo -n "$x" >$GIT_DIR/post-update.stdin +echo STDOUT post-update +echo STDERR post-update >&2 +EOF +chmod u+x victim/.git/hooks/post-update + +test_expect_success push ' + git-send-pack ./victim/.git/ master >send.out 2>send.err +' + +test_expect_success 'hooks ran' ' + test -f victim/.git/update.args && + test -f victim/.git/update.stdin && + test -f victim/.git/post-update.args && + test -f victim/.git/post-update.stdin +' + +test_expect_success 'update hook arguments' ' + echo refs/heads/master $commit0 $commit1 | + diff -u - victim/.git/update.args +' + +test_expect_success 'post-update hook arguments' ' + echo refs/heads/master | + diff -u - victim/.git/post-update.args +' + +test_expect_failure 'update hook stdin is /dev/null' ' + test -s victim/.git/update.stdin +' + +test_expect_failure 'post-update hook stdin is /dev/null' ' + test -s victim/.git/post-update.stdin +' + +test_expect_failure 'send-pack produced no output' ' + test -s send.out +' + +test_expect_success 'send-pack stderr contains hook messages' ' + grep "STDOUT update" send.err && + grep "STDERR update" send.err && + grep "STDOUT post-update" send.err && + grep "STDERR post-update" send.err +' + +test_done diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh index f7625a6f46..ef78df67ea 100755 --- a/t/t5500-fetch-pack.sh +++ b/t/t5500-fetch-pack.sh @@ -97,7 +97,7 @@ pull_to_client () { ( mkdir client && cd client && - git-init-db 2>> log2.txt + git-init 2>> log2.txt ) add A1 @@ -128,4 +128,54 @@ pull_to_client 2nd "B" $((64*3)) pull_to_client 3rd "A" $((1*3)) # old fails +test_expect_success "clone shallow" "git-clone --depth 2 . shallow" + +(cd shallow; git-count-objects -v) > count.shallow + +test_expect_success "clone shallow object count" \ + "test \"in-pack: 18\" = \"$(grep in-pack count.shallow)\"" + +count_output () { + sed -e '/^in-pack:/d' -e '/^packs:/d' -e '/: 0$/d' "$1" +} + +test_expect_success "clone shallow object count (part 2)" ' + test -z "$(count_output count.shallow)" +' + +test_expect_success "fsck in shallow repo" \ + "(cd shallow; git-fsck-objects --full)" + +#test_done; exit + +add B66 $B65 +add B67 $B66 + +test_expect_success "pull in shallow repo" \ + "(cd shallow; git pull .. B)" + +(cd shallow; git-count-objects -v) > count.shallow +test_expect_success "clone shallow object count" \ + "test \"count: 6\" = \"$(grep count count.shallow)\"" + +add B68 $B67 +add B69 $B68 + +test_expect_success "deepening pull in shallow repo" \ + "(cd shallow; git pull --depth 4 .. B)" + +(cd shallow; git-count-objects -v) > count.shallow +test_expect_success "clone shallow object count" \ + "test \"count: 12\" = \"$(grep count count.shallow)\"" + +test_expect_success "deepening fetch in shallow repo" \ + "(cd shallow; git fetch --depth 4 .. A:A)" + +(cd shallow; git-count-objects -v) > count.shallow +test_expect_success "clone shallow object count" \ + "test \"count: 18\" = \"$(grep count count.shallow)\"" + +test_expect_failure "pull in shallow repo with missing merge base" \ + "(cd shallow; git pull --depth 4 .. A)" + test_done diff --git a/t/t5510-fetch.sh b/t/t5510-fetch.sh new file mode 100755 index 0000000000..3ce9446210 --- /dev/null +++ b/t/t5510-fetch.sh @@ -0,0 +1,84 @@ +#!/bin/sh +# Copyright (c) 2006, Junio C Hamano. + +test_description='Per branch config variables affects "git fetch". + +' + +. ./test-lib.sh + +D=`pwd` + +test_expect_success setup ' + echo >file original && + git add file && + git commit -a -m original' + +test_expect_success "clone and setup child repos" ' + git clone . one && + cd one && + echo >file updated by one && + git commit -a -m "updated by one" && + cd .. && + git clone . two && + cd two && + git repo-config branch.master.remote one && + git repo-config remote.one.url ../one/.git/ && + git repo-config remote.one.fetch refs/heads/master:refs/heads/one && + cd .. && + git clone . three && + cd three && + git repo-config branch.master.remote two && + git repo-config branch.master.merge refs/heads/one && + mkdir -p .git/remotes && + { + echo "URL: ../two/.git/" + echo "Pull: refs/heads/master:refs/heads/two" + echo "Pull: refs/heads/one:refs/heads/one" + } >.git/remotes/two +' + +test_expect_success "fetch test" ' + cd "$D" && + echo >file updated by origin && + git commit -a -m "updated by origin" && + cd two && + git fetch && + test -f .git/refs/heads/one && + mine=`git rev-parse refs/heads/one` && + his=`cd ../one && git rev-parse refs/heads/master` && + test "z$mine" = "z$his" +' + +test_expect_success "fetch test for-merge" ' + cd "$D" && + cd three && + git fetch && + test -f .git/refs/heads/two && + test -f .git/refs/heads/one && + master_in_two=`cd ../two && git rev-parse master` && + one_in_two=`cd ../two && git rev-parse one` && + { + echo "$master_in_two not-for-merge" + echo "$one_in_two " + } >expected && + cut -f -2 .git/FETCH_HEAD >actual && + diff expected actual' + +test_expect_success 'fetch following tags' ' + + cd "$D" && + git tag -a -m 'annotated' anno HEAD && + git tag light HEAD && + + mkdir four && + cd four && + git init && + + git fetch .. :track && + git show-ref --verify refs/tags/anno && + git show-ref --verify refs/tags/light + +' + +test_done diff --git a/t/t5520-pull.sh b/t/t5520-pull.sh new file mode 100755 index 0000000000..7eb37838bb --- /dev/null +++ b/t/t5520-pull.sh @@ -0,0 +1,33 @@ +#!/bin/sh + +test_description='pulling into void' + +. ./test-lib.sh + +D=`pwd` + +test_expect_success setup ' + + echo file >file && + git add file && + git commit -a -m original + +' + +test_expect_success 'pulling into void' ' + mkdir cloned && + cd cloned && + git init && + git pull .. +' + +cd "$D" + +test_expect_success 'checking the results' ' + test -f file && + test -f cloned/file && + diff file cloned/file +' + +test_done + diff --git a/t/t5600-clone-fail-cleanup.sh b/t/t5600-clone-fail-cleanup.sh index 0c6a363be9..041be04f5c 100755 --- a/t/t5600-clone-fail-cleanup.sh +++ b/t/t5600-clone-fail-cleanup.sh @@ -25,6 +25,12 @@ test_create_repo foo # clone doesn't like it if there is no HEAD. Is that a bug? (cd foo && touch file && git add file && git commit -m 'add file' >/dev/null 2>&1) +# source repository given to git-clone should be relative to the +# current path not to the target dir +test_expect_failure \ + 'clone of non-existent (relative to $PWD) source should fail' \ + 'git-clone ../foo baz' + test_expect_success \ 'clone should work now that source exists' \ 'git-clone foo bar' diff --git a/t/t5710-info-alternate.sh b/t/t5710-info-alternate.sh index 2e1b48a89b..b9f6d96363 100755 --- a/t/t5710-info-alternate.sh +++ b/t/t5710-info-alternate.sh @@ -58,6 +58,8 @@ test_expect_failure 'creating too deep nesting' \ git clone -l -s D E && git clone -l -s E F && git clone -l -s F G && +git clone -l -s G H && +cd H && test_valid_repo' cd "$base_dir" diff --git a/t/t6001-rev-list-graft.sh b/t/t6001-rev-list-graft.sh new file mode 100755 index 0000000000..b2131cdacd --- /dev/null +++ b/t/t6001-rev-list-graft.sh @@ -0,0 +1,113 @@ +#!/bin/sh + +test_description='Revision traversal vs grafts and path limiter' + +. ./test-lib.sh + +test_expect_success setup ' + mkdir subdir && + echo >fileA fileA && + echo >subdir/fileB fileB && + git add fileA subdir/fileB && + git commit -a -m "Initial in one history." && + A0=`git rev-parse --verify HEAD` && + + echo >fileA fileA modified && + git commit -a -m "Second in one history." && + A1=`git rev-parse --verify HEAD` && + + echo >subdir/fileB fileB modified && + git commit -a -m "Third in one history." && + A2=`git rev-parse --verify HEAD` && + + rm -f .git/refs/heads/master .git/index && + + echo >fileA fileA again && + echo >subdir/fileB fileB again && + git add fileA subdir/fileB && + git commit -a -m "Initial in alternate history." && + B0=`git rev-parse --verify HEAD` && + + echo >fileA fileA modified in alternate history && + git commit -a -m "Second in alternate history." && + B1=`git rev-parse --verify HEAD` && + + echo >subdir/fileB fileB modified in alternate history && + git commit -a -m "Third in alternate history." && + B2=`git rev-parse --verify HEAD` && + : done +' + +check () { + type=$1 + shift + + arg= + which=arg + rm -f test.expect + for a + do + if test "z$a" = z-- + then + which=expect + child= + continue + fi + if test "$which" = arg + then + arg="$arg$a " + continue + fi + if test "$type" = basic + then + echo "$a" + else + if test "z$child" != z + then + echo "$child $a" + fi + child="$a" + fi + done >test.expect + if test "$type" != basic && test "z$child" != z + then + echo >>test.expect $child + fi + if test $type = basic + then + git rev-list $arg >test.actual + elif test $type = parents + then + git rev-list --parents $arg >test.actual + elif test $type = parents-raw + then + git rev-list --parents --pretty=raw $arg | + sed -n -e 's/^commit //p' >test.actual + fi + diff test.expect test.actual +} + +for type in basic parents parents-raw +do + test_expect_success 'without grafts' " + rm -f .git/info/grafts + check $type $B2 -- $B2 $B1 $B0 + " + + test_expect_success 'with grafts' " + echo '$B0 $A2' >.git/info/grafts + check $type $B2 -- $B2 $B1 $B0 $A2 $A1 $A0 + " + + test_expect_success 'without grafts, with pathlimit' " + rm -f .git/info/grafts + check $type $B2 subdir -- $B2 $B0 + " + + test_expect_success 'with grafts, with pathlimit' " + echo '$B0 $A2' >.git/info/grafts + check $type $B2 subdir -- $B2 $B0 $A2 $A0 + " + +done +test_done diff --git a/t/t6005-rev-list-count.sh b/t/t6005-rev-list-count.sh new file mode 100755 index 0000000000..334fccf58c --- /dev/null +++ b/t/t6005-rev-list-count.sh @@ -0,0 +1,51 @@ +#!/bin/sh + +test_description='git-rev-list --max-count and --skip test' + +. ./test-lib.sh + +test_expect_success 'setup' ' + for n in 1 2 3 4 5 ; do \ + echo $n > a ; \ + git add a ; \ + git commit -m "$n" ; \ + done +' + +test_expect_success 'no options' ' + test $(git-rev-list HEAD | wc -l) = 5 +' + +test_expect_success '--max-count' ' + test $(git-rev-list HEAD --max-count=0 | wc -l) = 0 && + test $(git-rev-list HEAD --max-count=3 | wc -l) = 3 && + test $(git-rev-list HEAD --max-count=5 | wc -l) = 5 && + test $(git-rev-list HEAD --max-count=10 | wc -l) = 5 +' + +test_expect_success '--max-count all forms' ' + test $(git-rev-list HEAD --max-count=1 | wc -l) = 1 && + test $(git-rev-list HEAD -1 | wc -l) = 1 && + test $(git-rev-list HEAD -n1 | wc -l) = 1 && + test $(git-rev-list HEAD -n 1 | wc -l) = 1 +' + +test_expect_success '--skip' ' + test $(git-rev-list HEAD --skip=0 | wc -l) = 5 && + test $(git-rev-list HEAD --skip=3 | wc -l) = 2 && + test $(git-rev-list HEAD --skip=5 | wc -l) = 0 && + test $(git-rev-list HEAD --skip=10 | wc -l) = 0 +' + +test_expect_success '--skip --max-count' ' + test $(git-rev-list HEAD --skip=0 --max-count=0 | wc -l) = 0 && + test $(git-rev-list HEAD --skip=0 --max-count=10 | wc -l) = 5 && + test $(git-rev-list HEAD --skip=3 --max-count=0 | wc -l) = 0 && + test $(git-rev-list HEAD --skip=3 --max-count=1 | wc -l) = 1 && + test $(git-rev-list HEAD --skip=3 --max-count=2 | wc -l) = 2 && + test $(git-rev-list HEAD --skip=3 --max-count=10 | wc -l) = 2 && + test $(git-rev-list HEAD --skip=5 --max-count=10 | wc -l) = 0 && + test $(git-rev-list HEAD --skip=10 --max-count=10 | wc -l) = 0 +' + +test_done diff --git a/t/t6021-merge-criss-cross.sh b/t/t6021-merge-criss-cross.sh index 8f7366da8d..499cafb882 100755 --- a/t/t6021-merge-criss-cross.sh +++ b/t/t6021-merge-criss-cross.sh @@ -10,12 +10,6 @@ test_description='Test criss-cross merge' . ./test-lib.sh -if test "$no_python"; then - echo "Skipping: no python => no recursive merge" - test_done - exit 0 -fi - test_expect_success 'prepare repository' \ 'echo "1 2 diff --git a/t/t6022-merge-rename.sh b/t/t6022-merge-rename.sh index 5ac25647ab..b608e202c1 100755 --- a/t/t6022-merge-rename.sh +++ b/t/t6022-merge-rename.sh @@ -3,12 +3,6 @@ test_description='Merge-recursive merging renames' . ./test-lib.sh -if test "$no_python"; then - echo "Skipping: no python => no recursive merge" - test_done - exit 0 -fi - test_expect_success setup \ ' cat >A <<\EOF && @@ -48,15 +42,20 @@ O OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO EOF git add A M && -git commit -m initial && +git commit -m "initial has A and M" && git branch white && git branch red && git branch blue && +git branch yellow && sed -e "/^g /s/.*/g : master changes a line/" <A >A+ && mv A+ A && git commit -a -m "master updates A" && +git checkout yellow && +rm -f M && +git commit -a -m "yellow removes M" && + git checkout white && sed -e "/^g /s/.*/g : white changes a line/" <A >B && sed -e "/^G /s/.*/G : colored branch changes a line/" <M >N && @@ -85,27 +84,27 @@ test_expect_success 'pull renaming branch into unrenaming one' \ git show-branch git pull . white && { echo "BAD: should have conflicted" - exit 1 + return 1 } git ls-files -s test "$(git ls-files -u B | wc -l)" -eq 3 || { echo "BAD: should have left stages for B" - exit 1 + return 1 } test "$(git ls-files -s N | wc -l)" -eq 1 || { echo "BAD: should have merged N" - exit 1 + return 1 } sed -ne "/^g/{ p q }" B | grep master || { echo "BAD: should have listed our change first" - exit 1 + return 1 } test "$(git diff white N | wc -l)" -eq 0 || { echo "BAD: should have taken colored branch" - exit 1 + return 1 } ' @@ -116,26 +115,26 @@ test_expect_success 'pull renaming branch into another renaming one' \ git checkout red git pull . white && { echo "BAD: should have conflicted" - exit 1 + return 1 } test "$(git ls-files -u B | wc -l)" -eq 3 || { echo "BAD: should have left stages" - exit 1 + return 1 } test "$(git ls-files -s N | wc -l)" -eq 1 || { echo "BAD: should have merged N" - exit 1 + return 1 } sed -ne "/^g/{ p q }" B | grep red || { echo "BAD: should have listed our change first" - exit 1 + return 1 } test "$(git diff white N | wc -l)" -eq 0 || { echo "BAD: should have taken colored branch" - exit 1 + return 1 } ' @@ -145,26 +144,26 @@ test_expect_success 'pull unrenaming branch into renaming one' \ git show-branch git pull . master && { echo "BAD: should have conflicted" - exit 1 + return 1 } test "$(git ls-files -u B | wc -l)" -eq 3 || { echo "BAD: should have left stages" - exit 1 + return 1 } test "$(git ls-files -s N | wc -l)" -eq 1 || { echo "BAD: should have merged N" - exit 1 + return 1 } sed -ne "/^g/{ p q }" B | grep red || { echo "BAD: should have listed our change first" - exit 1 + return 1 } test "$(git diff white N | wc -l)" -eq 0 || { echo "BAD: should have taken colored branch" - exit 1 + return 1 } ' @@ -174,35 +173,149 @@ test_expect_success 'pull conflicting renames' \ git show-branch git pull . blue && { echo "BAD: should have conflicted" - exit 1 + return 1 } test "$(git ls-files -u A | wc -l)" -eq 1 || { echo "BAD: should have left a stage" - exit 1 + return 1 } test "$(git ls-files -u B | wc -l)" -eq 1 || { echo "BAD: should have left a stage" - exit 1 + return 1 } test "$(git ls-files -u C | wc -l)" -eq 1 || { echo "BAD: should have left a stage" - exit 1 + return 1 } test "$(git ls-files -s N | wc -l)" -eq 1 || { echo "BAD: should have merged N" - exit 1 + return 1 } sed -ne "/^g/{ p q }" B | grep red || { echo "BAD: should have listed our change first" - exit 1 + return 1 } test "$(git diff white N | wc -l)" -eq 0 || { echo "BAD: should have taken colored branch" - exit 1 + return 1 + } +' + +test_expect_success 'interference with untracked working tree file' ' + + git reset --hard + git show-branch + echo >A this file should not matter + git pull . white && { + echo "BAD: should have conflicted" + return 1 + } + test -f A || { + echo "BAD: should have left A intact" + return 1 + } +' + +test_expect_success 'interference with untracked working tree file' ' + + git reset --hard + git checkout white + git show-branch + rm -f A + echo >A this file should not matter + git pull . red && { + echo "BAD: should have conflicted" + return 1 + } + test -f A || { + echo "BAD: should have left A intact" + return 1 + } +' + +test_expect_success 'interference with untracked working tree file' ' + + git reset --hard + rm -f A M + git checkout -f master + git tag -f anchor + git show-branch + git pull . yellow || { + echo "BAD: should have cleanly merged" + return 1 + } + test -f M && { + echo "BAD: should have removed M" + return 1 + } + git reset --hard anchor +' + +test_expect_success 'updated working tree file should prevent the merge' ' + + git reset --hard + rm -f A M + git checkout -f master + git tag -f anchor + git show-branch + echo >>M one line addition + cat M >M.saved + git pull . yellow && { + echo "BAD: should have complained" + return 1 + } + diff M M.saved || { + echo "BAD: should have left M intact" + return 1 + } + rm -f M.saved +' + +test_expect_success 'updated working tree file should prevent the merge' ' + + git reset --hard + rm -f A M + git checkout -f master + git tag -f anchor + git show-branch + echo >>M one line addition + cat M >M.saved + git update-index M + git pull . yellow && { + echo "BAD: should have complained" + return 1 + } + diff M M.saved || { + echo "BAD: should have left M intact" + return 1 + } + rm -f M.saved +' + +test_expect_success 'interference with untracked working tree file' ' + + git reset --hard + rm -f A M + git checkout -f yellow + git tag -f anchor + git show-branch + echo >M this file should not matter + git pull . master || { + echo "BAD: should have cleanly merged" + return 1 + } + test -f M || { + echo "BAD: should have left M intact" + return 1 + } + git ls-files -s | grep M && { + echo "BAD: M must be untracked in the result" + return 1 } + git reset --hard anchor ' test_done diff --git a/t/t6023-merge-file.sh b/t/t6023-merge-file.sh new file mode 100644 index 0000000000..1c21d8c986 --- /dev/null +++ b/t/t6023-merge-file.sh @@ -0,0 +1,138 @@ +#!/bin/sh + +test_description='RCS merge replacement: merge-file' +. ./test-lib.sh + +cat > orig.txt << EOF +Dominus regit me, +et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +EOF + +cat > new1.txt << EOF +Dominus regit me, +et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +Nam et si ambulavero in medio umbrae mortis, +non timebo mala, quoniam tu mecum es: +virga tua et baculus tuus ipsa me consolata sunt. +EOF + +cat > new2.txt << EOF +Dominus regit me, et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +EOF + +cat > new3.txt << EOF +DOMINUS regit me, +et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +EOF + +cat > new4.txt << EOF +Dominus regit me, et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +EOF +echo -n "propter nomen suum." >> new4.txt + +cp new1.txt test.txt +test_expect_success "merge without conflict" \ + "git-merge-file test.txt orig.txt new2.txt" + +cp new1.txt test2.txt +test_expect_success "merge without conflict (missing LF at EOF)" \ + "git-merge-file test2.txt orig.txt new2.txt" + +test_expect_success "merge result added missing LF" \ + "diff -u test.txt test2.txt" + +cp test.txt backup.txt +test_expect_failure "merge with conflicts" \ + "git-merge-file test.txt orig.txt new3.txt" + +cat > expect.txt << EOF +<<<<<<< test.txt +Dominus regit me, et nihil mihi deerit. +======= +DOMINUS regit me, +et nihil mihi deerit. +>>>>>>> new3.txt +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +Nam et si ambulavero in medio umbrae mortis, +non timebo mala, quoniam tu mecum es: +virga tua et baculus tuus ipsa me consolata sunt. +EOF + +test_expect_success "expected conflict markers" "diff -u test.txt expect.txt" + +cp backup.txt test.txt +test_expect_failure "merge with conflicts, using -L" \ + "git-merge-file -L 1 -L 2 test.txt orig.txt new3.txt" + +cat > expect.txt << EOF +<<<<<<< 1 +Dominus regit me, et nihil mihi deerit. +======= +DOMINUS regit me, +et nihil mihi deerit. +>>>>>>> new3.txt +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +Nam et si ambulavero in medio umbrae mortis, +non timebo mala, quoniam tu mecum es: +virga tua et baculus tuus ipsa me consolata sunt. +EOF + +test_expect_success "expected conflict markers, with -L" \ + "diff -u test.txt expect.txt" + +sed "s/ tu / TU /" < new1.txt > new5.txt +test_expect_failure "conflict in removed tail" \ + "git-merge-file -p orig.txt new1.txt new5.txt > out" + +cat > expect << EOF +Dominus regit me, +et nihil mihi deerit. +In loco pascuae ibi me collocavit, +super aquam refectionis educavit me; +animam meam convertit, +deduxit me super semitas jusitiae, +propter nomen suum. +<<<<<<< orig.txt +======= +Nam et si ambulavero in medio umbrae mortis, +non timebo mala, quoniam TU mecum es: +virga tua et baculus tuus ipsa me consolata sunt. +>>>>>>> new5.txt +EOF + +test_expect_success "expected conflict markers" "diff -u expect out" + +test_done + diff --git a/t/t6023-merge-rename-nocruft.sh b/t/t6023-merge-rename-nocruft.sh new file mode 100755 index 0000000000..69c66cf6fa --- /dev/null +++ b/t/t6023-merge-rename-nocruft.sh @@ -0,0 +1,97 @@ +#!/bin/sh + +test_description='Merge-recursive merging renames' +. ./test-lib.sh + +test_expect_success setup \ +' +cat >A <<\EOF && +a aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +b bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb +c cccccccccccccccccccccccccccccccccccccccccccccccc +d dddddddddddddddddddddddddddddddddddddddddddddddd +e eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee +f ffffffffffffffffffffffffffffffffffffffffffffffff +g gggggggggggggggggggggggggggggggggggggggggggggggg +h hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh +i iiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiii +j jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj +k kkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk +l llllllllllllllllllllllllllllllllllllllllllllllll +m mmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm +n nnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnn +o oooooooooooooooooooooooooooooooooooooooooooooooo +EOF + +cat >M <<\EOF && +A AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA +B BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB +C CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC +D DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD +E EEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEE +F FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF +G GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG +H HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH +I IIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII +J JJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJ +K KKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKK +L LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL +M MMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMM +N NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN +O OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO +EOF + +git add A M && +git commit -m "initial has A and M" && +git branch white && +git branch red && + +git checkout white && +sed -e "/^g /s/.*/g : white changes a line/" <A >B && +sed -e "/^G /s/.*/G : colored branch changes a line/" <M >N && +rm -f A M && +git update-index --add --remove A B M N && +git commit -m "white renames A->B, M->N" && + +git checkout red && +echo created by red >R && +git update-index --add R && +git commit -m "red creates R" && + +git checkout master' + +# This test broke in 65ac6e9c3f47807cb603af07a6a9e1a43bc119ae +test_expect_success 'merge white into red (A->B,M->N)' \ +' + git checkout -b red-white red && + git merge white && + git write-tree >/dev/null || { + echo "BAD: merge did not complete" + return 1 + } + + test -f B || { + echo "BAD: B does not exist in working directory" + return 1 + } + test -f N || { + echo "BAD: N does not exist in working directory" + return 1 + } + test -f R || { + echo "BAD: R does not exist in working directory" + return 1 + } + + test -f A && { + echo "BAD: A still exists in working directory" + return 1 + } + test -f M && { + echo "BAD: M still exists in working directory" + return 1 + } + return 0 +' + +test_done diff --git a/t/t6024-recursive-merge.sh b/t/t6024-recursive-merge.sh new file mode 100644 index 0000000000..31b96257b4 --- /dev/null +++ b/t/t6024-recursive-merge.sh @@ -0,0 +1,84 @@ +#!/bin/sh + +test_description='Test merge without common ancestors' +. ./test-lib.sh + +# This scenario is based on a real-world repository of Shawn Pearce. + +# 1 - A - D - F +# \ X / +# B X +# X \ +# 2 - C - E - G + +GIT_COMMITTER_DATE="2006-12-12 23:28:00 +0100" +export GIT_COMMITTER_DATE + +test_expect_success "setup tests" ' +echo 1 > a1 && +git add a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:00" git commit -m 1 a1 && + +git checkout -b A master && +echo A > a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:01" git commit -m A a1 && + +git checkout -b B master && +echo B > a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:02" git commit -m B a1 && + +git checkout -b D A && +git-rev-parse B > .git/MERGE_HEAD && +echo D > a1 && +git update-index a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:03" git commit -m D && + +git symbolic-ref HEAD refs/heads/other && +echo 2 > a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:04" git commit -m 2 a1 && + +git checkout -b C && +echo C > a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:05" git commit -m C a1 && + +git checkout -b E C && +git-rev-parse B > .git/MERGE_HEAD && +echo E > a1 && +git update-index a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:06" git commit -m E && + +git checkout -b G E && +git-rev-parse A > .git/MERGE_HEAD && +echo G > a1 && +git update-index a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:07" git commit -m G && + +git checkout -b F D && +git-rev-parse C > .git/MERGE_HEAD && +echo F > a1 && +git update-index a1 && +GIT_AUTHOR_DATE="2006-12-12 23:00:08" git commit -m F +' + +test_expect_failure "combined merge conflicts" "git merge -m final G" + +cat > expect << EOF +<<<<<<< HEAD:a1 +F +======= +G +>>>>>>> G:a1 +EOF + +test_expect_success "result contains a conflict" "diff -u expect a1" + +git ls-files --stage > out +cat > expect << EOF +100644 da056ce14a2241509897fa68bb2b3b6e6194ef9e 1 a1 +100644 cf84443e49e1b366fac938711ddf4be2d4d1d9e9 2 a1 +100644 fd7923529855d0b274795ae3349c5e0438333979 3 a1 +EOF + +test_expect_success "virtual trees were processed" "diff -u expect out" + +test_done diff --git a/t/t7001-mv.sh b/t/t7001-mv.sh index b7fcdb390c..344033249c 100755 --- a/t/t7001-mv.sh +++ b/t/t7001-mv.sh @@ -86,4 +86,36 @@ test_expect_success \ 'move into "."' \ 'git-mv path1/path2/ .' +test_expect_success "Michael Cassar's test case" ' + rm -fr .git papers partA && + git init && + mkdir -p papers/unsorted papers/all-papers partA && + echo a > papers/unsorted/Thesis.pdf && + echo b > partA/outline.txt && + echo c > papers/unsorted/_another && + git add papers partA && + T1=`git write-tree` && + + git mv papers/unsorted/Thesis.pdf papers/all-papers/moo-blah.pdf && + + T=`git write-tree` && + git ls-tree -r $T | grep partA/outline.txt || { + git ls-tree -r $T + (exit 1) + } +' + +rm -fr papers partA path? + +test_expect_success "Sergey Vlasov's test case" ' + rm -fr .git && + git init && + mkdir ab && + date >ab.c && + date >ab/d && + git add ab.c ab && + git commit -m 'initial' && + git mv ab a +' + test_done diff --git a/t/t7201-co.sh b/t/t7201-co.sh index b64e8b7d77..085d4a096b 100755 --- a/t/t7201-co.sh +++ b/t/t7201-co.sh @@ -31,6 +31,15 @@ test_expect_success setup ' git checkout master ' +test_expect_success "checkout from non-existing branch" ' + + git checkout -b delete-me master && + rm .git/refs/heads/delete-me && + test refs/heads/delete-me = "$(git symbolic-ref HEAD)" && + git checkout master && + test refs/heads/master = "$(git symbolic-ref HEAD)" +' + test_expect_success "checkout with dirty tree without -m" ' fill 0 1 2 3 4 5 >one && diff --git a/t/t9100-git-svn-basic.sh b/t/t9100-git-svn-basic.sh index 34a3ccd31c..040da92756 100755 --- a/t/t9100-git-svn-basic.sh +++ b/t/t9100-git-svn-basic.sh @@ -19,180 +19,168 @@ esac echo 'define NO_SVN_TESTS to skip git-svn tests' -mkdir import -cd import - -echo foo > foo -if test -z "$NO_SYMLINK" -then - ln -s foo foo.link -fi -mkdir -p dir/a/b/c/d/e -echo 'deep dir' > dir/a/b/c/d/e/file -mkdir -p bar -echo 'zzz' > bar/zzz -echo '#!/bin/sh' > exec.sh -chmod +x exec.sh -svn import -m 'import for git-svn' . "$svnrepo" >/dev/null - -cd .. -rm -rf import - test_expect_success \ - 'initialize git-svn' \ - "git-svn init $svnrepo" + 'initialize git-svn' " + mkdir import && + cd import && + echo foo > foo && + ln -s foo foo.link + mkdir -p dir/a/b/c/d/e && + echo 'deep dir' > dir/a/b/c/d/e/file && + mkdir bar && + echo 'zzz' > bar/zzz && + echo '#!/bin/sh' > exec.sh && + chmod +x exec.sh && + svn import -m 'import for git-svn' . $svnrepo >/dev/null && + cd .. && + rm -rf import && + git-svn init $svnrepo" test_expect_success \ 'import an SVN revision into git' \ 'git-svn fetch' -test_expect_success "checkout from svn" "svn co $svnrepo $SVN_TREE" +test_expect_success "checkout from svn" "svn co $svnrepo '$SVN_TREE'" name='try a deep --rmdir with a commit' -git checkout -f -b mybranch remotes/git-svn -mv dir/a/b/c/d/e/file dir/file -cp dir/file file -git update-index --add --remove dir/a/b/c/d/e/file dir/file file -git commit -m "$name" - -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch && - svn up $SVN_TREE && - test -d $SVN_TREE/dir && test ! -d $SVN_TREE/dir/a" +test_expect_success "$name" " + git checkout -f -b mybranch remotes/git-svn && + mv dir/a/b/c/d/e/file dir/file && + cp dir/file file && + git update-index --add --remove dir/a/b/c/d/e/file dir/file file && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch && + svn up '$SVN_TREE' && + test -d '$SVN_TREE'/dir && test ! -d '$SVN_TREE'/dir/a" name='detect node change from file to directory #1' -mkdir dir/new_file -mv dir/file dir/new_file/file -mv dir/new_file dir/file -git update-index --remove dir/file -git update-index --add dir/file/file -git commit -m "$name" - -test_expect_failure "$name" \ - 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch' \ - || true +test_expect_failure "$name" " + mkdir dir/new_file && + mv dir/file dir/new_file/file && + mv dir/new_file dir/file && + git update-index --remove dir/file && + git update-index --add dir/file/file && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch" || true name='detect node change from directory to file #1' -rm -rf dir $GIT_DIR/index -git checkout -f -b mybranch2 remotes/git-svn -mv bar/zzz zzz -rm -rf bar -mv zzz bar -git update-index --remove -- bar/zzz -git update-index --add -- bar -git commit -m "$name" - -test_expect_failure "$name" \ - 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch2' \ - || true +test_expect_failure "$name" " + rm -rf dir '$GIT_DIR'/index && + git checkout -f -b mybranch2 remotes/git-svn && + mv bar/zzz zzz && + rm -rf bar && + mv zzz bar && + git update-index --remove -- bar/zzz && + git update-index --add -- bar && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch2" || true name='detect node change from file to directory #2' -rm -f $GIT_DIR/index -git checkout -f -b mybranch3 remotes/git-svn -rm bar/zzz -git-update-index --remove bar/zzz -mkdir bar/zzz -echo yyy > bar/zzz/yyy -git-update-index --add bar/zzz/yyy -git commit -m "$name" - -test_expect_failure "$name" \ - 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch3' \ - || true +test_expect_failure "$name" " + rm -f '$GIT_DIR'/index && + git checkout -f -b mybranch3 remotes/git-svn && + rm bar/zzz && + git-update-index --remove bar/zzz && + mkdir bar/zzz && + echo yyy > bar/zzz/yyy && + git-update-index --add bar/zzz/yyy && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch3" || true name='detect node change from directory to file #2' -rm -f $GIT_DIR/index -git checkout -f -b mybranch4 remotes/git-svn -rm -rf dir -git update-index --remove -- dir/file -touch dir -echo asdf > dir -git update-index --add -- dir -git commit -m "$name" - -test_expect_failure "$name" \ - 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch4' \ - || true +test_expect_failure "$name" " + rm -f '$GIT_DIR'/index && + git checkout -f -b mybranch4 remotes/git-svn && + rm -rf dir && + git update-index --remove -- dir/file && + touch dir && + echo asdf > dir && + git update-index --add -- dir && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch4" || true name='remove executable bit from a file' -rm -f $GIT_DIR/index -git checkout -f -b mybranch5 remotes/git-svn -chmod -x exec.sh -git update-index exec.sh -git commit -m "$name" - -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test ! -x $SVN_TREE/exec.sh" +test_expect_success "$name" " + rm -f '$GIT_DIR'/index && + git checkout -f -b mybranch5 remotes/git-svn && + chmod -x exec.sh && + git update-index exec.sh && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch5 && + svn up '$SVN_TREE' && + test ! -x '$SVN_TREE'/exec.sh" name='add executable bit back file' -chmod +x exec.sh -git update-index exec.sh -git commit -m "$name" - -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -x $SVN_TREE/exec.sh" - - - -if test -z "$NO_SYMLINK" -then - name='executable file becomes a symlink to bar/zzz (file)' - rm exec.sh - ln -s bar/zzz exec.sh - git update-index exec.sh - git commit -m "$name" - - test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -L $SVN_TREE/exec.sh" - - name='new symlink is added to a file that was also just made executable' - chmod +x bar/zzz - ln -s bar/zzz exec-2.sh - git update-index --add bar/zzz exec-2.sh - git commit -m "$name" - - test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -x $SVN_TREE/bar/zzz && - test -L $SVN_TREE/exec-2.sh" - - name='modify a symlink to become a file' - echo git help > help || true - rm exec-2.sh - cp help exec-2.sh - git update-index exec-2.sh - git commit -m "$name" - - test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -f $SVN_TREE/exec-2.sh && - test ! -L $SVN_TREE/exec-2.sh && - diff -u help $SVN_TREE/exec-2.sh" -fi - +test_expect_success "$name" " + chmod +x exec.sh && + git update-index exec.sh && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch5 && + svn up '$SVN_TREE' && + test -x '$SVN_TREE'/exec.sh" + + +name='executable file becomes a symlink to bar/zzz (file)' +test_expect_success "$name" " + rm exec.sh && + ln -s bar/zzz exec.sh && + git update-index exec.sh && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch5 && + svn up '$SVN_TREE' && + test -L '$SVN_TREE'/exec.sh" + +name='new symlink is added to a file that was also just made executable' + +test_expect_success "$name" " + chmod +x bar/zzz && + ln -s bar/zzz exec-2.sh && + git update-index --add bar/zzz exec-2.sh && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch5 && + svn up '$SVN_TREE' && + test -x '$SVN_TREE'/bar/zzz && + test -L '$SVN_TREE'/exec-2.sh" + +name='modify a symlink to become a file' +test_expect_success "$name" " + echo git help > help || true && + rm exec-2.sh && + cp help exec-2.sh && + git update-index exec-2.sh && + git commit -m '$name' && + git-svn set-tree --find-copies-harder --rmdir \ + remotes/git-svn..mybranch5 && + svn up '$SVN_TREE' && + test -f '$SVN_TREE'/exec-2.sh && + test ! -L '$SVN_TREE'/exec-2.sh && + diff -u help $SVN_TREE/exec-2.sh" if test "$have_utf8" = t then name="commit with UTF-8 message: locale: $GIT_SVN_LC_ALL" - echo '# hello' >> exec-2.sh - git update-index exec-2.sh - git commit -m 'éïâˆ' - export LC_ALL="$GIT_SVN_LC_ALL" - test_expect_success "$name" "git-svn commit HEAD" + LC_ALL="$GIT_SVN_LC_ALL" + export LC_ALL + test_expect_success "$name" " + echo '# hello' >> exec-2.sh && + git update-index exec-2.sh && + git commit -m 'éïâˆ' && + git-svn set-tree HEAD" unset LC_ALL else echo "UTF-8 locale not set, test skipped ($GIT_SVN_LC_ALL)" @@ -207,12 +195,6 @@ test_expect_success "$name" \ git-rev-list --pretty=raw remotes/alt | grep ^tree | uniq > b && diff -u a b" -if test -n "$NO_SYMLINK" -then - test_done - exit 0 -fi - name='check imported tree checksums expected tree checksums' rm -f expected if test "$have_utf8" = t @@ -228,6 +210,9 @@ tree 56a30b966619b863674f5978696f4a3594f2fca9 tree d667270a1f7b109f5eb3aaea21ede14b56bfdd6e tree 8f51f74cf0163afc9ad68a4b1537288c4558b5a4 EOF + +echo tree 4b825dc642cb6eb9a060e54bf8d69288fbee4904 >> expected + test_expect_success "$name" "diff -u a expected" test_done diff --git a/t/t9101-git-svn-props.sh b/t/t9101-git-svn-props.sh index a5a235f100..46fcec50a5 100755 --- a/t/t9101-git-svn-props.sh +++ b/t/t9101-git-svn-props.sh @@ -57,13 +57,10 @@ test_expect_success 'setup some commits to svn' \ 'cd test_wc && echo Greetings >> kw.c && svn commit -m "Not yet an Id" && - svn up && echo Hello world >> kw.c && svn commit -m "Modified file, but still not yet an Id" && - svn up && svn propset svn:keywords Id kw.c && - svn commit -m "Propset Id" && - svn up && + svn commit -m "Propset Id" cd ..' test_expect_success 'initialize git-svn' "git-svn init $svnrepo" @@ -74,7 +71,7 @@ test_expect_success "$name" \ 'git checkout -b mybranch remotes/git-svn && echo Hi again >> kw.c && git commit -a -m "test keywoards ignoring" && - git-svn commit remotes/git-svn..mybranch && + git-svn set-tree remotes/git-svn..mybranch && git pull . remotes/git-svn' expect='/* $Id$ */' @@ -86,8 +83,7 @@ test_expect_success "propset CR on crlf files" \ svn propset svn:eol-style CR empty && svn propset svn:eol-style CR crlf && svn propset svn:eol-style CR ne_crlf && - svn commit -m "propset CR on crlf files" && - svn up && + svn commit -m "propset CR on crlf files" cd ..' test_expect_success 'fetch and pull latest from svn and checkout a new wc' \ @@ -111,8 +107,7 @@ cd test_wc svn propset svn:eol-style CRLF ne_cr && svn propset svn:keywords Id cr && svn propset svn:keywords Id ne_cr && - svn commit -m "propset CRLF on cr files" && - svn up' + svn commit -m "propset CRLF on cr files"' cd .. test_expect_success 'fetch and pull latest from svn' \ 'git-svn fetch && git pull . remotes/git-svn' diff --git a/t/t9102-git-svn-deep-rmdir.sh b/t/t9102-git-svn-deep-rmdir.sh index d693d183c8..572aaedc06 100755 --- a/t/t9102-git-svn-deep-rmdir.sh +++ b/t/t9102-git-svn-deep-rmdir.sh @@ -21,7 +21,7 @@ test_expect_success 'mirror via git-svn' " test_expect_success 'Try a commit on rmdir' " git rm -f deeply/nested/directory/number/2/another && git commit -a -m 'remove another' && - git-svn commit --rmdir HEAD && + git-svn set-tree --rmdir HEAD && svn ls -R $svnrepo | grep ^deeply/nested/directory/number/1 " diff --git a/t/t9103-git-svn-graft-branches.sh b/t/t9103-git-svn-graft-branches.sh index cc62d4ece8..b5f7677021 100755 --- a/t/t9103-git-svn-graft-branches.sh +++ b/t/t9103-git-svn-graft-branches.sh @@ -1,6 +1,8 @@ test_description='git-svn graft-branches' . ./lib-git-svn.sh +svnrepo="$svnrepo/test-git-svn" + test_expect_success 'initialize repo' " mkdir import && cd import && @@ -14,25 +16,19 @@ test_expect_success 'initialize repo' " cd wc && echo feedme >> branches/a/readme && svn commit -m hungry && - svn up && cd trunk && svn merge -r3:4 $svnrepo/branches/a && svn commit -m 'merge with a' && cd ../.. && - svn log -v $svnrepo && - git-svn init -i trunk $svnrepo/trunk && - git-svn init -i a $svnrepo/branches/a && - git-svn init -i tags/a $svnrepo/tags/a && - git-svn fetch -i tags/a && - git-svn fetch -i a && - git-svn fetch -i trunk + git-svn multi-init $svnrepo -T trunk -b branches -t tags && + git-svn multi-fetch " r1=`git-rev-list remotes/trunk | tail -n1` r2=`git-rev-list remotes/tags/a | tail -n1` r3=`git-rev-list remotes/a | tail -n1` -r4=`git-rev-list remotes/a | head -n1` -r5=`git-rev-list remotes/trunk | head -n1` +r4=`git-rev-parse remotes/a` +r5=`git-rev-parse remotes/trunk` test_expect_success 'test graft-branches regexes and copies' " test -n "$r1" && diff --git a/t/t9104-git-svn-follow-parent.sh b/t/t9104-git-svn-follow-parent.sh index 01488ff78a..8d2e2fec39 100755 --- a/t/t9104-git-svn-follow-parent.sh +++ b/t/t9104-git-svn-follow-parent.sh @@ -6,13 +6,6 @@ test_description='git-svn --follow-parent fetching' . ./lib-git-svn.sh -if test -n "$GIT_SVN_NO_LIB" && test "$GIT_SVN_NO_LIB" -ne 0 -then - echo 'Skipping: --follow-parent needs SVN libraries' - test_done - exit 0 -fi - test_expect_success 'initialize repo' " mkdir import && cd import && diff --git a/t/t9105-git-svn-commit-diff.sh b/t/t9105-git-svn-commit-diff.sh index f994b72f80..6323c7e3ac 100755 --- a/t/t9105-git-svn-commit-diff.sh +++ b/t/t9105-git-svn-commit-diff.sh @@ -4,13 +4,6 @@ test_description='git-svn commit-diff' . ./lib-git-svn.sh -if test -n "$GIT_SVN_NO_LIB" && test "$GIT_SVN_NO_LIB" -ne 0 -then - echo 'Skipping: commit-diff needs SVN libraries' - test_done - exit 0 -fi - test_expect_success 'initialize repo' " mkdir import && cd import && @@ -33,7 +26,7 @@ prev=`git rev-parse --verify HEAD^1` test_expect_success 'test the commit-diff command' " test -n '$prev' && test -n '$head' && - git-svn commit-diff '$prev' '$head' '$svnrepo' && + git-svn commit-diff -r1 '$prev' '$head' '$svnrepo' && svn co $svnrepo wc && cmp readme wc/readme " diff --git a/t/t9106-git-svn-commit-diff-clobber.sh b/t/t9106-git-svn-commit-diff-clobber.sh new file mode 100755 index 0000000000..59b6425ce4 --- /dev/null +++ b/t/t9106-git-svn-commit-diff-clobber.sh @@ -0,0 +1,67 @@ +#!/bin/sh +# +# Copyright (c) 2006 Eric Wong +test_description='git-svn commit-diff clobber' +. ./lib-git-svn.sh + +test_expect_success 'initialize repo' " + mkdir import && + cd import && + echo initial > file && + svn import -m 'initial' . $svnrepo && + cd .. && + echo initial > file && + git update-index --add file && + git commit -a -m 'initial' + " +test_expect_success 'commit change from svn side' " + svn co $svnrepo t.svn && + cd t.svn && + echo second line from svn >> file && + svn commit -m 'second line from svn' && + cd .. && + rm -rf t.svn + " + +test_expect_failure 'commit conflicting change from git' " + echo second line from git >> file && + git commit -a -m 'second line from git' && + git-svn commit-diff -r1 HEAD~1 HEAD $svnrepo + " || true + +test_expect_success 'commit complementing change from git' " + git reset --hard HEAD~1 && + echo second line from svn >> file && + git commit -a -m 'second line from svn' && + echo third line from git >> file && + git commit -a -m 'third line from git' && + git-svn commit-diff -r2 HEAD~1 HEAD $svnrepo + " + +test_expect_failure 'dcommit fails to commit because of conflict' " + git-svn init $svnrepo && + git-svn fetch && + git reset --hard refs/remotes/git-svn && + svn co $svnrepo t.svn && + cd t.svn && + echo fourth line from svn >> file && + svn commit -m 'fourth line from svn' && + cd .. && + rm -rf t.svn && + echo 'fourth line from git' >> file && + git commit -a -m 'fourth line from git' && + git-svn dcommit + " || true + +test_expect_success 'dcommit does the svn equivalent of an index merge' " + git reset --hard refs/remotes/git-svn && + echo 'index merge' > file2 && + git update-index --add file2 && + git commit -a -m 'index merge' && + echo 'more changes' >> file2 && + git update-index file2 && + git commit -a -m 'more changes' && + git-svn dcommit + " + +test_done diff --git a/t/t9200-git-cvsexportcommit.sh b/t/t9200-git-cvsexportcommit.sh new file mode 100755 index 0000000000..315119abff --- /dev/null +++ b/t/t9200-git-cvsexportcommit.sh @@ -0,0 +1,215 @@ +#!/bin/bash +# +# Copyright (c) Robin Rosenberg +# +test_description='CVS export comit. ' + +. ./test-lib.sh + +cvs >/dev/null 2>&1 +if test $? -ne 1 +then + test_expect_success 'skipping git-cvsexportcommit tests, cvs not found' : + test_done + exit +fi + +CVSROOT=$(pwd)/cvsroot +CVSWORK=$(pwd)/cvswork +GIT_DIR=$(pwd)/.git +export CVSROOT CVSWORK GIT_DIR + +rm -rf "$CVSROOT" "$CVSWORK" +mkdir "$CVSROOT" && +cvs init && +cvs -Q co -d "$CVSWORK" . && +echo >empty && +git add empty && +git commit -q -a -m "Initial" 2>/dev/null || +exit 1 + +test_expect_success \ + 'New file' \ + 'mkdir A B C D E F && + echo hello1 >A/newfile1.txt && + echo hello2 >B/newfile2.txt && + cp ../test9200a.png C/newfile3.png && + cp ../test9200a.png D/newfile4.png && + git add A/newfile1.txt && + git add B/newfile2.txt && + git add C/newfile3.png && + git add D/newfile4.png && + git commit -a -m "Test: New file" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git cvsexportcommit -c $id && + test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.1/" && + test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "newfile2.txt/1.1/" && + test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "newfile3.png/1.1/-kb" && + test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "newfile4.png/1.1/-kb" && + diff A/newfile1.txt ../A/newfile1.txt && + diff B/newfile2.txt ../B/newfile2.txt && + diff C/newfile3.png ../C/newfile3.png && + diff D/newfile4.png ../D/newfile4.png + )' + +test_expect_success \ + 'Remove two files, add two and update two' \ + 'echo Hello1 >>A/newfile1.txt && + rm -f B/newfile2.txt && + rm -f C/newfile3.png && + echo Hello5 >E/newfile5.txt && + cp ../test9200b.png D/newfile4.png && + cp ../test9200a.png F/newfile6.png && + git add E/newfile5.txt && + git add F/newfile6.png && + git commit -a -m "Test: Remove, add and update" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git cvsexportcommit -c $id && + test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.2/" && + test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "newfile4.png/1.2/-kb" && + test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" && + test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" && + diff A/newfile1.txt ../A/newfile1.txt && + diff D/newfile4.png ../D/newfile4.png && + diff E/newfile5.txt ../E/newfile5.txt && + diff F/newfile6.png ../F/newfile6.png + )' + +# Should fail (but only on the git-cvsexportcommit stage) +test_expect_success \ + 'Fail to change binary more than one generation old' \ + 'cat F/newfile6.png >>D/newfile4.png && + git commit -a -m "generatiion 1" && + cat F/newfile6.png >>D/newfile4.png && + git commit -a -m "generation 2" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + ! git cvsexportcommit -c $id + )' + +#test_expect_success \ +# 'Fail to remove binary file more than one generation old' \ +# 'git reset --hard HEAD^ && +# cat F/newfile6.png >>D/newfile4.png && +# git commit -a -m "generation 2 (again)" && +# rm -f D/newfile4.png && +# git commit -a -m "generation 3" && +# id=$(git rev-list --max-count=1 HEAD) && +# (cd "$CVSWORK" && +# ! git cvsexportcommit -c $id +# )' + +# We reuse the state from two tests back here + +# This test is here because a patch for only binary files will +# fail with gnu patch, so cvsexportcommit must handle that. +test_expect_success \ + 'Remove only binary files' \ + 'git reset --hard HEAD^^ && + rm -f D/newfile4.png && + git commit -a -m "test: remove only a binary file" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git cvsexportcommit -c $id && + test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.2/" && + test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" && + test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" && + diff A/newfile1.txt ../A/newfile1.txt && + diff E/newfile5.txt ../E/newfile5.txt && + diff F/newfile6.png ../F/newfile6.png + )' + +test_expect_success \ + 'Remove only a text file' \ + 'rm -f A/newfile1.txt && + git commit -a -m "test: remove only a binary file" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git cvsexportcommit -c $id && + test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "" && + test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" && + test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" && + diff E/newfile5.txt ../E/newfile5.txt && + diff F/newfile6.png ../F/newfile6.png + )' + +test_expect_success \ + 'New file with spaces in file name' \ + 'mkdir "G g" && + echo ok then >"G g/with spaces.txt" && + git add "G g/with spaces.txt" && \ + cp ../test9200a.png "G g/with spaces.png" && \ + git add "G g/with spaces.png" && + git commit -a -m "With spaces" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git-cvsexportcommit -c $id && + test "$(echo $(sort "G g/CVS/Entries"|cut -d/ -f2,3,5))" = "with spaces.png/1.1/-kb with spaces.txt/1.1/" + )' + +test_expect_success \ + 'Update file with spaces in file name' \ + 'echo Ok then >>"G g/with spaces.txt" && + cat ../test9200a.png >>"G g/with spaces.png" && \ + git add "G g/with spaces.png" && + git commit -a -m "Update with spaces" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git-cvsexportcommit -c $id + test "$(echo $(sort "G g/CVS/Entries"|cut -d/ -f2,3,5))" = "with spaces.png/1.2/-kb with spaces.txt/1.2/" + )' + +# This test contains ISO-8859-1 characters +test_expect_success \ + 'File with non-ascii file name' \ + 'mkdir -p Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö && + echo Foo >Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö/gårdetsågårdet.txt && + git add Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö/gårdetsågårdet.txt && + cp ../test9200a.png Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö/gårdetsågårdet.png && + git add Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö/gårdetsågårdet.png && + git commit -a -m "Går det så går det" && \ + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + git-cvsexportcommit -v -c $id && + test "$(echo $(sort Å/goo/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z/å/ä/ö/CVS/Entries|cut -d/ -f2,3,5))" = "gårdetsågårdet.png/1.1/-kb gårdetsågårdet.txt/1.1/" + )' + +test_expect_success \ + 'Mismatching patch should fail' \ + 'date >>"E/newfile5.txt" && + git add "E/newfile5.txt" && + git commit -a -m "Update one" && + date >>"E/newfile5.txt" && + git add "E/newfile5.txt" && + git commit -a -m "Update two" && + id=$(git rev-list --max-count=1 HEAD) && + (cd "$CVSWORK" && + ! git-cvsexportcommit -c $id + )' + +test_expect_success \ + 'Retain execute bit' \ + 'mkdir G && + echo executeon >G/on && + chmod +x G/on && + echo executeoff >G/off && + git add G/on && + git add G/off && + git commit -a -m "Execute test" && + (cd "$CVSWORK" && + git-cvsexportcommit -c HEAD + test -x G/on && + ! test -x G/off + )' + +test_done diff --git a/t/test-lib.sh b/t/test-lib.sh index 470a909891..8e3ee6cd7b 100755 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -28,13 +28,21 @@ unset GIT_DIR unset GIT_EXTERNAL_DIFF unset GIT_INDEX_FILE unset GIT_OBJECT_DIRECTORY -unset GIT_TRACE unset SHA1_FILE_DIRECTORIES unset SHA1_FILE_DIRECTORY export GIT_AUTHOR_EMAIL GIT_AUTHOR_NAME export GIT_COMMITTER_EMAIL GIT_COMMITTER_NAME export EDITOR VISUAL +case $(echo $GIT_TRACE |tr "[A-Z]" "[a-z]") in + 1|2|true) + echo "* warning: Some tests will not work if GIT_TRACE" \ + "is set as to trace on STDERR ! *" + echo "* warning: Please set GIT_TRACE to something" \ + "other than 1, 2 or true ! *" + ;; +esac + # Each test should start with something like this, after copyright notices: # # test_description='Description of this test... @@ -68,7 +76,8 @@ do -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) verbose=t; shift ;; --no-python) - no_python=t; shift ;; + # noop now... + shift ;; *) break ;; esac @@ -87,6 +96,17 @@ test_count=0 trap 'echo >&5 "FATAL: Unexpected exit with code $?"; exit 1' exit +test_tick () { + if test -z "${test_tick+set}" + then + test_tick=1112911993 + else + test_tick=$(($test_tick + 60)) + fi + GIT_COMMITTER_DATE="$test_tick -0700" + GIT_AUTHOR_DATE="$test_tick -0700" + export GIT_COMMITTER_DATE GIT_AUTHOR_DATE +} # You are not expected to call test_ok_ and test_failure_ directly, use # the text_expect_* functions instead. @@ -116,43 +136,79 @@ test_run_ () { return 0 } +test_skip () { + this_test=$(expr "./$0" : '.*/\(t[0-9]*\)-[^/]*$') + this_test="$this_test.$(expr "$test_count" + 1)" + to_skip= + for skp in $GIT_SKIP_TESTS + do + case "$this_test" in + $skp) + to_skip=t + esac + done + case "$to_skip" in + t) + say >&3 "skipping test: $@" + test_count=$(expr "$test_count" + 1) + say "skip $test_count: $1" + : true + ;; + *) + false + ;; + esac +} + test_expect_failure () { test "$#" = 2 || error "bug in the test script: not 2 parameters to test-expect-failure" - say >&3 "expecting failure: $2" - test_run_ "$2" - if [ "$?" = 0 -a "$eval_ret" != 0 ] + if ! test_skip "$@" then - test_ok_ "$1" - else - test_failure_ "$@" + say >&3 "expecting failure: $2" + test_run_ "$2" + if [ "$?" = 0 -a "$eval_ret" != 0 -a "$eval_ret" -lt 129 ] + then + test_ok_ "$1" + else + test_failure_ "$@" + fi fi + echo >&3 "" } test_expect_success () { test "$#" = 2 || error "bug in the test script: not 2 parameters to test-expect-success" - say >&3 "expecting success: $2" - test_run_ "$2" - if [ "$?" = 0 -a "$eval_ret" = 0 ] + if ! test_skip "$@" then - test_ok_ "$1" - else - test_failure_ "$@" + say >&3 "expecting success: $2" + test_run_ "$2" + if [ "$?" = 0 -a "$eval_ret" = 0 ] + then + test_ok_ "$1" + else + test_failure_ "$@" + fi fi + echo >&3 "" } test_expect_code () { test "$#" = 3 || error "bug in the test script: not 3 parameters to test-expect-code" - say >&3 "expecting exit code $1: $3" - test_run_ "$3" - if [ "$?" = 0 -a "$eval_ret" = "$1" ] + if ! test_skip "$@" then - test_ok_ "$2" - else - test_failure_ "$@" + say >&3 "expecting exit code $1: $3" + test_run_ "$3" + if [ "$?" = 0 -a "$eval_ret" = "$1" ] + then + test_ok_ "$2" + else + test_failure_ "$@" + fi fi + echo >&3 "" } # Most tests can use the created repository, but some amy need to create more. @@ -164,8 +220,8 @@ test_create_repo () { repo="$1" mkdir "$repo" cd "$repo" || error "Cannot setup test environment" - "$GIT_EXEC_PATH/git" init-db --template=$GIT_EXEC_PATH/templates/blt/ 2>/dev/null || - error "cannot run git init-db -- have you built things yet?" + "$GIT_EXEC_PATH/git" init --template=$GIT_EXEC_PATH/templates/blt/ >/dev/null 2>&1 || + error "cannot run git init -- have you built things yet?" mv .git/hooks .git/hooks-disabled cd "$owd" } @@ -196,20 +252,12 @@ test_done () { # t/ subdirectory and are run in trash subdirectory. PATH=$(pwd)/..:$PATH GIT_EXEC_PATH=$(pwd)/.. -export PATH GIT_EXEC_PATH - -# Similarly use ../compat/subprocess.py if our python does not -# have subprocess.py on its own. -PYTHON=`sed -e '1{ - s/^#!// - q -}' ../git-merge-recursive` || { - error "You haven't built things yet, have you?" -} -"$PYTHON" -c 'import subprocess' 2>/dev/null || { - PYTHONPATH=$(pwd)/../compat - export PYTHONPATH -} +GIT_TEMPLATE_DIR=$(pwd)/../templates/blt +HOME=$(pwd)/trash +export PATH GIT_EXEC_PATH GIT_TEMPLATE_DIR HOME + +GITPERLLIB=$(pwd)/../perl/blib/lib:$(pwd)/../perl/blib/arch/auto/Git +export GITPERLLIB test -d ../templates/blt || { error "You haven't built things yet, have you?" } @@ -219,3 +267,22 @@ test=trash rm -fr "$test" test_create_repo $test cd "$test" + +this_test=$(expr "./$0" : '.*/\(t[0-9]*\)-[^/]*$') +for skp in $GIT_SKIP_TESTS +do + to_skip= + for skp in $GIT_SKIP_TESTS + do + case "$this_test" in + $skp) + to_skip=t + esac + done + case "$to_skip" in + t) + say >&3 "skipping test $this_test altogether" + say "skip all tests in $this_test" + test_done + esac +done diff --git a/t/test9200a.png b/t/test9200a.png Binary files differnew file mode 100644 index 0000000000..7b181d15ce --- /dev/null +++ b/t/test9200a.png diff --git a/t/test9200b.png b/t/test9200b.png Binary files differnew file mode 100644 index 0000000000..ac22ccbd3e --- /dev/null +++ b/t/test9200b.png diff --git a/templates/hooks--commit-msg b/templates/hooks--commit-msg index 0b906caa98..9b04f2d69c 100644 --- a/templates/hooks--commit-msg +++ b/templates/hooks--commit-msg @@ -8,6 +8,10 @@ # # To enable this hook, make this file executable. +# Uncomment the below to add a Signed-off-by line to the message. +# SOB=$(git var GIT_AUTHOR_IDENT | sed -n 's/^\(.*>\).*$/Signed-off-by: \1/p') +# grep -qs "^$SOB" "$1" || echo "$SOB" >> "$1" + # This example catches duplicate Signed-off-by lines. test "" = "$(grep '^Signed-off-by: ' "$1" | diff --git a/templates/hooks--update b/templates/hooks--update index 76d5ac2477..9863a800c8 100644 --- a/templates/hooks--update +++ b/templates/hooks--update @@ -19,7 +19,7 @@ ref_type=$(git cat-file -t "$3") case "$1","$ref_type" in refs/tags/*,commit) echo "*** Un-annotated tags are not allowed in this repo" >&2 - echo "*** Use 'git tag [ -a | -s ]' for tags you want to propagate." + echo "*** Use 'git tag [ -a | -s ]' for tags you want to propagate." >&2 exit 1;; refs/tags/*,tag) echo "### Pushing version '${1##refs/tags/}' to the masses" >&2 diff --git a/templates/remotes-- b/templates/remotes-- deleted file mode 100644 index fae88709a6..0000000000 --- a/templates/remotes-- +++ /dev/null @@ -1 +0,0 @@ -: this is just to ensure the directory exists. diff --git a/test-date.c b/test-date.c index 93e802759f..62e8f2387a 100644 --- a/test-date.c +++ b/test-date.c @@ -1,6 +1,3 @@ -#include <stdio.h> -#include <time.h> - #include "cache.h" int main(int argc, char **argv) diff --git a/test-delta.c b/test-delta.c index 1be8ee0c72..16595ef0a9 100644 --- a/test-delta.c +++ b/test-delta.c @@ -8,13 +8,7 @@ * published by the Free Software Foundation. */ -#include <stdio.h> -#include <unistd.h> -#include <string.h> -#include <fcntl.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/mman.h> +#include "git-compat-util.h" #include "delta.h" static const char usage[] = @@ -74,7 +68,7 @@ int main(int argc, char *argv[]) } fd = open (argv[4], O_WRONLY|O_CREAT|O_TRUNC, 0666); - if (fd < 0 || write(fd, out_buf, out_size) != out_size) { + if (fd < 0 || write_in_full(fd, out_buf, out_size) != out_size) { perror(argv[4]); return 1; } diff --git a/trace.c b/trace.c new file mode 100644 index 0000000000..27fef868c4 --- /dev/null +++ b/trace.c @@ -0,0 +1,150 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) 2000-2002 Michael R. Elkins <me@mutt.org> + * Copyright (C) 2002-2004 Oswald Buddenhagen <ossi@users.sf.net> + * Copyright (C) 2004 Theodore Y. Ts'o <tytso@mit.edu> + * Copyright (C) 2006 Mike McCormack + * Copyright (C) 2006 Christian Couder + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include "cache.h" +#include "quote.h" + +/* Stolen from "imap-send.c". */ +static int git_vasprintf(char **strp, const char *fmt, va_list ap) +{ + int len; + char tmp[1024]; + + if ((len = vsnprintf(tmp, sizeof(tmp), fmt, ap)) < 0 || + !(*strp = xmalloc(len + 1))) + return -1; + if (len >= (int)sizeof(tmp)) + vsprintf(*strp, fmt, ap); + else + memcpy(*strp, tmp, len + 1); + return len; +} + +/* Stolen from "imap-send.c". */ +int nfvasprintf(char **str, const char *fmt, va_list va) +{ + int ret = git_vasprintf(str, fmt, va); + if (ret < 0) + die("Fatal: Out of memory\n"); + return ret; +} + +/* Get a trace file descriptor from GIT_TRACE env variable. */ +static int get_trace_fd(int *need_close) +{ + char *trace = getenv("GIT_TRACE"); + + if (!trace || !strcmp(trace, "") || + !strcmp(trace, "0") || !strcasecmp(trace, "false")) + return 0; + if (!strcmp(trace, "1") || !strcasecmp(trace, "true")) + return STDERR_FILENO; + if (strlen(trace) == 1 && isdigit(*trace)) + return atoi(trace); + if (*trace == '/') { + int fd = open(trace, O_WRONLY | O_APPEND | O_CREAT, 0666); + if (fd == -1) { + fprintf(stderr, + "Could not open '%s' for tracing: %s\n" + "Defaulting to tracing on stderr...\n", + trace, strerror(errno)); + return STDERR_FILENO; + } + *need_close = 1; + return fd; + } + + fprintf(stderr, "What does '%s' for GIT_TRACE means ?\n", trace); + fprintf(stderr, "If you want to trace into a file, " + "then please set GIT_TRACE to an absolute pathname " + "(starting with /).\n"); + fprintf(stderr, "Defaulting to tracing on stderr...\n"); + + return STDERR_FILENO; +} + +static const char err_msg[] = "Could not trace into fd given by " + "GIT_TRACE environment variable"; + +void trace_printf(const char *format, ...) +{ + char *trace_str; + va_list rest; + int need_close = 0; + int fd = get_trace_fd(&need_close); + + if (!fd) + return; + + va_start(rest, format); + nfvasprintf(&trace_str, format, rest); + va_end(rest); + + write_or_whine_pipe(fd, trace_str, strlen(trace_str), err_msg); + + free(trace_str); + + if (need_close) + close(fd); +} + +void trace_argv_printf(const char **argv, int count, const char *format, ...) +{ + char *argv_str, *format_str, *trace_str; + size_t argv_len, format_len, trace_len; + va_list rest; + int need_close = 0; + int fd = get_trace_fd(&need_close); + + if (!fd) + return; + + /* Get the argv string. */ + argv_str = sq_quote_argv(argv, count); + argv_len = strlen(argv_str); + + /* Get the formated string. */ + va_start(rest, format); + nfvasprintf(&format_str, format, rest); + va_end(rest); + + /* Allocate buffer for trace string. */ + format_len = strlen(format_str); + trace_len = argv_len + format_len + 1; /* + 1 for \n */ + trace_str = xmalloc(trace_len + 1); + + /* Copy everything into the trace string. */ + strncpy(trace_str, format_str, format_len); + strncpy(trace_str + format_len, argv_str, argv_len); + strcpy(trace_str + trace_len - 1, "\n"); + + write_or_whine_pipe(fd, trace_str, trace_len, err_msg); + + free(argv_str); + free(format_str); + free(trace_str); + + if (need_close) + close(fd); +} diff --git a/tree-diff.c b/tree-diff.c index 7e2f4f088a..37d235e06e 100644 --- a/tree-diff.c +++ b/tree-diff.c @@ -215,6 +215,24 @@ int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const cha return retval; } +int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt) +{ + int retval; + void *tree; + struct tree_desc empty, real; + + tree = read_object_with_reference(new, tree_type, &real.size, NULL); + if (!tree) + die("unable to read root tree (%s)", sha1_to_hex(new)); + real.buf = tree; + + empty.size = 0; + empty.buf = ""; + retval = diff_tree(&empty, &real, base, opt); + free(tree); + return retval; +} + static int count_paths(const char **paths) { int i = 0; diff --git a/tree-walk.c b/tree-walk.c index 14cc5aea6c..70f899957e 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -113,7 +113,6 @@ void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callb struct name_entry *entry = xmalloc(n*sizeof(*entry)); for (;;) { - struct name_entry entry[3]; unsigned long mask = 0; int i, last; @@ -200,10 +199,17 @@ int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned ch int retval; void *tree; struct tree_desc t; + unsigned char root[20]; - tree = read_object_with_reference(tree_sha1, tree_type, &t.size, NULL); + tree = read_object_with_reference(tree_sha1, tree_type, &t.size, root); if (!tree) return -1; + + if (name[0] == '\0') { + hashcpy(sha1, root); + return 0; + } + t.buf = tree; retval = find_tree_entry(&t, name, sha1, mode); free(tree); @@ -4,7 +4,6 @@ #include "commit.h" #include "tag.h" #include "tree-walk.h" -#include <stdlib.h> const char *tree_type = "tree"; diff --git a/unpack-file.c b/unpack-file.c index ccddf1d4b0..d24acc2a67 100644 --- a/unpack-file.c +++ b/unpack-file.c @@ -17,7 +17,7 @@ static char *create_temp_file(unsigned char *sha1) fd = mkstemp(path); if (fd < 0) die("unable to create temp-file"); - if (write(fd, buf, size) != size) + if (write_in_full(fd, buf, size) != size) die("unable to write temp-file"); close(fd); return path; diff --git a/unpack-trees.c b/unpack-trees.c index 3ac0289b3a..2e2232cbb0 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1,6 +1,5 @@ -#include <signal.h> -#include <sys/time.h> #include "cache.h" +#include "dir.h" #include "tree.h" #include "tree-walk.h" #include "cache-tree.h" @@ -77,6 +76,12 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len, { int baselen = strlen(base); int src_size = len + 1; + int i_stk = i_stk; + int retval = 0; + + if (o->dir) + i_stk = push_exclude_per_directory(o->dir, base, strlen(base)); + do { int i; const char *first; @@ -143,7 +148,7 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len, } /* No name means we're done */ if (!first) - return 0; + goto leave_directory; pathlen = strlen(first); ce_size = cache_entry_size(baselen + pathlen); @@ -240,13 +245,20 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len, newbase[baselen + pathlen] = '/'; newbase[baselen + pathlen + 1] = '\0'; if (unpack_trees_rec(subposns, len, newbase, o, - indpos, df_conflict_list)) - return -1; + indpos, df_conflict_list)) { + retval = -1; + goto leave_directory; + } free(newbase); } free(subposns); free(src); } while (1); + + leave_directory: + if (o->dir) + pop_exclude_per_directory(o->dir, i_stk); + return retval; } /* Unlink the last component and attempt to remove leading @@ -370,7 +382,7 @@ int unpack_trees(struct object_list *trees, struct unpack_trees_options *o) int i; struct object_list *posn = trees; struct tree_entry_list df_conflict_list; - struct cache_entry df_conflict_entry; + static struct cache_entry *dfc; memset(&df_conflict_list, 0, sizeof(df_conflict_list)); df_conflict_list.next = &df_conflict_list; @@ -381,8 +393,10 @@ int unpack_trees(struct object_list *trees, struct unpack_trees_options *o) state.refresh_cache = 1; o->merge_size = len; - memset(&df_conflict_entry, 0, sizeof(df_conflict_entry)); - o->df_conflict_entry = &df_conflict_entry; + + if (!dfc) + dfc = xcalloc(1, sizeof(struct cache_entry) + 1); + o->df_conflict_entry = dfc; if (len) { posns = xmalloc(len * sizeof(struct tree_entry_list *)); @@ -456,7 +470,7 @@ static void invalidate_ce_path(struct cache_entry *ce) /* * We do not want to remove or overwrite a working tree file that - * is not tracked. + * is not tracked, unless it is ignored. */ static void verify_absent(const char *path, const char *action, struct unpack_trees_options *o) @@ -465,7 +479,7 @@ static void verify_absent(const char *path, const char *action, if (o->index_only || o->reset || !o->update) return; - if (!lstat(path, &st)) + if (!lstat(path, &st) && !(o->dir && excluded(o->dir, path))) die("Untracked working tree file '%s' " "would be %s by merge.", path, action); } @@ -642,7 +656,7 @@ int threeway_merge(struct cache_entry **stages, (remote_deleted && head && head_match)) { if (index) return deleted_entry(index, index, o); - else if (path) + else if (path && !head_deleted) verify_absent(path, "removed", o); return 0; } @@ -661,8 +675,6 @@ int threeway_merge(struct cache_entry **stages, if (index) { verify_uptodate(index, o); } - else if (path) - verify_absent(path, "overwritten", o); o->nontrivial_merge = 1; diff --git a/unpack-trees.h b/unpack-trees.h index c4601621cd..191f7442f1 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -16,6 +16,7 @@ struct unpack_trees_options { int verbose_update; int aggressive; const char *prefix; + struct dir_struct *dir; merge_fn_t fn; int head_idx; diff --git a/upload-pack.c b/upload-pack.c index 51ce936b06..3a466c6a3e 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -1,24 +1,38 @@ -#include <signal.h> -#include <sys/wait.h> -#include <sys/poll.h> #include "cache.h" #include "refs.h" #include "pkt-line.h" +#include "sideband.h" #include "tag.h" #include "object.h" #include "commit.h" #include "exec_cmd.h" +#include "diff.h" +#include "revision.h" +#include "list-objects.h" static const char upload_pack_usage[] = "git-upload-pack [--strict] [--timeout=nn] <dir>"; -#define THEY_HAVE (1U << 0) -#define OUR_REF (1U << 1) -#define WANTED (1U << 2) +/* bits #0..7 in revision.h, #8..10 in commit.c */ +#define THEY_HAVE (1u << 11) +#define OUR_REF (1u << 12) +#define WANTED (1u << 13) +#define COMMON_KNOWN (1u << 14) +#define REACHABLE (1u << 15) + +#define SHALLOW (1u << 16) +#define NOT_SHALLOW (1u << 17) +#define CLIENT_SHALLOW (1u << 18) + +static unsigned long oldest_have; + static int multi_ack, nr_our_refs; -static int use_thin_pack; +static int use_thin_pack, use_ofs_delta; static struct object_array have_obj; static struct object_array want_obj; static unsigned int timeout; +/* 0 for no sideband, + * otherwise maximum packet size (up to 65520 bytes). + */ static int use_sideband; static void reset_timeout(void) @@ -33,45 +47,53 @@ static int strip(char *line, int len) return len; } -#define PACKET_MAX 1000 static ssize_t send_client_data(int fd, const char *data, ssize_t sz) { - ssize_t ssz; - const char *p; - - if (!data) { - if (!use_sideband) - return 0; - packet_flush(1); + if (use_sideband) + return send_sideband(1, fd, data, sz, use_sideband); + if (fd == 3) + /* emergency quit */ + fd = 2; + if (fd == 2) { + /* XXX: are we happy to lose stuff here? */ + xwrite(fd, data, sz); + return sz; } + return safe_write(fd, data, sz); +} - if (!use_sideband) { - if (fd == 3) - /* emergency quit */ - fd = 2; - if (fd == 2) { - xwrite(fd, data, sz); - return sz; - } - return safe_write(fd, data, sz); - } - p = data; - ssz = sz; - while (sz) { - unsigned n; - char hdr[5]; - - n = sz; - if (PACKET_MAX - 5 < n) - n = PACKET_MAX - 5; - sprintf(hdr, "%04x", n + 5); - hdr[4] = fd; - safe_write(1, hdr, 5); - safe_write(1, p, n); - p += n; - sz -= n; +FILE *pack_pipe = NULL; +static void show_commit(struct commit *commit) +{ + if (commit->object.flags & BOUNDARY) + fputc('-', pack_pipe); + if (fputs(sha1_to_hex(commit->object.sha1), pack_pipe) < 0) + die("broken output pipe"); + fputc('\n', pack_pipe); + fflush(pack_pipe); + free(commit->buffer); + commit->buffer = NULL; +} + +static void show_object(struct object_array_entry *p) +{ + /* An object with name "foo\n0000000..." can be used to + * confuse downstream git-pack-objects very badly. + */ + const char *ep = strchr(p->name, '\n'); + if (ep) { + fprintf(pack_pipe, "%s %.*s\n", sha1_to_hex(p->item->sha1), + (int) (ep - p->name), + p->name); } - return ssz; + else + fprintf(pack_pipe, "%s %s\n", + sha1_to_hex(p->item->sha1), p->name); +} + +static void show_edge(struct commit *commit) +{ + fprintf(pack_pipe, "-%s\n", sha1_to_hex(commit->object.sha1)); } static void create_pack_file(void) @@ -95,48 +117,40 @@ static void create_pack_file(void) if (!pid_rev_list) { int i; - int args; - const char **argv; - const char **p; - char *buf; + struct rev_info revs; - if (create_full_pack) { - args = 10; - use_thin_pack = 0; /* no point doing it */ - } - else - args = have_obj.nr + want_obj.nr + 5; - p = xmalloc(args * sizeof(char *)); - argv = (const char **) p; - buf = xmalloc(args * 45); + pack_pipe = fdopen(lp_pipe[1], "w"); - dup2(lp_pipe[1], 1); - close(0); - close(lp_pipe[0]); - close(lp_pipe[1]); - *p++ = "rev-list"; - *p++ = use_thin_pack ? "--objects-edge" : "--objects"; if (create_full_pack) - *p++ = "--all"; - else { + use_thin_pack = 0; /* no point doing it */ + init_revisions(&revs, NULL); + revs.tag_objects = 1; + revs.tree_objects = 1; + revs.blob_objects = 1; + if (use_thin_pack) + revs.edge_hint = 1; + + if (create_full_pack) { + const char *args[] = {"rev-list", "--all", NULL}; + setup_revisions(2, args, &revs, NULL); + } else { for (i = 0; i < want_obj.nr; i++) { struct object *o = want_obj.objects[i].item; - *p++ = buf; - memcpy(buf, sha1_to_hex(o->sha1), 41); - buf += 41; + /* why??? */ + o->flags &= ~UNINTERESTING; + add_pending_object(&revs, o, NULL); } - } - if (!create_full_pack) for (i = 0; i < have_obj.nr; i++) { struct object *o = have_obj.objects[i].item; - *p++ = buf; - *buf++ = '^'; - memcpy(buf, sha1_to_hex(o->sha1), 41); - buf += 41; + o->flags |= UNINTERESTING; + add_pending_object(&revs, o, NULL); } - *p++ = NULL; - execv_git_cmd(argv); - die("git-upload-pack: unable to exec git-rev-list"); + setup_revisions(0, NULL, &revs, NULL); + } + prepare_revision_walk(&revs); + mark_edges_uninteresting(revs.commits, &revs, show_edge); + traverse_commit_list(&revs, show_commit, show_object); + exit(0); } if (pipe(pu_pipe) < 0) @@ -160,7 +174,9 @@ static void create_pack_file(void) close(pu_pipe[1]); close(pe_pipe[0]); close(pe_pipe[1]); - execl_git_cmd("pack-objects", "--stdout", "--progress", NULL); + execl_git_cmd("pack-objects", "--stdout", "--progress", + use_ofs_delta ? "--delta-base-offset" : NULL, + NULL); kill(pid_rev_list, SIGKILL); die("git-upload-pack: unable to exec git-pack-objects"); } @@ -227,7 +243,7 @@ static void create_pack_file(void) *cp++ = buffered; outsz++; } - sz = read(pu_pipe[0], cp, + sz = xread(pu_pipe[0], cp, sizeof(data) - outsz); if (0 < sz) ; @@ -252,7 +268,7 @@ static void create_pack_file(void) /* Status ready; we ship that in the side-band * or dump to the standard error. */ - sz = read(pe_pipe[0], progress, + sz = xread(pe_pipe[0], progress, sizeof(progress)); if (0 < sz) send_client_data(2, progress, sz); @@ -308,7 +324,8 @@ static void create_pack_file(void) goto fail; fprintf(stderr, "flushed.\n"); } - send_client_data(1, NULL, 0); + if (use_sideband) + packet_flush(1); return; } fail: @@ -323,11 +340,12 @@ static void create_pack_file(void) static int got_sha1(char *hex, unsigned char *sha1) { struct object *o; + int we_knew_they_have = 0; if (get_sha1_hex(hex, sha1)) die("git-upload-pack: expected SHA1 object, got '%s'", hex); if (!has_sha1_file(sha1)) - return 0; + return -1; o = lookup_object(sha1); if (!(o && o->parsed)) @@ -336,22 +354,92 @@ static int got_sha1(char *hex, unsigned char *sha1) die("oops (%s)", sha1_to_hex(sha1)); if (o->type == OBJ_COMMIT) { struct commit_list *parents; + struct commit *commit = (struct commit *)o; if (o->flags & THEY_HAVE) - return 0; - o->flags |= THEY_HAVE; - for (parents = ((struct commit*)o)->parents; + we_knew_they_have = 1; + else + o->flags |= THEY_HAVE; + if (!oldest_have || (commit->date < oldest_have)) + oldest_have = commit->date; + for (parents = commit->parents; parents; parents = parents->next) parents->item->object.flags |= THEY_HAVE; } - add_object_array(o, NULL, &have_obj); + if (!we_knew_they_have) { + add_object_array(o, NULL, &have_obj); + return 1; + } + return 0; +} + +static int reachable(struct commit *want) +{ + struct commit_list *work = NULL; + + insert_by_date(want, &work); + while (work) { + struct commit_list *list = work->next; + struct commit *commit = work->item; + free(work); + work = list; + + if (commit->object.flags & THEY_HAVE) { + want->object.flags |= COMMON_KNOWN; + break; + } + if (!commit->object.parsed) + parse_object(commit->object.sha1); + if (commit->object.flags & REACHABLE) + continue; + commit->object.flags |= REACHABLE; + if (commit->date < oldest_have) + continue; + for (list = commit->parents; list; list = list->next) { + struct commit *parent = list->item; + if (!(parent->object.flags & REACHABLE)) + insert_by_date(parent, &work); + } + } + want->object.flags |= REACHABLE; + clear_commit_marks(want, REACHABLE); + free_commit_list(work); + return (want->object.flags & COMMON_KNOWN); +} + +static int ok_to_give_up(void) +{ + int i; + + if (!have_obj.nr) + return 0; + + for (i = 0; i < want_obj.nr; i++) { + struct object *want = want_obj.objects[i].item; + + if (want->flags & COMMON_KNOWN) + continue; + want = deref_tag(want, "a want line", 0); + if (!want || want->type != OBJ_COMMIT) { + /* no way to tell if this is reachable by + * looking at the ancestry chain alone, so + * leave a note to ourselves not to worry about + * this object anymore. + */ + want_obj.objects[i].item->flags |= COMMON_KNOWN; + continue; + } + if (!reachable((struct commit *)want)) + return 0; + } return 1; } static int get_common_commits(void) { static char line[1000]; - unsigned char sha1[20], last_sha1[20]; + unsigned char sha1[20]; + char hex[41], last_hex[41]; int len; track_object_refs = 0; @@ -368,21 +456,29 @@ static int get_common_commits(void) } len = strip(line, len); if (!strncmp(line, "have ", 5)) { - if (got_sha1(line+5, sha1) && - (multi_ack || have_obj.nr == 1)) { - packet_write(1, "ACK %s%s\n", - sha1_to_hex(sha1), - multi_ack ? " continue" : ""); - if (multi_ack) - hashcpy(last_sha1, sha1); + switch (got_sha1(line+5, sha1)) { + case -1: /* they have what we do not */ + if (multi_ack && ok_to_give_up()) + packet_write(1, "ACK %s continue\n", + sha1_to_hex(sha1)); + break; + default: + memcpy(hex, sha1_to_hex(sha1), 41); + if (multi_ack) { + const char *msg = "ACK %s continue\n"; + packet_write(1, msg, hex); + memcpy(last_hex, hex, 41); + } + else if (have_obj.nr == 1) + packet_write(1, "ACK %s\n", hex); + break; } continue; } if (!strcmp(line, "done")) { if (have_obj.nr > 0) { if (multi_ack) - packet_write(1, "ACK %s\n", - sha1_to_hex(last_sha1)); + packet_write(1, "ACK %s\n", last_hex); return 0; } packet_write(1, "NAK\n"); @@ -394,8 +490,9 @@ static int get_common_commits(void) static void receive_needs(void) { + struct object_array shallows = {0, 0, NULL}; static char line[1000]; - int len; + int len, depth = 0; for (;;) { struct object *o; @@ -403,8 +500,29 @@ static void receive_needs(void) len = packet_read_line(0, line, sizeof(line)); reset_timeout(); if (!len) - return; + break; + if (!strncmp("shallow ", line, 8)) { + unsigned char sha1[20]; + struct object *object; + use_thin_pack = 0; + if (get_sha1(line + 8, sha1)) + die("invalid shallow line: %s", line); + object = parse_object(sha1); + if (!object) + die("did not find object for %s", line); + object->flags |= CLIENT_SHALLOW; + add_object_array(object, NULL, &shallows); + continue; + } + if (!strncmp("deepen ", line, 7)) { + char *end; + use_thin_pack = 0; + depth = strtol(line + 7, &end, 0); + if (end == line + 7 || depth <= 0) + die("Invalid deepen: %s", line); + continue; + } if (strncmp("want ", line, 5) || get_sha1_hex(line+5, sha1_buf)) die("git-upload-pack: protocol error, " @@ -413,8 +531,12 @@ static void receive_needs(void) multi_ack = 1; if (strstr(line+45, "thin-pack")) use_thin_pack = 1; - if (strstr(line+45, "side-band")) - use_sideband = 1; + if (strstr(line+45, "ofs-delta")) + use_ofs_delta = 1; + if (strstr(line+45, "side-band-64k")) + use_sideband = LARGE_PACKET_MAX; + else if (strstr(line+45, "side-band")) + use_sideband = DEFAULT_PACKET_MAX; /* We have sent all our refs already, and the other end * should have chosen out of them; otherwise they are @@ -432,11 +554,58 @@ static void receive_needs(void) add_object_array(o, NULL, &want_obj); } } + if (depth == 0 && shallows.nr == 0) + return; + if (depth > 0) { + struct commit_list *result, *backup; + int i; + backup = result = get_shallow_commits(&want_obj, depth, + SHALLOW, NOT_SHALLOW); + while (result) { + struct object *object = &result->item->object; + if (!(object->flags & (CLIENT_SHALLOW|NOT_SHALLOW))) { + packet_write(1, "shallow %s", + sha1_to_hex(object->sha1)); + register_shallow(object->sha1); + } + result = result->next; + } + free_commit_list(backup); + for (i = 0; i < shallows.nr; i++) { + struct object *object = shallows.objects[i].item; + if (object->flags & NOT_SHALLOW) { + struct commit_list *parents; + packet_write(1, "unshallow %s", + sha1_to_hex(object->sha1)); + object->flags &= ~CLIENT_SHALLOW; + /* make sure the real parents are parsed */ + unregister_shallow(object->sha1); + object->parsed = 0; + parse_commit((struct commit *)object); + parents = ((struct commit *)object)->parents; + while (parents) { + add_object_array(&parents->item->object, + NULL, &want_obj); + parents = parents->next; + } + } + /* make sure commit traversal conforms to client */ + register_shallow(object->sha1); + } + packet_flush(1); + } else + if (shallows.nr > 0) { + int i; + for (i = 0; i < shallows.nr; i++) + register_shallow(shallows.objects[i].item->sha1); + } + free(shallows.objects); } -static int send_ref(const char *refname, const unsigned char *sha1) +static int send_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data) { - static const char *capabilities = "multi_ack thin-pack side-band"; + static const char *capabilities = "multi_ack thin-pack side-band" + " side-band-64k ofs-delta shallow"; struct object *o = parse_object(sha1); if (!o) @@ -462,8 +631,8 @@ static int send_ref(const char *refname, const unsigned char *sha1) static void upload_pack(void) { reset_timeout(); - head_ref(send_ref); - for_each_ref(send_ref); + head_ref(send_ref, NULL); + for_each_ref(send_ref, NULL); packet_flush(1); receive_needs(); if (want_obj.nr) { @@ -29,12 +29,17 @@ static void error_builtin(const char *err, va_list params) report("error: ", err, params); } +static void warn_builtin(const char *warn, va_list params) +{ + report("warning: ", warn, params); +} /* If we are in a dlopen()ed .so write to a global variable would segfault * (ugh), so keep things static. */ static void (*usage_routine)(const char *err) NORETURN = usage_builtin; static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin; static void (*error_routine)(const char *err, va_list params) = error_builtin; +static void (*warn_routine)(const char *err, va_list params) = warn_builtin; void set_usage_routine(void (*routine)(const char *err) NORETURN) { @@ -51,6 +56,11 @@ void set_error_routine(void (*routine)(const char *err, va_list params)) error_routine = routine; } +void set_warn_routine(void (*routine)(const char *warn, va_list params)) +{ + warn_routine = routine; +} + void usage(const char *err) { @@ -75,3 +85,12 @@ int error(const char *err, ...) va_end(params); return -1; } + +void warn(const char *warn, ...) +{ + va_list params; + + va_start(params, warn); + warn_routine(warn, params); + va_end(params); +} diff --git a/utf8.c b/utf8.c new file mode 100644 index 0000000000..7c80eeccb4 --- /dev/null +++ b/utf8.c @@ -0,0 +1,341 @@ +#include "git-compat-util.h" +#include "utf8.h" + +/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */ + +struct interval { + int first; + int last; +}; + +/* auxiliary function for binary search in interval table */ +static int bisearch(wchar_t ucs, const struct interval *table, int max) { + int min = 0; + int mid; + + if (ucs < table[0].first || ucs > table[max].last) + return 0; + while (max >= min) { + mid = (min + max) / 2; + if (ucs > table[mid].last) + min = mid + 1; + else if (ucs < table[mid].first) + max = mid - 1; + else + return 1; + } + + return 0; +} + +/* The following two functions define the column width of an ISO 10646 + * character as follows: + * + * - The null character (U+0000) has a column width of 0. + * + * - Other C0/C1 control characters and DEL will lead to a return + * value of -1. + * + * - Non-spacing and enclosing combining characters (general + * category code Mn or Me in the Unicode database) have a + * column width of 0. + * + * - SOFT HYPHEN (U+00AD) has a column width of 1. + * + * - Other format characters (general category code Cf in the Unicode + * database) and ZERO WIDTH SPACE (U+200B) have a column width of 0. + * + * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF) + * have a column width of 0. + * + * - Spacing characters in the East Asian Wide (W) or East Asian + * Full-width (F) category as defined in Unicode Technical + * Report #11 have a column width of 2. + * + * - All remaining characters (including all printable + * ISO 8859-1 and WGL4 characters, Unicode control characters, + * etc.) have a column width of 1. + * + * This implementation assumes that wchar_t characters are encoded + * in ISO 10646. + */ + +static int wcwidth(wchar_t ch) +{ + /* + * Sorted list of non-overlapping intervals of non-spacing characters, + * generated by + * "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c". + */ + static const struct interval combining[] = { + { 0x0300, 0x0357 }, { 0x035D, 0x036F }, { 0x0483, 0x0486 }, + { 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 }, + { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, + { 0x05C4, 0x05C4 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 }, + { 0x064B, 0x0658 }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 }, + { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F }, + { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, + { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 }, + { 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, + { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, + { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, + { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, + { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, + { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, + { 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, + { 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, + { 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, + { 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, + { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, + { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, + { 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, + { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, + { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, + { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, + { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, + { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, + { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, + { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, + { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 }, + { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x1712, 0x1714 }, + { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 }, + { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 }, + { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D }, + { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 }, + { 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x200B, 0x200F }, + { 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F }, + { 0x20D0, 0x20EA }, { 0x302A, 0x302F }, { 0x3099, 0x309A }, + { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 }, + { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 }, + { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, + { 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 }, + { 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF } + }; + + /* test for 8-bit control characters */ + if (ch == 0) + return 0; + if (ch < 32 || (ch >= 0x7f && ch < 0xa0)) + return -1; + + /* binary search in table of non-spacing characters */ + if (bisearch(ch, combining, sizeof(combining) + / sizeof(struct interval) - 1)) + return 0; + + /* + * If we arrive here, ch is neither a combining nor a C0/C1 + * control character. + */ + + return 1 + + (ch >= 0x1100 && + /* Hangul Jamo init. consonants */ + (ch <= 0x115f || + ch == 0x2329 || ch == 0x232a || + /* CJK ... Yi */ + (ch >= 0x2e80 && ch <= 0xa4cf && + ch != 0x303f) || + /* Hangul Syllables */ + (ch >= 0xac00 && ch <= 0xd7a3) || + /* CJK Compatibility Ideographs */ + (ch >= 0xf900 && ch <= 0xfaff) || + /* CJK Compatibility Forms */ + (ch >= 0xfe30 && ch <= 0xfe6f) || + /* Fullwidth Forms */ + (ch >= 0xff00 && ch <= 0xff60) || + (ch >= 0xffe0 && ch <= 0xffe6) || + (ch >= 0x20000 && ch <= 0x2fffd) || + (ch >= 0x30000 && ch <= 0x3fffd))); +} + +/* + * This function returns the number of columns occupied by the character + * pointed to by the variable start. The pointer is updated to point at + * the next character. If it was not valid UTF-8, the pointer is set to NULL. + */ +int utf8_width(const char **start) +{ + unsigned char *s = (unsigned char *)*start; + wchar_t ch; + + if (*s < 0x80) { + /* 0xxxxxxx */ + ch = *s; + *start += 1; + } else if ((s[0] & 0xe0) == 0xc0) { + /* 110XXXXx 10xxxxxx */ + if ((s[1] & 0xc0) != 0x80 || + /* overlong? */ + (s[0] & 0xfe) == 0xc0) + goto invalid; + ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f); + *start += 2; + } else if ((s[0] & 0xf0) == 0xe0) { + /* 1110XXXX 10Xxxxxx 10xxxxxx */ + if ((s[1] & 0xc0) != 0x80 || + (s[2] & 0xc0) != 0x80 || + /* overlong? */ + (s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) || + /* surrogate? */ + (s[0] == 0xed && (s[1] & 0xe0) == 0xa0) || + /* U+FFFE or U+FFFF? */ + (s[0] == 0xef && s[1] == 0xbf && + (s[2] & 0xfe) == 0xbe)) + goto invalid; + ch = ((s[0] & 0x0f) << 12) | + ((s[1] & 0x3f) << 6) | (s[2] & 0x3f); + *start += 3; + } else if ((s[0] & 0xf8) == 0xf0) { + /* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */ + if ((s[1] & 0xc0) != 0x80 || + (s[2] & 0xc0) != 0x80 || + (s[3] & 0xc0) != 0x80 || + /* overlong? */ + (s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) || + /* > U+10FFFF? */ + (s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4) + goto invalid; + ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) | + ((s[2] & 0x3f) << 6) | (s[3] & 0x3f); + *start += 4; + } else { +invalid: + *start = NULL; + return 0; + } + + return wcwidth(ch); +} + +int is_utf8(const char *text) +{ + while (*text) { + if (*text == '\n' || *text == '\t' || *text == '\r') { + text++; + continue; + } + utf8_width(&text); + if (!text) + return 0; + } + return 1; +} + +static void print_spaces(int count) +{ + static const char s[] = " "; + while (count >= sizeof(s)) { + fwrite(s, sizeof(s) - 1, 1, stdout); + count -= sizeof(s) - 1; + } + fwrite(s, count, 1, stdout); +} + +/* + * Wrap the text, if necessary. The variable indent is the indent for the + * first line, indent2 is the indent for all other lines. + */ +void print_wrapped_text(const char *text, int indent, int indent2, int width) +{ + int w = indent, assume_utf8 = is_utf8(text); + const char *bol = text, *space = NULL; + + for (;;) { + char c = *text; + if (!c || isspace(c)) { + if (w < width || !space) { + const char *start = bol; + if (space) + start = space; + else + print_spaces(indent); + fwrite(start, text - start, 1, stdout); + if (!c) { + putchar('\n'); + return; + } else if (c == '\t') + w |= 0x07; + space = text; + w++; + text++; + } + else { + putchar('\n'); + text = bol = space + 1; + space = NULL; + w = indent = indent2; + } + continue; + } + if (assume_utf8) + w += utf8_width(&text); + else { + w++; + text++; + } + } +} + +int is_encoding_utf8(const char *name) +{ + if (!name) + return 1; + if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8")) + return 1; + return 0; +} + +/* + * Given a buffer and its encoding, return it re-encoded + * with iconv. If the conversion fails, returns NULL. + */ +#ifndef NO_ICONV +char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding) +{ + iconv_t conv; + size_t insz, outsz, outalloc; + char *out, *outpos, *cp; + + if (!in_encoding) + return NULL; + conv = iconv_open(out_encoding, in_encoding); + if (conv == (iconv_t) -1) + return NULL; + insz = strlen(in); + outsz = insz; + outalloc = outsz + 1; /* for terminating NUL */ + out = xmalloc(outalloc); + outpos = out; + cp = (char *)in; + + while (1) { + size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz); + + if (cnt == -1) { + size_t sofar; + if (errno != E2BIG) { + free(out); + iconv_close(conv); + return NULL; + } + /* insz has remaining number of bytes. + * since we started outsz the same as insz, + * it is likely that insz is not enough for + * converting the rest. + */ + sofar = outpos - out; + outalloc = sofar + insz * 2 + 32; + out = xrealloc(out, outalloc); + outpos = out + sofar; + outsz = outalloc - sofar - 1; + } + else { + *outpos = '\0'; + break; + } + } + iconv_close(conv); + return out; +} +#endif diff --git a/utf8.h b/utf8.h new file mode 100644 index 0000000000..a07c5a88af --- /dev/null +++ b/utf8.h @@ -0,0 +1,16 @@ +#ifndef GIT_UTF8_H +#define GIT_UTF8_H + +int utf8_width(const char **start); +int is_utf8(const char *text); +int is_encoding_utf8(const char *name); + +void print_wrapped_text(const char *text, int indent, int indent2, int len); + +#ifndef NO_ICONV +char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding); +#else +#define reencode_string(a,b,c) NULL +#endif + +#endif @@ -4,9 +4,6 @@ * Copyright (C) Eric Biederman, 2005 */ #include "cache.h" -#include <stdio.h> -#include <errno.h> -#include <string.h> static const char var_usage[] = "git-var [-l | <variable>]"; diff --git a/write_or_die.c b/write_or_die.c index ab4cb8a69c..4e8183e93e 100644 --- a/write_or_die.c +++ b/write_or_die.c @@ -1,20 +1,84 @@ #include "cache.h" -void write_or_die(int fd, const void *buf, size_t count) +int read_in_full(int fd, void *buf, size_t count) +{ + char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t loaded = xread(fd, p, count); + if (loaded <= 0) + return total ? total : loaded; + count -= loaded; + p += loaded; + total += loaded; + } + + return total; +} + +void read_or_die(int fd, void *buf, size_t count) +{ + ssize_t loaded; + + loaded = read_in_full(fd, buf, count); + if (loaded != count) { + if (loaded < 0) + die("read error (%s)", strerror(errno)); + die("read error: end of file"); + } +} + +int write_in_full(int fd, const void *buf, size_t count) { const char *p = buf; - ssize_t written; + ssize_t total = 0; while (count > 0) { - written = xwrite(fd, p, count); - if (written == 0) - die("disk full?"); - else if (written < 0) { - if (errno == EPIPE) - exit(0); - die("write error (%s)", strerror(errno)); + size_t written = xwrite(fd, p, count); + if (written < 0) + return -1; + if (!written) { + errno = ENOSPC; + return -1; } count -= written; p += written; + total += written; } + + return total; +} + +void write_or_die(int fd, const void *buf, size_t count) +{ + if (write_in_full(fd, buf, count) < 0) { + if (errno == EPIPE) + exit(0); + die("write error (%s)", strerror(errno)); + } +} + +int write_or_whine_pipe(int fd, const void *buf, size_t count, const char *msg) +{ + if (write_in_full(fd, buf, count) < 0) { + if (errno == EPIPE) + exit(0); + fprintf(stderr, "%s: write error (%s)\n", + msg, strerror(errno)); + return 0; + } + + return 1; +} + +int write_or_whine(int fd, const void *buf, size_t count, const char *msg) +{ + if (write_in_full(fd, buf, count) < 0) { + fprintf(stderr, "%s: write error (%s)\n", + msg, strerror(errno)); + return 0; + } + + return 1; } diff --git a/wt-status.c b/wt-status.c new file mode 100644 index 0000000000..daba9a6105 --- /dev/null +++ b/wt-status.c @@ -0,0 +1,359 @@ +#include "cache.h" +#include "wt-status.h" +#include "color.h" +#include "object.h" +#include "dir.h" +#include "commit.h" +#include "diff.h" +#include "revision.h" +#include "diffcore.h" + +int wt_status_use_color = 0; +static char wt_status_colors[][COLOR_MAXLEN] = { + "", /* WT_STATUS_HEADER: normal */ + "\033[32m", /* WT_STATUS_UPDATED: green */ + "\033[31m", /* WT_STATUS_CHANGED: red */ + "\033[31m", /* WT_STATUS_UNTRACKED: red */ +}; + +static const char use_add_msg[] = +"use \"git add <file>...\" to update what will be committed"; +static const char use_add_rm_msg[] = +"use \"git add/rm <file>...\" to update what will be committed"; +static const char use_add_to_include_msg[] = +"use \"git add <file>...\" to include in what will be committed"; + +static int parse_status_slot(const char *var, int offset) +{ + if (!strcasecmp(var+offset, "header")) + return WT_STATUS_HEADER; + if (!strcasecmp(var+offset, "updated") + || !strcasecmp(var+offset, "added")) + return WT_STATUS_UPDATED; + if (!strcasecmp(var+offset, "changed")) + return WT_STATUS_CHANGED; + if (!strcasecmp(var+offset, "untracked")) + return WT_STATUS_UNTRACKED; + die("bad config variable '%s'", var); +} + +static const char* color(int slot) +{ + return wt_status_use_color ? wt_status_colors[slot] : ""; +} + +void wt_status_prepare(struct wt_status *s) +{ + unsigned char sha1[20]; + const char *head; + + head = resolve_ref("HEAD", sha1, 0, NULL); + s->branch = head ? xstrdup(head) : NULL; + + s->reference = "HEAD"; + s->amend = 0; + s->verbose = 0; + s->untracked = 0; + + s->commitable = 0; + s->workdir_dirty = 0; + s->workdir_untracked = 0; +} + +static void wt_status_print_cached_header(const char *reference) +{ + const char *c = color(WT_STATUS_HEADER); + color_printf_ln(c, "# Changes to be committed:"); + if (reference) { + color_printf_ln(c, "# (use \"git reset %s <file>...\" to unstage)", reference); + } else { + color_printf_ln(c, "# (use \"git rm --cached <file>...\" to unstage)"); + } + color_printf_ln(c, "#"); +} + +static void wt_status_print_header(const char *main, const char *sub) +{ + const char *c = color(WT_STATUS_HEADER); + color_printf_ln(c, "# %s:", main); + color_printf_ln(c, "# (%s)", sub); + color_printf_ln(c, "#"); +} + +static void wt_status_print_trailer(void) +{ + color_printf_ln(color(WT_STATUS_HEADER), "#"); +} + +static const char *quote_crlf(const char *in, char *buf, size_t sz) +{ + const char *scan; + char *out; + const char *ret = in; + + for (scan = in, out = buf; *scan; scan++) { + int ch = *scan; + int quoted; + + switch (ch) { + case '\n': + quoted = 'n'; + break; + case '\r': + quoted = 'r'; + break; + default: + *out++ = ch; + continue; + } + *out++ = '\\'; + *out++ = quoted; + ret = buf; + } + *out = '\0'; + return ret; +} + +static void wt_status_print_filepair(int t, struct diff_filepair *p) +{ + const char *c = color(t); + const char *one, *two; + char onebuf[PATH_MAX], twobuf[PATH_MAX]; + + one = quote_crlf(p->one->path, onebuf, sizeof(onebuf)); + two = quote_crlf(p->two->path, twobuf, sizeof(twobuf)); + + color_printf(color(WT_STATUS_HEADER), "#\t"); + switch (p->status) { + case DIFF_STATUS_ADDED: + color_printf(c, "new file: %s", one); + break; + case DIFF_STATUS_COPIED: + color_printf(c, "copied: %s -> %s", one, two); + break; + case DIFF_STATUS_DELETED: + color_printf(c, "deleted: %s", one); + break; + case DIFF_STATUS_MODIFIED: + color_printf(c, "modified: %s", one); + break; + case DIFF_STATUS_RENAMED: + color_printf(c, "renamed: %s -> %s", one, two); + break; + case DIFF_STATUS_TYPE_CHANGED: + color_printf(c, "typechange: %s", one); + break; + case DIFF_STATUS_UNKNOWN: + color_printf(c, "unknown: %s", one); + break; + case DIFF_STATUS_UNMERGED: + color_printf(c, "unmerged: %s", one); + break; + default: + die("bug: unhandled diff status %c", p->status); + } + printf("\n"); +} + +static void wt_status_print_updated_cb(struct diff_queue_struct *q, + struct diff_options *options, + void *data) +{ + struct wt_status *s = data; + int shown_header = 0; + int i; + for (i = 0; i < q->nr; i++) { + if (q->queue[i]->status == 'U') + continue; + if (!shown_header) { + wt_status_print_cached_header(s->reference); + s->commitable = 1; + shown_header = 1; + } + wt_status_print_filepair(WT_STATUS_UPDATED, q->queue[i]); + } + if (shown_header) + wt_status_print_trailer(); +} + +static void wt_status_print_changed_cb(struct diff_queue_struct *q, + struct diff_options *options, + void *data) +{ + struct wt_status *s = data; + int i; + if (q->nr) { + const char *msg = use_add_msg; + s->workdir_dirty = 1; + for (i = 0; i < q->nr; i++) + if (q->queue[i]->status == DIFF_STATUS_DELETED) { + msg = use_add_rm_msg; + break; + } + wt_status_print_header("Changed but not updated", msg); + } + for (i = 0; i < q->nr; i++) + wt_status_print_filepair(WT_STATUS_CHANGED, q->queue[i]); + if (q->nr) + wt_status_print_trailer(); +} + +void wt_status_print_initial(struct wt_status *s) +{ + int i; + char buf[PATH_MAX]; + + read_cache(); + if (active_nr) { + s->commitable = 1; + wt_status_print_cached_header(NULL); + } + for (i = 0; i < active_nr; i++) { + color_printf(color(WT_STATUS_HEADER), "#\t"); + color_printf_ln(color(WT_STATUS_UPDATED), "new file: %s", + quote_crlf(active_cache[i]->name, + buf, sizeof(buf))); + } + if (active_nr) + wt_status_print_trailer(); +} + +static void wt_status_print_updated(struct wt_status *s) +{ + struct rev_info rev; + init_revisions(&rev, NULL); + setup_revisions(0, NULL, &rev, s->reference); + rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK; + rev.diffopt.format_callback = wt_status_print_updated_cb; + rev.diffopt.format_callback_data = s; + rev.diffopt.detect_rename = 1; + run_diff_index(&rev, 1); +} + +static void wt_status_print_changed(struct wt_status *s) +{ + struct rev_info rev; + init_revisions(&rev, ""); + setup_revisions(0, NULL, &rev, NULL); + rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK; + rev.diffopt.format_callback = wt_status_print_changed_cb; + rev.diffopt.format_callback_data = s; + run_diff_files(&rev, 0); +} + +static void wt_status_print_untracked(struct wt_status *s) +{ + struct dir_struct dir; + const char *x; + int i; + int shown_header = 0; + + memset(&dir, 0, sizeof(dir)); + + dir.exclude_per_dir = ".gitignore"; + if (!s->untracked) { + dir.show_other_directories = 1; + dir.hide_empty_directories = 1; + } + x = git_path("info/exclude"); + if (file_exists(x)) + add_excludes_from_file(&dir, x); + + read_directory(&dir, ".", "", 0); + for(i = 0; i < dir.nr; i++) { + /* check for matching entry, which is unmerged; lifted from + * builtin-ls-files:show_other_files */ + struct dir_entry *ent = dir.entries[i]; + int pos = cache_name_pos(ent->name, ent->len); + struct cache_entry *ce; + if (0 <= pos) + die("bug in wt_status_print_untracked"); + pos = -pos - 1; + if (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) == ent->len && + !memcmp(ce->name, ent->name, ent->len)) + continue; + } + if (!shown_header) { + s->workdir_untracked = 1; + wt_status_print_header("Untracked files", + use_add_to_include_msg); + shown_header = 1; + } + color_printf(color(WT_STATUS_HEADER), "#\t"); + color_printf_ln(color(WT_STATUS_UNTRACKED), "%.*s", + ent->len, ent->name); + } +} + +static void wt_status_print_verbose(struct wt_status *s) +{ + struct rev_info rev; + init_revisions(&rev, NULL); + setup_revisions(0, NULL, &rev, s->reference); + rev.diffopt.output_format |= DIFF_FORMAT_PATCH; + rev.diffopt.detect_rename = 1; + run_diff_index(&rev, 1); +} + +void wt_status_print(struct wt_status *s) +{ + unsigned char sha1[20]; + s->is_initial = get_sha1(s->reference, sha1) ? 1 : 0; + + if (s->branch) { + const char *on_what = "On branch "; + const char *branch_name = s->branch; + if (!strncmp(branch_name, "refs/heads/", 11)) + branch_name += 11; + else if (!strcmp(branch_name, "HEAD")) { + branch_name = ""; + on_what = "Not currently on any branch."; + } + color_printf_ln(color(WT_STATUS_HEADER), + "# %s%s", on_what, branch_name); + } + + if (s->is_initial) { + color_printf_ln(color(WT_STATUS_HEADER), "#"); + color_printf_ln(color(WT_STATUS_HEADER), "# Initial commit"); + color_printf_ln(color(WT_STATUS_HEADER), "#"); + wt_status_print_initial(s); + } + else { + wt_status_print_updated(s); + discard_cache(); + } + + wt_status_print_changed(s); + wt_status_print_untracked(s); + + if (s->verbose && !s->is_initial) + wt_status_print_verbose(s); + if (!s->commitable) { + if (s->amend) + printf("# No changes\n"); + else if (s->workdir_dirty) + printf("no changes added to commit (use \"git add\" and/or \"git commit [-a|-i|-o]\")\n"); + else if (s->workdir_untracked) + printf("nothing added to commit but untracked files present (use \"git add\" to track)\n"); + else if (s->is_initial) + printf("nothing to commit (create/copy files and use \"git add\" to track)\n"); + else + printf("nothing to commit (working directory clean)\n"); + } +} + +int git_status_config(const char *k, const char *v) +{ + if (!strcmp(k, "status.color") || !strcmp(k, "color.status")) { + wt_status_use_color = git_config_colorbool(k, v); + return 0; + } + if (!strncmp(k, "status.color.", 13) || !strncmp(k, "color.status", 13)) { + int slot = parse_status_slot(k, 13); + color_parse(v, k, wt_status_colors[slot]); + } + return git_default_config(k, v); +} diff --git a/wt-status.h b/wt-status.h new file mode 100644 index 0000000000..cfea4ae688 --- /dev/null +++ b/wt-status.h @@ -0,0 +1,28 @@ +#ifndef STATUS_H +#define STATUS_H + +enum color_wt_status { + WT_STATUS_HEADER, + WT_STATUS_UPDATED, + WT_STATUS_CHANGED, + WT_STATUS_UNTRACKED, +}; + +struct wt_status { + int is_initial; + char *branch; + const char *reference; + int verbose; + int amend; + int untracked; + /* These are computed during processing of the individual sections */ + int commitable; + int workdir_dirty; + int workdir_untracked; +}; + +int git_status_config(const char *var, const char *value); +void wt_status_prepare(struct wt_status *s); +void wt_status_print(struct wt_status *s); + +#endif /* STATUS_H */ diff --git a/xdiff-interface.c b/xdiff-interface.c index 6a82da73b6..6c1f99b149 100644 --- a/xdiff-interface.c +++ b/xdiff-interface.c @@ -69,9 +69,9 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf) for (i = 0; i < nbuf; i++) { if (mb[i].ptr[mb[i].size-1] != '\n') { /* Incomplete line */ - priv->remainder = realloc(priv->remainder, - priv->remainder_size + - mb[i].size); + priv->remainder = xrealloc(priv->remainder, + priv->remainder_size + + mb[i].size); memcpy(priv->remainder + priv->remainder_size, mb[i].ptr, mb[i].size); priv->remainder_size += mb[i].size; @@ -83,9 +83,9 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf) consume_one(priv, mb[i].ptr, mb[i].size); continue; } - priv->remainder = realloc(priv->remainder, - priv->remainder_size + - mb[i].size); + priv->remainder = xrealloc(priv->remainder, + priv->remainder_size + + mb[i].size); memcpy(priv->remainder + priv->remainder_size, mb[i].ptr, mb[i].size); consume_one(priv, priv->remainder, @@ -102,3 +102,22 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf) } return 0; } + +int read_mmfile(mmfile_t *ptr, const char *filename) +{ + struct stat st; + FILE *f; + + if (stat(filename, &st)) + return error("Could not stat %s", filename); + if ((f = fopen(filename, "rb")) == NULL) + return error("Could not open %s", filename); + ptr->ptr = xmalloc(st.st_size); + if (fread(ptr->ptr, st.st_size, 1, f) != 1) + return error("Could not read %s", filename); + fclose(f); + ptr->size = st.st_size; + return 0; +} + + diff --git a/xdiff-interface.h b/xdiff-interface.h index 1346908bea..1918808081 100644 --- a/xdiff-interface.h +++ b/xdiff-interface.h @@ -17,5 +17,6 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf); int parse_hunk_header(char *line, int len, int *ob, int *on, int *nb, int *nn); +int read_mmfile(mmfile_t *ptr, const char *filename); #endif diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h index c9f817818a..fa409d5234 100644 --- a/xdiff/xdiff.h +++ b/xdiff/xdiff.h @@ -49,6 +49,9 @@ extern "C" { #define XDL_BDOP_CPY 2 #define XDL_BDOP_INSB 3 +#define XDL_MERGE_MINIMAL 0 +#define XDL_MERGE_EAGER 1 +#define XDL_MERGE_ZEALOUS 2 typedef struct s_mmfile { char *ptr; @@ -90,6 +93,10 @@ long xdl_mmfile_size(mmfile_t *mmf); int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdemitconf_t const *xecfg, xdemitcb_t *ecb); +int xdl_merge(mmfile_t *orig, mmfile_t *mf1, const char *name1, + mmfile_t *mf2, const char *name2, + xpparam_t const *xpp, int level, mmbuffer_t *result); + #ifdef __cplusplus } #endif /* #ifdef __cplusplus */ diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c index d76e76a0e6..9aeebc473b 100644 --- a/xdiff/xdiffi.c +++ b/xdiff/xdiffi.c @@ -45,7 +45,6 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, xdalgoenv_t *xenv); static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2); -static int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags); @@ -397,7 +396,7 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, } -static int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { +int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->nrec; char *rchg = xdf->rchg, *rchgo = xdfo->rchg; xrecord_t **recs = xdf->recs; diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h index d3b72716b5..472aeaecfa 100644 --- a/xdiff/xdiffi.h +++ b/xdiff/xdiffi.h @@ -50,6 +50,7 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv); int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdfenv_t *xe); +int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags); int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr); void xdl_free_script(xdchange_t *xscr); int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, diff --git a/xdiff/xemit.c b/xdiff/xemit.c index 714c563547..e291dc7608 100644 --- a/xdiff/xemit.c +++ b/xdiff/xemit.c @@ -86,11 +86,10 @@ static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll) { if (len > 0 && (isalpha((unsigned char)*rec) || /* identifier? */ *rec == '_' || /* also identifier? */ - *rec == '(' || /* lisp defun? */ - *rec == '#')) { /* #define? */ + *rec == '$')) { /* mysterious GNU diff's invention */ if (len > sz) len = sz; - if (len && rec[len - 1] == '\n') + while (0 < len && isspace((unsigned char)rec[len - 1])) len--; memcpy(buf, rec, len); *ll = len; @@ -119,7 +118,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, xdemitconf_t const *xecfg) { long s1, s2, e1, e2, lctx; xdchange_t *xch, *xche; - char funcbuf[40]; + char funcbuf[80]; long funclen = 0; if (xecfg->flags & XDL_EMIT_COMMON) diff --git a/xdiff/xmacros.h b/xdiff/xmacros.h index 4c2fde80c1..e2cd2023b3 100644 --- a/xdiff/xmacros.h +++ b/xdiff/xmacros.h @@ -24,14 +24,15 @@ #define XMACROS_H -#define GR_PRIME 0x9e370001UL #define XDL_MIN(a, b) ((a) < (b) ? (a): (b)) #define XDL_MAX(a, b) ((a) > (b) ? (a): (b)) #define XDL_ABS(v) ((v) >= 0 ? (v): -(v)) #define XDL_ISDIGIT(c) ((c) >= '0' && (c) <= '9') -#define XDL_HASHLONG(v, b) (((unsigned long)(v) * GR_PRIME) >> ((CHAR_BIT * sizeof(unsigned long)) - (b))) +#define XDL_ADDBITS(v,b) ((v) + ((v) >> (b))) +#define XDL_MASKBITS(b) ((1UL << (b)) - 1) +#define XDL_HASHLONG(v,b) (XDL_ADDBITS((unsigned long)(v), b) & XDL_MASKBITS(b)) #define XDL_PTRFREE(p) do { if (p) { xdl_free(p); (p) = NULL; } } while (0) #define XDL_LE32_PUT(p, v) \ do { \ diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c new file mode 100644 index 0000000000..b83b3348cc --- /dev/null +++ b/xdiff/xmerge.c @@ -0,0 +1,426 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003-2006 Davide Libenzi, Johannes E. Schindelin + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + +typedef struct s_xdmerge { + struct s_xdmerge *next; + /* + * 0 = conflict, + * 1 = no conflict, take first, + * 2 = no conflict, take second. + */ + int mode; + long i1, i2; + long chg1, chg2; +} xdmerge_t; + +static int xdl_append_merge(xdmerge_t **merge, int mode, + long i1, long chg1, long i2, long chg2) +{ + xdmerge_t *m = *merge; + if (m && (i1 <= m->i1 + m->chg1 || i2 <= m->i2 + m->chg2)) { + if (mode != m->mode) + m->mode = 0; + m->chg1 = i1 + chg1 - m->i1; + m->chg2 = i2 + chg2 - m->i2; + } else { + m = xdl_malloc(sizeof(xdmerge_t)); + if (!m) + return -1; + m->next = NULL; + m->mode = mode; + m->i1 = i1; + m->chg1 = chg1; + m->i2 = i2; + m->chg2 = chg2; + if (*merge) + (*merge)->next = m; + *merge = m; + } + return 0; +} + +static int xdl_cleanup_merge(xdmerge_t *c) +{ + int count = 0; + xdmerge_t *next_c; + + /* were there conflicts? */ + for (; c; c = next_c) { + if (c->mode == 0) + count++; + next_c = c->next; + free(c); + } + return count; +} + +static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, + int line_count, long flags) +{ + int i; + xrecord_t **rec1 = xe1->xdf2.recs + i1; + xrecord_t **rec2 = xe2->xdf2.recs + i2; + + for (i = 0; i < line_count; i++) { + int result = xdl_recmatch(rec1[i]->ptr, rec1[i]->size, + rec2[i]->ptr, rec2[i]->size, flags); + if (!result) + return -1; + } + return 0; +} + +static int xdl_recs_copy(xdfenv_t *xe, int i, int count, int add_nl, char *dest) +{ + xrecord_t **recs = xe->xdf2.recs + i; + int size = 0; + + if (count < 1) + return 0; + + for (i = 0; i < count; size += recs[i++]->size) + if (dest) + memcpy(dest + size, recs[i]->ptr, recs[i]->size); + if (add_nl) { + i = recs[count - 1]->size; + if (i == 0 || recs[count - 1]->ptr[i - 1] != '\n') { + if (dest) + dest[size] = '\n'; + size++; + } + } + return size; +} + +static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1, + xdfenv_t *xe2, const char *name2, xdmerge_t *m, char *dest) +{ + const int marker_size = 7; + int marker1_size = (name1 ? strlen(name1) + 1 : 0); + int marker2_size = (name2 ? strlen(name2) + 1 : 0); + int conflict_marker_size = 3 * (marker_size + 1) + + marker1_size + marker2_size; + int size, i1, j; + + for (size = i1 = 0; m; m = m->next) { + if (m->mode == 0) { + size += xdl_recs_copy(xe1, i1, m->i1 - i1, 0, + dest ? dest + size : NULL); + if (dest) { + for (j = 0; j < marker_size; j++) + dest[size++] = '<'; + if (marker1_size) { + dest[size] = ' '; + memcpy(dest + size + 1, name1, + marker1_size - 1); + size += marker1_size; + } + dest[size++] = '\n'; + } else + size += conflict_marker_size; + size += xdl_recs_copy(xe1, m->i1, m->chg1, 1, + dest ? dest + size : NULL); + if (dest) { + for (j = 0; j < marker_size; j++) + dest[size++] = '='; + dest[size++] = '\n'; + } + size += xdl_recs_copy(xe2, m->i2, m->chg2, 1, + dest ? dest + size : NULL); + if (dest) { + for (j = 0; j < marker_size; j++) + dest[size++] = '>'; + if (marker2_size) { + dest[size] = ' '; + memcpy(dest + size + 1, name2, + marker2_size - 1); + size += marker2_size; + } + dest[size++] = '\n'; + } + } else if (m->mode == 1) + size += xdl_recs_copy(xe1, i1, m->i1 + m->chg1 - i1, 0, + dest ? dest + size : NULL); + else if (m->mode == 2) + size += xdl_recs_copy(xe2, m->i2 - m->i1 + i1, + m->i1 + m->chg2 - i1, 0, + dest ? dest + size : NULL); + else + continue; + i1 = m->i1 + m->chg1; + } + size += xdl_recs_copy(xe1, i1, xe1->xdf2.nrec - i1, 0, + dest ? dest + size : NULL); + return size; +} + +/* + * Sometimes, changes are not quite identical, but differ in only a few + * lines. Try hard to show only these few lines as conflicting. + */ +static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, + xpparam_t const *xpp) +{ + for (; m; m = m->next) { + mmfile_t t1, t2; + xdfenv_t xe; + xdchange_t *xscr, *x; + int i1 = m->i1, i2 = m->i2; + + /* let's handle just the conflicts */ + if (m->mode) + continue; + + /* no sense refining a conflict when one side is empty */ + if (m->chg1 == 0 || m->chg2 == 0) + continue; + + /* + * This probably does not work outside git, since + * we have a very simple mmfile structure. + */ + t1.ptr = (char *)xe1->xdf2.recs[m->i1]->ptr; + t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1]->ptr + + xe1->xdf2.recs[m->i1 + m->chg1 - 1]->size - t1.ptr; + t2.ptr = (char *)xe2->xdf2.recs[m->i2]->ptr; + t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1]->ptr + + xe2->xdf2.recs[m->i2 + m->chg2 - 1]->size - t2.ptr; + if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0) + return -1; + if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 || + xdl_change_compact(&xe.xdf2, &xe.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe, &xscr) < 0) { + xdl_free_env(&xe); + return -1; + } + if (!xscr) { + /* If this happens, the changes are identical. */ + xdl_free_env(&xe); + m->mode = 4; + continue; + } + x = xscr; + m->i1 = xscr->i1 + i1; + m->chg1 = xscr->chg1; + m->i2 = xscr->i2 + i2; + m->chg2 = xscr->chg2; + while (xscr->next) { + xdmerge_t *m2 = xdl_malloc(sizeof(xdmerge_t)); + if (!m2) { + xdl_free_env(&xe); + xdl_free_script(x); + return -1; + } + xscr = xscr->next; + m2->next = m->next; + m->next = m2; + m = m2; + m->mode = 0; + m->i1 = xscr->i1 + i1; + m->chg1 = xscr->chg1; + m->i2 = xscr->i2 + i2; + m->chg2 = xscr->chg2; + } + xdl_free_env(&xe); + xdl_free_script(x); + } + return 0; +} + +/* + * level == 0: mark all overlapping changes as conflict + * level == 1: mark overlapping changes as conflict only if not identical + * level == 2: analyze non-identical changes for minimal conflict set + * + * returns < 0 on error, == 0 for no conflicts, else number of conflicts + */ +static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1, const char *name1, + xdfenv_t *xe2, xdchange_t *xscr2, const char *name2, + int level, xpparam_t const *xpp, mmbuffer_t *result) { + xdmerge_t *changes, *c; + int i1, i2, chg1, chg2; + + c = changes = NULL; + + while (xscr1 && xscr2) { + if (!changes) + changes = c; + if (xscr1->i1 + xscr1->chg1 < xscr2->i1) { + i1 = xscr1->i2; + i2 = xscr2->i2 - xscr2->i1 + xscr1->i1; + chg1 = xscr1->chg2; + chg2 = xscr1->chg1; + if (xdl_append_merge(&c, 1, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr1 = xscr1->next; + continue; + } + if (xscr2->i1 + xscr2->chg1 < xscr1->i1) { + i1 = xscr1->i2 - xscr1->i1 + xscr2->i1; + i2 = xscr2->i2; + chg1 = xscr2->chg1; + chg2 = xscr2->chg2; + if (xdl_append_merge(&c, 2, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr2 = xscr2->next; + continue; + } + if (level < 1 || xscr1->i1 != xscr2->i1 || + xscr1->chg1 != xscr2->chg1 || + xscr1->chg2 != xscr2->chg2 || + xdl_merge_cmp_lines(xe1, xscr1->i2, + xe2, xscr2->i2, + xscr1->chg2, xpp->flags)) { + /* conflict */ + int off = xscr1->i1 - xscr2->i1; + int ffo = off + xscr1->chg1 - xscr2->chg1; + + i1 = xscr1->i2; + i2 = xscr2->i2; + if (off > 0) + i1 -= off; + else + i2 += off; + chg1 = xscr1->i2 + xscr1->chg2 - i1; + chg2 = xscr2->i2 + xscr2->chg2 - i2; + if (ffo > 0) + chg2 += ffo; + else + chg1 -= ffo; + if (xdl_append_merge(&c, 0, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + } + + i1 = xscr1->i1 + xscr1->chg1; + i2 = xscr2->i1 + xscr2->chg1; + + if (i1 >= i2) + xscr2 = xscr2->next; + if (i2 >= i1) + xscr1 = xscr1->next; + } + while (xscr1) { + if (!changes) + changes = c; + i1 = xscr1->i2; + i2 = xscr1->i1 + xe2->xdf2.nrec - xe2->xdf1.nrec; + chg1 = xscr1->chg2; + chg2 = xscr1->chg1; + if (xdl_append_merge(&c, 1, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr1 = xscr1->next; + } + while (xscr2) { + if (!changes) + changes = c; + i1 = xscr2->i1 + xe1->xdf2.nrec - xe1->xdf1.nrec; + i2 = xscr2->i2; + chg1 = xscr2->chg1; + chg2 = xscr2->chg2; + if (xdl_append_merge(&c, 2, i1, chg1, i2, chg2)) { + xdl_cleanup_merge(changes); + return -1; + } + xscr2 = xscr2->next; + } + if (!changes) + changes = c; + /* refine conflicts */ + if (level > 1 && xdl_refine_conflicts(xe1, xe2, changes, xpp) < 0) { + xdl_cleanup_merge(changes); + return -1; + } + /* output */ + if (result) { + int size = xdl_fill_merge_buffer(xe1, name1, xe2, name2, + changes, NULL); + result->ptr = xdl_malloc(size); + if (!result->ptr) { + xdl_cleanup_merge(changes); + return -1; + } + result->size = size; + xdl_fill_merge_buffer(xe1, name1, xe2, name2, changes, + result->ptr); + } + return xdl_cleanup_merge(changes); +} + +int xdl_merge(mmfile_t *orig, mmfile_t *mf1, const char *name1, + mmfile_t *mf2, const char *name2, + xpparam_t const *xpp, int level, mmbuffer_t *result) { + xdchange_t *xscr1, *xscr2; + xdfenv_t xe1, xe2; + int status; + + result->ptr = NULL; + result->size = 0; + + if (xdl_do_diff(orig, mf1, xpp, &xe1) < 0 || + xdl_do_diff(orig, mf2, xpp, &xe2) < 0) { + return -1; + } + if (xdl_change_compact(&xe1.xdf1, &xe1.xdf2, xpp->flags) < 0 || + xdl_change_compact(&xe1.xdf2, &xe1.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe1, &xscr1) < 0) { + xdl_free_env(&xe1); + return -1; + } + if (xdl_change_compact(&xe2.xdf1, &xe2.xdf2, xpp->flags) < 0 || + xdl_change_compact(&xe2.xdf2, &xe2.xdf1, xpp->flags) < 0 || + xdl_build_script(&xe2, &xscr2) < 0) { + xdl_free_env(&xe2); + return -1; + } + status = 0; + if (xscr1 || xscr2) { + if (!xscr1) { + result->ptr = xdl_malloc(mf2->size); + memcpy(result->ptr, mf2->ptr, mf2->size); + result->size = mf2->size; + } else if (!xscr2) { + result->ptr = xdl_malloc(mf1->size); + memcpy(result->ptr, mf1->ptr, mf1->size); + result->size = mf1->size; + } else { + status = xdl_do_merge(&xe1, xscr1, name1, + &xe2, xscr2, name2, + level, xpp, result); + } + xdl_free_script(xscr1); + xdl_free_script(xscr2); + } + xdl_free_env(&xe1); + xdl_free_env(&xe2); + + return status; +} diff --git a/xdiff/xutils.c b/xdiff/xutils.c index f7bdd395ad..1b899f32c4 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -191,36 +191,30 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags) int i1, i2; if (flags & XDF_IGNORE_WHITESPACE) { - for (i1 = i2 = 0; i1 < s1 && i2 < s2; i1++, i2++) { + for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) { if (isspace(l1[i1])) while (isspace(l1[i1]) && i1 < s1) i1++; - else if (isspace(l2[i2])) + if (isspace(l2[i2])) while (isspace(l2[i2]) && i2 < s2) i2++; - else if (l1[i1] != l2[i2]) - return l2[i2] - l1[i1]; + if (i1 < s1 && i2 < s2 && l1[i1++] != l2[i2++]) + return 0; } - if (i1 >= s1) - return 1; - else if (i2 >= s2) - return -1; + return (i1 >= s1 && i2 >= s2); } else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) { - for (i1 = i2 = 0; i1 < s1 && i2 < s2; i1++, i2++) { + for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) { if (isspace(l1[i1])) { if (!isspace(l2[i2])) - return -1; + return 0; while (isspace(l1[i1]) && i1 < s1) i1++; while (isspace(l2[i2]) && i2 < s2) i2++; - } else if (l1[i1] != l2[i2]) - return l2[i2] - l1[i1]; + } else if (l1[i1++] != l2[i2++]) + return 0; } - if (i1 >= s1) - return 1; - else if (i2 >= s2) - return -1; + return (i1 >= s1 && i2 >= s2); } else return s1 == s2 && !memcmp(l1, l2, s1); @@ -233,9 +227,11 @@ unsigned long xdl_hash_record(char const **data, char const *top, long flags) { for (; ptr < top && *ptr != '\n'; ptr++) { if (isspace(*ptr) && (flags & XDF_WHITESPACE_FLAGS)) { - while (ptr < top && isspace(*ptr) && ptr[1] != '\n') + while (ptr + 1 < top && isspace(ptr[1]) + && ptr[1] != '\n') ptr++; - if (flags & XDF_IGNORE_WHITESPACE_CHANGE) { + if (flags & XDF_IGNORE_WHITESPACE_CHANGE + && ptr[1] != '\n') { ha += (ha << 5); ha ^= (unsigned long) ' '; } |
