diff options
Diffstat (limited to 'Documentation')
188 files changed, 29331 insertions, 0 deletions
diff --git a/Documentation/.gitignore b/Documentation/.gitignore new file mode 100644 index 0000000000..6a51331b2f --- /dev/null +++ b/Documentation/.gitignore @@ -0,0 +1,7 @@ +*.xml +*.html +*.1 +*.7 +howto-index.txt +doc.dep +cmds-*.txt diff --git a/Documentation/Makefile b/Documentation/Makefile new file mode 100644 index 0000000000..7c1c9e1918 --- /dev/null +++ b/Documentation/Makefile @@ -0,0 +1,138 @@ +MAN1_TXT= \ + $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \ + $(wildcard git-*.txt)) \ + gitk.txt +MAN7_TXT=git.txt + +DOC_HTML=$(patsubst %.txt,%.html,$(MAN1_TXT) $(MAN7_TXT)) + +ARTICLES = tutorial +ARTICLES += tutorial-2 +ARTICLES += core-tutorial +ARTICLES += cvs-migration +ARTICLES += diffcore +ARTICLES += howto-index +ARTICLES += repository-layout +ARTICLES += hooks +ARTICLES += everyday +ARTICLES += git-tools +# with their own formatting rules. +SP_ARTICLES = glossary howto/revert-branch-rebase user-manual + +DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES)) + +DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT)) +DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT)) + +prefix?=$(HOME) +bindir?=$(prefix)/bin +mandir?=$(prefix)/man +man1dir=$(mandir)/man1 +man7dir=$(mandir)/man7 +# DESTDIR= + +ASCIIDOC=asciidoc +ASCIIDOC_EXTRA = +INSTALL?=install +DOC_REF = origin/man + +-include ../config.mak.autogen +-include ../config.mak + +# +# Please note that there is a minor bug in asciidoc. +# The version after 6.0.3 _will_ include the patch found here: +# http://marc.theaimsgroup.com/?l=git&m=111558757202243&w=2 +# +# Until that version is released you may have to apply the patch +# yourself - yes, all 6 characters of it! +# + +all: html man + +html: $(DOC_HTML) + +$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN7): asciidoc.conf + +man: man1 man7 +man1: $(DOC_MAN1) +man7: $(DOC_MAN7) + +install: man + $(INSTALL) -d -m755 $(DESTDIR)$(man1dir) $(DESTDIR)$(man7dir) + $(INSTALL) -m644 $(DOC_MAN1) $(DESTDIR)$(man1dir) + $(INSTALL) -m644 $(DOC_MAN7) $(DESTDIR)$(man7dir) + + +# +# Determine "include::" file references in asciidoc files. +# +doc.dep : $(wildcard *.txt) build-docdep.perl + rm -f $@+ $@ + perl ./build-docdep.perl >$@+ + mv $@+ $@ + +-include doc.dep + +cmds_txt = cmds-ancillaryinterrogators.txt \ + cmds-ancillarymanipulators.txt \ + cmds-mainporcelain.txt \ + cmds-plumbinginterrogators.txt \ + cmds-plumbingmanipulators.txt \ + cmds-synchingrepositories.txt \ + cmds-synchelpers.txt \ + cmds-purehelpers.txt \ + cmds-foreignscminterface.txt + +$(cmds_txt): cmd-list.perl $(MAN1_TXT) + perl ./cmd-list.perl + +git.7 git.html: git.txt core-intro.txt + +clean: + rm -f *.xml *.html *.1 *.7 howto-index.txt howto/*.html doc.dep + rm -f $(cmds_txt) + +%.html : %.txt + $(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf $(ASCIIDOC_EXTRA) $< + +%.1 %.7 : %.xml + xmlto -m callouts.xsl man $< + +%.xml : %.txt + $(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf $< + +user-manual.xml: user-manual.txt user-manual.conf + $(ASCIIDOC) -b docbook -d book $< + +XSLT = http://docbook.sourceforge.net/release/xsl/current/html/docbook.xsl +XSLTOPTS = --nonet --xinclude --stringparam html.stylesheet docbook-xsl.css + +user-manual.html: user-manual.xml + xsltproc $(XSLTOPTS) -o $@ $(XSLT) $< + +glossary.html : glossary.txt sort_glossary.pl + cat $< | \ + perl sort_glossary.pl | \ + $(ASCIIDOC) -b xhtml11 - > glossary.html + +howto-index.txt: howto-index.sh $(wildcard howto/*.txt) + rm -f $@+ $@ + sh ./howto-index.sh $(wildcard howto/*.txt) >$@+ + mv $@+ $@ + +$(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt + $(ASCIIDOC) -b xhtml11 $*.txt + +WEBDOC_DEST = /pub/software/scm/git/docs + +$(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt + rm -f $@+ $@ + 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/RelNotes-1.5.0.1.txt b/Documentation/RelNotes-1.5.0.1.txt new file mode 100644 index 0000000000..fea3f9935b --- /dev/null +++ b/Documentation/RelNotes-1.5.0.1.txt @@ -0,0 +1,42 @@ +GIT v1.5.0.1 Release Notes +========================== + +Fixes since v1.5.0 +------------------ + +* Documentation updates + + - Clarifications and corrections to 1.5.0 release notes. + + - The main documentation did not link to git-remote documentation. + + - Clarified introductory text of git-rebase documentation. + + - Converted remaining mentions of update-index on Porcelain + documents to git-add/git-rm. + + - Some i18n.* configuration variables were incorrectly + described as core.*; fixed. + +* Bugfixes + + - git-add and git-update-index on a filesystem on which + executable bits are unreliable incorrectly reused st_mode + bits even when the path changed between symlink and regular + file. + + - git-daemon marks the listening sockets with FD_CLOEXEC so + that it won't be leaked into the children. + + - segfault from git-blame when the mandatory pathname + parameter was missing was fixed; usage() message is given + instead. + + - git-rev-list did not read $GIT_DIR/config file, which means + that did not honor i18n.logoutputencoding correctly. + +* Tweaks + + - sliding mmap() inefficiently mmaped the same region of a + packfile with an access pattern that used objects in the + reverse order. This has been made more efficient. diff --git a/Documentation/RelNotes-1.5.0.2.txt b/Documentation/RelNotes-1.5.0.2.txt new file mode 100644 index 0000000000..b061e50ff0 --- /dev/null +++ b/Documentation/RelNotes-1.5.0.2.txt @@ -0,0 +1,65 @@ +GIT v1.5.0.2 Release Notes +========================== + +Fixes since v1.5.0.1 +-------------------- + +* Bugfixes + + - Automated merge conflict handling when changes to symbolic + links conflicted were completely broken. The merge-resolve + strategy created a regular file with conflict markers in it + in place of the symbolic link. The default strategy, + merge-recursive was even more broken. It removed the path + that was pointed at by the symbolic link. Both of these + problems have been fixed. + + - 'git diff maint master next' did not correctly give combined + diff across three trees. + + - 'git fast-import' portability fix for Solaris. + + - 'git show-ref --verify' without arguments did not error out + but segfaulted. + + - 'git diff :tracked-file `pwd`/an-untracked-file' gave an extra + slashes after a/ and b/. + + - 'git format-patch' produced too long filenames if the commit + message had too long line at the beginning. + + - Running 'make all' and then without changing anything + running 'make install' still rebuilt some files. This + was inconvenient when building as yourself and then + installing as root (especially problematic when the source + directory is on NFS and root is mapped to nobody). + + - 'git-rerere' failed to deal with two unconflicted paths that + sorted next to each other. + + - 'git-rerere' attempted to open(2) a symlink and failed if + there was a conflict. Since a conflicting change to a + symlink would not benefit from rerere anyway, the command + now ignores conflicting changes to symlinks. + + - 'git-repack' did not like to pass more than 64 arguments + internally to underlying 'rev-list' logic, which made it + impossible to repack after accumulating many (small) packs + in the repository. + + - 'git-diff' to review the combined diff during a conflicted + merge were not reading the working tree version correctly + when changes to a symbolic link conflicted. It should have + read the data using readlink(2) but read from the regular + file the symbolic link pointed at. + + - 'git-remote' did not like period in a remote's name. + +* Documentation updates + + - added and clarified core.bare, core.legacyheaders configurations. + + - updated "git-clone --depth" documentation. + + +* Assorted git-gui fixes. diff --git a/Documentation/RelNotes-1.5.0.3.txt b/Documentation/RelNotes-1.5.0.3.txt new file mode 100644 index 0000000000..cd500f96bf --- /dev/null +++ b/Documentation/RelNotes-1.5.0.3.txt @@ -0,0 +1,58 @@ +GIT v1.5.0.3 Release Notes +========================== + +Fixes since v1.5.0.2 +-------------------- + +* Bugfixes + + - 'git.el' honors the commit coding system from the configuration. + + - 'blameview' in contrib/ correctly digs deeper when a line is + clicked. + + - 'http-push' correctly makes sure the remote side has leading + path. Earlier it started in the middle of the path, and + incorrectly. + + - 'git-merge' did not exit with non-zero status when the + working tree was dirty and cannot fast forward. It does + now. + + - 'cvsexportcommit' does not lose yet-to-be-used message file. + + - int-vs-size_t typefix when running combined diff on files + over 2GB long. + + - 'git apply --whitespace=strip' should not touch unmodified + lines. + + - 'git-mailinfo' choke when a logical header line was too long. + + - 'git show A..B' did not error out. Negative ref ("not A" in + this example) does not make sense for the purpose of the + command, so now it errors out. + + - 'git fmt-merge-msg --file' without file parameter did not + correctly error out. + + - 'git archimport' barfed upon encountering a commit without + summary. + + - 'git index-pack' did not protect itself from getting a short + read out of pread(2). + + - 'git http-push' had a few buffer overruns. + + - Build dependency fixes to rebuild fetch.o when other headers + change. + +* Documentation updates + + - user-manual updates. + + - Options to 'git remote add' were described insufficiently. + + - Configuration format.suffix was not documented. + + - Other formatting and spelling fixes. diff --git a/Documentation/RelNotes-1.5.0.txt b/Documentation/RelNotes-1.5.0.txt new file mode 100644 index 0000000000..daf4bdb0d7 --- /dev/null +++ b/Documentation/RelNotes-1.5.0.txt @@ -0,0 +1,469 @@ +GIT v1.5.0 Release Notes +======================== + +Old news +-------- + +This section is for people who are upgrading from ancient +versions of git. Although all of the changes in this section +happened before the current v1.4.4 release, they are summarized +here in the v1.5.0 release notes for people who skipped earlier +versions. + +As of git v1.5.0 there are some optional features that changes +the repository to allow data to be stored and transferred more +efficiently. These features are not enabled by default, as they +will make the repository unusable with older versions of git. +Specifically, the available options are: + + - There is a configuration variable core.legacyheaders that + changes the format of loose objects so that they are more + efficient to pack and to send out of the repository over git + native protocol, since v1.4.2. However, loose objects + written in the new format cannot be read by git older than + that version; people fetching from your repository using + older clients over dumb transports (e.g. http) using older + versions of git will also be affected. + + To let git use the new loose object format, you have to + set core.legacyheaders to false. + + - Since v1.4.3, configuration repack.usedeltabaseoffset allows + packfile to be created in more space efficient format, which + cannot be read by git older than that version. + + To let git use the new format for packfiles, you have to + set repack.usedeltabaseoffset to true. + +The above two new features are not enabled by default and you +have to explicitly ask for them, because they make repositories +unreadable by older versions of git, and in v1.5.0 we still do +not enable them by default for the same reason. We will change +this default probably 1 year after 1.4.2's release, when it is +reasonable to expect everybody to have new enough version of +git. + + - 'git pack-refs' appeared in v1.4.4; this command allows tags + to be accessed much more efficiently than the traditional + 'one-file-per-tag' format. Older git-native clients can + still fetch from a repository that packed and pruned refs + (the server side needs to run the up-to-date version of git), + but older dumb transports cannot. Packing of refs is done by + an explicit user action, either by use of "git pack-refs + --prune" command or by use of "git gc" command. + + - 'git -p' to paginate anything -- many commands do pagination + by default on a tty. Introduced between v1.4.1 and v1.4.2; + this may surprise old timers. + + - 'git archive' superseded 'git tar-tree' in v1.4.3; + + - 'git cvsserver' was new invention in v1.3.0; + + - 'git repo-config', 'git grep', 'git rebase' and 'gitk' were + seriously enhanced during v1.4.0 timeperiod. + + - 'gitweb' became part of git.git during v1.4.0 timeperiod and + seriously modified since then. + + - reflog is an v1.4.0 invention. This allows you to name a + revision that a branch used to be at (e.g. "git diff + master@{yesterday} master" allows you to see changes since + yesterday's tip of the branch). + + +Updates in v1.5.0 since v1.4.4 series +------------------------------------- + +* Index manipulation + + - git-add is to add contents to the index (aka "staging area" + for the next commit), whether the file the contents happen to + be is an existing one or a newly created one. + + - git-add without any argument does not add everything + anymore. Use 'git-add .' instead. Also you can add + otherwise ignored files with an -f option. + + - git-add tries to be more friendly to users by offering an + interactive mode ("git-add -i"). + + - git-commit <path> used to refuse to commit if <path> was + different between HEAD and the index (i.e. update-index was + used on it earlier). This check was removed. + + - git-rm is much saner and safer. It is used to remove paths + from both the index file and the working tree, and makes sure + you are not losing any local modification before doing so. + + - git-reset <tree> <paths>... can be used to revert index + entries for selected paths. + + - git-update-index is much less visible. Many suggestions to + use the command in git output and documentation have now been + replaced by simpler commands such as "git add" or "git rm". + + +* Repository layout and objects transfer + + - The data for origin repository is stored in the configuration + file $GIT_DIR/config, not in $GIT_DIR/remotes/, for newly + created clones. The latter is still supported and there is + no need to convert your existing repository if you are + already comfortable with your workflow with the layout. + + - git-clone always uses what is known as "separate remote" + layout for a newly created repository with a working tree. + + A repository with the separate remote layout starts with only + one default branch, 'master', to be used for your own + development. Unlike the traditional layout that copied all + the upstream branches into your branch namespace (while + renaming their 'master' to your 'origin'), the new layout + puts upstream branches into local "remote-tracking branches" + with their own namespace. These can be referenced with names + such as "origin/$upstream_branch_name" and are stored in + .git/refs/remotes rather than .git/refs/heads where normal + branches are stored. + + This layout keeps your own branch namespace less cluttered, + avoids name collision with your upstream, makes it possible + to automatically track new branches created at the remote + after you clone from it, and makes it easier to interact with + more than one remote repository (you can use "git remote" to + add other repositories to track). There might be some + surprises: + + * 'git branch' does not show the remote tracking branches. + It only lists your own branches. Use '-r' option to view + the tracking branches. + + * If you are forking off of a branch obtained from the + upstream, you would have done something like 'git branch + my-next next', because traditional layout dropped the + tracking branch 'next' into your own branch namespace. + With the separate remote layout, you say 'git branch next + origin/next', which allows you to use the matching name + 'next' for your own branch. It also allows you to track a + remote other than 'origin' (i.e. where you initially cloned + from) and fork off of a branch from there the same way + (e.g. "git branch mingw j6t/master"). + + Repositories initialized with the traditional layout continue + to work. + + - New branches that appear on the origin side after a clone is + made are also tracked automatically. This is done with an + wildcard refspec "refs/heads/*:refs/remotes/origin/*", which + older git does not understand, so if you clone with 1.5.0, + you would need to downgrade remote.*.fetch in the + configuration file to specify each branch you are interested + in individually if you plan to fetch into the repository with + older versions of git (but why would you?). + + - Similarly, wildcard refspec "refs/heads/*:refs/remotes/me/*" + can be given to "git-push" command to update the tracking + branches that is used to track the repository you are pushing + from on the remote side. + + - git-branch and git-show-branch know remote tracking branches + (use the command line switch "-r" to list only tracked branches). + + - git-push can now be used to delete a remote branch or a tag. + This requires the updated git on the remote side (use "git + push <remote> :refs/heads/<branch>" to delete "branch"). + + - git-push more aggressively keeps the transferred objects + packed. Earlier we recommended to monitor amount of loose + objects and repack regularly, but you should repack when you + accumulated too many small packs this way as well. Updated + git-count-objects helps you with this. + + - git-fetch also more aggressively keeps the transferred objects + packed. This behavior of git-push and git-fetch can be + tweaked with a single configuration transfer.unpacklimit (but + usually there should not be any need for a user to tweak it). + + - A new command, git-remote, can help you manage your remote + tracking branch definitions. + + - You may need to specify explicit paths for upload-pack and/or + receive-pack due to your ssh daemon configuration on the + other end. This can now be done via remote.*.uploadpack and + remote.*.receivepack configuration. + + +* Bare repositories + + - Certain commands change their behavior in a bare repository + (i.e. a repository without associated working tree). We use + a fairly conservative heuristic (if $GIT_DIR is ".git", or + ends with "/.git", the repository is not bare) to decide if a + repository is bare, but "core.bare" configuration variable + can be used to override the heuristic when it misidentifies + your repository. + + - git-fetch used to complain updating the current branch but + this is now allowed for a bare repository. So is the use of + 'git-branch -f' to update the current branch. + + - Porcelain-ish commands that require a working tree refuses to + work in a bare repository. + + +* Reflog + + - Reflog records the history from the view point of the local + repository. In other words, regardless of the real history, + the reflog shows the history as seen by one particular + repository (this enables you to ask "what was the current + revision in _this_ repository, yesterday at 1pm?"). This + facility is enabled by default for repositories with working + trees, and can be accessed with the "branch@{time}" and + "branch@{Nth}" notation. + + - "git show-branch" learned showing the reflog data with the + new -g option. "git log" has -g option to view reflog + entries in a more verbose manner. + + - git-branch knows how to rename branches and moves existing + reflog data from the old branch to the new one. + + - In addition to the reflog support in v1.4.4 series, HEAD + reference maintains its own log. "HEAD@{5.minutes.ago}" + means the commit you were at 5 minutes ago, which takes + branch switching into account. If you want to know where the + tip of your current branch was at 5 minutes ago, you need to + explicitly say its name (e.g. "master@{5.minutes.ago}") or + omit the refname altogether i.e. "@{5.minutes.ago}". + + - The commits referred to by reflog entries are now protected + against pruning. The new command "git reflog expire" can be + used to truncate older reflog entries and entries that refer + to commits that have been pruned away previously with older + versions of git. + + Existing repositories that have been using reflog may get + complaints from fsck-objects and may not be able to run + git-repack, if you had run git-prune from older git; please + run "git reflog expire --stale-fix --all" first to remove + reflog entries that refer to commits that are no longer in + the repository when that happens. + + +* Crufts removal + + - We used to say "old commits are retrievable using reflog and + 'master@{yesterday}' syntax as long as you haven't run + git-prune". We no longer have to say the latter half of the + above sentence, as git-prune does not remove things reachable + from reflog entries. + + - There is a toplevel garbage collector script, 'git-gc', that + runs periodic cleanup functions, including 'git-repack -a -d', + 'git-reflog expire', 'git-pack-refs --prune', and 'git-rerere + gc'. + + - The output from fsck ("fsck-objects" is called just "fsck" + now, but the old name continues to work) was needlessly + alarming in that it warned missing objects that are reachable + only from dangling objects. This has been corrected and the + output is much more useful. + + +* Detached HEAD + + - You can use 'git-checkout' to check out an arbitrary revision + or a tag as well, instead of named branches. This will + dissociate your HEAD from the branch you are currently on. + + A typical use of this feature is to "look around". E.g. + + $ git checkout v2.6.16 + ... compile, test, etc. + $ git checkout v2.6.17 + ... compile, test, etc. + + - After detaching your HEAD, you can go back to an existing + branch with usual "git checkout $branch". Also you can + start a new branch using "git checkout -b $newbranch" to + start a new branch at that commit. + + - You can even pull from other repositories, make merges and + commits while your HEAD is detached. Also you can use "git + reset" to jump to arbitrary commit, while still keeping your + HEAD detached. + + Remember that a detached state is volatile, i.e. it will be forgotten + as soon as you move away from it with the checkout or reset command, + unless a branch is created from it as mentioned above. It is also + possible to rescue a lost detached state from the HEAD reflog. + + +* Packed refs + + - Repositories with hundreds of tags have been paying large + overhead, both in storage and in runtime, due to the + traditional one-ref-per-file format. A new command, + git-pack-refs, can be used to "pack" them in more efficient + representation (you can let git-gc do this for you). + + - Clones and fetches over dumb transports are now aware of + packed refs and can download from repositories that use + them. + + +* Configuration + + - configuration related to color setting are consolidated under + color.* namespace (older diff.color.*, status.color.* are + still supported). + + - 'git-repo-config' command is accessible as 'git-config' now. + + +* Updated features + + - git-describe uses better criteria to pick a base ref. It + used to pick the one with the newest timestamp, but now it + picks the one that is topologically the closest (that is, + among ancestors of commit C, the ref T that has the shortest + output from "git-rev-list T..C" is chosen). + + - git-describe gives the number of commits since the base ref + between the refname and the hash suffix. E.g. the commit one + before v2.6.20-rc6 in the kernel repository is: + + v2.6.20-rc5-306-ga21b069 + + which tells you that its object name begins with a21b069, + v2.6.20-rc5 is an ancestor of it (meaning, the commit + contains everything -rc5 has), and there are 306 commits + since v2.6.20-rc5. + + - git-describe with --abbrev=0 can be used to show only the + name of the base ref. + + - git-blame learned a new option, --incremental, that tells it + to output the blames as they are assigned. A sample script + to use it is also included as contrib/blameview. + + - git-blame starts annotating from the working tree by default. + + +* Less external dependency + + - We no longer require the "merge" program from the RCS suite. + All 3-way file-level merges are now done internally. + + - The original implementation of git-merge-recursive which was + in Python has been removed; we have a C implementation of it + now. + + - git-shortlog is no longer a Perl script. It no longer + requires output piped from git-log; it can accept revision + parameters directly on the command line. + + +* I18n + + - We have always encouraged the commit message to be encoded in + UTF-8, but the users are allowed to use legacy encoding as + appropriate for their projects. This will continue to be the + case. However, a non UTF-8 commit encoding _must_ be + explicitly set with i18n.commitencoding in the repository + where a commit is made; otherwise git-commit-tree will + complain if the log message does not look like a valid UTF-8 + string. + + - The value of i18n.commitencoding in the originating + repository is recorded in the commit object on the "encoding" + header, if it is not UTF-8. git-log and friends notice this, + and reencodes the message to the log output encoding when + displaying, if they are different. The log output encoding + is determined by "git log --encoding=<encoding>", + i18n.logoutputencoding configuration, or i18n.commitencoding + configuration, in the decreasing order of preference, and + defaults to UTF-8. + + - Tools for e-mailed patch application now default to -u + behavior; i.e. it always re-codes from the e-mailed encoding + to the encoding specified with i18n.commitencoding. This + unfortunately forces projects that have happily been using a + legacy encoding without setting i18n.commitencoding to set + the configuration, but taken with other improvement, please + excuse us for this very minor one-time inconvenience. + + +* e-mailed patches + + - See the above I18n section. + + - git-format-patch now enables --binary without being asked. + git-am does _not_ default to it, as sending binary patch via + e-mail is unusual and is harder to review than textual + patches and it is prudent to require the person who is + applying the patch to explicitly ask for it. + + - The default suffix for git-format-patch output is now ".patch", + not ".txt". This can be changed with --suffix=.txt option, + or setting the config variable "format.suffix" to ".txt". + + +* Foreign SCM interfaces + + - git-svn now requires the Perl SVN:: libraries, the + command-line backend was too slow and limited. + + - the 'commit' subcommand of git-svn has been renamed to + 'set-tree', and 'dcommit' is the recommended replacement for + day-to-day work. + + - git fast-import backend. + + +* User support + + - Quite a lot of documentation updates. + + - Bash completion scripts have been updated heavily. + + - Better error messages for often used Porcelainish commands. + + - Git GUI. This is a simple Tk based graphical interface for + common Git operations. + + +* Sliding mmap + + - We used to assume that we can mmap the whole packfile while + in use, but with a large project this consumes huge virtual + memory space and truly huge ones would not fit in the + userland address space on 32-bit platforms. We now mmap huge + packfile in pieces to avoid this problem. + + +* Shallow clones + + - There is a partial support for 'shallow' repositories that + keeps only recent history. A 'shallow clone' is created by + specifying how deep that truncated history should be + (e.g. "git clone --depth 5 git://some.where/repo.git"). + + Currently a shallow repository has number of limitations: + + - Cloning and fetching _from_ a shallow clone are not + supported (nor tested -- so they might work by accident but + they are not expected to). + + - Pushing from nor into a shallow clone are not expected to + work. + + - Merging inside a shallow repository would work as long as a + merge base is found in the recent history, but otherwise it + will be like merging unrelated histories and may result in + huge conflicts. + + but this would be more than adequate for people who want to + look at near the tip of a big project with a deep history and + send patches in e-mail format. diff --git a/Documentation/RelNotes-1.5.1.txt b/Documentation/RelNotes-1.5.1.txt new file mode 100644 index 0000000000..f374e1c2c7 --- /dev/null +++ b/Documentation/RelNotes-1.5.1.txt @@ -0,0 +1,117 @@ +GIT v1.5.1 Release Notes +======================== + +Updates since v1.5.0 +-------------------- + +* Deprecated commands and options. + + - git-diff-stages and git-resolve have been removed. + +* New commands and options. + + - "git log" and friends take --reverse. This makes output + that typically goes reverse order in chronological order. + "git shortlog" usually lists commits in chronological order, + but with "--reverse", they are shown in reverse + chronological order. + + - "git diff" learned --ignore-space-at-eol. This is a weaker + form of --ignore-space-change. + + - "git diff --no-index pathA pathB" can be used as diff + replacement with git specific enhancements. + + - "git diff --pretty=format:<string>" to allow more flexible + custom log output. + + - "git name-rev" learned --refs=<pattern>, to limit the tags + used for naming the given revisions only to the ones + matching the given pattern. + + - "git remote update" is to run "git fetch" for defined remotes + to update tracking branches. + + - "git cvsimport" can now take '-d' to talk with a CVS + repository different from what are recorded in CVS/Root + (overriding it with environment CVSROOT does not work). + + - "git bundle" can help sneaker-netting your changes between + repositories. + + - A new configuration "core.symlinks" can be used to disable + symlinks on filesystems that do not support them; they are + checked out as regular files instead. + + +* Updated behaviour of existing commands. + + - git-svn got almost a rewrite. + + - core.autocrlf configuration, when set to 'true', makes git + to convert CRLF at the end of lines in text files to LF when + reading from the filesystem, and convert in reverse when + writing to the filesystem. The variable can be set to + 'input', in which case the conversion happens only while + reading from the filesystem but files are written out with + LF at the end of lines. Currently, which paths to consider + 'text' (i.e. be subjected to the autocrlf mechanism) is + decided purely based on the contents, but the plan is to + allow users to explicitly override this heuristic based on + paths. + + - The behaviour of 'git-apply', when run in a subdirectory, + without --index nor --cached were inconsistent with that of + the command with these options. This was fixed to match the + behaviour with --index. A patch that is meant to be applied + with -p1 from the toplevel of the project tree can be + applied with any custom -p<n> option. A patch that is not + relative to the toplevel needs to be applied with -p<n> + option with or without --index (or --cached). + + - "git diff" outputs a trailing HT when pathnames have embedded + SP on +++/--- header lines, in order to help "GNU patch" to + parse its output. "git apply" was already updated to accept + this modified output format since ce74618d (Sep 22, 2006). + + - "git cvsserver" runs hooks/update and honors its exit status. + + - "git cvsserver" can be told to send everything with -kb. + + - "git diff --check" also honors the --color output option. + + - "git name-rev" used to stress the fact that a ref is a tag too + much, by saying something like "v1.2.3^0~22". It now says + "v1.2.3~22" in such a case (it still says "v1.2.3^0" if it does + not talk about an ancestor of the commit that is tagged, which + makes sense). + + - "git rev-list --boundary" now shows boundary markers for the + commits omitted by --max-age and --max-count condition. + + - The configuration mechanism now reads $(prefix)/etc/gitconfig. + + - "git apply --verbose" shows what preimage lines were wanted + when it couldn't find them. + + - "git status" in a read-only repository got a bit saner. + + - "git fetch" (hence "git clone" and "git pull") are less + noisy when the output does not go to tty. + +* Hooks + + - The sample update hook to show how to send out notification + e-mail was updated to show only new commits that appeared in + the repository. Earlier, it showed new commits that appeared + on the branch. + +-- +exec >/var/tmp/1 +O=v1.5.0.3-268-g3ddad98 +echo O=`git describe master` +git shortlog --no-merges $O..master ^maint + +# Local Variables: +# mode: text +# End: diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches new file mode 100644 index 0000000000..131bcff9b2 --- /dev/null +++ b/Documentation/SubmittingPatches @@ -0,0 +1,376 @@ +Checklist (and a short version for the impatient): + + - make commits of logical units + - check for unnecessary whitespace with "git diff --check" + before committing + - do not check in commented out code or unneeded files + - provide a meaningful commit message + - the first line of the commit message should be a short + description and should skip the full stop + - if you want your work included in git.git, add a + "Signed-off-by: Your Name <your@email.com>" line to the + commit message (or just use the option "-s" when + committing) to confirm that you agree to the Developer's + Certificate of Origin + - do not PGP sign your patch + - use "git format-patch -M" to create the patch + - do not attach your patch, but read in the mail + body, unless you cannot teach your mailer to + leave the formatting of the patch alone. + - be careful doing cut & paste into your mailer, not to + corrupt whitespaces. + - provide additional information (which is unsuitable for + the commit message) between the "---" and the diffstat + - send the patch to the list _and_ the maintainer + +Long version: + +I started reading over the SubmittingPatches document for Linux +kernel, primarily because I wanted to have a document similar to +it for the core GIT to make sure people understand what they are +doing when they write "Signed-off-by" line. + +But the patch submission requirements are a lot more relaxed +here on the technical/contents front, because the core GIT is +thousand times smaller ;-). So here is only the relevant bits. + + +(1) Make separate commits for logically separate changes. + +Unless your patch is really trivial, you should not be sending +out a patch that was generated between your working tree and +your commit head. Instead, always make a commit with complete +commit message and generate a series of patches from your +repository. It is a good discipline. + +Describe the technical detail of the change(s). + +If your description starts to get too long, that's a sign that you +probably need to split up your commit to finer grained pieces. + +Oh, another thing. I am picky about whitespaces. Make sure your +changes do not trigger errors with the sample pre-commit hook shipped +in templates/hooks--pre-commit. To help ensure this does not happen, +run git diff --check on your changes before you commit. + + +(2) Generate your patch using git tools out of your commits. + +git based diff tools (git, Cogito, and StGIT included) generate +unidiff which is the preferred format. + +You do not have to be afraid to use -M option to "git diff" or +"git format-patch", if your patch involves file renames. The +receiving end can handle them just fine. + +Please make sure your patch does not include any extra files +which do not belong in a patch submission. Make sure to review +your patch after generating it, to ensure accuracy. Before +sending out, please make sure it cleanly applies to the "master" +branch head. If you are preparing a work based on "next" branch, +that is fine, but please mark it as such. + + +(3) Sending your patches. + +People on the git mailing list need to be able to read and +comment on the changes you are submitting. It is important for +a developer to be able to "quote" your changes, using standard +e-mail tools, so that they may comment on specific portions of +your code. For this reason, all patches should be submitted +"inline". WARNING: Be wary of your MUAs word-wrap +corrupting your patch. Do not cut-n-paste your patch; you can +lose tabs that way if you are not careful. + +It is a common convention to prefix your subject line with +[PATCH]. This lets people easily distinguish patches from other +e-mail discussions. + +"git format-patch" command follows the best current practice to +format the body of an e-mail message. At the beginning of the +patch should come your commit message, ending with the +Signed-off-by: lines, and a line that consists of three dashes, +followed by the diffstat information and the patch itself. If +you are forwarding a patch from somebody else, optionally, at +the beginning of the e-mail message just before the commit +message starts, you can put a "From: " line to name that person. + +You often want to add additional explanation about the patch, +other than the commit message itself. Place such "cover letter" +material between the three dash lines and the diffstat. + +Do not attach the patch as a MIME attachment, compressed or not. +Do not let your e-mail client send quoted-printable. Do not let +your e-mail client send format=flowed which would destroy +whitespaces in your patches. Many +popular e-mail applications will not always transmit a MIME +attachment as plain text, making it impossible to comment on +your code. A MIME attachment also takes a bit more time to +process. This does not decrease the likelihood of your +MIME-attached change being accepted, but it makes it more likely +that it will be postponed. + +Exception: If your mailer is mangling patches then someone may ask +you to re-send them using MIME, that is OK. + +Do not PGP sign your patch, at least for now. Most likely, your +maintainer or other people on the list would not have your PGP +key and would not bother obtaining it anyway. Your patch is not +judged by who you are; a good patch from an unknown origin has a +far better chance of being accepted than a patch from a known, +respected origin that is done poorly or does incorrect things. + +If you really really really really want to do a PGP signed +patch, format it as "multipart/signed", not a text/plain message +that starts with '-----BEGIN PGP SIGNED MESSAGE-----'. That is +not a text/plain, it's something else. + +Note that your maintainer does not necessarily read everything +on the git mailing list. If your patch is for discussion first, +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/. + + +(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 +that are being emailed around. Although core GIT is a lot +smaller project it is a good discipline to follow it. + +The sign-off is a simple line at the end of the explanation for +the patch, which certifies that you wrote it or otherwise have +the right to pass it on as a open-source patch. The rules are +pretty simple: if you can certify the below: + + Developer's Certificate of Origin 1.1 + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I + have the right to submit it under the open source license + indicated in the file; or + + (b) The contribution is based upon previous work that, to the best + of my knowledge, is covered under an appropriate open source + license and I have the right under that license to submit that + work with modifications, whether created in whole or in part + by me, under the same open source license (unless I am + permitted to submit under a different license), as indicated + in the file; or + + (c) The contribution was provided directly to me by some other + person who certified (a), (b) or (c) and I have not modified + it. + + (d) I understand and agree that this project and the contribution + are public and that a record of the contribution (including all + personal information I submit with it, including my sign-off) is + maintained indefinitely and may be redistributed consistent with + this project or the open source license(s) involved. + +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. + + +------------------------------------------------ +MUA specific hints + +Some of patches I receive or pick up from the list share common +patterns of breakage. Please make sure your MUA is set up +properly not to corrupt whitespaces. Here are two common ones +I have seen: + +* Empty context lines that do not have _any_ whitespace. + +* Non empty context lines that have one extra whitespace at the + beginning. + +One test you could do yourself if your MUA is set up correctly is: + +* Send the patch to yourself, exactly the way you would, except + To: and Cc: lines, which would not contain the list and + maintainer address. + +* Save that patch to a file in UNIX mailbox format. Call it say + a.patch. + +* Try to apply to the tip of the "master" branch from the + git.git public repository: + + $ git fetch http://kernel.org/pub/scm/git/git.git master:test-apply + $ git checkout test-apply + $ git reset --hard + $ git applymbox a.patch + +If it does not apply correctly, there can be various reasons. + +* Your patch itself does not apply cleanly. That is _bad_ but + does not have much to do with your MUA. Please rebase the + patch appropriately. + +* Your MUA corrupted your patch; applymbox would complain that + the patch does not apply. Look at .dotest/ subdirectory and + see what 'patch' file contains and check for the common + corruption patterns mentioned above. + +* While you are at it, check what are in 'info' and + 'final-commit' files as well. If what is in 'final-commit' is + not exactly what you would want to see in the commit log + message, it is very likely that your maintainer would end up + hand editing the log message when he applies your patch. + Things like "Hi, this is my first patch.\n", if you really + want to put in the patch e-mail, should come after the + three-dash line that signals the end of the commit message. + + +Pine +---- + +(Johannes Schindelin) + +I don't know how many people still use pine, but for those poor +souls it may be good to mention that the quell-flowed-text is +needed for recent versions. + +... the "no-strip-whitespace-before-send" option, too. AFAIK it +was introduced in 4.60. + +(Linus Torvalds) + +And 4.58 needs at least this. + +--- +diff-tree 8326dd8350be64ac7fc805f6563a1d61ad10d32c (from e886a61f76edf5410573e92e38ce22974f9c40f1) +Author: Linus Torvalds <torvalds@g5.osdl.org> +Date: Mon Aug 15 17:23:51 2005 -0700 + + Fix pine whitespace-corruption bug + + There's no excuse for unconditionally removing whitespace from + the pico buffers on close. + +diff --git a/pico/pico.c b/pico/pico.c +--- a/pico/pico.c ++++ b/pico/pico.c +@@ -219,7 +219,9 @@ PICO *pm; + switch(pico_all_done){ /* prepare for/handle final events */ + case COMP_EXIT : /* already confirmed */ + packheader(); ++#if 0 + stripwhitespace(); ++#endif + c |= COMP_EXIT; + break; + + +(Daniel Barkalow) + +> A patch to SubmittingPatches, MUA specific help section for +> users of Pine 4.63 would be very much appreciated. + +Ah, it looks like a recent version changed the default behavior to do the +right thing, and inverted the sense of the configuration option. (Either +that or Gentoo did it.) So you need to set the +"no-strip-whitespace-before-send" option, unless the option you have is +"strip-whitespace-before-send", in which case you should avoid checking +it. + + +Thunderbird +----------- + +(A Large Angry SCM) + +Here are some hints on how to successfully submit patches inline using +Thunderbird. + +This recipe appears to work with the current [*1*] Thunderbird from Suse. + +The following Thunderbird extensions are needed: + AboutConfig 0.5 + http://aboutconfig.mozdev.org/ + External Editor 0.7.2 + http://globs.org/articles.php?lng=en&pg=8 + +1) Prepare the patch as a text file using your method of choice. + +2) Before opening a compose window, use Edit->Account Settings to +uncheck the "Compose messages in HTML format" setting in the +"Composition & Addressing" panel of the account to be used to send the +patch. [*2*] + +3) In the main Thunderbird window, _before_ you open the compose window +for the patch, use Tools->about:config to set the following to the +indicated values: + mailnews.send_plaintext_flowed => false + mailnews.wraplength => 0 + +4) Open a compose window and click the external editor icon. + +5) In the external editor window, read in the patch file and exit the +editor normally. + +6) Back in the compose window: Add whatever other text you wish to the +message, complete the addressing and subject fields, and press send. + +7) Optionally, undo the about:config/account settings changes made in +steps 2 & 3. + + +[Footnotes] +*1* Version 1.0 (20041207) from the MozillaThunderbird-1.0-5 rpm of Suse +9.3 professional updates. + +*2* It may be possible to do this with about:config and the following +settings but I haven't tried, yet. + mail.html_compose => false + mail.identity.default.compose_html => false + mail.identity.id?.compose_html => false + + +Gnus +---- + +'|' in the *Summary* buffer can be used to pipe the current +message to an external program, and this is a handy way to drive +"git am". However, if the message is MIME encoded, what is +piped into the program is the representation you see in your +*Article* buffer after unwrapping MIME. This is often not what +you would want for two reasons. It tends to screw up non ASCII +characters (most notably in people's names), and also +whitespaces (fatal in patches). Running 'C-u g' to display the +message in raw form before using '|' to run the pipe can work +this problem around. + + +KMail +----- + +This should help you to submit patches inline using KMail. + +1) Prepare the patch as a text file. + +2) Click on New Mail. + +3) Go under "Options" in the Composer window and be sure that +"Word wrap" is not set. + +4) Use Message -> Insert file... and insert the patch. + +5) Back in the compose window: add whatever other text you wish to the +message, complete the addressing and subject fields, and press send. diff --git a/Documentation/asciidoc.conf b/Documentation/asciidoc.conf new file mode 100644 index 0000000000..44b1ce4c6b --- /dev/null +++ b/Documentation/asciidoc.conf @@ -0,0 +1,39 @@ +## gitlink: macro +# +# Usage: gitlink:command[manpage-section] +# +# Note, {0} is the manpage section, while {target} is the command. +# +# Show GIT link as: <command>(<section>); if section is defined, else just show +# the command. + +[attributes] +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[gitlink-inlinemacro] +{0%{target}} +{0#<citerefentry>} +{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>} +{0#</citerefentry>} +endif::backend-docbook[] + +ifdef::backend-docbook[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout> +{title#}</example> +endif::backend-docbook[] + +ifdef::backend-xhtml11[] +[gitlink-inlinemacro] +<a href="{target}.html">{target}{0?({0})}</a> +endif::backend-xhtml11[] + + diff --git a/Documentation/build-docdep.perl b/Documentation/build-docdep.perl new file mode 100755 index 0000000000..ba4205e030 --- /dev/null +++ b/Documentation/build-docdep.perl @@ -0,0 +1,46 @@ +#!/usr/bin/perl + +my %include = (); +my %included = (); + +for my $text (<*.txt>) { + open I, '<', $text || die "cannot read: $text"; + while (<I>) { + if (/^include::/) { + chomp; + s/^include::\s*//; + s/\[\]//; + $include{$text}{$_} = 1; + $included{$_} = 1; + } + } + close I; +} + +# Do we care about chained includes??? +my $changed = 1; +while ($changed) { + $changed = 0; + while (my ($text, $included) = each %include) { + for my $i (keys %$included) { + # $text has include::$i; if $i includes $j + # $text indirectly includes $j. + if (exists $include{$i}) { + for my $j (keys %{$include{$i}}) { + if (!exists $include{$text}{$j}) { + $include{$text}{$j} = 1; + $included{$j} = 1; + $changed = 1; + } + } + } + } + } +} + +while (my ($text, $included) = each %include) { + if (! exists $included{$text} && + (my $base = $text) =~ s/\.txt$//) { + print "$base.html $base.xml : ", join(" ", keys %$included), "\n"; + } +} diff --git a/Documentation/callouts.xsl b/Documentation/callouts.xsl new file mode 100644 index 0000000000..6a361a2136 --- /dev/null +++ b/Documentation/callouts.xsl @@ -0,0 +1,30 @@ +<!-- callout.xsl: converts asciidoc callouts to man page format --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"> +<xsl:template match="co"> + <xsl:value-of select="concat('\fB(',substring-after(@id,'-'),')\fR')"/> +</xsl:template> +<xsl:template match="calloutlist"> + <xsl:text>.sp </xsl:text> + <xsl:apply-templates/> + <xsl:text> </xsl:text> +</xsl:template> +<xsl:template match="callout"> + <xsl:value-of select="concat('\fB',substring-after(@arearefs,'-'),'. \fR')"/> + <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($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + +</xsl:stylesheet> diff --git a/Documentation/cmd-list.perl b/Documentation/cmd-list.perl new file mode 100755 index 0000000000..f61c77aa7c --- /dev/null +++ b/Documentation/cmd-list.perl @@ -0,0 +1,187 @@ +# + +sub format_one { + my ($out, $name) = @_; + my ($state, $description); + open I, '<', "$name.txt" or die "No such file $name.txt"; + while (<I>) { + if (/^NAME$/) { + $state = 1; + next; + } + if ($state == 1 && /^----$/) { + $state = 2; + next; + } + next if ($state != 2); + chomp; + $description = $_; + last; + } + close I; + if (!defined $description) { + die "No description found in $name.txt"; + } + if (my ($verify_name, $text) = ($description =~ /^($name) - (.*)/)) { + print $out "gitlink:$name\[1\]::\n"; + print $out "\t$text.\n\n"; + } + else { + die "Description does not match $name: $description"; + } +} + +my %cmds = (); +while (<DATA>) { + next if /^#/; + + chomp; + my ($name, $cat) = /^(\S+)\s+(.*)$/; + push @{$cmds{$cat}}, $name; +} + +for my $cat (qw(ancillaryinterrogators + ancillarymanipulators + mainporcelain + plumbinginterrogators + plumbingmanipulators + synchingrepositories + foreignscminterface + purehelpers + synchelpers)) { + my $out = "cmds-$cat.txt"; + open O, '>', "$out+" or die "Cannot open output file $out+"; + for (@{$cmds{$cat}}) { + format_one(\*O, $_); + } + close O; + rename "$out+", "$out"; +} + +__DATA__ +git-add mainporcelain +git-am mainporcelain +git-annotate ancillaryinterrogators +git-applymbox ancillaryinterrogators +git-applypatch purehelpers +git-apply plumbingmanipulators +git-archimport foreignscminterface +git-archive mainporcelain +git-bisect mainporcelain +git-blame ancillaryinterrogators +git-branch mainporcelain +git-bundle mainporcelain +git-cat-file plumbinginterrogators +git-checkout-index plumbingmanipulators +git-checkout mainporcelain +git-check-ref-format purehelpers +git-cherry ancillaryinterrogators +git-cherry-pick mainporcelain +git-clean mainporcelain +git-clone mainporcelain +git-commit mainporcelain +git-commit-tree plumbingmanipulators +git-convert-objects ancillarymanipulators +git-count-objects ancillaryinterrogators +git-cvsexportcommit foreignscminterface +git-cvsimport foreignscminterface +git-cvsserver foreignscminterface +git-daemon synchingrepositories +git-describe mainporcelain +git-diff-files plumbinginterrogators +git-diff-index plumbinginterrogators +git-diff mainporcelain +git-diff-tree plumbinginterrogators +git-fast-import ancillarymanipulators +git-fetch mainporcelain +git-fetch-pack synchingrepositories +git-fmt-merge-msg purehelpers +git-for-each-ref plumbinginterrogators +git-format-patch mainporcelain +git-fsck ancillaryinterrogators +git-gc mainporcelain +git-get-tar-commit-id ancillaryinterrogators +git-grep mainporcelain +git-hash-object plumbingmanipulators +git-http-fetch synchelpers +git-http-push synchelpers +git-imap-send foreignscminterface +git-index-pack plumbingmanipulators +git-init mainporcelain +git-instaweb ancillaryinterrogators +gitk mainporcelain +git-local-fetch synchingrepositories +git-log mainporcelain +git-lost-found ancillarymanipulators +git-ls-files plumbinginterrogators +git-ls-remote plumbinginterrogators +git-ls-tree plumbinginterrogators +git-mailinfo purehelpers +git-mailsplit purehelpers +git-merge-base plumbinginterrogators +git-merge-file plumbingmanipulators +git-merge-index plumbingmanipulators +git-merge mainporcelain +git-merge-one-file purehelpers +git-merge-tree ancillaryinterrogators +git-mktag plumbingmanipulators +git-mktree plumbingmanipulators +git-mv mainporcelain +git-name-rev plumbinginterrogators +git-pack-objects plumbingmanipulators +git-pack-redundant plumbinginterrogators +git-pack-refs ancillarymanipulators +git-parse-remote synchelpers +git-patch-id purehelpers +git-peek-remote purehelpers +git-prune ancillarymanipulators +git-prune-packed plumbingmanipulators +git-pull mainporcelain +git-push mainporcelain +git-quiltimport foreignscminterface +git-read-tree plumbingmanipulators +git-rebase mainporcelain +git-receive-pack synchelpers +git-reflog ancillarymanipulators +git-relink ancillarymanipulators +git-repack ancillarymanipulators +git-config ancillarymanipulators +git-remote ancillarymanipulators +git-request-pull foreignscminterface +git-rerere ancillaryinterrogators +git-reset mainporcelain +git-revert mainporcelain +git-rev-list plumbinginterrogators +git-rev-parse ancillaryinterrogators +git-rm mainporcelain +git-runstatus ancillaryinterrogators +git-send-email foreignscminterface +git-send-pack synchingrepositories +git-shell synchelpers +git-shortlog mainporcelain +git-show mainporcelain +git-show-branch ancillaryinterrogators +git-show-index plumbinginterrogators +git-show-ref plumbinginterrogators +git-sh-setup purehelpers +git-ssh-fetch synchingrepositories +git-ssh-upload synchingrepositories +git-status mainporcelain +git-stripspace purehelpers +git-svn foreignscminterface +git-svnimport foreignscminterface +git-symbolic-ref plumbingmanipulators +git-tag mainporcelain +git-tar-tree plumbinginterrogators +git-unpack-file plumbinginterrogators +git-unpack-objects plumbingmanipulators +git-update-index plumbingmanipulators +git-update-ref plumbingmanipulators +git-update-server-info synchingrepositories +git-upload-archive synchelpers +git-upload-pack synchelpers +git-var plumbinginterrogators +git-verify-pack plumbinginterrogators +git-verify-tag ancillaryinterrogators +git-whatchanged ancillaryinterrogators +git-write-tree plumbingmanipulators diff --git a/Documentation/config.txt b/Documentation/config.txt new file mode 100644 index 0000000000..5408dd67d3 --- /dev/null +++ b/Documentation/config.txt @@ -0,0 +1,573 @@ +CONFIGURATION FILE +------------------ + +The git configuration file contains a number of variables that affect +the git command's behavior. `.git/config` file for each repository +is used to store the information for that repository, and +`$HOME/.gitconfig` is used to store per user information to give +fallback values for `.git/config` file. The file `/etc/gitconfig` +can be used to store system-wide defaults. + +They can be used by both the git plumbing +and the porcelains. The variables are divided into sections, where +in the fully qualified variable name the variable itself is the last +dot-separated segment and the section name is everything before the last +dot. The variable names are case-insensitive and only alphanumeric +characters are allowed. Some variables may appear multiple times. + +Syntax +~~~~~~ + +The syntax is fairly flexible and permissive; whitespaces are mostly +ignored. The '#' and ';' characters begin comments to the end of line, +blank lines are ignored. + +The file consists of sections and variables. A section begins with +the name of the section in square brackets and continues until the next +section begins. Section names are not case sensitive. Only alphanumeric +characters, '`-`' and '`.`' are allowed in section names. Each variable +must belong to some section, which means that there must be section +header before first setting of a variable. + +Sections can be further divided into subsections. To begin a subsection +put its name in double quotes, separated by space from the section name, +in the section header, like in example below: + +-------- + [section "subsection"] + +-------- + +Subsection names can contain any characters except newline (doublequote +'`"`' and backslash have to be escaped as '`\"`' and '`\\`', +respectively) and are case sensitive. Section header cannot span multiple +lines. Variables may belong directly to a section or to a given subsection. +You can have `[section]` if you have `[section "subsection"]`, but you +don't need to. + +There is also (case insensitive) alternative `[section.subsection]` syntax. +In this syntax subsection names follow the same restrictions as for section +name. + +All the other lines are recognized as setting variables, in the form +'name = value'. If there is no equal sign on the line, the entire line +is taken as 'name' and the variable is recognized as boolean "true". +The variable names are case-insensitive and only alphanumeric +characters and '`-`' are allowed. There can be more than one value +for a given variable; we say then that variable is multivalued. + +Leading and trailing whitespace in a variable value is discarded. +Internal whitespace within a variable value is retained verbatim. + +The values following the equals sign in variable assign are all either +a string, an integer, or a boolean. Boolean values may be given as yes/no, +0/1 or true/false. Case is not significant in boolean values, when +converting value to the canonical form using '--bool' type specifier; +`git-config` will ensure that the output is "true" or "false". + +String values may be entirely or partially enclosed in double quotes. +You need to enclose variable value in double quotes if you want to +preserve leading or trailing whitespace, or if variable value contains +beginning of comment characters (if it contains '#' or ';'). +Double quote '`"`' and backslash '`\`' characters in variable value must +be escaped: use '`\"`' for '`"`' and '`\\`' for '`\`'. + +The following escape sequences (beside '`\"`' and '`\\`') are recognized: +'`\n`' for newline character (NL), '`\t`' for horizontal tabulation (HT, TAB) +and '`\b`' for backspace (BS). No other char escape sequence, nor octal +char sequences are valid. + +Variable value ending in a '`\`' is continued on the next line in the +customary UNIX fashion. + +Some variables may require special value format. + +Example +~~~~~~~ + + # Core variables + [core] + ; Don't trust file modes + filemode = false + + # Our diff algorithm + [diff] + external = "/usr/local/bin/gnu-diff -u" + renames = true + + [branch "devel"] + remote = origin + merge = refs/heads/devel + + # Proxy settings + [core] + gitProxy="ssh" for "ssh://kernel.org/" + gitProxy=default-proxy ; for the rest + +Variables +~~~~~~~~~ + +Note that this list is non-comprehensive and not necessarily complete. +For command-specific variables, you will find a more detailed description +in the appropriate manual page. You will find a description of non-core +porcelain configuration variables in the respective porcelain documentation. + +core.fileMode:: + If false, the executable bit differences between the index and + the working copy are ignored; useful on broken filesystems like FAT. + See gitlink:git-update-index[1]. True by default. + +core.symlinks:: + If false, symbolic links are checked out as small plain files that + contain the link text. gitlink:git-update-index[1] and + gitlink:git-add[1] will not change the recorded type to regular + file. Useful on filesystems like FAT that do not support + symbolic links. True by default. + +core.gitProxy:: + A "proxy command" to execute (as 'command host port') instead + of establishing direct connection to the remote server when + using the git protocol for fetching. If the variable value is + in the "COMMAND for DOMAIN" format, the command is applied only + on hostnames ending with the specified domain string. This variable + may be set multiple times and is matched in the given order; + the first match wins. ++ +Can be overridden by the 'GIT_PROXY_COMMAND' environment variable +(which always applies universally, without the special "for" +handling). + +core.ignoreStat:: + The working copy files are assumed to stay unchanged until you + mark them otherwise manually - Git will not detect the file changes + by lstat() calls. This is useful on systems where those are very + slow, such as Microsoft Windows. See gitlink:git-update-index[1]. + False by default. + +core.preferSymlinkRefs:: + Instead of the default "symref" format for HEAD + and other symbolic reference files, use symbolic links. + This is sometimes needed to work with old scripts that + expect HEAD to be a symbolic link. + +core.bare:: + If true this repository is assumed to be 'bare' and has no + working directory associated with it. If this is the case a + number of commands that require a working directory will be + disabled, such as gitlink:git-add[1] or gitlink:git-merge[1]. ++ +This setting is automatically guessed by gitlink:git-clone[1] or +gitlink:git-init[1] when the repository was created. By default a +repository that ends in "/.git" is assumed to be not bare (bare = +false), while all other repositories are assumed to be bare (bare += true). + +core.logAllRefUpdates:: + 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 + version. + +core.sharedRepository:: + When 'group' (or 'true'), the repository is made shareable between + several users in a group (making sure all the files and objects are + 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[1]. False by default. + +core.warnAmbiguousRefs:: + If true, git will warn you if the ref name you passed it is ambiguous + and might match multiple refs in the .git/refs/ tree. True by default. + +core.compression:: + An integer -1..9, indicating the compression level for objects that + are not in a pack file. -1 is the zlib and git default. 0 means no + compression, and 1..9 are various speed/size tradeoffs, 9 being + slowest. + +core.legacyheaders:: + A boolean which + changes the format of loose objects so that they are more + efficient to pack and to send out of the repository over git + native protocol, since v1.4.2. However, loose objects + written in the new format cannot be read by git older than + that version; people fetching from your repository using + older versions of git over dumb transports (e.g. http) + will also be affected. ++ +To let git use the new loose object format, you have to +set core.legacyheaders to false. + +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 + "git last" is equivalent to "git cat-file commit HEAD". To avoid + confusion and troubles with script usage, aliases that + hide existing git commands are ignored. Arguments are split by + spaces, the usual shell quoting and escaping is supported. + quote pair and a backslash can be used to quote them. + + If the alias expansion is prefixed with an exclamation point, + it will be treated as a shell command. For example, defining + "alias.new = !gitk --all --not ORIG_HEAD", the invocation + "git new" is equivalent to running the shell command + "gitk --all --not ORIG_HEAD". + +apply.whitespace:: + Tells `git-apply` how to handle whitespaces, in the same way + as the '--whitespace' option. See gitlink:git-apply[1]. + +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). ++ +The value for these configuration variables is a list of colors (at most +two) and attributes (at most one), separated by spaces. The colors +accepted are `normal`, `black`, `red`, `green`, `yellow`, `blue`, +`magenta`, `cyan` and `white`; the attributes are `bold`, `dim`, `ul`, +`blink` and `reverse`. The first color given is the foreground; the +second is the background. The position of the attribute, if any, +doesn't matter. + +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. + +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), `new` (added lines), + `commit` (commit headers), or `whitespace` (highlighting dubious + whitespace). 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 + detection; equivalent to the git diff option '-l'. + +diff.renames:: + Tells git to detect renames. If set to any boolean value, it + will enable basic rename detection. If set to "copies" or + "copy", it will detect copies, as well. + +fetch.unpackLimit:: + If the number of objects fetched over the git native + transfer 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. + +format.headers:: + Additional email headers to include in a patch to be submitted + by mail. See gitlink:git-format-patch[1]. + +format.suffix:: + The default for format-patch is to output files with the suffix + `.patch`. Use this variable to change that suffix (make sure to + include the dot if you want it). + +gc.packrefs:: + `git gc` does not run `git pack-refs` in a bare repository by + default so that older dumb-transport clients can still fetch + from the repository. Setting this to `true` lets `git + gc` to run `git pack-refs`. Setting this to `false` tells + `git gc` never to run `git pack-refs`. The default setting is + `notbare`. Enable it only when you know you do not have to + support such clients. The default setting will change to `true` + at some stage, and setting this to `false` will continue to + prevent `git pack-refs` from being run from `git gc`. + +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]. + +gitcvs.logfile:: + Path to a log file where the cvs pserver interface well... logs + various stuff. See gitlink:git-cvsserver[1]. + +http.sslVerify:: + Whether to verify the SSL certificate when fetching or pushing + over HTTPS. Can be overridden by the 'GIT_SSL_NO_VERIFY' environment + variable. + +http.sslCert:: + File containing the SSL certificate when fetching or pushing + over HTTPS. Can be overridden by the 'GIT_SSL_CERT' environment + variable. + +http.sslKey:: + File containing the SSL private key when fetching or pushing + over HTTPS. Can be overridden by the 'GIT_SSL_KEY' environment + variable. + +http.sslCAInfo:: + File containing the certificates to verify the peer with when + fetching or pushing over HTTPS. Can be overridden by the + 'GIT_SSL_CAINFO' environment variable. + +http.sslCAPath:: + Path containing files with the CA certificates to verify the peer + with when fetching or pushing over HTTPS. Can be overridden + by the 'GIT_SSL_CAPATH' environment variable. + +http.maxRequests:: + How many HTTP requests to launch in parallel. Can be overridden + by the 'GIT_HTTP_MAX_REQUESTS' environment variable. Default is 5. + +http.lowSpeedLimit, http.lowSpeedTime:: + If the HTTP transfer speed is less than 'http.lowSpeedLimit' + for longer than 'http.lowSpeedTime' seconds, the transfer is aborted. + 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 + importing commits from emails or in the gitk graphical history + 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. + +merge.verbosity:: + Controls the amount of output shown by the recursive merge + strategy. Level 0 outputs nothing except a final error + message if conflicts were detected. Level 1 outputs only + conflicts, 2 outputs conflicts and file changes. Level 5 and + above outputs debugging information. The default is level 2. + +pack.window:: + The size of the window used by gitlink:git-pack-objects[1] when no + window size is given on the command line. Defaults to 10. + +pull.octopus:: + The default merge strategy to use when pulling multiple branches + at once. + +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]. + +remote.<name>.skipDefaultUpdate:: + If true, this remote will be skipped by default when updating + using the remote subcommand of gitlink:git-remote[1]. + +remote.<name>.receivepack:: + The default program to execute on the remote side when pushing. See + option \--exec of gitlink:git-push[1]. + +remote.<name>.uploadpack:: + The default program to execute on the remote side when fetching. See + option \--exec of gitlink:git-fetch-pack[1]. + +remote.<name>.tagopt:: + Setting this value to --no-tags disables automatic tag following when fetching + from remote <name> + +remotes.<group>:: + The list of remotes which are fetched by "git remote update + <group>". See gitlink:git-remote[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]. + +showbranch.default:: + The default set of branches for gitlink:git-show-branch[1]. + See gitlink:git-show-branch[1]. + +tar.umask:: + By default, gitlink:git-tar-tree[1] sets file and directories modes + to 0666 or 0777. While this is both useful and acceptable for projects + such as the Linux Kernel, it might be excessive for other projects. + With this variable, it becomes possible to tell + gitlink:git-tar-tree[1] to apply a specific umask to the modes above. + The special value "user" indicates that the user's current umask will + be used. This should be enough for most projects, as it will lead to + the same permissions as gitlink:git-checkout[1] would use. The default + value remains 0, which means world read-write. + +user.email:: + Your email address to be recorded in any newly created commits. + Can be overridden by the 'GIT_AUTHOR_EMAIL' and 'GIT_COMMITTER_EMAIL' + environment variables. See gitlink:git-commit-tree[1]. + +user.name:: + Your full name to be recorded in any newly created commits. + Can be overridden by the 'GIT_AUTHOR_NAME' and 'GIT_COMMITTER_NAME' + environment variables. See gitlink:git-commit-tree[1]. + +user.signingkey:: + If gitlink:git-tag[1] is not selecting the key you want it to + automatically when creating a signed tag, you can override the + default selection with this variable. This option is passed + unchanged to gpg's --local-user parameter, so you may specify a key + using any method that gpg supports. + +whatchanged.difftree:: + The default gitlink:git-diff-tree[1] arguments to be used + for gitlink:git-whatchanged[1]. + +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. + +transfer.unpackLimit:: + When `fetch.unpackLimit` or `receive.unpackLimit` are + not set, the value of this variable is used instead. + + diff --git a/Documentation/core-intro.txt b/Documentation/core-intro.txt new file mode 100644 index 0000000000..eea44d9d56 --- /dev/null +++ b/Documentation/core-intro.txt @@ -0,0 +1,592 @@ +//////////////////////////////////////////////////////////////// + + GIT - the stupid content tracker + +//////////////////////////////////////////////////////////////// + +"git" can mean anything, depending on your mood. + + - random three-letter combination that is pronounceable, and not + actually used by any common UNIX command. The fact that it is a + mispronunciation of "get" may or may not be relevant. + - stupid. contemptible and despicable. simple. Take your pick from the + dictionary of slang. + - "global information tracker": you're in a good mood, and it actually + works for you. Angels sing, and a light suddenly fills the room. + - "goddamn idiotic truckload of sh*t": when it breaks + +This is a (not so) stupid but extremely fast directory content manager. +It doesn't do a whole lot at its core, but what it 'does' do is track +directory contents efficiently. + +There are two object abstractions: the "object database", and the +"current directory cache" aka "index". + +The Object Database +~~~~~~~~~~~~~~~~~~~ +The object database is literally just a content-addressable collection +of objects. All objects are named by their content, which is +approximated by the SHA1 hash of the object itself. Objects may refer +to other objects (by referencing their SHA1 hash), and so you can +build up a hierarchy of objects. + +All objects have a statically determined "type" aka "tag", which is +determined at object creation time, and which identifies the format of +the object (i.e. how it is used, and how it can refer to other +objects). There are currently four different object types: "blob", +"tree", "commit" and "tag". + +A "blob" object cannot refer to any other object, and is, like the type +implies, a pure storage object containing some user data. It is used to +actually store the file data, i.e. a blob object is associated with some +particular version of some file. + +A "tree" object is an object that ties one or more "blob" objects into a +directory structure. In addition, a tree object can refer to other tree +objects, thus creating a directory hierarchy. + +A "commit" object ties such directory hierarchies together into +a DAG of revisions - each "commit" is associated with exactly one tree +(the directory hierarchy at the time of the commit). In addition, a +"commit" refers to one or more "parent" commit objects that describe the +history of how we arrived at that directory hierarchy. + +As a special case, a commit object with no parents is called the "root" +object, and is the point of an initial project commit. Each project +must have at least one root, and while you can tie several different +root objects together into one project by creating a commit object which +has two or more separate roots as its ultimate parents, that's probably +just going to confuse people. So aim for the notion of "one root object +per project", even if git itself does not enforce that. + +A "tag" object symbolically identifies and can be used to sign other +objects. It contains the identifier and type of another object, a +symbolic name (of course!) and, optionally, a signature. + +Regardless of object type, all objects share the following +characteristics: they are all deflated with zlib, and have a header +that not only specifies their type, but also provides size information +about the data in the object. It's worth noting that the SHA1 hash +that is used to name the object is the hash of the original data +plus this header, so `sha1sum` 'file' does not match the object name +for 'file'. +(Historical note: in the dawn of the age of git the hash +was the sha1 of the 'compressed' object.) + +As a result, the general consistency of an object can always be tested +independently of the contents or the type of the object: all objects can +be validated by verifying that (a) their hashes match the content of the +file and (b) the object successfully inflates to a stream of bytes that +forms a sequence of <ascii type without space> + <space> + <ascii decimal +size> + <byte\0> + <binary object data>. + +The structured objects can further have their structure and +connectivity to other objects verified. This is generally done with +the `git-fsck` program, which generates a full dependency graph +of all objects, and verifies their internal consistency (in addition +to just verifying their superficial consistency through the hash). + +The object types in some more detail: + +Blob Object +~~~~~~~~~~~ +A "blob" object is nothing but a binary blob of data, and doesn't +refer to anything else. There is no signature or any other +verification of the data, so while the object is consistent (it 'is' +indexed by its sha1 hash, so the data itself is certainly correct), it +has absolutely no other attributes. No name associations, no +permissions. It is purely a blob of data (i.e. normally "file +contents"). + +In particular, since the blob is entirely defined by its data, if two +files in a directory tree (or in multiple different versions of the +repository) have the same contents, they will share the same blob +object. The object is totally independent of its location in the +directory tree, and renaming a file does not change the object that +file is associated with in any way. + +A blob is typically created when gitlink:git-update-index[1] +(or gitlink:git-add[1]) is run, and its data can be accessed by +gitlink:git-cat-file[1]. + +Tree Object +~~~~~~~~~~~ +The next hierarchical object type is the "tree" object. A tree object +is a list of mode/name/blob data, sorted by name. Alternatively, the +mode data may specify a directory mode, in which case instead of +naming a blob, that name is associated with another TREE object. + +Like the "blob" object, a tree object is uniquely determined by the +set contents, and so two separate but identical trees will always +share the exact same object. This is true at all levels, i.e. it's +true for a "leaf" tree (which does not refer to any other trees, only +blobs) as well as for a whole subdirectory. + +For that reason a "tree" object is just a pure data abstraction: it +has no history, no signatures, no verification of validity, except +that since the contents are again protected by the hash itself, we can +trust that the tree is immutable and its contents never change. + +So you can trust the contents of a tree to be valid, the same way you +can trust the contents of a blob, but you don't know where those +contents 'came' from. + +Side note on trees: since a "tree" object is a sorted list of +"filename+content", you can create a diff between two trees without +actually having to unpack two trees. Just ignore all common parts, +and your diff will look right. In other words, you can effectively +(and efficiently) tell the difference between any two random trees by +O(n) where "n" is the size of the difference, rather than the size of +the tree. + +Side note 2 on trees: since the name of a "blob" depends entirely and +exclusively on its contents (i.e. there are no names or permissions +involved), you can see trivial renames or permission changes by +noticing that the blob stayed the same. However, renames with data +changes need a smarter "diff" implementation. + +A tree is created with gitlink:git-write-tree[1] and +its data can be accessed by gitlink:git-ls-tree[1]. +Two trees can be compared with gitlink:git-diff-tree[1]. + +Commit Object +~~~~~~~~~~~~~ +The "commit" object is an object that introduces the notion of +history into the picture. In contrast to the other objects, it +doesn't just describe the physical state of a tree, it describes how +we got there, and why. + +A "commit" is defined by the tree-object that it results in, the +parent commits (zero, one or more) that led up to that point, and a +comment on what happened. Again, a commit is not trusted per se: +the contents are well-defined and "safe" due to the cryptographically +strong signatures at all levels, but there is no reason to believe +that the tree is "good" or that the merge information makes sense. +The parents do not have to actually have any relationship with the +result, for example. + +Note on commits: unlike real SCM's, commits do not contain +rename information or file mode change information. All of that is +implicit in the trees involved (the result tree, and the result trees +of the parents), and describing that makes no sense in this idiotic +file manager. + +A commit is created with gitlink:git-commit-tree[1] and +its data can be accessed by gitlink:git-cat-file[1]. + +Trust +~~~~~ +An aside on the notion of "trust". Trust is really outside the scope +of "git", but it's worth noting a few things. First off, since +everything is hashed with SHA1, you 'can' trust that an object is +intact and has not been messed with by external sources. So the name +of an object uniquely identifies a known state - just not a state that +you may want to trust. + +Furthermore, since the SHA1 signature of a commit refers to the +SHA1 signatures of the tree it is associated with and the signatures +of the parent, a single named commit specifies uniquely a whole set +of history, with full contents. You can't later fake any step of the +way once you have the name of a commit. + +So to introduce some real trust in the system, the only thing you need +to do is to digitally sign just 'one' special note, which includes the +name of a top-level commit. Your digital signature shows others +that you trust that commit, and the immutability of the history of +commits tells others that they can trust the whole history. + +In other words, you can easily validate a whole archive by just +sending out a single email that tells the people the name (SHA1 hash) +of the top commit, and digitally sign that email using something +like GPG/PGP. + +To assist in this, git also provides the tag object... + +Tag Object +~~~~~~~~~~ +Git provides the "tag" object to simplify creating, managing and +exchanging symbolic and signed tokens. The "tag" object at its +simplest simply symbolically identifies another object by containing +the sha1, type and symbolic name. + +However it can optionally contain additional signature information +(which git doesn't care about as long as there's less than 8k of +it). This can then be verified externally to git. + +Note that despite the tag features, "git" itself only handles content +integrity; the trust framework (and signature provision and +verification) has to come from outside. + +A tag is created with gitlink:git-mktag[1], +its data can be accessed by gitlink:git-cat-file[1], +and the signature can be verified by +gitlink:git-verify-tag[1]. + + +The "index" aka "Current Directory Cache" +----------------------------------------- +The index is a simple binary file, which contains an efficient +representation of a virtual directory content at some random time. It +does so by a simple array that associates a set of names, dates, +permissions and content (aka "blob") objects together. The cache is +always kept ordered by name, and names are unique (with a few very +specific rules) at any point in time, but the cache has no long-term +meaning, and can be partially updated at any time. + +In particular, the index certainly does not need to be consistent with +the current directory contents (in fact, most operations will depend on +different ways to make the index 'not' be consistent with the directory +hierarchy), but it has three very important attributes: + +'(a) it can re-generate the full state it caches (not just the +directory structure: it contains pointers to the "blob" objects so +that it can regenerate the data too)' + +As a special case, there is a clear and unambiguous one-way mapping +from a current directory cache to a "tree object", which can be +efficiently created from just the current directory cache without +actually looking at any other data. So a directory cache at any one +time uniquely specifies one and only one "tree" object (but has +additional data to make it easy to match up that tree object with what +has happened in the directory) + +'(b) it has efficient methods for finding inconsistencies between that +cached state ("tree object waiting to be instantiated") and the +current state.' + +'(c) it can additionally efficiently represent information about merge +conflicts between different tree objects, allowing each pathname to be +associated with sufficient information about the trees involved that +you can create a three-way merge between them.' + +Those are the three ONLY things that the directory cache does. It's a +cache, and the normal operation is to re-generate it completely from a +known tree object, or update/compare it with a live tree that is being +developed. If you blow the directory cache away entirely, you generally +haven't lost any information as long as you have the name of the tree +that it described. + +At the same time, the index is at the same time also the +staging area for creating new trees, and creating a new tree always +involves a controlled modification of the index file. In particular, +the index file can have the representation of an intermediate tree that +has not yet been instantiated. So the index can be thought of as a +write-back cache, which can contain dirty information that has not yet +been written back to the backing store. + + + +The Workflow +------------ +Generally, all "git" operations work on the index file. Some operations +work *purely* on the index file (showing the current state of the +index), but most operations move data to and from the index file. Either +from the database or from the working directory. Thus there are four +main combinations: + +1) working directory -> index +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You update the index with information from the working directory with +the gitlink:git-update-index[1] command. You +generally update the index information by just specifying the filename +you want to update, like so: + + git-update-index filename + +but to avoid common mistakes with filename globbing etc, the command +will not normally add totally new entries or remove old entries, +i.e. it will normally just update existing cache entries. + +To tell git that yes, you really do realize that certain files no +longer exist, or that new files should be added, you +should use the `--remove` and `--add` flags respectively. + +NOTE! A `--remove` flag does 'not' mean that subsequent filenames will +necessarily be removed: if the files still exist in your directory +structure, the index will be updated with their new status, not +removed. The only thing `--remove` means is that update-cache will be +considering a removed file to be a valid thing, and if the file really +does not exist any more, it will update the index accordingly. + +As a special case, you can also do `git-update-index --refresh`, which +will refresh the "stat" information of each index to match the current +stat information. It will 'not' update the object status itself, and +it will only update the fields that are used to quickly test whether +an object still matches its old backing store object. + +2) index -> object database +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You write your current index file to a "tree" object with the program + + git-write-tree + +that doesn't come with any options - it will just write out the +current index into the set of tree objects that describe that state, +and it will return the name of the resulting top-level tree. You can +use that tree to re-generate the index at any time by going in the +other direction: + +3) object database -> index +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You read a "tree" file from the object database, and use that to +populate (and overwrite - don't do this if your index contains any +unsaved state that you might want to restore later!) your current +index. Normal operation is just + + git-read-tree <sha1 of tree> + +and your index file will now be equivalent to the tree that you saved +earlier. However, that is only your 'index' file: your working +directory contents have not been modified. + +4) index -> working directory +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You update your working directory from the index by "checking out" +files. This is not a very common operation, since normally you'd just +keep your files updated, and rather than write to your working +directory, you'd tell the index files about the changes in your +working directory (i.e. `git-update-index`). + +However, if you decide to jump to a new version, or check out somebody +else's version, or just restore a previous tree, you'd populate your +index file with read-tree, and then you need to check out the result +with + + git-checkout-index filename + +or, if you want to check out all of the index, use `-a`. + +NOTE! git-checkout-index normally refuses to overwrite old files, so +if you have an old version of the tree already checked out, you will +need to use the "-f" flag ('before' the "-a" flag or the filename) to +'force' the checkout. + + +Finally, there are a few odds and ends which are not purely moving +from one representation to the other: + +5) Tying it all together +~~~~~~~~~~~~~~~~~~~~~~~~ +To commit a tree you have instantiated with "git-write-tree", you'd +create a "commit" object that refers to that tree and the history +behind it - most notably the "parent" commits that preceded it in +history. + +Normally a "commit" has one parent: the previous state of the tree +before a certain change was made. However, sometimes it can have two +or more parent commits, in which case we call it a "merge", due to the +fact that such a commit brings together ("merges") two or more +previous states represented by other commits. + +In other words, while a "tree" represents a particular directory state +of a working directory, a "commit" represents that state in "time", +and explains how we got there. + +You create a commit object by giving it the tree that describes the +state at the time of the commit, and a list of parents: + + git-commit-tree <tree> -p <parent> [-p <parent2> ..] + +and then giving the reason for the commit on stdin (either through +redirection from a pipe or file, or by just typing it at the tty). + +git-commit-tree will return the name of the object that represents +that commit, and you should save it away for later use. Normally, +you'd commit a new `HEAD` state, and while git doesn't care where you +save the note about that state, in practice we tend to just write the +result to the file pointed at by `.git/HEAD`, so that we can always see +what the last committed state was. + +Here is an ASCII art by Jon Loeliger that illustrates how +various pieces fit together. + +------------ + + commit-tree + commit obj + +----+ + | | + | | + V V + +-----------+ + | Object DB | + | Backing | + | Store | + +-----------+ + ^ + write-tree | | + tree obj | | + | | read-tree + | | tree obj + V + +-----------+ + | Index | + | "cache" | + +-----------+ + update-index ^ + blob obj | | + | | + checkout-index -u | | checkout-index + stat | | blob obj + V + +-----------+ + | Working | + | Directory | + +-----------+ + +------------ + + +6) Examining the data +~~~~~~~~~~~~~~~~~~~~~ + +You can examine the data represented in the object database and the +index with various helper tools. For every object, you can use +gitlink:git-cat-file[1] to examine details about the +object: + + git-cat-file -t <objectname> + +shows the type of the object, and once you have the type (which is +usually implicit in where you find the object), you can use + + git-cat-file blob|tree|commit|tag <objectname> + +to show its contents. NOTE! Trees have binary content, and as a result +there is a special helper for showing that content, called +`git-ls-tree`, which turns the binary content into a more easily +readable form. + +It's especially instructive to look at "commit" objects, since those +tend to be small and fairly self-explanatory. In particular, if you +follow the convention of having the top commit name in `.git/HEAD`, +you can do + + git-cat-file commit HEAD + +to see what the top commit was. + +7) Merging multiple trees +~~~~~~~~~~~~~~~~~~~~~~~~~ + +Git helps you do a three-way merge, which you can expand to n-way by +repeating the merge procedure arbitrary times until you finally +"commit" the state. The normal situation is that you'd only do one +three-way merge (two parents), and commit it, but if you like to, you +can do multiple parents in one go. + +To do a three-way merge, you need the two sets of "commit" objects +that you want to merge, use those to find the closest common parent (a +third "commit" object), and then use those commit objects to find the +state of the directory ("tree" object) at these points. + +To get the "base" for the merge, you first look up the common parent +of two commits with + + git-merge-base <commit1> <commit2> + +which will return you the commit they are both based on. You should +now look up the "tree" objects of those commits, which you can easily +do with (for example) + + git-cat-file commit <commitname> | head -1 + +since the tree object information is always the first line in a commit +object. + +Once you know the three trees you are going to merge (the one +"original" tree, aka the common case, and the two "result" trees, aka +the branches you want to merge), you do a "merge" read into the +index. This will complain if it has to throw away your old index contents, so you should +make sure that you've committed those - in fact you would normally +always do a merge against your last commit (which should thus match +what you have in your current index anyway). + +To do the merge, do + + git-read-tree -m -u <origtree> <yourtree> <targettree> + +which will do all trivial merge operations for you directly in the +index file, and you can just write the result out with +`git-write-tree`. + +Historical note. We did not have `-u` facility when this +section was first written, so we used to warn that +the merge is done in the index file, not in your +working tree, and your working tree will not match your +index after this step. +This is no longer true. The above command, thanks to `-u` +option, updates your working tree with the merge results for +paths that have been trivially merged. + + +8) Merging multiple trees, continued +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Sadly, many merges aren't trivial. If there are files that have +been added.moved or removed, or if both branches have modified the +same file, you will be left with an index tree that contains "merge +entries" in it. Such an index tree can 'NOT' be written out to a tree +object, and you will have to resolve any such merge clashes using +other tools before you can write out the result. + +You can examine such index state with `git-ls-files --unmerged` +command. An example: + +------------------------------------------------ +$ git-read-tree -m $orig HEAD $target +$ git-ls-files --unmerged +100644 263414f423d0e4d70dae8fe53fa34614ff3e2860 1 hello.c +100644 06fa6a24256dc7e560efa5687fa84b51f0263c3a 2 hello.c +100644 cc44c73eb783565da5831b4d820c962954019b69 3 hello.c +------------------------------------------------ + +Each line of the `git-ls-files --unmerged` output begins with +the blob mode bits, blob SHA1, 'stage number', and the +filename. The 'stage number' is git's way to say which tree it +came from: stage 1 corresponds to `$orig` tree, stage 2 `HEAD` +tree, and stage3 `$target` tree. + +Earlier we said that trivial merges are done inside +`git-read-tree -m`. For example, if the file did not change +from `$orig` to `HEAD` nor `$target`, or if the file changed +from `$orig` to `HEAD` and `$orig` to `$target` the same way, +obviously the final outcome is what is in `HEAD`. What the +above example shows is that file `hello.c` was changed from +`$orig` to `HEAD` and `$orig` to `$target` in a different way. +You could resolve this by running your favorite 3-way merge +program, e.g. `diff3` or `merge`, on the blob objects from +these three stages yourself, like this: + +------------------------------------------------ +$ git-cat-file blob 263414f... >hello.c~1 +$ git-cat-file blob 06fa6a2... >hello.c~2 +$ git-cat-file blob cc44c73... >hello.c~3 +$ merge hello.c~2 hello.c~1 hello.c~3 +------------------------------------------------ + +This would leave the merge result in `hello.c~2` file, along +with conflict markers if there are conflicts. After verifying +the merge result makes sense, you can tell git what the final +merge result for this file is by: + + mv -f hello.c~2 hello.c + git-update-index hello.c + +When a path is in unmerged state, running `git-update-index` for +that path tells git to mark the path resolved. + +The above is the description of a git merge at the lowest level, +to help you understand what conceptually happens under the hood. +In practice, nobody, not even git itself, uses three `git-cat-file` +for this. There is `git-merge-index` program that extracts the +stages to temporary files and calls a "merge" script on it: + + git-merge-index git-merge-one-file hello.c + +and that is what higher level `git merge -s resolve` is implemented +with. diff --git a/Documentation/core-tutorial.txt b/Documentation/core-tutorial.txt new file mode 100644 index 0000000000..97cdb90cb4 --- /dev/null +++ b/Documentation/core-tutorial.txt @@ -0,0 +1,1691 @@ +A git core tutorial for developers +================================== + +Introduction +------------ + +This is trying to be a short tutorial on setting up and using a git +repository, mainly because being hands-on and using explicit examples is +often the best way of explaining what is going on. + +In normal life, most people wouldn't use the "core" git programs +directly, but rather script around them to make them more palatable. +Understanding the core git stuff may help some people get those scripts +done, though, and it may also be instructive in helping people +understand what it is that the higher-level helper scripts are actually +doing. + +The core git is often called "plumbing", with the prettier user +interfaces on top of it called "porcelain". You may not want to use the +plumbing directly very often, but it can be good to know what the +plumbing does for when the porcelain isn't flushing. + +The material presented here often goes deep describing how things +work internally. If you are mostly interested in using git as a +SCM, you can skip them during your first pass. + +[NOTE] +And those "too deep" descriptions are often marked as Note. + +[NOTE] +If you are already familiar with another version control system, +like CVS, you may want to take a look at +link:everyday.html[Everyday GIT in 20 commands or so] first +before reading this. + + +Creating a git repository +------------------------- + +Creating a new git repository couldn't be easier: all git repositories start +out empty, and the only thing you need to do is find yourself a +subdirectory that you want to use as a working tree - either an empty +one for a totally new project, or an existing working tree that you want +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`: + +------------------------------------------------ +$ mkdir git-tutorial +$ cd git-tutorial +$ git-init +------------------------------------------------ + +to which git will reply + +---------------- +Initialized empty Git repository in .git/ +---------------- + +which is just git's way of saying that you haven't been doing anything +strange, and that it will have created a local `.git` directory setup for +your new project. You will now have a `.git` directory, and you can +inspect that with `ls`. For your new empty project, it should show you +three entries, among other things: + + - a file called `HEAD`, that has `ref: refs/heads/master` in it. + This is similar to a symbolic link and points at + `refs/heads/master` relative to the `HEAD` file. ++ +Don't worry about the fact that the file that the `HEAD` link points to +doesn't even exist yet -- you haven't created the commit that will +start your `HEAD` development branch yet. + + - a subdirectory called `objects`, which will contain all the + objects of your project. You should never have any real reason to + look at the objects directly, but you might want to know that these + objects are what contains all the real 'data' in your repository. + + - a subdirectory called `refs`, which contains references to objects. + +In particular, the `refs` subdirectory will contain two other +subdirectories, named `heads` and `tags` respectively. They do +exactly what their names imply: they contain references to any number +of different 'heads' of development (aka 'branches'), and to any +'tags' that you have created to name specific versions in your +repository. + +One note: the special `master` head is the default branch, which is +why the `.git/HEAD` file was created points to it even if it +doesn't yet exist. Basically, the `HEAD` link is supposed to always +point to the branch you are working on right now, and you always +start out expecting to work on the `master` branch. + +However, this is only a convention, and you can name your branches +anything you want, and don't have to ever even 'have' a `master` +branch. A number of the git tools will assume that `.git/HEAD` is +valid, though. + +[NOTE] +An 'object' is identified by its 160-bit SHA1 hash, aka 'object name', +and a reference to an object is always the 40-byte hex +representation of that SHA1 name. The files in the `refs` +subdirectory are expected to contain these hex references +(usually with a final `\'\n\'` at the end), and you should thus +expect to see a number of 41-byte files containing these +references in these `refs` subdirectories when you actually start +populating your tree. + +[NOTE] +An advanced user may want to take a look at the +link:repository-layout.html[repository layout] document +after finishing this tutorial. + +You have now created your first git repository. Of course, since it's +empty, that's not very useful, so let's start populating it with data. + + +Populating a git repository +--------------------------- + +We'll keep this simple and stupid, so we'll start off with populating a +few trivial files just to get a feel for it. + +Start off with just creating any random files that you want to maintain +in your git repository. We'll start off with a few bad examples, just to +get a feel for how this works: + +------------------------------------------------ +$ echo "Hello World" >hello +$ echo "Silly example" >example +------------------------------------------------ + +you have now created two files in your working tree (aka 'working directory'), +but to actually check in your hard work, you will have to go through two steps: + + - fill in the 'index' file (aka 'cache') with the information about your + working tree state. + + - commit that index file as an object. + +The first step is trivial: when you want to tell git about any changes +to your working tree, you use the `git-update-index` program. That +program normally just takes a list of filenames you want to update, but +to avoid trivial mistakes, it refuses to add new entries to the index +(or remove existing ones) unless you explicitly tell it that you're +adding a new entry with the `\--add` flag (or removing an entry with the +`\--remove`) flag. + +So to populate the index with the two files you just created, you can do + +------------------------------------------------ +$ git-update-index --add hello example +------------------------------------------------ + +and you have now told git to track those two files. + +In fact, as you did that, if you now look into your object directory, +you'll notice that git will have added two new objects to the object +database. If you did exactly the steps above, you should now be able to do + + +---------------- +$ ls .git/objects/??/* +---------------- + +and see two files: + +---------------- +.git/objects/55/7db03de997c86a4a028e1ebd3a1ceb225be238 +.git/objects/f2/4c74a2e500f5ee1332c86b94199f52b1d1d962 +---------------- + +which correspond with the objects with names of `557db...` and +`f24c7...` respectively. + +If you want to, you can use `git-cat-file` to look at those objects, but +you'll have to use the object name, not the filename of the object: + +---------------- +$ git-cat-file -t 557db03de997c86a4a028e1ebd3a1ceb225be238 +---------------- + +where the `-t` tells `git-cat-file` to tell you what the "type" of the +object is. git will tell you that you have a "blob" object (i.e., just a +regular file), and you can see the contents with + +---------------- +$ git-cat-file "blob" 557db03 +---------------- + +which will print out "Hello World". The object `557db03` is nothing +more than the contents of your file `hello`. + +[NOTE] +Don't confuse that object with the file `hello` itself. The +object is literally just those specific *contents* of the file, and +however much you later change the contents in file `hello`, the object +we just looked at will never change. Objects are immutable. + +[NOTE] +The second example demonstrates that you can +abbreviate the object name to only the first several +hexadecimal digits in most places. + +Anyway, as we mentioned previously, you normally never actually take a +look at the objects themselves, and typing long 40-character hex +names is not something you'd normally want to do. The above digression +was just to show that `git-update-index` did something magical, and +actually saved away the contents of your files into the git object +database. + +Updating the index did something else too: it created a `.git/index` +file. This is the index that describes your current working tree, and +something you should be very aware of. Again, you normally never worry +about the index file itself, but you should be aware of the fact that +you have not actually really "checked in" your files into git so far, +you've only *told* git about them. + +However, since git knows about them, you can now start using some of the +most basic git commands to manipulate the files or look at their status. + +In particular, let's not even check in the two files into git yet, we'll +start off by adding another line to `hello` first: + +------------------------------------------------ +$ echo "It's a new day for git" >>hello +------------------------------------------------ + +and you can now, since you told git about the previous state of `hello`, ask +git what has changed in the tree compared to your old index, using the +`git-diff-files` command: + +------------ +$ git-diff-files +------------ + +Oops. That wasn't very readable. It just spit out its own internal +version of a `diff`, but that internal version really just tells you +that it has noticed that "hello" has been modified, and that the old object +contents it had have been replaced with something else. + +To make it readable, we can tell git-diff-files to output the +differences as a patch, using the `-p` flag: + +------------ +$ git-diff-files -p +diff --git a/hello b/hello +index 557db03..263414f 100644 +--- a/hello ++++ b/hello +@@ -1 +1,2 @@ + Hello World ++It's a new day for git +---- + +i.e. the diff of the change we caused by adding another line to `hello`. + +In other words, `git-diff-files` always shows us the difference between +what is recorded in the index, and what is currently in the working +tree. That's very useful. + +A common shorthand for `git-diff-files -p` is to just write `git +diff`, which will do the same thing. + +------------ +$ git diff +diff --git a/hello b/hello +index 557db03..263414f 100644 +--- a/hello ++++ b/hello +@@ -1 +1,2 @@ + Hello World ++It's a new day for git +------------ + + +Committing git state +-------------------- + +Now, we want to go to the next stage in git, which is to take the files +that git knows about in the index, and commit them as a real tree. We do +that in two phases: creating a 'tree' object, and committing that 'tree' +object as a 'commit' object together with an explanation of what the +tree was all about, along with information of how we came to that state. + +Creating a tree object is trivial, and is done with `git-write-tree`. +There are no options or other input: git-write-tree will take the +current index state, and write an object that describes that whole +index. In other words, we're now tying together all the different +filenames with their contents (and their permissions), and we're +creating the equivalent of a git "directory" object: + +------------------------------------------------ +$ git-write-tree +------------------------------------------------ + +and this will just output the name of the resulting tree, in this case +(if you have done exactly as I've described) it should be + +---------------- +8988da15d077d4829fc51d8544c097def6644dbb +---------------- + +which is another incomprehensible object name. Again, if you want to, +you can use `git-cat-file -t 8988d\...` to see that this time the object +is not a "blob" object, but a "tree" object (you can also use +`git-cat-file` to actually output the raw object contents, but you'll see +mainly a binary mess, so that's less interesting). + +However -- normally you'd never use `git-write-tree` on its own, because +normally you always commit a tree into a commit object using the +`git-commit-tree` command. In fact, it's easier to not actually use +`git-write-tree` on its own at all, but to just pass its result in as an +argument to `git-commit-tree`. + +`git-commit-tree` normally takes several arguments -- it wants to know +what the 'parent' of a commit was, but since this is the first commit +ever in this new repository, and it has no parents, we only need to pass in +the object name of the tree. However, `git-commit-tree` +also wants to get a commit message +on its standard input, and it will write out the resulting object name for the +commit to its standard output. + +And this is where we create the `.git/refs/heads/master` file +which is pointed at by `HEAD`. This file is supposed to contain +the reference to the top-of-tree of the master branch, and since +that's exactly what `git-commit-tree` spits out, we can do this +all with a sequence of simple shell commands: + +------------------------------------------------ +$ tree=$(git-write-tree) +$ commit=$(echo 'Initial commit' | git-commit-tree $tree) +$ git-update-ref HEAD $commit +------------------------------------------------ + +In this case this creates a totally new commit that is not related to +anything else. Normally you do this only *once* for a project ever, and +all later commits will be parented on top of an earlier commit. + +Again, normally you'd never actually do this by hand. There is a +helpful script called `git commit` that will do all of this for you. So +you could have just written `git commit` +instead, and it would have done the above magic scripting for you. + + +Making a change +--------------- + +Remember how we did the `git-update-index` on file `hello` and then we +changed `hello` afterward, and could compare the new state of `hello` with the +state we saved in the index file? + +Further, remember how I said that `git-write-tree` writes the contents +of the *index* file to the tree, and thus what we just committed was in +fact the *original* contents of the file `hello`, not the new ones. We did +that on purpose, to show the difference between the index state, and the +state in the working tree, and how they don't have to match, even +when we commit things. + +As before, if we do `git-diff-files -p` in our git-tutorial project, +we'll still see the same difference we saw last time: the index file +hasn't changed by the act of committing anything. However, now that we +have committed something, we can also learn to use a new command: +`git-diff-index`. + +Unlike `git-diff-files`, which showed the difference between the index +file and the working tree, `git-diff-index` shows the differences +between a committed *tree* and either the index file or the working +tree. In other words, `git-diff-index` wants a tree to be diffed +against, and before we did the commit, we couldn't do that, because we +didn't have anything to diff against. + +But now we can do + +---------------- +$ git-diff-index -p HEAD +---------------- + +(where `-p` has the same meaning as it did in `git-diff-files`), and it +will show us the same difference, but for a totally different reason. +Now we're comparing the working tree not against the index file, +but against the tree we just wrote. It just so happens that those two +are obviously the same, so we get the same result. + +Again, because this is a common operation, you can also just shorthand +it with + +---------------- +$ git diff HEAD +---------------- + +which ends up doing the above for you. + +In other words, `git-diff-index` normally compares a tree against the +working tree, but when given the `\--cached` flag, it is told to +instead compare against just the index cache contents, and ignore the +current working tree state entirely. Since we just wrote the index +file to HEAD, doing `git-diff-index \--cached -p HEAD` should thus return +an empty set of differences, and that's exactly what it does. + +[NOTE] +================ +`git-diff-index` really always uses the index for its +comparisons, and saying that it compares a tree against the working +tree is thus not strictly accurate. In particular, the list of +files to compare (the "meta-data") *always* comes from the index file, +regardless of whether the `\--cached` flag is used or not. The `\--cached` +flag really only determines whether the file *contents* to be compared +come from the working tree or not. + +This is not hard to understand, as soon as you realize that git simply +never knows (or cares) about files that it is not told about +explicitly. git will never go *looking* for files to compare, it +expects you to tell it what the files are, and that's what the index +is there for. +================ + +However, our next step is to commit the *change* we did, and again, to +understand what's going on, keep in mind the difference between "working +tree contents", "index file" and "committed tree". We have changes +in the working tree that we want to commit, and we always have to +work through the index file, so the first thing we need to do is to +update the index cache: + +------------------------------------------------ +$ git-update-index hello +------------------------------------------------ + +(note how we didn't need the `\--add` flag this time, since git knew +about the file already). + +Note what happens to the different `git-diff-\*` versions here. After +we've updated `hello` in the index, `git-diff-files -p` now shows no +differences, but `git-diff-index -p HEAD` still *does* show that the +current state is different from the state we committed. In fact, now +`git-diff-index` shows the same difference whether we use the `--cached` +flag or not, since now the index is coherent with the working tree. + +Now, since we've updated `hello` in the index, we can commit the new +version. We could do it by writing the tree by hand again, and +committing the tree (this time we'd have to use the `-p HEAD` flag to +tell commit that the HEAD was the *parent* of the new commit, and that +this wasn't an initial commit any more), but you've done that once +already, so let's just use the helpful script this time: + +------------------------------------------------ +$ git commit +------------------------------------------------ + +which starts an editor for you to write the commit message and tells you +a bit about what you have done. + +Write whatever message you want, and all the lines that start with '#' +will be pruned out, and the rest will be used as the commit message for +the change. If you decide you don't want to commit anything after all at +this point (you can continue to edit things and update the index), you +can just leave an empty message. Otherwise `git commit` will commit +the change for you. + +You've now made your first real git commit. And if you're interested in +looking at what `git commit` really does, feel free to investigate: +it's a few very simple shell scripts to generate the helpful (?) commit +message headers, and a few one-liners that actually do the +commit itself (`git-commit`). + + +Inspecting Changes +------------------ + +While creating changes is useful, it's even more useful if you can tell +later what changed. The most useful command for this is another of the +`diff` family, namely `git-diff-tree`. + +`git-diff-tree` can be given two arbitrary trees, and it will tell you the +differences between them. Perhaps even more commonly, though, you can +give it just a single commit object, and it will figure out the parent +of that commit itself, and show the difference directly. Thus, to get +the same diff that we've already seen several times, we can now do + +---------------- +$ git-diff-tree -p HEAD +---------------- + +(again, `-p` means to show the difference as a human-readable patch), +and it will show what the last commit (in `HEAD`) actually changed. + +[NOTE] +============ +Here is an ASCII art by Jon Loeliger that illustrates how +various diff-\* commands compare things. + + diff-tree + +----+ + | | + | | + V V + +-----------+ + | Object DB | + | Backing | + | Store | + +-----------+ + ^ ^ + | | + | | diff-index --cached + | | + diff-index | V + | +-----------+ + | | Index | + | | "cache" | + | +-----------+ + | ^ + | | + | | diff-files + | | + V V + +-----------+ + | Working | + | Directory | + +-----------+ +============ + +More interestingly, you can also give `git-diff-tree` the `--pretty` flag, +which tells it to also show the commit message and author and date of the +commit, and you can tell it to show a whole series of diffs. +Alternatively, you can tell it to be "silent", and not show the diffs at +all, but just show the actual commit message. + +In fact, together with the `git-rev-list` program (which generates a +list of revisions), `git-diff-tree` ends up being a veritable fount of +changes. A trivial (but very useful) script called `git-whatchanged` is +included with git which does exactly this, and shows a log of recent +activities. + +To see the whole history of our pitiful little git-tutorial project, you +can do + +---------------- +$ git log +---------------- + +which shows just the log messages, or if we want to see the log together +with the associated patches use the more complex (and much more +powerful) + +---------------- +$ git-whatchanged -p --root +---------------- + +and you will see exactly what has changed in the repository over its +short history. + +[NOTE] +The `\--root` flag is a flag to `git-diff-tree` to tell it to +show the initial aka 'root' commit too. Normally you'd probably not +want to see the initial import diff, but since the tutorial project +was started from scratch and is so small, we use it to make the result +a bit more interesting. + +With that, you should now be having some inkling of what git does, and +can explore on your own. + +[NOTE] +Most likely, you are not directly using the core +git Plumbing commands, but using Porcelain like Cogito on top +of it. Cogito works a bit differently and you usually do not +have to run `git-update-index` yourself for changed files (you +do tell underlying git about additions and removals via +`cg-add` and `cg-rm` commands). Just before you make a commit +with `cg-commit`, Cogito figures out which files you modified, +and runs `git-update-index` on them for you. + + +Tagging a version +----------------- + +In git, there are two kinds of tags, a "light" one, and an "annotated tag". + +A "light" tag is technically nothing more than a branch, except we put +it in the `.git/refs/tags/` subdirectory instead of calling it a `head`. +So the simplest form of tag involves nothing more than + +------------------------------------------------ +$ git tag my-first-tag +------------------------------------------------ + +which just writes the current `HEAD` into the `.git/refs/tags/my-first-tag` +file, after which point you can then use this symbolic name for that +particular state. You can, for example, do + +---------------- +$ git diff my-first-tag +---------------- + +to diff your current state against that tag (which at this point will +obviously be an empty diff, but if you continue to develop and commit +stuff, you can use your tag as an "anchor-point" to see what has changed +since you tagged it. + +An "annotated tag" is actually a real git object, and contains not only a +pointer to the state you want to tag, but also a small tag name and +message, along with optionally a PGP signature that says that yes, +you really did +that tag. You create these annotated tags with either the `-a` or +`-s` flag to `git tag`: + +---------------- +$ git tag -s <tagname> +---------------- + +which will sign the current `HEAD` (but you can also give it another +argument that specifies the thing to tag, i.e., you could have tagged the +current `mybranch` point by using `git tag <tagname> mybranch`). + +You normally only do signed tags for major releases or things +like that, while the light-weight tags are useful for any marking you +want to do -- any time you decide that you want to remember a certain +point, just create a private tag for it, and you have a nice symbolic +name for the state at that point. + + +Copying repositories +-------------------- + +git repositories are normally totally self-sufficient and relocatable. +Unlike CVS, for example, there is no separate notion of +"repository" and "working tree". A git repository normally *is* the +working tree, with the local git information hidden in the `.git` +subdirectory. There is nothing else. What you see is what you got. + +[NOTE] +You can tell git to split the git internal information from +the directory that it tracks, but we'll ignore that for now: it's not +how normal projects work, and it's really only meant for special uses. +So the mental model of "the git information is always tied directly to +the working tree that it describes" may not be technically 100% +accurate, but it's a good model for all normal use. + +This has two implications: + + - if you grow bored with the tutorial repository you created (or you've + made a mistake and want to start all over), you can just do simple ++ +---------------- +$ rm -rf git-tutorial +---------------- ++ +and it will be gone. There's no external repository, and there's no +history outside the project you created. + + - if you want to move or duplicate a git repository, you can do so. There + is `git clone` command, but if all you want to do is just to + create a copy of your repository (with all the full history that + went along with it), you can do so with a regular + `cp -a git-tutorial new-git-tutorial`. ++ +Note that when you've moved or copied a git repository, your git index +file (which caches various information, notably some of the "stat" +information for the files involved) will likely need to be refreshed. +So after you do a `cp -a` to create a new copy, you'll want to do ++ +---------------- +$ git-update-index --refresh +---------------- ++ +in the new repository to make sure that the index file is up-to-date. + +Note that the second point is true even across machines. You can +duplicate a remote git repository with *any* regular copy mechanism, be it +`scp`, `rsync` or `wget`. + +When copying a remote repository, you'll want to at a minimum update the +index cache when you do this, and especially with other peoples' +repositories you often want to make sure that the index cache is in some +known state (you don't know *what* they've done and not yet checked in), +so usually you'll precede the `git-update-index` with a + +---------------- +$ git-read-tree --reset HEAD +$ git-update-index --refresh +---------------- + +which will force a total index re-build from the tree pointed to by `HEAD`. +It resets the index contents to `HEAD`, and then the `git-update-index` +makes sure to match up all index entries with the checked-out files. +If the original repository had uncommitted changes in its +working tree, `git-update-index --refresh` notices them and +tells you they need to be updated. + +The above can also be written as simply + +---------------- +$ git reset +---------------- + +and in fact a lot of the common git command combinations can be scripted +with the `git xyz` interfaces. You can learn things by just looking +at what the various git scripts do. For example, `git reset` is the +above two lines implemented in `git-reset`, but some things like +`git status` and `git commit` are slightly more complex scripts around +the basic git commands. + +Many (most?) public remote repositories will not contain any of +the checked out files or even an index file, and will *only* contain the +actual core git files. Such a repository usually doesn't even have the +`.git` subdirectory, but has all the git files directly in the +repository. + +To create your own local live copy of such a "raw" git repository, you'd +first create your own subdirectory for the project, and then copy the +raw repository contents into the `.git` directory. For example, to +create your own copy of the git repository, you'd do the following + +---------------- +$ mkdir my-git +$ cd my-git +$ rsync -rL rsync://rsync.kernel.org/pub/scm/git/git.git/ .git +---------------- + +followed by + +---------------- +$ git-read-tree HEAD +---------------- + +to populate the index. However, now you have populated the index, and +you have all the git internal files, but you will notice that you don't +actually have any of the working tree files to work on. To get +those, you'd check them out with + +---------------- +$ git-checkout-index -u -a +---------------- + +where the `-u` flag means that you want the checkout to keep the index +up-to-date (so that you don't have to refresh it afterward), and the +`-a` flag means "check out all files" (if you have a stale copy or an +older version of a checked out tree you may also need to add the `-f` +flag first, to tell git-checkout-index to *force* overwriting of any old +files). + +Again, this can all be simplified with + +---------------- +$ git clone rsync://rsync.kernel.org/pub/scm/git/git.git/ my-git +$ cd my-git +$ git checkout +---------------- + +which will end up doing all of the above for you. + +You have now successfully copied somebody else's (mine) remote +repository, and checked it out. + + +Creating a new branch +--------------------- + +Branches in git are really nothing more than pointers into the git +object database from within the `.git/refs/` subdirectory, and as we +already discussed, the `HEAD` branch is nothing but a symlink to one of +these object pointers. + +You can at any time create a new branch by just picking an arbitrary +point in the project history, and just writing the SHA1 name of that +object into a file under `.git/refs/heads/`. You can use any filename you +want (and indeed, subdirectories), but the convention is that the +"normal" branch is called `master`. That's just a convention, though, +and nothing enforces it. + +To show that as an example, let's go back to the git-tutorial repository we +used earlier, and create a branch in it. You do that by simply just +saying that you want to check out a new branch: + +------------ +$ git checkout -b mybranch +------------ + +will create a new branch based at the current `HEAD` position, and switch +to it. + +[NOTE] +================================================ +If you make the decision to start your new branch at some +other point in the history than the current `HEAD`, you can do so by +just telling `git checkout` what the base of the checkout would be. +In other words, if you have an earlier tag or branch, you'd just do + +------------ +$ git checkout -b mybranch earlier-commit +------------ + +and it would create the new branch `mybranch` at the earlier commit, +and check out the state at that time. +================================================ + +You can always just jump back to your original `master` branch by doing + +------------ +$ git checkout master +------------ + +(or any other branch-name, for that matter) and if you forget which +branch you happen to be on, a simple + +------------ +$ cat .git/HEAD +------------ + +will tell you where it's pointing. To get the list of branches +you have, you can say + +------------ +$ git branch +------------ + +which is nothing more than a simple script around `ls .git/refs/heads`. +There will be asterisk in front of the branch you are currently on. + +Sometimes you may wish to create a new branch _without_ actually +checking it out and switching to it. If so, just use the command + +------------ +$ git branch <branchname> [startingpoint] +------------ + +which will simply _create_ the branch, but will not do anything further. +You can then later -- once you decide that you want to actually develop +on that branch -- switch to that branch with a regular `git checkout` +with the branchname as the argument. + + +Merging two branches +-------------------- + +One of the ideas of having a branch is that you do some (possibly +experimental) work in it, and eventually merge it back to the main +branch. So assuming you created the above `mybranch` that started out +being the same as the original `master` branch, let's make sure we're in +that branch, and do some work there. + +------------------------------------------------ +$ git checkout mybranch +$ echo "Work, work, work" >>hello +$ git commit -m 'Some work.' -i hello +------------------------------------------------ + +Here, we just added another line to `hello`, and we used a shorthand for +doing both `git-update-index hello` and `git commit` by just giving the +filename directly to `git commit`, with an `-i` flag (it tells +git to 'include' that file in addition to what you have done to +the index file so far when making the commit). The `-m` flag is to give the +commit log message from the command line. + +Now, to make it a bit more interesting, let's assume that somebody else +does some work in the original branch, and simulate that by going back +to the master branch, and editing the same file differently there: + +------------ +$ git checkout master +------------ + +Here, take a moment to look at the contents of `hello`, and notice how they +don't contain the work we just did in `mybranch` -- because that work +hasn't happened in the `master` branch at all. Then do + +------------ +$ echo "Play, play, play" >>hello +$ echo "Lots of fun" >>example +$ git commit -m 'Some fun.' -i hello example +------------ + +since the master branch is obviously in a much better mood. + +Now, you've got two branches, and you decide that you want to merge the +work done. Before we do that, let's introduce a cool graphical tool that +helps you view what's going on: + +---------------- +$ gitk --all +---------------- + +will show you graphically both of your branches (that's what the `\--all` +means: normally it will just show you your current `HEAD`) and their +histories. You can also see exactly how they came to be from a common +source. + +Anyway, let's exit `gitk` (`^Q` or the File menu), and decide that we want +to merge the work we did on the `mybranch` branch into the `master` +branch (which is currently our `HEAD` too). To do that, there's a nice +script called `git merge`, which wants to know which branches you want +to resolve and what the merge is all about: + +------------ +$ git merge "Merge work in mybranch" HEAD mybranch +------------ + +where the first argument is going to be used as the commit message if +the merge can be resolved automatically. + +Now, in this case we've intentionally created a situation where the +merge will need to be fixed up by hand, though, so git will do as much +of it as it can automatically (which in this case is just merge the `example` +file, which had no differences in the `mybranch` branch), and say: + +---------------- + Auto-merging hello + CONFLICT (content): Merge conflict in hello + Automatic merge failed; fix up by hand +---------------- + +It tells you that it did an "Automatic merge", which +failed due to conflicts in `hello`. + +Not to worry. It left the (trivial) conflict in `hello` in the same form you +should already be well used to if you've ever used CVS, so let's just +open `hello` in our editor (whatever that may be), and fix it up somehow. +I'd suggest just making it so that `hello` contains all four lines: + +------------ +Hello World +It's a new day for git +Play, play, play +Work, work, work +------------ + +and once you're happy with your manual merge, just do a + +------------ +$ git commit -i hello +------------ + +which will very loudly warn you that you're now committing a merge +(which is correct, so never mind), and you can write a small merge +message about your adventures in git-merge-land. + +After you're done, start up `gitk \--all` to see graphically what the +history looks like. Notice that `mybranch` still exists, and you can +switch to it, and continue to work with it if you want to. The +`mybranch` branch will not contain the merge, but next time you merge it +from the `master` branch, git will know how you merged it, so you'll not +have to do _that_ merge again. + +Another useful tool, especially if you do not always work in X-Window +environment, is `git show-branch`. + +------------------------------------------------ +$ git show-branch --topo-order master mybranch +* [master] Merge work in mybranch + ! [mybranch] Some work. +-- +- [master] Merge work in mybranch +*+ [mybranch] Some work. +------------------------------------------------ + +The first two lines indicate that it is showing the two branches +and the first line of the commit log message from their +top-of-the-tree commits, you are currently on `master` branch +(notice the asterisk `\*` character), and the first column for +the later output lines is used to show commits contained in the +`master` branch, and the second column for the `mybranch` +branch. Three commits are shown along with their log messages. +All of them have non blank characters in the first column (`*` +shows an ordinary commit on the current branch, `.` is a merge commit), which +means they are now part of the `master` branch. Only the "Some +work" commit has the plus `+` character in the second column, +because `mybranch` has not been merged to incorporate these +commits from the master branch. The string inside brackets +before the commit log message is a short name you can use to +name the commit. In the above example, 'master' and 'mybranch' +are branch heads. 'master~1' is the first parent of 'master' +branch head. Please see 'git-rev-parse' documentation if you +see more complex cases. + +Now, let's pretend you are the one who did all the work in +`mybranch`, and the fruit of your hard work has finally been merged +to the `master` branch. Let's go back to `mybranch`, and run +`git merge` to get the "upstream changes" back to your branch. + +------------ +$ git checkout mybranch +$ git merge "Merge upstream changes." HEAD master +------------ + +This outputs something like this (the actual commit object names +would be different) + +---------------- +Updating from ae3a2da... to a80b4aa.... +Fast forward + example | 1 + + hello | 1 + + 2 files changed, 2 insertions(+), 0 deletions(-) +---------------- + +Because your branch did not contain anything more than what are +already merged into the `master` branch, the merge operation did +not actually do a merge. Instead, it just updated the top of +the tree of your branch to that of the `master` branch. This is +often called 'fast forward' merge. + +You can run `gitk \--all` again to see how the commit ancestry +looks like, or run `show-branch`, which tells you this. + +------------------------------------------------ +$ git show-branch master mybranch +! [master] Merge work in mybranch + * [mybranch] Merge work in mybranch +-- +-- [master] Merge work in mybranch +------------------------------------------------ + + +Merging external work +--------------------- + +It's usually much more common that you merge with somebody else than +merging with your own branches, so it's worth pointing out that git +makes that very easy too, and in fact, it's not that different from +doing a `git merge`. In fact, a remote merge ends up being nothing +more than "fetch the work from a remote repository into a temporary tag" +followed by a `git merge`. + +Fetching from a remote repository is done by, unsurprisingly, +`git fetch`: + +---------------- +$ git fetch <remote-repository> +---------------- + +One of the following transports can be used to name the +repository to download from: + +Rsync:: + `rsync://remote.machine/path/to/repo.git/` ++ +Rsync transport is usable for both uploading and downloading, +but is completely unaware of what git does, and can produce +unexpected results when you download from the public repository +while the repository owner is uploading into it via `rsync` +transport. Most notably, it could update the files under +`refs/` which holds the object name of the topmost commits +before uploading the files in `objects/` -- the downloader would +obtain head commit object name while that object itself is still +not available in the repository. For this reason, it is +considered deprecated. + +SSH:: + `remote.machine:/path/to/repo.git/` or ++ +`ssh://remote.machine/path/to/repo.git/` ++ +This transport can be used for both uploading and downloading, +and requires you to have a log-in privilege over `ssh` to the +remote machine. It finds out the set of objects the other side +lacks by exchanging the head commits both ends have and +transfers (close to) minimum set of objects. It is by far the +most efficient way to exchange git objects between repositories. + +Local directory:: + `/path/to/repo.git/` ++ +This transport is the same as SSH transport but uses `sh` to run +both ends on the local machine instead of running other end on +the remote machine via `ssh`. + +git Native:: + `git://remote.machine/path/to/repo.git/` ++ +This transport was designed for anonymous downloading. Like SSH +transport, it finds out the set of objects the downstream side +lacks and transfers (close to) minimum set of objects. + +HTTP(S):: + `http://remote.machine/path/to/repo.git/` ++ +Downloader from http and https URL +first obtains the topmost commit object name from the remote site +by looking at the specified refname under `repo.git/refs/` directory, +and then tries to obtain the +commit object by downloading from `repo.git/objects/xx/xxx\...` +using the object name of that commit object. Then it reads the +commit object to find out its parent commits and the associate +tree object; it repeats this process until it gets all the +necessary objects. Because of this behavior, they are +sometimes also called 'commit walkers'. ++ +The 'commit walkers' are sometimes also called 'dumb +transports', because they do not require any git aware smart +server like git Native transport does. Any stock HTTP server +that does not even support directory index would suffice. But +you must prepare your repository with `git-update-server-info` +to help dumb transport downloaders. ++ +There are (confusingly enough) `git-ssh-fetch` and `git-ssh-upload` +programs, which are 'commit walkers'; they outlived their +usefulness when git Native and SSH transports were introduced, +and not used by `git pull` or `git push` scripts. + +Once you fetch from the remote repository, you `merge` that +with your current branch. + +However -- it's such a common thing to `fetch` and then +immediately `merge`, that it's called `git pull`, and you can +simply do + +---------------- +$ git pull <remote-repository> +---------------- + +and optionally give a branch-name for the remote end as a second +argument. + +[NOTE] +You could do without using any branches at all, by +keeping as many local repositories as you would like to have +branches, and merging between them with `git pull`, just like +you merge between branches. The advantage of this approach is +that it lets you keep a set of files for each `branch` checked +out and you may find it easier to switch back and forth if you +juggle multiple lines of development simultaneously. Of +course, you will pay the price of more disk usage to hold +multiple working trees, but disk space is cheap these days. + +It is likely that you will be pulling from the same remote +repository from time to time. As a short hand, you can store +the remote repository URL in the local repository's config file +like this: + +------------------------------------------------ +$ git config remote.linus.url http://www.kernel.org/pub/scm/git/git.git/ +------------------------------------------------ + +and use the "linus" keyword with `git pull` instead of the full URL. + +Examples. + +. `git pull linus` +. `git pull linus tag v0.99.1` + +the above are equivalent to: + +. `git pull http://www.kernel.org/pub/scm/git/git.git/ HEAD` +. `git pull http://www.kernel.org/pub/scm/git/git.git/ tag v0.99.1` + + +How does the merge work? +------------------------ + +We said this tutorial shows what plumbing does to help you cope +with the porcelain that isn't flushing, but we so far did not +talk about how the merge really works. If you are following +this tutorial the first time, I'd suggest to skip to "Publishing +your work" section and come back here later. + +OK, still with me? To give us an example to look at, let's go +back to the earlier repository with "hello" and "example" file, +and bring ourselves back to the pre-merge state: + +------------ +$ git show-branch --more=3 master mybranch +! [master] Merge work in mybranch + * [mybranch] Merge work in mybranch +-- +-- [master] Merge work in mybranch ++* [master^2] Some work. ++* [master^] Some fun. +------------ + +Remember, before running `git merge`, our `master` head was at +"Some fun." commit, while our `mybranch` head was at "Some +work." commit. + +------------ +$ git checkout mybranch +$ git reset --hard master^2 +$ git checkout master +$ git reset --hard master^ +------------ + +After rewinding, the commit structure should look like this: + +------------ +$ git show-branch +* [master] Some fun. + ! [mybranch] Some work. +-- + + [mybranch] Some work. +* [master] Some fun. +*+ [mybranch^] New day. +------------ + +Now we are ready to experiment with the merge by hand. + +`git merge` command, when merging two branches, uses 3-way merge +algorithm. First, it finds the common ancestor between them. +The command it uses is `git-merge-base`: + +------------ +$ mb=$(git-merge-base HEAD mybranch) +------------ + +The command writes the commit object name of the common ancestor +to the standard output, so we captured its output to a variable, +because we will be using it in the next step. BTW, the common +ancestor commit is the "New day." commit in this case. You can +tell it by: + +------------ +$ git-name-rev $mb +my-first-tag +------------ + +After finding out a common ancestor commit, the second step is +this: + +------------ +$ git-read-tree -m -u $mb HEAD mybranch +------------ + +This is the same `git-read-tree` command we have already seen, +but it takes three trees, unlike previous examples. This reads +the contents of each tree into different 'stage' in the index +file (the first tree goes to stage 1, the second stage 2, +etc.). After reading three trees into three stages, the paths +that are the same in all three stages are 'collapsed' into stage +0. Also paths that are the same in two of three stages are +collapsed into stage 0, taking the SHA1 from either stage 2 or +stage 3, whichever is different from stage 1 (i.e. only one side +changed from the common ancestor). + +After 'collapsing' operation, paths that are different in three +trees are left in non-zero stages. At this point, you can +inspect the index file with this command: + +------------ +$ git-ls-files --stage +100644 7f8b141b65fdcee47321e399a2598a235a032422 0 example +100644 263414f423d0e4d70dae8fe53fa34614ff3e2860 1 hello +100644 06fa6a24256dc7e560efa5687fa84b51f0263c3a 2 hello +100644 cc44c73eb783565da5831b4d820c962954019b69 3 hello +------------ + +In our example of only two files, we did not have unchanged +files so only 'example' resulted in collapsing, but in real-life +large projects, only small number of files change in one commit, +and this 'collapsing' tends to trivially merge most of the paths +fairly quickly, leaving only a handful the real changes in non-zero +stages. + +To look at only non-zero stages, use `\--unmerged` flag: + +------------ +$ git-ls-files --unmerged +100644 263414f423d0e4d70dae8fe53fa34614ff3e2860 1 hello +100644 06fa6a24256dc7e560efa5687fa84b51f0263c3a 2 hello +100644 cc44c73eb783565da5831b4d820c962954019b69 3 hello +------------ + +The next step of merging is to merge these three versions of the +file, using 3-way merge. This is done by giving +`git-merge-one-file` command as one of the arguments to +`git-merge-index` command: + +------------ +$ git-merge-index git-merge-one-file hello +Auto-merging hello. +merge: warning: conflicts during merge +ERROR: Merge conflict in hello. +fatal: merge program failed +------------ + +`git-merge-one-file` script is called with parameters to +describe those three versions, and is responsible to leave the +merge results in the working tree. +It is a fairly straightforward shell script, and +eventually calls `merge` program from RCS suite to perform a +file-level 3-way merge. In this case, `merge` detects +conflicts, and the merge result with conflict marks is left in +the working tree.. This can be seen if you run `ls-files +--stage` again at this point: + +------------ +$ git-ls-files --stage +100644 7f8b141b65fdcee47321e399a2598a235a032422 0 example +100644 263414f423d0e4d70dae8fe53fa34614ff3e2860 1 hello +100644 06fa6a24256dc7e560efa5687fa84b51f0263c3a 2 hello +100644 cc44c73eb783565da5831b4d820c962954019b69 3 hello +------------ + +This is the state of the index file and the working file after +`git merge` returns control back to you, leaving the conflicting +merge for you to resolve. Notice that the path `hello` is still +unmerged, and what you see with `git diff` at this point is +differences since stage 2 (i.e. your version). + + +Publishing your work +-------------------- + +So, we can use somebody else's work from a remote repository, but +how can *you* prepare a repository to let other people pull from +it? + +Your do your real work in your working tree that has your +primary repository hanging under it as its `.git` subdirectory. +You *could* make that repository accessible remotely and ask +people to pull from it, but in practice that is not the way +things are usually done. A recommended way is to have a public +repository, make it reachable by other people, and when the +changes you made in your primary working tree are in good shape, +update the public repository from it. This is often called +'pushing'. + +[NOTE] +This public repository could further be mirrored, and that is +how git repositories at `kernel.org` are managed. + +Publishing the changes from your local (private) repository to +your remote (public) repository requires a write privilege on +the remote machine. You need to have an SSH account there to +run a single command, `git-receive-pack`. + +First, you need to create an empty repository on the remote +machine that will house your public repository. This empty +repository will be populated and be kept up-to-date by pushing +into it later. Obviously, this repository creation needs to be +done only once. + +[NOTE] +`git push` uses a pair of programs, +`git-send-pack` on your local machine, and `git-receive-pack` +on the remote machine. The communication between the two over +the network internally uses an SSH connection. + +Your private repository's git directory is usually `.git`, but +your public repository is often named after the project name, +i.e. `<project>.git`. Let's create such a public repository for +project `my-git`. After logging into the remote machine, create +an empty directory: + +------------ +$ mkdir my-git.git +------------ + +Then, make that directory into a git repository by running +`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 +------------ + +Make sure this directory is available for others you want your +changes to be pulled by via the transport of your choice. Also +you need to make sure that you have the `git-receive-pack` +program on the `$PATH`. + +[NOTE] +Many installations of sshd do not invoke your shell as the login +shell when you directly run programs; what this means is that if +your login shell is `bash`, only `.bashrc` is read and not +`.bash_profile`. As a workaround, make sure `.bashrc` sets up +`$PATH` so that you can run `git-receive-pack` program. + +[NOTE] +If you plan to publish this repository to be accessed over http, +you should do `chmod +x my-git.git/hooks/post-update` at this +point. This makes sure that every time you push into this +repository, `git-update-server-info` is run. + +Your "public repository" is now ready to accept your changes. +Come back to the machine you have your private repository. From +there, run this command: + +------------ +$ git push <public-host>:/path/to/my-git.git master +------------ + +This synchronizes your public repository to match the named +branch head (i.e. `master` in this case) and objects reachable +from them in your current repository. + +As a real example, this is how I update my public git +repository. Kernel.org mirror network takes care of the +propagation to other publicly visible machines: + +------------ +$ git push master.kernel.org:/pub/scm/git/git.git/ +------------ + + +Packing your repository +----------------------- + +Earlier, we saw that one file under `.git/objects/??/` directory +is stored for each git object you create. This representation +is efficient to create atomically and safely, but +not so convenient to transport over the network. Since git objects are +immutable once they are created, there is a way to optimize the +storage by "packing them together". The command + +------------ +$ git repack +------------ + +will do it for you. If you followed the tutorial examples, you +would have accumulated about 17 objects in `.git/objects/??/` +directories by now. `git repack` tells you how many objects it +packed, and stores the packed file in `.git/objects/pack` +directory. + +[NOTE] +You will see two files, `pack-\*.pack` and `pack-\*.idx`, +in `.git/objects/pack` directory. They are closely related to +each other, and if you ever copy them by hand to a different +repository for whatever reason, you should make sure you copy +them together. The former holds all the data from the objects +in the pack, and the latter holds the index for random +access. + +If you are paranoid, running `git-verify-pack` command would +detect if you have a corrupt pack, but do not worry too much. +Our programs are always perfect ;-). + +Once you have packed objects, you do not need to leave the +unpacked objects that are contained in the pack file anymore. + +------------ +$ git prune-packed +------------ + +would remove them for you. + +You can try running `find .git/objects -type f` before and after +you run `git prune-packed` if you are curious. Also `git +count-objects` would tell you how many unpacked objects are in +your repository and how much space they are consuming. + +[NOTE] +`git pull` is slightly cumbersome for HTTP transport, as a +packed repository may contain relatively few objects in a +relatively large pack. If you expect many HTTP pulls from your +public repository you might want to repack & prune often, or +never. + +If you run `git repack` again at this point, it will say +"Nothing to pack". Once you continue your development and +accumulate the changes, running `git repack` again will create a +new pack, that contains objects created since you packed your +repository the last time. We recommend that you pack your project +soon after the initial import (unless you are starting your +project from scratch), and then run `git repack` every once in a +while, depending on how active your project is. + +When a repository is synchronized via `git push` and `git pull` +objects packed in the source repository are usually stored +unpacked in the destination, unless rsync transport is used. +While this allows you to use different packing strategies on +both ends, it also means you may need to repack both +repositories every once in a while. + + +Working with Others +------------------- + +Although git is a truly distributed system, it is often +convenient to organize your project with an informal hierarchy +of developers. Linux kernel development is run this way. There +is a nice illustration (page 17, "Merges to Mainline") in +link:http://tinyurl.com/a2jdg[Randy Dunlap's presentation]. + +It should be stressed that this hierarchy is purely *informal*. +There is nothing fundamental in git that enforces the "chain of +patch flow" this hierarchy implies. You do not have to pull +from only one remote repository. + +A recommended workflow for a "project lead" goes like this: + +1. Prepare your primary repository on your local machine. Your + work is done there. + +2. Prepare a public repository accessible to others. ++ +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`, +`$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 +with `chmod +x post-update`. This makes sure `git-update-server-info` +keeps the necessary files up-to-date. + +3. Push into the public repository from your primary + repository. + +4. `git repack` the public repository. This establishes a big + pack that contains the initial set of objects as the + baseline, and possibly `git prune` if the transport + used for pulling from your repository supports packed + repositories. + +5. Keep working in your primary repository. Your changes + include modifications of your own, patches you receive via + e-mails, and merges resulting from pulling the "public" + repositories of your "subsystem maintainers". ++ +You can repack this private repository whenever you feel like. + +6. Push your changes to the public repository, and announce it + to the public. + +7. Every once in a while, "git repack" the public repository. + Go back to step 5. and continue working. + + +A recommended work cycle for a "subsystem maintainer" who works +on that project and has an own "public repository" goes like this: + +1. Prepare your work repository, by `git clone` the public + repository of the "project lead". The URL used for the + initial cloning is stored in the remote.origin.url + configuration variable. + +2. Prepare a public repository accessible to others, just like + the "project lead" person does. + +3. Copy over the packed files from "project lead" public + repository to your public repository, unless the "project + lead" repository lives on the same machine as yours. In the + latter case, you can use `objects/info/alternates` file to + point at the repository you are borrowing from. + +4. Push into the public repository from your primary + repository. Run `git repack`, and possibly `git prune` if the + transport used for pulling from your repository supports + packed repositories. + +5. Keep working in your primary repository. Your changes + include modifications of your own, patches you receive via + e-mails, and merges resulting from pulling the "public" + repositories of your "project lead" and possibly your + "sub-subsystem maintainers". ++ +You can repack this private repository whenever you feel +like. + +6. Push your changes to your public repository, and ask your + "project lead" and possibly your "sub-subsystem + maintainers" to pull from it. + +7. Every once in a while, `git repack` the public repository. + Go back to step 5. and continue working. + + +A recommended work cycle for an "individual developer" who does +not have a "public" repository is somewhat different. It goes +like this: + +1. Prepare your work repository, by `git clone` the public + repository of the "project lead" (or a "subsystem + maintainer", if you work on a subsystem). The URL used for + the initial cloning is stored in the remote.origin.url + configuration variable. + +2. Do your work in your repository on 'master' branch. + +3. Run `git fetch origin` from the public repository of your + upstream every once in a while. This does only the first + half of `git pull` but does not merge. The head of the + public repository is stored in `.git/refs/remotes/origin/master`. + +4. Use `git cherry origin` to see which ones of your patches + were accepted, and/or use `git rebase origin` to port your + unmerged changes forward to the updated upstream. + +5. Use `git format-patch origin` to prepare patches for e-mail + submission to your upstream and send it out. Go back to + step 2. and continue. + + +Working with Others, Shared Repository Style +-------------------------------------------- + +If you are coming from CVS background, the style of cooperation +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.html[git for CVS users] for the details. + +Bundling your work together +--------------------------- + +It is likely that you will be working on more than one thing at +a time. It is easy to manage those more-or-less independent tasks +using branches with git. + +We have already seen how branches work previously, +with "fun and work" example using two branches. The idea is the +same if there are more than two branches. Let's say you started +out from "master" head, and have some new code in the "master" +branch, and two independent fixes in the "commit-fix" and +"diff-fix" branches: + +------------ +$ git show-branch +! [commit-fix] Fix commit message normalization. + ! [diff-fix] Fix rename detection. + * [master] Release candidate #1 +--- + + [diff-fix] Fix rename detection. + + [diff-fix~1] Better common substring algorithm. ++ [commit-fix] Fix commit message normalization. + * [master] Release candidate #1 +++* [diff-fix~2] Pretty-print messages. +------------ + +Both fixes are tested well, and at this point, you want to merge +in both of them. You could merge in 'diff-fix' first and then +'commit-fix' next, like this: + +------------ +$ git merge 'Merge fix in diff-fix' master diff-fix +$ git merge 'Merge fix in commit-fix' master commit-fix +------------ + +Which would result in: + +------------ +$ git show-branch +! [commit-fix] Fix commit message normalization. + ! [diff-fix] Fix rename detection. + * [master] Merge fix in commit-fix +--- + - [master] Merge fix in commit-fix ++ * [commit-fix] Fix commit message normalization. + - [master~1] Merge fix in diff-fix + +* [diff-fix] Fix rename detection. + +* [diff-fix~1] Better common substring algorithm. + * [master~2] Release candidate #1 +++* [master~3] Pretty-print messages. +------------ + +However, there is no particular reason to merge in one branch +first and the other next, when what you have are a set of truly +independent changes (if the order mattered, then they are not +independent by definition). You could instead merge those two +branches into the current branch at once. First let's undo what +we just did and start over. We would want to get the master +branch before these two merges by resetting it to 'master~2': + +------------ +$ git reset --hard master~2 +------------ + +You can make sure 'git show-branch' matches the state before +those two 'git merge' you just did. Then, instead of running +two 'git merge' commands in a row, you would merge these two +branch heads (this is known as 'making an Octopus'): + +------------ +$ git merge commit-fix diff-fix +$ git show-branch +! [commit-fix] Fix commit message normalization. + ! [diff-fix] Fix rename detection. + * [master] Octopus merge of branches 'diff-fix' and 'commit-fix' +--- + - [master] Octopus merge of branches 'diff-fix' and 'commit-fix' ++ * [commit-fix] Fix commit message normalization. + +* [diff-fix] Fix rename detection. + +* [diff-fix~1] Better common substring algorithm. + * [master~1] Release candidate #1 +++* [master~2] Pretty-print messages. +------------ + +Note that you should not do Octopus because you can. An octopus +is a valid thing to do and often makes it easier to view the +commit history if you are merging more than two independent +changes at the same time. However, if you have merge conflicts +with any of the branches you are merging in and need to hand +resolve, that is an indication that the development happened in +those branches were not independent after all, and you should +merge two at a time, documenting how you resolved the conflicts, +and the reason why you preferred changes made in one side over +the other. Otherwise it would make the project history harder +to follow, not easier. + +[ to be continued.. cvsimports ] diff --git a/Documentation/cvs-migration.txt b/Documentation/cvs-migration.txt new file mode 100644 index 0000000000..3b6b494162 --- /dev/null +++ b/Documentation/cvs-migration.txt @@ -0,0 +1,171 @@ +git for CVS users +================= + +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. + +Developing against a shared repository +-------------------------------------- + +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: + +------------------------------------------------ +$ 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. If there are uncommitted changes in your working tree, commit +them first before running git pull. + +[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 config -l` and the gitlink:git-config[1] man +page for details. +================================ + +You can update the shared repository with your changes by first committing +your changes, and then using the gitlink:git-push[1] command: + +------------------------------------------------ +$ git push origin master +------------------------------------------------ + +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. + +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: + +------------ +$ git push origin +$ git push foo.com:/pub/project.git/ +------------ + +as long as the shared repository does not have any branches +other than `master`. + +Setting Up a Shared Repository +------------------------------ + +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). + +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: + +------------------------------------------------ +$ 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 +easy way to do this is to give all the team members ssh access to the +machine where the repository is hosted. If you don't want to give them a +full shell on the machine, there is a restricted shell which only allows +users to do git pushes and pulls; see gitlink:git-shell[1]. + +Put all the committers in the same group, and make the repository +writable by that group: + +------------------------------------------------ +$ chgrp -R $group /pub/my-repo.git +------------------------------------------------ + +Make sure committers have a umask of at most 027, so that the directories +they create are writable and searchable by other group members. + +Importing a CVS archive +----------------------- + +First, install version 2.1 or higher of cvsps from +link:http://www.cobite.com/cvsps/[http://www.cobite.com/cvsps/] and make +sure it is in your path. Then cd to a checked out CVS working directory +of the project you are interested in and run gitlink:git-cvsimport[1]: + +------------------------------------------- +$ git cvsimport -C <destination> <module> +------------------------------------------- + +This puts a git archive of the named CVS module in the directory +<destination>, which will be created if necessary. + +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. + +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. + +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.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]. + +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. + +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 new file mode 100644 index 0000000000..378e72f38f --- /dev/null +++ b/Documentation/diff-format.txt @@ -0,0 +1,214 @@ +The output format from "git-diff-index", "git-diff-tree" and +"git-diff-files" are very similar. + +These commands all compare two sets of things; what is +compared differs: + +git-diff-index <tree-ish>:: + compares the <tree-ish> and the files on the filesystem. + +git-diff-index --cached <tree-ish>:: + compares the <tree-ish> and the index. + +git-diff-tree [-r] <tree-ish-1> <tree-ish-2> [<pattern>...]:: + compares the trees named by the two arguments. + +git-diff-files [<pattern>...]:: + compares the index and the files on the filesystem. + + +An output line is formatted this way: + +------------------------------------------------ +in-place edit :100644 100644 bcd1234... 0123456... M file0 +copy-edit :100644 100644 abcd123... 1234567... C68 file1 file2 +rename-edit :100644 100644 abcd123... 1234567... R86 file1 file3 +create :000000 100644 0000000... 1234567... A file4 +delete :100644 000000 1234567... 0000000... D file5 +unmerged :000000 000000 0000000... 0000000... U file6 +------------------------------------------------ + +That is, from the left to the right: + +. a colon. +. mode for "src"; 000000 if creation or unmerged. +. a space. +. mode for "dst"; 000000 if deletion or unmerged. +. a space. +. sha1 for "src"; 0\{40\} if creation or unmerged. +. a space. +. sha1 for "dst"; 0\{40\} if creation, unmerged or "look at work tree". +. a space. +. status, followed by optional "score" number. +. a tab or a NUL when '-z' option is used. +. path for "src" +. a tab or a NUL when '-z' option is used; only exists for C or R. +. path for "dst"; only exists for C or R. +. an LF or a NUL when '-z' option is used, to terminate the record. + +<sha1> is shown as all 0's if a file is new on the filesystem +and it is out of sync with the index. + +Example: + +------------------------------------------------ +:100644 100644 5be4a4...... 000000...... M file.c +------------------------------------------------ + +When `-z` option is not used, TAB, LF, and backslash characters +in pathnames are represented as `\t`, `\n`, and `\\`, +respectively. + + +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. You can customize the creation +of such patches via the GIT_EXTERNAL_DIFF and the GIT_DIFF_OPTS +environment variables. + +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 ++ +The `a/` and `b/` filenames are the same unless rename/copy is +involved. Especially, even for a creation or a deletion, +`/dev/null` is _not_ used in place of `a/` or `b/` filenames. ++ +When rename/copy is involved, `file1` and `file2` show the +name of the source file of the rename/copy and the name of +the file that rename/copy produces, respectively. + +2. It is followed by one or more extended header lines: + + old mode <mode> + new mode <mode> + deleted file mode <mode> + new file mode <mode> + copy from <path> + copy to <path> + rename from <path> + rename to <path> + similarity index <number> + dissimilarity index <number> + index <hash>..<hash> <mode> + +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 +-------------------- + +git-diff-tree and git-diff-files can take '-c' or '--cc' option +to produce 'combined diff', which looks like this: + +------------ +diff --combined describe.c +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; + 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 different 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 +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 result. A `+` character +in the column N means that the line appears in the last file, +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 +file2, plus `++` to mean one line that was added does not appear +in either file1 nor file2). Also two other lines are the same +from file1 but do not appear in file2 (hence prefixed with ` +`). + +When shown by `git diff-tree -c`, it compares the parents of a +merge commit with the merge result (i.e. file1..fileN are the +parents). When shown by `git diff-files -c`, it compares the +two unresolved merge parents with the working tree file +(i.e. file1 is stage 2 aka "our version", file2 is stage 3 aka +"their version"). + diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt new file mode 100644 index 0000000000..d8696b7b36 --- /dev/null +++ b/Documentation/diff-options.txt @@ -0,0 +1,163 @@ +-p:: + Generate patch (see section on generating patches) + +-u:: + Synonym for "-p". + +--raw:: + Generate the raw format. + +--patch-with-raw:: + Synonym for "-p --raw". + +--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 + such as creations, renames and mode changes. + +--patch-with-stat:: + Synonym for "-p --stat". + +-z:: + \0 line termination on output + +--name-only:: + Show only names of changed files. + +--name-status:: + Show only names and status of changed files. + +--color:: + Show colored diff. + +--no-color:: + Turn off colored diff, even when the configuration file + gives the default to color output. + +--color-words:: + Show colored word diff, i.e. color words which have changed. + +--no-renames:: + Turn off rename detection, even when the configuration + file gives the default to do so. + +--check:: + Warn if changes introduce trailing whitespace + or an indent that uses a space before a tab. + +--full-index:: + Instead of the first handful characters, show full + object name of pre- and post-image blob on the "index" + line when generating a patch format output. + +--binary:: + In addition to --full-index, output "binary diff" that + can be applied with "git apply". + +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + name in diff-raw format output and diff-tree header + lines, show only handful hexdigits prefix. This is + independent of --full-index option above, which controls + the diff-patch output format. Non default number of + digits can be specified with --abbrev=<n>. + +-B:: + Break complete rewrite changes into pairs of delete and create. + +-M:: + Detect renames. + +-C:: + Detect copies as well as renames. + +--diff-filter=[ACDMRTUXB*]:: + Select only files that are Added (`A`), Copied (`C`), + Deleted (`D`), Modified (`M`), Renamed (`R`), have their + type (mode) changed (`T`), are Unmerged (`U`), are + Unknown (`X`), or have had their pairing Broken (`B`). + Any combination of the filter characters may be used. + When `*` (All-or-none) is added to the combination, all + paths are selected if there is any file that matches + other criteria in the comparison; if there is no file + that matches other criteria, nothing is selected. + +--find-copies-harder:: + For performance reasons, by default, -C option finds copies only + if the original file of the copy was modified in the same + changeset. This flag makes the command + inspect unmodified files as candidates for the source of + copy. This is a very expensive operation for large + projects, so use it with caution. + +-l<num>:: + -M and -C options require O(n^2) processing time where n + is the number of potential rename/copy targets. This + option prevents rename/copy detection from running if + the number of rename/copy targets exceeds the specified + number. + +-S<string>:: + Look for differences that contain the change in <string>. + +--pickaxe-all:: + When -S finds a change, show all the changes in that + changeset, not just the files that contain the change + in <string>. + +--pickaxe-regex:: + Make the <string> not a plain string but an extended POSIX + regex to match. + +-O<orderfile>:: + Output the patch in the order specified in the + <orderfile>, which has one shell glob pattern per line. + +-R:: + Swap two inputs; that is, show differences from index or + on-disk file to tree contents. + +--text:: + Treat all files as text. + +-a:: + Shorthand for "--text". + +--ignore-space-at-eol:: + Ignore changes in white spaces at EOL. + +--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/diffcore.txt b/Documentation/diffcore.txt new file mode 100644 index 0000000000..34cd306bb1 --- /dev/null +++ b/Documentation/diffcore.txt @@ -0,0 +1,272 @@ +Tweaking diff output +==================== +June 2005 + + +Introduction +------------ + +The diff commands git-diff-index, git-diff-files, and git-diff-tree +can be told to manipulate differences they find in +unconventional ways before showing diff(1) output. The manipulation +is collectively called "diffcore transformation". This short note +describes what they are and how to use them to produce diff outputs +that are easier to understand than the conventional kind. + + +The chain of operation +---------------------- + +The git-diff-* family works by first comparing two sets of +files: + + - git-diff-index compares contents of a "tree" object and the + working directory (when '\--cached' flag is not used) or a + "tree" object and the index file (when '\--cached' flag is + used); + + - git-diff-files compares contents of the index file and the + working directory; + + - git-diff-tree compares contents of two "tree" objects; + +In all of these cases, the commands themselves compare +corresponding paths in the two sets of files. The result of +comparison is passed from these commands to what is internally +called "diffcore", in a format similar to what is output when +the -p option is not used. E.g. + +------------------------------------------------ +in-place edit :100644 100644 bcd1234... 0123456... M file0 +create :000000 100644 0000000... 1234567... A file4 +delete :100644 000000 1234567... 0000000... D file5 +unmerged :000000 000000 0000000... 0000000... U file6 +------------------------------------------------ + +The diffcore mechanism is fed a list of such comparison results +(each of which is called "filepair", although at this point each +of them talks about a single file), and transforms such a list +into another list. There are currently 6 such transformations: + +- diffcore-pathspec +- diffcore-break +- diffcore-rename +- diffcore-merge-broken +- diffcore-pickaxe +- diffcore-order + +These are applied in sequence. The set of filepairs git-diff-\* +commands find are used as the input to diffcore-pathspec, and +the output from diffcore-pathspec is used as the input to the +next transformation. The final result is then passed to the +output routine and generates either diff-raw format (see Output +format sections of the manual for git-diff-\* commands) or +diff-patch format. + + +diffcore-pathspec: For Ignoring Files Outside Our Consideration +--------------------------------------------------------------- + +The first transformation in the chain is diffcore-pathspec, and +is controlled by giving the pathname parameters to the +git-diff-* commands on the command line. The pathspec is used +to limit the world diff operates in. It removes the filepairs +outside the specified set of pathnames. E.g. If the input set +of filepairs included: + +------------------------------------------------ +:100644 100644 bcd1234... 0123456... M junkfile +------------------------------------------------ + +but the command invocation was "git-diff-files myfile", then the +junkfile entry would be removed from the list because only "myfile" +is under consideration. + +Implementation note. For performance reasons, git-diff-tree +uses the pathname parameters on the command line to cull set of +filepairs it feeds the diffcore mechanism itself, and does not +use diffcore-pathspec, but the end result is the same. + + +diffcore-break: For Splitting Up "Complete Rewrites" +---------------------------------------------------- + +The second transformation in the chain is diffcore-break, and is +controlled by the -B option to the git-diff-* commands. This is +used to detect a filepair that represents "complete rewrite" and +break such filepair into two filepairs that represent delete and +create. E.g. If the input contained this filepair: + +------------------------------------------------ +:100644 100644 bcd1234... 0123456... M file0 +------------------------------------------------ + +and if it detects that the file "file0" is completely rewritten, +it changes it to: + +------------------------------------------------ +:100644 000000 bcd1234... 0000000... D file0 +:000000 100644 0000000... 0123456... A file0 +------------------------------------------------ + +For the purpose of breaking a filepair, diffcore-break examines +the extent of changes between the contents of the files before +and after modification (i.e. the contents that have "bcd1234..." +and "0123456..." as their SHA1 content ID, in the above +example). The amount of deletion of original contents and +insertion of new material are added together, and if it exceeds +the "break score", the filepair is broken into two. The break +score defaults to 50% of the size of the smaller of the original +and the result (i.e. if the edit shrinks the file, the size of +the result is used; if the edit lengthens the file, the size of +the original is used), and can be customized by giving a number +after "-B" option (e.g. "-B75" to tell it to use 75%). + + +diffcore-rename: For Detection Renames and Copies +------------------------------------------------- + +This transformation is used to detect renames and copies, and is +controlled by the -M option (to detect renames) and the -C option +(to detect copies as well) to the git-diff-* commands. If the +input contained these filepairs: + +------------------------------------------------ +:100644 000000 0123456... 0000000... D fileX +:000000 100644 0000000... 0123456... A file0 +------------------------------------------------ + +and the contents of the deleted file fileX is similar enough to +the contents of the created file file0, then rename detection +merges these filepairs and creates: + +------------------------------------------------ +:100644 100644 0123456... 0123456... R100 fileX file0 +------------------------------------------------ + +When the "-C" option is used, the original contents of modified files, +and deleted files (and also unmodified files, if the +"\--find-copies-harder" option is used) are considered as candidates +of the source files in rename/copy operation. If the input were like +these filepairs, that talk about a modified file fileY and a newly +created file file0: + +------------------------------------------------ +:100644 100644 0123456... 1234567... M fileY +:000000 100644 0000000... bcd3456... A file0 +------------------------------------------------ + +the original contents of fileY and the resulting contents of +file0 are compared, and if they are similar enough, they are +changed to: + +------------------------------------------------ +:100644 100644 0123456... 1234567... M fileY +:100644 100644 0123456... bcd3456... C100 fileY file0 +------------------------------------------------ + +In both rename and copy detection, the same "extent of changes" +algorithm used in diffcore-break is used to determine if two +files are "similar enough", and can be customized to use +a similarity score different from the default of 50% by giving a +number after the "-M" or "-C" option (e.g. "-M8" to tell it to use +8/10 = 80%). + +Note. When the "-C" option is used with `\--find-copies-harder` +option, git-diff-\* commands feed unmodified filepairs to +diffcore mechanism as well as modified ones. This lets the copy +detector consider unmodified files as copy source candidates at +the expense of making it slower. Without `\--find-copies-harder`, +git-diff-\* commands can detect copies only if the file that was +copied happened to have been modified in the same changeset. + + +diffcore-merge-broken: For Putting "Complete Rewrites" Back Together +-------------------------------------------------------------------- + +This transformation is used to merge filepairs broken by +diffcore-break, and not transformed into rename/copy by +diffcore-rename, back into a single modification. This always +runs when diffcore-break is used. + +For the purpose of merging broken filepairs back, it uses a +different "extent of changes" computation from the ones used by +diffcore-break and diffcore-rename. It counts only the deletion +from the original, and does not count insertion. If you removed +only 10 lines from a 100-line document, even if you added 910 +new lines to make a new 1000-line document, you did not do a +complete rewrite. diffcore-break breaks such a case in order to +help diffcore-rename to consider such filepairs as candidate of +rename/copy detection, but if filepairs broken that way were not +matched with other filepairs to create rename/copy, then this +transformation merges them back into the original +"modification". + +The "extent of changes" parameter can be tweaked from the +default 80% (that is, unless more than 80% of the original +material is deleted, the broken pairs are merged back into a +single modification) by giving a second number to -B option, +like these: + +* -B50/60 (give 50% "break score" to diffcore-break, use 60% + for diffcore-merge-broken). + +* -B/60 (the same as above, since diffcore-break defaults to 50%). + +Note that earlier implementation left a broken pair as a separate +creation and deletion patches. This was an unnecessary hack and +the latest implementation always merges all the broken pairs +back into modifications, but the resulting patch output is +formatted differently for easier review in case of such +a complete rewrite by showing the entire contents of old version +prefixed with '-', followed by the entire contents of new +version prefixed with '+'. + + +diffcore-pickaxe: For Detecting Addition/Deletion of Specified String +--------------------------------------------------------------------- + +This transformation is used to find filepairs that represent +changes that touch a specified string, and is controlled by the +-S option and the `\--pickaxe-all` option to the git-diff-* +commands. + +When diffcore-pickaxe is in use, it checks if there are +filepairs whose "original" side has the specified string and +whose "result" side does not. Such a filepair represents "the +string appeared in this changeset". It also checks for the +opposite case that loses the specified string. + +When `\--pickaxe-all` is not in effect, diffcore-pickaxe leaves +only such filepairs that touch the specified string in its +output. When `\--pickaxe-all` is used, diffcore-pickaxe leaves all +filepairs intact if there is such a filepair, or makes the +output empty otherwise. The latter behaviour is designed to +make reviewing of the changes in the context of the whole +changeset easier. + + +diffcore-order: For Sorting the Output Based on Filenames +--------------------------------------------------------- + +This is used to reorder the filepairs according to the user's +(or project's) taste, and is controlled by the -O option to the +git-diff-* commands. + +This takes a text file each of whose lines is a shell glob +pattern. Filepairs that match a glob pattern on an earlier line +in the file are output before ones that match a later line, and +filepairs that do not match any glob pattern are output last. + +As an example, a typical orderfile for the core git probably +would look like this: + +------------------------------------------------ +README +Makefile +Documentation +*.h +*.c +t +------------------------------------------------ + diff --git a/Documentation/docbook-xsl.css b/Documentation/docbook-xsl.css new file mode 100644 index 0000000000..8821e305dd --- /dev/null +++ b/Documentation/docbook-xsl.css @@ -0,0 +1,286 @@ +/*
+ CSS stylesheet for XHTML produced by DocBook XSL stylesheets.
+ Tested with XSL stylesheets 1.61.2, 1.67.2
+*/
+
+span.strong {
+ font-weight: bold;
+}
+
+body blockquote {
+ margin-top: .75em;
+ line-height: 1.5;
+ margin-bottom: .75em;
+}
+
+html body {
+ margin: 1em 5% 1em 5%;
+ line-height: 1.2;
+}
+
+body div {
+ margin: 0;
+}
+
+h1, h2, h3, h4, h5, h6,
+div.toc p b,
+div.list-of-figures p b,
+div.list-of-tables p b,
+div.abstract p.title
+{
+ color: #527bbd;
+ font-family: tahoma, verdana, sans-serif;
+}
+
+div.toc p:first-child,
+div.list-of-figures p:first-child,
+div.list-of-tables p:first-child,
+div.example p.title
+{
+ margin-bottom: 0.2em;
+}
+
+body h1 {
+ margin: .0em 0 0 -4%;
+ line-height: 1.3;
+ border-bottom: 2px solid silver;
+}
+
+body h2 {
+ margin: 0.5em 0 0 -4%;
+ line-height: 1.3;
+ border-bottom: 2px solid silver;
+}
+
+body h3 {
+ margin: .8em 0 0 -3%;
+ line-height: 1.3;
+}
+
+body h4 {
+ margin: .8em 0 0 -3%;
+ line-height: 1.3;
+}
+
+body h5 {
+ margin: .8em 0 0 -2%;
+ line-height: 1.3;
+}
+
+body h6 {
+ margin: .8em 0 0 -1%;
+ line-height: 1.3;
+}
+
+body hr {
+ border: none; /* Broken on IE6 */
+}
+div.footnotes hr {
+ border: 1px solid silver;
+}
+
+div.navheader th, div.navheader td, div.navfooter td {
+ font-family: sans-serif;
+ font-size: 0.9em;
+ font-weight: bold;
+ color: #527bbd;
+}
+div.navheader img, div.navfooter img {
+ border-style: none;
+}
+div.navheader a, div.navfooter a {
+ font-weight: normal;
+}
+div.navfooter hr {
+ border: 1px solid silver;
+}
+
+body td {
+ line-height: 1.2
+}
+
+body th {
+ line-height: 1.2;
+}
+
+ol {
+ line-height: 1.2;
+}
+
+ul, body dir, body menu {
+ line-height: 1.2;
+}
+
+html {
+ margin: 0;
+ padding: 0;
+}
+
+body h1, body h2, body h3, body h4, body h5, body h6 {
+ margin-left: 0
+}
+
+body pre {
+ margin: 0.5em 10% 0.5em 1em;
+ line-height: 1.0;
+ color: navy;
+}
+
+tt.literal, code.literal {
+ color: navy;
+}
+
+div.literallayout p {
+ padding: 0em;
+ margin: 0em;
+}
+
+div.literallayout {
+ font-family: monospace;
+# margin: 0.5em 10% 0.5em 1em;
+ margin: 0em;
+ color: navy;
+ border: 1px solid silver;
+ background: #f4f4f4;
+ padding: 0.5em;
+}
+
+.programlisting, .screen {
+ border: 1px solid silver;
+ background: #f4f4f4;
+ margin: 0.5em 10% 0.5em 0;
+ padding: 0.5em 1em;
+}
+
+div.sidebar {
+ background: #ffffee;
+ margin: 1.0em 10% 0.5em 0;
+ padding: 0.5em 1em;
+ border: 1px solid silver;
+}
+div.sidebar * { padding: 0; }
+div.sidebar div { margin: 0; }
+div.sidebar p.title {
+ font-family: sans-serif;
+ margin-top: 0.5em;
+ margin-bottom: 0.2em;
+}
+
+div.bibliomixed {
+ margin: 0.5em 5% 0.5em 1em;
+}
+
+div.glossary dt {
+ font-weight: bold;
+}
+div.glossary dd p {
+ margin-top: 0.2em;
+}
+
+dl {
+ margin: .8em 0;
+ line-height: 1.2;
+}
+
+dt {
+ margin-top: 0.5em;
+}
+
+dt span.term {
+ font-style: italic;
+}
+
+div.variablelist dd p {
+ margin-top: 0;
+}
+
+div.itemizedlist li, div.orderedlist li {
+ margin-left: -0.8em;
+ margin-top: 0.5em;
+}
+
+ul, ol {
+ list-style-position: outside;
+}
+
+div.sidebar ul, div.sidebar ol {
+ margin-left: 2.8em;
+}
+
+div.itemizedlist p.title,
+div.orderedlist p.title,
+div.variablelist p.title
+{
+ margin-bottom: -0.8em;
+}
+
+div.revhistory table {
+ border-collapse: collapse;
+ border: none;
+}
+div.revhistory th {
+ border: none;
+ color: #527bbd;
+ font-family: tahoma, verdana, sans-serif;
+}
+div.revhistory td {
+ border: 1px solid silver;
+}
+
+/* Keep TOC and index lines close together. */
+div.toc dl, div.toc dt,
+div.list-of-figures dl, div.list-of-figures dt,
+div.list-of-tables dl, div.list-of-tables dt,
+div.indexdiv dl, div.indexdiv dt
+{
+ line-height: normal;
+ margin-top: 0;
+ margin-bottom: 0;
+}
+
+/*
+ Table styling does not work because of overriding attributes in
+ generated HTML.
+*/
+div.table table,
+div.informaltable table
+{
+ margin-left: 0;
+ margin-right: 5%;
+ margin-bottom: 0.8em;
+}
+div.informaltable table
+{
+ margin-top: 0.4em
+}
+div.table thead,
+div.table tfoot,
+div.table tbody,
+div.informaltable thead,
+div.informaltable tfoot,
+div.informaltable tbody
+{
+ /* No effect in IE6. */
+ border-top: 2px solid #527bbd;
+ border-bottom: 2px solid #527bbd;
+}
+div.table thead, div.table tfoot,
+div.informaltable thead, div.informaltable tfoot
+{
+ font-weight: bold;
+}
+
+div.mediaobject img {
+ border: 1px solid silver;
+ margin-bottom: 0.8em;
+}
+div.figure p.title,
+div.table p.title
+{
+ margin-top: 1em;
+ margin-bottom: 0.4em;
+}
+
+@media print {
+ div.navheader, div.navfooter { display: none; }
+}
diff --git a/Documentation/everyday.txt b/Documentation/everyday.txt new file mode 100644 index 0000000000..08c61b1f1a --- /dev/null +++ b/Documentation/everyday.txt @@ -0,0 +1,465 @@ +Everyday GIT With 20 Commands Or So +=================================== + +<<Basic Repository>> commands are needed by people who have a +repository --- that is everybody, because every working tree of +git is a repository. + +In addition, <<Individual Developer (Standalone)>> commands are +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 +the <<Individual Developer (Participant)>> section as well. + +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 for the care and feeding +of git repositories. + + +Basic Repository[[Basic Repository]] +------------------------------------ + +Everybody uses these commands to maintain git repositories. + + * gitlink:git-init[1] or gitlink:git-clone[1] to create a + new repository. + + * gitlink:git-fsck[1] to check the repository for errors. + + * 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 +~~~~~~~~ + +Check health and remove cruft.:: ++ +------------ +$ git fsck <1> +$ git count-objects <2> +$ git repack <3> +$ git gc <4> +------------ ++ +<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 +of loose objects accumulation may be a good rule of thumb. +<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.:: ++ +------------ +$ git repack -a -d <1> +$ git prune +------------ ++ +<1> pack all the objects reachable from the refs into one pack, +then remove the other packs. + + +Individual Developer (Standalone)[[Individual Developer (Standalone)]] +---------------------------------------------------------------------- + +A standalone individual developer does not exchange patches with +other people, and works alone in a single repository, using the +following commands. + + * gitlink:git-show-branch[1] to see where you are. + + * gitlink:git-log[1] to see what happened. + + * gitlink:git-checkout[1] and gitlink:git-branch[1] to switch + branches. + + * 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. + + * gitlink:git-commit[1] to advance the current branch. + + * gitlink:git-reset[1] and gitlink:git-checkout[1] (with + pathname parameters) to undo changes. + + * gitlink:git-merge[1] to merge between local branches. + + * gitlink:git-rebase[1] to maintain topic branches. + + * gitlink:git-tag[1] to mark known point. + +Examples +~~~~~~~~ + +Use a tarball as a starting point for a new repository.:: ++ +------------ +$ tar zxf frotz.tar.gz +$ cd frotz +$ git-init +$ git add . <1> +$ git commit -m 'import of frotz source tree.' +$ git tag v2.43 <2> +------------ ++ +<1> add everything under the current directory. +<2> make a lightweight, unannotated tag. + +Create a topic branch and develop.:: ++ +------------ +$ git checkout -b alsa-audio <1> +$ edit/compile/test +$ git checkout -- curses/ux_audio_oss.c <2> +$ git add curses/ux_audio_alsa.c <3> +$ edit/compile/test +$ git diff HEAD <4> +$ git commit -a -s <5> +$ edit/compile/test +$ git reset --soft HEAD^ <6> +$ edit/compile/test +$ git diff ORIG_HEAD <7> +$ git commit -a -c ORIG_HEAD <8> +$ git checkout master <9> +$ 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`. +<3> you need to tell git if you added a new file; removal and +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. +<7> look at the changes since the premature commit we took back. +<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. +<11> review commit logs; other forms to limit output can be +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)]] +------------------------------------------------------------------------ + +A developer working as a participant in a group project needs to +learn how to communicate with others, and uses these commands in +addition to the ones needed by a standalone developer. + + * gitlink:git-clone[1] from the upstream to prime your local + repository. + + * gitlink:git-pull[1] and gitlink:git-fetch[1] from "origin" + to keep up-to-date with the upstream. + + * gitlink:git-push[1] to shared repository, if you adopt CVS + style shared repository workflow. + + * gitlink:git-format-patch[1] to prepare e-mail submission, if + you adopt Linux kernel-style public forum workflow. + +Examples +~~~~~~~~ + +Clone the upstream and work on it. Feed changes to upstream.:: ++ +------------ +$ git clone git://git.kernel.org/pub/scm/.../torvalds/linux-2.6 my2.6 +$ cd my2.6 +$ edit/compile/test; git commit -a -s <1> +$ git format-patch origin <2> +$ git pull <3> +$ 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> +$ git fetch --tags <8> +------------ ++ +<1> repeat as needed. +<2> extract patches from your branch for e-mail submission. +<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 +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/`. + + +Push into another repository.:: ++ +------------ +satellite$ git clone mothership:frotz frotz <1> +satellite$ cd frotz +satellite$ git 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 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 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 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. + +Branch off of a specific tag.:: ++ +------------ +$ git checkout -b private2.6.14 v2.6.14 <1> +$ edit/compile/test; git commit -a +$ git checkout master +$ git format-patch -k -m --stdout v2.6.14..private2.6.14 | + git am -3 -k <2> +------------ ++ +<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 +without a formal "merging". + + +Integrator[[Integrator]] +------------------------ + +A fairly central person acting as the integrator in a group +project receives changes made by others, reviews and integrates +them and publishes the result for others to use, using these +commands in addition to the ones needed by participants. + + * gitlink:git-am[1] to apply patches e-mailed in from your + contributors. + + * gitlink:git-pull[1] to merge from your trusted lieutenants. + + * gitlink:git-format-patch[1] to prepare and send suggested + alternative to contributors. + + * gitlink:git-revert[1] to undo botched commits. + + * gitlink:git-push[1] to publish the bleeding edge. + + +Examples +~~~~~~~~ + +My typical GIT day.:: ++ +------------ +$ git status <1> +$ git show-branch <2> +$ mailx <3> +& s 2 3 4 5 ./+to-apply +& s 7 8 ./+hold-linus +& q +$ 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 next <7> +$ git merge topic/one topic/two && git merge hold/linus <8> +$ git checkout maint +$ git cherry-pick master~4 <9> +$ compile/test +$ git tag -s -m 'GIT 0.99.9x' v0.99.9x <10> +$ git fetch ko && git show-branch master maint 'tags/ko-*' <11> +$ git push ko <12> +$ git push ko v0.99.9x <13> +------------ ++ +<1> see what I was in the middle of doing, if any. +<2> see what topic branches I have and think about how ready +they are. +<3> read mails, save ones that are applicable, and save others +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. +<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 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 +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, and `next` should have +everything `ko-next` has. + +<12> push out the bleeding edge. +<13> push the tag out, too. + + +Repository Administration[[Repository Administration]] +------------------------------------------------------ + +A repository administrator uses the following tools to set up +and maintain access to the repository by developers. + + * gitlink:git-daemon[1] to allow anonymous download from + repository. + + * gitlink:git-shell[1] can be used as a 'restricted login shell' + for shared central repository users. + +link:howto/update-hook-example.txt[update hook howto] has a good +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 --export-all /pub/scm +------------ ++ +The actual configuration line should be on one line. + +Run git-daemon to serve /pub/scm from xinetd.:: ++ +------------ +$ cat /etc/xinetd.d/git-daemon +# default: off +# description: The git server offers access to git repositories +service git +{ + disable = no + type = UNLISTED + port = 9418 + socket_type = stream + wait = no + user = nobody + server = /usr/bin/git-daemon + server_args = --inetd --export-all --base-path=/pub/scm + log_on_failure += USERID +} +------------ ++ +Check your xinetd(8) documentation and setup, this is from a Fedora system. +Others might be different. + +Give push/pull only access to developers.:: ++ +------------ +$ grep git /etc/passwd <1> +alice:x:1000:1000::/home/alice:/usr/bin/git-shell +bob:x:1001:1001::/home/bob:/usr/bin/git-shell +cindy:x:1002:1002::/home/cindy:/usr/bin/git-shell +david:x:1003:1003::/home/david:/usr/bin/git-shell +$ grep git /etc/shells <2> +/usr/bin/git-shell +------------ ++ +<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 +get an ssh access to the machine. +<2> in many distributions /etc/shells needs to list what is used +as the login shell. + +CVS-style shared repository.:: ++ +------------ +$ grep git /etc/group <1> +git:x:9418:alice,bob,cindy,david +$ cd /home/devo.git +$ ls -l <2> + lrwxrwxrwx 1 david git 17 Dec 4 22:40 HEAD -> refs/heads/master + drwxrwsr-x 2 david git 4096 Dec 4 22:40 branches + -rw-rw-r-- 1 david git 84 Dec 4 22:40 config + -rw-rw-r-- 1 david git 58 Dec 4 22:40 description + drwxrwsr-x 2 david git 4096 Dec 4 22:40 hooks + -rw-rw-r-- 1 david git 37504 Dec 4 22:40 index + drwxrwsr-x 2 david git 4096 Dec 4 22:40 info + drwxrwsr-x 4 david git 4096 Dec 4 22:40 objects + drwxrwsr-x 4 david git 4096 Nov 7 14:58 refs + drwxrwsr-x 2 david git 4096 Dec 4 22:40 remotes +$ ls -l hooks/update <3> + -r-xr-xr-x 1 david git 3536 Dec 4 22:40 update +$ cat info/allowed-users <4> +refs/heads/master alice\|cindy +refs/heads/doc-update bob +refs/tags/v[0-9]* david +------------ ++ +<1> place the developers into the same git group. +<2> and make the shared repository writable by the group. +<3> use update-hook example by Carl from Documentation/howto/ +for branch policy control. +<4> alice and cindy can push into master, only bob can push into doc-update. +david is the release manager and is the only person who can +create and push version tags. + +HTTP server to support dumb protocol transfer.:: ++ +------------ +dev$ git update-server-info <1> +dev$ ftp user@isp.example.com <2> +ftp> cp -r .git /home/user/myproject.git +------------ ++ +<1> make sure your info/refs and objects/info/packs are up-to-date +<2> upload to public HTTP server hosted by your ISP. diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt new file mode 100644 index 0000000000..5b4d184a73 --- /dev/null +++ b/Documentation/fetch-options.txt @@ -0,0 +1,48 @@ +-a, \--append:: + Append ref names and object names of fetched refs to the + existing contents of `.git/FETCH_HEAD`. Without this + option old data in `.git/FETCH_HEAD` will be overwritten. + +\--upload-pack <upload-pack>:: + When given, and the repository to fetch from is handled + by 'git-fetch-pack', '--exec=<upload-pack>' is passed to + the command to specify non-default path for the command + run on the other end. + +-f, \--force:: + When `git-fetch` is used with `<rbranch>:<lbranch>` + refspec, it refuses to update the local branch + `<lbranch>` unless the remote branch `<rbranch>` it + fetches is a descendant of `<lbranch>`. This option + overrides that check. + +\--no-tags:: + By default, `git-fetch` fetches tags that point at + objects that are downloaded from the remote repository + and stores them locally. This option disables this + automatic tag following. + +-t, \--tags:: + Most of the tags are fetched automatically as branch + heads are downloaded, but tags that do not point at + objects reachable from the branch heads that are being + tracked will not be fetched by this mechanism. This + flag lets all tags and their associated objects be + downloaded. + +-k, \--keep:: + Keep downloaded pack. + +-u, \--update-head-ok:: + By default `git-fetch` refuses to update the head which + corresponds to the current branch. This flag disables the + 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 new file mode 100644 index 0000000000..755d7186f5 --- /dev/null +++ b/Documentation/git-add.txt @@ -0,0 +1,215 @@ +git-add(1) +========== + +NAME +---- +git-add - Add file contents to the changeset to be committed next + +SYNOPSIS +-------- +'git-add' [-n] [-v] [-f] [--interactive | -i] [--] <file>... + +DESCRIPTION +----------- +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. + + +OPTIONS +------- +<file>...:: + 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. + +-v:: + Be verbose. + +-f:: + Allow adding otherwise ignored files. + +-i, \--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). + + +EXAMPLES +-------- +git-add Documentation/\\*.txt:: + + 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 +subdirectories of `Documentation/` directory. + +git-add git-*.sh:: + + 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 + 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 its +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-mv[1] +gitlink:git-commit[1] +gitlink:git-update-index[1] + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-am.txt b/Documentation/git-am.txt new file mode 100644 index 0000000000..4fb1d84413 --- /dev/null +++ b/Documentation/git-am.txt @@ -0,0 +1,124 @@ +git-am(1) +========= + +NAME +---- +git-am - Apply a series of patches from a mailbox + + +SYNOPSIS +-------- +[verse] +'git-am' [--signoff] [--dotest=<dir>] [--utf8 | --no-utf8] [--binary] [--3way] + [--interactive] [--whitespace=<option>] [-C<n>] [-p<n>] + <mbox>... +'git-am' [--skip | --resolved] + +DESCRIPTION +----------- +Splits mail messages in a mailbox into commit log message, +authorship information and patches, and applies them to the +current branch. + +OPTIONS +------- +<mbox>...:: + The list of mailbox files to read patches from. If you do not + supply this argument, reads from the standard input. + +--signoff:: + Add `Signed-off-by:` line to the commit message, using + the committer identity of yourself. + +--dotest=<dir>:: + Instead of `.dotest` directory, use <dir> as a working + area to store extracted patches. + +--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:: + Pass `--allow-binary-replacement` flag to `git-apply` + (see gitlink:git-apply[1]). + +--3way:: + When the patch does not apply cleanly, fall back on + 3-way merge, if the patch records the identity of blobs + it is supposed to apply to, and we have those blobs + locally. + +--skip:: + Skip the current patch. This is only meaningful when + restarting an aborted patch. + +--whitespace=<option>:: + This flag is passed to the `git-apply` program that applies + the patch. + +-C<n>, -p<n>:: + These flag are passed to the `git-apply` program that applies + the patch. + +--interactive:: + Run interactively, just like git-applymbox. + +--resolved:: + After a patch failure (e.g. attempting to apply + conflicting patch), the user has applied it by hand and + the index file stores the result of the application. + Make a commit using the authorship and commit log + extracted from the e-mail message and the current index + file, and continue. + +DISCUSSION +---------- + +When initially invoking it, you give it names of the mailboxes +to crunch. Upon seeing the first patch that does not apply, it +aborts in the middle, just like 'git-applymbox' does. You can +recover from this in one of two ways: + +. skip the current one by re-running the command with '--skip' + option. + +. hand resolve the conflict in the working directory, and update + the index file to bring it in a state that the patch should + have produced. Then run the command with '--resolved' option. + +The command refuses to process new mailboxes while `.dotest` +directory exists, so if you decide to start over from scratch, +run `rm -f .dotest` before running the command with mailbox +names. + + +SEE ALSO +-------- +gitlink:git-applymbox[1], gitlink:git-applypatch[1], gitlink:git-apply[1]. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Petr Baudis, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-annotate.txt b/Documentation/git-annotate.txt new file mode 100644 index 0000000000..7baf73111b --- /dev/null +++ b/Documentation/git-annotate.txt @@ -0,0 +1,44 @@ +git-annotate(1) +=============== + +NAME +---- +git-annotate - Annotate file lines with commit info + +SYNOPSIS +-------- +git-annotate [options] file [revision] + +DESCRIPTION +----------- +Annotates each line in the given file with information from the commit +which introduced the line. Optionally annotate from a given revision. + +OPTIONS +------- +-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:: + Show help message. + +SEE ALSO +-------- +gitlink:git-blame[1] + +AUTHOR +------ +Written by Ryan Anderson <ryan@michonline.com>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt new file mode 100644 index 0000000000..065ba1bf24 --- /dev/null +++ b/Documentation/git-apply.txt @@ -0,0 +1,185 @@ +git-apply(1) +============ + +NAME +---- +git-apply - Apply a patch on a git index file and a working tree + + +SYNOPSIS +-------- +[verse] +'git-apply' [--stat] [--numstat] [--summary] [--check] [--index] [--apply] + [--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 +----------- +Reads supplied diff output and applies it on a git index file +and a work tree. + +OPTIONS +------- +<patch>...:: + The files to read patch from. '-' can be used to read + from the standard input. + +--stat:: + Instead of applying the patch, output diffstat for the + input. Turns off "apply". + +--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`. Turns off "apply". + +--summary:: + Instead of applying the patch, output a condensed + summary of information obtained from git diff extended + headers, such as creations, renames and mode changes. + Turns off "apply". + +--check:: + Instead of applying the patch, see if the patch is + applicable to the current work tree and/or the index + file and detects errors. Turns off "apply". + +--index:: + When --check is in effect, or when applying the patch + (which is the default when none of the options that + disables it is in effect), make sure the patch is + applicable to what the current index file records. If + the file to be patched in the work tree is not + 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 + the patch applies to. When this flag is given, and if + 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 + this flag, the pathnames output will have TAB, LF, and + backslash characters replaced with `\t`, `\n`, and `\\`, + respectively. + +-p<n>:: + Remove <n> leading slashes from traditional diff paths. The + default is 1. + +-C<n>:: + Ensure at least <n> lines of surrounding context match before + and after each change. When fewer lines of surrounding + 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, 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. + +--no-add:: + When applying a patch, ignore additions made by the + patch. This can be used to extract common part between + two files by first running `diff` on them and applying + the result with this option, which would apply the + deletion part but not addition part. + +--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 + that ends with trailing whitespaces (this includes a + line that solely consists of whitespaces). By default, + the command outputs warning messages and applies the + patch. + 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: ++ +* `nowarn` turns off the trailing whitespace warning. +* `warn` outputs warnings for a few such errors, but applies the + patch (default). +* `error` outputs warnings for a few such errors, and refuses + to apply the patch. +* `error-all` is similar to `error` but shows all errors. +* `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 +------------- + +apply.whitespace:: + When no `--whitespace` flag is given from the command + line, this configuration item is used as the default. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-applymbox.txt b/Documentation/git-applymbox.txt new file mode 100644 index 0000000000..95dc65a583 --- /dev/null +++ b/Documentation/git-applymbox.txt @@ -0,0 +1,92 @@ +git-applymbox(1) +================ + +NAME +---- +git-applymbox - Apply a series of patches in a mailbox + + +SYNOPSIS +-------- +'git-applymbox' [-u] [-k] [-q] [-m] ( -c .dotest/<num> | <mbox> ) [ <signoff> ] + +DESCRIPTION +----------- +Splits mail messages in a mailbox into commit log message, +authorship information and patches, and applies them to the +current branch. + + +OPTIONS +------- +-q:: + Apply patches interactively. The user will be given + opportunity to edit the log message and the patch before + attempting to apply it. + +-k:: + Usually the program 'cleans up' the Subject: header line + to extract the title line for the commit log message, + among which (1) remove 'Re:' or 're:', (2) leading + whitespaces, (3) '[' up to ']', typically '[PATCH]', and + then prepends "[PATCH] ". This flag forbids this + munging, and is most useful when used to read back 'git + format-patch --mbox' output. + +-m:: + Patches are applied with `git-apply` command, and unless + it cleanly applies without fuzz, the processing fails. + With this flag, if a tree that the patch applies cleanly + is found in a repository, the patch is applied to the + tree and then a 3-way merge between the resulting tree + and the current tree. + +-u:: + 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 + apply, the command exits with an error message. The + patch and extracted message are found in .dotest/, and + you could re-run 'git applymbox' with '-c .dotest/<num>' + flag to restart the process after inspecting and fixing + them. + +<mbox>:: + The name of the file that contains the e-mail messages + with patches. This file should be in the UNIX mailbox + format. See 'SubmittingPatches' document to learn about + the formatting convention for e-mail submission. + +<signoff>:: + The name of the file that contains your "Signed-off-by" + line. See 'SubmittingPatches' document to learn what + "Signed-off-by" line means. You can also just say + 'yes', 'true', 'me', or 'please' to use an automatically + generated "Signed-off-by" line based on your committer + identity. + + +SEE ALSO +-------- +gitlink:git-am[1], gitlink:git-applypatch[1]. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-applypatch.txt b/Documentation/git-applypatch.txt new file mode 100644 index 0000000000..451434a757 --- /dev/null +++ b/Documentation/git-applypatch.txt @@ -0,0 +1,53 @@ +git-applypatch(1) +================= + +NAME +---- +git-applypatch - Apply one patch extracted from an e-mail + + +SYNOPSIS +-------- +'git-applypatch' <msg> <patch> <info> [<signoff>] + +DESCRIPTION +----------- +This is usually not what an end user wants to run directly. See +gitlink:git-am[1] instead. + +Takes three files <msg>, <patch>, and <info> prepared from an +e-mail message by 'git-mailinfo', and creates a commit. It is +usually not necessary to use this command directly. + +This command can run `applypatch-msg`, `pre-applypatch`, and +`post-applypatch` hooks. See link:hooks.html[hooks] for more +information. + + +OPTIONS +------- +<msg>:: + Commit log message (sans the first line, which comes + from e-mail Subject stored in <info>). + +<patch>:: + The patch to apply. + +<info>:: + Author and subject information extracted from e-mail, + used on "author" line and as the first line of the + commit log message. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-archimport.txt b/Documentation/git-archimport.txt new file mode 100644 index 0000000000..82cb41d279 --- /dev/null +++ b/Documentation/git-archimport.txt @@ -0,0 +1,121 @@ +git-archimport(1) +================= + +NAME +---- +git-archimport - Import an Arch repository into git + + +SYNOPSIS +-------- +[verse] +'git-archimport' [-h] [-v] [-o] [-a] [-f] [-T] [-D depth] [-t tempdir] + <archive/branch>[:<git-branch>] ... + +DESCRIPTION +----------- +Imports a project from one or more Arch repositories. It will follow branches +and repositories within the namespaces defined by the <archive/branch> +parameters supplied. If it cannot find the remote branch a merge comes from +it will just import it as a regular commit. If it can find it, it will mark it +as a merge whenever possible (see discussion below). + +The script expects you to provide the key roots where it can start the import +from an 'initial import' or 'tag' type of Arch commit. It will follow and +import new branches within the provided roots. + +It expects to be dealing with one project only. If it sees +branches that have different roots, it will refuse to run. In that case, +edit your <archive/branch> parameters to define clearly the scope of the +import. + +`git-archimport` uses `tla` extensively in the background to access the +Arch repository. +Make sure you have a recent version of `tla` available in the path. `tla` must +know about the repositories you pass to `git-archimport`. + +For the initial import `git-archimport` expects to find itself in an empty +directory. To follow the development of a project that uses Arch, rerun +`git-archimport` with the same parameters as the initial import to perform +incremental imports. + +While git-archimport will try to create sensible branch names for the +archives that it imports, it is also possible to specify git branch names +manually. To do so, write a git branch name after each <archive/branch> +parameter, separated by a colon. This way, you can shorten the Arch +branch names and convert Arch jargon to git jargon, for example mapping a +"PROJECT--devo--VERSION" branch to "master". + +Associating multiple Arch branches to one git branch is possible; the +result will make the most sense only if no commits are made to the first +branch, after the second branch is created. Still, this is useful to +convert Arch repositories that had been rotated periodically. + + +MERGES +------ +Patch merge data from Arch is used to mark merges in git as well. git +does not care much about tracking patches, and only considers a merge when a +branch incorporates all the commits since the point they forked. The end result +is that git will have a good idea of how far branches have diverged. So the +import process does lose some patch-trading metadata. + +Fortunately, when you try and merge branches imported from Arch, +git will find a good merge base, and it has a good chance of identifying +patches that have been traded out-of-sequence between the branches. + +OPTIONS +------- + +-h:: + Display usage. + +-v:: + Verbose output. + +-T:: + Many tags. Will create a tag for every commit, reflecting the commit + name in the Arch repository. + +-f:: + Use the fast patchset import strategy. This can be significantly + faster for large trees, but cannot handle directory renames or + permissions changes. The default strategy is slow and safe. + +-o:: + Use this for compatibility with old-style branch names used by + earlier versions of git-archimport. Old-style branch names + were category--branch, whereas new-style branch names are + archive,category--branch--version. In both cases, names given + on the command-line will override the automatically-generated + ones. + +-D <depth>:: + Follow merge ancestry and attempt to import trees that have been + merged from. Specify a depth greater than 1 if patch logs have been + pruned. + +-a:: + Attempt to auto-register archives at http://mirrors.sourcecontrol.net + This is particularly useful with the -D option. + +-t <tmpdir>:: + Override the default tempdir. + + +<archive/branch>:: + Archive/branch identifier in a format that `tla log` understands. + + +Author +------ +Written by Martin Langhoff <martin@catalyst.net.nz>. + +Documentation +-------------- +Documentation by Junio C Hamano, Martin Langhoff and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt new file mode 100644 index 0000000000..493474b2ee --- /dev/null +++ b/Documentation/git-archive.txt @@ -0,0 +1,113 @@ +git-archive(1) +============== + +NAME +---- +git-archive - Creates an archive of files from a 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-bisect.txt b/Documentation/git-bisect.txt new file mode 100644 index 0000000000..16ec7269b2 --- /dev/null +++ b/Documentation/git-bisect.txt @@ -0,0 +1,136 @@ +git-bisect(1) +============= + +NAME +---- +git-bisect - Find the change that introduced a bug by binary search + + +SYNOPSIS +-------- +'git bisect' <subcommand> <options> + +DESCRIPTION +----------- +The command takes various subcommands, and different options +depending on the subcommand: + + git bisect start [<paths>...] + git bisect bad <rev> + git bisect good <rev> + git bisect reset [<branch>] + git bisect visualize + git bisect replay <logfile> + git bisect log + +This command uses 'git-rev-list --bisect' option to help drive +the binary search process to find which change introduced a bug, +given an old "good" commit object name and a later "bad" commit +object name. + +The way you use it is: + +------------------------------------------------ +$ git bisect start +$ git bisect bad # Current version is bad +$ git bisect good v2.6.13-rc2 # v2.6.13-rc2 was the last version + # tested that was good +------------------------------------------------ + +When you give at least one bad and one good versions, it will +bisect the revision tree and say something like: + +------------------------------------------------ +Bisecting: 675 revisions left to test after this +------------------------------------------------ + +and check out the state in the middle. Now, compile that kernel, and boot +it. Now, let's say that this booted kernel works fine, then just do + +------------------------------------------------ +$ git bisect good # this one is good +------------------------------------------------ + +which will now say + +------------------------------------------------ +Bisecting: 337 revisions left to test after this +------------------------------------------------ + +and you continue along, compiling that one, testing it, and depending on +whether it is good or bad, you say "git bisect good" or "git bisect bad", +and ask for the next bisection. + +Until you have no more left, and you'll have been left with the first bad +kernel rev in "refs/bisect/bad". + +Oh, and then after you want to reset to the original head, do a + +------------------------------------------------ +$ git bisect reset +------------------------------------------------ + +to get back to the master branch, instead of being in one of the bisection +branches ("git bisect start" will do that for you too, actually: it will +reset the bisection state, and before it does that it checks that you're +not using some old bisection branch). + +During the bisection process, you can say + +------------ +$ git bisect visualize +------------ + +to see the currently remaining suspects in `gitk`. + +The good/bad input is logged, and `git bisect +log` shows what you have done so far. You can truncate its +output somewhere and save it in a file, and run + +------------ +$ git bisect replay that-file +------------ + +if you find later you made a mistake telling good/bad about a +revision. + +If in a middle of bisect session, you know what the bisect +suggested to try next is not a good one to test (e.g. the change +the commit introduces is known not to work in your environment +and you know it does not have anything to do with the bug you +are chasing), you may want to find a near-by commit and try that +instead. It goes something like this: + +------------ +$ git bisect good/bad # previous round was good/bad. +Bisecting: 337 revisions left to test after this +$ git bisect visualize # oops, that is uninteresting. +$ git reset --hard HEAD~3 # try 3 revs before what + # was suggested +------------ + +Then compile and test the one you chose to try. After that, +tell bisect what the result was as usual. + +You can further cut down the number of trials if you know what +part of the tree is involved in the problem you are tracking +down, by giving paths parameters when you say `bisect start`, +like this: + +------------ +$ git bisect start arch/i386 include/asm-i386 +------------ + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-blame.txt b/Documentation/git-blame.txt new file mode 100644 index 0000000000..5c9888d014 --- /dev/null +++ b/Documentation/git-blame.txt @@ -0,0 +1,223 @@ +git-blame(1) +============ + +NAME +---- +git-blame - Show what revision and author last modified each line of a file + +SYNOPSIS +-------- +[verse] +'git-blame' [-c] [-l] [-t] [-f] [-n] [-p] [--incremental] [-L n,m] [-S <revs-file>] + [-M] [-C] [-C] [--since=<date>] [<rev> | --contents <file>] [--] <file> + +DESCRIPTION +----------- + +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 occurred 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 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). + +-t, --time:: + Show raw timestamp (Default: off). + +-S, --rev-file <revs-file>:: + 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. + +--incremental:: + Show the result incrementally in a format designed for + machine consumption. + +--contents <file>:: + When <rev> is not specified, the command annotates the + changes starting backwards from the working tree copy. + This flag makes the command pretend as if the working + tree copy has the contents of he named file (specify + `-` to make the command read from the standard input). + +-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 minimum 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. + + +SPECIFYING 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 these +(they mean the same thing -- both ask for 21 lines starting at +line 40): + + git blame -L 40,60 foo + git blame -L 40,+21 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 + + +INCREMENTAL OUTPUT +------------------ + +When called with `--incremental` option, the command outputs the +result as it is built. The output generally will talk about +lines touched by more recent commits first (i.e. the lines will +be annotated out of order) and is meant to be used by +interactive viewers. + +The output format is similar to the Porcelain format, but it +does not contain the actual lines from the file that is being +annotated. + +. Each blame entry always starts with a line of: + + <40-byte hex sha1> <sourceline> <resultline> <num_lines> ++ +Line numbers count from 1. + +. The first time that commit shows up in the stream, it has various + other information about it printed out with a one-word tag at the + beginning of each line about that "extended commit info" (author, + email, committer, dates, summary etc). + +. Unlike Porcelain format, the filename information is always + given and terminates the entry: + + "filename" <whitespace-quoted-filename-goes-here> ++ +and thus it's really quite easy to parse for some line- and word-oriented +parser (which should be quite natural for most scripting languages). ++ +[NOTE] +For people who do parsing: to make it more robust, just ignore any +lines in between the first and last one ("<sha1>" and "filename" lines) +where you don't recognize the tag-words (or care about that particular +one) at the beginning of the "extended information" lines. That way, if +there is ever added information (like the commit encoding or extended +commit commentary), a blame viewer won't ever care. + + +SEE ALSO +-------- +gitlink:git-annotate[1] + +AUTHOR +------ +Written by Junio C Hamano <junkio@cox.net> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-branch.txt b/Documentation/git-branch.txt new file mode 100644 index 0000000000..3ea3b80635 --- /dev/null +++ b/Documentation/git-branch.txt @@ -0,0 +1,154 @@ +git-branch(1) +============= + +NAME +---- +git-branch - List, create, or delete branches + +SYNOPSIS +-------- +[verse] +'git-branch' [--color | --no-color] [-r | -a] + [-v [--abbrev=<length> | --no-abbrev]] +'git-branch' [-l] [-f] <branchname> [<start-point>] +'git-branch' (-m | -M) [<oldbranch>] <newbranch> +'git-branch' (-d | -D) [-r] <branchname>... + +DESCRIPTION +----------- +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. Use -r together with -d +to delete remote-tracking branches. + + +OPTIONS +------- +-d:: + Delete a branch. The branch must be fully merged. + +-D:: + Delete a branch irrespective of its index status. + +-l:: + Create the branch's ref log. This activates recording of + all changes to made the branch ref, enabling use of date + based sha1 expressions such as "<branchname>@{yesterday}". + +-f:: + 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 or delete (if used with -d) the remote-tracking branches. + +-a:: + List both remote-tracking branches and local branches. + +-v:: + Show sha1 and commit subject line for each head. + +--abbrev=<length>:: + Alter minimum display length for sha1 in output listing, + default value is 7. + +--no-abbrev:: + Display the full sha1s in output listing rather than abbreviating them. + +<branchname>:: + The name of the branch to create or delete. + The new branch name must pass all checks defined by + gitlink:git-check-ref-format[1]. Some of these checks + may restrict the characters allowed in a branch name. + +<start-point>:: + The new branch will be created with a HEAD equal to this. It may + 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 +-------- + +Start development off of a known tag:: ++ +------------ +$ git clone git://git.kernel.org/pub/scm/.../linux-2.6 my2.6 +$ cd my2.6 +$ git branch my2.6.14 v2.6.14 <1> +$ git checkout my2.6.14 +------------ ++ +<1> This step and the next one could be combined into a single step with +"checkout -b my2.6.14 v2.6.14". + +Delete unneeded branch:: ++ +------------ +$ git clone git://git.kernel.org/.../git.git my.git +$ cd my.git +$ git branch -d -r todo html man <1> +$ git branch -D test <2> +------------ ++ +<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. + + +Notes +----- + +If you are creating a branch that you want to immediately checkout, it's +easier to use the git checkout command with its `-b` option to create +a branch and check it out with a single command. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and 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-bundle.txt b/Documentation/git-bundle.txt new file mode 100644 index 0000000000..92e7a68722 --- /dev/null +++ b/Documentation/git-bundle.txt @@ -0,0 +1,139 @@ +git-bundle(1) +============= + +NAME +---- +git-bundle - Move objects and refs by archive + + +SYNOPSIS +-------- +'git-bundle' create <file> [git-rev-list args] +'git-bundle' verify <file> +'git-bundle' list-heads <file> [refname...] +'git-bundle' unbundle <file> [refname...] + +DESCRIPTION +----------- + +Some workflows require that one or more branches of development on one +machine be replicated on another machine, but the two machines cannot +be directly connected so the interactive git protocols (git, ssh, +rsync, http) cannot be used. This command provides support for +git-fetch and git-pull to operate by packaging objects and references +in an archive at the originating machine, then importing those into +another repository using gitlink:git-fetch[1] and gitlink:git-pull[1] +after moving the archive by some means (i.e., by sneakernet). As no +direct connection between repositories exists, the user must specify a +basis for the bundle that is held by the destination repository: the +bundle assumes that all objects in the basis are already in the +destination repository. + +OPTIONS +------- + +create <file>:: + Used to create a bundle named 'file'. This requires the + git-rev-list arguments to define the bundle contents. + +verify <file>:: + Used to check that a bundle file is valid and will apply + cleanly to the current repository. This includes checks on the + bundle format itself as well as checking that the prerequisite + commits exist and are fully linked in the current repository. + git-bundle prints a list of missing commits, if any, and exits + with non-zero status. + +list-heads <file>:: + Lists the references defined in the bundle. If followed by a + list of references, only references matching those given are + printed out. + +unbundle <file>:: + Passes the objects in the bundle to gitlink:git-index-pack[1] + for storage in the repository, then prints the names of all + defined references. If a reflist is given, only references + matching those in the given list are printed. This command is + really plumbing, intended to be called only by + gitlink:git-fetch[1]. + +[git-rev-list-args...]:: + A list of arguments, acceptable to git-rev-parse and + git-rev-list, that specify the specific objects and references + to transport. For example, "master~10..master" causes the + current master reference to be packaged along with all objects + added since its 10th ancestor commit. There is no explicit + limit to the number of references and objects that may be + packaged. + + +[refname...]:: + A list of references used to limit the references reported as + available. This is principally of use to git-fetch, which + expects to receive only those references asked for and not + necessarily everything in the pack (in this case, git-bundle is + acting like gitlink:git-fetch-pack[1]). + +SPECIFYING REFERENCES +--------------------- + +git-bundle will only package references that are shown by +git-show-ref: this includes heads, tags, and remote heads. References +such as master~1 cannot be packaged, but are perfectly suitable for +defining the basis. More than one reference may be packaged, and more +than one basis can be specified. The objects packaged are those not +contained in the union of the given bases. Each basis can be +specified explicitly (e.g., ^master~10), or implicitly (e.g., +master~10..master, master --since=10.days.ago). + +It is very important that the basis used be held by the destination. +It is okay to err on the side of conservatism, causing the bundle file +to contain objects already in the destination as these are ignored +when unpacking at the destination. + +EXAMPLE +------- + +Assume two repositories exist as R1 on machine A, and R2 on machine B. +For whatever reason, direct connection between A and B is not allowed, +but we can move data from A to B via some mechanism (CD, email, etc). +We want to update R2 with developments made on branch master in R1. +We set a tag in R1 (lastR2bundle) after the previous such transport, +and move it afterwards to help build the bundle. + +in R1 on A: +$ git-bundle create mybundle master ^lastR2bundle +$ git tag -f lastR2bundle master + +(move mybundle from A to B by some mechanism) + +in R2 on B: +$ git-bundle verify mybundle +$ git-fetch mybundle refspec + +where refspec is refInBundle:localRef + + +Also, with something like this in your config: + +[remote "bundle"] + url = /home/me/tmp/file.bdl + fetch = refs/heads/*:refs/remotes/origin/* + +You can first sneakernet the bundle file to ~/tmp/file.bdl and +then these commands: + +$ git ls-remote bundle +$ git fetch bundle +$ git pull bundle + +would treat it as if it is talking with a remote side over the +network. + +Author +------ +Written by Mark Levedahl <mdl123@verizon.net> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt new file mode 100644 index 0000000000..075c0d05ef --- /dev/null +++ b/Documentation/git-cat-file.txt @@ -0,0 +1,74 @@ +git-cat-file(1) +=============== + +NAME +---- +git-cat-file - Provide content or type/size information for repository objects + + +SYNOPSIS +-------- +'git-cat-file' [-t | -s | -e | -p | <type>] <object> + +DESCRIPTION +----------- +Provides content or type of objects in the repository. The type +is required unless '-t' or '-p' is used to find the object type, +or '-s' is used to find the object size. + +OPTIONS +------- +<object>:: + The name of the object to show. + For a more complete list of ways to spell object names, see + "SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + +-t:: + Instead of the content, show the object type identified by + <object>. + +-s:: + Instead of the content, show the object size identified by + <object>. + +-e:: + Suppress all output; instead exit with zero status if <object> + exists and is a valid object. + +-p:: + Pretty-print the contents of <object> based on its type. + +<type>:: + Typically this matches the real type of <object> but asking + for a type that can trivially be dereferenced from the given + <object> is also permitted. An example is to ask for a + "tree" with <object> being a commit object that contains it, + or to ask for a "blob" with <object> being a tag object that + points at it. + +OUTPUT +------ +If '-t' is specified, one of the <type>. + +If '-s' is specified, the size of the <object> in bytes. + +If '-e' is specified, no output. + +If '-p' is specified, the contents of <object> are pretty-printed. + +Otherwise the raw (though uncompressed) contents of the <object> will +be returned. + + +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-check-ref-format.txt b/Documentation/git-check-ref-format.txt new file mode 100644 index 0000000000..13a5f43049 --- /dev/null +++ b/Documentation/git-check-ref-format.txt @@ -0,0 +1,55 @@ +git-check-ref-format(1) +======================= + +NAME +---- +git-check-ref-format - Make sure ref name is well formed + +SYNOPSIS +-------- +'git-check-ref-format' <refname> + +DESCRIPTION +----------- +Checks if a given 'refname' is acceptable, and exits non-zero if +it is not. + +A reference is used in git to specify branches and tags. A +branch head is stored under `$GIT_DIR/refs/heads` directory, and +a tag is stored under `$GIT_DIR/refs/tags` directory. git +imposes the following rules on how refs are named: + +. It can include slash `/` for hierarchical (directory) + grouping, but no slash-separated component can begin with a + dot `.`; + +. It cannot have two consecutive dots `..` anywhere; + +. It cannot have ASCII control character (i.e. bytes whose + values are lower than \040, or \177 `DEL`), space, tilde `~`, + caret `{caret}`, colon `:`, question-mark `?`, asterisk `*`, + or open bracket `[` anywhere; + +. It cannot end with a slash `/`. + +These rules makes it easy for shell script based tools to parse +refnames, pathname expansion by the shell when a refname is used +unquoted (by mistake), and also avoids ambiguities in certain +refname expressions (see gitlink:git-rev-parse[1]). Namely: + +. double-dot `..` are often used as in `ref1..ref2`, and in some + context this notation means `{caret}ref1 ref2` (i.e. not in + ref1 and in ref2). + +. tilde `~` and caret `{caret}` are used to introduce postfix + 'nth parent' and 'peel onion' operation. + +. colon `:` is used as in `srcref:dstref` to mean "use srcref\'s + value and store it in dstref" in fetch and push operations. + It may also be used to select a specific object such as with + gitlink:git-cat-file[1] "git-cat-file blob v1.3.3:refs.c". + + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-checkout-index.txt b/Documentation/git-checkout-index.txt new file mode 100644 index 0000000000..6dd6db04bb --- /dev/null +++ b/Documentation/git-checkout-index.txt @@ -0,0 +1,185 @@ +git-checkout-index(1) +===================== + +NAME +---- +git-checkout-index - Copy files from the index to the working tree + + +SYNOPSIS +-------- +[verse] +'git-checkout-index' [-u] [-q] [-a] [-f] [-n] [--prefix=<string>] + [--stage=<number>|all] + [--temp] + [-z] [--stdin] + [--] [<file>]\* + +DESCRIPTION +----------- +Will copy all files listed from the index to the working directory +(not overwriting existing files). + +OPTIONS +------- +-u|--index:: + update stat information for the checked out entries in + the index file. + +-q|--quiet:: + be quiet if files exist or are not in the index + +-f|--force:: + forces overwrite of existing files + +-a|--all:: + checks out all files in the index. Cannot be used + together with explicit filenames. + +-n|--no-create:: + Don't checkout new files, only refresh files already checked + out. + +--prefix=<string>:: + When creating files, prepend <string> (usually a directory + including a trailing /) + +--stage=<number>|all:: + Instead of checking out unmerged entries, copy out the + files from named stage. <number> must be between 1 and 3. + Note: --stage=all automatically implies --temp. + +--temp:: + Instead of copying the files to the working directory + write the content to temporary files. The temporary name + associations will be written to stdout. + +--stdin:: + Instead of taking list of paths from the command line, + read list of paths from the standard input. Paths are + separated by LF (i.e. one path per line) by default. + +-z:: + Only meaningful with `--stdin`; paths are separated with + NUL character instead of LF. + +\--:: + Do not interpret any more arguments as options. + +The order of the flags used to matter, but not anymore. + +Just doing `git-checkout-index` does nothing. You probably meant +`git-checkout-index -a`. And if you want to force it, you want +`git-checkout-index -f -a`. + +Intuitiveness is not the goal here. Repeatability is. The reason for +the "no arguments means no work" behavior is that from scripts you are +supposed to be able to do: + +---------------- +$ find . -name '*.h' -print0 | xargs -0 git-checkout-index -f -- +---------------- + +which will force all existing `*.h` files to be replaced with their +cached copies. If an empty command line implied "all", then this would +force-refresh everything in the index, which was not the point. But +since git-checkout-index accepts --stdin it would be faster to use: + +---------------- +$ find . -name '*.h' -print0 | git-checkout-index -f -z --stdin +---------------- + +The `--` is just a good idea when you know the rest will be filenames; +it will prevent problems with a filename of, for example, `-a`. +Using `--` is probably a good policy in scripts. + + +Using --temp or --stage=all +--------------------------- +When `--temp` is used (or implied by `--stage=all`) +`git-checkout-index` will create a temporary file for each index +entry being checked out. The index will not be updated with stat +information. These options can be useful if the caller needs all +stages of all unmerged entries so that the unmerged files can be +processed by an external merge tool. + +A listing will be written to stdout providing the association of +temporary file names to tracked path names. The listing format +has two variations: + + . tempname TAB path RS ++ +The first format is what gets used when `--stage` is omitted or +is not `--stage=all`. The field tempname is the temporary file +name holding the file content and path is the tracked path name in +the index. Only the requested entries are output. + + . stage1temp SP stage2temp SP stage3tmp TAB path RS ++ +The second format is what gets used when `--stage=all`. The three +stage temporary fields (stage1temp, stage2temp, stage3temp) list the +name of the temporary file if there is a stage entry in the index +or `.` if there is no stage entry. Paths which only have a stage 0 +entry will always be omitted from the output. + +In both formats RS (the record separator) is newline by default +but will be the null byte if -z was passed on the command line. +The temporary file names are always safe strings; they will never +contain directory separators or whitespace characters. The path +field is always relative to the current directory and the temporary +file names are always relative to the top level directory. + +If the object being copied out to a temporary file is a symbolic +link the content of the link will be written to a normal file. It is +up to the end-user or the Porcelain to make use of this information. + + +EXAMPLES +-------- +To update and refresh only the files already checked out:: ++ +---------------- +$ git-checkout-index -n -f -a && git-update-index --ignore-missing --refresh +---------------- + +Using `git-checkout-index` to "export an entire tree":: + The prefix ability basically makes it trivial to use + `git-checkout-index` as an "export as tree" function. + Just read the desired tree into the index, and do: ++ +---------------- +$ git-checkout-index --prefix=git-export-dir/ -a +---------------- ++ +`git-checkout-index` will "export" the index into the specified +directory. ++ +The final "/" is important. The exported name is literally just +prefixed with the specified string. Contrast this with the +following example. + +Export files with a prefix:: ++ +---------------- +$ git-checkout-index --prefix=.merged- Makefile +---------------- ++ +This will check out the currently cached copy of `Makefile` +into the file `.merged-Makefile`. + + +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-checkout.txt b/Documentation/git-checkout.txt new file mode 100644 index 0000000000..1ae77be450 --- /dev/null +++ b/Documentation/git-checkout.txt @@ -0,0 +1,202 @@ +git-checkout(1) +=============== + +NAME +---- +git-checkout - Checkout and switch to a branch + +SYNOPSIS +-------- +[verse] +'git-checkout' [-q] [-f] [-b <new_branch> [-l]] [-m] [<branch>] +'git-checkout' [<tree-ish>] <paths>... + +DESCRIPTION +----------- + +When <paths> are not given, this command switches branches by +updating the index and working tree to reflect the specified +branch, <branch>, and updating HEAD to be <branch> or, if +specified, <new_branch>. Using -b will cause <new_branch> to +be created. + +When <paths> are given, this command does *not* switch +branches. It updates the named paths in the working tree from +the index file (i.e. it runs `git-checkout-index -f -u`), or a +named commit. In +this case, `-f` and `-b` options are meaningless and giving +either of them results in an error. <tree-ish> argument can be +used to specify a specific tree-ish (i.e. commit, tag or tree) +to update the index for the given paths before updating the +working tree. + + +OPTIONS +------- +-q:: + Quiet, supress feedback messages. + +-f:: + Force a re-read of everything. + +-b:: + Create a new branch named <new_branch> and start it at + <branch>. The new branch name must pass all checks defined + by gitlink:git-check-ref-format[1]. Some of these checks + may restrict the characters allowed in a branch name. + +-l:: + Create the new branch's ref log. This activates recording of + all changes to made the branch ref, enabling use of date + based sha1 expressions such as "<branchname>@{yesterday}". + +-m:: + If you have local modifications to one or more files that + are different between the current branch and the branch to + which you are switching, the command refuses to switch + branches in order to preserve your modifications in context. + However, with this option, a three-way merge between the current + branch, your working tree contents, and the new branch + is done, and you will be on the new branch. ++ +When a merge conflict happens, the index entries for conflicting +paths are left unmerged, and you need to resolve the conflicts +and mark the resolved paths with `git add` (or `git rm` if the merge +should result in deletion of the path). + +<new_branch>:: + Name for the new branch. + +<branch>:: + Branch to checkout; may be any object ID that resolves to a + commit. Defaults to HEAD. ++ +When this parameter names a non-branch (but still a valid commit object), +your HEAD becomes 'detached'. + + +Detached HEAD +------------- + +It is sometimes useful to be able to 'checkout' a commit that is +not at the tip of one of your branches. The most obvious +example is to check out the commit at a tagged official release +point, like this: + +------------ +$ git checkout v2.6.18 +------------ + +Earlier versions of git did not allow this and asked you to +create a temporary branch using `-b` option, but starting from +version 1.5.0, the above command 'detaches' your HEAD from the +current branch and directly point at the commit named by the tag +(`v2.6.18` in the above example). + +You can use usual git commands while in this state. You can use +`git-reset --hard $othercommit` to further move around, for +example. You can make changes and create a new commit on top of +a detached HEAD. You can even create a merge by using `git +merge $othercommit`. + +The state you are in while your HEAD is detached is not recorded +by any branch (which is natural --- you are not on any branch). +What this means is that you can discard your temporary commits +and merges by switching back to an existing branch (e.g. `git +checkout master`), and a later `git prune` or `git gc` would +garbage-collect them. If you did this by mistake, you can ask +the reflog for HEAD where you were, e.g. + +------------ +$ git log -g -2 HEAD +------------ + + +EXAMPLES +-------- + +. The following sequence checks out the `master` branch, reverts +the `Makefile` to two revisions back, deletes hello.c by +mistake, and gets it back from the index. ++ +------------ +$ git checkout master <1> +$ git checkout master~2 Makefile <2> +$ rm -f hello.c +$ git checkout hello.c <3> +------------ ++ +<1> switch branch +<2> take out a file out of other commit +<3> restore hello.c from HEAD of current branch ++ +If you have an unfortunate branch that is named `hello.c`, this +step would be confused as an instruction to switch to that branch. +You should instead write: ++ +------------ +$ git checkout -- hello.c +------------ + +. After working in a wrong branch, switching to the correct +branch would be done using: ++ +------------ +$ git checkout mytopic +------------ ++ +However, your "wrong" branch and correct "mytopic" branch may +differ in files that you have locally modified, in which case, +the above checkout would fail like this: ++ +------------ +$ git checkout mytopic +fatal: Entry 'frotz' not uptodate. Cannot merge. +------------ ++ +You can give the `-m` flag to the command, which would try a +three-way merge: ++ +------------ +$ git checkout -m mytopic +Auto-merging frotz +------------ ++ +After this three-way merge, the local modifications are _not_ +registered in your index file, so `git diff` would show you what +changes you made since the tip of the new branch. + +. When a merge conflict happens during switching branches with +the `-m` option, you would see something like this: ++ +------------ +$ git checkout -m mytopic +Auto-merging frotz +merge: warning: conflicts during merge +ERROR: Merge conflict in frotz +fatal: merge program failed +------------ ++ +At this point, `git diff` shows the changes cleanly merged as in +the previous example, as well as the changes in the conflicted +files. Edit and resolve the conflict and mark it resolved with +`git add` as usual: ++ +------------ +$ edit frotz +$ git add frotz +------------ + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-cherry-pick.txt b/Documentation/git-cherry-pick.txt new file mode 100644 index 0000000000..3149d08da8 --- /dev/null +++ b/Documentation/git-cherry-pick.txt @@ -0,0 +1,71 @@ +git-cherry-pick(1) +================== + +NAME +---- +git-cherry-pick - Apply the change introduced by an existing commit + +SYNOPSIS +-------- +'git-cherry-pick' [--edit] [-n] [-x] <commit> + +DESCRIPTION +----------- +Given one existing commit, apply the change the patch introduces, and record a +new commit that records it. This requires your working tree to be clean (no +modifications from the HEAD commit). + +OPTIONS +------- +<commit>:: + Commit to cherry-pick. + For a more complete list of ways to spell commits, see + "SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + +-e|--edit:: + With this option, `git-cherry-pick` will let you edit the commit + message prior committing. + +-x:: + Cause the command to append which commit was + cherry-picked after the original commit message when + 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 + a commit log message stating which commit was + cherry-picked. This flag applies the change necessary + to cherry-pick the named commit to your working tree, + but does not make the commit. In addition, when this + option is used, your working tree does not have to match + the HEAD commit. The cherry-pick is done against the + beginning state of your working tree. ++ +This is useful when cherry-picking more than one commits' +effect to your working tree in a row. + + +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-cherry.txt b/Documentation/git-cherry.txt new file mode 100644 index 0000000000..27b67b81a5 --- /dev/null +++ b/Documentation/git-cherry.txt @@ -0,0 +1,67 @@ +git-cherry(1) +============= + +NAME +---- +git-cherry - Find commits not merged upstream + +SYNOPSIS +-------- +'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 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: + + __*__*__*__*__> <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 +has been applied <upstream> under a different commit id. For example, +this will happen if you're feeding patches <upstream> via email rather +than pushing or pulling commits directly. + + +OPTIONS +------- +-v:: + Verbose. + +<upstream>:: + Upstream branch to compare against. + +<head>:: + Working branch; defaults to HEAD. + +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-clean.txt b/Documentation/git-clean.txt new file mode 100644 index 0000000000..c61afbcdba --- /dev/null +++ b/Documentation/git-clean.txt @@ -0,0 +1,53 @@ +git-clean(1) +============ + +NAME +---- +git-clean - Remove untracked files from the working tree + +SYNOPSIS +-------- +[verse] +'git-clean' [-d] [-n] [-q] [-x | -X] [--] <paths>... + +DESCRIPTION +----------- +Removes files unknown to git. This allows to clean the working tree +from files that are not under version control. If the '-x' option is +specified, ignored files are also removed, allowing to remove all +build products. +When optional `<paths>...` arguments are given, the paths +affected are further limited to those that match them. + + +OPTIONS +------- +-d:: + Remove untracked directories in addition to untracked files. + +-n:: + Don't actually remove anything, just show what would be done. + +-q:: + Be quiet, only report errors, but not the files that are + successfully removed. + +-x:: + Don't use the ignore rules. This allows removing all untracked + files, including build products. This can be used (possibly in + conjunction with gitlink:git-reset[1]) to create a pristine + working directory to test a clean build. + +-X:: + Remove only files ignored by git. This may be useful to rebuild + everything from scratch, but keep manually created files. + + +Author +------ +Written by Pavel Roskin <proski@gnu.org> + + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt new file mode 100644 index 0000000000..6d32c491a5 --- /dev/null +++ b/Documentation/git-clone.txt @@ -0,0 +1,178 @@ +git-clone(1) +============ + +NAME +---- +git-clone - Clones a repository into a new directory + + +SYNOPSIS +-------- +[verse] +'git-clone' [--template=<template_directory>] [-l [-s]] [-q] [-n] [--bare] + [-o <name>] [-u <upload-pack>] [--reference <repository>] + [--depth <depth>] <repository> [<directory>] + +DESCRIPTION +----------- + +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. + +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 default configuration is achieved by creating references to +the remote branch heads under `$GIT_DIR/refs/remotes/origin` and +by initializing `remote.origin.url` and `remote.origin.fetch` +configuration variables. + + +OPTIONS +------- +--local:: +-l:: + When the repository to clone from is on a local machine, + this flag bypasses normal "git aware" transport + mechanism and clones the repository by making a copy of + HEAD and everything under objects and refs directories. + The files under .git/objects/ directory are hardlinked + to save space when possible. + +--shared:: +-s:: + When the repository to clone is on the local machine, + instead of using hard links, automatically setup + .git/objects/info/alternates to share the objects + with the source repository. The resulting repository + starts out without any object of its own. + +--reference <repository>:: + If the reference repository is on the local machine + automatically setup .git/objects/info/alternates to + obtain objects from the reference repository. Using + an already existing repository as an alternate will + require less objects to be copied from the repository + being cloned, reducing network and local storage costs. + +--quiet:: +-q:: + Operate quietly. This flag is passed to "rsync" and + "git-fetch-pack" commands when given. + +-n:: + No checkout of HEAD is performed after the clone is complete. + +--bare:: + Make a 'bare' GIT repository. That is, instead of + creating `<directory>` and placing the administrative + files in `<directory>/.git`, make the `<directory>` + itself the `$GIT_DIR`. This 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 remote name 'origin' to keep track + of the upstream repository, use <name> instead. + +--upload-pack <upload-pack>:: +-u <upload-pack>:: + When given, and the repository to clone from is handled + by 'git-fetch-pack', '--exec=<upload-pack>' is passed to + the command to specify non-default path for the command + run on the other end. + +--template=<template_directory>:: + Specify the directory from which templates will be used; + if unset the templates are taken from the installation + defined default, typically `/usr/share/git-core/templates`. + +--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 + be any URL git-fetch supports. + +<directory>:: + The name of a new directory to clone into. The "humanish" + part of the source repository is used if no directory is + explicitly given ("repo" for "/path/to/repo.git" and "foo" + for "host.xz:foo/.git"). Cloning into an existing directory + is not allowed. + +Examples +-------- + +Clone from upstream:: ++ +------------ +$ git clone git://git.kernel.org/pub/scm/.../linux-2.6 my2.6 +$ cd my2.6 +$ make +------------ + + +Make a local clone that borrows from the current directory, without checking things out:: ++ +------------ +$ git clone -l -s -n . ../copy +$ cd copy +$ git show-branch +------------ + + +Clone from upstream while borrowing from an existing local directory:: ++ +------------ +$ git clone --reference my2.6 \ + git://git.kernel.org/pub/scm/.../linux-2.7 \ + my2.7 +$ cd my2.7 +------------ + + +Create a bare repository to publish your changes to the public:: ++ +------------ +$ git clone --bare -l /home/proj/.git /pub/scm/proj.git +------------ + + +Create a repository on the kernel.org machine that borrows from Linus:: ++ +------------ +$ git clone --bare -l -s /pub/scm/.../torvalds/linux-2.6.git \ + /pub/scm/.../me/subsys-2.6.git +------------ + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + + +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-commit-tree.txt b/Documentation/git-commit-tree.txt new file mode 100644 index 0000000000..cf25507f8f --- /dev/null +++ b/Documentation/git-commit-tree.txt @@ -0,0 +1,108 @@ +git-commit-tree(1) +================== + +NAME +---- +git-commit-tree - Create a new commit object + + +SYNOPSIS +-------- +'git-commit-tree' <tree> [-p <parent commit>]\* < changelog + +DESCRIPTION +----------- +This is usually not what an end user wants to run directly. See +gitlink:git-commit[1] instead. + +Creates a new commit object based on the provided tree object and +emits the new commit object id on stdout. If no parent is given then +it is considered to be an initial tree. + +A commit object usually has 1 parent (a commit after a change) or up +to 16 parents. More than one parent represents a merge of branches +that led to them. + +While a tree represents a particular directory state of a working +directory, a commit represents that state in "time", and explains how +to get there. + +Normally a commit would identify a new "HEAD" state, and while git +doesn't care where you save the note about that state, in practice we +tend to just write the result to the file that is pointed at by +`.git/HEAD`, so that we can always see what the last committed +state was. + +OPTIONS +------- +<tree>:: + An existing tree object + +-p <parent commit>:: + Each '-p' indicates the id of a parent commit object. + + +Commit Information +------------------ + +A commit encapsulates: + +- all parent object ids +- author name, email and date +- committer name and email and the commit time. + +If not provided, "git-commit-tree" uses your name, hostname and domain to +provide author and committer info. This can be overridden by +either `.git/config` file, or using the following environment variables. + + GIT_AUTHOR_NAME + GIT_AUTHOR_EMAIL + GIT_AUTHOR_DATE + GIT_COMMITTER_NAME + GIT_COMMITTER_EMAIL + +(nb "<", ">" and "\n"s are stripped) + +In `.git/config` file, the following items are used for GIT_AUTHOR_NAME and +GIT_AUTHOR_EMAIL: + + [user] + name = "Your Name" + email = "your@email.address.xz" + +A commit comment is read from stdin (max 999 chars). If a changelog +entry is not provided via "<" redirection, "git-commit-tree" will just wait +for one to be entered and terminated with ^D. + + +Diagnostics +----------- +You don't exist. Go away!:: + The passwd(5) gecos field couldn't be read +Your parents must have hated you!:: + The password(5) gecos field is longer than a giant static buffer. +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] + + +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-commit.txt b/Documentation/git-commit.txt new file mode 100644 index 0000000000..53a7bb0895 --- /dev/null +++ b/Documentation/git-commit.txt @@ -0,0 +1,262 @@ +git-commit(1) +============= + +NAME +---- +git-commit - Record changes to the repository + +SYNOPSIS +-------- +[verse] +'git-commit' [-a | --interactive] [-s] [-v] + [(-c | -C) <commit> | -F <file> | -m <msg> | --amend] + [--no-verify] [-e] [--author <author>] + [--] [[-i | -o ]<file>...] + +DESCRIPTION +----------- +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: + +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. + +5. by using the --interactive switch with the 'commit' command to decide one + by one which files should be part of the commit, before finalizing the + operation. Currently, this is done by invoking `git-add --interactive`. + +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]. + + +OPTIONS +------- +-a|--all:: + 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 + and the authorship information (including the timestamp) + when creating the commit. With '-C', the editor is not + invoked; with '-c' the user can further edit the commit + message. + +-F <file>:: + Take the commit message from the given file. Use '-' to + read the message from the standard input. + +--author <author>:: + Override the author name used in the commit. Use + `A U Thor <author@example.com>` format. + +-m <msg>:: + Use the given <msg> as the commit message. + +-s|--signoff:: + Add Signed-off-by line at the end of the commit message. + +--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 + `-m`, and from file with `-C` are usually used as the + commit log message unmodified. This option lets you + further edit the message taken from these sources. + +--amend:: + + Used to amend the tip of the current branch. Prepare the tree + object you would want to replace the latest commit as usual + (this includes the usual -i/-o and explicit paths), and the + commit log editor is seeded with the commit message from the + tip of the current branch. The commit you create replaces the + current tip -- if it was a merge, it will have the parents of + the current tip as parents -- so the current top commit is + discarded. ++ +-- +It is a rough equivalent for: +------ + $ git reset --soft HEAD^ + $ ... do something else to come up with the right tree ... + $ git commit -c ORIG_HEAD + +------ +but can be used to amend a merge commit. +-- + +-i|--include:: + 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. + +-q|--quiet:: + Suppress commit summary message. + +\--:: + Do not interpret any more arguments as options. + +<file>...:: + 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. + + +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 +------------ + +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 +---------- + +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 commit in the body. + +include::i18n.txt[] + +ENVIRONMENT VARIABLES +--------------------- +The command specified by either the VISUAL or EDITOR environment +variables is used to edit the commit log message. + +HOOKS +----- +This command can run `commit-msg`, `pre-commit`, and +`post-commit` hooks. See link:hooks.html[hooks] for more +information. + + +SEE ALSO +-------- +gitlink:git-add[1], +gitlink:git-rm[1], +gitlink:git-mv[1], +gitlink:git-merge[1], +gitlink:git-commit-tree[1] + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +Junio C Hamano <junkio@cox.net> + + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-config.txt b/Documentation/git-config.txt new file mode 100644 index 0000000000..68de5881bd --- /dev/null +++ b/Documentation/git-config.txt @@ -0,0 +1,235 @@ +git-config(1) +============= + +NAME +---- +git-config - Get and set repository or global options + + +SYNOPSIS +-------- +[verse] +'git-config' [--global] [type] name [value [value_regex]] +'git-config' [--global] [type] --add name value +'git-config' [--global] [type] --replace-all name [value [value_regex]] +'git-config' [--global] [type] --get name [value_regex] +'git-config' [--global] [type] --get-all name [value_regex] +'git-config' [--global] [type] --unset name [value_regex] +'git-config' [--global] [type] --unset-all name [value_regex] +'git-config' [--global] [type] --rename-section old_name new_name +'git-config' [--global] [type] --remove-section name +'git-config' [--global] -l | --list + +DESCRIPTION +----------- +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. + +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 +prepend a single exclamation mark in front (see EXAMPLES). + +The type specifier can be either '--int' or '--bool', which will make +'git-config' ensure that the variable(s) are of the given type and +convert the value to the canonical form (simple decimal number for int, +a "true" or "false" string for bool). If no type specifier is passed, +no checks or transformations are performed on the value. + +This command will fail if: + +. The .git/config file is invalid, +. 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, +. you try to unset/set an option for which multiple lines match, or +. you use --global option without $HOME being properly set. + + +OPTIONS +------- + +--replace-all:: + Default behavior is to replace at most one line. This replaces + all lines matching the key (and optionally the value_regex). + +--add:: + Adds a new line to the option without altering any existing + values. This is the same as providing '^$' as the value_regex. + +--get:: + Get the value for a given key (optionally filtered by a regex + matching the value). 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 + is not exactly one. + +--get-regexp:: + Like --get-all, but interprets the name as a regular expression. + +--global:: + Use global ~/.gitconfig file rather than the repository .git/config. + +--remove-section:: + Remove the given section from the configuration file. + +--rename-section:: + Rename the given section to a new name. + +--unset:: + Remove the line matching the key from config file. + +--unset-all:: + Remove all matching lines from config file. + +-l, --list:: + List all variables set in config file. + +--bool:: + git-config will ensure that the output is "true" or "false" + +--int:: + git-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 +----------- + +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 $GIT_CONFIG; when Git will support global + configuration files, this will cause it to take the configuration + from the global configuration file in addition to the given file. + + +EXAMPLE +------- + +Given a .git/config like this: + + # + # This is the config file, and + # a '#' or ';' character indicates + # a comment + # + + ; core variables + [core] + ; Don't trust file modes + filemode = false + + ; Our diff algorithm + [diff] + external = "/usr/local/bin/gnu-diff -u" + renames = true + + ; Proxy settings + [core] + gitproxy="ssh" for "ssh://kernel.org/" + gitproxy="proxy-command" for kernel.org + gitproxy="myprotocol-command" for "my://" + gitproxy=default-proxy ; for all the rest + +you can set the filemode to true with + +------------ +% git config core.filemode true +------------ + +The hypothetical proxy command entries actually have a postfix to discern +what URL they apply to. Here is how to change the entry for kernel.org +to "ssh". + +------------ +% git config core.gitproxy '"ssh" for kernel.org' 'for kernel.org$' +------------ + +This makes sure that only the key/value pair for kernel.org is replaced. + +To delete the entry for renames, do + +------------ +% git config --unset diff.renames +------------ + +If you want to delete an entry for a multivar (like core.gitproxy above), +you have to provide a regex matching the value of exactly one line. + +To query the value for a given key, do + +------------ +% git config --get core.filemode +------------ + +or + +------------ +% git config core.filemode +------------ + +or, to query a multivar: + +------------ +% git config --get core.gitproxy "for kernel.org$" +------------ + +If you want to know all the values for a multivar, do: + +------------ +% git config --get-all core.gitproxy +------------ + +If you like to live dangerous, you can replace *all* core.gitproxy by a +new one with + +------------ +% git config --replace-all core.gitproxy ssh +------------ + +However, if you really only want to replace the line for the default proxy, +i.e. the one without a "for ..." postfix, do something like this: + +------------ +% git config core.gitproxy ssh '! for ' +------------ + +To actually match only values with an exclamation mark, you have to + +------------ +% git config section.key value '[!]' +------------ + +To add a new proxy, without altering any of the existing ones, use + +------------ +% git config core.gitproxy '"proxy" for example.com' +------------ + + +include::config.txt[] + + +Author +------ +Written by Johannes Schindelin <Johannes.Schindelin@gmx.de> + +Documentation +-------------- +Documentation by Johannes Schindelin, Petr Baudis and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-convert-objects.txt b/Documentation/git-convert-objects.txt new file mode 100644 index 0000000000..b1220c06e1 --- /dev/null +++ b/Documentation/git-convert-objects.txt @@ -0,0 +1,29 @@ +git-convert-objects(1) +====================== + +NAME +---- +git-convert-objects - Converts old-style git repository + + +SYNOPSIS +-------- +'git-convert-objects' + +DESCRIPTION +----------- +Converts old-style git repository to the latest format + + +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-count-objects.txt b/Documentation/git-count-objects.txt new file mode 100644 index 0000000000..91c8c92c76 --- /dev/null +++ b/Documentation/git-count-objects.txt @@ -0,0 +1,38 @@ +git-count-objects(1) +==================== + +NAME +---- +git-count-objects - Count unpacked number of objects and their disk consumption + +SYNOPSIS +-------- +'git-count-objects' [-v] + +DESCRIPTION +----------- +This counts the number of unpacked object files and disk space consumed by +them, to help you decide when it is a good time to repack. + + +OPTIONS +------- +-v:: + In addition to the number of loose objects and disk + space consumed, it reports the number of in-pack + objects, number of packs, and number of objects that can be + removed by running `git-prune-packed`. + + +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-cvsexportcommit.txt b/Documentation/git-cvsexportcommit.txt new file mode 100644 index 0000000000..555b8234f0 --- /dev/null +++ b/Documentation/git-cvsexportcommit.txt @@ -0,0 +1,95 @@ +git-cvsexportcommit(1) +====================== + +NAME +---- +git-cvsexportcommit - Export a single commit to a CVS checkout + + +SYNOPSIS +-------- +'git-cvsexportcommit' [-h] [-v] [-c] [-P] [-p] [-a] [-d cvsroot] [-f] [-m msgprefix] [PARENTCOMMIT] COMMITID + + +DESCRIPTION +----------- +Exports a commit from GIT to a CVS checkout, making it easier +to merge patches from a git repository into a CVS repository. + +Execute it from the root of the CVS working copy. GIT_DIR must be defined. +See examples below. + +It does its best to do the safe thing, it will check that the files are +unchanged and up to date in the CVS checkout, and it will not autocommit +by default. + +Supports file additions, removals, and commits that affect binary files. + +If the commit is a merge commit, you must tell git-cvsapplycommit what parent +should the changeset be done against. + +OPTIONS +------- + +-c:: + Commit automatically if the patch applied cleanly. It will not + commit if any hunks fail to apply or there were other problems. + +-p:: + Be pedantic (paranoid) when applying patches. Invokes patch with + --fuzz=0 + +-a:: + Add authorship information. Adds Author line, and Committer (if + different from Author) to the message. + +-d:: + Set an alternative CVSROOT to use. This corresponds to the CVS + -d parameter. Usually users will not want to set this, except + if using CVS in an asymmetric fashion. + +-f:: + Force the merge even if the files are not up to date. + +-P:: + Force the parent commit, even if it is not a direct parent. + +-m:: + Prepend the commit message with the provided prefix. + Useful for patch series and the like. + +-v:: + Verbose. + +EXAMPLES +-------- + +Merge one patch into CVS:: ++ +------------ +$ export GIT_DIR=~/project/.git +$ cd ~/project_cvs_checkout +$ git-cvsexportcommit -v <commit-sha1> +$ cvs commit -F .mgs <files> +------------ + +Merge pending patches into CVS automatically -- only if you really know what you are doing :: ++ +------------ +$ export GIT_DIR=~/project/.git +$ cd ~/project_cvs_checkout +$ git-cherry cvshead myhead | sed -n 's/^+ //p' | xargs -l1 git-cvsexportcommit -c -p -v +------------ + +Author +------ +Written by Martin Langhoff <martin@catalyst.net.nz> + +Documentation +-------------- +Documentation by Martin Langhoff <martin@catalyst.net.nz> + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-cvsimport.txt b/Documentation/git-cvsimport.txt new file mode 100644 index 0000000000..0d59c06139 --- /dev/null +++ b/Documentation/git-cvsimport.txt @@ -0,0 +1,153 @@ +git-cvsimport(1) +================ + +NAME +---- +git-cvsimport - Salvage your data out of another SCM people love to hate + + +SYNOPSIS +-------- +[verse] +'git-cvsimport' [-o <branch-for-HEAD>] [-h] [-v] [-d <CVSROOT>] [-s <subst>] + [-p <options-for-cvsps>] [-C <git_repository>] [-i] [-P <file>] + [-m] [-M regex] [<CVS_module>] + + +DESCRIPTION +----------- +Imports a CVS repository into git. It will either create a new +repository, or incrementally import into an existing one. + +Splitting the CVS log into patch sets is done by 'cvsps'. +At least version 2.1 is required. + +You should *never* do any work of your own on the branches that are +created by git-cvsimport. The initial import will create and populate a +"master" branch from the CVS repository's main branch which you're free +to work with; after that, you need to 'git merge' incremental imports, or +any CVS branches, yourself. + +OPTIONS +------- +-d <CVSROOT>:: + The root of the CVS archive. May be local (a simple path) or remote; + currently, only the :local:, :ext: and :pserver: access methods + are supported. + +-C <target-dir>:: + The git repository to import to. If the directory doesn't + exist, it will be created. Default is the current directory. + +-i:: + Import-only: don't perform a checkout after importing. This option + ensures the working directory and index remain untouched and will + not create them if they do not exist. + +-k:: + Kill keywords: will extract files with -kk from the CVS archive + to avoid noisy changesets. Highly recommended, but off by default + to preserve compatibility with early imported trees. + +-u:: + Convert underscores in tag and branch names to dots. + +-o <branch-for-HEAD>:: + The 'HEAD' branch from CVS is imported to the 'origin' branch within + the git repository, as 'HEAD' already has a special meaning for git. + Use this option if you want to import into a different branch. ++ +Use '-o master' for continuing an import that was initially done by +the old cvs2git tool. + +-p <options-for-cvsps>:: + Additional options for cvsps. + The options '-u' and '-A' are implicit and should not be used here. ++ +If you need to pass multiple options, separate them with a comma. + +-P <cvsps-output-file>:: + Instead of calling cvsps, read the provided cvsps output file. Useful + for debugging or when cvsps is being handled outside cvsimport. + +-m:: + Attempt to detect merges based on the commit message. This option + will enable default regexes that try to capture the name source + branch name from the commit message. + +-M <regex>:: + Attempt to detect merges based on the commit message with a custom + regex. It can be used with -m to also see the default regexes. + You must escape forward slashes. + +-v:: + Verbosity: let 'cvsimport' report what it is doing. + +<CVS_module>:: + The CVS module you want to import. Relative to <CVSROOT>. + +-h:: + Print a short usage message and exit. + +-z <fuzz>:: + 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> + +-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. + +-A <author-conv-file>:: + CVS by default uses the Unix username when writing its + commit logs. Using this option and an author-conv-file + in this format ++ +--------- + exon=Andreas Ericsson <ae@op5.se> + spawn=Simon Pawn <spawn@frog-pond.org> + +--------- ++ +git-cvsimport will make it appear as those authors had +their GIT_AUTHOR_NAME and GIT_AUTHOR_EMAIL set properly +all along. ++ +For convenience, this data is saved to $GIT_DIR/cvs-authors +each time the -A option is provided and read from that same +file each time git-cvsimport is run. ++ +It is not recommended to use this feature if you intend to +export changes back to CVS again later with +gitlink:git-cvsexportcommit[1]. + +OUTPUT +------ +If '-v' is specified, the script reports what it is doing. + +Otherwise, success is indicated the Unix way, i.e. by simply exiting with +a zero exit status. + + +Author +------ +Written by Matthias Urlichs <smurf@smurf.noris.de>, with help from +various participants of the git-list <git@vger.kernel.org>. + +Documentation +-------------- +Documentation by Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt new file mode 100644 index 0000000000..e328db3797 --- /dev/null +++ b/Documentation/git-cvsserver.txt @@ -0,0 +1,161 @@ +git-cvsserver(1) +================ + +NAME +---- +git-cvsserver - A CVS server emulator for git + +SYNOPSIS +-------- +[verse] +export CVS_SERVER=git-cvsserver +'cvs' -d :ext:user@server/path/repo.git co <HEAD_name> + +DESCRIPTION +----------- + +This application is a CVS emulation layer for git. + +It is highly functional. However, not all methods are implemented, +and for those methods that are implemented, +not all switches are implemented. + +Testing has been done using both the CLI CVS client, and the Eclipse CVS +plugin. Most functionality works fine with both of these clients. + +LIMITATIONS +----------- + +Currently cvsserver works over SSH connections for read/write clients, and +over pserver for anonymous CVS access. + +CVS clients cannot tag, branch or perform GIT merges. + +INSTALLATION +------------ + +1. If you are going to offer anonymous CVS access via pserver, add a line in + /etc/inetd.conf like ++ +-- +------ + cvspserver stream tcp nowait nobody git-cvsserver pserver + +------ +Note: In some cases, you need to pass the 'pserver' argument twice for +git-cvsserver to see it. So the line would look like + +------ + cvspserver stream tcp nowait nobody git-cvsserver pserver pserver + +------ +No special setup is needed for SSH access, other than having GIT tools +in the PATH. If you have clients that do not accept the CVS_SERVER +env variable, you can rename git-cvsserver to cvs. +-- +2. For each repo that you want accessible from CVS you need to edit config in + the repo and add the following section. ++ +-- +------ + [gitcvs] + enabled=1 + # optional for debugging + logfile=/path/to/logfile + +------ +Note: you need to ensure each user that is going to invoke git-cvsserver has +write access to the log file and to the git repository. When offering anon +access via pserver, this means that the nobody user should have write access +to at least the sqlite database at the root of the repository. +-- +3. On the client machine you need to set the following variables. + CVSROOT should be set as per normal, but the directory should point at the + appropriate git repo. For example: ++ +-- +For SSH access, CVS_SERVER should be set to git-cvsserver + +Example: + +------ + export CVSROOT=:ext:user@server:/var/git/project.git + export CVS_SERVER=git-cvsserver +------ +-- +4. For SSH clients that will make commits, make sure their .bashrc file + sets the GIT_AUTHOR and GIT_COMMITTER variables. + +5. Clients should now be able to check out the project. Use the CVS 'module' + name to indicate what GIT 'head' you want to check out. Example: ++ +------ + cvs co -d project-master master +------ + +Eclipse CVS Client Notes +------------------------ + +To get a checkout with the Eclipse CVS client: + +1. Select "Create a new project -> From CVS checkout" +2. Create a new location. See the notes below for details on how to choose the + right protocol. +3. Browse the 'modules' available. It will give you a list of the heads in + the repository. You will not be able to browse the tree from there. Only + the heads. +4. Pick 'HEAD' when it asks what branch/tag to check out. Untick the + "launch commit wizard" to avoid committing the .project file. + +Protocol notes: If you are using anonymous access via pserver, just select that. +Those using SSH access should choose the 'ext' protocol, and configure 'ext' +access on the Preferences->Team->CVS->ExtConnection pane. Set CVS_SERVER to +'git-cvsserver'. Not that password support is not good when using 'ext', +you will definitely want to have SSH keys setup. + +Alternatively, you can just use the non-standard extssh protocol that Eclipse +offer. In that case CVS_SERVER is ignored, and you will have to replace +the cvs utility on the server with git-cvsserver or manipulate your .bashrc +so that calling 'cvs' effectively calls git-cvsserver. + +Clients known to work +--------------------- + +CVS 1.12.9 on Debian +CVS 1.11.17 on MacOSX (from Fink package) +Eclipse 3.0, 3.1.2 on MacOSX (see Eclipse CVS Client Notes) +TortoiseCVS + +Operations supported +-------------------- + +All the operations required for normal use are supported, including +checkout, diff, status, update, log, add, remove, commit. +Legacy monitoring operations are not supported (edit, watch and related). +Exports and tagging (tags and branches) are not supported at this stage. + +The server will set the -k mode to binary when relevant. In proper GIT +tradition, the contents of the files are always respected. +No keyword expansion or newline munging is supported. + +Dependencies +------------ + +git-cvsserver depends on DBD::SQLite. + +Copyright and Authors +--------------------- + +This program is copyright The Open University UK - 2006. + +Authors: Martyn Smith <martyn@catalyst.net.nz> + Martin Langhoff <martin@catalyst.net.nz> + with ideas and patches from participants of the git-list <git@vger.kernel.org>. + +Documentation +-------------- +Documentation by Martyn Smith <martyn@catalyst.net.nz> and Martin Langhoff <martin@catalyst.net.nz> Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-daemon.txt b/Documentation/git-daemon.txt new file mode 100644 index 0000000000..9ddab71203 --- /dev/null +++ b/Documentation/git-daemon.txt @@ -0,0 +1,238 @@ +git-daemon(1) +============= + +NAME +---- +git-daemon - A really simple server for git repositories + +SYNOPSIS +-------- +[verse] +'git-daemon' [--verbose] [--syslog] [--export-all] + [--timeout=n] [--init-timeout=n] [--strict-paths] + [--base-path=path] [--user-path | --user-path=path] + [--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 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 +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. + +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 +------- +--strict-paths:: + Match paths exactly (i.e. don't allow "/foo/repo" when the real path is + "/foo/repo.git" or "/foo/repo/.git") and don't do user-relative paths. + git-daemon will refuse to start when this option is enabled and no + whitelist is specified. + +--base-path:: + Remap all the path requests as relative to the given path. + This is sort of "GIT root" - if you run git-daemon with + '--base-path=/srv/git' on example.com, then if you later try to pull + '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 + do not have the 'git-daemon-export-ok' file. + +--inetd:: + Have the server run as an inetd service. Implies --syslog. + Incompatible with --port, --listen, --user and --group options. + +--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 + client request is received (typically a rather low value, since + that should be basically immediate). + +--timeout:: + Timeout for specific client sub-requests. This includes the time + it takes for the server to process the sub-request and time spent + waiting for next client's request. + +--syslog:: + Log to syslog instead of stderr. Note that this option does not imply + --verbose, thus by default only error conditions will be logged. + +--user-path, --user-path=path:: + Allow ~user notation to be used in requests. When + specified with no parameter, requests to + git://host/~alice/foo is taken as a request to access + 'foo' repository in the home directory of user `alice`. + If `--user-path=path` is specified, the same request is + taken as a request to access `path/foo` repository in + the home directory of user `alice`. + +--verbose:: + Log details about the incoming connections and requested files. + +--reuseaddr:: + Use SO_REUSEADDR when binding the listening socket. + This allows the server to restart without waiting for + old connections to time out. + +--detach:: + Detach from the shell. Implies --syslog. + +--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=service, --forbid-override=service:: + 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 +<yoshfuji@linux-ipv6.org> and the git-list <git@vger.kernel.org> + +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-describe.txt b/Documentation/git-describe.txt new file mode 100644 index 0000000000..47a583d3a6 --- /dev/null +++ b/Documentation/git-describe.txt @@ -0,0 +1,122 @@ +git-describe(1) +=============== + +NAME +---- +git-describe - Show the most recent tag that is reachable from a commit + + +SYNOPSIS +-------- +'git-describe' [--all] [--tags] [--abbrev=<n>] <committish>... + +DESCRIPTION +----------- +The command finds the most recent tag that is reachable from a +commit, and if the commit itself is pointed at by the tag, shows +the tag. Otherwise, it suffixes the tag name with the number of +additional commits and the abbreviated object name of the commit. + + +OPTIONS +------- +<committish>:: + The object name of the committish. + +--all:: + Instead of using only the annotated tags, use any ref + found in `.git/refs/`. + +--tags:: + Instead of using only the annotated tags, use any tag + found in `.git/refs/tags`. + +--abbrev=<n>:: + Instead of using the default 8 hexadecimal digits as the + abbreviated object name, use <n> digits. + +--candidates=<n>:: + Instead of considering only the 10 most recent tags as + candidates to describe the input committish consider + up to <n> candidates. Increasing <n> above 10 will take + slightly longer but may produce a more accurate result. + +--debug:: + Verbosely display information about the searching strategy + being employed to standard error. The tag name will still + be printed to standard out. + +EXAMPLES +-------- + +With something like git.git current tree, I get: + + [torvalds@g5 git]$ git-describe parent + v1.0.4-14-g2414721 + +i.e. the current head of my "parent" branch is based on v1.0.4, +but since it has a handful commits on top of that, +describe has added the number of additional commits ("14") and +an abbreviated object name for the commit itself ("2414721") +at the end. + +The number of additional commits is the number +of commits which would be displayed by "git log v1.0.4..parent". +The hash suffix is "-g" + 7-char abbreviation for the tip commit +of parent (which was `2414721b194453f058079d897d13c4e377f92dc6`). + +Doing a "git-describe" on a tag-name will just show the tag name: + + [torvalds@g5 git]$ git-describe v1.0.4 + v1.0.4 + +With --all, the command can use branch heads as references, so +the output shows the reference path as well: + + [torvalds@g5 git]$ git describe --all --abbrev=4 v1.0.5^2 + tags/v1.0.0-21-g975b + + [torvalds@g5 git]$ git describe --all HEAD^ + heads/lt/describe-7-g975b + +With --abbrev set to 0, the command can be used to find the +closest tagname without any suffix: + + [torvalds@g5 git]$ git describe --abbrev=0 v1.0.5^2 + tags/v1.0.0 + +SEARCH STRATEGY +--------------- + +For each committish supplied "git describe" will first look for +a tag which tags exactly that commit. Annotated tags will always +be preferred over lightweight tags, and tags with newer dates will +always be preferred over tags with older dates. If an exact match +is found, its name will be output and searching will stop. + +If an exact match was not found "git describe" will walk back +through the commit history to locate an ancestor commit which +has been tagged. The ancestor's tag will be output along with an +abbreviation of the input committish's SHA1. + +If multiple tags were found during the walk then the tag which +has the fewest commits different from the input committish will be +selected and output. Here fewest commits different is defined as +the number of commits which would be shown by "git log tag..input" +will be the smallest number of commits possible. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org>, but somewhat +butchered by Junio C Hamano <junkio@cox.net>. Later significantly +updated by Shawn Pearce <spearce@spearce.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-diff-files.txt b/Documentation/git-diff-files.txt new file mode 100644 index 0000000000..b78c4c64f1 --- /dev/null +++ b/Documentation/git-diff-files.txt @@ -0,0 +1,61 @@ +git-diff-files(1) +================= + +NAME +---- +git-diff-files - Compares files in the working tree and the index + + +SYNOPSIS +-------- +'git-diff-files' [-q] [-0|-1|-2|-3|-c|--cc|-n|--no-index] [<common diff options>] [<path>...] + +DESCRIPTION +----------- +Compares the files in the working tree and the index. When paths +are specified, compares only those named paths. Otherwise all +entries in the index are compared. The output format is the +same as "git-diff-index" and "git-diff-tree". + +OPTIONS +------- +include::diff-options.txt[] + +-1 -2 -3 or --base --ours --theirs, and -0:: + Diff against the "base" version, "our branch" or "their + branch" respectively. With these options, diffs for + merged entries are not shown. ++ +The default is to diff against our branch (-2) and the +cleanly resolved paths. The option -0 can be given to +omit diff output for unmerged entries and just show "Unmerged". + +-c,--cc:: + This compares stage 2 (our branch), stage 3 (their + branch) and the working tree file and outputs a combined + diff, similar to the way 'diff-tree' shows a merge + commit with these flags. + +\-n,\--no-index:: + Compare the two given files / directories. + +-q:: + Remain silent even on nonexistent files + +Output format +------------- +include::diff-format.txt[] + + +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-diff-index.txt b/Documentation/git-diff-index.txt new file mode 100644 index 0000000000..2df581c2c9 --- /dev/null +++ b/Documentation/git-diff-index.txt @@ -0,0 +1,133 @@ +git-diff-index(1) +================= + +NAME +---- +git-diff-index - Compares content and mode of blobs between the index and repository + + +SYNOPSIS +-------- +'git-diff-index' [-m] [--cached] [<common diff options>] <tree-ish> [<path>...] + +DESCRIPTION +----------- +Compares the content and mode of the blobs found via a tree +object with the content of the current index and, optionally +ignoring the stat state of the file on disk. When paths are +specified, compares only those named paths. Otherwise all +entries in the index are compared. + +OPTIONS +------- +include::diff-options.txt[] + +<tree-ish>:: + The id of a tree object to diff against. + +--cached:: + do not consider the on-disk file at all + +-m:: + By default, files recorded in the index but not checked + out are reported as deleted. This flag makes + "git-diff-index" say that all non-checked-out files are up + to date. + +Output format +------------- +include::diff-format.txt[] + +Operating Modes +--------------- +You can choose whether you want to trust the index file entirely +(using the '--cached' flag) or ask the diff logic to show any files +that don't match the stat state as being "tentatively changed". Both +of these operations are very useful indeed. + +Cached Mode +----------- +If '--cached' is specified, it allows you to ask: + + show me the differences between HEAD and the current index + contents (the ones I'd write with a "git-write-tree") + +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, 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 + +Example: let's say I had renamed `commit.c` to `git-commit.c`, and I had +done an "git-update-index" to make that effective in the index file. +"git-diff-files" wouldn't show anything at all, since the index file +matches my working directory. But doing a "git-diff-index" does: + + torvalds@ppc970:~/git> git-diff-index --cached HEAD + -100644 blob 4161aecc6700a2eb579e842af0b7f22b98443f74 commit.c + +100644 blob 4161aecc6700a2eb579e842af0b7f22b98443f74 git-commit.c + +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 +nicer for the case where you just want to check where you are. + +So doing a "git-diff-index --cached" is basically very useful when you are +asking yourself "what have I already marked for being committed, and +what's the difference to a previous tree". + +Non-cached Mode +--------------- +The "non-cached" mode takes a different approach, and is potentially +the more useful of the two in that what it does can't be emulated with +a "git-write-tree" + "git-diff-tree". Thus that's the default mode. +The non-cached version asks the question: + + show me the differences between HEAD and the currently checked out + tree - index contents _and_ files that aren't up-to-date + +which is obviously a very useful question too, since that tells you what +you *could* commit. Again, the output matches the "git-diff-tree -r" +output to a tee, but with a twist. + +The twist is that if some file doesn't match the index, we don't have +a backing store thing for it, and we use the magic "all-zero" sha1 to +show that. So let's say that you have edited `kernel/sched.c`, but +have not actually done a "git-update-index" on it yet - there is no +"object" associated with the new state, and you get: + + torvalds@ppc970:~/v2.6/linux> git-diff-index HEAD + *100644->100664 blob 7476bb......->000000...... kernel/sched.c + +i.e., it shows that the tree has changed, and that `kernel/sched.c` has is +not up-to-date and may contain new stuff. The all-zero sha1 means that to +get the real diff, you need to look at the object in the working directory +directly rather than do an object-to-object diff. + +NOTE: As with other commands of this type, "git-diff-index" does not +actually look at the contents of the file at all. So maybe +`kernel/sched.c` hasn't actually changed, and it's just that you +touched it. In either case, it's a note that you need to +"git-update-index" it to make the index be in sync. + +NOTE: You can have a mixture of files show up as "has been updated" +and "is still dirty in the working directory" together. You can always +tell which file is in which state, since the "has been updated" ones +show a valid sha1, and the "not in sync with the index" ones will +always have the special all-zero sha1. + + +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-diff-tree.txt b/Documentation/git-diff-tree.txt new file mode 100644 index 0000000000..5d6e9dc751 --- /dev/null +++ b/Documentation/git-diff-tree.txt @@ -0,0 +1,166 @@ +git-diff-tree(1) +================ + +NAME +---- +git-diff-tree - Compares the content and mode of blobs found via two tree objects + + +SYNOPSIS +-------- +[verse] +'git-diff-tree' [--stdin] [-m] [-s] [-v] [--no-commit-id] [--pretty] + [-t] [-r] [-c | --cc] [--root] [<common diff options>] + <tree-ish> [<tree-ish>] [<path>...] + +DESCRIPTION +----------- +Compares the content and mode of the blobs found via two tree objects. + +If there is only one <tree-ish> given, the commit is compared with its parents +(see --stdin below). + +Note that "git-diff-tree" can use the tree encapsulated in a commit object. + +OPTIONS +------- +include::diff-options.txt[] + +<tree-ish>:: + The id of a tree object. + +<path>...:: + If provided, the results are limited to a subset of files + matching one of these prefix strings. + i.e., file matches `/^<pattern1>|<pattern2>|.../` + Note that this parameter does not provide any wildcard or regexp + features. + +-r:: + recurse into sub-trees + +-t:: + show tree entry itself as well as subtrees. Implies -r. + +--root:: + When '--root' is specified the initial commit will be showed as a big + creation event. This is equivalent to a diff against the NULL tree. + +--stdin:: + When '--stdin' is specified, the command does not take + <tree-ish> arguments from the command line. Instead, it + reads either one <commit> or a pair of <tree-ish> + separated with a single space from its standard input. ++ +When a single commit is given on one line of such input, it compares +the commit with its parents. The following flags further affects its +behavior. This does not apply to the case where two <tree-ish> +separated with a single space are given. + +-m:: + By default, "git-diff-tree --stdin" does not show + differences for merge commits. With this flag, it shows + differences to that commit from all of its parents. See + also '-c'. + +-s:: + By default, "git-diff-tree --stdin" shows differences, + either in machine-readable form (without '-p') or in patch + form (with '-p'). This output can be suppressed. It is + only useful with '-v' flag. + +-v:: + This flag causes "git-diff-tree --stdin" to also show + the commit message before the differences. + +include::pretty-formats.txt[] + +--no-commit-id:: + git-diff-tree outputs a line with the commit ID when + applicable. This flag suppressed the commit ID output. + +-c:: + This flag changes the way a merge commit is displayed + (which means it is useful only when the command is given + one <tree-ish>, or '--stdin'). 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 (which is what the '-m' option does). + Furthermore, it lists only files which were modified + from all parents. + +--cc:: + This flag changes the way a merge commit patch is displayed, + in a similar way to the '-c' option. It implies the '-c' + and '-p' 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. When this optimization makes all + hunks disappear, the commit itself and the commit log + message is not shown, just like in any other "empty diff" case. + +--always:: + Show the commit itself and the commit log message even + if the diff itself is empty. + + +Limiting Output +--------------- +If you're only interested in differences in a subset of files, for +example some architecture-specific files, you might do: + + git-diff-tree -r <tree-ish> <tree-ish> arch/ia64 include/asm-ia64 + +and it will only show you what changed in those two directories. + +Or if you are searching for what changed in just `kernel/sched.c`, just do + + git-diff-tree -r <tree-ish> <tree-ish> kernel/sched.c + +and it will ignore all differences to other files. + +The pattern is always the prefix, and is matched exactly. There are no +wildcards. Even stricter, it has to match a complete path component. +I.e. "foo" does not pick up `foobar.h`. "foo" does match `foo/bar.h` +so it can be used to name subdirectories. + +An example of normal usage is: + + torvalds@ppc970:~/git> git-diff-tree 5319e4...... + *100664->100664 blob ac348b.......->a01513....... git-fsck-objects.c + +which tells you that the last commit changed just one file (it's from +this one: + +----------------------------------------------------------------------------- +commit 3c6f7ca19ad4043e9e72fa94106f352897e651a8 +tree 5319e4d609cdd282069cc4dce33c1db559539b03 +parent b4e628ea30d5ab3606119d2ea5caeab141d38df7 +author Linus Torvalds <torvalds@ppc970.osdl.org> Sat Apr 9 12:02:30 2005 +committer Linus Torvalds <torvalds@ppc970.osdl.org> Sat Apr 9 12:02:30 2005 + +Make "git-fsck-objects" print out all the root commits it finds. + +Once I do the reference tracking, I'll also make it print out all the +HEAD commits it finds, which is even more interesting. +----------------------------------------------------------------------------- + +in case you care). + +Output format +------------- +include::diff-format.txt[] + + +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-diff.txt b/Documentation/git-diff.txt new file mode 100644 index 0000000000..044cee9b42 --- /dev/null +++ b/Documentation/git-diff.txt @@ -0,0 +1,141 @@ +git-diff(1) +=========== + +NAME +---- +git-diff - Show changes between commits, commit and working tree, etc + + +SYNOPSIS +-------- +'git-diff' [<common 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. + +'git-diff' [--options] [--] [<path>...]:: + + 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]. + + If exactly two paths are given, and at least one is untracked, + compare the two files / directories. This behavior can be + forced by --no-index. + +'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>. + +For a more complete list of ways to spell <commit>, see +"SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + + +OPTIONS +------- +include::diff-options.txt[] + +<path>...:: + 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 +-------- + +Various ways to check your working tree:: ++ +------------ +$ git diff <1> +$ git diff --cached <2> +$ git diff HEAD <3> +------------ ++ +<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 +would be committing if you run "git commit -a" + +Comparing with arbitrary commits:: ++ +------------ +$ git diff test <1> +$ git diff HEAD -- ./test <2> +$ git diff HEAD^ HEAD <3> +------------ ++ +<1> instead of using the tip of the current branch, compare with the +tip of "test" branch. +<2> instead of comparing with the tip of "test" branch, compare with +the tip of the current branch, but limit the comparison to the +file "test". +<3> compare the version before the last commit and the last commit. + + +Limiting the diff output:: ++ +------------ +$ git diff --diff-filter=MRC <1> +$ git diff --name-status -r <2> +$ git diff arch/i386 include/asm-i386 <3> +------------ ++ +<1> show only modification, rename and copy, but not addition +nor deletion. +<2> show only names and the nature of change, but not actual +diff output. --name-status disables usual patch generation +which in turn also disables recursive behavior, so without -r +you would only see the directory name if there is a change in a +file in a subdirectory. +<3> limit diff output to named subtrees. + +Munging the diff output:: ++ +------------ +$ git diff --find-copies-harder -B -C <1> +$ git diff -R <2> +------------ ++ +<1> spend extra cycles to find renames, copies and complete +rewrites (very expensive). +<2> output diff in reverse. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-fast-import.txt b/Documentation/git-fast-import.txt new file mode 100644 index 0000000000..eaba6fd4c1 --- /dev/null +++ b/Documentation/git-fast-import.txt @@ -0,0 +1,912 @@ +git-fast-import(1) +================== + +NAME +---- +git-fast-import - Backend for fast Git data importers + + +SYNOPSIS +-------- +frontend | 'git-fast-import' [options] + +DESCRIPTION +----------- +This program is usually not what the end user wants to run directly. +Most end users want to use one of the existing frontend programs, +which parses a specific type of foreign source and feeds the contents +stored there to git-fast-import. + +fast-import reads a mixed command/data stream from standard input and +writes one or more packfiles directly into the current repository. +When EOF is received on standard input, fast import writes out +updated branch and tag refs, fully updating the current repository +with the newly imported data. + +The fast-import backend itself can import into an empty repository (one that +has already been initialized by gitlink:git-init[1]) or incrementally +update an existing populated repository. Whether or not incremental +imports are supported from a particular foreign source depends on +the frontend program in use. + + +OPTIONS +------- +--date-format=<fmt>:: + Specify the type of dates the frontend will supply to + fast-import within `author`, `committer` and `tagger` commands. + See ``Date Formats'' below for details about which formats + are supported, and their syntax. + +--force:: + Force updating modified existing branches, even if doing + so would cause commits to be lost (as the new commit does + not contain the old commit). + +--max-pack-size=<n>:: + Maximum size of each output packfile, expressed in MiB. + The default is 4096 (4 GiB) as that is the maximum allowed + packfile size (due to file format limitations). Some + importers may wish to lower this, such as to ensure the + resulting packfiles fit on CDs. + +--depth=<n>:: + Maximum delta depth, for blob and tree deltification. + Default is 10. + +--active-branches=<n>:: + Maximum number of branches to maintain active at once. + See ``Memory Utilization'' below for details. Default is 5. + +--export-marks=<file>:: + Dumps the internal marks table to <file> when complete. + Marks are written one per line as `:markid SHA-1`. + Frontends can use this file to validate imports after they + have been completed, or to save the marks table across + incremental runs. As <file> is only opened and truncated + at checkpoint (or completion) the same path can also be + safely given to \--import-marks. + +--import-marks=<file>:: + Before processing any input, load the marks specified in + <file>. The input file must exist, must be readable, and + must use the same format as produced by \--export-marks. + Multiple options may be supplied to import more than one + set of marks. If a mark is defined to different values, + the last file wins. + +--export-pack-edges=<file>:: + After creating a packfile, print a line of data to + <file> listing the filename of the packfile and the last + commit on each branch that was written to that packfile. + This information may be useful after importing projects + whose total object set exceeds the 4 GiB packfile limit, + as these commits can be used as edge points during calls + to gitlink:git-pack-objects[1]. + +--quiet:: + Disable all non-fatal output, making fast-import silent when it + is successful. This option disables the output shown by + \--stats. + +--stats:: + Display some basic statistics about the objects fast-import has + created, the packfiles they were stored into, and the + memory used by fast-import during this run. Showing this output + is currently the default, but can be disabled with \--quiet. + + +Performance +----------- +The design of fast-import allows it to import large projects in a minimum +amount of memory usage and processing time. Assuming the frontend +is able to keep up with fast-import and feed it a constant stream of data, +import times for projects holding 10+ years of history and containing +100,000+ individual commits are generally completed in just 1-2 +hours on quite modest (~$2,000 USD) hardware. + +Most bottlenecks appear to be in foreign source data access (the +source just cannot extract revisions fast enough) or disk IO (fast-import +writes as fast as the disk will take the data). Imports will run +faster if the source data is stored on a different drive than the +destination Git repository (due to less IO contention). + + +Development Cost +---------------- +A typical frontend for fast-import tends to weigh in at approximately 200 +lines of Perl/Python/Ruby code. Most developers have been able to +create working importers in just a couple of hours, even though it +is their first exposure to fast-import, and sometimes even to Git. This is +an ideal situation, given that most conversion tools are throw-away +(use once, and never look back). + + +Parallel Operation +------------------ +Like `git-push` or `git-fetch`, imports handled by fast-import are safe to +run alongside parallel `git repack -a -d` or `git gc` invocations, +or any other Git operation (including `git prune`, as loose objects +are never used by fast-import). + +fast-import does not lock the branch or tag refs it is actively importing. +After the import, during its ref update phase, fast-import tests each +existing branch ref to verify the update will be a fast-forward +update (the commit stored in the ref is contained in the new +history of the commit to be written). If the update is not a +fast-forward update, fast-import will skip updating that ref and instead +prints a warning message. fast-import will always attempt to update all +branch refs, and does not stop on the first failure. + +Branch updates can be forced with \--force, but its recommended that +this only be used on an otherwise quiet repository. Using \--force +is not necessary for an initial import into an empty repository. + + +Technical Discussion +-------------------- +fast-import tracks a set of branches in memory. Any branch can be created +or modified at any point during the import process by sending a +`commit` command on the input stream. This design allows a frontend +program to process an unlimited number of branches simultaneously, +generating commits in the order they are available from the source +data. It also simplifies the frontend programs considerably. + +fast-import does not use or alter the current working directory, or any +file within it. (It does however update the current Git repository, +as referenced by `GIT_DIR`.) Therefore an import frontend may use +the working directory for its own purposes, such as extracting file +revisions from the foreign source. This ignorance of the working +directory also allows fast-import to run very quickly, as it does not +need to perform any costly file update operations when switching +between branches. + +Input Format +------------ +With the exception of raw file data (which Git does not interpret) +the fast-import input format is text (ASCII) based. This text based +format simplifies development and debugging of frontend programs, +especially when a higher level language such as Perl, Python or +Ruby is being used. + +fast-import is very strict about its input. Where we say SP below we mean +*exactly* one space. Likewise LF means one (and only one) linefeed. +Supplying additional whitespace characters will cause unexpected +results, such as branch names or file names with leading or trailing +spaces in their name, or early termination of fast-import when it encounters +unexpected input. + +Date Formats +~~~~~~~~~~~~ +The following date formats are supported. A frontend should select +the format it will use for this import by passing the format name +in the \--date-format=<fmt> command line option. + +`raw`:: + This is the Git native format and is `<time> SP <offutc>`. + It is also fast-import's default format, if \--date-format was + not specified. ++ +The time of the event is specified by `<time>` as the number of +seconds since the UNIX epoch (midnight, Jan 1, 1970, UTC) and is +written as an ASCII decimal integer. ++ +The local offset is specified by `<offutc>` as a positive or negative +offset from UTC. For example EST (which is 5 hours behind UTC) +would be expressed in `<tz>` by ``-0500'' while UTC is ``+0000''. +The local offset does not affect `<time>`; it is used only as an +advisement to help formatting routines display the timestamp. ++ +If the local offset is not available in the source material, use +``+0000'', or the most common local offset. For example many +organizations have a CVS repository which has only ever been accessed +by users who are located in the same location and timezone. In this +case a reasonable offset from UTC could be assumed. ++ +Unlike the `rfc2822` format, this format is very strict. Any +variation in formatting will cause fast-import to reject the value. + +`rfc2822`:: + This is the standard email format as described by RFC 2822. ++ +An example value is ``Tue Feb 6 11:22:18 2007 -0500''. The Git +parser is accurate, but a little on the lenient side. It is the +same parser used by gitlink:git-am[1] when applying patches +received from email. ++ +Some malformed strings may be accepted as valid dates. In some of +these cases Git will still be able to obtain the correct date from +the malformed string. There are also some types of malformed +strings which Git will parse wrong, and yet consider valid. +Seriously malformed strings will be rejected. ++ +Unlike the `raw` format above, the timezone/UTC offset information +contained in an RFC 2822 date string is used to adjust the date +value to UTC prior to storage. Therefore it is important that +this information be as accurate as possible. ++ +If the source material uses RFC 2822 style dates, +the frontend should let fast-import handle the parsing and conversion +(rather than attempting to do it itself) as the Git parser has +been well tested in the wild. ++ +Frontends should prefer the `raw` format if the source material +already uses UNIX-epoch format, can be coaxed to give dates in that +format, or its format is easiliy convertible to it, as there is no +ambiguity in parsing. + +`now`:: + Always use the current time and timezone. The literal + `now` must always be supplied for `<when>`. ++ +This is a toy format. The current time and timezone of this system +is always copied into the identity string at the time it is being +created by fast-import. There is no way to specify a different time or +timezone. ++ +This particular format is supplied as its short to implement and +may be useful to a process that wants to create a new commit +right now, without needing to use a working directory or +gitlink:git-update-index[1]. ++ +If separate `author` and `committer` commands are used in a `commit` +the timestamps may not match, as the system clock will be polled +twice (once for each command). The only way to ensure that both +author and committer identity information has the same timestamp +is to omit `author` (thus copying from `committer`) or to use a +date format other than `now`. + +Commands +~~~~~~~~ +fast-import accepts several commands to update the current repository +and control the current import process. More detailed discussion +(with examples) of each command follows later. + +`commit`:: + Creates a new branch or updates an existing branch by + creating a new commit and updating the branch to point at + the newly created commit. + +`tag`:: + Creates an annotated tag object from an existing commit or + branch. Lightweight tags are not supported by this command, + as they are not recommended for recording meaningful points + in time. + +`reset`:: + Reset an existing branch (or a new branch) to a specific + revision. This command must be used to change a branch to + a specific revision without making a commit on it. + +`blob`:: + Convert raw file data into a blob, for future use in a + `commit` command. This command is optional and is not + needed to perform an import. + +`checkpoint`:: + Forces fast-import to close the current packfile, generate its + unique SHA-1 checksum and index, and start a new packfile. + This command is optional and is not needed to perform + an import. + +`commit` +~~~~~~~~ +Create or update a branch with a new commit, recording one logical +change to the project. + +.... + 'commit' SP <ref> LF + mark? + ('author' SP <name> SP LT <email> GT SP <when> LF)? + 'committer' SP <name> SP LT <email> GT SP <when> LF + data + ('from' SP <committish> LF)? + ('merge' SP <committish> LF)? + (filemodify | filedelete | filedeleteall)* + LF +.... + +where `<ref>` is the name of the branch to make the commit on. +Typically branch names are prefixed with `refs/heads/` in +Git, so importing the CVS branch symbol `RELENG-1_0` would use +`refs/heads/RELENG-1_0` for the value of `<ref>`. The value of +`<ref>` must be a valid refname in Git. As `LF` is not valid in +a Git refname, no quoting or escaping syntax is supported here. + +A `mark` command may optionally appear, requesting fast-import to save a +reference to the newly created commit for future use by the frontend +(see below for format). It is very common for frontends to mark +every commit they create, thereby allowing future branch creation +from any imported commit. + +The `data` command following `committer` must supply the commit +message (see below for `data` command syntax). To import an empty +commit message use a 0 length data. Commit messages are free-form +and are not interpreted by Git. Currently they must be encoded in +UTF-8, as fast-import does not permit other encodings to be specified. + +Zero or more `filemodify`, `filedelete` and `filedeleteall` commands +may be included to update the contents of the branch prior to +creating the commit. These commands may be supplied in any order. +However it is recommended that a `filedeleteall` command preceed +all `filemodify` commands in the same commit, as `filedeleteall` +wipes the branch clean (see below). + +`author` +^^^^^^^^ +An `author` command may optionally appear, if the author information +might differ from the committer information. If `author` is omitted +then fast-import will automatically use the committer's information for +the author portion of the commit. See below for a description of +the fields in `author`, as they are identical to `committer`. + +`committer` +^^^^^^^^^^^ +The `committer` command indicates who made this commit, and when +they made it. + +Here `<name>` is the person's display name (for example +``Com M Itter'') and `<email>` is the person's email address +(``cm@example.com''). `LT` and `GT` are the literal less-than (\x3c) +and greater-than (\x3e) symbols. These are required to delimit +the email address from the other fields in the line. Note that +`<name>` is free-form and may contain any sequence of bytes, except +`LT` and `LF`. It is typically UTF-8 encoded. + +The time of the change is specified by `<when>` using the date format +that was selected by the \--date-format=<fmt> command line option. +See ``Date Formats'' above for the set of supported formats, and +their syntax. + +`from` +^^^^^^ +The `from` command is used to specify the commit to initialize +this branch from. This revision will be the first ancestor of the +new commit. + +Omitting the `from` command in the first commit of a new branch +will cause fast-import to create that commit with no ancestor. This +tends to be desired only for the initial commit of a project. +Omitting the `from` command on existing branches is usually desired, +as the current commit on that branch is automatically assumed to +be the first ancestor of the new commit. + +As `LF` is not valid in a Git refname or SHA-1 expression, no +quoting or escaping syntax is supported within `<committish>`. + +Here `<committish>` is any of the following: + +* The name of an existing branch already in fast-import's internal branch + table. If fast-import doesn't know the name, its treated as a SHA-1 + expression. + +* A mark reference, `:<idnum>`, where `<idnum>` is the mark number. ++ +The reason fast-import uses `:` to denote a mark reference is this character +is not legal in a Git branch name. The leading `:` makes it easy +to distingush between the mark 42 (`:42`) and the branch 42 (`42` +or `refs/heads/42`), or an abbreviated SHA-1 which happened to +consist only of base-10 digits. ++ +Marks must be declared (via `mark`) before they can be used. + +* A complete 40 byte or abbreviated commit SHA-1 in hex. + +* Any valid Git SHA-1 expression that resolves to a commit. See + ``SPECIFYING REVISIONS'' in gitlink:git-rev-parse[1] for details. + +The special case of restarting an incremental import from the +current branch value should be written as: +---- + from refs/heads/branch^0 +---- +The `{caret}0` suffix is necessary as fast-import does not permit a branch to +start from itself, and the branch is created in memory before the +`from` command is even read from the input. Adding `{caret}0` will force +fast-import to resolve the commit through Git's revision parsing library, +rather than its internal branch table, thereby loading in the +existing value of the branch. + +`merge` +^^^^^^^ +Includes one additional ancestor commit, and makes the current +commit a merge commit. An unlimited number of `merge` commands per +commit are permitted by fast-import, thereby establishing an n-way merge. +However Git's other tools never create commits with more than 15 +additional ancestors (forming a 16-way merge). For this reason +it is suggested that frontends do not use more than 15 `merge` +commands per commit. + +Here `<committish>` is any of the commit specification expressions +also accepted by `from` (see above). + +`filemodify` +^^^^^^^^^^^^ +Included in a `commit` command to add a new file or change the +content of an existing file. This command has two different means +of specifying the content of the file. + +External data format:: + The data content for the file was already supplied by a prior + `blob` command. The frontend just needs to connect it. ++ +.... + 'M' SP <mode> SP <dataref> SP <path> LF +.... ++ +Here `<dataref>` can be either a mark reference (`:<idnum>`) +set by a prior `blob` command, or a full 40-byte SHA-1 of an +existing Git blob object. + +Inline data format:: + The data content for the file has not been supplied yet. + The frontend wants to supply it as part of this modify + command. ++ +.... + 'M' SP <mode> SP 'inline' SP <path> LF + data +.... ++ +See below for a detailed description of the `data` command. + +In both formats `<mode>` is the type of file entry, specified +in octal. Git only supports the following modes: + +* `100644` or `644`: A normal (not-executable) file. The majority + of files in most projects use this mode. If in doubt, this is + what you want. +* `100755` or `755`: A normal, but executable, file. +* `120000`: A symlink, the content of the file will be the link target. + +In both formats `<path>` is the complete path of the file to be added +(if not already existing) or modified (if already existing). + +A `<path>` string must use UNIX-style directory separators (forward +slash `/`), may contain any byte other than `LF`, and must not +start with double quote (`"`). + +If an `LF` or double quote must be encoded into `<path>` shell-style +quoting should be used, e.g. `"path/with\n and \" in it"`. + +The value of `<path>` must be in canoncial form. That is it must not: + +* contain an empty directory component (e.g. `foo//bar` is invalid), +* end with a directory separator (e.g. `foo/` is invalid), +* start with a directory separator (e.g. `/foo` is invalid), +* contain the special component `.` or `..` (e.g. `foo/./bar` and + `foo/../bar` are invalid). + +It is recommended that `<path>` always be encoded using UTF-8. + +`filedelete` +^^^^^^^^^^^^ +Included in a `commit` command to remove a file from the branch. +If the file removal makes its directory empty, the directory will +be automatically removed too. This cascades up the tree until the +first non-empty directory or the root is reached. + +.... + 'D' SP <path> LF +.... + +here `<path>` is the complete path of the file to be removed. +See `filemodify` above for a detailed description of `<path>`. + +`filedeleteall` +^^^^^^^^^^^^^^^ +Included in a `commit` command to remove all files (and also all +directories) from the branch. This command resets the internal +branch structure to have no files in it, allowing the frontend +to subsequently add all interesting files from scratch. + +.... + 'deleteall' LF +.... + +This command is extremely useful if the frontend does not know +(or does not care to know) what files are currently on the branch, +and therefore cannot generate the proper `filedelete` commands to +update the content. + +Issuing a `filedeleteall` followed by the needed `filemodify` +commands to set the correct content will produce the same results +as sending only the needed `filemodify` and `filedelete` commands. +The `filedeleteall` approach may however require fast-import to use slightly +more memory per active branch (less than 1 MiB for even most large +projects); so frontends that can easily obtain only the affected +paths for a commit are encouraged to do so. + +`mark` +~~~~~~ +Arranges for fast-import to save a reference to the current object, allowing +the frontend to recall this object at a future point in time, without +knowing its SHA-1. Here the current object is the object creation +command the `mark` command appears within. This can be `commit`, +`tag`, and `blob`, but `commit` is the most common usage. + +.... + 'mark' SP ':' <idnum> LF +.... + +where `<idnum>` is the number assigned by the frontend to this mark. +The value of `<idnum>` is expressed as an ASCII decimal integer. +The value 0 is reserved and cannot be used as +a mark. Only values greater than or equal to 1 may be used as marks. + +New marks are created automatically. Existing marks can be moved +to another object simply by reusing the same `<idnum>` in another +`mark` command. + +`tag` +~~~~~ +Creates an annotated tag referring to a specific commit. To create +lightweight (non-annotated) tags see the `reset` command below. + +.... + 'tag' SP <name> LF + 'from' SP <committish> LF + 'tagger' SP <name> SP LT <email> GT SP <when> LF + data + LF +.... + +where `<name>` is the name of the tag to create. + +Tag names are automatically prefixed with `refs/tags/` when stored +in Git, so importing the CVS branch symbol `RELENG-1_0-FINAL` would +use just `RELENG-1_0-FINAL` for `<name>`, and fast-import will write the +corresponding ref as `refs/tags/RELENG-1_0-FINAL`. + +The value of `<name>` must be a valid refname in Git and therefore +may contain forward slashes. As `LF` is not valid in a Git refname, +no quoting or escaping syntax is supported here. + +The `from` command is the same as in the `commit` command; see +above for details. + +The `tagger` command uses the same format as `committer` within +`commit`; again see above for details. + +The `data` command following `tagger` must supply the annotated tag +message (see below for `data` command syntax). To import an empty +tag message use a 0 length data. Tag messages are free-form and are +not interpreted by Git. Currently they must be encoded in UTF-8, +as fast-import does not permit other encodings to be specified. + +Signing annotated tags during import from within fast-import is not +supported. Trying to include your own PGP/GPG signature is not +recommended, as the frontend does not (easily) have access to the +complete set of bytes which normally goes into such a signature. +If signing is required, create lightweight tags from within fast-import with +`reset`, then create the annotated versions of those tags offline +with the standard gitlink:git-tag[1] process. + +`reset` +~~~~~~~ +Creates (or recreates) the named branch, optionally starting from +a specific revision. The reset command allows a frontend to issue +a new `from` command for an existing branch, or to create a new +branch from an existing commit without creating a new commit. + +.... + 'reset' SP <ref> LF + ('from' SP <committish> LF)? + LF +.... + +For a detailed description of `<ref>` and `<committish>` see above +under `commit` and `from`. + +The `reset` command can also be used to create lightweight +(non-annotated) tags. For example: + +==== + reset refs/tags/938 + from :938 +==== + +would create the lightweight tag `refs/tags/938` referring to +whatever commit mark `:938` references. + +`blob` +~~~~~~ +Requests writing one file revision to the packfile. The revision +is not connected to any commit; this connection must be formed in +a subsequent `commit` command by referencing the blob through an +assigned mark. + +.... + 'blob' LF + mark? + data +.... + +The mark command is optional here as some frontends have chosen +to generate the Git SHA-1 for the blob on their own, and feed that +directly to `commit`. This is typically more work than its worth +however, as marks are inexpensive to store and easy to use. + +`data` +~~~~~~ +Supplies raw data (for use as blob/file content, commit messages, or +annotated tag messages) to fast-import. Data can be supplied using an exact +byte count or delimited with a terminating line. Real frontends +intended for production-quality conversions should always use the +exact byte count format, as it is more robust and performs better. +The delimited format is intended primarily for testing fast-import. + +Exact byte count format:: + The frontend must specify the number of bytes of data. ++ +.... + 'data' SP <count> LF + <raw> LF +.... ++ +where `<count>` is the exact number of bytes appearing within +`<raw>`. The value of `<count>` is expressed as an ASCII decimal +integer. The `LF` on either side of `<raw>` is not +included in `<count>` and will not be included in the imported data. + +Delimited format:: + A delimiter string is used to mark the end of the data. + fast-import will compute the length by searching for the delimiter. + This format is primarly useful for testing and is not + recommended for real data. ++ +.... + 'data' SP '<<' <delim> LF + <raw> LF + <delim> LF +.... ++ +where `<delim>` is the chosen delimiter string. The string `<delim>` +must not appear on a line by itself within `<raw>`, as otherwise +fast-import will think the data ends earlier than it really does. The `LF` +immediately trailing `<raw>` is part of `<raw>`. This is one of +the limitations of the delimited format, it is impossible to supply +a data chunk which does not have an LF as its last byte. + +`checkpoint` +~~~~~~~~~~~~ +Forces fast-import to close the current packfile, start a new one, and to +save out all current branch refs, tags and marks. + +.... + 'checkpoint' LF + LF +.... + +Note that fast-import automatically switches packfiles when the current +packfile reaches \--max-pack-size, or 4 GiB, whichever limit is +smaller. During an automatic packfile switch fast-import does not update +the branch refs, tags or marks. + +As a `checkpoint` can require a significant amount of CPU time and +disk IO (to compute the overall pack SHA-1 checksum, generate the +corresponding index file, and update the refs) it can easily take +several minutes for a single `checkpoint` command to complete. + +Frontends may choose to issue checkpoints during extremely large +and long running imports, or when they need to allow another Git +process access to a branch. However given that a 30 GiB Subversion +repository can be loaded into Git through fast-import in about 3 hours, +explicit checkpointing may not be necessary. + + +Tips and Tricks +--------------- +The following tips and tricks have been collected from various +users of fast-import, and are offered here as suggestions. + +Use One Mark Per Commit +~~~~~~~~~~~~~~~~~~~~~~~ +When doing a repository conversion, use a unique mark per commit +(`mark :<n>`) and supply the \--export-marks option on the command +line. fast-import will dump a file which lists every mark and the Git +object SHA-1 that corresponds to it. If the frontend can tie +the marks back to the source repository, it is easy to verify the +accuracy and completeness of the import by comparing each Git +commit to the corresponding source revision. + +Coming from a system such as Perforce or Subversion this should be +quite simple, as the fast-import mark can also be the Perforce changeset +number or the Subversion revision number. + +Freely Skip Around Branches +~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Don't bother trying to optimize the frontend to stick to one branch +at a time during an import. Although doing so might be slightly +faster for fast-import, it tends to increase the complexity of the frontend +code considerably. + +The branch LRU builtin to fast-import tends to behave very well, and the +cost of activating an inactive branch is so low that bouncing around +between branches has virtually no impact on import performance. + +Handling Renames +~~~~~~~~~~~~~~~~ +When importing a renamed file or directory, simply delete the old +name(s) and modify the new name(s) during the corresponding commit. +Git performs rename detection after-the-fact, rather than explicitly +during a commit. + +Use Tag Fixup Branches +~~~~~~~~~~~~~~~~~~~~~~ +Some other SCM systems let the user create a tag from multiple +files which are not from the same commit/changeset. Or to create +tags which are a subset of the files available in the repository. + +Importing these tags as-is in Git is impossible without making at +least one commit which ``fixes up'' the files to match the content +of the tag. Use fast-import's `reset` command to reset a dummy branch +outside of your normal branch space to the base commit for the tag, +then commit one or more file fixup commits, and finally tag the +dummy branch. + +For example since all normal branches are stored under `refs/heads/` +name the tag fixup branch `TAG_FIXUP`. This way it is impossible for +the fixup branch used by the importer to have namespace conflicts +with real branches imported from the source (the name `TAG_FIXUP` +is not `refs/heads/TAG_FIXUP`). + +When committing fixups, consider using `merge` to connect the +commit(s) which are supplying file revisions to the fixup branch. +Doing so will allow tools such as gitlink:git-blame[1] to track +through the real commit history and properly annotate the source +files. + +After fast-import terminates the frontend will need to do `rm .git/TAG_FIXUP` +to remove the dummy branch. + +Import Now, Repack Later +~~~~~~~~~~~~~~~~~~~~~~~~ +As soon as fast-import completes the Git repository is completely valid +and ready for use. Typicallly this takes only a very short time, +even for considerably large projects (100,000+ commits). + +However repacking the repository is necessary to improve data +locality and access performance. It can also take hours on extremely +large projects (especially if -f and a large \--window parameter is +used). Since repacking is safe to run alongside readers and writers, +run the repack in the background and let it finish when it finishes. +There is no reason to wait to explore your new Git project! + +If you choose to wait for the repack, don't try to run benchmarks +or performance tests until repacking is completed. fast-import outputs +suboptimal packfiles that are simply never seen in real use +situations. + +Repacking Historical Data +~~~~~~~~~~~~~~~~~~~~~~~~~ +If you are repacking very old imported data (e.g. older than the +last year), consider expending some extra CPU time and supplying +\--window=50 (or higher) when you run gitlink:git-repack[1]. +This will take longer, but will also produce a smaller packfile. +You only need to expend the effort once, and everyone using your +project will benefit from the smaller repository. + + +Packfile Optimization +--------------------- +When packing a blob fast-import always attempts to deltify against the last +blob written. Unless specifically arranged for by the frontend, +this will probably not be a prior version of the same file, so the +generated delta will not be the smallest possible. The resulting +packfile will be compressed, but will not be optimal. + +Frontends which have efficient access to all revisions of a +single file (for example reading an RCS/CVS ,v file) can choose +to supply all revisions of that file as a sequence of consecutive +`blob` commands. This allows fast-import to deltify the different file +revisions against each other, saving space in the final packfile. +Marks can be used to later identify individual file revisions during +a sequence of `commit` commands. + +The packfile(s) created by fast-import do not encourage good disk access +patterns. This is caused by fast-import writing the data in the order +it is received on standard input, while Git typically organizes +data within packfiles to make the most recent (current tip) data +appear before historical data. Git also clusters commits together, +speeding up revision traversal through better cache locality. + +For this reason it is strongly recommended that users repack the +repository with `git repack -a -d` after fast-import completes, allowing +Git to reorganize the packfiles for faster data access. If blob +deltas are suboptimal (see above) then also adding the `-f` option +to force recomputation of all deltas can significantly reduce the +final packfile size (30-50% smaller can be quite typical). + + +Memory Utilization +------------------ +There are a number of factors which affect how much memory fast-import +requires to perform an import. Like critical sections of core +Git, fast-import uses its own memory allocators to ammortize any overheads +associated with malloc. In practice fast-import tends to ammoritize any +malloc overheads to 0, due to its use of large block allocations. + +per object +~~~~~~~~~~ +fast-import maintains an in-memory structure for every object written in +this execution. On a 32 bit system the structure is 32 bytes, +on a 64 bit system the structure is 40 bytes (due to the larger +pointer sizes). Objects in the table are not deallocated until +fast-import terminates. Importing 2 million objects on a 32 bit system +will require approximately 64 MiB of memory. + +The object table is actually a hashtable keyed on the object name +(the unique SHA-1). This storage configuration allows fast-import to reuse +an existing or already written object and avoid writing duplicates +to the output packfile. Duplicate blobs are surprisingly common +in an import, typically due to branch merges in the source. + +per mark +~~~~~~~~ +Marks are stored in a sparse array, using 1 pointer (4 bytes or 8 +bytes, depending on pointer size) per mark. Although the array +is sparse, frontends are still strongly encouraged to use marks +between 1 and n, where n is the total number of marks required for +this import. + +per branch +~~~~~~~~~~ +Branches are classified as active and inactive. The memory usage +of the two classes is significantly different. + +Inactive branches are stored in a structure which uses 96 or 120 +bytes (32 bit or 64 bit systems, respectively), plus the length of +the branch name (typically under 200 bytes), per branch. fast-import will +easily handle as many as 10,000 inactive branches in under 2 MiB +of memory. + +Active branches have the same overhead as inactive branches, but +also contain copies of every tree that has been recently modified on +that branch. If subtree `include` has not been modified since the +branch became active, its contents will not be loaded into memory, +but if subtree `src` has been modified by a commit since the branch +became active, then its contents will be loaded in memory. + +As active branches store metadata about the files contained on that +branch, their in-memory storage size can grow to a considerable size +(see below). + +fast-import automatically moves active branches to inactive status based on +a simple least-recently-used algorithm. The LRU chain is updated on +each `commit` command. The maximum number of active branches can be +increased or decreased on the command line with \--active-branches=. + +per active tree +~~~~~~~~~~~~~~~ +Trees (aka directories) use just 12 bytes of memory on top of the +memory required for their entries (see ``per active file'' below). +The cost of a tree is virtually 0, as its overhead ammortizes out +over the individual file entries. + +per active file entry +~~~~~~~~~~~~~~~~~~~~~ +Files (and pointers to subtrees) within active trees require 52 or 64 +bytes (32/64 bit platforms) per entry. To conserve space, file and +tree names are pooled in a common string table, allowing the filename +``Makefile'' to use just 16 bytes (after including the string header +overhead) no matter how many times it occurs within the project. + +The active branch LRU, when coupled with the filename string pool +and lazy loading of subtrees, allows fast-import to efficiently import +projects with 2,000+ branches and 45,114+ files in a very limited +memory footprint (less than 2.7 MiB per active branch). + + +Author +------ +Written by Shawn O. Pearce <spearce@spearce.org>. + +Documentation +-------------- +Documentation by Shawn O. Pearce <spearce@spearce.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-fetch-pack.txt b/Documentation/git-fetch-pack.txt new file mode 100644 index 0000000000..a99a5b321f --- /dev/null +++ b/Documentation/git-fetch-pack.txt @@ -0,0 +1,96 @@ +git-fetch-pack(1) +================= + +NAME +---- +git-fetch-pack - Receive missing objects from another repository + + +SYNOPSIS +-------- +'git-fetch-pack' [--all] [--quiet|-q] [--keep|-k] [--thin] [--upload-pack=<git-upload-pack>] [--depth=<n>] [--no-progress] [-v] [<host>:]<directory> [<refs>...] + +DESCRIPTION +----------- +Usually you would want to use gitlink:git-fetch[1] which is a +higher level wrapper of this command instead. + +Invokes 'git-upload-pack' on a potentially remote repository, +and asks it to send objects missing from this repository, to +update the named heads. The list of commits available locally +is found out by scanning local $GIT_DIR/refs/ and sent to +'git-upload-pack' running on the other end. + +This command degenerates to download everything to complete the +asked refs from the remote side when the local side does not +have a common ancestor commit. + + +OPTIONS +------- +\--all:: + Fetch all remote refs. + +\--quiet, \-q:: + Pass '-q' flag to 'git-unpack-objects'; this makes the + cloning process less verbose. + +\--keep, \-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. If provided twice then the pack is + locked against repacking. + +\--thin:: + Spend extra cycles to minimize the number of objects to be sent. + Use it on slower connection. + +\--upload-pack=<git-upload-pack>:: + Use this to specify the path to 'git-upload-pack' on the + remote side, if is not found on your $PATH. + Installations of sshd ignores the user's environment + setup scripts for login shells (e.g. .bash_profile) and + your privately installed git may not be found on the system + default $PATH. Another workaround suggested is to set + up your $PATH in ".bashrc", but this flag is for people + who do not want to pay the overhead for non-interactive + shells by having a lean .bashrc file (they set most of + the things up in .bash_profile). + +\--exec=<git-upload-pack>:: + Same as \--upload-pack=<git-upload-pack>. + +\--depth=<n>:: + Limit fetching to ancestor-chains not longer than n. + +\--no-progress:: + Do not show the progress. + +\-v:: + Run verbosely. + +<host>:: + A remote host that houses the repository. When this + part is specified, 'git-upload-pack' is invoked via + ssh. + +<directory>:: + The repository to sync from. + +<refs>...:: + The remote heads to update from. This is relative to + $GIT_DIR (e.g. "HEAD", "refs/heads/master"). When + unspecified, update from all heads the remote side has. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-fetch.txt b/Documentation/git-fetch.txt new file mode 100644 index 0000000000..5fbeab76b7 --- /dev/null +++ b/Documentation/git-fetch.txt @@ -0,0 +1,56 @@ +git-fetch(1) +============ + +NAME +---- +git-fetch - Download objects and refs from another repository + + +SYNOPSIS +-------- +'git-fetch' <options> <repository> <refspec>... + + +DESCRIPTION +----------- +Fetches named heads or tags from another repository, along with +the objects necessary to complete them. + +The ref names and their object names of fetched refs are stored +in `.git/FETCH_HEAD`. This information is left for a later merge +operation done by "git merge". + +When <refspec> stores the fetched result in tracking branches, +the tags that point at these branches are automatically +followed. This is done by first fetching from the remote using +the given <refspec>s, and if the repository has objects that are +pointed by remote tags that it does not yet have, then fetch +those missing tags. If the other end has tags that point at +branches you are not interested in, you will not get them. + + +OPTIONS +------- +include::fetch-options.txt[] + +include::pull-fetch-param.txt[] + +include::urls.txt[] + +SEE ALSO +-------- +gitlink:git-pull[1] + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +Junio C Hamano <junkio@cox.net> + +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-fmt-merge-msg.txt b/Documentation/git-fmt-merge-msg.txt new file mode 100644 index 0000000000..a70eb3994a --- /dev/null +++ b/Documentation/git-fmt-merge-msg.txt @@ -0,0 +1,39 @@ +git-fmt-merge-msg(1) +==================== + +NAME +---- +git-fmt-merge-msg - Produce a merge commit message + + +SYNOPSIS +-------- +'git-fmt-merge-msg' <$GIT_DIR/FETCH_HEAD + +DESCRIPTION +----------- +Takes the list of merged objects on stdin and produces a suitable +commit message to be used for the merge commit, usually to be +passed as the '<merge-message>' argument of `git-merge`. + +This script is intended mostly for internal use by scripts +automatically invoking `git-merge`. + + +SEE ALSO +-------- +gitlink:git-merge[1] + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Petr Baudis, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt new file mode 100644 index 0000000000..f49b0d944c --- /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|--tcl] [--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 interpolated 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, --tcl:: + 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 $GIT_DIR/). + +objecttype:: + The type of the object (`blob`, `tree`, `commit`, `tag`). + +objectsize:: + The size of the object (the same as `git-cat-file -s` reports). + +objectname:: + The object name (aka SHA-1). + +In addition to the above, for commit and tag objects, the header +field names (`tree`, `parent`, `object`, `type`, and `tag`) can +be used to specify the value in the header field. + +Fields that have name-email-date tuple as its value (`author`, +`committer`, and `tagger`) can be suffixed with `name`, `email`, +and `date` to extract the named component. + +The first line of the message in a commit and tag object is +`subject`, the remaining lines are `body`. The whole message +is `contents`. + +For sorting purposes, fields with numeric values sort in numeric +order (`objectsize`, `authordate`, `committerdate`, `taggerdate`). +All other fields are used to sort in their byte-value order. + +In any case, a field name that refers to a field inapplicable to +the object referred by the ref does not cause an error. It +returns an empty string instead. + + +EXAMPLES +-------- + +An example directly producing formatted text. Show the most recent +3 tagged commits:: + +------------ +#!/bin/sh + +git-for-each-ref --count=3 --sort='-*authordate' \ +--format='From: %(*authorname) %(*authoremail) +Subject: %(*subject) +Date: %(*authordate) +Ref: %(*refname) + +%(*body) +' 'refs/tags' +------------ + + +A simple example showing the use of shell eval on the output, +demonstrating the use of --shell. List the prefixes of all heads:: +------------ +#!/bin/sh + +git-for-each-ref --shell --format="ref=%(refname)" refs/heads | \ +while read entry +do + eval "$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-format-patch.txt b/Documentation/git-format-patch.txt new file mode 100644 index 0000000000..111d7c60bf --- /dev/null +++ b/Documentation/git-format-patch.txt @@ -0,0 +1,166 @@ +git-format-patch(1) +=================== + +NAME +---- +git-format-patch - Prepare patches for e-mail submission + + +SYNOPSIS +-------- +[verse] +'git-format-patch' [-n | -k] [-o <dir> | --stdout] [--thread] + [--attach[=<boundary>] | --inline[=<boundary>]] + [-s | --signoff] [<common diff options>] [--start-number <n>] + [--in-reply-to=Message-Id] [--suffix=.<sfx>] + [--ignore-if-in-upstream] + <since>[..<until>] + +DESCRIPTION +----------- + +Prepare each commit between <since> and <until> with its patch in +one file per commit, formatted to resemble UNIX mailbox format. +If ..<until> is not specified, the head of the current working +tree is implied. For a more complete list of ways to spell +<since> and <until>, see "SPECIFYING REVISIONS" section in +gitlink:git-rev-parse[1]. + +The output of this command is convenient for e-mail submission or +for use with gitlink:git-am[1]. + +Each output file is numbered sequentially from 1, and uses the +first line of the commit message (massaged for pathname safety) as +the filename. The names of the output files are printed to standard +output, unless the --stdout option is specified. + +If -o is specified, output files are created in <dir>. Otherwise +they are created in the current working directory. + +If -n is specified, instead of "[PATCH] Subject", the first line +is formatted as "[PATCH n/m] Subject". + +If given --thread, git-format-patch will generate In-Reply-To and +References headers to make the second and subsequent patch mails appear +as replies to the first mail; this also generates a Message-Id header to +reference. + +OPTIONS +------- +include::diff-options.txt[] + +-o|--output-directory <dir>:: + Use <dir> to store the resulting files, instead of the + current working directory. + +-n|--numbered:: + Name output in '[PATCH n/m]' format. + +--start-number <n>:: + Start numbering the patches at <n> instead of 1. + +-k|--keep-subject:: + Do not strip/add '[PATCH]' from the first line of the + commit log message. + +-s|--signoff:: + Add `Signed-off-by:` line to the commit message, using + the committer identity of yourself. + +--stdout:: + Print all commits to the standard output in mbox format, + instead of creating a file for each one. + +--attach[=<boundary>]:: + Create multipart/mixed attachment, the first part of + which is the commit message and the patch itself in the + second part, with "Content-Disposition: attachment". + +--inline[=<boundary>]:: + Create multipart/mixed attachment, the first part of + which is the commit message and the patch itself in the + second part, with "Content-Disposition: inline". + +--thread:: + Add In-Reply-To and References headers to make the second and + subsequent mails appear as replies to the first. Also generates + the Message-Id header to reference. + +--in-reply-to=Message-Id:: + Make the first mail (or all the mails with --no-thread) appear as a + reply to the given Message-Id, which avoids breaking threads to + provide a new patch series. + +--ignore-if-in-upstream:: + Do not include a patch that matches a commit in + <until>..<since>. This will examine all patches reachable + from <since> but not from <until> and compare them with the + patches being generated, and any patch that matches is + ignored. + +--suffix=.<sfx>:: + Instead of using `.patch` as the suffix for generated + filenames, use specifed suffix. A common alternative is + `--suffix=.txt`. ++ +Note that you would need to include the leading dot `.` if you +want a filename like `0001-description-of-my-change.patch`, and +the first letter does not have to be a dot. Leaving it empty would +not add any suffix. + +CONFIGURATION +------------- +You can specify extra mail header lines to be added to each +message in the repository configuration. Also you can specify +the default suffix different from the built-in one: + +------------ +[format] + headers = "Organization: git-foo\n" + suffix = .txt +------------ + + +EXAMPLES +-------- + +git-format-patch -k --stdout R1..R2 | git-am -3 -k:: + Extract commits between revisions R1 and R2, and apply + them on top of the current branch using `git-am` to + cherry-pick them. + +git-format-patch origin:: + Extract all commits which are in the current branch but + not in the origin branch. For each commit a separate file + is created in the current directory. + +git-format-patch -M -B origin:: + The same as the previous one. Additionally, it detects + and handles renames and complete rewrites intelligently to + produce a renaming patch. A renaming patch reduces the + amount of text output, and generally makes it easier to + review it. Note that the "patch" program does not + understand renaming patches, so use it only when you know + the recipient uses git to apply your patch. + +git-format-patch -3:: + Extract three topmost commits from the current branch + and format them as e-mailable patches. + +See Also +-------- +gitlink:git-am[1], gitlink:git-send-email[1] + + +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-fsck-objects.txt b/Documentation/git-fsck-objects.txt new file mode 100644 index 0000000000..f21061ecfe --- /dev/null +++ b/Documentation/git-fsck-objects.txt @@ -0,0 +1,17 @@ +git-fsck-objects(1) +=================== + +NAME +---- +git-fsck-objects - Verifies the connectivity and validity of the objects in the database + + +SYNOPSIS +-------- +'git-fsck-objects' ... + +DESCRIPTION +----------- + +This is a synonym for gitlink:git-fsck[1]. Please refer to the +documentation of that command. diff --git a/Documentation/git-fsck.txt b/Documentation/git-fsck.txt new file mode 100644 index 0000000000..058009d2fa --- /dev/null +++ b/Documentation/git-fsck.txt @@ -0,0 +1,139 @@ +git-fsck(1) +=========== + +NAME +---- +git-fsck - Verifies the connectivity and validity of the objects in the database + + +SYNOPSIS +-------- +[verse] +'git-fsck' [--tags] [--root] [--unreachable] [--cache] + [--full] [--strict] [<object>*] + +DESCRIPTION +----------- +Verifies the connectivity and validity of the objects in the database. + +OPTIONS +------- +<object>:: + An object to treat as the head of an unreachability trace. ++ +If no objects are given, git-fsck defaults to using the +index file and all SHA1 references in .git/refs/* as heads. + +--unreachable:: + Print out objects that exist but that aren't readable from any + of the reference nodes. + +--root:: + Report root nodes. + +--tags:: + Report tags. + +--cache:: + Consider any object recorded in the index also as a head node for + an unreachability trace. + +--full:: + Check not just objects in GIT_OBJECT_DIRECTORY + ($GIT_DIR/objects), but also the ones found in alternate + object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES + or $GIT_DIR/objects/info/alternates, + and in packed git archives found in $GIT_DIR/objects/pack + and corresponding pack subdirectories in alternate + object pools. + +--strict:: + Enable more strict checking, namely to catch a file mode + recorded with g+w bit set, which was created by older + versions of git. Existing repositories, including the + Linux kernel, git itself, and sparse repository have old + objects that triggers this check, but it is recommended + to check new projects with this flag. + +It tests SHA1 and general object sanity, and it does full tracking of +the resulting reachability and everything else. It prints out any +corruption it finds (missing or bad objects), and if you use the +'--unreachable' flag it will also print out objects that exist but +that aren't readable from any of the specified head nodes. + +So for example + + git-fsck --unreachable HEAD $(cat .git/refs/heads/*) + +will do quite a _lot_ of verification on the tree. There are a few +extra validity tests to be added (make sure that tree objects are +sorted properly etc), but on the whole if "git-fsck" is happy, you +do have a valid tree. + +Any corrupt objects you will have to find in backups or other archives +(i.e., you can just remove them and do an "rsync" with some other site in +the hopes that somebody else has the object you have corrupted). + +Of course, "valid tree" doesn't mean that it wasn't generated by some +evil person, and the end result might be crap. git is a revision +tracking system, not a quality assurance system ;) + +Extracted Diagnostics +--------------------- + +expect dangling commits - potential heads - due to lack of head information:: + You haven't specified any nodes as heads so it won't be + possible to differentiate between un-parented commits and + root nodes. + +missing sha1 directory '<dir>':: + The directory holding the sha1 objects is missing. + +unreachable <type> <object>:: + The <type> object <object>, isn't actually referred to directly + or indirectly in any of the trees or commits seen. This can + mean that there's another root node that you're not specifying + or that the tree is corrupt. If you haven't missed a root node + then you might as well delete unreachable nodes since they + can't be used. + +missing <type> <object>:: + The <type> object <object>, is referred to but isn't present in + the database. + +dangling <type> <object>:: + The <type> object <object>, is present in the database but never + 'directly' used. A dangling commit could be a root node. + +warning: git-fsck: tree <tree> has full pathnames in it:: + And it shouldn't... + +sha1 mismatch <object>:: + The database has an object who's sha1 doesn't match the + database value. + This indicates a serious data integrity problem. + +Environment Variables +--------------------- + +GIT_OBJECT_DIRECTORY:: + used to specify the object database root (usually $GIT_DIR/objects) + +GIT_INDEX_FILE:: + used to specify the index file of the index + +GIT_ALTERNATE_OBJECT_DIRECTORIES:: + used to specify additional object database roots (usually unset) + +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-gc.txt b/Documentation/git-gc.txt new file mode 100644 index 0000000000..bc1658434a --- /dev/null +++ b/Documentation/git-gc.txt @@ -0,0 +1,83 @@ +git-gc(1) +========= + +NAME +---- +git-gc - Cleanup unnecessary files and optimize the local repository + + +SYNOPSIS +-------- +'git-gc' [--prune] + +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. + +OPTIONS +------- + +--prune:: + Usually `git-gc` packs refs, expires old reflog entries, + packs loose objects, + and removes old 'rerere' records. Removal + of unreferenced loose objects is an unsafe operation + while other git operations are in progress, so it is not + done by default. Pass this option if you want it, and only + when you know nobody else is creating new objects in the + repository at the same time (e.g. never use this option + in a cron script). + + +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 occurring. 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. + +The optional configuration variable 'gc.packrefs' determines if +`git gc` runs `git-pack-refs`. Without the configuration, `git-pack-refs` +is not run in bare repositories by default, to allow older dumb-transport +clients fetch from the repository, but this will change in the future. + +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-get-tar-commit-id.txt b/Documentation/git-get-tar-commit-id.txt new file mode 100644 index 0000000000..48805b651c --- /dev/null +++ b/Documentation/git-get-tar-commit-id.txt @@ -0,0 +1,37 @@ +git-get-tar-commit-id(1) +======================== + +NAME +---- +git-get-tar-commit-id - Extract commit ID from an archive created using git-tar-tree + + +SYNOPSIS +-------- +'git-get-tar-commit-id' < <tarfile> + + +DESCRIPTION +----------- +Acts as a filter, extracting the commit ID stored in archives created by +git-tar-tree. It reads only the first 1024 bytes of input, thus its +runtime is not influenced by the size of <tarfile> very much. + +If no commit ID is found, git-get-tar-commit-id quietly exists with a +return code of 1. This can happen if <tarfile> had not been created +using git-tar-tree or if the first parameter of git-tar-tree had been +a tree ID instead of a commit ID or tag. + + +Author +------ +Written by Rene Scharfe <rene.scharfe@lsrfire.ath.cx> + +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-grep.txt b/Documentation/git-grep.txt new file mode 100644 index 0000000000..0140c8e358 --- /dev/null +++ b/Documentation/git-grep.txt @@ -0,0 +1,136 @@ +git-grep(1) +=========== + +NAME +---- +git-grep - Print lines matching a pattern + + +SYNOPSIS +-------- +[verse] +'git-grep' [--cached] + [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp] + [-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] [--all-match] + [-A <post-context>] [-B <pre-context>] [-C <context>] + [-f <file>] [-e] <pattern> [--and|--or|--not|(|)|-e <pattern>...] + [<tree>...] + [--] [<path>...] + +DESCRIPTION +----------- +Look for specified patterns in the working tree files, blobs +registered in the index file, or given tree objects. + + +OPTIONS +------- +--cached:: + Instead of searching in the working tree files, check + the blobs registered in the index file. + +-a | --text:: + Process binary files as if they were text. + +-i | --ignore-case:: + Ignore case differences between the patterns and the + files. + +-w | --word-regexp:: + Match the pattern only at word boundary (either begin at the + beginning of a line, or preceded by a non-word character; end at + the end of a line or followed by a non-word character). + +-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 + option forces paths to be output relative to the project + top directory. + +-E | --extended-regexp | -G | --basic-regexp:: + Use POSIX extended/basic regexp for patterns. Default + is to use basic regexp. + +-n:: + Prefix the line number to matching lines. + +-l | --files-with-matches | -L | --files-without-match:: + Instead of showing every matched line, show only the + names of files that contain (or do not contain) matches. + +-c | --count:: + Instead of showing every matched line, show the number of + lines that match. + +-[ABC] <context>:: + Show `context` trailing (`A` -- after), or leading (`B` + -- before), or both (`C` -- context) lines, and place a + line containing `--` between contiguous groups of + matches. + +-f <file>:: + Read patterns from <file>, one per line. + +-e:: + The next parameter is the pattern. This option has to be + used for patterns starting with - and should be used in + scripts passing user input to grep. Multiple patterns are + combined by 'or'. + +--and | --or | --not | ( | ):: + Specify how multiple patterns are combined using Boolean + expressions. `--or` is the default operator. `--and` has + 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. + +\--:: + Signals the end of options; the rest of the parameters + are <path> limiters. + + +Example +------- + +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 +revamped by Junio C Hamano. + + +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-hash-object.txt b/Documentation/git-hash-object.txt new file mode 100644 index 0000000000..5edc36f060 --- /dev/null +++ b/Documentation/git-hash-object.txt @@ -0,0 +1,46 @@ +git-hash-object(1) +================== + +NAME +---- +git-hash-object - Compute object ID and optionally creates a blob from a file + + +SYNOPSIS +-------- +'git-hash-object' [-t <type>] [-w] [--stdin] [--] <file>... + +DESCRIPTION +----------- +Computes the object ID value for an object with specified type +with the contents of the named file (which can be outside of the +work tree), and optionally writes the resulting object into the +object database. Reports its object ID to its standard output. +This is used by "git-cvsimport" to update the index +without modifying files in the work tree. When <type> is not +specified, it defaults to "blob". + +OPTIONS +------- + +-t <type>:: + Specify the type (default: "blob"). + +-w:: + Actually write the object into the object database. + +--stdin:: + Read the object from standard input instead of from a file. + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +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-http-fetch.txt b/Documentation/git-http-fetch.txt new file mode 100644 index 0000000000..7dc2df3044 --- /dev/null +++ b/Documentation/git-http-fetch.txt @@ -0,0 +1,53 @@ +git-http-fetch(1) +================= + +NAME +---- +git-http-fetch - Download from a remote git repository via HTTP + + +SYNOPSIS +-------- +'git-http-fetch' [-c] [-t] [-a] [-d] [-v] [-w filename] [--recover] [--stdin] <commit> <url> + +DESCRIPTION +----------- +Downloads a remote git repository via HTTP. + +OPTIONS +------- +commit-id:: + Either the hash or the filename under [URL]/refs/ to + pull. + +-c:: + Get the commit objects. +-t:: + Get trees associated with the commit objects. +-a:: + Get all the objects. +-v:: + Report what is downloaded. + +-w <filename>:: + Writes the commit-id into the filename under $GIT_DIR/refs/<filename> on + the local end after the transfer is complete. + +--stdin:: + Instead of a commit id on the commandline (which is not expected in this + case), 'git-http-fetch' expects lines on stdin in the format + + <commit-id>['\t'<filename-as-in--w>] + +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-http-push.txt b/Documentation/git-http-push.txt new file mode 100644 index 0000000000..4b4a46169c --- /dev/null +++ b/Documentation/git-http-push.txt @@ -0,0 +1,89 @@ +git-http-push(1) +================ + +NAME +---- +git-http-push - Push objects over HTTP/DAV to another repository + + +SYNOPSIS +-------- +'git-http-push' [--complete] [--force] [--verbose] <url> <ref> [<ref>...] + +DESCRIPTION +----------- +Sends missing objects to remote repository, and updates the +remote branch. + + +OPTIONS +------- +--complete:: + Do not assume that the remote repository is complete in its + current state, and verify all objects in the entire local + ref's history exist in the remote repository. + +--force:: + Usually, the command refuses to update a remote ref that + is not an ancestor of the local ref used to overwrite it. + This flag disables the check. What this means is that + the remote repository can lose commits; use it with + care. + +--verbose:: + Report the list of objects being walked locally and the + list of objects successfully sent to the remote repository. + +<ref>...:: + The remote refs to update. + + +Specifying the Refs +------------------- + +A '<ref>' specification can be either a single pattern, or a pair +of such patterns separated by a colon ":" (this means that a ref name +cannot have a colon in it). A single pattern '<name>' is just a +shorthand for '<name>:<name>'. + +Each pattern pair consists of the source side (before the colon) +and the destination side (after the colon). The ref to be +pushed is determined by finding a match that matches the source +side, and where it is pushed is determined by using the +destination side. + + - It is an error if <src> does not match exactly one of the + local refs. + + - If <dst> does not match any remote ref, either + + * it has to start with "refs/"; <dst> is used as the + destination literally in this case. + + * <src> == <dst> and the ref that matched the <src> must not + exist in the set of remote refs; the ref matched <src> + locally is used as the name of the destination. + +Without '--force', the <src> ref is stored at the remote only if +<dst> does not exist, or <dst> is a proper subset (i.e. an +ancestor) of <src>. This check, known as "fast forward check", +is performed in order to avoid accidentally overwriting the +remote ref and lose other peoples' commits from there. + +With '--force', the fast forward check is disabled for all refs. + +Optionally, a <ref> parameter can be prefixed with a plus '+' sign +to disable the fast-forward check only on that ref. + + +Author +------ +Written by Nick Hengeveld <nickh@reactrix.com> + +Documentation +-------------- +Documentation by Nick Hengeveld + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-imap-send.txt b/Documentation/git-imap-send.txt new file mode 100644 index 0000000000..eca9e9ccef --- /dev/null +++ b/Documentation/git-imap-send.txt @@ -0,0 +1,62 @@ +git-imap-send(1) +================ + +NAME +---- +git-imap-send - Dump a mailbox from stdin into an imap folder + + +SYNOPSIS +-------- +'git-imap-send' + + +DESCRIPTION +----------- +This command uploads a mailbox generated with git-format-patch +into an imap drafts folder. This allows patches to be sent as +other email is sent with mail clients that cannot read mailbox +files directly. + +Typical usage is something like: + +git-format-patch --signoff --stdout --attach origin | git-imap-send + + +CONFIGURATION +------------- + +git-imap-send requires the following values in the repository +configuration file (shown with examples): + +.......................... +[imap] + Folder = "INBOX.Drafts" + +[imap] + Tunnel = "ssh -q user@server.com /usr/bin/imapd ./Maildir 2> /dev/null" + +[imap] + Host = imap.server.com + User = bob + Pass = pwd + Port = 143 +.......................... + + +BUGS +---- +Doesn't handle lines starting with "From " in the message body. + + +Author +------ +Derived from isync 1.0.1 by Mike McCormack. + +Documentation +-------------- +Documentation by Mike McCormack + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-index-pack.txt b/Documentation/git-index-pack.txt new file mode 100644 index 0000000000..2229ee86b7 --- /dev/null +++ b/Documentation/git-index-pack.txt @@ -0,0 +1,94 @@ +git-index-pack(1) +================= + +NAME +---- +git-index-pack - Build pack index file for an existing packed archive + + +SYNOPSIS +-------- +'git-index-pack' [-v] [-o <index-file>] <pack-file> +'git-index-pack' --stdin [--fix-thin] [--keep] [-v] [-o <index-file>] [<pack-file>] + + +DESCRIPTION +----------- +Reads a packed archive (.pack) from the specified file, and +builds a pack index file (.idx) for it. The packed archive +together with the pack index can then be placed in the +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 + file is constructed from the name of packed archive + file by replacing .pack with .idx (and the program + 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 +------ +Written by Sergey Vlasov <vsu@altlinux.ru> + +Documentation +------------- +Documentation by Sergey Vlasov + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-init-db.txt b/Documentation/git-init-db.txt new file mode 100644 index 0000000000..5412135d76 --- /dev/null +++ b/Documentation/git-init-db.txt @@ -0,0 +1,19 @@ +git-init-db(1) +============== + +NAME +---- +git-init-db - Creates an empty git repository + + +SYNOPSIS +-------- +'git-init-db' [--template=<template_directory>] [--shared[=<permissions>]] + + +DESCRIPTION +----------- + +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..1b64d3ab03 --- /dev/null +++ b/Documentation/git-init.txt @@ -0,0 +1,111 @@ +git-init(1) +=========== + +NAME +---- +git-init - Create an empty git repository or reinitialize an existing one + + +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-instaweb.txt b/Documentation/git-instaweb.txt new file mode 100644 index 0000000000..52a6aa6e82 --- /dev/null +++ b/Documentation/git-instaweb.txt @@ -0,0 +1,84 @@ +git-instaweb(1) +=============== + +NAME +---- +git-instaweb - Instantly browse your working repository in gitweb + +SYNOPSIS +-------- +'git-instaweb' [--local] [--httpd=<httpd>] [--port=<port>] [--browser=<browser>] + +'git-instaweb' [--start] [--stop] [--restart] + +DESCRIPTION +----------- +A simple script to setup gitweb and a web server for browsing the local +repository. + +OPTIONS +------- + +-l|--local:: + Only bind the web server to the local IP (127.0.0.1). + +-d|--httpd:: + The HTTP daemon command-line that will be executed. + Command-line options may be specified here, and the + configuration file will be added at the end of the command-line. + Currently, lighttpd and apache2 are the only supported servers. + (Default: lighttpd) + +-m|--module-path:: + The module path (only needed if httpd is Apache). + (Default: /usr/lib/apache2/modules) + +-p|--port:: + The port number to bind the httpd to. (Default: 1234) + +-b|--browser:: + + The web browser command-line to execute to view the gitweb page. + If blank, the URL of the gitweb instance will be printed to + stdout. (Default: 'firefox') + +--start:: + Start the httpd instance and exit. This does not generate + any of the configuration files for spawning a new instance. + +--stop:: + Stop the httpd instance and exit. This does not generate + any of the configuration files for spawning a new instance, + nor does it close the browser. + +--restart:: + Restart the httpd instance and exit. This does not generate + any of the configuration files for spawning a new instance. + +CONFIGURATION +------------- + +You may specify configuration in your .git/config + +----------------------------------------------------------------------- +[instaweb] + local = true + httpd = apache2 -f + port = 4321 + browser = konqueror + modulepath = /usr/lib/apache2/modules + +----------------------------------------------------------------------- + +Author +------ +Written by Eric Wong <normalperson@yhbt.net> + +Documentation +-------------- +Documentation by Eric Wong <normalperson@yhbt.net>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-local-fetch.txt b/Documentation/git-local-fetch.txt new file mode 100644 index 0000000000..22048d82bd --- /dev/null +++ b/Documentation/git-local-fetch.txt @@ -0,0 +1,49 @@ +git-local-fetch(1) +================== + +NAME +---- +git-local-fetch - Duplicate another git repository on a local system + + +SYNOPSIS +-------- +'git-local-fetch' [-c] [-t] [-a] [-d] [-v] [-w filename] [--recover] [-l] [-s] [-n] commit-id path + +DESCRIPTION +----------- +Duplicates another git repository on a local system. + +OPTIONS +------- +-c:: + Get the commit objects. +-t:: + Get trees associated with the commit objects. +-a:: + Get all the objects. +-v:: + Report what is downloaded. + +-w <filename>:: + Writes the commit-id into the filename under $GIT_DIR/refs/<filename> on + the local end after the transfer is complete. + +--stdin:: + Instead of a commit id on the commandline (which is not expected in this + case), 'git-local-fetch' expects lines on stdin in the format + + <commit-id>['\t'<filename-as-in--w>] + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +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 new file mode 100644 index 0000000000..361eaec700 --- /dev/null +++ b/Documentation/git-log.txt @@ -0,0 +1,88 @@ +git-log(1) +========== + +NAME +---- +git-log - Show commit logs + + +SYNOPSIS +-------- +'git-log' <option>... + +DESCRIPTION +----------- +Shows the commit logs. + +The command takes options applicable to the gitlink:git-rev-list[1] +command to control what is shown and how, and options applicable to +the gitlink:git-diff-tree[1] commands to control how the changes +each commit introduces are shown. + +This manual page describes only the most frequently used options. + + +OPTIONS +------- + +include::pretty-formats.txt[] + +-<n>:: + Limits the number of commits to show. + +<since>..<until>:: + 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. + For a more complete list of ways to spell <since> + and <until>, see "SPECIFYING REVISIONS" section in + gitlink:git-rev-parse[1]. + +-p:: + Show the change the commit introduces in a patch form. + +<paths>...:: + Show only commits that affect the specified paths. + + +Examples +-------- +git log --no-merges:: + + Show the whole commit history, but skip any merges + +git log v2.6.12.. include/scsi drivers/scsi:: + + Show all commits since version 'v2.6.12' that changed any file + in the include/scsi or drivers/scsi subdirectories + +git log --since="2 weeks ago" \-- gitk:: + + Show the changes during the last two weeks to the file 'gitk'. + The "--" is necessary to avoid confusion with the *branch* named + 'gitk' + +git log -r --name-status release..test:: + + Show the commits that are in the "test" branch but not yet + 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> + +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-lost-found.txt b/Documentation/git-lost-found.txt new file mode 100644 index 0000000000..f52a9d7f68 --- /dev/null +++ b/Documentation/git-lost-found.txt @@ -0,0 +1,78 @@ +git-lost-found(1) +================= + +NAME +---- +git-lost-found - Recover lost refs that luckily have not yet been pruned + +SYNOPSIS +-------- +'git-lost-found' + +DESCRIPTION +----------- +Finds dangling commits and tags from the object database, and +creates refs to them in .git/lost-found/ directory. Commits and +tags that dereference to commits go to .git/lost-found/commit +and others are stored in .git/lost-found/other directory. + + +OUTPUT +------ +One line description from the commit and tag found along with +their object name are printed on the standard output. + + +EXAMPLE +------- + +Suppose you run 'git tag -f' and mistyped the tag to overwrite. +The ref to your tag is overwritten, but until you run 'git +prune', it is still there. + +------------ +$ git lost-found +[1ef2b196d909eed523d4f3c9bf54b78cdd6843c6] GIT 0.99.9c +... +------------ + +Also you can use gitk to browse how they relate to each other +and existing (probably old) tags. + +------------ +$ gitk $(cd .git/lost-found/commit && echo ??*) +------------ + +After making sure that it is the object you are looking for, you +can reconnect it to your regular .git/refs hierarchy. + +------------ +$ git cat-file -t 1ef2b196 +tag +$ git cat-file tag 1ef2b196 +object fa41bbce8e38c67a218415de6cfa510c7e50032a +type commit +tag v0.99.9c +tagger Junio C Hamano <junkio@cox.net> 1131059594 -0800 + +GIT 0.99.9c + +This contains the following changes from the "master" branch, since +... +$ git update-ref refs/tags/not-lost-anymore 1ef2b196 +$ git rev-parse not-lost-anymore +1ef2b196d909eed523d4f3c9bf54b78cdd6843c6 +------------ + +Author +------ +Written by Junio C Hamano 濱野 純 <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-ls-files.txt b/Documentation/git-ls-files.txt new file mode 100644 index 0000000000..79e0b7b71a --- /dev/null +++ b/Documentation/git-ls-files.txt @@ -0,0 +1,254 @@ +git-ls-files(1) +=============== + +NAME +---- +git-ls-files - Show information about files in the index and the working tree + + +SYNOPSIS +-------- +[verse] +'git-ls-files' [-z] [-t] [-v] + (--[cached|deleted|others|ignored|stage|unmerged|killed|modified])\* + (-[c|d|o|i|s|u|k|m])\* + [-x <pattern>|--exclude=<pattern>] + [-X <file>|--exclude-from=<file>] + [--exclude-per-directory=<file>] + [--error-unmatch] + [--full-name] [--abbrev] [--] [<file>]\* + +DESCRIPTION +----------- +This merges the file listing in the directory cache index with the +actual working directory list, and shows different combinations of the +two. + +One or more of the options below may be used to determine the files +shown: + +OPTIONS +------- +-c|--cached:: + Show cached files in the output (default) + +-d|--deleted:: + Show deleted files in the output + +-m|--modified:: + Show modified files in the output + +-o|--others:: + Show other files in the output + +-i|--ignored:: + Show ignored files in the output + Note the this also reverses any exclude list present. + +-s|--stage:: + Show stage files in the output + +--directory:: + If a whole directory is classified as "other", show just its + name (with a trailing slash) and not its whole contents. + +--no-empty-directory:: + Do not list empty directories. Has no effect without --directory. + +-u|--unmerged:: + Show unmerged files in the output (forces --stage) + +-k|--killed:: + Show files on the filesystem that need to be removed due + to file/directory conflicts for checkout-index to + succeed. + +-z:: + \0 line termination on output. + +-x|--exclude=<pattern>:: + Skips files matching pattern. + Note that pattern is a shell wildcard pattern. + +-X|--exclude-from=<file>:: + exclude patterns are read from <file>; 1 per line. + +--exclude-per-directory=<file>:: + read additional exclude patterns that apply only to the + directory and its subdirectories in <file>. + +--error-unmatch:: + If any <file> does not appear in the index, treat this as an + error (return 1). + +-t:: + Identify the file status with the following tags (followed by + a space) at the start of each line: + H:: cached + M:: unmerged + R:: removed/deleted + C:: modified/changed + K:: to be killed + ?:: other + +-v:: + Similar to `-t`, but use lowercase letters for files + that are marked as 'always matching index'. + +--full-name:: + When run from a subdirectory, the command usually + outputs paths relative to the current directory. This + option forces paths to be output relative to the project + top directory. + +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + +\--:: + Do not interpret any more arguments as options. + +<file>:: + Files to show. If no files are given all files which match the other + specified criteria are shown. + +Output +------ +show files just outputs the filename unless '--stage' is specified in +which case it outputs: + + [<tag> ]<mode> <object> <stage> <file> + +"git-ls-files --unmerged" and "git-ls-files --stage" can be used to examine +detailed information on unmerged paths. + +For an unmerged path, instead of recording a single mode/SHA1 pair, +the dircache records up to three such pairs; one from tree O in stage +1, A in stage 2, and B in stage 3. This information can be used by +the user (or the porcelain) to see what should eventually be recorded at the +path. (see git-read-tree for more information on state) + +When `-z` option is not used, TAB, LF, and backslash characters +in pathnames are represented as `\t`, `\n`, and `\\`, +respectively. + + +Exclude Patterns +---------------- + +'git-ls-files' can use a list of "exclude patterns" when +traversing the directory tree and finding files to show when the +flags --others or --ignored are specified. + +These exclude patterns come from these places: + + 1. command line flag --exclude=<pattern> specifies a single + pattern. + + 2. command line flag --exclude-from=<file> specifies a list of + patterns stored in a file. + + 3. command line flag --exclude-per-directory=<name> specifies + a name of the file in each directory 'git-ls-files' + examines, and if exists, its contents are used as an + additional list of patterns. + +An exclude pattern file used by (2) and (3) contains one pattern +per line. A line that starts with a '#' can be used as comment +for readability. + +There are three lists of patterns that are in effect at a given +time. They are built and ordered in the following way: + + * --exclude=<pattern> from the command line; patterns are + ordered in the same order as they appear on the command line. + + * lines read from --exclude-from=<file>; patterns are ordered + in the same order as they appear in the file. + + * When --exclude-per-directory=<name> is specified, upon + entering a directory that has such a file, its contents are + appended at the end of the current "list of patterns". They + are popped off when leaving the directory. + +Each pattern in the pattern list specifies "a match pattern" and +optionally the fate; either a file that matches the pattern is +considered excluded or included. A filename is matched against +the patterns in the three lists; the --exclude-from list is +checked first, then the --exclude-per-directory list, and then +finally the --exclude list. The last match determines its fate. +If there is no match in the three lists, the fate is "included". + +A pattern specified on the command line with --exclude or read +from the file specified with --exclude-from is relative to the +top of the directory tree. A pattern read from a file specified +by --exclude-per-directory is relative to the directory that the +pattern file appears in. + +An exclude pattern is of the following format: + + - an optional prefix '!' which means that the fate this pattern + specifies is "include", not the usual "exclude"; the + remainder of the pattern string is interpreted according to + the following rules. + + - if it does not contain a slash '/', it is a shell glob + pattern and used to match against the filename without + leading directories. + + - otherwise, it is a shell glob pattern, suitable for + consumption by fnmatch(3) with FNM_PATHNAME flag. I.e. a + slash in the pattern must match a slash in the pathname. + "Documentation/\*.html" matches "Documentation/git.html" but + not "ppc/ppc.html". As a natural exception, "/*.c" matches + "cat-file.c" but not "mozilla-sha1/sha1.c". + +An example: + +-------------------------------------------------------------- + $ cat .git/info/exclude + # ignore objects and archives, anywhere in the tree. + *.[oa] + $ cat Documentation/.gitignore + # ignore generated html files, + *.html + # except foo.html which is maintained by hand + !foo.html + $ git-ls-files --ignored \ + --exclude='Documentation/*.[0-9]' \ + --exclude-from=.git/info/exclude \ + --exclude-per-directory=.gitignore +-------------------------------------------------------------- + +Another example: + +-------------------------------------------------------------- + $ cat .gitignore + vmlinux* + $ ls arch/foo/kernel/vm* + arch/foo/kernel/vmlinux.lds.S + $ echo '!/vmlinux*' >arch/foo/kernel/.gitignore +-------------------------------------------------------------- + +The second .gitignore keeps `arch/foo/kernel/vmlinux.lds.S` file +from getting ignored. + + +See Also +-------- +gitlink:git-read-tree[1] + + +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-ls-remote.txt b/Documentation/git-ls-remote.txt new file mode 100644 index 0000000000..c254005ca3 --- /dev/null +++ b/Documentation/git-ls-remote.txt @@ -0,0 +1,73 @@ +git-ls-remote(1) +================ + +NAME +---- +git-ls-remote - List references in a remote repository + + +SYNOPSIS +-------- +[verse] +'git-ls-remote' [--heads] [--tags] [-u <exec> | --upload-pack <exec>] + <repository> <refs>... + +DESCRIPTION +----------- +Displays references available in a remote repository along with the associated +commit IDs. + + +OPTIONS +------- +-h|--heads, -t|--tags:: + 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. + +-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 daemon 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. Use "." (dot) to list references in + the local repository. + +<refs>...:: + When unspecified, all references, after filtering done + with --heads and --tags, are shown. When <refs>... are + specified, only references matching the given patterns + are displayed. + +EXAMPLES +-------- + + $ git ls-remote --tags ./. + d6602ec5194c87b0fc87103ca4d67251c76f233a refs/tags/v0.99 + f25a265a342aed6041ab0cc484224d9ca54b6f41 refs/tags/v0.99.1 + 7ceca275d047c90c0c7d5afb13ab97efdf51bd6e refs/tags/v0.99.3 + c5db5456ae3b0873fc659c19fafdde22313cc441 refs/tags/v0.99.2 + 0918385dbd9656cab0d1d81ba7453d49bbc16250 refs/tags/junio-gpg-pub + $ git ls-remote http://www.kernel.org/pub/scm/git/git.git master pu rc + 5fe978a5381f1fbad26a80e682ddd2a401966740 refs/heads/master + c781a84b5204fb294c9ccc79f8b3baceeb32c061 refs/heads/pu + b1d096f2926c4e37c9c0b6a7bf2119bedaa277cb refs/heads/rc + $ echo http://www.kernel.org/pub/scm/git/git.git >.git/branches/public + $ git ls-remote --tags public v\* + d6602ec5194c87b0fc87103ca4d67251c76f233a refs/tags/v0.99 + f25a265a342aed6041ab0cc484224d9ca54b6f41 refs/tags/v0.99.1 + c5db5456ae3b0873fc659c19fafdde22313cc441 refs/tags/v0.99.2 + 7ceca275d047c90c0c7d5afb13ab97efdf51bd6e refs/tags/v0.99.3 + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-ls-tree.txt b/Documentation/git-ls-tree.txt new file mode 100644 index 0000000000..7899394081 --- /dev/null +++ b/Documentation/git-ls-tree.txt @@ -0,0 +1,83 @@ +git-ls-tree(1) +============== + +NAME +---- +git-ls-tree - List the contents of a tree object + + +SYNOPSIS +-------- +[verse] +'git-ls-tree' [-d] [-r] [-t] [-z] + [--name-only] [--name-status] [--full-name] [--abbrev=[<n>]] + <tree-ish> [paths...] + +DESCRIPTION +----------- +Lists the contents of a given tree object, like what "/bin/ls -a" does +in the current working directory. Note that the usage is subtly different, +though - 'paths' denote just a list of patterns to match, e.g. so specifying +directory name (without '-r') will behave differently, and order of the +arguments does not matter. + +OPTIONS +------- +<tree-ish>:: + Id of a tree-ish. + +-d:: + Show only the named tree entry itself, not its children. + +-r:: + Recurse into sub-trees. + +-t:: + Show tree entries even when going to recurse them. Has no effect + if '-r' was not passed. '-d' implies '-t'. + +-z:: + \0 line termination on output. + +--name-only:: +--name-status:: + List only filenames (instead of the "long" output), one per line. + +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + +--full-name:: + Instead of showing the path names relative to the current working + directory, show the full path names. + +paths:: + When paths are given, show them (note that this isn't really raw + pathnames, but rather a list of patterns to match). Otherwise + implicitly uses the root level of the tree as the sole path argument. + + +Output Format +------------- + <mode> SP <type> SP <object> TAB <file> + +When the `-z` option is not used, TAB, LF, and backslash characters +in pathnames are represented as `\t`, `\n`, and `\\`, respectively. + + +Author +------ +Written by Petr Baudis <pasky@suse.cz> +Completely rewritten from scratch by Junio C Hamano <junkio@cox.net>, +another major rewrite 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-mailinfo.txt b/Documentation/git-mailinfo.txt new file mode 100644 index 0000000000..ba18133ead --- /dev/null +++ b/Documentation/git-mailinfo.txt @@ -0,0 +1,70 @@ +git-mailinfo(1) +=============== + +NAME +---- +git-mailinfo - Extracts patch and authorship from a single e-mail message + + +SYNOPSIS +-------- +'git-mailinfo' [-k] [-u | --encoding=<encoding>] <msg> <patch> + + +DESCRIPTION +----------- +Reading a single e-mail message from the standard input, and +writes the commit log message in <msg> file, and the patches in +<patch> file. The author name, e-mail and e-mail subject are +written out to the standard output to be used by git-applypatch +to create a commit. It is usually not necessary to use this +command directly. See gitlink:git-am[1] instead. + + +OPTIONS +------- +-k:: + Usually the program 'cleans up' the Subject: header line + to extract the title line for the commit log message, + among which (1) remove 'Re:' or 're:', (2) leading + whitespaces, (3) '[' up to ']', typically '[PATCH]', and + then prepends "[PATCH] ". This flag forbids this + munging, and is most useful when used to read back 'git + format-patch --mbox' output. + +-u:: + 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 + from what is specified by i18n.commitencoding, this flag + can be used to override it. + +<msg>:: + The commit log message extracted from e-mail, usually + except the title line which comes from e-mail Subject. + +<patch>:: + The patch extracted from e-mail. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +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-mailsplit.txt b/Documentation/git-mailsplit.txt new file mode 100644 index 0000000000..c11d6a530f --- /dev/null +++ b/Documentation/git-mailsplit.txt @@ -0,0 +1,52 @@ +git-mailsplit(1) +================ + +NAME +---- +git-mailsplit - Simple UNIX mbox splitter program + +SYNOPSIS +-------- +'git-mailsplit' [-b] [-f<nn>] [-d<prec>] -o<directory> [--] [<mbox>...] + +DESCRIPTION +----------- +Splits a mbox file into a list of files: "0001" "0002" .. in the specified +directory so you can process them further from there. + +OPTIONS +------- +<mbox>:: + Mbox file to split. If not given, the mbox is read from + the standard input. + +<directory>:: + Directory in which to place the individual messages. + +-b:: + If any file doesn't begin with a From line, assume it is a + single mail message instead of signaling error. + +-d<prec>:: + Instead of the default 4 digits with leading zeros, + different precision can be specified for the generated + filenames. + +-f<nn>:: + Skip the first <nn> numbers, for example if -f3 is specified, + start the numbering with 0004. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> +and 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-merge-base.txt b/Documentation/git-merge-base.txt new file mode 100644 index 0000000000..3190aed108 --- /dev/null +++ b/Documentation/git-merge-base.txt @@ -0,0 +1,43 @@ +git-merge-base(1) +================= + +NAME +---- +git-merge-base - Find as good common ancestors as possible for a merge + + +SYNOPSIS +-------- +'git-merge-base' [--all] <commit> <commit> + +DESCRIPTION +----------- + +"git-merge-base" finds as good a common ancestor as possible between +the two commits. That is, given two commits A and B 'git-merge-base A +B' will output a commit which is reachable from both A and B through +the parent relationship. + +Given a selection of equally good common ancestors it should not be +relied on to decide in any particular way. + +The "git-merge-base" algorithm is still in flux - use the source... + +OPTIONS +------- +--all:: + Output all common ancestors for the two commits instead of + just one. + +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-merge-file.txt b/Documentation/git-merge-file.txt new file mode 100644 index 0000000000..31882abb87 --- /dev/null +++ b/Documentation/git-merge-file.txt @@ -0,0 +1,92 @@ +git-merge-file(1) +================= + +NAME +---- +git-merge-file - Run a 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 new file mode 100644 index 0000000000..b8ee1ff2b0 --- /dev/null +++ b/Documentation/git-merge-index.txt @@ -0,0 +1,88 @@ +git-merge-index(1) +================== + +NAME +---- +git-merge-index - Run a merge for files needing merging + + +SYNOPSIS +-------- +'git-merge-index' [-o] [-q] <merge-program> (-a | \-- | <file>\*) + +DESCRIPTION +----------- +This looks up the <file>(s) in the index and, if there are any merge +entries, passes the SHA1 hash for those files as arguments 1, 2, 3 (empty +argument if no file), and <file> as argument 4. File modes for the three +files are passed as arguments 5, 6 and 7. + +OPTIONS +------- +\--:: + Do not interpret any more arguments as options. + +-a:: + Run merge against all files in the index that need merging. + +-o:: + Instead of stopping at the first failed merge, do all of them + in one shot - continue with merging even when previous merges + returned errors, and only return the error code after all the + merges are over. + +-q:: + Do not complain about failed merge program (the merge program + failure usually indicates conflicts during merge). This is for + porcelains which might want to emit custom messages. + +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 git's imitation of +the merge command from the RCS package. + +A sample script called "git-merge-one-file" is included in the +distribution. + +ALERT ALERT ALERT! The git "merge object order" is different from the +RCS "merge" program merge object order. In the above ordering, the +original is first. But the argument order to the 3-way merge program +"merge" is to have the original in the middle. Don't ask me why. + +Examples: + + torvalds@ppc970:~/merge-test> git-merge-index cat MM + This is MM from the original tree. # original + This is modified MM in the branch A. # merge1 + This is modified MM in the branch B. # merge2 + This is modified MM in the branch B. # current contents + +or + + torvalds@ppc970:~/merge-test> git-merge-index cat AA MM + cat: : No such file or directory + This is added AA in the branch A. + This is added AA in the branch B. + This is added AA in the branch B. + fatal: merge program failed + +where the latter example shows how "git-merge-index" will stop trying to +merge once anything has returned an error (i.e., "cat" returned an error +for the AA file, because it didn't exist in the original, and thus +"git-merge-index" didn't even try to merge the MM thing). + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> +One-shot merge by Petr Baudis <pasky@ucw.cz> + +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-merge-one-file.txt b/Documentation/git-merge-one-file.txt new file mode 100644 index 0000000000..f80ab3b8c4 --- /dev/null +++ b/Documentation/git-merge-one-file.txt @@ -0,0 +1,30 @@ +git-merge-one-file(1) +===================== + +NAME +---- +git-merge-one-file - The standard helper program to use with git-merge-index + + +SYNOPSIS +-------- +'git-merge-one-file' + +DESCRIPTION +----------- +This is the standard helper program to use with "git-merge-index" +to resolve a merge after the trivial merge done with "git-read-tree -m". + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org>, +Junio C Hamano <junkio@cox.net> and Petr Baudis <pasky@suse.cz>. + +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-merge-tree.txt b/Documentation/git-merge-tree.txt new file mode 100644 index 0000000000..35fb4fb713 --- /dev/null +++ b/Documentation/git-merge-tree.txt @@ -0,0 +1,37 @@ +git-merge-tree(1) +================= + +NAME +---- +git-merge-tree - Show three-way merge without touching index + + +SYNOPSIS +-------- +'git-merge-tree' <base-tree> <branch1> <branch2> + +DESCRIPTION +----------- +Reads three treeish, and output trivial merge results and +conflicting stages to the standard output. This is similar to +what three-way read-tree -m does, but instead of storing the +results in the index, the command outputs the entries to the +standard output. + +This is meant to be used by higher level scripts to compute +merge results outside index, and stuff the results back into the +index. For this reason, the output from the command omits +entries that match <branch1> tree. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-merge.txt b/Documentation/git-merge.txt new file mode 100644 index 0000000000..9c08efa53a --- /dev/null +++ b/Documentation/git-merge.txt @@ -0,0 +1,160 @@ +git-merge(1) +============ + +NAME +---- +git-merge - Join two or more development histories together + + +SYNOPSIS +-------- +[verse] +'git-merge' [-n] [--no-commit] [--squash] [-s <strategy>]... + [-m <msg>] <remote> <remote>... + +DESCRIPTION +----------- +This is the top-level interface to the merge machinery +which drives multiple merge strategy scripts. + + +OPTIONS +------- +include::merge-options.txt[] + +<msg>:: + The commit message to be used for the merge commit (in case + it is created). The `git-fmt-merge-msg` script can be used + to give a good default for automated `git-merge` invocations. + +<head>:: + 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 + least one <remote>. Specifying more than one <remote> + obviously means you are trying an Octopus. + +include::merge-strategies.txt[] + + +If you tried a merge which resulted in a complex conflicts and +would want to start over, you can recover with +gitlink:git-reset[1]. + + +HOW MERGE WORKS +--------------- + +A merge is always between the current `HEAD` and one or more +remote branch heads, and the index file must exactly match the +tree of `HEAD` commit (i.e. the contents of the last commit) when +it happens. In other words, `git-diff --cached HEAD` must +report no changes. + +[NOTE] +This is a bit of lie. In certain special cases, your index are +allowed to be different from the tree of `HEAD` commit. The most +notable case is when your `HEAD` commit is already ahead of what +is being merged, in which case your index can have arbitrary +difference from your `HEAD` commit. Otherwise, your index entries +are allowed have differences from your `HEAD` commit that match +the result of trivial merge (e.g. you received the same patch +from external source to produce the same result as what you are +merging). For example, if a path did not exist in the common +ancestor and your head commit but exists in the tree you are +merging into your repository, and if you already happen to have +that path exactly in your index, the merge does not have to +fail. + +Otherwise, merge will refuse to do any harm to your repository +(that is, it may fetch the objects from remote, and it may even +update the local branch used to keep track of the remote branch +with `git pull remote rbranch:lbranch`, but your working tree, +`.git/HEAD` pointer and index file are left intact). + +You may have local modifications in the working tree files. In +other words, `git-diff` is allowed to report changes. +However, the merge uses your working tree as the working area, +and in order to prevent the merge operation from losing such +changes, it makes sure that they do not interfere with the +merge. Those complex tables in read-tree documentation define +what it means for a path to "interfere with the merge". And if +your local modifications interfere with the merge, again, it +stops before touching anything. + +So in the above two "failed merge" case, you do not have to +worry about loss of data --- you simply were not ready to do +a merge, so no merge happened at all. You may want to finish +whatever you were in the middle of doing, and retry the same +pull after you are done and ready. + +When things cleanly merge, these things happen: + +1. the results are updated both in the index file and in your + working tree, +2. index file is written out as a tree, +3. the tree gets committed, and +4. the `HEAD` pointer gets advanced. + +Because of 2., we require that the original state of the index +file to match exactly the current `HEAD` commit; otherwise we +will write out your local changes already registered in your +index file along with the merge result, which is not good. +Because 1. involves only the paths different between your +branch and the remote branch you are pulling from during the +merge (which is typically a fraction of the whole tree), you can +have local modifications in your working tree as long as they do +not overlap with what the merge updates. + +When there are conflicts, these things happen: + +1. `HEAD` stays the same. + +2. Cleanly merged paths are updated both in the index file and + in your working tree. + +3. For conflicting paths, the index file records up to three + versions; stage1 stores the version from the common ancestor, + stage2 from `HEAD`, and stage3 from the remote branch (you + can inspect the stages with `git-ls-files -u`). The working + tree files have the result of "merge" program; i.e. 3-way + merge result with familiar conflict markers `<<< === >>>`. + +4. No other changes are done. In particular, the local + modifications you had before you started merge will stay the + same and the index entries for them stay as they were, + i.e. matching `HEAD`. + +After seeing a conflict, you can do two things: + + * Decide not to merge. The only clean-up you need are to reset + the index file to the `HEAD` commit to reverse 2. and to clean + up working tree changes made by 2. and 3.; `git-reset` can + be used for this. + + * Resolve the conflicts. `git-diff` would report only the + conflicting paths because of the above 2. and 3.. Edit the + working tree files into a desirable shape, `git-add` or `git-rm` + them, to make the index file contain what the merge result + should be, and run `git-commit` to commit the result. + + +SEE ALSO +-------- +gitlink:git-fmt-merge-msg[1], gitlink:git-pull[1] + + +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-mktag.txt b/Documentation/git-mktag.txt new file mode 100644 index 0000000000..2860a3d1ba --- /dev/null +++ b/Documentation/git-mktag.txt @@ -0,0 +1,47 @@ +git-mktag(1) +============ + +NAME +---- +git-mktag - Creates a tag object + + +SYNOPSIS +-------- +'git-mktag' < signature_file + +DESCRIPTION +----------- +Reads a tag contents on standard input and creates a tag object +that can also be used to sign other objects. + +The output is the new tag's <object> identifier. + +Tag Format +---------- +A tag signature file has a very simple fixed format: three lines of + + object <sha1> + type <typename> + tag <tagname> + +followed by some 'optional' free-form signature that git itself +doesn't care about, but that can be verified with gpg or similar. + +The size of the full object is artificially limited to 8kB. (Just +because I'm a lazy bastard, and if you can't fit a signature in that +size, you're doing something wrong) + + +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-mktree.txt b/Documentation/git-mktree.txt new file mode 100644 index 0000000000..5f9ee603b7 --- /dev/null +++ b/Documentation/git-mktree.txt @@ -0,0 +1,35 @@ +git-mktree(1) +============= + +NAME +---- +git-mktree - Build a tree-object from ls-tree formatted text + + +SYNOPSIS +-------- +'git-mktree' [-z] + +DESCRIPTION +----------- +Reads standard input in non-recursive `ls-tree` output format, +and creates a tree object. The object name of the tree object +built is written to the standard output. + +OPTIONS +------- +-z:: + Read the NUL-terminated `ls-tree -z` output instead. + +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-mv.txt b/Documentation/git-mv.txt new file mode 100644 index 0000000000..6756b76bb1 --- /dev/null +++ b/Documentation/git-mv.txt @@ -0,0 +1,54 @@ +git-mv(1) +========= + +NAME +---- +git-mv - Move or rename a file, a directory, or a symlink + + +SYNOPSIS +-------- +'git-mv' <options>... <args>... + +DESCRIPTION +----------- +This script is used to move or rename a file, directory or symlink. + + git-mv [-f] [-n] <source> <destination> + git-mv [-f] [-n] [-k] <source> ... <destination directory> + +In the first form, it renames <source>, which must exist and be either +a file, symlink or directory, to <destination>. +In the second form, the last argument has to be an existing +directory; the given sources will be moved into this directory. + +The index is updated after successful completion, but the change must still be +committed. + +OPTIONS +------- +-f:: + Force renaming or moving of a file even if the target exists +-k:: + Skip move or rename actions which would lead to an error + condition. An error happens when a source is neither existing nor + controlled by GIT, or when it would overwrite an existing + file unless '-f' is given. +-n:: + Do nothing; only show what would happen + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> +Rewritten by Ryan Anderson <ryan@michonline.com> +Move functionality added by Josef Weidendorfer <Josef.Weidendorfer@gmx.de> + +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-name-rev.txt b/Documentation/git-name-rev.txt new file mode 100644 index 0000000000..5b5c4c865f --- /dev/null +++ b/Documentation/git-name-rev.txt @@ -0,0 +1,71 @@ +git-name-rev(1) +=============== + +NAME +---- +git-name-rev - Find symbolic names for given revs + + +SYNOPSIS +-------- +'git-name-rev' [--tags] [--refs=<pattern>] + ( --all | --stdin | <committish>... ) + +DESCRIPTION +----------- +Finds symbolic names suitable for human digestion for revisions given in any +format parsable by git-rev-parse. + + +OPTIONS +------- + +--tags:: + Do not use branch names, but only tags to name the commits + +--refs=<pattern>:: + Only use refs whose names match a given shell pattern. + +--all:: + List all commits reachable from all refs + +--stdin:: + Read from stdin, append "(<rev_name>)" to all sha1's of nameable + commits, and pass to stdout + +EXAMPLE +------- + +Given a commit, find out where it is relative to the local refs. Say somebody +wrote you about that fantastic commit 33db5f4d9027a10e477ccf054b2c1ab94f74c85a. +Of course, you look into the commit, but that only tells you what happened, but +not the context. + +Enter git-name-rev: + +------------ +% git name-rev 33db5f4d9027a10e477ccf054b2c1ab94f74c85a +33db5f4d9027a10e477ccf054b2c1ab94f74c85a tags/v0.99^0~940 +------------ + +Now you are wiser, because you know that it happened 940 revisions before v0.99. + +Another nice thing you can do is: + +------------ +% git log | git name-rev --stdin +------------ + + +Author +------ +Written by Johannes Schindelin <Johannes.Schindelin@gmx.de> + +Documentation +-------------- +Documentation by Johannes Schindelin. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-p4import.txt b/Documentation/git-p4import.txt new file mode 100644 index 0000000000..6edb9f12b8 --- /dev/null +++ b/Documentation/git-p4import.txt @@ -0,0 +1,168 @@ +git-p4import(1) +=============== + +NAME +---- +git-p4import - Import a Perforce repository into git + + +SYNOPSIS +-------- +`git-p4import` [-q|-v] [--notags] [--authors <file>] [-t <timezone>] <//p4repo/path> <branch> + +`git-p4import` --stitch <//p4repo/path> + +`git-p4import` + + +DESCRIPTION +----------- +Import a Perforce repository into an existing git repository. When +a <//p4repo/path> and <branch> are specified a new branch with the +given name will be created and the initial import will begin. + +Once the initial import is complete you can do an incremental import +of new commits from the Perforce repository. You do this by checking +out the appropriate git branch and then running `git-p4import` without +any options. + +The standard p4 client is used to communicate with the Perforce +repository; it must be configured correctly in order for `git-p4import` +to operate (see below). + + +OPTIONS +------- +-q:: + Do not display any progress information. + +-v:: + Give extra progress information. + +\--authors:: + Specify an authors file containing a mapping of Perforce user + ids to full names and email addresses (see Notes below). + +\--notags:: + Do not create a tag for each imported commit. + +\--stitch:: + Import the contents of the given perforce branch into the + currently checked out git branch. + +\--log:: + Store debugging information in the specified file. + +-t:: + Specify that the remote repository is in the specified timezone. + Timezone must be in the format "US/Pacific" or "Europe/London" + etc. You only need to specify this once, it will be saved in + the git config file for the repository. + +<//p4repo/path>:: + The Perforce path that will be imported into the specified branch. + +<branch>:: + The new branch that will be created to hold the Perforce imports. + + +P4 Client +--------- +You must make the `p4` client command available in your $PATH and +configure it to communicate with the target Perforce repository. +Typically this means you must set the "$P4PORT" and "$P4CLIENT" +environment variables. + +You must also configure a `p4` client "view" which maps the Perforce +branch into the top level of your git repository, for example: + +------------ +Client: myhost + +Root: /home/sean/import + +Options: noallwrite clobber nocompress unlocked modtime rmdir + +View: + //public/jam/... //myhost/jam/... +------------ + +With the above `p4` client setup, you could import the "jam" +perforce branch into a branch named "jammy", like so: + +------------ +$ mkdir -p /home/sean/import/jam +$ cd /home/sean/import/jam +$ git init +$ git p4import //public/jam jammy +------------ + + +Multiple Branches +----------------- +Note that by creating multiple "views" you can use `git-p4import` +to import additional branches into the same git repository. +However, the `p4` client has a limitation in that it silently +ignores all but the last "view" that maps into the same local +directory. So the following will *not* work: + +------------ +View: + //public/jam/... //myhost/jam/... + //public/other/... //myhost/jam/... + //public/guest/... //myhost/jam/... +------------ + +If you want more than one Perforce branch to be imported into the +same directory you must employ a workaround. A simple option is +to adjust your `p4` client before each import to only include a +single view. + +Another option is to create multiple symlinks locally which all +point to the same directory in your git repository and then use +one per "view" instead of listing the actual directory. + + +Tags +---- +A git tag of the form p4/xx is created for every change imported from +the Perforce repository where xx is the Perforce changeset number. +Therefore after the import you can use git to access any commit by its +Perforce number, e.g. git show p4/327. + +The tag associated with the HEAD commit is also how `git-p4import` +determines if there are new changes to incrementally import from the +Perforce repository. + +If you import from a repository with many thousands of changes +you will have an equal number of p4/xxxx git tags. Git tags can +be expensive in terms of disk space and repository operations. +If you don't need to perform further incremental imports, you +may delete the tags. + + +Notes +----- +You can interrupt the import (e.g. ctrl-c) at any time and restart it +without worry. + +Author information is automatically determined by querying the +Perforce "users" table using the id associated with each change. +However, if you want to manually supply these mappings you can do +so with the "--authors" option. It accepts a file containing a list +of mappings with each line containing one mapping in the format: + +------------ + perforce_id = Full Name <email@address.com> +------------ + + +Author +------ +Written by Sean Estabrooks <seanlkml@sympatico.ca> + + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt new file mode 100644 index 0000000000..fdc6f97289 --- /dev/null +++ b/Documentation/git-pack-objects.txt @@ -0,0 +1,159 @@ +git-pack-objects(1) +=================== + +NAME +---- +git-pack-objects - Create a packed archive of objects + + +SYNOPSIS +-------- +[verse] +'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 +----------- +Reads list of objects from the standard input, and writes a packed +archive with specified base-name, or to the standard output. + +A packed archive is an efficient way to transfer set of objects +between two repositories, and also is an archival format which +is efficient to access. The packed archive format (.pack) is +designed to be unpackable without having anything else, but for +random access, accompanied with the pack index file (.idx). + +'git-unpack-objects' command can read the packed archive and +expand the objects contained in the pack into "one-file +one-object" format; this is typically done by the smart-pull +commands when a pack is created on-the-fly for efficient network +transport by their peers. + +Placing both in the pack/ subdirectory of $GIT_OBJECT_DIRECTORY (or +any of the directories on $GIT_ALTERNATE_OBJECT_DIRECTORIES) +enables git to read from such an archive. + +In a packed archive, an object is either stored as a compressed +whole, or as a difference from some other object. The latter is +often called a delta. + + +OPTIONS +------- +base-name:: + Write into a pair of files (.pack and .idx), using + <base-name> to determine the name of the created file. + When this option is used, the two files are written in + <base-name>-<SHA1>.{pack,idx} files. <SHA1> is a hash + of the sorted object names to make the resulting filename + based on the pack content, and written to the standard + output of the command. + +--stdout:: + Write the pack contents (what would have been written to + .pack file) out to the standard output. + +--revs:: + Read the revision arguments from the standard input, instead of + individual object names. The revision arguments are processed + the same way as gitlink:git-rev-list[1] with `--objects` flag + uses its `commit` arguments to build the list of objects it + outputs. The objects on the resulting list are packed. + +--unpacked:: + This implies `--revs`. When processing the list of + revision arguments read from the standard input, limit + the objects packed to those that are not already packed. + +--all:: + This implies `--revs`. In addition to the list of + revision arguments read from the standard input, pretend + as if all refs under `$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 + 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. + +--incremental:: + This flag causes an object already in a pack ignored + even if it appears in the standard input. + +--local:: + This flag is similar to `--incremental`; instead of + ignoring all packed objects, it only ignores objects + that are packed and not in the local object store + (i.e. borrowed from an alternate). + +--non-empty:: + 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. + +--no-reuse-delta:: + When creating a packed archive in a repository that + has existing packs, the command reuses existing deltas. + This sometimes results in a slightly suboptimal pack. + 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 +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +------------- +Documentation by Junio C Hamano + +See Also +-------- +gitlink:git-rev-list[1] +gitlink:git-repack[1] +gitlink:git-prune-packed[1] + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-pack-redundant.txt b/Documentation/git-pack-redundant.txt new file mode 100644 index 0000000000..94bbea0db2 --- /dev/null +++ b/Documentation/git-pack-redundant.txt @@ -0,0 +1,58 @@ +git-pack-redundant(1) +===================== + +NAME +---- +git-pack-redundant - Find redundant pack files + + +SYNOPSIS +-------- +'git-pack-redundant' [ --verbose ] [ --alt-odb ] < --all | .pack filename ... > + +DESCRIPTION +----------- +This program computes which packs in your repository +are redundant. The output is suitable for piping to +'xargs rm' if you are in the root of the repository. + +git-pack-redundant accepts a list of objects on standard input. Any objects +given will be ignored when checking which packs are required. This makes the +following command useful when wanting to remove packs which contain unreachable +objects. + +git-fsck --full --unreachable | cut -d ' ' -f3 | \ +git-pack-redundant --all | xargs rm + +OPTIONS +------- + + +--all:: + Processes all packs. Any filenames on the command line are ignored. + +--alt-odb:: + Don't require objects present in packs from alternate object + directories to be present in local packs. + +--verbose:: + Outputs some statistics to stderr. Has a small performance penalty. + +Author +------ +Written by Lukas Sandström <lukass@etek.chalmers.se> + +Documentation +-------------- +Documentation by Lukas Sandström <lukass@etek.chalmers.se> + +See Also +-------- +gitlink:git-pack-objects[1] +gitlink:git-repack[1] +gitlink:git-prune-packed[1] + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-pack-refs.txt b/Documentation/git-pack-refs.txt new file mode 100644 index 0000000000..a20fc7de40 --- /dev/null +++ b/Documentation/git-pack-refs.txt @@ -0,0 +1,66 @@ +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. + +A recommended practice to deal with a repository with too many +refs is to pack its refs with `--all --prune` once, and +occasionally run `git-pack-refs \--prune`. Tags are by +definition stationary and are not expected to change. Branch +heads will be packed with the initial `pack-refs --all`, but +only the currently active branch heads will become unpacked, +and next `pack-refs` (without `--all`) will leave them +unpacked. + + +OPTIONS +------- + +\--all:: + +The command by default packs all tags and refs that are already +packed, and leaves other refs +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-parse-remote.txt b/Documentation/git-parse-remote.txt new file mode 100644 index 0000000000..11b1f4d2e2 --- /dev/null +++ b/Documentation/git-parse-remote.txt @@ -0,0 +1,50 @@ +git-parse-remote(1) +=================== + +NAME +---- +git-parse-remote - Routines to help parsing remote repository access parameters + + +SYNOPSIS +-------- +'. git-parse-remote' + +DESCRIPTION +----------- +This script is included in various scripts to supply +routines to parse files under $GIT_DIR/remotes/ and +$GIT_DIR/branches/ and configuration variables that are related +to fetching, pulling and pushing. + +The primary entry points are: + +get_remote_refs_for_fetch:: + Given the list of user-supplied `<repo> <refspec>...`, + return the list of refs to fetch after canonicalizing + them into `$GIT_DIR` relative paths + (e.g. `refs/heads/foo`). When `<refspec>...` is empty + the returned list of refs consists of the defaults + for the given `<repo>`, if specified in + `$GIT_DIR/remotes/`, `$GIT_DIR/branches/`, or `remote.*.fetch` + configuration. + +get_remote_refs_for_push:: + Given the list of user-supplied `<repo> <refspec>...`, + return the list of refs to push in a form suitable to be + fed to the `git-send-pack` command. When `<refspec>...` + is empty the returned list of refs consists of the + defaults for the given `<repo>`, if specified in + `$GIT_DIR/remotes/`. + +Author +------ +Written by Junio C Hamano. + +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-patch-id.txt b/Documentation/git-patch-id.txt new file mode 100644 index 0000000000..a7e9fd021a --- /dev/null +++ b/Documentation/git-patch-id.txt @@ -0,0 +1,43 @@ +git-patch-id(1) +=============== + +NAME +---- +git-patch-id - Compute unique ID for a patch + +SYNOPSIS +-------- +'git-patch-id' < <patch> + +DESCRIPTION +----------- +A "patch ID" is nothing but a SHA1 of the diff associated with a patch, with +whitespace and line numbers ignored. As such, it's "reasonably stable", but at +the same time also reasonably unique, i.e., two patches that have the same "patch +ID" are almost guaranteed to be the same thing. + +IOW, you can use this thing to look for likely duplicate commits. + +When dealing with git-diff-tree output, it takes advantage of +the fact that the patch is prefixed with the object name of the +commit, and outputs two 40-byte hexadecimal string. The first +string is the patch ID, and the second string is the commit ID. +This can be used to make a mapping from patch ID to commit ID. + +OPTIONS +------- +<patch>:: + The diff to create the ID of. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-peek-remote.txt b/Documentation/git-peek-remote.txt new file mode 100644 index 0000000000..74f37bd904 --- /dev/null +++ b/Documentation/git-peek-remote.txt @@ -0,0 +1,55 @@ +git-peek-remote(1) +================== + +NAME +---- +git-peek-remote - List the references in a remote repository + + +SYNOPSIS +-------- +'git-peek-remote' [--upload-pack=<git-upload-pack>] [<host>:]<directory> + +DESCRIPTION +----------- +Lists the references the remote repository has, and optionally +stores them in the local repository under the same name. + +OPTIONS +------- +\--upload-pack=<git-upload-pack>:: + Use this to specify the path to 'git-upload-pack' on the + remote side, if it is not found on your $PATH. Some + installations of sshd ignores the user's environment + setup scripts for login shells (e.g. .bash_profile) and + your privately installed git may not be found on the system + default $PATH. Another workaround suggested is to set + up your $PATH in ".bashrc", but this flag is for people + who do not want to pay the overhead for non-interactive + shells, but prefer having a lean .bashrc file (they set most of + the things up in .bash_profile). + +\--exec=<git-upload-pack>:: + Same \--upload-pack=<git-upload-pack>. + +<host>:: + A remote host that houses the repository. When this + part is specified, 'git-upload-pack' is invoked via + ssh. + +<directory>:: + The repository to sync from. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-prune-packed.txt b/Documentation/git-prune-packed.txt new file mode 100644 index 0000000000..310033e460 --- /dev/null +++ b/Documentation/git-prune-packed.txt @@ -0,0 +1,53 @@ +git-prune-packed(1) +===================== + +NAME +---- +git-prune-packed - Remove extra objects that are already in pack files + + +SYNOPSIS +-------- +'git-prune-packed' [-n] [-q] + + +DESCRIPTION +----------- +This program search the `$GIT_OBJECT_DIR` for all objects that currently +exist in a pack file as well as the independent object directories. + +All such extra objects are removed. + +A pack is a collection of objects, individually compressed, with delta +compression applied, stored in a single file, with an associated index file. + +Packs are used to reduce the load on mirror systems, backup engines, +disk storage, etc. + + +OPTIONS +------- +-n:: + 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> + +Documentation +-------------- +Documentation by Ryan Anderson <ryan@michonline.com> + +See Also +-------- +gitlink:git-pack-objects[1] +gitlink:git-repack[1] + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-prune.txt b/Documentation/git-prune.txt new file mode 100644 index 0000000000..0b44f3015d --- /dev/null +++ b/Documentation/git-prune.txt @@ -0,0 +1,61 @@ +git-prune(1) +============ + +NAME +---- +git-prune - Prunes all unreachable objects from the object database + + +SYNOPSIS +-------- +'git-prune' [-n] [--] [<head>...] + +DESCRIPTION +----------- + +This runs `git-fsck --unreachable` using all the refs +available in `$GIT_DIR/refs`, optionally with additional set of +objects specified on the command line, and prunes all +objects unreachable from any of these head objects from the object database. +In addition, it +prunes the unpacked objects that are also found in packs by +running `git prune-packed`. + +OPTIONS +------- + +-n:: + Do not remove anything; just report what it would + remove. + +\--:: + Do not interpret any more arguments as options. + +<head>...:: + In addition to objects + reachable from any of our references, keep objects + reachable from listed <head>s. + +EXAMPLE +------- + +To prune objects not used by your repository nor another that +borrows from your repository via its +`.git/objects/info/alternates`: + +------------ +$ git prune $(cd ../another && $(git-rev-parse --all)) +------------ + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-pull.txt b/Documentation/git-pull.txt new file mode 100644 index 0000000000..94478ed94d --- /dev/null +++ b/Documentation/git-pull.txt @@ -0,0 +1,168 @@ +git-pull(1) +=========== + +NAME +---- +git-pull - Fetch from and merge with another repository or a local branch + + +SYNOPSIS +-------- +'git-pull' <options> <repository> <refspec>... + + +DESCRIPTION +----------- +Runs `git-fetch` with the given parameters, and calls `git-merge` +to merge the retrieved head(s) into the current branch. + +Note that you can use `.` (current directory) as the +<repository> to pull from the local repository -- this is useful +when merging local branches into the current branch. + + +OPTIONS +------- +include::merge-options.txt[] + +include::fetch-options.txt[] + +include::pull-fetch-param.txt[] + +include::urls.txt[] + +include::merge-strategies.txt[] + +DEFAULT BEHAVIOUR +----------------- + +Often people use `git pull` without giving any parameter. +Traditionally, this has been equivalent to saying `git pull +origin`. However, when configuration `branch.<name>.remote` is +present while on branch `<name>`, that value is used instead of +`origin`. + +In order to determine what URL to use to fetch from, the value +of the configuration `remote.<origin>.url` is consulted +and if there is not any such variable, the value on `URL: ` line +in `$GIT_DIR/remotes/<origin>` file is used. + +In order to determine what remote branches to fetch (and +optionally store in the tracking branches) when the command is +run without any refspec parameters on the command line, values +of the configuration variable `remote.<origin>.fetch` are +consulted, and if there aren't any, `$GIT_DIR/remotes/<origin>` +file is consulted and its `Pull: ` lines are used. +In addition to the refspec formats described in the OPTIONS +section, you can have a globbing refspec that looks like this: + +------------ +refs/heads/*:refs/remotes/origin/* +------------ + +A globbing refspec must have a non-empty RHS (i.e. must store +what were fetched in tracking branches), and its LHS and RHS +must end with `/*`. The above specifies that all remote +branches are tracked using tracking branches in +`refs/remotes/origin/` hierarchy under the same name. + +The rule to determine which remote branch to merge after +fetching is a bit involved, in order not to break backward +compatibility. + +If explicit refspecs were given on the command +line of `git pull`, they are all merged. + +When no refspec was given on the command line, then `git pull` +uses the refspec from the configuration or +`$GIT_DIR/remotes/<origin>`. In such cases, the following +rules apply: + +. If `branch.<name>.merge` configuration for the current + branch `<name>` exists, that is the name of the branch at the + remote site that is merged. + +. If the refspec is a globbing one, nothing is merged. + +. Otherwise the remote branch of the first refspec is merged. + + +EXAMPLES +-------- + +git pull, git pull origin:: + 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-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. This `git pull .` + syntax is equivalent to `git 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 + when you want to include further changes to the merge, + or want to write your own merge commit message. ++ +You should refrain from abusing this option to sneak substantial +changes into a merge commit. Small fixups like bumping +release/version name would be acceptable. + +Command line pull of multiple branches from one repository:: ++ +------------------------------------------------ +$ git checkout master +$ git fetch origin +pu:pu maint:tmp +$ git pull . tmp +------------------------------------------------ ++ +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. ++ +The `pu` branch will be updated even if it is does not +fast-forward; the others will not be. ++ +The final command then merges the newly fetched `tmp` into master. + + +If you tried a pull which resulted in a complex conflicts and +would want to start over, you can recover with +gitlink:git-reset[1]. + + +SEE ALSO +-------- +gitlink:git-fetch[1], gitlink:git-merge[1], gitlink:git-config[1] + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> +and Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Jon Loeliger, +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-push.txt b/Documentation/git-push.txt new file mode 100644 index 0000000000..f8cc2b5432 --- /dev/null +++ b/Documentation/git-push.txt @@ -0,0 +1,111 @@ +git-push(1) +=========== + +NAME +---- +git-push - Update remote refs along with associated objects + + +SYNOPSIS +-------- +'git-push' [--all] [--tags] [--receive-pack=<git-receive-pack>] [--repo=all] [-f | --force] [-v] [<repository> <refspec>...] + +DESCRIPTION +----------- + +Updates remote refs using local refs, while sending objects +necessary to complete the given refs. + +You can make interesting things happen to a repository +every time you push into it, by setting up 'hooks' there. See +documentation for gitlink:git-receive-pack[1]. + + +OPTIONS +------- +<repository>:: + The "remote" repository that is destination of a push + operation. See the section <<URLS,GIT URLS>> below. + +<refspec>:: + The canonical format of a <refspec> parameter is + `+?<src>:<dst>`; that is, an optional plus `+`, followed + by the source ref, followed by a colon `:`, followed by + the destination ref. ++ +The <src> side can be an +arbitrary "SHA1 expression" that can be used as an +argument to `git-cat-file -t`. E.g. `master~4` (push +four parents before the current master head). ++ +The local ref that matches <src> is used +to fast forward the remote ref that matches <dst>. If +the optional plus `+` is used, the remote ref is updated +even if it does not result in a fast forward update. ++ +Note: If no explicit refspec is found, (that is neither +on the command line nor in any Push line of the +corresponding remotes file---see below), then all the +refs that exist both on the local side and on the remote +side are updated. ++ +`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. ++ +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 + refs be pushed. + +\--tags:: + All refs under `$GIT_DIR/refs/tags` are pushed, in + addition to refspecs explicitly listed on the command + line. + +\--receive-pack=<git-receive-pack>:: + Path to the 'git-receive-pack' program on the remote + end. Sometimes useful when pushing to a remote + repository over ssh, and you do not have the program in + a directory on the default $PATH. + +\--exec=<git-receive-pack>:: + Same as \--receive-pack=<git-receive-pack>. + +-f, \--force:: + Usually, the command refuses to update a remote ref that is + not a descendant of the local ref used to overwrite it. + This flag disables the check. This can cause the + remote repository to lose commits; use it with care. + +\--repo=<repo>:: + When no repository is specified the command defaults to + "origin"; this overrides it. + +\--thin, \--no-thin:: + These options are passed to `git-send-pack`. Thin + transfer spends extra cycles to minimize the number of + objects to be sent and meant to be used on slower connection. + +-v:: + Run verbosely. + +include::urls.txt[] + +Author +------ +Written by Junio C Hamano <junkio@cox.net>, later rewritten in C +by Linus Torvalds <torvalds@osdl.org> + +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-quiltimport.txt b/Documentation/git-quiltimport.txt new file mode 100644 index 0000000000..296937a416 --- /dev/null +++ b/Documentation/git-quiltimport.txt @@ -0,0 +1,61 @@ +git-quiltimport(1) +================ + +NAME +---- +git-quiltimport - Applies a quilt patchset onto the current branch + + +SYNOPSIS +-------- +[verse] +'git-quiltimport' [--dry-run] [--author <author>] [--patches <dir>] + + +DESCRIPTION +----------- +Applies a quilt patchset onto the current git branch, preserving +the patch boundaries, patch order, and patch descriptions present +in the quilt patchset. + +For each patch the code attempts to extract the author from the +patch description. If that fails it falls back to the author +specified with --author. If the --author flag was not given +the patch description is displayed and the user is asked to +interactively enter the author of the patch. + +If a subject is not found in the patch description the patch name is +preserved as the 1 line subject in the git description. + +OPTIONS +------- +--dry-run:: + Walk through the patches in the series and warn + if we cannot find all of the necessary information to commit + a patch. At the time of this writing only missing author + information is warned about. + +--author Author Name <Author Email>:: + The author name and email address to use when no author + information can be found in the patch description. + +--patches <dir>:: + The directory to find the quilt patches and the + quilt series file. ++ +The default for the patch directory is patches +or the value of the $QUILT_PATCHES environment +variable. + +Author +------ +Written by Eric Biederman <ebiederm@lnxi.com> + +Documentation +-------------- +Documentation by Eric Biederman <ebiederm@lnxi.com> + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt new file mode 100644 index 0000000000..0ff2890c7f --- /dev/null +++ b/Documentation/git-read-tree.txt @@ -0,0 +1,346 @@ +git-read-tree(1) +================ + +NAME +---- +git-read-tree - Reads tree information into the index + + +SYNOPSIS +-------- +'git-read-tree' (<tree-ish> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] [--exclude-per-directory=<gitignore>] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) + + +DESCRIPTION +----------- +Reads the tree information given by <tree-ish> into the index, +but does not actually *update* any of the files it "caches". (see: +gitlink:git-checkout-index[1]) + +Optionally, it can merge a tree into the index, perform a +fast-forward (i.e. 2-way) merge, or a 3-way merge, with the `-m` +flag. When used with `-m`, the `-u` flag causes it to also update +the files in the work tree with the result of the merge. + +Trivial merges are done by `git-read-tree` itself. Only conflicting paths +will be in unmerged state when `git-read-tree` returns. + +OPTIONS +------- +-m:: + Perform a merge, not just a read. The command will + refuse to run if your index file has unmerged entries, + indicating that you have not finished previous merge you + started. + +--reset:: + Same as -m, except that unmerged entries are discarded + instead of failing. + +-u:: + After a successful merge, update the files in the work + tree with the result of the merge. + +-i:: + Usually a merge requires the index file as well as the + files in the working tree are up to date with the + current head commit, in order not to lose local + changes. This flag disables the check with the working + tree and is meant to be used when creating a merge of + trees that are not directly related to the current + working tree status into a temporary index file. + +--aggressive:: + Usually a three-way merge by `git-read-tree` resolves + the merge for really trivial cases and leaves other + cases unresolved in the index, so that Porcelains can + implement different merge policies. This flag makes the + command to resolve a few more cases internally: ++ +* when one side removes a path and the other side leaves the path + unmodified. The resolution is to remove that path. +* when both sides remove a path. The resolution is to remove that path. +* when both sides adds a path identically. The resolution + is to add that path. + +--prefix=<prefix>/:: + Keep the current index contents, and read the contents + of named tree-ish under directory at `<prefix>`. The + original index file cannot have anything at the path + `<prefix>` itself, and have nothing in `<prefix>/` + 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. + + +Merging +------- +If `-m` is specified, `git-read-tree` can perform 3 kinds of +merge, a single tree merge if only 1 tree is given, a +fast-forward merge with 2 trees, or a 3-way merge if 3 trees are +provided. + + +Single Tree Merge +~~~~~~~~~~~~~~~~~ +If only 1 tree is specified, git-read-tree operates as if the user did not +specify `-m`, except that if the original index has an entry for a +given pathname, and the contents of the path matches with the tree +being read, the stat info from the index is used. (In other words, the +index's stat()s take precedence over the merged tree's). + +That means that if you do a `git-read-tree -m <newtree>` followed by a +`git-checkout-index -f -u -a`, the `git-checkout-index` only checks out +the stuff that really changed. + +This is used to avoid unnecessary false hits when `git-diff-files` is +run after `git-read-tree`. + + +Two Tree Merge +~~~~~~~~~~~~~~ + +Typically, this is invoked as `git-read-tree -m $H $M`, where $H +is the head commit of the current repository, and $M is the head +of a foreign tree, which is simply ahead of $H (i.e. we are in a +fast forward situation). + +When two trees are specified, the user is telling git-read-tree +the following: + + 1. The current index and work tree is derived from $H, but + the user may have local changes in them since $H; + + 2. The user wants to fast-forward to $M. + +In this case, the `git-read-tree -m $H $M` command makes sure +that no local change is lost as the result of this "merge". +Here are the "carry forward" rules: + + I (index) H M Result + ------------------------------------------------------- + 0 nothing nothing nothing (does not happen) + 1 nothing nothing exists use M + 2 nothing exists nothing remove path from index + 3 nothing exists exists use M + + clean I==H I==M + ------------------ + 4 yes N/A N/A nothing nothing keep index + 5 no N/A N/A nothing nothing keep index + + 6 yes N/A yes nothing exists keep index + 7 no N/A yes nothing exists keep index + 8 yes N/A no nothing exists fail + 9 no N/A no nothing exists fail + + 10 yes yes N/A exists nothing remove path from index + 11 no yes N/A exists nothing fail + 12 yes no N/A exists nothing fail + 13 no no N/A exists nothing fail + + clean (H=M) + ------ + 14 yes exists exists keep index + 15 no exists exists keep index + + clean I==H I==M (H!=M) + ------------------ + 16 yes no no exists exists fail + 17 no no no exists exists fail + 18 yes no yes exists exists keep index + 19 no no yes exists exists keep index + 20 yes yes no exists exists use M + 21 no yes no exists exists fail + +In all "keep index" cases, the index entry stays as in the +original index file. If the entry were not up to date, +git-read-tree keeps the copy in the work tree intact when +operating under the -u flag. + +When this form of git-read-tree returns successfully, you can +see what "local changes" you made are carried forward by running +`git-diff-index --cached $M`. Note that this does not +necessarily match `git-diff-index --cached $H` would have +produced before such a two tree merge. This is because of cases +18 and 19 --- if you already had the changes in $M (e.g. maybe +you picked it up via e-mail in a patch form), `git-diff-index +--cached $H` would have told you about the change before this +merge, but it would not show in `git-diff-index --cached $M` +output after two-tree merge. + + +3-Way Merge +~~~~~~~~~~~ +Each "index" entry has two bits worth of "stage" state. stage 0 is the +normal one, and is the only one you'd see in any kind of normal use. + +However, when you do `git-read-tree` with three trees, the "stage" +starts out at 1. + +This means that you can do + +---------------- +$ git-read-tree -m <tree1> <tree2> <tree3> +---------------- + +and you will end up with an index with all of the <tree1> entries in +"stage1", all of the <tree2> entries in "stage2" and all of the +<tree3> entries in "stage3". When performing a merge of another +branch into the current branch, we use the common ancestor tree +as <tree1>, the current branch head as <tree2>, and the other +branch head as <tree3>. + +Furthermore, `git-read-tree` has special-case logic that says: if you see +a file that matches in all respects in the following states, it +"collapses" back to "stage0": + + - stage 2 and 3 are the same; take one or the other (it makes no + difference - the same work has been done on our branch in + stage 2 and their branch in stage 3) + + - stage 1 and stage 2 are the same and stage 3 is different; take + stage 3 (our branch in stage 2 did not do anything since the + ancestor in stage 1 while their branch in stage 3 worked on + it) + + - stage 1 and stage 3 are the same and stage 2 is different take + stage 2 (we did something while they did nothing) + +The `git-write-tree` command refuses to write a nonsensical tree, and it +will complain about unmerged entries if it sees a single entry that is not +stage 0. + +OK, this all sounds like a collection of totally nonsensical rules, +but it's actually exactly what you want in order to do a fast +merge. The different stages represent the "result tree" (stage 0, aka +"merged"), the original tree (stage 1, aka "orig"), and the two trees +you are trying to merge (stage 2 and 3 respectively). + +The order of stages 1, 2 and 3 (hence the order of three +<tree-ish> command line arguments) are significant when you +start a 3-way merge with an index file that is already +populated. Here is an outline of how the algorithm works: + +- if a file exists in identical format in all three trees, it will + automatically collapse to "merged" state by git-read-tree. + +- a file that has _any_ difference what-so-ever in the three trees + will stay as separate entries in the index. It's up to "porcelain + policy" to determine how to remove the non-0 stages, and insert a + merged version. + +- the index file saves and restores with all this information, so you + can merge things incrementally, but as long as it has entries in + stages 1/2/3 (i.e., "unmerged entries") you can't write the result. So + now the merge algorithm ends up being really simple: + + * you walk the index in order, and ignore all entries of stage 0, + since they've already been done. + + * if you find a "stage1", but no matching "stage2" or "stage3", you + know it's been removed from both trees (it only existed in the + original tree), and you remove that entry. + + * if you find a matching "stage2" and "stage3" tree, you remove one + of them, and turn the other into a "stage0" entry. Remove any + matching "stage1" entry if it exists too. .. all the normal + trivial rules .. + +You would normally use `git-merge-index` with supplied +`git-merge-one-file` to do this last step. The script updates +the files in the working tree as it merges each path and at the +end of a successful merge. + +When you start a 3-way merge with an index file that is already +populated, it is assumed that it represents the state of the +files in your work tree, and you can even have files with +changes unrecorded in the index file. It is further assumed +that this state is "derived" from the stage 2 tree. The 3-way +merge refuses to run if it finds an entry in the original index +file that does not match stage 2. + +This is done to prevent you from losing your work-in-progress +changes, and mixing your random changes in an unrelated merge +commit. To illustrate, suppose you start from what has been +committed last to your repository: + +---------------- +$ JC=`git-rev-parse --verify "HEAD^0"` +$ git-checkout-index -f -u -a $JC +---------------- + +You do random edits, without running git-update-index. And then +you notice that the tip of your "upstream" tree has advanced +since you pulled from him: + +---------------- +$ git-fetch git://.... linus +$ LT=`cat .git/FETCH_HEAD` +---------------- + +Your work tree is still based on your HEAD ($JC), but you have +some edits since. Three-way merge makes sure that you have not +added or modified index entries since $JC, and if you haven't, +then does the right thing. So with the following sequence: + +---------------- +$ git-read-tree -m -u `git-merge-base $JC $LT` $JC $LT +$ git-merge-index git-merge-one-file -a +$ echo "Merge with Linus" | \ + git-commit-tree `git-write-tree` -p $JC -p $LT +---------------- + +what you would commit is a pure merge between $JC and $LT without +your work-in-progress changes, and your work tree would be +updated to the result of the merge. + +However, if you have local changes in the working tree that +would be overwritten by this merge,`git-read-tree` will refuse +to run to prevent your changes from being lost. + +In other words, there is no need to worry about what exists only +in the working tree. When you have local changes in a part of +the project that is not involved in the merge, your changes do +not interfere with the merge, and are kept intact. When they +*do* interfere, the merge does not even start (`git-read-tree` +complains loudly and fails without modifying anything). In such +a case, you can simply continue doing what you were in the +middle of doing, and when your working tree is ready (i.e. you +have finished your work-in-progress), attempt the merge again. + + +See Also +-------- +gitlink:git-write-tree[1]; gitlink:git-ls-files[1] + + +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-rebase.txt b/Documentation/git-rebase.txt new file mode 100644 index 0000000000..2f417a8f85 --- /dev/null +++ b/Documentation/git-rebase.txt @@ -0,0 +1,240 @@ +git-rebase(1) +============= + +NAME +---- +git-rebase - Forward-port local commits to the updated upstream head + +SYNOPSIS +-------- +'git-rebase' [-v] [--merge] [-C<n>] [--onto <newbase>] <upstream> [<branch>] + +'git-rebase' --continue | --skip | --abort + +DESCRIPTION +----------- +If <branch> is specified, git-rebase will perform an automatic +`git checkout <branch>` before doing anything else. Otherwise +it remains on the current branch. + +All changes made by commits in the current branch but that are not +in <upstream> are saved to a temporary area. This is the same set +of commits that would be shown by `git log <upstream>..HEAD`. + +The current branch is reset to <upstream>, or <newbase> if the +--onto option was supplied. This has the exact same effect as +`git reset --hard <upstream>` (or <newbase>). + +The commits that were previously saved into the temporary area are +then reapplied to the current branch, one by one, in order. + +It is possible that a merge failure will prevent this process from being +completely automatic. You will have to resolve any such merge failure +and run `git rebase --continue`. Another option is to bypass the commit +that caused the merge failure with `git rebase --skip`. To restore the +original <branch> and remove the .dotest working files, use the command +`git rebase --abort` instead. + +Assume the following history exists and the current branch is "topic": + +------------ + A---B---C topic + / + D---E---F---G master +------------ + +From this point, the result of either of the following commands: + + + git-rebase master + git-rebase master topic + +would be: + +------------ + A'--B'--C' topic + / + D---E---F---G master +------------ + +The latter form is just a short-hand of `git checkout topic` +followed by `git rebase master`. + +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`. + +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'. + +------------ + 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. + +A range of commits could also be removed with rebase. If we have +the following situation: + +------------ + E---F---G---H---I---J topicA +------------ + +then the command + + git-rebase --onto topicA~5 topicA~2 topicA + +would result in the removal of commits F and G: + +------------ + E---H'---I'---J' topicA +------------ + +This is useful if F and G were flawed in some way, or should not be +part of topicA. Note that the argument to --onto and the <upstream> +parameter can be any valid commit-ish. + +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 +file you edit, you need to tell git that the conflict has been resolved, +typically this would be done with + + + git add <filename> + + +After resolving the conflict manually and updating the index with the +desired resolution, you can continue the rebasing process with + + + git rebase --continue + + +Alternatively, you can undo the git-rebase with + + + git rebase --abort + +OPTIONS +------- +<newbase>:: + Starting point at which to create the new commits. If the + --onto option is not specified, the starting point is + <upstream>. May be any valid commit, and not just an + existing branch name. + +<upstream>:: + Upstream branch to compare against. May be any valid commit, + not just an existing branch name. + +<branch>:: + Working branch; defaults to HEAD. + +--continue:: + Restart the rebasing process after having resolved a merge conflict. + +--abort:: + Restore the original branch and abort the rebase operation. + +--skip:: + Restart the rebasing process by skipping the current patch. + +--merge:: + Use merging strategies to rebase. When the recursive (default) merge + strategy is used, this allows rebase to be aware of renames on the + upstream side. + +-s <strategy>, \--strategy=<strategy>:: + Use the given merge strategy; can be supplied more than + once to specify them in the order they should be tried. + If there is no `-s` option, a built-in list of strategies + 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. + +-C<n>:: + Ensure at least <n> lines of surrounding context match before + and after each change. When fewer lines of surrounding + context exist they all must match. By default no context is + ever ignored. + +include::merge-strategies.txt[] + +NOTES +----- +When you rebase a branch, you are changing its history in a way that +will cause problems for anyone who already has a copy of the branch +in their repository and tries to pull updates from you. You should +understand the implications of using 'git rebase' on a repository that +you share. + +When the git rebase command is run, it will first execute a "pre-rebase" +hook if one exists. You can use this hook to do sanity checks and +reject the rebase if it isn't appropriate. Please see the template +pre-rebase hook script for an example. + +You must be in the top directory of your project to start (or continue) +a rebase. Upon completion, <branch> will be the current branch. + +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-receive-pack.txt b/Documentation/git-receive-pack.txt new file mode 100644 index 0000000000..6914aa59c3 --- /dev/null +++ b/Documentation/git-receive-pack.txt @@ -0,0 +1,165 @@ +git-receive-pack(1) +=================== + +NAME +---- +git-receive-pack - Receive what is pushed into the repository + + +SYNOPSIS +-------- +'git-receive-pack' <directory> + +DESCRIPTION +----------- +Invoked by 'git-send-pack' and updates the repository with the +information fed from the remote end. + +This command is usually not invoked directly by the end user. +The UI for the protocol is on the 'git-send-pack' side, and the +program pair is meant to be used to push updates to remote +repository. For pull operations, see 'git-fetch-pack'. + +The command allows for creation and fast forwarding of sha1 refs +(heads/tags) on the remote end (strictly speaking, it is the +local end receive-pack runs, but to the user who is sitting at +the send-pack end, it is updating the remote. Confused?) + +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 config +option, which tells it if updates to a ref should be denied if they +are not fast-forwards. + +OPTIONS +------- +<directory>:: + The repository to sync into. + +pre-receive Hook +---------------- +Before any ref is updated, if $GIT_DIR/hooks/pre-receive file exists +and is executable, it will be invoked once with no parameters. The +standard input of the hook will be one line per ref to be updated: + + sha1-old SP sha1-new SP refname LF + +The refname value is relative to $GIT_DIR; e.g. for the master +head this is "refs/heads/master". The two sha1 values before +each refname are the object names for the refname before and after +the update. Refs to be created will have sha1-old equal to 0{40}, +while refs to be deleted will have sha1-new equal to 0{40}, otherwise +sha1-old and sha1-new should be valid objects in the repository. + +This hook is called before any refname is updated and before any +fast-forward checks are performed. + +If the pre-receive hook exits with a non-zero exit status no updates +will be performed, and the update, post-receive and post-update +hooks will not be invoked either. This can be useful to quickly +bail out if the update is not to be supported. + +update Hook +----------- +Before each ref is updated, if $GIT_DIR/hooks/update file exists +and is executable, it is invoked once per ref, with three parameters: + + $GIT_DIR/hooks/update refname sha1-old sha1-new + +The refname parameter is relative to $GIT_DIR; e.g. for the master +head this is "refs/heads/master". The two sha1 arguments are +the object names for the refname before and after the update. +Note that the hook is called before the refname is updated, +so either sha1-old is 0{40} (meaning there is no such ref yet), +or it should match what is recorded in refname. + +The hook should exit with non-zero status if it wants to disallow +updating the named ref. Otherwise it should exit with zero. + +Successful execution (a zero exit status) of this hook does not +ensure the ref will actully be updated, it is only a prerequisite. +As such it is not a good idea to send notices (e.g. email) from +this hook. Consider using the post-receive hook instead. + +post-receive Hook +----------------- +After all refs were updated (or attempted to be updated), if any +ref update was successful, and if $GIT_DIR/hooks/post-receive +file exists and is executable, it will be invoke once with no +parameters. The standard input of the hook will be one line +for each successfully updated ref: + + sha1-old SP sha1-new SP refname LF + +The refname value is relative to $GIT_DIR; e.g. for the master +head this is "refs/heads/master". The two sha1 values before +each refname are the object names for the refname before and after +the update. Refs that were created will have sha1-old equal to +0{40}, while refs that were deleted will have sha1-new equal to +0{40}, otherwise sha1-old and sha1-new should be valid objects in +the repository. + +Using this hook, it is easy to generate mails describing the updates +to the repository. This example script sends one mail message per +ref listing the commits pushed to the repository: + + #!/bin/sh + # mail out commit update information. + while read oval nval ref + do + if expr "$oval" : '0*$' >/dev/null + then + echo "Created a new ref, with the following commits:" + git-rev-list --pretty "$nval" + else + echo "New commits:" + git-rev-list --pretty "$nval" "^$oval" + fi | + mail -s "Changes to ref $ref" commit-list@mydomain + done + exit 0 + +The exit code from this hook invocation is ignored, however a +non-zero exit code will generate an error message. + +Note that it is possible for refname to not have sha1-new when this +hook runs. This can easily occur if another user modifies the ref +after it was updated by receive-pack, but before the hook was able +to evaluate it. It is recommended that hooks rely on sha1-new +rather than the current value of refname. + +post-update Hook +---------------- +After all other processing, if at least one ref was updated, and +if $GIT_DIR/hooks/post-update file exists and is executable, then +post-update will called with the list of refs that have been updated. +This can be used to implement any repository wide cleanup tasks. + +The exit code from this hook invocation is ignored; the only thing +left for git-receive-pack to do at that point is to exit itself +anyway. + +This hook can be used, for example, to run "git-update-server-info" +if the repository is packed and is served via a dumb transport. + + #!/bin/sh + exec git-update-server-info + + +SEE ALSO +-------- +gitlink:git-send-pack[1] + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-reflog.txt b/Documentation/git-reflog.txt new file mode 100644 index 0000000000..1e343bcdcd --- /dev/null +++ b/Documentation/git-reflog.txt @@ -0,0 +1,68 @@ +git-reflog(1) +============= + +NAME +---- +git-reflog - Manage reflog information + + +SYNOPSIS +-------- +'git reflog' <subcommand> <options> + +DESCRIPTION +----------- +The command takes various subcommands, and different options +depending on the subcommand: + +[verse] +git reflog expire [--dry-run] [--stale-fix] + [--expire=<time>] [--expire-unreachable=<time>] [--all] <refs>... + +git reflog [show] [log-options] + +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]. + +The subcommand "show" (which is also the default, in the absense of any +subcommands) will take all the normal log options, and show the log of +the current branch. It is basically an alias for 'git log -g --abbrev-commit +--pretty=oneline', see gitlink:git-log[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-relink.txt b/Documentation/git-relink.txt new file mode 100644 index 0000000000..aca60120c8 --- /dev/null +++ b/Documentation/git-relink.txt @@ -0,0 +1,37 @@ +git-relink(1) +============= + +NAME +---- +git-relink - Hardlink common objects in local repositories + +SYNOPSIS +-------- +'git-relink' [--safe] <dir> <dir> [<dir>]\* + +DESCRIPTION +----------- +This will scan 2 or more object repositories and look for common objects, check +if they are hardlinked, and replace one with a hardlink to the other if not. + +OPTIONS +------- +--safe:: + Stops if two objects with the same hash exist but have different sizes. + Default is to warn and continue. + +<dir>:: + Directories containing a .git/objects/ subdirectory. + +Author +------ +Written by Ryan Anderson <ryan@michonline.com> + +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..a9fb6a9a5e --- /dev/null +++ b/Documentation/git-remote.txt @@ -0,0 +1,131 @@ +git-remote(1) +============ + +NAME +---- +git-remote - manage set of tracked repositories + + +SYNOPSIS +-------- +[verse] +'git-remote' +'git-remote' add [-t <branch>] [-m <branch>] [-f] <name> <url> +'git-remote' show <name> +'git-remote' prune <name> +'git-remote' update [group] + +DESCRIPTION +----------- + +Manage the set of repositories ("remotes") whose branches you track. + + +COMMANDS +-------- + +With no arguments, shows a list of existing remotes. Several +subcommands are available to perform operations on the remotes. + +'add':: + +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>. ++ +With `-f` option, `git fetch <name>` is run immediately after +the remote information is set up. ++ +With `-t <branch>` option, instead of the default glob +refspec for the remote to track all branches under +`$GIT_DIR/remotes/<name>/`, a refspec to track only `<branch>` +is created. You can give more than one `-t <branch>` to track +multiple branche without grabbing all branches. ++ +With `-m <master>` option, `$GIT_DIR/remotes/<name>/HEAD` is set +up to point at remote's `<master>` branch instead of whatever +branch the `HEAD` at the remote repository actually points at. + +'show':: + +Gives some information about the remote <name>. + +'prune':: + +Deletes all stale tracking branches under <name>. +These stale branches have already been removed from the remote repository +referenced by <name>, but are still locally available in +"remotes/<name>". + +'update':: + +Fetch updates for a named set of remotes in the repository as defined by +remotes.<group>. If a named group is not specified on the command line, +the configuration parameter remotes.default will get used; if +remotes.default is not defined, all remotes which do not the +configuration parameter remote.<name>.skipDefaultUpdate set to true will +be updated. (See gitlink:git-config[1]). + + +DISCUSSION +---------- + +The remote configuration is achieved using the `remote.origin.url` and +`remote.origin.fetch` configuration variables. (See +gitlink:git-config[1]). + +Examples +-------- + +* Add a new remote, fetch, and check out a branch from it ++ +------------ +$ 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 +... +------------ + +* Imitate 'git clone' but track only selected branches ++ +------------ +$ mkdir project.git +$ cd project.git +$ git init +$ git remote add -f -t master -m master origin git://example.com/git.git/ +$ git merge origin +------------ + + +See Also +-------- +gitlink:git-fetch[1] +gitlink:git-branch[1] +gitlink:git-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 new file mode 100644 index 0000000000..d39abc126d --- /dev/null +++ b/Documentation/git-repack.txt @@ -0,0 +1,99 @@ +git-repack(1) +============= + +NAME +---- +git-repack - Pack unpacked objects in a repository + + +SYNOPSIS +-------- +'git-repack' [-a] [-d] [-f] [-l] [-n] [-q] [--window=N] [--depth=N] + +DESCRIPTION +----------- + +This script is used to combine all objects that do not currently +reside in a "pack", into a pack. + +A pack is a collection of objects, individually compressed, with +delta compression applied, stored in a single file, with an +associated index file. + +Packs are used to reduce the load on mirror systems, backup +engines, disk storage, etc. + +OPTIONS +------- + +-a:: + Instead of incrementally packing the unpacked objects, + pack everything available into a single pack. + Especially useful when packing a repository that is used + for private development and there is no need to worry + about people fetching via dumb file transfer protocols + from it. Use with '-d'. + +-d:: + After packing, if the newly created packs make some + existing packs redundant, remove the redundant packs. + Also runs gitlink:git-prune-packed[1]. + +-l:: + Pass the `--local` option to `git pack-objects`, see + gitlink:git-pack-objects[1]. + +-f:: + Pass the `--no-reuse-delta` option to `git pack-objects`, see + gitlink:git-pack-objects[1]. + +-q:: + Pass the `-q` option to `git pack-objects`, see + gitlink:git-pack-objects[1]. + +-n:: + 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> + +Documentation +-------------- +Documentation by Ryan Anderson <ryan@michonline.com> + +See Also +-------- +gitlink:git-pack-objects[1] +gitlink:git-prune-packed[1] + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-repo-config.txt b/Documentation/git-repo-config.txt new file mode 100644 index 0000000000..2deba31763 --- /dev/null +++ b/Documentation/git-repo-config.txt @@ -0,0 +1,18 @@ +git-repo-config(1) +================== + +NAME +---- +git-repo-config - Get and set repository or global options + + +SYNOPSIS +-------- +'git-repo-config' ... + + +DESCRIPTION +----------- + +This is a synonym for gitlink:git-config[1]. Please refer to the +documentation of that command. diff --git a/Documentation/git-request-pull.txt b/Documentation/git-request-pull.txt new file mode 100644 index 0000000000..478a5fd6b7 --- /dev/null +++ b/Documentation/git-request-pull.txt @@ -0,0 +1,40 @@ +git-request-pull(1) +=================== + +NAME +---- +git-request-pull - Generates a summary of pending changes + +SYNOPSIS +-------- +'git-request-pull' <start> <url> [<end>] + +DESCRIPTION +----------- + +Summarizes the changes between two commits to the standard output, and includes +the given URL in the generated summary. + +OPTIONS +------- +<start>:: + Commit to start at. + +<url>:: + URL to include in the summary. + +<end>:: + Commit to send at; defaults to HEAD. + +Author +------ +Written by Ryan Anderson <ryan@michonline.com> and 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-rerere.txt b/Documentation/git-rerere.txt new file mode 100644 index 0000000000..7ff9b05e68 --- /dev/null +++ b/Documentation/git-rerere.txt @@ -0,0 +1,211 @@ +git-rerere(1) +============= + +NAME +---- +git-rerere - Reuse recorded resolution of conflicted merges + +SYNOPSIS +-------- +'git-rerere' [clear|diff|status|gc] + +DESCRIPTION +----------- + +In a workflow that employs relatively long lived topic branches, +the developer sometimes needs to resolve the same conflict over +and over again until the topic branches are done (either merged +to the "release" branch, or sent out and accepted upstream). + +This command helps this process by recording conflicted +automerge results and corresponding hand-resolve results on the +initial manual merge, and later by noticing the same automerge +results and applying the previously recorded hand resolution. + +[NOTE] +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 automatically 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 +---------- + +When your topic branch modifies overlapping area that your +master branch (or upstream) touched since your topic branch +forked from it, you may want to test it with the latest master, +even before your topic branch is ready to be pushed upstream: + +------------ + o---*---o topic + / + o---o---o---*---o---o master +------------ + +For such a test, you need to merge master and topic somehow. +One way to do it is to pull master into the topic branch: + +------------ + $ git checkout topic + $ git merge master + + o---*---o---+ topic + / / + o---o---o---*---o---o master +------------ + +The commits marked with `*` touch the same area in the same +file; you need to resolve the conflicts when creating the commit +marked with `+`. Then you can test the result to make sure your +work-in-progress still works with what is in the latest master. + +After this test merge, there are two ways to continue your work +on the topic. The easiest is to build on top of the test merge +commit `+`, and when your work in the topic branch is finally +ready, pull the topic branch into master, and/or ask the +upstream to pull from you. By that time, however, the master or +the upstream might have been advanced since the test merge `+`, +in which case the final commit graph would look like this: + +------------ + $ git checkout topic + $ git merge master + $ ... work on both topic and master branches + $ git checkout master + $ git merge topic + + o---*---o---+---o---o topic + / / \ + o---o---o---*---o---o---o---o---+ master +------------ + +When your topic branch is long-lived, however, your topic branch +would end up having many such "Merge from master" commits on it, +which would unnecessarily clutter the development history. +Readers of the Linux kernel mailing list may remember that Linus +complained about such too frequent test merges when a subsystem +maintainer asked to pull from a branch full of "useless merges". + +As an alternative, to keep the topic branch clean of test +merges, you could blow away the test merge, and keep building on +top of the tip before the test merge: + +------------ + $ git checkout topic + $ git merge master + $ git reset --hard HEAD^ ;# rewind the test merge + $ ... work on both topic and master branches + $ git checkout master + $ git merge topic + + o---*---o-------o---o topic + / \ + o---o---o---*---o---o---o---o---+ master +------------ + +This would leave only one merge commit when your topic branch is +finally ready and merged into the master branch. This merge +would require you to resolve the conflict, introduced by the +commits marked with `*`. However, often this conflict is the +same conflict you resolved when you created the test merge you +blew away. `git-rerere` command helps you to resolve this final +conflicted merge using the information from your earlier hand +resolve. + +Running `git-rerere` command immediately after a conflicted +automerge records the conflicted working tree files, with the +usual conflict markers `<<<<<<<`, `=======`, and `>>>>>>>` in +them. Later, after you are done resolving the conflicts, +running `git-rerere` again records the resolved state of these +files. Suppose you did this when you created the test merge of +master into the topic branch. + +Next time, running `git-rerere` after seeing a conflicted +automerge, if the conflict is the same as the earlier one +recorded, it is noticed and a three-way merge between the +earlier conflicted automerge, the earlier manual resolution, and +the current conflicted automerge is performed by the command. +If this three-way merge resolves cleanly, the result is written +out to your working tree file, so you would not have to manually +resolve it. Note that `git-rerere` leaves the index file alone, +so you still need to do the final sanity checks with `git diff` +(or `git diff -c`) and `git add` when you are satisfied. + +As a convenience measure, `git-merge` automatically invokes +`git-rerere` when it exits with a failed automerge, which +records it if it is a new conflict, or reuses the earlier hand +resolve when it is not. `git-commit` also invokes `git-rerere` +when recording a merge result. What this means is that you do +not have to do anything special yourself (Note: you still have +to create `$GIT_DIR/rr-cache` directory to enable this command). + +In our example, when you did the test merge, the manual +resolution is recorded, and it will be reused when you do the +actual merge later with updated master and topic branch, as long +as the earlier resolution is still applicable. + +The information `git-rerere` records is also used when running +`git-rebase`. After blowing away the test merge and continuing +development on the topic branch: + +------------ + o---*---o-------o---o topic + / + o---o---o---*---o---o---o---o master + + $ git rebase master topic + + o---*---o-------o---o topic + / + o---o---o---*---o---o---o---o master +------------ + +you could run `git rebase master topic`, to keep yourself +up-to-date even before your topic is ready to be sent upstream. +This would result in falling back to three-way merge, and it +would conflict the same way the test merge you resolved earlier. +`git-rerere` is run by `git rebase` to help you resolve this +conflict. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-reset.txt b/Documentation/git-reset.txt new file mode 100644 index 0000000000..5b55cda512 --- /dev/null +++ b/Documentation/git-reset.txt @@ -0,0 +1,184 @@ +git-reset(1) +============ + +NAME +---- +git-reset - Reset current HEAD to the specified state + +SYNOPSIS +-------- +[verse] +'git-reset' [--mixed | --soft | --hard] [<commit>] +'git-reset' [--mixed] <commit> [--] <paths>... + +DESCRIPTION +----------- +Sets the current head to the specified commit and optionally resets the +index and working tree to match. + +This command is useful if you notice some small error in a recent +commit (or set of commits) and want to redo that part without showing +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:: + Resets the index but not the working tree (i.e., the changed files + are preserved but not marked for commit) and reports what has not + been updated. This is the default action. + +--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 "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> are lost. + +<commit>:: + Commit to make the current HEAD. + +Examples +-------- + +Undo a commit and redo:: ++ +------------ +$ git commit ... +$ git reset --soft HEAD^ <1> +$ edit <2> +$ git commit -a -c ORIG_HEAD <3> +------------ ++ +<1> This is most often done when you remembered what you +just committed is incomplete, or you misspelled your commit +message, or both. Leaves working tree as it was before "reset". +<2> make corrections to working tree files. +<3> "reset" copies the old head to .git/ORIG_HEAD; redo the +commit by starting with its log message. If you do not need to +edit the message further, you can give -C option instead. + +Undo commits permanently:: ++ +------------ +$ git commit ... +$ git reset --hard HEAD~3 <1> +------------ ++ +<1> The last three commits (HEAD, HEAD^, and HEAD~2) were bad +and you do not want to ever see them again. Do *not* do this if +you have already given these commits to somebody else. + +Undo a commit, making it a topic branch:: ++ +------------ +$ git branch topic/wip <1> +$ git reset --hard HEAD~3 <2> +$ git checkout topic/wip <3> +------------ ++ +<1> You have made some commits, but realize they were premature +to be in the "master" branch. You want to continue polishing +them in a topic branch, so create "topic/wip" branch off of the +current HEAD. +<2> Rewind the master branch to get rid of those three commits. +<3> Switch to "topic/wip" branch and keep working. + +Undo add:: ++ +------------ +$ edit <1> +$ git add frotz.c filfre.c +$ mailx <2> +$ git reset <3> +$ git pull git://info.example.com/ nitfol <4> +------------ ++ +<1> you are happily working on something, and find the changes +in these files are in good order. You do not want to see them +when you run "git diff", because you plan to work on other files +and changes with these files are distracting. +<2> somebody asks you to pull, and the changes sounds worthy of merging. +<3> however, you already dirtied the index (i.e. your index does +not match the HEAD commit). But you know the pull you are going +to make does not affect frotz.c nor filfre.c, so you revert the +index changes for these two files. Your changes in working tree +remain there. +<4> then you can pull and merge, leaving frotz.c and filfre.c +changes still in the working tree. + +Undo a merge or pull:: ++ +------------ +$ git pull <1> +Auto-merging nitfol +CONFLICT (content): Merge conflict in nitfol +Automatic merge failed/prevented; fix up by hand +$ git reset --hard <2> +$ git pull . topic/branch <3> +Updating from 41223... to 13134... +Fast forward +$ git reset --hard ORIG_HEAD <4> +------------ ++ +<1> try to update from the upstream resulted in a lot of +conflicts; you were not ready to spend a lot of time merging +right now, so you decide to do that later. +<2> "pull" has not made merge commit, so "git reset --hard" +which is a synonym for "git reset --hard HEAD" clears the mess +from the index file and the working tree. +<3> merge a topic branch into the current branch, which resulted +in a fast forward. +<4> but you decided that the topic branch is not ready for public +consumption yet. "pull" or "merge" always leaves the original +tip of the current branch in ORIG_HEAD, so resetting hard to it +brings your index file and the working tree back to that state, +and resets the tip of the branch to that commit. + +Interrupted workflow:: ++ +Suppose you are interrupted by an urgent fix request while you +are in the middle of a large change. The files in your +working tree are not in any shape to be committed yet, but you +need to get to the other branch for a quick bugfix. ++ +------------ +$ git checkout feature ;# you were working in "feature" branch and +$ work work work ;# got interrupted +$ git commit -a -m 'snapshot WIP' <1> +$ git checkout master +$ fix fix fix +$ git commit ;# commit with real log +$ git checkout feature +$ git reset --soft HEAD^ ;# go back to WIP state <2> +$ git reset <3> +------------ ++ +<1> This commit will get blown away so a throw-away log message is OK. +<2> This removes the 'WIP' commit from the commit history, and sets + your working tree to the state just before you made that snapshot. +<3> At this point the index file still has all the WIP changes you + committed as 'snapshot WIP'. This updates the index to show your + WIP files as uncommitted. + +Author +------ +Written by Junio C Hamano <junkio@cox.net> and Linus Torvalds <torvalds@osdl.org> + +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-rev-list.txt b/Documentation/git-rev-list.txt new file mode 100644 index 0000000000..4f145eaba4 --- /dev/null +++ b/Documentation/git-rev-list.txt @@ -0,0 +1,310 @@ +git-rev-list(1) +=============== + +NAME +---- +git-rev-list - Lists commit objects in reverse chronological order + + +SYNOPSIS +-------- +[verse] +'git-rev-list' [ \--max-count=number ] + [ \--skip=number ] + [ \--max-age=timestamp ] + [ \--min-age=timestamp ] + [ \--sparse ] + [ \--no-merges ] + [ \--remove-empty ] + [ \--not ] + [ \--all ] + [ \--stdin ] + [ \--topo-order ] + [ \--parents ] + [ \--encoding[=<encoding>] ] + [ \--(author|committer|grep)=<pattern> ] + [ [\--objects | \--objects-edge] [ \--unpacked ] ] + [ \--pretty | \--header ] + [ \--bisect ] + [ \--merge ] + [ \--reverse ] + [ \--walk-reflogs ] + <commit>... [ \-- <paths>... ] + +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. 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>'". For example, either of +the following may be used interchangeably: + +----------------------------------------------------------------------- + $ 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 +----------------------------------------------------------------------- + +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 +------- + +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. + +--parents:: + + Print the parents of the commit. + +Diff Formatting +~~~~~~~~~~~~~~~ + +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. + +-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':: + + Limit the number of commits output. + +--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. + +--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'. + +--all:: + + 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. + +-g, --walk-reflogs:: + + Instead of walking the commit ancestry chain, walk + reflog entries from the most recent one to older ones. + When this option is used you cannot specify commits to + exclude (that is, '{caret}commit', 'commit1..commit2', + nor 'commit1...commit2' notations cannot be used). ++ +With '\--pretty' format other than oneline (for obvious reasons), +this causes the output to have two extra lines of information +taken from the reflog. By default, 'commit@{Nth}' notation is +used in the output. When the starting commit is specified as +'commit@{now}', output also uses 'commit@{timestamp}' notation +instead. Under '\--pretty=oneline', the commit message is +prefixed with this information on the same line. + +--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. + +--reverse:: + + Output the commits in reverse 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, 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 new file mode 100644 index 0000000000..ccc66aae7f --- /dev/null +++ b/Documentation/git-rev-parse.txt @@ -0,0 +1,289 @@ +git-rev-parse(1) +================ + +NAME +---- +git-rev-parse - Pick out and massage parameters + + +SYNOPSIS +-------- +'git-rev-parse' [ --option ] <args>... + +DESCRIPTION +----------- + +Many git porcelainish commands take mixture of flags +(i.e. parameters that begin with a dash '-') and parameters +meant for underlying `git-rev-list` command they use internally +and flags and parameters for other commands they use as the +downstream of `git-rev-list`. This command is used to +distinguish between them. + + +OPTIONS +------- +--revs-only:: + Do not output flags and parameters not meant for + `git-rev-list` command. + +--no-revs:: + Do not output flags and parameters meant for + `git-rev-list` command. + +--flags:: + Do not output non-flag parameters. + +--no-flags:: + Do not output flag parameters. + +--default <arg>:: + If there is no parameter given by the user, use `<arg>` + instead. + +--verify:: + The parameter given must be usable as a single, valid + object name. Otherwise barf and abort. + +--sq:: + Usually the output is made one line per flag and + parameter. This option makes output a single line, + properly quoted for consumption by shell. Useful when + you expect your parameter to contain whitespaces and + newlines (e.g. when using pickaxe `-S` with + `git-diff-\*`). + +--not:: + When showing object names, prefix them with '{caret}' and + strip '{caret}' prefix from the object names that already have + one. + +--symbolic:: + Usually the object names are output in SHA1 form (with + possible '{caret}' prefix); this option makes them output in a + form as close to the original input as possible. + + +--all:: + Show all refs found in `$GIT_DIR/refs`. + +--branches:: + Show branch refs found in `$GIT_DIR/refs/heads`. + +--tags:: + Show tag refs found in `$GIT_DIR/refs/tags`. + +--remotes:: + Show tag refs found in `$GIT_DIR/refs/remotes`. + +--show-prefix:: + When the command is invoked from a subdirectory, show the + path of the current directory relative to the top-level + directory. + +--show-cdup:: + When the command is invoked from a subdirectory, show the + path of the top-level directory relative to the current + directory (typically a sequence of "../", or an empty string). + +--git-dir:: + Show `$GIT_DIR` if defined else show the path to the .git directory. + +--short, --short=number:: + Instead of outputting the full SHA1 values of object names try to + abbreviate them to a shorter unique name. When no length is specified + 7 is used. The minimum length is 4. + +--since=datestring, --after=datestring:: + Parses the date string, and outputs corresponding + --max-age= parameter for git-rev-list command. + +--until=datestring, --before=datestring:: + Parses the date string, and outputs corresponding + --min-age= parameter for git-rev-list command. + +<args>...:: + Flags and parameters to be parsed. + + +SPECIFYING REVISIONS +-------------------- + +A revision parameter typically, but not necessarily, names a +commit object. They use what is called an 'extended SHA1' +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. + E.g. dae86e1950b1277e545cee180551750029cfe735 and dae86e both + 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, `$GIT_DIR/refs/heads/<name>` if exists; + + . otherwise, `$GIT_DIR/refs/remotes/<name>` if exists; + + . otherwise, `$GIT_DIR/refs/remotes/<name>/HEAD` if exists. + +* A ref followed by the suffix '@' with a date specification + enclosed in a brace + pair (e.g. '\{yesterday\}', '\{1 month 2 weeks 3 days 1 hour 1 + second ago\}' or '\{1979-02-26 18:30:00\}') to specify the value + of the ref at a prior point in time. This suffix may only be + used immediately following a ref name and the ref must have an + existing log ($GIT_DIR/logs/<ref>). + +* A ref followed by the suffix '@' with an ordinal specification + enclosed in a brace pair (e.g. '\{1\}', '\{15\}') to specify + the n-th prior value of that ref. For example 'master@\{1\}' + is the immediate prior value of 'master' while 'master@\{5\}' + is the 5th prior value of 'master'. This suffix may only be used + immediately following a ref name and the ref must have an existing + log ($GIT_DIR/logs/<ref>). + +* You can use the '@' construct with an empty ref part to get at a + reflog of the current branch. For example, if you are on the + branch 'blabla', then '@\{1\}' means the same as 'blabla@\{1\}'. + +* A suffix '{caret}' to a revision parameter means the first parent of + that commit object. '{caret}<n>' means the <n>th parent (i.e. + 'rev{caret}' + is equivalent to 'rev{caret}1'). As a special rule, + '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 '{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. 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 + could be a tag, and dereference the tag recursively until an + object of that type is found or the object cannot be + dereferenced anymore (in which case, barf). `rev{caret}0` + introduced earlier is a short-hand for `rev{caret}\{commit\}`. + +* A suffix '{caret}' followed by an empty brace pair + (e.g. `v0.99.8{caret}\{\}`) means the object could be a tag, + and dereference the tag recursively until a non-tag object is + found. + +* A colon, followed by a slash, followed by a text: this names + a commit whose commit message starts with the specified text. + This name returns the youngest matching commit which is + reachable from any ref. If the commit message starts with a + '!', you have to repeat that; the special sequence ':/!', + followed by something else than '!' is reserved for now. + +* 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. + + G H I J + \ / \ / + D E F + \ | / \ + \ | / | + \|/ | + B C + \ / + \ / + A + + A = = A^0 + B = A^ = A^1 = A~1 + C = A^2 = A^2 + D = A^^ = A^1^1 = A~2 + E = B^2 = A^^2 + F = B^3 = A^^3 + G = A^^^ = A^1^1^1 = A~3 + H = D^2 = B^^2 = A^^^2 = A~2^2 + I = F^ = B^3^ = A^^3^ + J = F^2 = B^3^2 = A^^3^2 + + +SPECIFYING RANGES +----------------- + +History traversing commands such as `git-log` operate on a set +of commits, not just a single commit. To these commands, +specifying a single revision with the notation described in the +previous section means the set of commits reachable from that +commit, following the commit ancestry chain. + +To exclude commits reachable from a commit, a prefix `{caret}` +notation is used. E.g. "`{caret}r1 r2`" means commits reachable +from `r2` but exclude the ones reachable from `r1`. + +This set operation appears so often that there is a shorthand +for it. "`r1..r2`" is equivalent to "`{caret}r1 r2`". It is +the difference of two sets (subtract the set of commits +reachable from `r1` from the set of commits reachable from +`r2`). + +A similar notation "`r1\...r2`" is called symmetric difference +of `r1` and `r2` and is defined as +"`r1 r2 --not $(git-merge-base --all r1 r2)`". +It it the set of commits that are reachable from either one of +`r1` or `r2` but not from both. + +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 F B C F + 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 +------ +Written by Linus Torvalds <torvalds@osdl.org> and +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-revert.txt b/Documentation/git-revert.txt new file mode 100644 index 0000000000..8081bbaffa --- /dev/null +++ b/Documentation/git-revert.txt @@ -0,0 +1,59 @@ +git-revert(1) +============= + +NAME +---- +git-revert - Revert an existing commit + +SYNOPSIS +-------- +'git-revert' [--edit | --no-edit] [-n] <commit> + +DESCRIPTION +----------- +Given one existing commit, revert the change the patch introduces, and record a +new commit that records it. This requires your working tree to be clean (no +modifications from the HEAD commit). + +OPTIONS +------- +<commit>:: + Commit to revert. + For a more complete list of ways to spell commit names, see + "SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + +-e|--edit:: + With this option, `git-revert` will let you edit the commit + message prior committing the revert. This is the default if + you run the command from a terminal. + +--no-edit:: + With this option, `git-revert` will not start the commit + message editor. + +-n|--no-commit:: + Usually the command automatically creates a commit with + a commit log message stating which commit was reverted. + This flag applies the change necessary to revert the + named commit to your working tree, but does not make the + commit. In addition, when this option is used, your + working tree does not have to match the HEAD commit. + The revert is done against the beginning state of your + working tree. ++ +This is useful when reverting more than one commits' +effect to your working tree in a row. + + +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-rm.txt b/Documentation/git-rm.txt new file mode 100644 index 0000000000..6feebc0400 --- /dev/null +++ b/Documentation/git-rm.txt @@ -0,0 +1,91 @@ +git-rm(1) +========= + +NAME +---- +git-rm - Remove files from the working tree and from the index + +SYNOPSIS +-------- +'git-rm' [-f] [-n] [-r] [--cached] [--] <file>... + +DESCRIPTION +----------- +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. 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:: + Override the up-to-date check. + +-n:: + Don't actually remove the file(s), just show if they exist in + the index. + +-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 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 +-------- +git-rm Documentation/\\*.txt:: + Removes all `\*.txt` files from the index that are under the + `Documentation` directory and any of its subdirectories. ++ +Note that the asterisk `\*` is quoted from the shell in this +example; this lets the command include the files from +subdirectories of `Documentation/` directory. + +git-rm -f git-*.sh:: + Remove all git-*.sh scripts that are in the index. + 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 +-------- +gitlink:git-add[1] + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-runstatus.txt b/Documentation/git-runstatus.txt new file mode 100644 index 0000000000..8bb52f4687 --- /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 add' (or 'git rm' if you are deleting) 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 new file mode 100644 index 0000000000..9b3aabb6fe --- /dev/null +++ b/Documentation/git-send-email.txt @@ -0,0 +1,129 @@ +git-send-email(1) +================= + +NAME +---- +git-send-email - Send a collection of patches as emails + + +SYNOPSIS +-------- +'git-send-email' [options] <file|directory> [... file|directory] + + + +DESCRIPTION +----------- +Takes the patches given on the command line and emails them out. + +The header of the email is configurable by command line options. If not +specified on the command line, the user will be prompted with a ReadLine +enabled interface to provide the necessary information. + +OPTIONS +------- +The options available are: + +--bcc:: + Specify a "Bcc:" value for each email. ++ +The --bcc option must be repeated for each user you want on the bcc list. + +--cc:: + Specify a starting "Cc:" value for each email. ++ +The --cc option must be repeated for each user you want on the cc list. + +--chain-reply-to, --no-chain-reply-to:: + If this is set, each email will be sent as a reply to the previous + email sent. If disabled with "--no-chain-reply-to", all emails after + the first will be sent as replies to the first email sent. When using + this, it is recommended that the first file given be an overview of the + entire patch series. + Default is the value of the 'sendemail.chainreplyto' configuration + value; if that is unspecified, default to --chain-reply-to. + +--compose:: + Use $EDITOR to edit an introductory message for the + patch series. + +--from:: + Specify the sender of the emails. This will default to + the value GIT_COMMITTER_IDENT, as returned by "git-var -l". + The user will still be prompted to confirm this entry. + +--in-reply-to:: + Specify the contents of the first In-Reply-To header. + Subsequent emails will refer to the previous email + instead of this if --chain-reply-to is set (the default) + Only necessary if --compose is also set. If --compose + is not set, this will be prompted for. + +--no-signed-off-by-cc:: + Do not add emails found in Signed-off-by: lines to the cc list. + +--quiet:: + Make git-send-email less verbose. One line per email should be + all that is output. + +--smtp-server:: + 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. + Only necessary if --compose is also set. If --compose + is not set, this will be prompted for. + +--suppress-from:: + Do not add the From: address to the cc: list, if it shows up in a From: + line. + +--to:: + Specify the primary recipient of the emails generated. + Generally, this will be the upstream maintainer of the + project involved. ++ +The --to option must be repeated for each user you want on the to list. + + +CONFIGURATION +------------- +sendemail.aliasesfile:: + To avoid typing long email addresses, point this to one or more + email aliases files. You must also supply 'sendemail.aliasfiletype'. + +sendemail.aliasfiletype:: + Format of the file(s) specified in sendemail.aliasesfile. Must be + one of 'mutt', 'mailrc', 'pine', or 'gnus'. + +sendemail.bcc:: + Email address (or alias) to always bcc. + +sendemail.chainreplyto:: + Boolean value specifying the default to the '--chain_reply_to' + parameter. + +sendemail.smtpserver:: + Default smtp server to use. + +Author +------ +Written by Ryan Anderson <ryan@michonline.com> + +git-send-email is originally based upon +send_lots_of_email.pl by Greg Kroah-Hartman. + +Documentation +-------------- +Documentation by Ryan Anderson + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-send-pack.txt b/Documentation/git-send-pack.txt new file mode 100644 index 0000000000..205bfd2d25 --- /dev/null +++ b/Documentation/git-send-pack.txt @@ -0,0 +1,123 @@ +git-send-pack(1) +================ + +NAME +---- +git-send-pack - Push objects over git protocol to another repository + + +SYNOPSIS +-------- +'git-send-pack' [--all] [--force] [--receive-pack=<git-receive-pack>] [--verbose] [--thin] [<host>:]<directory> [<ref>...] + +DESCRIPTION +----------- +Usually you would want to use gitlink:git-push[1] which is a +higher level wrapper of this command instead. + +Invokes 'git-receive-pack' on a possibly remote repository, and +updates it from the current repository, sending named refs. + + +OPTIONS +------- +\--receive-pack=<git-receive-pack>:: + Path to the 'git-receive-pack' program on the remote + end. Sometimes useful when pushing to a remote + repository over ssh, and you do not have the program in + a directory on the default $PATH. + +\--exec=<git-receive-pack>:: + Same as \--receive-pack=<git-receive-pack>. + +\--all:: + Instead of explicitly specifying which refs to update, + update all refs that locally exist. + +\--force:: + Usually, the command refuses to update a remote ref that + is not an ancestor of the local ref used to overwrite it. + This flag disables the check. What this means is that + the remote repository can lose commits; use it with + care. + +\--verbose:: + Run verbosely. + +\--thin:: + Spend extra cycles to minimize the number of objects to be sent. + Use it on slower connection. + +<host>:: + A remote host to house the repository. When this + part is specified, 'git-receive-pack' is invoked via + ssh. + +<directory>:: + The repository to update. + +<ref>...:: + The remote refs to update. + + +Specifying the Refs +------------------- + +There are three ways to specify which refs to update on the +remote end. + +With '--all' flag, all refs that exist locally are transferred to +the remote side. You cannot specify any '<ref>' if you use +this flag. + +Without '--all' and without any '<ref>', the refs that exist +both on the local side and on the remote side are updated. + +When one or more '<ref>' are specified explicitly, it can be either a +single pattern, or a pair of such pattern separated by a colon +":" (this means that a ref name cannot have a colon in it). A +single pattern '<name>' is just a shorthand for '<name>:<name>'. + +Each pattern pair consists of the source side (before the colon) +and the destination side (after the colon). The ref to be +pushed is determined by finding a match that matches the source +side, and where it is pushed is determined by using the +destination side. + + - It is an error if <src> does not match exactly one of the + local refs. + + - It is an error if <dst> matches more than one remote refs. + + - If <dst> does not match any remote ref, either + + * it has to start with "refs/"; <dst> is used as the + destination literally in this case. + + * <src> == <dst> and the ref that matched the <src> must not + exist in the set of remote refs; the ref matched <src> + locally is used as the name of the destination. + +Without '--force', the <src> ref is stored at the remote only if +<dst> does not exist, or <dst> is a proper subset (i.e. an +ancestor) of <src>. This check, known as "fast forward check", +is performed in order to avoid accidentally overwriting the +remote ref and lose other peoples' commits from there. + +With '--force', the fast forward check is disabled for all refs. + +Optionally, a <ref> parameter can be prefixed with a plus '+' sign +to disable the fast-forward check only on that ref. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-sh-setup.txt b/Documentation/git-sh-setup.txt new file mode 100644 index 0000000000..2b2abebd60 --- /dev/null +++ b/Documentation/git-sh-setup.txt @@ -0,0 +1,72 @@ +git-sh-setup(1) +=============== + +NAME +---- +git-sh-setup - Common git shell script setup code + +SYNOPSIS +-------- +'git-sh-setup' + +DESCRIPTION +----------- + +This is not a command the end user would want to run. Ever. +This documentation is meant for people who are studying the +Porcelain-ish scripts and/or are writing new ones. + +The `git-sh-setup` scriptlet is designed to be sourced (using +`.`) by other shell scripts to set up some variables pointing at +the normal git directories and a few helper shell functions. + +Before sourcing it, your script should set up a few variables; +`USAGE` (and `LONG_USAGE`, if any) is used to define message +given by `usage()` shell function. `SUBDIRECTORY_OK` can be set +if the script can run from a subdirectory of the working tree +(some commands do not). + +The scriptlet sets `GIT_DIR` and `GIT_OBJECT_DIRECTORY` shell +variables, but does *not* export them to the environment. + +FUNCTIONS +--------- + +die:: + exit after emitting the supplied error message to the + standard error stream. + +usage:: + die with the usage message. + +set_reflog_action:: + set the message that will be recorded to describe the + end-user action in the reflog, when the script updates a + ref. + +is_bare_repository:: + outputs `true` or `false` to the standard output stream + to indicate if the repository is a bare repository + (i.e. without an associated working tree). + +cd_to_toplevel:: + runs chdir to the toplevel of the working tree. + +require_work_tree:: + checks if the repository is a bare repository, and dies + if so. Used by scripts that require working tree + (e.g. `checkout`). + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-shell.txt b/Documentation/git-shell.txt new file mode 100644 index 0000000000..228b9f14f3 --- /dev/null +++ b/Documentation/git-shell.txt @@ -0,0 +1,35 @@ +git-shell(1) +============ + +NAME +---- +git-shell - Restricted login shell for GIT-only SSH access + + +SYNOPSIS +-------- +'git-shell' -c <command> <argument> + +DESCRIPTION +----------- +This is meant to be used as a login shell for SSH accounts you want +to restrict to GIT pull/push access only. It permits execution only +of server-side GIT commands implementing the pull/push functionality. +The commands can be executed only by the '-c' option; the shell is not +interactive. + +Currently, only the `git-receive-pack` and `git-upload-pack` commands +are permitted to be called, with a single required argument. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Petr Baudis and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-shortlog.txt b/Documentation/git-shortlog.txt new file mode 100644 index 0000000000..b0df92e819 --- /dev/null +++ b/Documentation/git-shortlog.txt @@ -0,0 +1,57 @@ +git-shortlog(1) +=============== + +NAME +---- +git-shortlog - Summarize 'git log' output + +SYNOPSIS +-------- +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 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:: + Suppress commit description and provide a commit count summary only. + +FILES +----- +'.mailmap':: + If this file exists, it will be used for mapping author email + addresses to a real author name. One mapping per line, first + the author name followed by the email address enclosed by + '<' and '>'. Use hash '#' for comments. Example: + + # Keep alphabetized + Adam Morrow <adam@localhost.localdomain> + Eve Jones <eve@laptop.(none)> + +Author +------ +Written by Jeff Garzik <jgarzik@pobox.com> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-show-branch.txt b/Documentation/git-show-branch.txt new file mode 100644 index 0000000000..ba5313d51f --- /dev/null +++ b/Documentation/git-show-branch.txt @@ -0,0 +1,193 @@ +git-show-branch(1) +================== + +NAME +---- +git-show-branch - Show branches and their commits + +SYNOPSIS +-------- +[verse] +'git-show-branch' [--all] [--remotes] [--topo-order] [--current] + [--more=<n> | --list | --independent | --merge-base] + [--no-name | --sha1-name] [--topics] [<rev> | <glob>]... +'git-show-branch' (-g|--reflog)[=<n>[,<base>]] [--list] [<ref>] + +DESCRIPTION +----------- + +Shows the commit ancestry graph starting from the commits named +with <rev>s or <globs>s (or all refs under $GIT_DIR/refs/heads +and/or $GIT_DIR/refs/tags) semi-visually. + +It cannot show more than 29 branches and commits at a time. + +It uses `showbranch.default` multi-valued configuration items if +no <rev> nor <glob> is given on the command line. + + +OPTIONS +------- +<rev>:: + Arbitrary extended SHA1 expression (see `git-rev-parse`) + that typically names a branch HEAD or a tag. + +<glob>:: + A glob pattern that matches branch or tag names under + $GIT_DIR/refs. For example, if you have many topic + branches under $GIT_DIR/refs/heads/topic, giving + `topic/*` would show all of them. + +-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 + branch to the list of revs to be shown when it is not + given on the command line. + +--topo-order:: + By default, the branches and their commits are shown in + reverse chronological order. This option makes them + appear in topological order (i.e., descendant commits + are shown before their parents). + +--sparse:: + By default, the output omits merges that are reachable + from only one tip being shown. This option makes them + visible. + +--more=<n>:: + Usually the command stops output upon showing the commit + that is the common ancestor of all the branches. This + flag tells the command to go <n> more common commits + beyond that. When <n> is negative, display only the + <reference>s given, without showing the commit ancestry + tree. + +--list:: + Synonym to `--more=-1` + +--merge-base:: + Instead of showing the commit list, just act like the + 'git-merge-base -a' command, except that it can accept + more than two heads. + +--independent:: + Among the <reference>s given, display only the ones that + cannot be reached from any other <reference>. + +--no-name:: + Do not show naming strings for each commit. + +--sha1-name:: + Instead of naming the commits using the path to reach + them from heads (e.g. "master~2" to mean the grandparent + 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>[,<base>]] [<ref>]:: + Shows <n> most recent ref-log entries for the given + ref. If <base> is given, <n> entries going back from + that entry. <base> can be specified as count or date. + `-g` can be used as a short-hand for this option. When + no explicit <ref> parameter is given, it defaults to the + current branch (or `HEAD` if it is detached). + +Note that --more, --list, --independent and --merge-base options +are mutually exclusive. + + +OUTPUT +------ +Given N <references>, the first N lines are the one-line +description from their commit message. The branch head that is +pointed at by $GIT_DIR/HEAD is prefixed with an asterisk `*` +character while other heads are prefixed with a `!` character. + +Following these N lines, one-line log for each commit is +displayed, indented N places. If a commit is on the I-th +branch, the I-th indentation character shows a `+` sign; +otherwise it shows a space. Merge commits are denoted by +a `-` sign. Each commit shows a short name that +can be used as an extended SHA1 to name that commit. + +The following example shows three branches, "master", "fixes" +and "mhf": + +------------------------------------------------ +$ git show-branch master fixes mhf +* [master] Add 'git show-branch'. + ! [fixes] Introduce "reset type" flag to "git reset" + ! [mhf] Allow "+remote:local" refspec to cause --force when fetching. +--- + + [mhf] Allow "+remote:local" refspec to cause --force when fetching. + + [mhf~1] Use git-octopus when pulling more than one heads. + + [fixes] Introduce "reset type" flag to "git reset" + + [mhf~2] "git fetch --force". + + [mhf~3] Use .git/remote/origin, not .git/branches/origin. + + [mhf~4] Make "git pull" and "git fetch" default to origin + + [mhf~5] Infamous 'octopus merge' + + [mhf~6] Retire git-parse-remote. + + [mhf~7] Multi-head fetch. + + [mhf~8] Start adding the $GIT_DIR/remotes/ support. +*++ [master] Add 'git show-branch'. +------------------------------------------------ + +These three branches all forked from a common commit, [master], +whose commit message is "Add 'git show-branch'. "fixes" branch +adds one commit 'Introduce "reset type"'. "mhf" branch has many +other commits. The current branch is "master". + + +EXAMPLE +------- + +If you keep your primary branches immediately under +`$GIT_DIR/refs/heads`, and topic branches in subdirectories of +it, having the following in the configuration file may help: + +------------ +[showbranch] + default = --topo-order + default = heads/* + +------------ + +With this, `git show-branch` without extra parameters would show +only the primary branches. In addition, if you happen to be on +your topic branch, it is shown as well. + +------------ +$ git show-branch --reflog='10,1 hour ago' --list master +------------ + +shows 10 reflog entries going back from the tip as of 1 hour ago. +Without `--list`, the output also shows how these tips are +topologically related with each other. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + + +Documentation +-------------- +Documentation by Junio C Hamano. + + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-show-index.txt b/Documentation/git-show-index.txt new file mode 100644 index 0000000000..be09b62beb --- /dev/null +++ b/Documentation/git-show-index.txt @@ -0,0 +1,35 @@ +git-show-index(1) +================= + +NAME +---- +git-show-index - Show packed archive index + + +SYNOPSIS +-------- +'git-show-index' < idx-file + + +DESCRIPTION +----------- +Reads given idx file for packed git archive created with +git-pack-objects command, and dumps its contents. + +The information it outputs is subset of what you can get from +'git-verify-pack -v'; this command only shows the packfile +offset and SHA1 of each object. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano + +GIT +--- +Part of the gitlink:git[7] suite + 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 new file mode 100644 index 0000000000..5a219ab577 --- /dev/null +++ b/Documentation/git-show.txt @@ -0,0 +1,84 @@ +git-show(1) +=========== + +NAME +---- +git-show - Show various types of objects + + +SYNOPSIS +-------- +'git-show' [options] <object>... + +DESCRIPTION +----------- +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. + +The command takes options applicable to the gitlink:git-diff-tree[1] command to +control how the changes the commit introduces are shown. + +This manual page describes only the most frequently used options. + + +OPTIONS +------- +<object>:: + The name of the object to show. + For a more complete list of ways to spell object names, see + "SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + +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 +---------- + +include::i18n.txt[] + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +Junio C Hamano <junkio@cox.net>. Significantly enhanced by +Johannes Schindelin <Johannes.Schindelin@gmx.de>. + + +Documentation +------------- +Documentation by David Greaves, Petr Baudis and the git-list <git@vger.kernel.org>. + +This manual page is a stub. You can help the git documentation by expanding it. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-ssh-fetch.txt b/Documentation/git-ssh-fetch.txt new file mode 100644 index 0000000000..192b1f15a9 --- /dev/null +++ b/Documentation/git-ssh-fetch.txt @@ -0,0 +1,51 @@ +git-ssh-fetch(1) +================ + +NAME +---- +git-ssh-fetch - Fetch from a remote repository over ssh connection + + + +SYNOPSIS +-------- +'git-ssh-fetch' [-c] [-t] [-a] [-d] [-v] [-w filename] [--recover] commit-id url + +DESCRIPTION +----------- +Pulls from a remote repository over ssh connection, invoking +git-ssh-upload on the other end. It functions identically to +git-ssh-upload, aside from which end you run it on. + + +OPTIONS +------- +commit-id:: + Either the hash or the filename under [URL]/refs/ to + pull. + +-c:: + Get the commit objects. +-t:: + Get trees associated with the commit objects. +-a:: + Get all the objects. +-v:: + Report what is downloaded. +-w:: + Writes the commit-id into the filename under $GIT_DIR/refs/ on + the local end after the transfer is complete. + + +Author +------ +Written by Daniel Barkalow <barkalow@iabervon.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-ssh-upload.txt b/Documentation/git-ssh-upload.txt new file mode 100644 index 0000000000..a9b7e9f974 --- /dev/null +++ b/Documentation/git-ssh-upload.txt @@ -0,0 +1,47 @@ +git-ssh-upload(1) +================= + +NAME +---- +git-ssh-upload - Push to a remote repository over ssh connection + + +SYNOPSIS +-------- +'git-ssh-upload' [-c] [-t] [-a] [-d] [-v] [-w filename] [--recover] commit-id url + +DESCRIPTION +----------- +Pushes from a remote repository over ssh connection, invoking +git-ssh-fetch on the other end. It functions identically to +git-ssh-fetch, aside from which end you run it on. + +OPTIONS +------- +commit-id:: + Id of commit to push. + +-c:: + Get the commit objects. +-t:: + Get tree associated with the requested commit object. +-a:: + Get all the objects. +-v:: + Report what is uploaded. +-w:: + Writes the commit-id into the filename under [URL]/refs/ on + the remote end after the transfer is complete. + +Author +------ +Written by Daniel Barkalow <barkalow@iabervon.org> + +Documentation +-------------- +Documentation by Daniel Barkalow + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-status.txt b/Documentation/git-status.txt new file mode 100644 index 0000000000..e9e193f008 --- /dev/null +++ b/Documentation/git-status.txt @@ -0,0 +1,58 @@ +git-status(1) +============= + +NAME +---- +git-status - Show the working tree status + + +SYNOPSIS +-------- +'git-status' <options>... + +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 add' 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. + +The command takes the same set of options as `git-commit`; it +shows what would be committed if the same options are given to +`git-commit`. + + +OUTPUT +------ +The output from this command is designed to be used as a commit +template comments, and all the output lines are prefixed with '#'. + + +CONFIGURATION +------------- + +The command honors `color.status` (or `status.color` -- they +mean the same thing and the latter is kept for backward +compatibility) and `color.status.<slot>` configuration variables +to colorize its output. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +Junio C Hamano <junkio@cox.net>. + +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-stripspace.txt b/Documentation/git-stripspace.txt new file mode 100644 index 0000000000..3a03dd0410 --- /dev/null +++ b/Documentation/git-stripspace.txt @@ -0,0 +1,33 @@ +git-stripspace(1) +================= + +NAME +---- +git-stripspace - Filter out empty lines + + +SYNOPSIS +-------- +'git-stripspace' < <stream> + +DESCRIPTION +----------- +Remove multiple empty lines, and empty lines at beginning and end. + +OPTIONS +------- +<stream>:: + Byte stream to act on. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +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-svn.txt b/Documentation/git-svn.txt new file mode 100644 index 0000000000..9b5a3d6196 --- /dev/null +++ b/Documentation/git-svn.txt @@ -0,0 +1,500 @@ +git-svn(1) +========== + +NAME +---- +git-svn - Bidirectional operation between a single Subversion branch and git + +SYNOPSIS +-------- +'git-svn' <command> [options] [arguments] + +DESCRIPTION +----------- +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. + +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. Since its inception, +git-svn has gained the ability to track multiple branches in a manner +similar to git-svnimport. + +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':: + Initializes an empty git repository with additional + metadata directories for git-svn. The Subversion URL + may be specified as a command-line argument, or as full + URL arguments to -T/-t/-b. Optionally, the target + directory to operate on can be specified as a second + argument. Normally this command initializes the current + directory. + +-T<trunk_subdir>:: +--trunk=<trunk_subdir>:: +-t<tags_subdir>:: +--tags=<tags_subdir>:: +-b<branches_subdir>:: +--branches=<branches_subdir>:: + These are optional command-line options for 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) + +--no-metadata:: + Set the 'noMetadata' option in the [svn-remote] config. +--use-svm-props:: + Set the 'useSvmProps' option in the [svn-remote] config. +--use-svnsync-props:: + Set the 'useSvnsyncProps' option in the [svn-remote] config. +--rewrite-root=<URL>:: + Set the 'rewriteRoot' option in the [svn-remote] config. +--username=<USER>:: + For transports that SVN handles authentication for (http, + https, and plain svn), specify the username. For other + transports (eg svn+ssh://), you must include the username in + the URL, eg svn+ssh://foo@svn.bar.com/project + +--prefix=<prefix>:: + This allows one to specify a prefix which is prepended + to the names of remotes if trunk/branches/tags are + specified. 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. + +'fetch':: + + Fetch unfetched revisions from the Subversion remote we are + tracking. The name of the [svn-remote "..."] section in the + .git/config file may be specified as an optional command-line + argument. + +'clone':: + Runs 'init' and 'fetch'. It will automatically create a + directory based on the basename of the URL passed to it; + or if a second argument is passed; it will create a directory + and work within that. It accepts all arguments that the + 'init' and 'fetch' commands accept; with the exception of + '--fetch-all'. After a repository is cloned, the 'fetch' + command will be able to update revisions without affecting + the working tree; and the 'rebase' command will be able + to update the working tree with the latest changes. + +'rebase':: + This fetches revisions from the SVN parent of the current HEAD + and rebases the current (uncommitted to SVN) work against it. + +This works similarly to 'svn update' or 'git-pull' except that +it preserves linear history with 'git-rebase' instead of +'git-merge' for ease of dcommit-ing with git-svn. + +This accepts all options that 'git-svn fetch' and 'git-rebase' +accepts. However '--fetch-all' only fetches from the current +[svn-remote], and not all [svn-remote] definitions. + +Like 'git-rebase'; this requires that the working tree be clean +and have no uncommitted changes. + +'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 + simply overwrites files with those specified in the tree or + commit. All merging is assumed to have taken place + independently of git-svn functions. + +'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 interoperability 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. + +-- + +OPTIONS +------- +-- + +--shared[={false|true|umask|group|all|world|everybody}]:: +--template=<template_directory>:: + Only used with the 'init' command. + These are passed directly to gitlink:git-init[1]. + +-r <ARG>:: +--revision <ARG>:: + +Used with the 'fetch' command. + +This allows revision ranges for partial/cauterized history +to be supported. $NUMBER, $NUMBER1:$NUMBER2 (numeric ranges), +$NUMBER:HEAD, and BASE:$NUMBER are all supported. + +This can allow you to make partial mirrors when running fetch; +but is generally not recommended because history will be skipped +and lost. + +-:: +--stdin:: + +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 '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. + +config key: svn.rmdir + +-e:: +--edit:: + +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. + +config key: svn.edit + +-l<num>:: +--find-copies-harder:: + +Only used with the 'dcommit', 'set-tree' and 'commit-diff' commands. + +They are both passed directly to git-diff-tree see +gitlink:git-diff-tree[1] for more information. + +[verse] +config key: svn.l +config key: svn.findcopiesharder + +-A<filename>:: +--authors-file=<filename>:: + +Syntax is compatible with the files used by git-svnimport and +git-cvsimport: + +------------------------------------------------------------------------ + 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. + +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]. + +[verse] +config key: svn.repack +config key: svn.repackflags + +-m:: +--merge:: +-s<strategy>:: +--strategy=<strategy>:: + +These are only used with the 'dcommit' and 'rebase' commands. + +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 +---------------- +-- + +-i<GIT_SVN_ID>:: +--id <GIT_SVN_ID>:: + +This sets GIT_SVN_ID (instead of using the environment). This +allows the user to override the default refname to fetch from +when tracking a single URL. The 'log' and 'dcommit' commands +no longer require this switch as an argument. + +-R<remote name>:: +--svn-remote <remote name>:: + Specify the [svn-remote "<remote name>"] section to use, + this allows SVN multiple repositories to be tracked. + Default: "svn" + +--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. This feature is enabled by default, use + --no-follow-parent to disable it. + +config key: svn.followparent + +-- +CONFIG FILE-ONLY OPTIONS +------------------------ +-- + +svn.noMetadata:: +svn-remote.<name>.noMetadata:: + +This gets rid of the git-svn-id: lines at the end of every commit. + +If you lose your .git/svn/git-svn/.rev_db file, git-svn will not +be able to rebuild it and 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. Using this conflicts with the 'useSvmProps' +option for (hopefully) obvious reasons. + +svn.useSvmProps:: +svn-remote.<name>.useSvmProps:: + +This allows git-svn to re-map repository URLs and UUIDs from +mirrors created using SVN::Mirror (or svk) for metadata. + +If an SVN revision has a property, "svm:headrev", it is likely +that the revision was created by SVN::Mirror (also used by SVK). +The property contains a repository UUID and a revision. We want +to make it look like we are mirroring the original URL, so +introduce a helper function that returns the original identity +URL and UUID, and use it when generating metadata in commit +messages. + +svn.useSvnsyncProps:: +svn-remote.<name>.useSvnsyncprops:: + Similar to the useSvmProps option; this is for users + of the svnsync(1) command distributed with SVN 1.4.x and + later. + +svn-remote.<name>.rewriteRoot:: + This allows users to create repositories from alternate + URLs. For example, an administrator could run git-svn on the + server locally (accessing via file://) but wish to distribute + the repository with a public http:// or svn:// URL in the + metadata so users of it will see the public URL. + +Since the noMetadata, rewriteRoot, useSvnsyncProps and useSvmProps +options all affect the metadata generated and used by git-svn; they +*must* be set in the configuration file before any history is imported +and these settings should never be changed once they are set. + +Additionally, only one of these four options can be used per-svn-remote +section because they affect the 'git-svn-id:' metadata line. + +-- + +BASIC EXAMPLES +-------------- + +Tracking and contributing to a the trunk of a Subversion-managed project: + +------------------------------------------------------------------------ +# Clone a repo (like git clone): + git-svn clone http://svn.foo.org/project/trunk +# Enter the newly cloned directory: + cd trunk +# You should be on master branch, double-check with git-branch + git branch +# Do some work and commit locally to git: + git commit ... +# Something is committed to SVN, rebase your local changes against the +# latest changes in SVN: + git-svn rebase +# Now commit your changes (that were committed previously using git) to SVN, +# as well as automatically updating your working HEAD: + git-svn dcommit +# 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): + +------------------------------------------------------------------------ +# Clone a repo (like git clone): + git-svn clone http://svn.foo.org/project -T trunk -b branches -t tags +# View all branches and tags you have cloned: + git branch -r +# Reset your master to trunk (or any other branch, replacing 'trunk' +# with the appropriate name): + git reset --hard remotes/trunk +# You may only dcommit to one branch/tag/trunk at a time. The usage +# of dcommit/rebase/show-ignore should be the same as above. +------------------------------------------------------------------------ + +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-svn 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 does not do +automated merge/branch tracking by default and leaves it entirely up to +the user on the git side. git-svn does however follow copy +history of the directory that it is tracking, however (much like +how 'svn log' works). + +BUGS +---- + +We ignore all SVN properties except svn:executable. Any unhandled +properties are logged to $GIT_DIR/svn/<refname>/unhandled.log + +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 +the possible corner cases (git doesn't do it, either). Committing +renamed and copied files are fully supported if they're similar enough +for git to detect them. + +CONFIGURATION +------------- + +git-svn stores [svn-remote] configuration information in the +repository .git/config file. It is similar the core git +[remote] sections except 'fetch' keys do not accept glob +arguments; but they are instead handled by the 'branches' +and 'tags' keys. Since some SVN repositories are oddly +configured with multiple projects glob expansions such those +listed below are allowed: + +------------------------------------------------------------------------ +[svn-remote "project-a"] + url = http://server.org/svn + branches = branches/*/project-a:refs/remotes/project-a/branches/* + tags = tags/*/project-a:refs/remotes/project-a/tags/* + trunk = trunk/project-a:refs/remotes/project-a/trunk +------------------------------------------------------------------------ + +Keep in mind that the '*' (asterisk) wildcard of the local ref +(left of the ':') *must* be the farthest right path component; +however the remote wildcard may be anywhere as long as it's own +independent path componet (surrounded by '/' or EOL). This +type of configuration is not automatically created by 'init' and +should be manually entered with a text-editor or using +gitlink:git-config[1] + +SEE ALSO +-------- +gitlink:git-rebase[1] + +Author +------ +Written by Eric Wong <normalperson@yhbt.net>. + +Documentation +------------- +Written by Eric Wong <normalperson@yhbt.net>. diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt new file mode 100644 index 0000000000..b166cf3327 --- /dev/null +++ b/Documentation/git-svnimport.txt @@ -0,0 +1,177 @@ +git-svnimport(1) +================ +v0.1, July 2005 + +NAME +---- +git-svnimport - Import a SVN repository into git + + +SYNOPSIS +-------- +[verse] +'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ] + [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] + [ -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> ] + + +DESCRIPTION +----------- +Imports a SVN repository into git. It will either create a new +repository, or incrementally import into an existing one. + +SVN access is done by the SVN::Perl module. + +git-svnimport assumes that SVN repositories are organized into one +"trunk" directory where the main development happens, "branch/FOO" +directories for branches, and "/tags/FOO" directories for tags. +Other subdirectories are ignored. + +git-svnimport creates a file ".git/svn2git", which is required for +incremental SVN imports. + +OPTIONS +------- +-C <target-dir>:: + The GIT repository to import to. If the directory doesn't + exist, it will be created. Default is the current directory. + +-s <start_rev>:: + Start importing at this SVN change number. The default is 1. ++ +When importing incrementally, you might need to edit the .git/svn2git file. + +-i:: + Import-only: don't perform a checkout after importing. This option + ensures the working directory and index remain untouched and will + not create them if they do not exist. + +-T <trunk_subdir>:: + Name the SVN trunk. Default "trunk". + +-t <tag_subdir>:: + Name the SVN subdirectory for tags. Default "tags". + +-b <branch_subdir>:: + Name the SVN subdirectory for branches. Default "branches". + +-o <branch-for-HEAD>:: + The 'trunk' branch from SVN is imported to the 'origin' branch within + the git repository. Use this option if you want to import into a + different branch. + +-r:: + Prepend 'rX: ' to commit messages, where X is the imported + subversion revision. + +-I <ignorefile_name>:: + Import the svn:ignore directory property to files with this + name in each directory. (The Subversion and GIT ignore + syntaxes are similar enough that using the Subversion patterns + directly with "-I .gitignore" will almost always just work.) + +-A <author_file>:: + Read a file with lines on the form ++ +------ + username = User's Full Name <email@addr.es> + +------ ++ +and use "User's Full Name <email@addr.es>" as the GIT +author and committer for Subversion commits made by +"username". If encountering a commit made by a user not in the +list, abort. ++ +For convenience, this data is saved to $GIT_DIR/svn-authors +each time the -A option is provided, and read from that same +file each time git-svnimport is run with an existing GIT +repository without -A. + +-m:: + Attempt to detect merges based on the commit message. This option + will enable default regexes that try to capture the name source + branch name from the commit message. + +-M <regex>:: + Attempt to detect merges based on the commit message with a custom + regex. It can be used with -m to also see the default regexes. + You must escape forward slashes. + +-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. + +-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. + +-d:: + Use direct HTTP requests if possible. The "<path>" argument is used + only for retrieving the SVN logs; the path to the contents is + included in the SVN log. + +-D:: + Use direct HTTP requests if possible. The "<path>" argument is used + for retrieving the logs, as well as for the contents. ++ +There's no safe way to automatically find out which of these options to +use, so you need to try both. Usually, the one that's wrong will die +with a 40x error pretty quickly. + +<SVN_repository_URL>:: + The URL of the SVN module you want to import. For local + repositories, use "file:///absolute/path". ++ +If you're using the "-d" or "-D" option, this is the URL of the SVN +repository itself; it usually ends in "/svn". + +<path>:: + The path to the module you want to check out. + +-h:: + Print a short usage message and exit. + +OUTPUT +------ +If '-v' is specified, the script reports what it is doing. + +Otherwise, success is indicated the Unix way, i.e. by simply exiting with +a zero exit status. + +Author +------ +Written by Matthias Urlichs <smurf@smurf.noris.de>, with help from +various participants of the git-list <git@vger.kernel.org>. + +Based on a cvs2git script by the same author. + +Documentation +-------------- +Documentation by Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-symbolic-ref.txt b/Documentation/git-symbolic-ref.txt new file mode 100644 index 0000000000..a88f722860 --- /dev/null +++ b/Documentation/git-symbolic-ref.txt @@ -0,0 +1,61 @@ +git-symbolic-ref(1) +=================== + +NAME +---- +git-symbolic-ref - Read and modify symbolic refs + +SYNOPSIS +-------- +'git-symbolic-ref' [-q] [-m <reason>] <name> [<ref>] + +DESCRIPTION +----------- +Given one argument, reads which branch head the given symbolic +ref refers to and outputs its path, relative to the `.git/` +directory. Typically you would give `HEAD` as the <name> +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>. + +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`. + +OPTIONS +------- + +-q:: + Do not issue an error message if the <name> is not a + symbolic ref but a detached HEAD; instead exit with + non-zero status silently. + +-m:: + Update the reflog for <name> with <reason>. This is valid only + when creating or updating a symbolic ref. + +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). Therefore symbolic links are now deprecated +and symbolic refs are used by default. + +git-symbolic-ref will exit with status 0 if the contents of the +symbolic ref were printed correctly, with status 1 if the requested +name is not a symbolic ref, or 128 if another error occurs. + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt new file mode 100644 index 0000000000..70235e8ddb --- /dev/null +++ b/Documentation/git-tag.txt @@ -0,0 +1,225 @@ +git-tag(1) +========== + +NAME +---- +git-tag - Create, list, delete or verify a tag object signed with GPG + + +SYNOPSIS +-------- +[verse] +'git-tag' [-a | -s | -u <key-id>] [-f | -v] [-m <msg> | -F <file>] <name> [<head>] +'git-tag' -d <name>... +'git-tag' -l [<pattern>] + +DESCRIPTION +----------- +Adds a 'tag' reference in `.git/refs/tags/` + +Unless `-f` is given, the tag must not yet exist in +`.git/refs/tags/` directory. + +If one of `-a`, `-s`, or `-u <key-id>` is passed, the command +creates a 'tag' object, and requires the tag message. Unless +`-m <msg>` is given, an editor is started for the user to type +in the tag message. + +Otherwise just the SHA1 object name of the commit object is +written (i.e. a lightweight tag). + +A GnuPG signed tag object will be created when `-s` or `-u +<key-id>` is used. When `-u <key-id>` is not used, the +committer identity for the current user is used to find the +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). + +OPTIONS +------- +-a:: + Make an unsigned, annotated tag object + +-s:: + Make a GPG-signed tag, using the default e-mail address's key + +-u <key-id>:: + Make a GPG-signed tag, using the given key + +-f:: + Replace an existing tag with the given name (instead of failing) + +-d:: + Delete existing tags with the given names. + +-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. + +CONFIGURATION +------------- +By default, git-tag in sign-with-default mode (-s) will use your +committer identity (of the form "Your Name <your@email.address>") to +find a key. If you want to use a different default key, you can specify +it in the repository configuration as follows: + +[user] + signingkey = <gpg-key-id> + + +DISCUSSION +---------- + +On Re-tagging +~~~~~~~~~~~~~ + +What should you do when you tag a wrong commit and you would +want to re-tag? + +If you never pushed anything out, just re-tag it. Use "-f" to +replace the old one. And you're done. + +But if you have pushed things out (or others could just read +your repository directly), then others will have already seen +the old tag. In that case you can do one of two things: + +. The sane thing. +Just admit you screwed up, and use a different name. Others have +already seen one tag-name, and if you keep the same name, you +may be in the situation that two people both have "version X", +but they actually have 'different' "X"'s. So just call it "X.1" +and be done with it. + +. The insane thing. +You really want to call the new version "X" too, 'even though' +others have already seen the old one. So just use "git tag -f" +again, as if you hadn't already published the old one. + +However, Git does *not* (and it should not)change tags behind +users back. So if somebody already got the old tag, doing a "git +pull" on your tree shouldn't just make them overwrite the old +one. + +If somebody got a release tag from you, you cannot just change +the tag for them by updating your own one. This is a big +security issue, in that people MUST be able to trust their +tag-names. If you really want to do the insane thing, you need +to just fess up to it, and tell people that you messed up. You +can do that by making a very public announcement saying: + +------------ +Ok, I messed up, and I pushed out an earlier version tagged as X. I +then fixed something, and retagged the *fixed* tree as X again. + +If you got the wrong tag, and want the new one, please delete +the old one and fetch the new one by doing: + + git tag -d X + git fetch origin tag X + +to get my updated tag. + +You can test which tag you have by doing + + git rev-parse X + +which should return 0123456789abcdef.. if you have the new version. + +Sorry for inconvenience. +------------ + +Does this seem a bit complicated? It *should* be. There is no +way that it would be correct to just "fix" it behind peoples +backs. People need to know that their tags might have been +changed. + + +On Automatic following +~~~~~~~~~~~~~~~~~~~~~~ + +If you are following somebody else's tree, you are most likely +using tracking branches (`refs/heads/origin` in traditional +layout, or `refs/remotes/origin/master` in the separate-remote +layout). You usually want the tags from the other end. + +On the other hand, if you are fetching because you would want a +one-shot merge from somebody else, you typically do not want to +get tags from there. This happens more often for people near +the toplevel but not limited to them. Mere mortals when pulling +from each other do not necessarily want to automatically get +private anchor point tags from the other person. + +You would notice "please pull" messages on the mailing list says +repo URL and branch name alone. This is designed to be easily +cut&pasted to "git fetch" command line: + +------------ +Linus, please pull from + + git://git..../proj.git master + +to get the following updates... +------------ + +becomes: + +------------ +$ git pull git://git..../proj.git master +------------ + +In such a case, you do not want to automatically follow other's +tags. + +One important aspect of git is it is distributed, and being +distributed largely means there is no inherent "upstream" or +"downstream" in the system. On the face of it, the above +example might seem to indicate that the tag namespace is owned +by upper echelon of people and tags only flow downwards, but +that is not the case. It only shows that the usage pattern +determines who are interested in whose tags. + +A one-shot pull is a sign that a commit history is now crossing +the boundary between one circle of people (e.g. "people who are +primarily interested in networking part of the kernel") who may +have their own set of tags (e.g. "this is the third release +candidate from the networking group to be proposed for general +consumption with 2.6.21 release") to another circle of people +(e.g. "people who integrate various subsystem improvements"). +The latter are usually not interested in the detailed tags used +internally in the former group (that is what "internal" means). +That is why it is desirable not to follow tags automatically in +this case. + +It may well be that among networking people, they may want to +exchange the tags internal to their group, but in that workflow +they are most likely tracking with each other's progress by +having tracking branches. Again, the heuristic to automatically +follow such tags is a good thing. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org>, +Junio C Hamano <junkio@cox.net> and Chris Wright <chrisw@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-tar-tree.txt b/Documentation/git-tar-tree.txt new file mode 100644 index 0000000000..595940524e --- /dev/null +++ b/Documentation/git-tar-tree.txt @@ -0,0 +1,93 @@ +git-tar-tree(1) +=============== + +NAME +---- +git-tar-tree - Create a tar archive of the files in the named tree object + + +SYNOPSIS +-------- +'git-tar-tree' [--remote=<repo>] <tree-ish> [ <base> ] + +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. + +git-tar-tree 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. +It can be extracted using git-get-tar-commit-id. + +OPTIONS +------- + +<tree-ish>:: + The tree or commit to produce tar archive for. If it is + the object name of a commit object. + +<base>:: + Leading path to the files in the resulting tar archive. + +--remote=<repo>:: + Instead of making a tar archive from local repository, + retrieve a tar archive from a remote repository. + +CONFIGURATION +------------- +By default, file and directories modes are set to 0666 or 0777. 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 is 002, which means group +readable/writable files and directories. + +EXAMPLES +-------- +git tar-tree HEAD junk | (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 tar-tree v1.4.0 git-1.4.0 | gzip >git-1.4.0.tar.gz:: + + Create a tarball for v1.4.0 release. + +git tar-tree v1.4.0{caret}\{tree\} git-1.4.0 | gzip >git-1.4.0.tar.gz:: + + Create a tarball for v1.4.0 release, but without a + global extended pax header. + +git tar-tree --remote=example.com:git.git v1.4.0 >git-1.4.0.tar:: + + Get a tarball v1.4.0 from example.com. + +git tar-tree HEAD:Documentation/ git-docs > git-1.4.0-docs.tar:: + + Put everything in the current head's Documentation/ directory + into 'git-1.4.0-docs.tar', with the prefix 'git-docs/'. + +Author +------ +Written by 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-tools.txt b/Documentation/git-tools.txt new file mode 100644 index 0000000000..10653ff898 --- /dev/null +++ b/Documentation/git-tools.txt @@ -0,0 +1,115 @@ +A short git tools survey +======================== + + +Introduction +------------ + +Apart from git contrib/ area there are some others third-party tools +you may want to look. + +This document presents a brief summary of each tool and the corresponding +link. + + +Alternative/Augmentative Porcelains +----------------------------------- + + - *Cogito* (http://www.kernel.org/pub/software/scm/cogito/) + + Cogito is a version control system layered on top of the git tree history + storage system. It aims at seamless user interface and ease of use, + providing generally smoother user experience than the "raw" Core GIT + itself and indeed many other version control systems. + + + - *pg* (http://www.spearce.org/category/projects/scm/pg/) + + pg is a shell script wrapper around GIT to help the user manage a set of + patches to files. pg is somewhat like quilt or StGIT, but it does have a + slightly different feature set. + + + - *StGit* (http://www.procode.org/stgit/) + + Stacked GIT provides a quilt-like patch management functionality in the + GIT environment. You can easily manage your patches in the scope of GIT + until they get merged upstream. + + +History Viewers +--------------- + + - *gitk* (shipped with git-core) + + gitk is a simple Tk GUI for browsing history of GIT repositories easily. + + + - *gitview* (contrib/) + + gitview is a GTK based repository browser for git + + + - *gitweb* (shipped with git-core) + + GITweb provides full-fledged web interface for GIT repositories. + + + - *qgit* (http://digilander.libero.it/mcostalba/) + + QGit is a git/StGIT GUI viewer built on Qt/C++. QGit could be used + to browse history and directory tree, view annotated files, commit + changes cherry picking single files or applying patches. + Currently it is the fastest and most feature rich among the git + viewers and commit tools. + + - *tig* (http://jonas.nitro.dk/tig/) + + tig by Jonas Fonseca is a simple git repository browser + written using ncurses. Basically, it just acts as a front-end + for git-log and git-show/git-diff. Additionally, you can also + use it as a pager for git commands. + + +Foreign SCM interface +--------------------- + + - *git-svn* (shipped with git-core) + + git-svn is a simple conduit for changesets between a single Subversion + branch and git. + + + - *quilt2git / git2quilt* (http://home-tj.org/wiki/index.php/Misc) + + These utilities convert patch series in a quilt repository and commit + series in git back and forth. + + + - *hg-to-git* (contrib/) + + hg-to-git converts a Mercurial repository into a git one, and + preserves the full branch history in the process. hg-to-git can + also be used in an incremental way to keep the git repository + in sync with the master Mercurial repository. + + +Others +------ + + - *(h)gct* (http://www.cyd.liu.se/users/~freku045/gct/) + + Commit Tool or (h)gct is a GUI enabled commit tool for git and + Mercurial (hg). It allows the user to view diffs, select which files + to committed (or ignored / reverted) write commit messages and + perform the commit itself. + + - *git.el* (contrib/) + + This is an Emacs interface for git. The user interface is modeled on + pcl-cvs. It has been developed on Emacs 21 and will probably need some + tweaking to work on XEmacs. + + +http://git.or.cz/gitwiki/InterfacesFrontendsAndTools has more +comprehensive list. diff --git a/Documentation/git-unpack-file.txt b/Documentation/git-unpack-file.txt new file mode 100644 index 0000000000..213dc8196b --- /dev/null +++ b/Documentation/git-unpack-file.txt @@ -0,0 +1,36 @@ +git-unpack-file(1) +================== + +NAME +---- +git-unpack-file - Creates a temporary file with a blob's contents + + + +SYNOPSIS +-------- +'git-unpack-file' <blob> + +DESCRIPTION +----------- +Creates a file holding the contents of the blob specified by sha1. It +returns the name of the temporary file in the following format: + .merge_file_XXXXX + +OPTIONS +------- +<blob>:: + Must be a blob id + +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-unpack-objects.txt b/Documentation/git-unpack-objects.txt new file mode 100644 index 0000000000..ff6184b0f7 --- /dev/null +++ b/Documentation/git-unpack-objects.txt @@ -0,0 +1,55 @@ +git-unpack-objects(1) +===================== + +NAME +---- +git-unpack-objects - Unpack objects from a packed archive + + +SYNOPSIS +-------- +'git-unpack-objects' [-n] [-q] [-r] <pack-file + + +DESCRIPTION +----------- +Read a packed archive (.pack) from the standard input, expanding +the objects contained within and writing them into the repository in +"loose" (one object per file) format. + +Objects that already exist in the repository will *not* be unpacked +from the pack-file. Therefore, nothing will be unpacked if you use +this command on a pack-file that exists within the target repository. + +Please see the `git-repack` documentation for options to generate +new packs and replace existing ones. + +OPTIONS +------- +-n:: + Only list the objects that would be unpacked, don't actually unpack + them. + +-q:: + 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 +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +------------- +Documentation by Junio C Hamano + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt new file mode 100644 index 0000000000..cd5e014d48 --- /dev/null +++ b/Documentation/git-update-index.txt @@ -0,0 +1,323 @@ +git-update-index(1) +=================== + +NAME +---- +git-update-index - Register file contents in the working tree to the index + + +SYNOPSIS +-------- +[verse] +'git-update-index' + [--add] [--remove | --force-remove] [--replace] + [--refresh] [-q] [--unmerged] [--ignore-missing] + [--cacheinfo <mode> <object> <file>]\* + [--chmod=(+|-)x] + [--assume-unchanged | --no-assume-unchanged] + [--really-refresh] [--unresolve] [--again | -g] + [--info-only] [--index-info] + [-z] [--stdin] + [--verbose] + [--] [<file>]\* + +DESCRIPTION +----------- +Modifies the index or directory cache. Each file mentioned is updated +into the index and any 'unmerged' or 'needs updating' state is +cleared. + +The way "git-update-index" handles files it is told about can be modified +using the various options: + +OPTIONS +------- +--add:: + If a specified file isn't in the index already then it's + added. + Default behaviour is to ignore new files. + +--remove:: + If a specified file is in the index but is missing then it's + removed. + Default behavior is to ignore removed file. + +--refresh:: + Looks at the current index and checks to see if merges or + updates are needed by checking stat() information. + +-q:: + Quiet. If --refresh finds that the index needs an update, the + default behavior is to error out. This option makes + git-update-index continue anyway. + +--unmerged:: + If --refresh finds unmerged changes in the index, the default + behavior is to error out. This option makes git-update-index + continue anyway. + +--ignore-missing:: + Ignores missing files during a --refresh + +--cacheinfo <mode> <object> <path>:: + Directly insert the specified info into the index. + +--index-info:: + Read index information from stdin. + +--chmod=(+|-)x:: + Set the execute permissions on the updated files. + +--assume-unchanged, --no-assume-unchanged:: + When these flags are specified, the object name recorded + for the paths are not updated. Instead, these options + sets and unsets the "assume unchanged" bit for the + paths. When the "assume unchanged" bit is on, git stops + checking the working tree files for possible + modifications, so you need to manually unset the bit to + tell git when you change the working tree file. This is + sometimes helpful when working with a big project on a + filesystem that has very slow lstat(2) system call + (e.g. cifs). + +--again, -g:: + Runs `git-update-index` itself on the paths whose index + entries are different from those from the `HEAD` commit. + +--unresolve:: + Restores the 'unmerged' or 'needs updating' state of a + file during a merge if it was cleared by accident. + +--info-only:: + Do not create objects in the object database for all + <file> arguments that follow this flag; just insert + their object IDs into the index. + +--force-remove:: + Remove the file from the index even when the working directory + still has such a file. (Implies --remove.) + +--replace:: + By default, when a file `path` exists in the index, + git-update-index refuses an attempt to add `path/file`. + Similarly if a file `path/file` exists, a file `path` + cannot be added. With --replace flag, existing entries + that conflicts with the entry being added are + automatically removed with warning messages. + +--stdin:: + Instead of taking list of paths from the command line, + read list of paths from the standard input. Paths are + separated by LF (i.e. one path per line) by default. + +--verbose:: + Report what is being added and removed from index. + +-z:: + Only meaningful with `--stdin`; paths are separated with + NUL character instead of LF. + +\--:: + Do not interpret any more arguments as options. + +<file>:: + Files to act on. + Note that files beginning with '.' are discarded. This includes + `./file` and `dir/./file`. If you don't want this, then use + cleaner names. + The same applies to directories ending '/' and paths with '//' + +Using --refresh +--------------- +'--refresh' does not calculate a new sha1 file or bring the index +up-to-date for mode/content changes. But what it *does* do is to +"re-match" the stat information of a file with the index, so that you +can refresh the index for a file that hasn't been changed but where +the stat entry is out of date. + +For example, you'd want to do this after doing a "git-read-tree", to link +up the stat index details with the proper files. + +Using --cacheinfo or --info-only +-------------------------------- +'--cacheinfo' is used to register a file that is not in the +current working directory. This is useful for minimum-checkout +merging. + +To pretend you have a file with mode and sha1 at path, say: + +---------------- +$ git-update-index --cacheinfo mode sha1 path +---------------- + +'--info-only' is used to register files without placing them in the object +database. This is useful for status-only repositories. + +Both '--cacheinfo' and '--info-only' behave similarly: the index is updated +but the object database isn't. '--cacheinfo' is useful when the object is +in the database but the file isn't available locally. '--info-only' is +useful when the file is available, but you do not wish to update the +object database. + + +Using --index-info +------------------ + +`--index-info` is a more powerful mechanism that lets you feed +multiple entry definitions from the standard input, and designed +specifically for scripts. It can take inputs of three formats: + + . mode SP sha1 TAB path ++ +The first format is what "git-apply --index-info" +reports, and used to reconstruct a partial tree +that is used for phony merge base tree when falling +back on 3-way merge. + + . mode SP type SP sha1 TAB path ++ +The second format is to stuff git-ls-tree output +into the index file. + + . mode SP sha1 SP stage TAB path ++ +This format is to put higher order stages into the +index file and matches git-ls-files --stage output. + +To place a higher stage entry to the index, the path should +first be removed by feeding a mode=0 entry for the path, and +then feeding necessary input lines in the third format. + +For example, starting with this index: + +------------ +$ git ls-files -s +100644 8a1218a1024a212bb3db30becd860315f9f3ac52 0 frotz +------------ + +you can feed the following input to `--index-info`: + +------------ +$ git update-index --index-info +0 0000000000000000000000000000000000000000 frotz +100644 8a1218a1024a212bb3db30becd860315f9f3ac52 1 frotz +100755 8a1218a1024a212bb3db30becd860315f9f3ac52 2 frotz +------------ + +The first line of the input feeds 0 as the mode to remove the +path; the SHA1 does not matter as long as it is well formatted. +Then the second and third line feeds stage 1 and stage 2 entries +for that path. After the above, we would end up with this: + +------------ +$ git ls-files -s +100644 8a1218a1024a212bb3db30becd860315f9f3ac52 1 frotz +100755 8a1218a1024a212bb3db30becd860315f9f3ac52 2 frotz +------------ + + +Using ``assume unchanged'' bit +------------------------------ + +Many operations in git depend on your filesystem to have an +efficient `lstat(2)` implementation, so that `st_mtime` +information for working tree files can be cheaply checked to see +if the file contents have changed from the version recorded in +the index file. Unfortunately, some filesystems have +inefficient `lstat(2)`. If your filesystem is one of them, you +can set "assume unchanged" bit to paths you have not changed to +cause git not to do this check. Note that setting this bit on a +path does not mean git will check the contents of the file to +see if it has changed -- it makes git to omit any checking and +assume it has *not* changed. When you make changes to working +tree files, you have to explicitly tell git about it by dropping +"assume unchanged" bit, either before or after you modify them. + +In order to set "assume unchanged" bit, use `--assume-unchanged` +option. To unset, use `--no-assume-unchanged`. + +The command looks at `core.ignorestat` configuration variable. When +this is true, paths updated with `git-update-index paths...` and +paths updated with other git commands that update both index and +working tree (e.g. `git-apply --index`, `git-checkout-index -u`, +and `git-read-tree -u`) are automatically marked as "assume +unchanged". Note that "assume unchanged" bit is *not* set if +`git-update-index --refresh` finds the working tree file matches +the index (use `git-update-index --really-refresh` if you want +to mark them as "assume unchanged"). + + +Examples +-------- +To update and refresh only the files already checked out: + +---------------- +$ git-checkout-index -n -f -a && git-update-index --ignore-missing --refresh +---------------- + +On an inefficient filesystem with `core.ignorestat` set:: ++ +------------ +$ git update-index --really-refresh <1> +$ git update-index --no-assume-unchanged foo.c <2> +$ git diff --name-only <3> +$ edit foo.c +$ git diff --name-only <4> +M foo.c +$ git update-index foo.c <5> +$ git diff --name-only <6> +$ edit foo.c +$ git diff --name-only <7> +$ git update-index --no-assume-unchanged foo.c <8> +$ git diff --name-only <9> +M foo.c +------------ ++ +<1> forces lstat(2) to set "assume unchanged" bits for paths that match index. +<2> mark the path to be edited. +<3> this does lstat(2) and finds index matches the path. +<4> this does lstat(2) and finds index does *not* match the path. +<5> registering the new version to index sets "assume unchanged" bit. +<6> and it is assumed unchanged. +<7> even after you edit it. +<8> you can tell about the change after the fact. +<9> now it checks with lstat(2) and finds it has been changed. + + +Configuration +------------- + +The command honors `core.filemode` configuration variable. If +your repository is on an filesystem whose executable bits are +unreliable, this should be set to 'false' (see gitlink:git-config[1]). +This causes the command to ignore differences in file modes recorded +in the index and the file mode on the filesystem if they differ only on +executable bit. On such an unfortunate filesystem, you may +need to use `git-update-index --chmod=`. + +Quite similarly, if `core.symlinks` configuration variable is set +to 'false' (see gitlink:git-config[1]), symbolic links are checked out +as plain files, and this command does not modify a recorded file mode +from symbolic link to regular file. + +The command looks at `core.ignorestat` configuration variable. See +'Using "assume unchanged" bit' section above. + + +See Also +-------- +gitlink:git-config[1] + + +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-update-ref.txt b/Documentation/git-update-ref.txt new file mode 100644 index 0000000000..9424feab32 --- /dev/null +++ b/Documentation/git-update-ref.txt @@ -0,0 +1,90 @@ +git-update-ref(1) +================= + +NAME +---- +git-update-ref - Update the object name stored in a ref safely + +SYNOPSIS +-------- +'git-update-ref' [-m <reason>] (-d <ref> <oldvalue> | <ref> <newvalue> [<oldvalue>]) + +DESCRIPTION +----------- +Given two arguments, stores the <newvalue> in the <ref>, possibly +dereferencing the symbolic refs. E.g. `git-update-ref HEAD +<newvalue>` updates the current branch head to the new object. + +Given three arguments, stores the <newvalue> in the <ref>, +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>. 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 +"ref:". + +More importantly, it allows the update of a ref file to follow +these symbolic pointers, whether they are symlinks or these +"regular file symbolic refs". It follows *real* symlinks only +if they start with "refs/": otherwise it will just try to read +them and update them as a regular file (i.e. it will allow the +filesystem to follow them, but will overwrite such a symlink to +somewhere else with a regular filename). + +In general, using + + git-update-ref HEAD "$head" + +should be a _lot_ safer than doing + + echo "$head" > "$GIT_DIR/HEAD" + +both from a symlink following standpoint *and* an error checking +standpoint. The "refs/" rule for symlinks means that symlinks +that point to "outside" the tree are safe: they'll be followed +for reading but not for writing (so we'll never write through a +ref symlink to some other tree, if you have copied a whole +archive by creating a symlink tree). + +With `-d` flag, it deletes the named <ref> after verifying it +still contains <oldvalue>. + + +Logging Updates +--------------- +If config parameter "core.logAllRefUpdates" is true or the file +"$GIT_DIR/logs/<ref>" exists then `git-update-ref` will append +a line to the log file "$GIT_DIR/logs/<ref>" (dereferencing all +symbolic refs before creating the log name) describing the change +in ref value. Log lines are formatted as: + + . oldsha1 SP newsha1 SP committer LF ++ +Where "oldsha1" is the 40 character hexadecimal value previously +stored in <ref>, "newsha1" is the 40 character hexadecimal value of +<newvalue> and "committer" is the committer's name, email address +and date in the standard GIT committer ident format. + +Optionally with -m: + + . oldsha1 SP newsha1 SP committer TAB message LF ++ +Where all fields are as described above and "message" is the +value supplied to the -m option. + +An update will fail (without changing <ref>) if the current user is +unable to create a new log file, append to the existing log file +or does not have committer information available. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-update-server-info.txt b/Documentation/git-update-server-info.txt new file mode 100644 index 0000000000..88a03c7c5e --- /dev/null +++ b/Documentation/git-update-server-info.txt @@ -0,0 +1,58 @@ +git-update-server-info(1) +========================= + +NAME +---- +git-update-server-info - Update auxiliary info file to help dumb servers + + +SYNOPSIS +-------- +'git-update-server-info' [--force] + +DESCRIPTION +----------- +A dumb server that does not do on-the-fly pack generations must +have some auxiliary information files in $GIT_DIR/info and +$GIT_OBJECT_DIRECTORY/info directories to help clients discover +what references and packs the server has. This command +generates such auxiliary files. + + +OPTIONS +------- + +-f|--force:: + Update the info files from scratch. + + +OUTPUT +------ + +Currently the command updates the following files. Please see +link:repository-layout.html[repository-layout] for description +of what they are for: + +* objects/info/packs + +* info/refs + + +BUGS +---- +When you remove an existing ref, the command fails to update +info/refs file unless `--force` flag is given. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-upload-archive.txt b/Documentation/git-upload-archive.txt new file mode 100644 index 0000000000..403871d7c6 --- /dev/null +++ b/Documentation/git-upload-archive.txt @@ -0,0 +1,37 @@ +git-upload-archive(1) +==================== + +NAME +---- +git-upload-archive - Send archive back to git-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-pack.txt b/Documentation/git-upload-pack.txt new file mode 100644 index 0000000000..fd6519299a --- /dev/null +++ b/Documentation/git-upload-pack.txt @@ -0,0 +1,46 @@ +git-upload-pack(1) +================== + +NAME +---- +git-upload-pack - Send objects packed back to git-fetch-pack + + +SYNOPSIS +-------- +'git-upload-pack' [--strict] [--timeout=<n>] <directory> + +DESCRIPTION +----------- +Invoked by 'git-fetch-pack', learns what +objects the other side is missing, and sends them after packing. + +This command is usually not invoked directly by the end user. +The UI for the protocol is on the 'git-fetch-pack' side, and the +program pair is meant to be used to pull updates from a remote +repository. For push operations, see 'git-send-pack'. + + +OPTIONS +------- + +\--strict:: + Do not try <directory>/.git/ if <directory> is no git directory. + +\--timeout=<n>:: + Interrupt transfer after <n> seconds of inactivity. + +<directory>:: + The repository to sync from. + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-var.txt b/Documentation/git-var.txt new file mode 100644 index 0000000000..9b0de1c111 --- /dev/null +++ b/Documentation/git-var.txt @@ -0,0 +1,65 @@ +git-var(1) +========== + +NAME +---- +git-var - Show a git logical variable + + +SYNOPSIS +-------- +'git-var' [ -l | <variable> ] + +DESCRIPTION +----------- +Prints a git logical variable. + +OPTIONS +------- +-l:: + Cause the logical variables to be listed. In addition, all the + variables of the git configuration file .git/config are listed + as well. (However, the configuration variables listing functionality + is deprecated in favor of `git-config -l`.) + +EXAMPLE +-------- + $ git-var GIT_AUTHOR_IDENT + Eric W. Biederman <ebiederm@lnxi.com> 1121223278 -0600 + + +VARIABLES +---------- +GIT_AUTHOR_IDENT:: + The author of a piece of code. + +GIT_COMMITTER_IDENT:: + The person who put a piece of code into git. + +Diagnostics +----------- +You don't exist. Go away!:: + The passwd(5) gecos field couldn't be read +Your parents must have hated you!:: + The password(5) gecos field is longer than a giant static buffer. +Your sysadmin must hate you!:: + The password(5) name field is longer than a giant static buffer. + +See Also +-------- +gitlink:git-commit-tree[1] +gitlink:git-tag[1] +gitlink:git-config[1] + +Author +------ +Written by Eric Biederman <ebiederm@xmission.com> + +Documentation +-------------- +Documentation by Eric Biederman and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-verify-pack.txt b/Documentation/git-verify-pack.txt new file mode 100644 index 0000000000..7a6132b016 --- /dev/null +++ b/Documentation/git-verify-pack.txt @@ -0,0 +1,54 @@ +git-verify-pack(1) +================== + +NAME +---- +git-verify-pack - Validate packed git archive files + + +SYNOPSIS +-------- +'git-verify-pack' [-v] [--] <pack>.idx ... + + +DESCRIPTION +----------- +Reads given idx file for packed git archive created with +git-pack-objects command and verifies idx file and the +corresponding pack file. + +OPTIONS +------- +<pack>.idx ...:: + The idx files to verify. + +-v:: + After verifying the pack, show list of objects contained + in the pack. +\--:: + Do not interpret any more arguments as options. + +OUTPUT FORMAT +------------- +When specifying the -v option the format used is: + + SHA1 type size offset-in-packfile + +for objects that are not deltified in the pack, and + + SHA1 type size offset-in-packfile depth base-SHA1 + +for objects that are deltified. + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by Junio C Hamano + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-verify-tag.txt b/Documentation/git-verify-tag.txt new file mode 100644 index 0000000000..0f9bdb58dc --- /dev/null +++ b/Documentation/git-verify-tag.txt @@ -0,0 +1,32 @@ +git-verify-tag(1) +================= + +NAME +---- +git-verify-tag - Check the GPG signature of tag + +SYNOPSIS +-------- +'git-verify-tag' <tag> + +DESCRIPTION +----------- +Validates the gpg signature created by git-tag. + +OPTIONS +------- +<tag>:: + SHA1 identifier of a git tag object. + +Author +------ +Written by Jan Harkes <jaharkes@cs.cmu.edu> and Eric W. Biederman <ebiederm@xmission.com> + +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-whatchanged.txt b/Documentation/git-whatchanged.txt new file mode 100644 index 0000000000..399bff3bbc --- /dev/null +++ b/Documentation/git-whatchanged.txt @@ -0,0 +1,81 @@ +git-whatchanged(1) +================== + +NAME +---- +git-whatchanged - Show logs with difference each commit introduces + + +SYNOPSIS +-------- +'git-whatchanged' <option>... + +DESCRIPTION +----------- +Shows commit logs and diff output each commit introduces. The +command internally invokes 'git-rev-list' piped to +'git-diff-tree', and takes command line options for both of +these commands. + +This manual page describes only the most frequently used options. + + +OPTIONS +------- +-p:: + Show textual diffs, instead of the git internal diff + output format that is useful only to tell the changed + paths and their nature of changes. + +-<n>:: + Limit output to <n> commits. + +<since>..<until>:: + Limit output to between the two named commits (bottom + exclusive, top inclusive). + +-r:: + Show git internal diff output, but for the whole tree, + not just the top level. + +--pretty=<format>:: + Controls the output format for the commit logs. + <format> can be one of 'raw', 'medium', 'short', 'full', + and 'oneline'. + +-m:: + By default, differences for merge commits are not shown. + With this flag, show differences to that commit from all + of its parents. ++ +However, it is not very useful in general, although it +*is* useful on a file-by-file basis. + +Examples +-------- +git-whatchanged -p v2.6.12.. include/scsi drivers/scsi:: + + Show as patches the commits since version 'v2.6.12' that changed + any file in the include/scsi or drivers/scsi subdirectories + +git-whatchanged --since="2 weeks ago" \-- gitk:: + + Show the changes during the last two weeks to the file 'gitk'. + The "--" is necessary to avoid confusion with the *branch* named + 'gitk' + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> and +Junio C Hamano <junkio@cox.net> + + +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-write-tree.txt b/Documentation/git-write-tree.txt new file mode 100644 index 0000000000..96d5e07b11 --- /dev/null +++ b/Documentation/git-write-tree.txt @@ -0,0 +1,50 @@ +git-write-tree(1) +================= + +NAME +---- +git-write-tree - Create a tree object from the current index + + +SYNOPSIS +-------- +'git-write-tree' [--missing-ok] [--prefix=<prefix>/] + +DESCRIPTION +----------- +Creates a tree object using the current index. + +The index must be in a fully merged state. + +Conceptually, `git-write-tree` sync()s the current index contents +into a set of tree files. +In order to have that match what is actually in your directory right +now, you need to have done a `git-update-index` phase before you did the +`git-write-tree`. + + +OPTIONS +------- +--missing-ok:: + Normally `git-write-tree` ensures that the objects referenced by the + directory exist in the object database. This option disables this + check. + +--prefix=<prefix>/:: + Writes a tree object that represents a subdirectory + `<prefix>`. This can be used to write the tree object + for a subproject that is in the named subdirectory. + + +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.txt b/Documentation/git.txt new file mode 100644 index 0000000000..e875e8318d --- /dev/null +++ b/Documentation/git.txt @@ -0,0 +1,409 @@ +git(7) +====== + +NAME +---- +git - the stupid content tracker + + +SYNOPSIS +-------- +[verse] +'git' [--version] [--exec-path[=GIT_EXEC_PATH]] [-p|--paginate] + [--bare] [--git-dir=GIT_DIR] [--help] COMMAND [ARGS] + +DESCRIPTION +----------- +Git is a fast, scalable, distributed revision control system with an +unusually rich command set that provides both high-level operations +and full access to internals. + +See this link:tutorial.html[tutorial] to get started, then see +link:everyday.html[Everyday Git] for a useful minimum set of commands, and +"man git-commandname" for documentation of each command. CVS users may +also want to read link:cvs-migration.html[CVS migration]. +link:user-manual.html[Git User's Manual] is still work in +progress, but when finished hopefully it will guide a new user +in a coherent way to git enlightenment ;-). + +The COMMAND is either a name of a Git command (see below) or an alias +as defined in the configuration file (see gitlink:git-config[1]). + +ifdef::stalenotes[] +[NOTE] +============ +You are reading the documentation for the latest version of git. +Documentation for older releases are available here: + +* link:v1.5.0.3/git.html[documentation for release 1.5.0.3] + +* link:v1.5.0.3/RelNotes-1.5.0.3.txt[release notes for 1.5.0.3] + +* link:v1.5.0.2/RelNotes-1.5.0.2.txt[release notes for 1.5.0.2] + +* link:v1.5.0.1/RelNotes-1.5.0.1.txt[release notes for 1.5.0.1] + +* link:v1.5.0/RelNotes-1.5.0.txt[release notes for 1.5.0] + +* link:v1.4.4.4/git.html[documentation for release 1.4.4.4] + +* link:v1.3.3/git.html[documentation for release 1.3.3] + +* link:v1.2.6/git.html[documentation for release 1.2.6] + +* link:v1.0.13/git.html[documentation for release 1.0.13] + +============ + +endif::stalenotes[] + +OPTIONS +------- +--version:: + Prints the git suite version that the 'git' program came from. + +--help:: + Prints the synopsis and a list of the most commonly used + commands. If a git command is named this option will bring up + the man-page for that command. If the option '--all' or '-a' is + given then all available commands are printed. + +--exec-path:: + Path to wherever your core git programs are installed. + This can also be controlled by setting the GIT_EXEC_PATH + environment variable. If no path is given 'git' will print + the current setting and then exit. + +-p|--paginate:: + Pipe all output into 'less' (or if set, $PAGER). + +--git-dir=<path>:: + Set the path to the repository. This can also be controlled by + setting the GIT_DIR environment variable. + +--bare:: + Same as --git-dir=`pwd`. + +FURTHER DOCUMENTATION +--------------------- + +See the references above to get started using git. The following is +probably more detail than necessary for a first-time user. + +The <<Discussion,Discussion>> section below and the +link:core-tutorial.html[Core tutorial] both provide introductions to the +underlying git architecture. + +See also the link:howto-index.html[howto] documents for some useful +examples. + +GIT COMMANDS +------------ + +We divide git into high level ("porcelain") commands and low level +("plumbing") commands. + +High-level commands (porcelain) +------------------------------- + +We separate the porcelain commands into the main commands and some +ancillary user utilities. + +Main porcelain commands +~~~~~~~~~~~~~~~~~~~~~~~ + +include::cmds-mainporcelain.txt[] + +Ancillary Commands +~~~~~~~~~~~~~~~~~~ +Manipulators: + +include::cmds-ancillarymanipulators.txt[] + +Interrogators: + +include::cmds-ancillaryinterrogators.txt[] + + +Interacting with Others +~~~~~~~~~~~~~~~~~~~~~~~ + +These commands are to interact with foreign SCM and with other +people via patch over e-mail. + +include::cmds-foreignscminterface.txt[] + + +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]. + +The interface (input, output, set of options and the semantics) +to these low-level commands are meant to be a lot more stable +than Porcelain level commands, because these commands are +primarily for scripted use. The interface to Porcelain commands +on the other hand are subject to change in order to improve the +end user experience. + +The following description divides +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 +~~~~~~~~~~~~~~~~~~~~~ + +include::cmds-plumbingmanipulators.txt[] + + +Interrogation commands +~~~~~~~~~~~~~~~~~~~~~~ + +include::cmds-plumbinginterrogators.txt[] + +In general, the interrogate commands do not touch the files in +the working tree. + + +Synching repositories +~~~~~~~~~~~~~~~~~~~~~ + +include::cmds-synchingrepositories.txt[] + +The following are helper programs used by the above; end users +typically do not use them directly. + +include::cmds-synchelpers.txt[] + + +Internal helper commands +~~~~~~~~~~~~~~~~~~~~~~~~ + +These are internal helper commands used by other commands; end +users typically do not use them directly. + +include::cmds-purehelpers.txt[] + + +Configuration Mechanism +----------------------- + +Starting from 0.99.9 (actually mid 0.99.8.GIT), `.git/config` file +is used to hold per-repository configuration options. It is a +simple text file modeled after `.ini` format familiar to some +people. Here is an example: + +------------ +# +# A '#' or ';' character indicates a comment. +# + +; core variables +[core] + ; Don't trust file modes + filemode = false + +; user identity +[user] + name = "Junio C Hamano" + email = "junkio@twinsun.com" + +------------ + +Various commands read from the configuration file and adjust +their operation accordingly. + + +Identifier Terminology +---------------------- +<object>:: + Indicates the object name for any type of object. + +<blob>:: + Indicates a blob object name. + +<tree>:: + Indicates a tree object name. + +<commit>:: + Indicates a commit object name. + +<tree-ish>:: + Indicates a tree, commit or tag object name. A + command that takes a <tree-ish> argument ultimately wants to + operate on a <tree> object but automatically dereferences + <commit> and <tag> objects that point at a <tree>. + +<commit-ish>:: + Indicates a commit or tag object name. A + command that takes a <commit-ish> argument ultimately wants to + operate on a <commit> object but automatically dereferences + <tag> objects that point at a <commit>. + +<type>:: + Indicates that an object type is required. + Currently one of: `blob`, `tree`, `commit`, or `tag`. + +<file>:: + Indicates a filename - almost always relative to the + root of the tree structure `GIT_INDEX_FILE` describes. + +Symbolic Identifiers +-------------------- +Any git command accepting any <object> can also use the following +symbolic notation: + +HEAD:: + indicates the head of the current branch (i.e. the + contents of `$GIT_DIR/HEAD`). + +<tag>:: + a valid tag 'name' + (i.e. the contents of `$GIT_DIR/refs/tags/<tag>`). + +<head>:: + a valid head 'name' + (i.e. the contents of `$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 +------------------------ + +Please see link:repository-layout.html[repository layout] document. + +Read link:hooks.html[hooks] for more details about each hook. + +Higher level SCMs may provide and manage additional information in the +`$GIT_DIR`. + + +Terminology +----------- +Please see link:glossary.html[glossary] document. + + +Environment Variables +--------------------- +Various git commands use the following environment variables: + +The git Repository +~~~~~~~~~~~~~~~~~~ +These environment variables apply to 'all' core git commands. Nb: it +is worth noting that they may be used/overridden by SCMS sitting above +git so take care if using Cogito etc. + +'GIT_INDEX_FILE':: + This environment allows the specification of an alternate + index file. If not specified, the default of `$GIT_DIR/index` + is used. + +'GIT_OBJECT_DIRECTORY':: + If the object storage directory is specified via this + environment variable then the sha1 directories are created + underneath - otherwise the default `$GIT_DIR/objects` + directory is used. + +'GIT_ALTERNATE_OBJECT_DIRECTORIES':: + Due to the immutable nature of git objects, old objects can be + archived into shared, read-only directories. This variable + specifies a ":" separated list of git object directories which + can be used to search for git objects. New objects will not be + written to these directories. + +'GIT_DIR':: + If the 'GIT_DIR' environment variable is set then it + specifies a path to use instead of the default `.git` + for the base of the repository. + +git Commits +~~~~~~~~~~~ +'GIT_AUTHOR_NAME':: +'GIT_AUTHOR_EMAIL':: +'GIT_AUTHOR_DATE':: +'GIT_COMMITTER_NAME':: +'GIT_COMMITTER_EMAIL':: + see gitlink:git-commit-tree[1] + +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':: + 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 +~~~~~ +'GIT_PAGER':: + This environment variable overrides `$PAGER`. + +'GIT_TRACE':: + 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]] +------------------------ +include::core-intro.txt[] + +Authors +------- +* git's founding father is Linus Torvalds <torvalds@osdl.org>. +* The current git nurse is Junio C Hamano <junkio@cox.net>. +* The git potty was written by Andres Ericsson <ae@op5.se>. +* General upbringing is handled by the git-list <git@vger.kernel.org>. + +Documentation +-------------- +The documentation for git suite was started by David Greaves +<david@dgreaves.com>, and later enhanced greatly by the +contributors on the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/gitk.txt b/Documentation/gitk.txt new file mode 100644 index 0000000000..48c5894736 --- /dev/null +++ b/Documentation/gitk.txt @@ -0,0 +1,102 @@ +gitk(1) +======= + +NAME +---- +gitk - The git repository browser + +SYNOPSIS +-------- +'gitk' [<option>...] [<revs>] [--] [<path>...] + +DESCRIPTION +----------- +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 +------- +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. + +<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. + For a more complete list of ways to spell object names, see + "SPECIFYING REVISIONS" section in gitlink:git-rev-parse[1]. + +<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 preceding options. + +Examples +-------- +gitk 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 + +gitk --since="2 weeks ago" \-- gitk:: + + Show the changes during the last two weeks to the file '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>. + +Documentation +-------------- +Documentation by 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/glossary.txt b/Documentation/glossary.txt new file mode 100644 index 0000000000..9f446241e2 --- /dev/null +++ b/Documentation/glossary.txt @@ -0,0 +1,365 @@ +alternate object database:: + Via the alternates mechanism, a repository can inherit part of its + object database from another object database, which is called + "alternate". + +bare repository:: + A bare repository is normally an appropriately named + directory with a `.git` suffix that does not have a + locally checked-out copy of any of the files under revision + control. That is, all of the `git` administrative and + control files that would normally be present in the + hidden `.git` sub-directory are directly present in + the `repository.git` directory instead, and no other files + are present and checked out. Usually publishers of public + repositories make bare repositories available. + +blob object:: + Untyped object, e.g. the contents of a file. + +branch:: + A non-cyclical graph of revisions, i.e. the complete history of + a particular revision, which is called the branch head. The + branch heads are stored in `$GIT_DIR/refs/heads/`. + +cache:: + Obsolete for: index. + +chain:: + A list of objects, where each object in the list contains a + reference to its successor (for example, the successor of a commit + could be one of its parents). + +changeset:: + BitKeeper/cvsps speak for "commit". Since git does not store + changes, but states, it really does not make sense to use + the term "changesets" with git. + +checkout:: + The action of updating the working tree to a revision which was + stored in the object database. + +cherry-picking:: + In SCM jargon, "cherry pick" means to choose a subset of + changes out of a series of changes (typically commits) + and record them as a new series of changes on top of + different codebase. In GIT, this is performed by + "git cherry-pick" command to extract the change + introduced by an existing commit and to record it based + on the tip of the current branch as a new commit. + +clean:: + A working tree is clean, if it corresponds to the revision + referenced by the current head. Also see "dirty". + +commit:: + As a verb: The action of storing the current state of the index in the + object database. The result is a revision. + As a noun: Short hand for commit object. + +commit object:: + An object which contains the information about a particular + revision, such as parents, committer, author, date and the + tree object which corresponds to the top directory of the + stored revision. + +core git:: + Fundamental data structures and utilities of git. Exposes only + limited source code management tools. + +DAG:: + Directed acyclic graph. The commit objects form a directed acyclic + graph, because they have parents (directed), and the graph of commit + objects is acyclic (there is no chain which begins and ends with the + same object). + +dangling object:: + An unreachable object which is not reachable even from other + unreachable objects; a dangling object has no references to it + from any reference or object in the repository. + +dircache:: + You are *waaaaay* behind. + +dirty:: + A working tree is said to be dirty if it contains modifications + which have not been committed to the current branch. + +directory:: + The list you get with "ls" :-) + +ent:: + Favorite synonym to "tree-ish" by some total geeks. See + `http://en.wikipedia.org/wiki/Ent_(Middle-earth)` for an in-depth + explanation. Avoid this term, not to confuse people. + +fast forward:: + A fast-forward is a special type of merge where you have + a revision and you are "merging" another branch's changes + that happen to be a descendant of what you have. + In such these cases, you do not make a new merge commit but + instead just update to his revision. This will happen + frequently on a tracking branch of a remote repository. + +fetch:: + Fetching a branch means to get the branch's head ref from a + remote repository, to find out which objects are missing from + the local object database, and to get them, too. + +file system:: + Linus Torvalds originally designed git to be a user space file + system, i.e. the infrastructure to hold files and directories. + That ensured the efficiency and speed of git. + +git archive:: + Synonym for repository (for arch people). + +grafts:: + Grafts enables two otherwise different lines of development to be + joined together by recording fake ancestry information for commits. + This way you can make git pretend the set of parents a commit + has is different from what was recorded when the commit was created. + Configured via the `.git/info/grafts` file. + +hash:: + In git's context, synonym to object name. + +head:: + The top of a branch. It contains a ref to the corresponding + commit object. + +head ref:: + A ref pointing to a head. Often, this is abbreviated to "head". + Head refs are stored in `$GIT_DIR/refs/heads/`. + +hook:: + During the normal execution of several git commands, + call-outs are made to optional scripts that allow + a developer to add functionality or checking. + Typically, the hooks allow for a command to be pre-verified + and potentially aborted, and allow for a post-notification + after the operation is done. + The hook scripts are found in the `$GIT_DIR/hooks/` directory, + and are enabled by simply making them executable. + +index:: + A collection of files with stat information, whose contents are + stored as objects. The index is a stored version of your working + tree. Truth be told, it can also contain a second, and even a third + version of a working tree, which are used when merging. + +index entry:: + The information regarding a particular file, stored in the index. + An index entry can be unmerged, if a merge was started, but not + yet finished (i.e. if the index contains multiple versions of + that file). + +master:: + The default development branch. Whenever you create a git + repository, a branch named "master" is created, and becomes + the active branch. In most cases, this contains the local + development, though that is purely conventional and not required. + +merge:: + To merge branches means to try to accumulate the changes since a + common ancestor and apply them to the first branch. An automatic + merge uses heuristics to accomplish that. Evidently, an automatic + merge can fail. + +object:: + The unit of storage in git. It is uniquely identified by + the SHA1 of its contents. Consequently, an object can not + be changed. + +object database:: + Stores a set of "objects", and an individual object is identified + by its object name. The objects usually live in `$GIT_DIR/objects/`. + +object identifier:: + Synonym for object name. + +object name:: + The unique identifier of an object. The hash of the object's contents + using the Secure Hash Algorithm 1 and usually represented by the 40 + character hexadecimal encoding of the hash of the object (possibly + followed by a white space). + +object type:: + One of the identifiers "commit","tree","tag" and "blob" describing + the type of an object. + +octopus:: + To merge more than two branches. Also denotes an intelligent + predator. + +origin:: + 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 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 + space or to transmit them efficiently). + +pack index:: + The list of identifiers, and other information, of the objects in a + pack, to assist in efficiently accessing the contents of a pack. + +parent:: + A commit object contains a (possibly empty) list of the logical + predecessor(s) in the line of development, i.e. its parents. + +pickaxe:: + The term pickaxe refers to an option to the diffcore routines + that help select changes that add or delete a given text string. + With the --pickaxe-all option, it can be used to view the + full changeset that introduced or removed, say, a particular + line of text. See gitlink:git-diff[1]. + +plumbing:: + Cute name for core git. + +porcelain:: + Cute name for programs and program suites depending on core git, + presenting a high level access to core git. Porcelains expose + more of a SCM interface than the plumbing. + +pull:: + Pulling a branch means to fetch it and merge it. + +push:: + Pushing a branch means to get the branch's head ref from a remote + repository, find out if it is an ancestor to the branch's local + head ref is a direct, and in that case, putting all objects, which + are reachable from the local head ref, and which are missing from + the remote repository, into the remote object database, and updating + the remote head ref. If the remote head is not an ancestor to the + local head, the push fails. + +reachable:: + 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 + development ("master"), and reapply the (possibly cherry-picked) + changes from that branch. + +ref:: + A 40-byte hex representation of a SHA1 or a name that denotes + a particular object. These may be stored in `$GIT_DIR/refs/`. + +refspec:: + A refspec is used by fetch and push to describe the mapping + between remote ref and local ref. They are combined with + a colon in the format <src>:<dst>, preceded by an optional + plus sign, +. For example: + `git fetch $URL refs/heads/master:refs/heads/origin` + 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 branch + at $URL". See also gitlink:git-push[1] + +repository:: + A collection of refs together with an object database containing + all objects, which are reachable from the refs, possibly accompanied + by meta data from one or more porcelains. A repository can + share an object database with other repositories. + +resolve:: + The action of fixing up manually what a failed automatic merge + left behind. + +revision:: + A particular state of files and directories which was stored in + the object database. It is referenced by a commit object. + +rewind:: + To throw away part of the development, i.e. to assign the head to + an earlier revision. + +SCM:: + Source code management (tool). + +SHA1:: + Synonym for object name. + +shallow repository:: + A shallow repository has an incomplete history some of + whose commits have parents cauterized away (in other + words, git is told to pretend that these commits do not + have the parents, even though they are recorded in the + commit object). This is sometimes useful when you are + interested only in the recent history of a project even + though the real history recorded in the upstream is + much larger. A shallow repository is created by giving + `--depth` option to gitlink:git-clone[1], and its + history can be later deepened with gitlink:git-fetch[1]. + +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 + are very easy and inexpensive, it is often desirable to + have several small branches that each contain very well + defined concepts or small incremental yet related changes. + +tracking branch:: + A regular git branch that is used to follow changes from + another repository. A tracking branch should not contain + direct modifications or have local commits made to it. + A tracking branch can usually be identified as the + right-hand-side ref in a Pull: refspec. + +tree object:: + An object containing a list of file names and modes along with refs + to the associated blob and/or tree objects. A tree is equivalent + to a directory. + +tree:: + Either a working tree, or a tree object together with the + dependent blob and tree objects (i.e. a stored representation + of a working tree). + +tree-ish:: + A ref pointing to either a commit object, a tree object, or a + tag object pointing to a tag or commit or tree object. + +tag object:: + An object containing a ref pointing to another object, which can + contain a message just like a commit object. It can also + contain a (PGP) signature, in which case it is called a "signed + tag object". + +tag:: + A ref pointing to a tag or commit object. In contrast to a head, + a tag is not changed by a commit. Tags (not tag objects) are + stored in `$GIT_DIR/refs/tags/`. A git tag has nothing to do with + a Lisp tag (which is called object type in git's context). + A tag is most typically used to mark a particular point in the + commit ancestry chain. + +unmerged index:: + An index which contains unmerged index entries. + +unreachable object:: + An object which is not reachable from a branch, tag, or any + other reference. + +working tree:: + The set of files and directories currently being worked on, + i.e. you can work in your working tree without using git at all. + diff --git a/Documentation/hooks.txt b/Documentation/hooks.txt new file mode 100644 index 0000000000..b083290d12 --- /dev/null +++ b/Documentation/hooks.txt @@ -0,0 +1,159 @@ +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` 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`. + +This document describes the currently defined hooks. + +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 +`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. + +pre-applypatch +-------------- + +This hook is invoked by `git-applypatch` script, which is +typically invoked by `git-applymbox`. It takes no parameter, +and is invoked after the patch is applied, but before a commit +is made. Exiting with non-zero status causes the working tree +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. + +post-applypatch +--------------- + +This hook is invoked by `git-applypatch` script, which is +typically invoked by `git-applymbox`. It takes no parameter, +and is invoked after the patch is applied and a commit is made. + +This hook is meant primarily for notification, and cannot affect +the outcome of `git-applypatch`. + +pre-commit +---------- + +This hook is invoked by `git-commit`, and can be bypassed +with `\--no-verify` option. It takes no parameter, and is +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 +of lines with trailing whitespaces and aborts the commit when +such a line is found. + +commit-msg +---------- + +This hook is invoked by `git-commit`, and can be bypassed +with `\--no-verify` option. 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-commit` to +abort. + +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 'commit-msg' hook, when enabled, detects duplicate +"Signed-off-by" lines, and aborts the commit if one is found. + +post-commit +----------- + +This hook is invoked by `git-commit`. It takes no +parameter, and is invoked after a commit is made. + +This hook is meant primarily for notification, and cannot affect +the outcome of `git-commit`. + +update +------ + +This hook is invoked by `git-receive-pack` on the remote 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. + +A zero exit from the update hook allows the ref to be updated. +Exiting with a non-zero status prevents `git-receive-pack` +from updating the ref. + +This hook can be used to prevent 'forced' update on certain refs by +making sure that the object name is a commit object that is a +descendant of the commit object named by the old object name. +That is, to enforce a "fast forward only" policy. + +It could also be used to log the old..new status. However, it +does not know the entire set of branches, so it would end up +firing one e-mail per ref when used naively, though. + +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 `stderr`, so if you +want to report something to the `git-send-pack` on the other end, +you can simply `echo` your messages. + +The default 'update' hook, when enabled, demonstrates how to +send out a notification e-mail. + +post-update +----------- + +This hook is invoked by `git-receive-pack` on the remote 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. + +It takes a variable number of parameters, each of which is the +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, +but it does not know what their original and updated values are, +so it is a poor place to do log old..new. + +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 +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`. diff --git a/Documentation/howto-index.sh b/Documentation/howto-index.sh new file mode 100755 index 0000000000..34aa30c5b9 --- /dev/null +++ b/Documentation/howto-index.sh @@ -0,0 +1,56 @@ +#!/bin/sh + +cat <<\EOF +GIT Howto Index +=============== + +Here is a collection of mailing list postings made by various +people describing how they use git in their workflow. + +EOF + +for txt +do + title=`expr "$txt" : '.*/\(.*\)\.txt$'` + from=`sed -ne ' + /^$/q + /^From:[ ]/{ + s/// + s/^[ ]*// + s/[ ]*$// + s/^/by / + p + } + ' "$txt"` + + abstract=`sed -ne ' + /^Abstract:[ ]/{ + s/^[^ ]*// + x + s/.*// + x + : again + /^[ ]/{ + s/^[ ]*// + H + n + b again + } + x + p + q + }' "$txt"` + + if grep 'Content-type: text/asciidoc' >/dev/null $txt + then + file=`expr "$txt" : '\(.*\)\.txt$'`.html + else + file="$txt" + fi + + echo "* link:$file[$title] $from +$abstract + +" + +done diff --git a/Documentation/howto/dangling-objects.txt b/Documentation/howto/dangling-objects.txt new file mode 100644 index 0000000000..e82ddae3cf --- /dev/null +++ b/Documentation/howto/dangling-objects.txt @@ -0,0 +1,109 @@ +From: Linus Torvalds <torvalds@linux-foundation.org> +Subject: Re: Question about fsck-objects output +Date: Thu, 25 Jan 2007 12:01:06 -0800 (PST) +Message-ID: <Pine.LNX.4.64.0701251144290.25027@woody.linux-foundation.org> +Archived-At: <http://permalink.gmane.org/gmane.comp.version-control.git/37754> +Abstract: Linus describes what dangling objects are, when they + are left behind, and how to view their relationship with branch + heads in gitk + +On Thu, 25 Jan 2007, Larry Streepy wrote: + +> Sorry to ask such a basic question, but I can't quite decipher the output of +> fsck-objects. When I run it, I get this: +> +> git fsck-objects +> dangling commit 2213f6d4dd39ca8baebd0427723723e63208521b +> dangling commit f0d4e00196bd5ee54463e9ea7a0f0e8303da767f +> dangling blob 6a6d0b01b3e96d49a8f2c7addd4ef8c3bd1f5761 +> +> +> Even after a "repack -a -d" they still exist. The man page has a short +> explanation, but, at least for me, it wasn't fully enlightening. :-) +> +> The man page says that dangling commits could be "root" commits, but since my +> repo started as a clone of another repo, I don't see how I could have any root +> commits. Also, the page doesn't really describe what a dangling blob is. +> +> So, can someone explain what these artifacts are and if they are a problem +> that I should be worried about? + +The most common situation is that you've rebased a branch (or you have +pulled from somebody else who rebased a branch, like the "pu" branch in +the git.git archive itself). + +What happens is that the old head of the original branch still exists, as +does obviously everything it pointed to. The branch pointer itself just +doesn't, since you replaced it with another one. + +However, there are certainly other situations too that cause dangling +objects. For example, the "dangling blob" situation you have tends to be +because you did a "git add" of a file, but then, before you actually +committed it and made it part of the bigger picture, you changed something +else in that file and committed that *updated* thing - the old state that +you added originally ends up not being pointed to by any commit/tree, so +it's now a dangling blob object. + +Similarly, when the "recursive" merge strategy runs, and finds that there +are criss-cross merges and thus more than one merge base (which is fairly +unusual, but it does happen), it will generate one temporary midway tree +(or possibly even more, if you had lots of criss-crossing merges and +more than two merge bases) as a temporary internal merge base, and again, +those are real objects, but the end result will not end up pointing to +them, so they end up "dangling" in your repository. + +Generally, dangling objects aren't anything to worry about. They can even +be very useful: if you screw something up, the dangling objects can be how +you recover your old tree (say, you did a rebase, and realized that you +really didn't want to - you can look at what dangling objects you have, +and decide to reset your head to some old dangling state). + +For commits, the most useful thing to do with dangling objects tends to be +to do a simple + + gitk <dangling-commit-sha-goes-here> --not --all + +which means exactly what it sounds like: it says that you want to see the +commit history that is described by the dangling commit(s), but you do NOT +want to see the history that is described by all your branches and tags +(which are the things you normally reach). That basically shows you in a +nice way what the danglign commit was (and notice that it might not be +just one commit: we only report the "tip of the line" as being dangling, +but there might be a whole deep and complex commit history that has gotten +dropped - rebasing will do that). + +For blobs and trees, you can't do the same, but you can examine them. You +can just do + + git show <dangling-blob/tree-sha-goes-here> + +to show what the contents of the blob were (or, for a tree, basically what +the "ls" for that directory was), and that may give you some idea of what +the operation was that left that dangling object. + +Usually, dangling blobs and trees aren't very interesting. They're almost +always the result of either being a half-way mergebase (the blob will +often even have the conflict markers from a merge in it, if you have had +conflicting merges that you fixed up by hand), or simply because you +interrupted a "git fetch" with ^C or something like that, leaving _some_ +of the new objects in the object database, but just dangling and useless. + +Anyway, once you are sure that you're not interested in any dangling +state, you can just prune all unreachable objects: + + git prune + +and they'll be gone. But you should only run "git prune" on a quiescent +repository - it's kind of like doing a filesystem fsck recovery: you don't +want to do that while the filesystem is mounted. + +(The same is true of "git-fsck-objects" itself, btw - but since +git-fsck-objects never actually *changes* the repository, it just reports +on what it found, git-fsck-objects itself is never "dangerous" to run. +Running it while somebody is actually changing the repository can cause +confusing and scary messages, but it won't actually do anything bad. In +contrast, running "git prune" while somebody is actively changing the +repository is a *BAD* idea). + + Linus + diff --git a/Documentation/howto/isolate-bugs-with-bisect.txt b/Documentation/howto/isolate-bugs-with-bisect.txt new file mode 100644 index 0000000000..926bbdc3cb --- /dev/null +++ b/Documentation/howto/isolate-bugs-with-bisect.txt @@ -0,0 +1,65 @@ +From: Linus Torvalds <torvalds () osdl ! org> +To: git@vger.kernel.org +Date: 2005-11-08 1:31:34 +Subject: Real-life kernel debugging scenario +Abstract: Short-n-sweet, Linus tells us how to leverage `git-bisect` to perform + bug isolation on a repository where "good" and "bad" revisions are known + in order to identify a suspect commit. + + +How To Use git-bisect To Isolate a Bogus Commit +=============================================== + +The way to use "git bisect" couldn't be easier. + +Figure out what the oldest bad state you know about is (that's usually the +head of "master", since that's what you just tried to boot and failed at). +Also, figure out the most recent known-good commit (usually the _previous_ +kernel you ran: and if you've only done a single "pull" in between, it +will be ORIG_HEAD). + +Then do + + git bisect start + git bisect bad master <- mark "master" as the bad state + git bisect good ORIG_HEAD <- mark ORIG_HEAD as good (or + whatever other known-good + thing you booted last) + +and at this point "git bisect" will churn for a while, and tell you what +the mid-point between those two commits are, and check that state out as +the head of the new "bisect" branch. + +Compile and reboot. + +If it's good, just do + + git bisect good <- mark current head as good + +otherwise, reboot into a good kernel instead, and do (surprise surprise, +git really is very intuitive): + + git bisect bad <- mark current head as bad + +and whatever you do, git will select a new half-way point. Do this for a +while, until git tells you exactly which commit was the first bad commit. +That's your culprit. + +It really works wonderfully well, except for the case where there was +_another_ commit that broke something in between, like introduced some +stupid compile error. In that case you should not mark that commit good or +bad: you should try to find another commit close-by, and do a "git reset +--hard <newcommit>" to try out _that_ commit instead, and then test that +instead (and mark it good or bad). + +You can do "git bisect visualize" while you do all this to see what's +going on by starting up gitk on the bisection range. + +Finally, once you've figured out exactly which commit was bad, you can +then go back to the master branch, and try reverting just that commit: + + git checkout master + git revert <bad-commit-id> + +to verify that the top-of-kernel works with that single commit reverted. + diff --git a/Documentation/howto/make-dist.txt b/Documentation/howto/make-dist.txt new file mode 100644 index 0000000000..00e330b293 --- /dev/null +++ b/Documentation/howto/make-dist.txt @@ -0,0 +1,52 @@ +Date: Fri, 12 Aug 2005 22:39:48 -0700 (PDT) +From: Linus Torvalds <torvalds@osdl.org> +To: Dave Jones <davej@redhat.com> +cc: git@vger.kernel.org +Subject: Re: Fwd: Re: git checkout -f branch doesn't remove extra files +Abstract: In this article, Linus talks about building a tarball, + incremental patch, and ChangeLog, given a base release and two + rc releases, following the convention of giving the patch from + the base release and the latest rc, with ChangeLog between the + last rc and the latest rc. + +On Sat, 13 Aug 2005, Dave Jones wrote: +> +> > Git actually has a _lot_ of nifty tools. I didn't realize that people +> > didn't know about such basic stuff as "git-tar-tree" and "git-ls-files". +> +> Maybe its because things are moving so fast :) Or maybe I just wasn't +> paying attention on that day. (I even read the git changes via RSS, +> so I should have no excuse). + +Well, git-tar-tree has been there since late April - it's actually one of +those really early commands. I'm pretty sure the RSS feed came later ;) + +I use it all the time in doing releases, it's a lot faster than creating a +tar tree by reading the filesystem (even if you don't have to check things +out). A hidden pearl. + +This is my crappy "release-script": + + [torvalds@g5 ~]$ cat bin/release-script + #!/bin/sh + stable="$1" + last="$2" + new="$3" + echo "# git-tag v$new" + echo "git-tar-tree v$new linux-$new | gzip -9 > ../linux-$new.tar.gz" + echo "git-diff-tree -p v$stable v$new | gzip -9 > ../patch-$new.gz" + echo "git-rev-list --pretty v$new ^v$last > ../ChangeLog-$new" + echo "git-rev-list --pretty=short v$new ^v$last | git-shortlog > ../ShortLog" + echo "git-diff-tree -p v$last v$new | git-apply --stat > ../diffstat-$new" + +and when I want to do a new kernel release I literally first tag it, and +then do + + release-script 2.6.12 2.6.13-rc6 2.6.13-rc7 + +and check that things look sane, and then just cut-and-paste the commands. + +Yeah, it's stupid. + + Linus + diff --git a/Documentation/howto/rebase-and-edit.txt b/Documentation/howto/rebase-and-edit.txt new file mode 100644 index 0000000000..646c55cc69 --- /dev/null +++ b/Documentation/howto/rebase-and-edit.txt @@ -0,0 +1,81 @@ +Date: Sat, 13 Aug 2005 22:16:02 -0700 (PDT) +From: Linus Torvalds <torvalds@osdl.org> +To: Steve French <smfrench@austin.rr.com> +cc: git@vger.kernel.org +Subject: Re: sending changesets from the middle of a git tree +Abstract: In this article, Linus demonstrates how a broken commit + in a sequence of commits can be removed by rewinding the head and + reapplying selected changes. + +On Sat, 13 Aug 2005, Linus Torvalds wrote: + +> That's correct. Same things apply: you can move a patch over, and create a +> new one with a modified comment, but basically the _old_ commit will be +> immutable. + +Let me clarify. + +You can entirely _drop_ old branches, so commits may be immutable, but +nothing forces you to keep them. Of course, when you drop a commit, you'll +always end up dropping all the commits that depended on it, and if you +actually got somebody else to pull that commit you can't drop it from +_their_ repository, but undoing things is not impossible. + +For example, let's say that you've made a mess of things: you've committed +three commits "old->a->b->c", and you notice that "a" was broken, but you +want to save "b" and "c". What you can do is + + # Create a branch "broken" that is the current code + # for reference + git branch broken + + # Reset the main branch to three parents back: this + # effectively undoes the three top commits + git reset HEAD^^^ + git checkout -f + + # Check the result visually to make sure you know what's + # going on + gitk --all + + # Re-apply the two top ones from "broken" + # + # First "parent of broken" (aka b): + git-diff-tree -p broken^ | git-apply --index + git commit --reedit=broken^ + + # Then "top of broken" (aka c): + git-diff-tree -p broken | git-apply --index + git commit --reedit=broken + +and you've now re-applied (and possibly edited the comments) the two +commits b/c, and commit "a" is basically gone (it still exists in the +"broken" branch, of course). + +Finally, check out the end result again: + + # Look at the new commit history + gitk --all + +to see that everything looks sensible. + +And then, you can just remove the broken branch if you decide you really +don't want it: + + # remove 'broken' branch + git branch -d broken + + # Prune old objects if you're really really sure + git prune + +And yeah, I'm sure there are other ways of doing this. And as usual, the +above is totally untested, and I just wrote it down in this email, so if +I've done something wrong, you'll have to figure it out on your own ;) + + Linus +- +To unsubscribe from this list: send the line "unsubscribe git" in +the body of a message to majordomo@vger.kernel.org +More majordomo info at http://vger.kernel.org/majordomo-info.html + + diff --git a/Documentation/howto/rebase-from-internal-branch.txt b/Documentation/howto/rebase-from-internal-branch.txt new file mode 100644 index 0000000000..3b3a5c2e69 --- /dev/null +++ b/Documentation/howto/rebase-from-internal-branch.txt @@ -0,0 +1,165 @@ +From: Junio C Hamano <junkio@cox.net> +To: git@vger.kernel.org +Cc: Petr Baudis <pasky@suse.cz>, Linus Torvalds <torvalds@osdl.org> +Subject: Re: sending changesets from the middle of a git tree +Date: Sun, 14 Aug 2005 18:37:39 -0700 +Abstract: In this article, JC talks about how he rebases the + public "pu" branch using the core GIT tools when he updates + the "master" branch, and how "rebase" works. Also discussed + is how this applies to individual developers who sends patches + upstream. + +Petr Baudis <pasky@suse.cz> writes: + +> Dear diary, on Sun, Aug 14, 2005 at 09:57:13AM CEST, I got a letter +> where Junio C Hamano <junkio@cox.net> told me that... +>> Linus Torvalds <torvalds@osdl.org> writes: +>> +>> > Junio, maybe you want to talk about how you move patches from your "pu" +>> > branch to the real branches. +>> +> Actually, wouldn't this be also precisely for what StGIT is intended to? + +Exactly my feeling. I was sort of waiting for Catalin to speak +up. With its basing philosophical ancestry on quilt, this is +the kind of task StGIT is designed to do. + +I just have done a simpler one, this time using only the core +GIT tools. + +I had a handful commits that were ahead of master in pu, and I +wanted to add some documentation bypassing my usual habit of +placing new things in pu first. At the beginning, the commit +ancestry graph looked like this: + + *"pu" head + master --> #1 --> #2 --> #3 + +So I started from master, made a bunch of edits, and committed: + + $ git checkout master + $ cd Documentation; ed git.txt ... + $ cd ..; git add Documentation/*.txt + $ git commit -s + +After the commit, the ancestry graph would look like this: + + *"pu" head + master^ --> #1 --> #2 --> #3 + \ + \---> master + +The old master is now master^ (the first parent of the master). +The new master commit holds my documentation updates. + +Now I have to deal with "pu" branch. + +This is the kind of situation I used to have all the time when +Linus was the maintainer and I was a contributor, when you look +at "master" branch being the "maintainer" branch, and "pu" +branch being the "contributor" branch. Your work started at the +tip of the "maintainer" branch some time ago, you made a lot of +progress in the meantime, and now the maintainer branch has some +other commits you do not have yet. And "git rebase" was written +with the explicit purpose of helping to maintain branches like +"pu". You _could_ merge master to pu and keep going, but if you +eventually want to cherrypick and merge some but not necessarily +all changes back to the master branch, it often makes later +operations for _you_ easier if you rebase (i.e. carry forward +your changes) "pu" rather than merge. So I ran "git rebase": + + $ git checkout pu + $ git rebase master pu + +What this does is to pick all the commits since the current +branch (note that I now am on "pu" branch) forked from the +master branch, and forward port these changes. + + master^ --> #1 --> #2 --> #3 + \ *"pu" head + \---> master --> #1' --> #2' --> #3' + +The diff between master^ and #1 is applied to master and +committed to create #1' commit with the commit information (log, +author and date) taken from commit #1. On top of that #2' and #3' +commits are made similarly out of #2 and #3 commits. + +Old #3 is not recorded in any of the .git/refs/heads/ file +anymore, so after doing this you will have dangling commit if +you ran fsck-cache, which is normal. After testing "pu", you +can run "git prune" to get rid of those original three commits. + +While I am talking about "git rebase", I should talk about how +to do cherrypicking using only the core GIT tools. + +Let's go back to the earlier picture, with different labels. + +You, as an individual developer, cloned upstream repository and +made a couple of commits on top of it. + + *your "master" head + upstream --> #1 --> #2 --> #3 + +You would want changes #2 and #3 incorporated in the upstream, +while you feel that #1 may need further improvements. So you +prepare #2 and #3 for e-mail submission. + + $ git format-patch master^^ master + +This creates two files, 0001-XXXX.patch and 0002-XXXX.patch. Send +them out "To: " your project maintainer and "Cc: " your mailing +list. You could use contributed script git-send-email if +your host has necessary perl modules for this, but your usual +MUA would do as long as it does not corrupt whitespaces in the +patch. + +Then you would wait, and you find out that the upstream picked +up your changes, along with other changes. + + where *your "master" head + upstream --> #1 --> #2 --> #3 + used \ + to be \--> #A --> #2' --> #3' --> #B --> #C + *upstream head + +The two commits #2' and #3' in the above picture record the same +changes your e-mail submission for #2 and #3 contained, but +probably with the new sign-off line added by the upstream +maintainer and definitely with different committer and ancestry +information, they are different objects from #2 and #3 commits. + +You fetch from upstream, but not merge. + + $ git fetch upstream + +This leaves the updated upstream head in .git/FETCH_HEAD but +does not touch your .git/HEAD nor .git/refs/heads/master. +You run "git rebase" now. + + $ git rebase FETCH_HEAD master + +Earlier, I said that rebase applies all the commits from your +branch on top of the upstream head. Well, I lied. "git rebase" +is a bit smarter than that and notices that #2 and #3 need not +be applied, so it only applies #1. The commit ancestry graph +becomes something like this: + + where *your old "master" head + upstream --> #1 --> #2 --> #3 + used \ your new "master" head* + to be \--> #A --> #2' --> #3' --> #B --> #C --> #1' + *upstream + head + +Again, "git prune" would discard the disused commits #1-#3 and +you continue on starting from the new "master" head, which is +the #1' commit. + +-jc + +- +To unsubscribe from this list: send the line "unsubscribe git" in +the body of a message to majordomo@vger.kernel.org +More majordomo info at http://vger.kernel.org/majordomo-info.html + + diff --git a/Documentation/howto/rebuild-from-update-hook.txt b/Documentation/howto/rebuild-from-update-hook.txt new file mode 100644 index 0000000000..02621b54a0 --- /dev/null +++ b/Documentation/howto/rebuild-from-update-hook.txt @@ -0,0 +1,87 @@ +Subject: [HOWTO] Using post-update hook +Message-ID: <7vy86o6usx.fsf@assigned-by-dhcp.cox.net> +From: Junio C Hamano <junkio@cox.net> +Date: Fri, 26 Aug 2005 18:19:10 -0700 +Abstract: In this how-to article, JC talks about how he + uses the post-update hook to automate git documentation page + shown at http://www.kernel.org/pub/software/scm/git/docs/. + +The pages under http://www.kernel.org/pub/software/scm/git/docs/ +are built from Documentation/ directory of the git.git project +and needed to be kept up-to-date. The www.kernel.org/ servers +are mirrored and I was told that the origin of the mirror is on +the machine $some.kernel.org, on which I was given an account +when I took over git maintainership from Linus. + +The directories relevant to this how-to are these two: + + /pub/scm/git/git.git/ The public git repository. + /pub/software/scm/git/docs/ The HTML documentation page. + +So I made a repository to generate the documentation under my +home directory over there. + + $ cd + $ mkdir doc-git && cd doc-git + $ git clone /pub/scm/git/git.git/ docgen + +What needs to happen is to update the $HOME/doc-git/docgen/ +working tree, build HTML docs there and install the result in +/pub/software/scm/git/docs/ directory. So I wrote a little +script: + + $ cat >dododoc.sh <<\EOF + #!/bin/sh + cd $HOME/doc-git/docgen || exit + + unset GIT_DIR + + git pull /pub/scm/git/git.git/ master && + cd Documentation && + make install-webdoc + EOF + +Initially I used to run this by hand whenever I push into the +public git repository. Then I did a cron job that ran twice a +day. The current round uses the post-update hook mechanism, +like this: + + $ cat >/pub/scm/git/git.git/hooks/post-update <<\EOF + #!/bin/sh + # + # An example hook script to prepare a packed repository for use over + # dumb transports. + # + # To enable this hook, make this file executable by "chmod +x post-update". + + case " $* " in + *' refs/heads/master '*) + echo $HOME/doc-git/dododoc.sh | at now + ;; + esac + exec git-update-server-info + EOF + $ chmod +x /pub/scm/git/git.git/hooks/post-update + +There are four things worth mentioning: + + - The update-hook is run after the repository accepts a "git + push", under my user privilege. It is given the full names + of refs that have been updated as arguments. My post-update + runs the dododoc.sh script only when the master head is + updated. + + - When update-hook is run, GIT_DIR is set to '.' by the calling + receive-pack. This is inherited by the dododoc.sh run via + the "at" command, and needs to be unset; otherwise, "git + pull" it does into $HOME/doc-git/docgen/ repository would not + work correctly. + + - The stdout of update hook script is not connected to git + push; I run the heavy part of the command inside "at", to + receive the execution report via e-mail. + + - This is still crude and does not protect against simultaneous + make invocations stomping on each other. I would need to add + some locking mechanism for this. + diff --git a/Documentation/howto/revert-branch-rebase.txt b/Documentation/howto/revert-branch-rebase.txt new file mode 100644 index 0000000000..d88ec23a97 --- /dev/null +++ b/Documentation/howto/revert-branch-rebase.txt @@ -0,0 +1,193 @@ +From: Junio C Hamano <junkio@cox.net> +To: git@vger.kernel.org +Subject: [HOWTO] Reverting an existing commit +Abstract: In this article, JC gives a small real-life example of using + 'git revert' command, and using a temporary branch and tag for safety + and easier sanity checking. +Date: Mon, 29 Aug 2005 21:39:02 -0700 +Content-type: text/asciidoc +Message-ID: <7voe7g3uop.fsf@assigned-by-dhcp.cox.net> + +Reverting an existing commit +============================ + +One of the changes I pulled into the 'master' branch turns out to +break building GIT with GCC 2.95. While they were well intentioned +portability fixes, keeping things working with gcc-2.95 was also +important. Here is what I did to revert the change in the 'master' +branch and to adjust the 'pu' branch, using core GIT tools and +barebone Porcelain. + +First, prepare a throw-away branch in case I screw things up. + +------------------------------------------------ +$ git checkout -b revert-c99 master +------------------------------------------------ + +Now I am on the 'revert-c99' branch. Let's figure out which commit to +revert. I happen to know that the top of the 'master' branch is a +merge, and its second parent (i.e. foreign commit I merged from) has +the change I would want to undo. Further I happen to know that that +merge introduced 5 commits or so: + +------------------------------------------------ +$ git show-branch --more=4 master master^2 | head +* [master] Merge refs/heads/portable from http://www.cs.berkeley.... + ! [master^2] Replace C99 array initializers with code. +-- +- [master] Merge refs/heads/portable from http://www.cs.berkeley.... +*+ [master^2] Replace C99 array initializers with code. +*+ [master^2~1] Replace unsetenv() and setenv() with older putenv(). +*+ [master^2~2] Include sys/time.h in daemon.c. +*+ [master^2~3] Fix ?: statements. +*+ [master^2~4] Replace zero-length array decls with []. +* [master~1] tutorial note about git branch +------------------------------------------------ + +The '--more=4' above means "after we reach the merge base of refs, +show until we display four more common commits". That last commit +would have been where the "portable" branch was forked from the main +git.git repository, so this would show everything on both branches +since then. I just limited the output to the first handful using +'head'. + +Now I know 'master^2~4' (pronounce it as "find the second parent of +the 'master', and then go four generations back following the first +parent") is the one I would want to revert. Since I also want to say +why I am reverting it, the '-n' flag is given to 'git revert'. This +prevents it from actually making a commit, and instead 'git revert' +leaves the commit log message it wanted to use in '.msg' file: + +------------------------------------------------ +$ git revert -n master^2~4 +$ cat .msg +Revert "Replace zero-length array decls with []." + +This reverts 6c5f9baa3bc0d63e141e0afc23110205379905a4 commit. +$ git diff HEAD ;# to make sure what we are reverting makes sense. +$ make CC=gcc-2.95 clean test ;# make sure it fixed the breakage. +$ make clean test ;# make sure it did not cause other breakage. +------------------------------------------------ + +The reverted change makes sense (from reading the 'diff' output), does +fix the problem (from 'make CC=gcc-2.95' test), and does not cause new +breakage (from the last 'make test'). I'm ready to commit: + +------------------------------------------------ +$ git commit -a -s ;# read .msg into the log, + # and explain why I am reverting. +------------------------------------------------ + +I could have screwed up in any of the above steps, but in the worst +case I could just have done 'git checkout master' to start over. +Fortunately I did not have to; what I have in the current branch +'revert-c99' is what I want. So merge that back into 'master': + +------------------------------------------------ +$ git checkout master +$ git merge revert-c99 ;# this should be a fast forward +Updating from 10d781b9caa4f71495c7b34963bef137216f86a8 to e3a693c... + cache.h | 8 ++++---- + commit.c | 2 +- + ls-files.c | 2 +- + receive-pack.c | 2 +- + server-info.c | 2 +- + 5 files changed, 8 insertions(+), 8 deletions(-) +------------------------------------------------ + +There is no need to redo the test at this point. We fast forwarded +and we know 'master' matches 'revert-c99' exactly. In fact: + +------------------------------------------------ +$ git diff master..revert-c99 +------------------------------------------------ + +says nothing. + +Then we rebase the 'pu' branch as usual. + +------------------------------------------------ +$ git checkout pu +$ git tag pu-anchor pu +$ git rebase master +* Applying: Redo "revert" using three-way merge machinery. +First trying simple merge strategy to cherry-pick. +Finished one cherry-pick. +* Applying: Remove git-apply-patch-script. +First trying simple merge strategy to cherry-pick. +Simple cherry-pick fails; trying Automatic cherry-pick. +Removing Documentation/git-apply-patch-script.txt +Removing git-apply-patch-script +Finished one cherry-pick. +* Applying: Document "git cherry-pick" and "git revert" +First trying simple merge strategy to cherry-pick. +Finished one cherry-pick. +* Applying: mailinfo and applymbox updates +First trying simple merge strategy to cherry-pick. +Finished one cherry-pick. +* Applying: Show commits in topo order and name all commits. +First trying simple merge strategy to cherry-pick. +Finished one cherry-pick. +* Applying: More documentation updates. +First trying simple merge strategy to cherry-pick. +Finished one cherry-pick. +------------------------------------------------ + +The temporary tag 'pu-anchor' is me just being careful, in case 'git +rebase' screws up. After this, I can do these for sanity check: + +------------------------------------------------ +$ git diff pu-anchor..pu ;# make sure we got the master fix. +$ make CC=gcc-2.95 clean test ;# make sure it fixed the breakage. +$ make clean test ;# make sure it did not cause other breakage. +------------------------------------------------ + +Everything is in the good order. I do not need the temporary branch +nor tag anymore, so remove them: + +------------------------------------------------ +$ rm -f .git/refs/tags/pu-anchor +$ git branch -d revert-c99 +------------------------------------------------ + +It was an emergency fix, so we might as well merge it into the +'release candidate' branch, although I expect the next release would +be some days off: + +------------------------------------------------ +$ git checkout rc +$ git pull . master +Packing 0 objects +Unpacking 0 objects + +* committish: e3a693c... refs/heads/master from . +Trying to merge e3a693c... into 8c1f5f0... using 10d781b... +Committed merge 7fb9b7262a1d1e0a47bbfdcbbcf50ce0635d3f8f + cache.h | 8 ++++---- + commit.c | 2 +- + ls-files.c | 2 +- + receive-pack.c | 2 +- + server-info.c | 2 +- + 5 files changed, 8 insertions(+), 8 deletions(-) +------------------------------------------------ + +And the final repository status looks like this: + +------------------------------------------------ +$ git show-branch --more=1 master pu rc +! [master] Revert "Replace zero-length array decls with []." + ! [pu] git-repack: Add option to repack all objects. + * [rc] Merge refs/heads/master from . +--- + + [pu] git-repack: Add option to repack all objects. + + [pu~1] More documentation updates. + + [pu~2] Show commits in topo order and name all commits. + + [pu~3] mailinfo and applymbox updates + + [pu~4] Document "git cherry-pick" and "git revert" + + [pu~5] Remove git-apply-patch-script. + + [pu~6] Redo "revert" using three-way merge machinery. + - [rc] Merge refs/heads/master from . +++* [master] Revert "Replace zero-length array decls with []." + - [rc~1] Merge refs/heads/master from . +... [master~1] Merge refs/heads/portable from http://www.cs.berkeley.... +------------------------------------------------ diff --git a/Documentation/howto/separating-topic-branches.txt b/Documentation/howto/separating-topic-branches.txt new file mode 100644 index 0000000000..090e2c9b01 --- /dev/null +++ b/Documentation/howto/separating-topic-branches.txt @@ -0,0 +1,91 @@ +From: Junio C Hamano <junkio@cox.net> +Subject: Separating topic branches +Abstract: In this article, JC describes how to separate topic branches. + +This text was originally a footnote to a discussion about the +behaviour of the git diff commands. + +Often I find myself doing that [running diff against something other +than HEAD] while rewriting messy development history. For example, I +start doing some work without knowing exactly where it leads, and end +up with a history like this: + + "master" + o---o + \ "topic" + o---o---o---o---o---o + +At this point, "topic" contains something I know I want, but it +contains two concepts that turned out to be completely independent. +And often, one topic component is larger than the other. It may +contain more than two topics. + +In order to rewrite this mess to be more manageable, I would first do +"diff master..topic", to extract the changes into a single patch, start +picking pieces from it to get logically self-contained units, and +start building on top of "master": + + $ git diff master..topic >P.diff + $ git checkout -b topicA master + ... pick and apply pieces from P.diff to build + ... commits on topicA branch. + + o---o---o + / "topicA" + o---o"master" + \ "topic" + o---o---o---o---o---o + +Before doing each commit on "topicA" HEAD, I run "diff HEAD" +before update-index the affected paths, or "diff --cached HEAD" +after. Also I would run "diff --cached master" to make sure +that the changes are only the ones related to "topicA". Usually +I do this for smaller topics first. + +After that, I'd do the remainder of the original "topic", but +for that, I do not start from the patchfile I extracted by +comparing "master" and "topic" I used initially. Still on +"topicA", I extract "diff topic", and use it to rebuild the +other topic: + + $ git diff -R topic >P.diff ;# --cached also would work fine + $ git checkout -b topicB master + ... pick and apply pieces from P.diff to build + ... commits on topicB branch. + + "topicB" + o---o---o---o---o + / + /o---o---o + |/ "topicA" + o---o"master" + \ "topic" + o---o---o---o---o---o + +After I am done, I'd try a pretend-merge between "topicA" and +"topicB" in order to make sure I have not missed anything: + + $ git pull . topicA ;# merge it into current "topicB" + $ git diff topic + "topicB" + o---o---o---o---o---* (pretend merge) + / / + /o---o---o----------' + |/ "topicA" + o---o"master" + \ "topic" + o---o---o---o---o---o + +The last diff better not to show anything other than cleanups +for crufts. Then I can finally clean things up: + + $ git branch -D topic + $ git reset --hard HEAD^ ;# nuke pretend merge + + "topicB" + o---o---o---o---o + / + /o---o---o + |/ "topicA" + o---o"master" + diff --git a/Documentation/howto/setup-git-server-over-http.txt b/Documentation/howto/setup-git-server-over-http.txt new file mode 100644 index 0000000000..8eadc20494 --- /dev/null +++ b/Documentation/howto/setup-git-server-over-http.txt @@ -0,0 +1,256 @@ +From: Rutger Nijlunsing <rutger@nospam.com> +Subject: Setting up a git repository which can be pushed into and pulled from over HTTP. +Date: Thu, 10 Aug 2006 22:00:26 +0200 + +Since Apache is one of those packages people like to compile +themselves while others prefer the bureaucrat's dream Debian, it is +impossible to give guidelines which will work for everyone. Just send +some feedback to the mailing list at git@vger.kernel.org to get this +document tailored to your favorite distro. + + +What's needed: + +- Have an Apache web-server + + On Debian: + $ apt-get install apache2 + To get apache2 by default started, + edit /etc/default/apache2 and set NO_START=0 + +- can edit the configuration of it. + + This could be found under /etc/httpd, or refer to your Apache documentation. + + On Debian: this means being able to edit files under /etc/apache2 + +- can restart it. + + 'apachectl --graceful' might do. If it doesn't, just stop and + restart apache. Be warning that active connections to your server + might be aborted by this. + + On Debian: + $ /etc/init.d/apache2 restart + or + $ /etc/init.d/apache2 force-reload + (which seems to do the same) + This adds symlinks from the /etc/apache2/mods-enabled to + /etc/apache2/mods-available. + +- have permissions to chown a directory + +- have git installed at the server _and_ client + +In effect, this probably means you're going to be root. + + +Step 1: setup a bare GIT repository +----------------------------------- + +At the time of writing, git-http-push cannot remotely create a GIT +repository. So we have to do that at the server side with git. Another +option would be to generate an empty repository at the client and copy +it to the server with WebDAV. But then you're probably the first to +try that out :) + +Create the directory under the DocumentRoot of the directories served +by Apache. As an example we take /usr/local/apache2, but try "grep +DocumentRoot /where/ever/httpd.conf" to find your root: + + $ cd /usr/local/apache/htdocs + $ mkdir my-new-repo.git + + On Debian: + + $ cd /var/www + $ mkdir my-new-repo.git + + +Initialize a bare repository + + $ cd my-new-repo.git + $ git --bare init + + +Change the ownership to your web-server's credentials. Use "grep ^User +httpd.conf" and "grep ^Group httpd.conf" to find out: + + $ chown -R www.www . + + On Debian: + + $ chown -R www-data.www-data . + + +If you do not know which user Apache runs as, you can alternatively do +a "chmod -R a+w .", inspect the files which are created later on, and +set the permissions appropriately. + +Restart apache2, and check whether http://server/my-new-repo.git gives +a directory listing. If not, check whether apache started up +successfully. + + +Step 2: enable DAV on this repository +------------------------------------- + +First make sure the dav_module is loaded. For this, insert in httpd.conf: + + LoadModule dav_module libexec/httpd/libdav.so + AddModule mod_dav.c + +Also make sure that this line exists which is the file used for +locking DAV operations: + + DAVLockDB "/usr/local/apache2/temp/DAV.lock" + + On Debian these steps can be performed with: + + Enable the dav and dav_fs modules of apache: + $ a2enmod dav_fs + (just to be sure. dav_fs might be unneeded, I don't know) + $ a2enmod dav + The DAV lock is located in /etc/apache2/mods-available/dav_fs.conf: + DAVLockDB /var/lock/apache2/DAVLock + +Of course, it can point somewhere else, but the string is actually just a +prefix in some Apache configurations, and therefore the _directory_ has to +be writable by the user Apache runs as. + +Then, add something like this to your httpd.conf + + <Location /my-new-repo.git> + DAV on + AuthType Basic + AuthName "Git" + AuthUserFile /usr/local/apache2/conf/passwd.git + Require valid-user + </Location> + + On Debian: + Create (or add to) /etc/apache2/conf.d/git.conf : + + <Location /my-new-repo.git> + DAV on + AuthType Basic + AuthName "Git" + AuthUserFile /etc/apache2/passwd.git + Require valid-user + </Location> + + Debian automatically reads all files under /etc/apach2/conf.d. + +The password file can be somewhere else, but it has to be readable by +Apache and preferably not readable by the world. + +Create this file by + $ htpasswd -c /usr/local/apache2/conf/passwd.git <user> + + On Debian: + $ htpasswd -c /etc/apache2/passwd.git <user> + +You will be asked a password, and the file is created. Subsequent calls +to htpasswd should omit the '-c' option, since you want to append to the +existing file. + +You need to restart Apache. + +Now go to http://<username>@<servername>/my-new-repo.git in your +browser to check whether it asks for a password and accepts the right +password. + +On Debian: + + To test the WebDAV part, do: + + $ apt-get install litmus + $ litmus http://<servername>/my-new-repo.git <username> <password> + + Most tests should pass. + +A command line tool to test WebDAV is cadaver. + +If you're into Windows, from XP onwards Internet Explorer supports +WebDAV. For this, do Internet Explorer -> Open Location -> +http://<servername>/my-new-repo.git [x] Open as webfolder -> login . + + +Step 3: setup the client +------------------------ + +Make sure that you have HTTP support, i.e. your git was built with curl. +The easiest way to check is to look for the executable 'git-http-push'. + +Then, add the following to your $HOME/.netrc (you can do without, but will be +asked to input your password a _lot_ of times): + + machine <servername> + login <username> + password <password> + +...and set permissions: + chmod 600 ~/.netrc + +If you want to access the web-server by its IP, you have to type that in, +instead of the server name. + +To check whether all is OK, do: + + curl --netrc --location -v http://<username>@<servername>/my-new-repo.git/ + +...this should give a directory listing in HTML of /var/www/my-new-repo.git . + + +Now, add the remote in your existing repository which contains the project +you want to export: + + $ git-config remote.upload.url \ + http://<username>@<servername>/my-new-repo.git/ + +It is important to put the last '/'; Without it, the server will send +a redirect which git-http-push does not (yet) understand, and git-http-push +will repeat the request infinitely. + + +Step 4: make the initial push +----------------------------- + +From your client repository, do + + $ git push upload master + +This pushes branch 'master' (which is assumed to be the branch you +want to export) to repository called 'upload', which we previously +defined with git-config. + + +Troubleshooting: +---------------- + +If git-http-push says + + Error: no DAV locking support on remote repo http://... + +then it means the web-server did not accept your authentication. Make sure +that the user name and password matches in httpd.conf, .netrc and the URL +you are uploading to. + +If git-http-push shows you an error (22/502) when trying to MOVE a blob, +it means that your web-server somehow does not recognize its name in the +request; This can happen when you start Apache, but then disable the +network interface. A simple restart of Apache helps. + +Errors like (22/502) are of format (curl error code/http error +code). So (22/404) means something like 'not found' at the server. + +Reading /usr/local/apache2/logs/error_log is often helpful. + + On Debian: Read /var/log/apache2/error.log instead. + + +Debian References: http://www.debian-administration.org/articles/285 + +Authors + Johannes Schindelin <Johannes.Schindelin@gmx.de> + Rutger Nijlunsing <git@wingding.demon.nl> diff --git a/Documentation/howto/update-hook-example.txt b/Documentation/howto/update-hook-example.txt new file mode 100644 index 0000000000..3a33696f00 --- /dev/null +++ b/Documentation/howto/update-hook-example.txt @@ -0,0 +1,172 @@ +From: Junio C Hamano <junkio@cox.net> and Carl Baldwin <cnb@fc.hp.com> +Subject: control access to branches. +Date: Thu, 17 Nov 2005 23:55:32 -0800 +Message-ID: <7vfypumlu3.fsf@assigned-by-dhcp.cox.net> +Abstract: An example hooks/update script is presented to + implement repository maintenance policies, such as who can push + into which branch and who can make a tag. + +When your developer runs git-push into the repository, +git-receive-pack is run (either locally or over ssh) as that +developer, so is hooks/update script. Quoting from the relevant +section of the documentation: + + Before each ref is updated, if $GIT_DIR/hooks/update file exists + and executable, it is called with three parameters: + + $GIT_DIR/hooks/update refname sha1-old sha1-new + + The refname parameter is relative to $GIT_DIR; e.g. for the + master head this is "refs/heads/master". Two sha1 are the + object names for the refname before and after the update. Note + that the hook is called before the refname is updated, so either + sha1-old is 0{40} (meaning there is no such ref yet), or it + should match what is recorded in refname. + +So if your policy is (1) always require fast-forward push +(i.e. never allow "git-push repo +branch:branch"), (2) you +have a list of users allowed to update each branch, and (3) you +do not let tags to be overwritten, then you can use something +like this as your hooks/update script. + +[jc: editorial note. This is a much improved version by Carl +since I posted the original outline] + +-- >8 -- beginning of script -- >8 -- + +#!/bin/bash + +umask 002 + +# If you are having trouble with this access control hook script +# you can try setting this to true. It will tell you exactly +# why a user is being allowed/denied access. + +verbose=false + +# Default shell globbing messes things up downstream +GLOBIGNORE=* + +function grant { + $verbose && echo >&2 "-Grant- $1" + echo grant + exit 0 +} + +function deny { + $verbose && echo >&2 "-Deny- $1" + echo deny + exit 1 +} + +function info { + $verbose && echo >&2 "-Info- $1" +} + +# Implement generic branch and tag policies. +# - Tags should not be updated once created. +# - Branches should only be fast-forwarded. +case "$1" in + refs/tags/*) + [ -f "$GIT_DIR/$1" ] && + deny >/dev/null "You can't overwrite an existing tag" + ;; + refs/heads/*) + # No rebasing or rewinding + if expr "$2" : '0*$' >/dev/null; then + info "The branch '$1' is new..." + else + # updating -- make sure it is a fast forward + mb=$(git-merge-base "$2" "$3") + case "$mb,$2" in + "$2,$mb") info "Update is fast-forward" ;; + *) deny >/dev/null "This is not a fast-forward update." ;; + esac + fi + ;; + *) + deny >/dev/null \ + "Branch is not under refs/heads or refs/tags. What are you trying to do?" + ;; +esac + +# Implement per-branch controls based on username +allowed_users_file=$GIT_DIR/info/allowed-users +username=$(id -u -n) +info "The user is: '$username'" + +if [ -f "$allowed_users_file" ]; then + rc=$(cat $allowed_users_file | grep -v '^#' | grep -v '^$' | + while read head_pattern user_patterns; do + matchlen=$(expr "$1" : "$head_pattern") + if [ "$matchlen" == "${#1}" ]; then + info "Found matching head pattern: '$head_pattern'" + for user_pattern in $user_patterns; do + info "Checking user: '$username' against pattern: '$user_pattern'" + matchlen=$(expr "$username" : "$user_pattern") + if [ "$matchlen" == "${#username}" ]; then + grant "Allowing user: '$username' with pattern: '$user_pattern'" + fi + done + deny "The user is not in the access list for this branch" + fi + done + ) + case "$rc" in + grant) grant >/dev/null "Granting access based on $allowed_users_file" ;; + deny) deny >/dev/null "Denying access based on $allowed_users_file" ;; + *) ;; + esac +fi + +allowed_groups_file=$GIT_DIR/info/allowed-groups +groups=$(id -G -n) +info "The user belongs to the following groups:" +info "'$groups'" + +if [ -f "$allowed_groups_file" ]; then + rc=$(cat $allowed_groups_file | grep -v '^#' | grep -v '^$' | + while read head_pattern group_patterns; do + matchlen=$(expr "$1" : "$head_pattern") + if [ "$matchlen" == "${#1}" ]; then + info "Found matching head pattern: '$head_pattern'" + for group_pattern in $group_patterns; do + for groupname in $groups; do + info "Checking group: '$groupname' against pattern: '$group_pattern'" + matchlen=$(expr "$groupname" : "$group_pattern") + if [ "$matchlen" == "${#groupname}" ]; then + grant "Allowing group: '$groupname' with pattern: '$group_pattern'" + fi + done + done + deny "None of the user's groups are in the access list for this branch" + fi + done + ) + case "$rc" in + grant) grant >/dev/null "Granting access based on $allowed_groups_file" ;; + deny) deny >/dev/null "Denying access based on $allowed_groups_file" ;; + *) ;; + esac +fi + +deny >/dev/null "There are no more rules to check. Denying access" + +-- >8 -- end of script -- >8 -- + +This uses two files, $GIT_DIR/info/allowed-users and +allowed-groups, to describe which heads can be pushed into by +whom. The format of each file would look like this: + + refs/heads/master junio + refs/heads/cogito$ pasky + refs/heads/bw/ linus + refs/heads/tmp/ * + refs/tags/v[0-9]* junio + +With this, Linus can push or create "bw/penguin" or "bw/zebra" +or "bw/panda" branches, Pasky can do only "cogito", and JC can +do master branch and make versioned tags. And anybody can do +tmp/blah branches. + +------------ diff --git a/Documentation/howto/using-topic-branches.txt b/Documentation/howto/using-topic-branches.txt new file mode 100644 index 0000000000..2c98194cb8 --- /dev/null +++ b/Documentation/howto/using-topic-branches.txt @@ -0,0 +1,296 @@ +Date: Mon, 15 Aug 2005 12:17:41 -0700 +From: tony.luck@intel.com +Subject: Some tutorial text (was git/cogito workshop/bof at linuxconf au?) +Abstract: In this article, Tony Luck discusses how he uses GIT + as a Linux subsystem maintainer. + +Here's something that I've been putting together on how I'm using +GIT as a Linux subsystem maintainer. + +-Tony + +Last updated w.r.t. GIT 1.1 + +Linux subsystem maintenance using GIT +------------------------------------- + +My requirements here are to be able to create two public trees: + +1) A "test" tree into which patches are initially placed so that they +can get some exposure when integrated with other ongoing development. +This tree is available to Andrew for pulling into -mm whenever he wants. + +2) A "release" tree into which tested patches are moved for final +sanity checking, and as a vehicle to send them upstream to Linus +(by sending him a "please pull" request.) + +Note that the period of time that each patch spends in the "test" tree +is dependent on the complexity of the change. Since GIT does not support +cherry picking, it is not practical to simply apply all patches to the +test tree and then pull to the release tree as that would leave trivial +patches blocked in the test tree waiting for complex changes to accumulate +enough test time to graduate. + +Back in the BitKeeper days I achieved this by creating small forests of +temporary trees, one tree for each logical grouping of patches, and then +pulling changes from these trees first to the test tree, and then to the +release tree. At first I replicated this in GIT, but then I realised +that I could so this far more efficiently using branches inside a single +GIT repository. + +So here is the step-by-step guide how this all works for me. + +First create your work tree by cloning Linus's public tree: + + $ git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git work + +Change directory into the cloned tree you just created + + $ cd work + +Set up a remotes file so that you can fetch the latest from Linus' master +branch into a local branch named "linus": + + $ cat > .git/remotes/linus + URL: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + Pull: master:linus + ^D + +and create the linus branch: + + $ git branch linus + +The "linus" branch will be used to track the upstream kernel. To update it, +you simply run: + + $ git fetch linus + +you can do this frequently (and it should be safe to do so with pending +work in your tree, but perhaps not if you are in mid-merge). + +If you need to keep track of other public trees, you can add remote branches +for them too: + + $ git branch another + $ cat > .git/remotes/another + URL: ... insert URL here ... + Pull: name-of-branch-in-this-remote-tree:another + ^D + +and run: + + $ git fetch another + +Now create the branches in which you are going to work, these start +out at the current tip of the linus branch. + + $ git branch test linus + $ git branch release linus + +These can be easily kept up to date by merging from the "linus" branch: + + $ git checkout test && git merge "Auto-update from upstream" test linus + $ git checkout release && git merge "Auto-update from upstream" release linus + +Important note! If you have any local changes in these branches, then +this merge will create a commit object in the history (with no local +changes git will simply do a "Fast forward" merge). Many people dislike +the "noise" that this creates in the Linux history, so you should avoid +doing this capriciously in the "release" branch, as these noisy commits +will become part of the permanent history when you ask Linus to pull +from the release branch. + +Set up so that you can push upstream to your public tree (you need to +log-in to the remote system and create an empty tree there before the +first push). + + $ cat > .git/remotes/mytree + URL: master.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git + Push: release + Push: test + ^D + +and the push both the test and release trees using: + + $ git push mytree + +or push just one of the test and release branches using: + + $ git push mytree test +or + $ git push mytree release + +Now to apply some patches from the community. Think of a short +snappy name for a branch to hold this patch (or related group of +patches), and create a new branch from the current tip of the +linus branch: + + $ git checkout -b speed-up-spinlocks linus + +Now you apply the patch(es), run some tests, and commit the change(s). If +the patch is a multi-part series, then you should apply each as a separate +commit to this branch. + + $ ... patch ... test ... commit [ ... patch ... test ... commit ]* + +When you are happy with the state of this change, you can pull it into the +"test" branch in preparation to make it public: + + $ git checkout test && git merge "Pull speed-up-spinlock changes" test speed-up-spinlocks + +It is unlikely that you would have any conflicts here ... but you might if you +spent a while on this step and had also pulled new versions from upstream. + +Some time later when enough time has passed and testing done, you can pull the +same branch into the "release" tree ready to go upstream. This is where you +see the value of keeping each patch (or patch series) in its own branch. It +means that the patches can be moved into the "release" tree in any order. + + $ git checkout release && git merge "Pull speed-up-spinlock changes" release speed-up-spinlocks + +After a while, you will have a number of branches, and despite the +well chosen names you picked for each of them, you may forget what +they are for, or what status they are in. To get a reminder of what +changes are in a specific branch, use: + + $ git-whatchanged branchname ^linus | git-shortlog + +To see whether it has already been merged into the test or release branches +use: + + $ git-rev-list branchname ^test +or + $ git-rev-list branchname ^release + +[If this branch has not yet been merged you will see a set of SHA1 values +for the commits, if it has been merged, then there will be no output] + +Once a patch completes the great cycle (moving from test to release, then +pulled by Linus, and finally coming back into your local "linus" branch) +the branch for this change is no longer needed. You detect this when the +output from: + + $ git-rev-list branchname ^linus + +is empty. At this point the branch can be deleted: + + $ git branch -d branchname + +Some changes are so trivial that it is not necessary to create a separate +branch and then merge into each of the test and release branches. For +these changes, just apply directly to the "release" branch, and then +merge that into the "test" branch. + +To create diffstat and shortlog summaries of changes to include in a "please +pull" request to Linus you can use: + + $ git-whatchanged -p release ^linus | diffstat -p1 +and + $ git-whatchanged release ^linus | git-shortlog + + +Here are some of the scripts that I use to simplify all this even further. + +==== update script ==== +# Update a branch in my GIT tree. If the branch to be updated +# is "linus", then pull from kernel.org. Otherwise merge local +# linus branch into test|release branch + +case "$1" in +test|release) + git checkout $1 && git merge "Auto-update from upstream" $1 linus + ;; +linus) + before=$(cat .git/refs/heads/linus) + git fetch linus + after=$(cat .git/refs/heads/linus) + if [ $before != $after ] + then + git-whatchanged $after ^$before | git-shortlog + fi + ;; +*) + echo "Usage: $0 linus|test|release" 1>&2 + exit 1 + ;; +esac + +==== merge script ==== +# Merge a branch into either the test or release branch + +pname=$0 + +usage() +{ + echo "Usage: $pname branch test|release" 1>&2 + exit 1 +} + +if [ ! -f .git/refs/heads/"$1" ] +then + echo "Can't see branch <$1>" 1>&2 + usage +fi + +case "$2" in +test|release) + if [ $(git-rev-list $1 ^$2 | wc -c) -eq 0 ] + then + echo $1 already merged into $2 1>&2 + exit 1 + fi + git checkout $2 && git merge "Pull $1 into $2 branch" $2 $1 + ;; +*) + usage + ;; +esac + +==== status script ==== +# report on status of my ia64 GIT tree + +gb=$(tput setab 2) +rb=$(tput setab 1) +restore=$(tput setab 9) + +if [ `git-rev-list release ^test | wc -c` -gt 0 ] +then + echo $rb Warning: commits in release that are not in test $restore + git-whatchanged release ^test +fi + +for branch in `ls .git/refs/heads` +do + if [ $branch = linus -o $branch = test -o $branch = release ] + then + continue + fi + + echo -n $gb ======= $branch ====== $restore " " + status= + for ref in test release linus + do + if [ `git-rev-list $branch ^$ref | wc -c` -gt 0 ] + then + status=$status${ref:0:1} + fi + done + case $status in + trl) + echo $rb Need to pull into test $restore + ;; + rl) + echo "In test" + ;; + l) + echo "Waiting for linus" + ;; + "") + echo $rb All done $restore + ;; + *) + echo $rb "<$status>" $restore + ;; + esac + git-whatchanged $branch ^linus | git-shortlog +done diff --git a/Documentation/i18n.txt b/Documentation/i18n.txt new file mode 100644 index 0000000000..b95f99be6c --- /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 i18n.commitencoding in `.git/config` file, like this: ++ +------------ +[i18n] + commitencoding = ISO-8859-1 +------------ ++ +Commit objects created with the above setting record the value +of `i18n.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 + `i18n.logoutputencoding` in `.git/config` file, like this: ++ +------------ +[i18n] + logoutputencoding = ISO-8859-1 +------------ ++ +If you do not have this configuration variable, the value of +`i18n.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/install-webdoc.sh b/Documentation/install-webdoc.sh new file mode 100755 index 0000000000..cd3a18eb7f --- /dev/null +++ b/Documentation/install-webdoc.sh @@ -0,0 +1,29 @@ +#!/bin/sh + +T="$1" + +for h in *.html *.txt howto/*.txt howto/*.html RelNotes-*.txt *.css +do + if test -f "$T/$h" && + diff -u -I'Last updated [0-9][0-9]-[A-Z][a-z][a-z]-' "$T/$h" "$h" + then + :; # up to date + else + echo >&2 "# install $h $T/$h" + rm -f "$T/$h" + mkdir -p `dirname "$T/$h"` + cp "$h" "$T/$h" + fi +done +strip_leading=`echo "$T/" | sed -e 's|.|.|g'` +for th in "$T"/*.html "$T"/*.txt "$T"/howto/*.txt "$T"/howto/*.html +do + h=`expr "$th" : "$strip_leading"'\(.*\)'` + case "$h" in + index.html) continue ;; + esac + test -f "$h" && continue + echo >&2 "# rm -f $th" + rm -f "$th" +done +ln -sf git.html "$T/index.html" diff --git a/Documentation/merge-options.txt b/Documentation/merge-options.txt new file mode 100644 index 0000000000..182cef54be --- /dev/null +++ b/Documentation/merge-options.txt @@ -0,0 +1,24 @@ +-n, \--no-summary:: + Do not show diffstat at the end of the merge. + +--no-commit:: + Perform the merge but pretend the merge failed and do + not autocommit, to give the user a chance to inspect and + further tweak the merge result before committing. + +--squash:: + Produce the working tree and index state as if a real + merge happened, but do not actually make a commit or + move the `HEAD`, nor record `$GIT_DIR/MERGE_HEAD` to + cause the next `git commit` command to create a merge + commit. This allows you to create a single commit on + top of the current branch whose effect is the same as + merging another branch (or more in case of an octopus). + +-s <strategy>, \--strategy=<strategy>:: + Use the given merge strategy; can be supplied more than + once to specify them in the order they should be tried. + If there is no `-s` option, a built-in list of strategies + is used instead (`git-merge-recursive` when merging a single + head, `git-merge-octopus` otherwise). + diff --git a/Documentation/merge-strategies.txt b/Documentation/merge-strategies.txt new file mode 100644 index 0000000000..7df0266ba8 --- /dev/null +++ b/Documentation/merge-strategies.txt @@ -0,0 +1,35 @@ +MERGE STRATEGIES +---------------- + +resolve:: + This can only resolve two heads (i.e. the current branch + and another branch you pulled from) using 3-way merge + algorithm. It tries to carefully detect criss-cross + merge ambiguities and is considered generally safe and + fast. + +recursive:: + This can only resolve two heads using 3-way merge + algorithm. When there are more than one common + ancestors that can be used for 3-way merge, it creates a + merged tree of the common ancestors and uses that as + the reference tree for the 3-way merge. This has been + reported to result in fewer merge conflicts without + causing mis-merges by tests done on actual merge commits + taken from Linux 2.6 kernel development history. + Additionally this can detect and handle merges involving + renames. This is the default merge strategy when + pulling or merging one branch. + +octopus:: + This resolves more than two-head case, but refuses to do + complex merge that needs manual resolution. It is + primarily meant to be used for bundling topic branch + heads together. This is the default merge strategy when + pulling or merging more than one branches. + +ours:: + This resolves any number of heads, but the result of the + merge is always the current branch head. It is meant to + be used to supersede old development history of side + branches. diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt new file mode 100644 index 0000000000..2fe6c31967 --- /dev/null +++ b/Documentation/pretty-formats.txt @@ -0,0 +1,129 @@ +--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. + + * 'format:' ++ +The 'format:' format allows you to specify which information +you want to show. It works a little bit like printf format, +with the notable exception that you get a newline with '%n' +instead of '\n'. + +E.g, 'format:"The author of %h was %an, %ar%nThe title was >>%s<<"' +would show something like this: + +The author of fe6e0ee was Junio C Hamano, 23 hours ago +The title was >>t4119: test autocomputing -p<n> for traditional diff input.<< + +The placeholders are: + +- '%H': commit hash +- '%h': abbreviated commit hash +- '%T': tree hash +- '%t': abbreviated tree hash +- '%P': parent hashes +- '%p': abbreviated parent hashes +- '%an': author name +- '%ae': author email +- '%ad': author date +- '%aD': author date, RFC2822 style +- '%ar': author date, relative +- '%at': author date, UNIX timestamp +- '%cn': committer name +- '%ce': committer email +- '%cd': committer date +- '%cD': committer date, RFC2822 style +- '%cr': committer date, relative +- '%ct': committer date, UNIX timestamp +- '%e': encoding +- '%s': subject +- '%b': body +- '%Cred': switch color to red +- '%Cgreen': switch color to green +- '%Cblue': switch color to blue +- '%Creset': reset color +- '%n': newline + + +--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 new file mode 100644 index 0000000000..8d4e950abc --- /dev/null +++ b/Documentation/pull-fetch-param.txt @@ -0,0 +1,65 @@ +<repository>:: + The "remote" repository that is the source of a fetch + or pull operation. See the section <<URLS,GIT URLS>> below. + +<refspec>:: + The canonical format of a <refspec> parameter is + `+?<src>:<dst>`; that is, an optional plus `+`, followed + by the source ref, followed by a colon `:`, followed by + the destination ref. ++ +The remote ref that matches <src> +is fetched, and if <dst> is not empty string, the local +ref that matches it is fast forwarded using <src>. +Again, if the optional plus `+` is used, the local ref +is updated even if it does not result in a fast forward +update. ++ +[NOTE] +If the remote branch from which you want to pull is +modified in non-linear ways such as being rewound and +rebased frequently, then a pull will attempt a merge with +an older version of itself, likely conflict, and fail. +It is under these conditions that you would want to use +the `+` sign to indicate non-fast-forward updates will +be needed. There is currently no easy way to determine +or declare that a branch will be made available in a +repository with this behavior; the pulling user simply +must know this is the expected usage pattern for a branch. ++ +[NOTE] +You never do your own development on branches that appear +on the right hand side of a <refspec> colon on `Pull:` lines; +they are to be updated by `git-fetch`. If you intend to do +development derived from a remote branch `B`, have a `Pull:` +line to track it (i.e. `Pull: B:remote-B`), and have a separate +branch `my-B` to do your development on top of it. The latter +is created by `git branch my-B remote-B` (or its equivalent `git +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. ++ +[NOTE] +There is a difference between listing multiple <refspec> +directly on `git-pull` command line and having multiple +`Pull:` <refspec> lines for a <repository> and running +`git-pull` command without any explicit <refspec> parameters. +<refspec> listed explicitly on the command line are always +merged into the current branch after fetching. In other words, +if you list more than one remote refs, you would be making +an Octopus. While `git-pull` run without any explicit <refspec> +parameter takes default <refspec>s from `Pull:` lines, it +merges only the first <refspec> found into the current branch, +after fetching all the remote refs. This is because making an +Octopus from remote refs is rarely done, while keeping track +of multiple remote heads in one-go by fetching more than one +is often useful. ++ +Some short-cut notations are also supported. ++ +* `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`; + it requests fetching everything up to the given tag. +* A parameter <ref> without a colon is equivalent to + <ref>: when pulling/fetching, so it merges <ref> into the current + branch without storing the remote branch anywhere locally diff --git a/Documentation/repository-layout.txt b/Documentation/repository-layout.txt new file mode 100644 index 0000000000..0459bd9ca1 --- /dev/null +++ b/Documentation/repository-layout.txt @@ -0,0 +1,181 @@ +git repository layout +===================== + +You may find these things in your git repository (`.git` +directory for a repository associated with your working tree, or +`'project'.git` directory for a public 'bare' repository). + +objects:: + Object store associated with this repository. Usually + an object store is self sufficient (i.e. all the objects + that are referred to by an object found in it are also + found in it), but there are couple of ways to violate + it. ++ +. You could populate the repository by running a commit walker +without `-a` option. Depending on which options are given, you +could have only commit objects without associated blobs and +trees this way, for example. A repository with this kind of +incomplete object store is not suitable to be published to the +outside world but sometimes useful for private repository. +. You also could have an incomplete but locally usable repository +by cloning shallowly. See gitlink:git-clone[1]. +. You can be using `objects/info/alternates` mechanism, or +`$GIT_ALTERNATE_OBJECT_DIRECTORIES` mechanism to 'borrow' +objects from other object stores. A repository with this kind +of incomplete object store is not suitable to be published for +use with dumb transports but otherwise is OK as long as +`objects/info/alternates` points at the right object stores +it borrows from. + +objects/[0-9a-f][0-9a-f]:: + Traditionally, each object is stored in its own file. + They are split into 256 subdirectories using the first + two letters from its object name to keep the number of + directory entries `objects` directory itself needs to + hold. Objects found here are often called 'unpacked' + (or 'loose') objects. + +objects/pack:: + Packs (files that store many object in compressed form, + along with index files to allow them to be randomly + accessed) are found in this directory. + +objects/info:: + Additional information about the object store is + recorded in this directory. + +objects/info/packs:: + This file is to help dumb transports discover what packs + are available in this object store. Whenever a pack is + added or removed, `git update-server-info` should be run + to keep this file up-to-date if the repository is + published for dumb transports. `git repack` does this + by default. + +objects/info/alternates:: + 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 + directory. The `git prune` command knows to keep + objects reachable from refs found in this directory and + its subdirectories. + +refs/heads/`name`:: + records tip-of-the-tree commit objects of branch `name` + +refs/tags/`name`:: + records any object name (not necessarily a commit + object, or a tag object that points at a commit object). + +refs/remotes/`name`:: + records tip-of-the-tree commit objects of branches copied + from a remote repository. + +packed-refs:: + records the same information as refs/heads/, refs/tags/, + and friends record in a more efficient way. See + gitlink:git-pack-refs[1]. + +HEAD:: + 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 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. ++ +HEAD can also record a specific commit directly, instead of +being a symref to point at the current branch. Such a state +is often called 'detached HEAD', and almost all commands work +identically as normal. See gitlink:git-checkout[1] for +details. + +branches:: + A slightly deprecated way to store shorthands to be used + to specify URL to `git fetch`, `git pull` and `git push` + commands is to store a file in `branches/'name'` and + give 'name' to these commands in place of 'repository' + argument. + +hooks:: + Hooks are customization scripts used by various git + commands. A handful of sample hooks are installed when + `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. + +index:: + The current index file for the repository. It is + usually not found in a bare repository. + +info:: + Additional information about the repository is recorded + in this directory. + +info/refs:: + This file helps dumb transports discover what refs are + available in this repository. If the repository is + published for dumb transports, this file should be + regenerated by `git update-server-info` every time a tag + or branch is created or modified. This is normally done + from the `hooks/update` hook, which is run by the + `git-receive-pack` command when you `git push` into the + repository. + +info/grafts:: + This file records fake commit ancestry information, to + pretend the set of parents a commit has is different + from how the commit was actually created. One record + per line describes a commit and its fake parents by + listing their 40-byte hexadecimal object names separated + by a space and terminated by a newline. + +info/exclude:: + This file, by convention among Porcelains, stores the + exclude pattern list. `.gitignore` is the per-directory + ignore file. `git status`, `git add`, `git rm` and `git + clean` look at it but the core git commands do not look + at it. See also: gitlink:git-ls-files[1] `--exclude-from` + and `--exclude-per-directory`. + +remotes:: + Stores shorthands to be used to give URL and default + refnames to interact with remote repository to `git + fetch`, `git pull` and `git push` commands. + +logs:: + Records of changes made to refs are stored in this + directory. See the documentation on git-update-ref + for more information. + +logs/refs/heads/`name`:: + Records all changes made to the branch tip named `name`. + +logs/refs/tags/`name`:: + Records all changes made to the tag named `name`. + +shallow:: + This is similar to `info/grafts` but is internally used + and maintained by shallow clone mechanism. See `--depth` + option to gitlink:git-clone[1] and gitlink:git-fetch[1]. + diff --git a/Documentation/sort_glossary.pl b/Documentation/sort_glossary.pl new file mode 100644 index 0000000000..05dc7b2c7b --- /dev/null +++ b/Documentation/sort_glossary.pl @@ -0,0 +1,69 @@ +#!/usr/bin/perl + +%terms=(); + +while(<>) { + if(/^(\S.*)::$/) { + my $term=$1; + if(defined($terms{$term})) { + die "$1 defined twice\n"; + } + $terms{$term}=""; + LOOP: while(<>) { + if(/^$/) { + last LOOP; + } + if(/^ \S/) { + $terms{$term}.=$_; + } else { + die "Error 1: $_"; + } + } + } +} + +sub format_tab_80 ($) { + my $text=$_[0]; + my $result=""; + $text=~s/\s+/ /g; + $text=~s/^\s+//; + while($text=~/^(.{1,72})(|\s+(\S.*)?)$/) { + $result.=" ".$1."\n"; + $text=$3; + } + return $result; +} + +sub no_spaces ($) { + my $result=$_[0]; + $result=~tr/ /_/; + return $result; +} + +print 'GIT Glossary +============ + +This list is sorted alphabetically: + +'; + +@keys=sort {uc($a) cmp uc($b)} keys %terms; +$pattern='(\b(?<!link:git-)'.join('\b|\b(?<!-)',reverse @keys).'\b)'; +foreach $key (@keys) { + $terms{$key}=~s/$pattern/sprintf "<<ref_".no_spaces($1).",$1>>";/eg; + print '[[ref_'.no_spaces($key).']]'.$key."::\n" + .format_tab_80($terms{$key})."\n"; +} + +print ' + +Author +------ +Written by Johannes Schindelin <Johannes.Schindelin@gmx.de> and +the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the link:git.html[git] suite +'; + diff --git a/Documentation/technical/pack-format.txt b/Documentation/technical/pack-format.txt new file mode 100644 index 0000000000..0e1ffb2427 --- /dev/null +++ b/Documentation/technical/pack-format.txt @@ -0,0 +1,116 @@ +GIT pack format +=============== + += pack-*.pack file has the following format: + + - The header appears at the beginning and consists of the following: + + 4-byte signature: + The signature is: {'P', 'A', 'C', 'K'} + + 4-byte version number (network byte order): + GIT currently accepts version number 2 or 3 but + generates version 2 only. + + 4-byte number of objects contained in the pack (network byte order) + + Observation: we cannot have more than 4G versions ;-) and + more than 4G objects in a pack. + + - The header is followed by number of object entries, each of + which looks like this: + + (undeltified representation) + n-byte type and length (4-bit type, (n-1)*7+4-bit length) + compressed data + + (deltified representation) + n-byte type and length (4-bit type, (n-1)*7+4-bit length) + 20-byte base object name + compressed delta data + + Observation: length of each object is encoded in a variable + length format and is not constrained to 32-bit or anything. + + - The trailer records 20-byte SHA1 checksum of all of the above. + += pack-*.idx file has the following format: + + - The header consists of 256 4-byte network byte order + integers. N-th entry of this table records the number of + objects in the corresponding pack, the first byte of whose + object name are smaller than N. This is called the + 'first-level fan-out' table. + + Observation: we would need to extend this to an array of + 8-byte integers to go beyond 4G objects per pack, but it is + not strictly necessary. + + - The header is followed by sorted 24-byte entries, one entry + per object in the pack. Each entry is: + + 4-byte network byte order integer, recording where the + object is stored in the packfile as the offset from the + beginning. + + 20-byte object name. + + Observation: we would definitely need to extend this to + 8-byte integer plus 20-byte object name to handle a packfile + that is larger than 4GB. + + - The file is concluded with a trailer: + + A copy of the 20-byte SHA1 checksum at the end of + corresponding packfile. + + 20-byte SHA1-checksum of all of the above. + +Pack Idx file: + + idx + +--------------------------------+ + | fanout[0] = 2 |-. + +--------------------------------+ | + | fanout[1] | | + +--------------------------------+ | + | fanout[2] | | + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | + | fanout[255] | | + +--------------------------------+ | +main | offset | | +index | object name 00XXXXXXXXXXXXXXXX | | +table +--------------------------------+ | + | offset | | + | object name 00XXXXXXXXXXXXXXXX | | + +--------------------------------+ | + .-| offset |<+ + | | object name 01XXXXXXXXXXXXXXXX | + | +--------------------------------+ + | | offset | + | | object name 01XXXXXXXXXXXXXXXX | + | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + | | offset | + | | object name FFXXXXXXXXXXXXXXXX | + | +--------------------------------+ +trailer | | packfile checksum | + | +--------------------------------+ + | | idxfile checksum | + | +--------------------------------+ + .-------. + | +Pack file entry: <+ + + packed object header: + 1-byte type (upper 4-bit) + size0 (lower 4-bit) + n-byte sizeN (as long as MSB is set, each 7-bit) + size0..sizeN form 4+7+7+..+7 bit integer, size0 + is the most significant part. + packed object data: + If it is not DELTA, then deflated bytes (the size above + is the size before compression). + If it is DELTA, then + 20-byte base object name SHA1 (the size above is the + size of the delta data that follows). + delta data, deflated. diff --git a/Documentation/technical/pack-heuristics.txt b/Documentation/technical/pack-heuristics.txt new file mode 100644 index 0000000000..103eb5d989 --- /dev/null +++ b/Documentation/technical/pack-heuristics.txt @@ -0,0 +1,466 @@ + Concerning Git's Packing Heuristics + =================================== + + Oh, here's a really stupid question: + + Where do I go + to learn the details + of git's packing heuristics? + +Be careful what you ask! + +Followers of the git, please open the git IRC Log and turn to +February 10, 2006. + +It's a rare occasion, and we are joined by the King Git Himself, +Linus Torvalds (linus). Nathaniel Smith, (njs`), has the floor +and seeks enlightenment. Others are present, but silent. + +Let's listen in! + + <njs`> Oh, here's a really stupid question -- where do I go to + learn the details of git's packing heuristics? google avails + me not, reading the source didn't help a lot, and wading + through the whole mailing list seems less efficient than any + of that. + +It is a bold start! A plea for help combined with a simultaneous +tri-part attack on some of the tried and true mainstays in the quest +for enlightenment. Brash accusations of google being useless. Hubris! +Maligning the source. Heresy! Disdain for the mailing list archives. +Woe. + + <pasky> yes, the packing-related delta stuff is somewhat + mysterious even for me ;) + +Ah! Modesty after all. + + <linus> njs, I don't think the docs exist. That's something where + I don't think anybody else than me even really got involved. + Most of the rest of git others have been busy with (especially + Junio), but packing nobody touched after I did it. + +It's cryptic, yet vague. Linus in style for sure. Wise men +interpret this as an apology. A few argue it is merely a +statement of fact. + + <njs`> I guess the next step is "read the source again", but I + have to build up a certain level of gumption first :-) + +Indeed! On both points. + + <linus> The packing heuristic is actually really really simple. + +Bait... + + <linus> But strange. + +And switch. That ought to do it! + + <linus> Remember: git really doesn't follow files. So what it does is + - generate a list of all objects + - sort the list according to magic heuristics + - walk the list, using a sliding window, seeing if an object + can be diffed against another object in the window + - write out the list in recency order + +The traditional understatement: + + <njs`> I suspect that what I'm missing is the precise definition of + the word "magic" + +The traditional insight: + + <pasky> yes + +And Babel-like confusion flowed. + + <njs`> oh, hmm, and I'm not sure what this sliding window means either + + <pasky> iirc, it appeared to me to be just the sha1 of the object + when reading the code casually ... + + ... which simply doesn't sound as a very good heuristics, though ;) + + <njs`> .....and recency order. okay, I think it's clear I didn't + even realize how much I wasn't realizing :-) + +Ah, grasshopper! And thus the enlightenment begins anew. + + <linus> The "magic" is actually in theory totally arbitrary. + ANY order will give you a working pack, but no, it's not + ordered by SHA1. + + Before talking about the ordering for the sliding delta + window, let's talk about the recency order. That's more + important in one way. + + <njs`> Right, but if all you want is a working way to pack things + together, you could just use cat and save yourself some + trouble... + +Waaait for it.... + + <linus> The recency ordering (which is basically: put objects + _physically_ into the pack in the order that they are + "reachable" from the head) is important. + + <njs`> okay + + <linus> It's important because that's the thing that gives packs + good locality. It keeps the objects close to the head (whether + they are old or new, but they are _reachable_ from the head) + at the head of the pack. So packs actually have absolutely + _wonderful_ IO patterns. + +Read that again, because it is important. + + <linus> But recency ordering is totally useless for deciding how + to actually generate the deltas, so the delta ordering is + something else. + + The delta ordering is (wait for it): + - first sort by the "basename" of the object, as defined by + the name the object was _first_ reached through when + generating the object list + - within the same basename, sort by size of the object + - but always sort different types separately (commits first). + + That's not exactly it, but it's very close. + + <njs`> The "_first_ reached" thing is not too important, just you + need some way to break ties since the same objects may be + reachable many ways, yes? + +And as if to clarify: + + <linus> The point is that it's all really just any random + heuristic, and the ordering is totally unimportant for + correctness, but it helps a lot if the heuristic gives + "clumping" for things that are likely to delta well against + each other. + +It is an important point, so secretly, I did my own research and have +included my results below. To be fair, it has changed some over time. +And through the magic of Revisionistic History, I draw upon this entry +from The Git IRC Logs on my father's birthday, March 1: + + <gitster> The quote from the above linus should be rewritten a + bit (wait for it): + - first sort by type. Different objects never delta with + each other. + - then sort by filename/dirname. hash of the basename + occupies the top BITS_PER_INT-DIR_BITS bits, and bottom + DIR_BITS are for the hash of leading path elements. + - then if we are doing "thin" pack, the objects we are _not_ + going to pack but we know about are sorted earlier than + other objects. + - and finally sort by size, larger to smaller. + +In one swell-foop, clarification and obscurification! Nonetheless, +authoritative. Cryptic, yet concise. It even solicits notions of +quotes from The Source Code. Clearly, more study is needed. + + <gitster> That's the sort order. What this means is: + - we do not delta different object types. + - we prefer to delta the objects with the same full path, but + allow files with the same name from different directories. + - we always prefer to delta against objects we are not going + to send, if there are some. + - we prefer to delta against larger objects, so that we have + lots of removals. + + The penultimate rule is for "thin" packs. It is used when + the other side is known to have such objects. + +There it is again. "Thin" packs. I'm thinking to myself, "What +is a 'thin' pack?" So I ask: + + <jdl> What is a "thin" pack? + + <gitster> Use of --objects-edge to rev-list as the upstream of + pack-objects. The pack transfer protocol negotiates that. + +Woo hoo! Cleared that _right_ up! + + <gitster> There are two directions - push and fetch. + +There! Did you see it? It is not '"push" and "pull"'! How often the +confusion has started here. So casually mentioned, too! + + <gitster> For push, git-send-pack invokes git-receive-pack on the + other end. The receive-pack says "I have up to these commits". + send-pack looks at them, and computes what are missing from + the other end. So "thin" could be the default there. + + In the other direction, fetch, git-fetch-pack and + git-clone-pack invokes git-upload-pack on the other end + (via ssh or by talking to the daemon). + + There are two cases: fetch-pack with -k and clone-pack is one, + fetch-pack without -k is the other. clone-pack and fetch-pack + with -k will keep the downloaded packfile without expanded, so + we do not use thin pack transfer. Otherwise, the generated + pack will have delta without base object in the same pack. + + But fetch-pack without -k will explode the received pack into + individual objects, so we automatically ask upload-pack to + give us a thin pack if upload-pack supports it. + +OK then. + +Uh. + +Let's return to the previous conversation still in progress. + + <njs`> and "basename" means something like "the tail of end of + path of file objects and dir objects, as per basename(3), and + we just declare all commit and tag objects to have the same + basename" or something? + +Luckily, that too is a point that gitster clarified for us! + +If I might add, the trick is to make files that _might_ be similar be +located close to each other in the hash buckets based on their file +names. It used to be that "foo/Makefile", "bar/baz/quux/Makefile" and +"Makefile" all landed in the same bucket due to their common basename, +"Makefile". However, now they land in "close" buckets. + +The algorithm allows not just for the _same_ bucket, but for _close_ +buckets to be considered delta candidates. The rationale is +essentially that files, like Makefiles, often have very similar +content no matter what directory they live in. + + <linus> I played around with different delta algorithms, and with + making the "delta window" bigger, but having too big of a + sliding window makes it very expensive to generate the pack: + you need to compare every object with a _ton_ of other objects. + + There are a number of other trivial heuristics too, which + basically boil down to "don't bother even trying to delta this + pair" if we can tell before-hand that the delta isn't worth it + (due to size differences, where we can take a previous delta + result into account to decide that "ok, no point in trying + that one, it will be worse"). + + End result: packing is actually very size efficient. It's + somewhat CPU-wasteful, but on the other hand, since you're + really only supposed to do it maybe once a month (and you can + do it during the night), nobody really seems to care. + +Nice Engineering Touch, there. Find when it doesn't matter, and +proclaim it a non-issue. Good style too! + + <njs`> So, just to repeat to see if I'm following, we start by + getting a list of the objects we want to pack, we sort it by + this heuristic (basically lexicographically on the tuple + (type, basename, size)). + + Then we walk through this list, and calculate a delta of + each object against the last n (tunable parameter) objects, + and pick the smallest of these deltas. + +Vastly simplified, but the essence is there! + + <linus> Correct. + + <njs`> And then once we have picked a delta or fulltext to + represent each object, we re-sort by recency, and write them + out in that order. + + <linus> Yup. Some other small details: + +And of course there is the "Other Shoe" Factor too. + + <linus> - We limit the delta depth to another magic value (right + now both the window and delta depth magic values are just "10") + + <njs`> Hrm, my intuition is that you'd end up with really _bad_ IO + patterns, because the things you want are near by, but to + actually reconstruct them you may have to jump all over in + random ways. + + <linus> - When we write out a delta, and we haven't yet written + out the object it is a delta against, we write out the base + object first. And no, when we reconstruct them, we actually + get nice IO patterns, because: + - larger objects tend to be "more recent" (Linus' law: files grow) + - we actively try to generate deltas from a larger object to a + smaller one + - this means that the top-of-tree very seldom has deltas + (i.e. deltas in _practice_ are "backwards deltas") + +Again, we should reread that whole paragraph. Not just because +Linus has slipped Linus's Law in there on us, but because it is +important. Let's make sure we clarify some of the points here: + + <njs`> So the point is just that in practice, delta order and + recency order match each other quite well. + + <linus> Yes. There's another nice side to this (and yes, it was + designed that way ;): + - the reason we generate deltas against the larger object is + actually a big space saver too! + + <njs`> Hmm, but your last comment (if "we haven't yet written out + the object it is a delta against, we write out the base object + first"), seems like it would make these facts mostly + irrelevant because even if in practice you would not have to + wander around much, in fact you just brute-force say that in + the cases where you might have to wander, don't do that :-) + + <linus> Yes and no. Notice the rule: we only write out the base + object first if the delta against it was more recent. That + means that you can actually have deltas that refer to a base + object that is _not_ close to the delta object, but that only + happens when the delta is needed to generate an _old_ object. + + <linus> See? + +Yeah, no. I missed that on the first two or three readings myself. + + <linus> This keeps the front of the pack dense. The front of the + pack never contains data that isn't relevant to a "recent" + object. The size optimization comes from our use of xdelta + (but is true for many other delta algorithms): removing data + is cheaper (in size) than adding data. + + When you remove data, you only need to say "copy bytes n--m". + In contrast, in a delta that _adds_ data, you have to say "add + these bytes: 'actual data goes here'" + + *** njs` has quit: Read error: 104 (Connection reset by peer) + + <linus> Uhhuh. I hope I didn't blow njs` mind. + + *** njs` has joined channel #git + + <pasky> :) + +The silent observers are amused. Of course. + +And as if njs` was expected to be omniscient: + + <linus> njs - did you miss anything? + +OK, I'll spell it out. That's Geek Humor. If njs` was not actually +connected for a little bit there, how would he know if missed anything +while he was disconnected? He's a benevolent dictator with a sense of +humor! Well noted! + + <njs`> Stupid router. Or gremlins, or whatever. + +It's a cheap shot at Cisco. Take 'em when you can. + + <njs`> Yes and no. Notice the rule: we only write out the base + object first if the delta against it was more recent. + + I'm getting lost in all these orders, let me re-read :-) + So the write-out order is from most recent to least recent? + (Conceivably it could be the opposite way too, I'm not sure if + we've said) though my connection back at home is logging, so I + can just read what you said there :-) + +And for those of you paying attention, the Omniscient Trick has just +been detailed! + + <linus> Yes, we always write out most recent first + +For the other record: + + <pasky> njs`: http://pastebin.com/547965 + +The 'net never forgets, so that should be good until the end of time. + + <njs`> And, yeah, I got the part about deeper-in-history stuff + having worse IO characteristics, one sort of doesn't care. + + <linus> With the caveat that if the "most recent" needs an older + object to delta against (hey, shrinking sometimes does + happen), we write out the old object with the delta. + + <njs`> (if only it happened more...) + + <linus> Anyway, the pack-file could easily be denser still, but + because it's used both for streaming (the git protocol) and + for on-disk, it has a few pessimizations. + +Actually, it is a made-up word. But it is a made-up word being +used as setup for a later optimization, which is a real word: + + <linus> In particular, while the pack-file is then compressed, + it's compressed just one object at a time, so the actual + compression factor is less than it could be in theory. But it + means that it's all nice random-access with a simple index to + do "object name->location in packfile" translation. + + <njs`> I'm assuming the real win for delta-ing large->small is + more homogeneous statistics for gzip to run over? + + (You have to put the bytes in one place or another, but + putting them in a larger blob wins on compression) + + Actually, what is the compression strategy -- each delta + individually gzipped, the whole file gzipped, somewhere in + between, no compression at all, ....? + + Right. + +Reality IRC sets in. For example: + + <pasky> I'll read the rest in the morning, I really have to go + sleep or there's no hope whatsoever for me at the today's + exam... g'nite all. + +Heh. + + <linus> pasky: g'nite + + <njs`> pasky: 'luck + + <linus> Right: large->small matters exactly because of compression + behaviour. If it was non-compressed, it probably wouldn't make + any difference. + + <njs`> yeah + + <linus> Anyway: I'm not even trying to claim that the pack-files + are perfect, but they do tend to have a nice balance of + density vs ease-of use. + +Gasp! OK, saved. That's a fair Engineering trade off. Close call! +In fact, Linus reflects on some Basic Engineering Fundamentals, +design options, etc. + + <linus> More importantly, they allow git to still _conceptually_ + never deal with deltas at all, and be a "whole object" store. + + Which has some problems (we discussed bad huge-file + behaviour on the git lists the other day), but it does mean + that the basic git concepts are really really simple and + straightforward. + + It's all been quite stable. + + Which I think is very much a result of having very simple + basic ideas, so that there's never any confusion about what's + going on. + + Bugs happen, but they are "simple" bugs. And bugs that + actually get some object store detail wrong are almost always + so obvious that they never go anywhere. + + <njs`> Yeah. + +Nuff said. + + <linus> Anyway. I'm off for bed. It's not 6AM here, but I've got + three kids, and have to get up early in the morning to send + them off. I need my beauty sleep. + + <njs`> :-) + + <njs`> appreciate the infodump, I really was failing to find the + details on git packs :-) + +And now you know the rest of the story. diff --git a/Documentation/technical/pack-protocol.txt b/Documentation/technical/pack-protocol.txt new file mode 100644 index 0000000000..9cd48b4859 --- /dev/null +++ b/Documentation/technical/pack-protocol.txt @@ -0,0 +1,41 @@ +Pack transfer protocols +======================= + +There are two Pack push-pull protocols. + +upload-pack (S) | fetch/clone-pack (C) protocol: + + # Tell the puller what commits we have and what their names are + S: SHA1 name + S: ... + S: SHA1 name + S: # flush -- it's your turn + # Tell the pusher what commits we want, and what we have + C: want name + C: .. + C: want name + C: have SHA1 + C: have SHA1 + C: ... + C: # flush -- occasionally ask "had enough?" + S: NAK + C: have SHA1 + C: ... + C: have SHA1 + S: ACK + C: done + S: XXXXXXX -- packfile contents. + +send-pack | receive-pack protocol. + + # Tell the pusher what commits we have and what their names are + C: SHA1 name + C: ... + C: SHA1 name + C: # flush -- it's your turn + # Tell the puller what the pusher has + S: old-SHA1 new-SHA1 name + S: old-SHA1 new-SHA1 name + S: ... + S: # flush -- done with the list + S: XXXXXXX --- packfile contents. diff --git a/Documentation/technical/racy-git.txt b/Documentation/technical/racy-git.txt new file mode 100644 index 0000000000..5030d9f2f8 --- /dev/null +++ b/Documentation/technical/racy-git.txt @@ -0,0 +1,195 @@ +Use of index and Racy git problem +================================= + +Background +---------- + +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 +"virtual" in the sense that it does not necessarily have to, and +often does not, match the files in the working tree. + +There are cases git needs to examine the differences between the +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 are different from what are +recorded in the index to avoid stomping on local changes in them +during patch application, switching branches, and merging. + +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 compares the result +with this information (this is what was originally done by the +`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. + +Note: not all members in `struct stat` obtained via `lstat(2)` +are used for this comparison. For example, `st_atime` obviously +is not useful. Currently, git compares the file type (regular +files vs symbolic links) and executable bits (only for regular +files) from `st_mode` member, `st_mtime` and `st_ctime` +timestamps, `st_uid`, `st_gid`, `st_ino`, and `st_size` members. +With a `USE_STDEV` compile-time option, `st_dev` is also +compared, but this is not enabled by default because this member +is not stable on network filesystems. With `USE_NSEC` +compile-time option, `st_mtim.tv_nsec` and `st_ctim.tv_nsec` +members are also compared, but this is not enabled by default +because the value of this member becomes meaningless once the +inode is evicted from the inode cache on filesystems that do not +store it on disk. + + +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' 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` +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 +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 +that appear clean when they may not be because of this problem +are called "racily clean". + +To avoid this problem, git does two things: + +. When the cached stat information says the file has not been + modified, and the `st_mtime` is the same as (or newer than) + the timestamp of the index file itself (which is the time `git + update-index foo` finished running in the above example), it + also compares the contents with the object registered in the + index entry to make sure they match. + +. When the index file is updated that contains racily clean + entries, cached `st_size` information is truncated to zero + before writing a new version of the index file. + +Because the index file itself is written after collecting all +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 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. + +The callers that want to check if an index entry matches the +corresponding file in the working tree continue to call +`ce_match_stat()`, but with this change, `ce_match_stat()` uses +`ce_modified_check_fs()` to see if racily clean ones are +actually clean after comparing the cached stat information using +`ce_match_stat_basic()`. + +The problem the latter solves is this sequence: + + $ git update-index 'foo' + : modify 'foo' in-place without changing its size + : wait for enough time + $ git update-index 'bar' + +Without the latter, the timestamp of the index file gets a newer +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 that the index entry +does not match the file and git does not have to fall back on more +expensive `ce_modified_check_fs()`. + + +Runtime penalty +--------------- + +The runtime penalty of falling back to `ce_modified_check_fs()` +from `ce_match_stat()` can be very expensive when there are many +racily clean entries. An obvious way to artificially create +this situation is to give the same timestamp to all the files in +the working tree in a large project, run `git update-index` on +them, and give the same timestamp to the index file: + + $ date >.datestamp + $ git ls-files | xargs touch -r .datestamp + $ git ls-files | git update-index --stdin + $ touch -r .datestamp .git/index + +This will make all index entries racily clean. The linux-2.6 +project, for example, there are over 20,000 files in the working +tree. On my Athron 64X2 3800+, after the above: + + $ /usr/bin/time git diff-files + 1.68user 0.54system 0:02.22elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k + 0inputs+0outputs (0major+67111minor)pagefaults 0swaps + $ git update-index MAINTAINERS + $ /usr/bin/time git diff-files + 0.02user 0.12system 0:00.14elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k + 0inputs+0outputs (0major+935minor)pagefaults 0swaps + +Running `git update-index` in the middle checked the racily +clean entries, and left the cached `st_mtime` for all the paths +intact because they were actually clean (so this step took about +the same amount of time as the first `git diff-files`). After +that, they are not racily clean anymore but are truly clean, so +the second invocation of `git diff-files` fully took advantage +of the cached stat information. + + +Avoiding runtime penalty +------------------------ + +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 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. + +. `git checkout` of a large project from an empty index into an + unpopulated working tree. + +Note: switching branches with `git checkout` keeps the cached +stat information of existing working tree files that are the +same between the current branch and the new branch, which are +all older than the resulting index file, and they will not +become racily clean. Only the files that are actually checked +out can become racily clean. + +In a large project where raciness avoidance cost really matters, +however, the initial computation of all object names in the +index takes more than one second, and the index file is written +out after all that happens. Therefore the timestamp of the +index file will be more than one seconds later than the the +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. + +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/technical/trivial-merge.txt b/Documentation/technical/trivial-merge.txt new file mode 100644 index 0000000000..24c84100b0 --- /dev/null +++ b/Documentation/technical/trivial-merge.txt @@ -0,0 +1,121 @@ +Trivial merge rules +=================== + +This document describes the outcomes of the trivial merge logic in read-tree. + +One-way merge +------------- + +This replaces the index with a different tree, keeping the stat info +for entries that don't change, and allowing -u to make the minimum +required changes to the working tree to have it match. + +Entries marked '+' have stat information. Spaces marked '*' don't +affect the result. + + index tree result + ----------------------- + * (empty) (empty) + (empty) tree tree + index+ tree tree + index+ index index+ + +Two-way merge +------------- + +It is permitted for the index to lack an entry; this does not prevent +any case from applying. + +If the index exists, it is an error for it not to match either the old +or the result. + +If multiple cases apply, the one used is listed first. + +A result which changes the index is an error if the index is not empty +and not up-to-date. + +Entries marked '+' have stat information. Spaces marked '*' don't +affect the result. + + case index old new result + ------------------------------------- + 0/2 (empty) * (empty) (empty) + 1/3 (empty) * new new + 4/5 index+ (empty) (empty) index+ + 6/7 index+ (empty) index index+ + 10 index+ index (empty) (empty) + 14/15 index+ old old index+ + 18/19 index+ old index index+ + 20 index+ index new new + +Three-way merge +--------------- + +It is permitted for the index to lack an entry; this does not prevent +any case from applying. + +If the index exists, it is an error for it not to match either the +head or (if the merge is trivial) the result. + +If multiple cases apply, the one used is listed first. + +A result of "no merge" means that index is left in stage 0, ancest in +stage 1, head in stage 2, and remote in stage 3 (if any of these are +empty, no entry is left for that stage). Otherwise, the given entry is +left in stage 0, and there are no other entries. + +A result of "no merge" is an error if the index is not empty and not +up-to-date. + +*empty* means that the tree must not have a directory-file conflict + with the entry. + +For multiple ancestors, a '+' means that this case applies even if +only one ancestor or remote fits; a '^' means all of the ancestors +must be the same. + +case ancest head remote result +---------------------------------------- +1 (empty)+ (empty) (empty) (empty) +2ALT (empty)+ *empty* remote remote +2 (empty)^ (empty) remote no merge +3ALT (empty)+ head *empty* head +3 (empty)^ head (empty) no merge +4 (empty)^ head remote no merge +5ALT * head head head +6 ancest+ (empty) (empty) no merge +8 ancest^ (empty) ancest no merge +7 ancest+ (empty) remote no merge +10 ancest^ ancest (empty) no merge +9 ancest+ head (empty) no merge +16 anc1/anc2 anc1 anc2 no merge +13 ancest+ head ancest head +14 ancest+ ancest remote remote +11 ancest+ head remote no merge + +Only #2ALT and #3ALT use *empty*, because these are the only cases +where there can be conflicts that didn't exist before. Note that we +allow directory-file conflicts between things in different stages +after the trivial merge. + +A possible alternative for #6 is (empty), which would make it like +#1. This is not used, due to the likelihood that it arises due to +moving the file to multiple different locations or moving and deleting +it in different branches. + +Case #1 is included for completeness, and also in case we decide to +put on '+' markings; any path that is never mentioned at all isn't +handled. + +Note that #16 is when both #13 and #14 apply; in this case, we refuse +the trivial merge, because we can't tell from this data which is +right. This is a case of a reverted patch (in some direction, maybe +multiple times), and the right answer depends on looking at crossings +of history or common ancestors of the ancestors. + +Note that, between #6, #7, #9, and #11, all cases not otherwise +covered are handled in this table. + +For #8 and #10, there is alternative behavior, not currently +implemented, where the result is (empty). As currently implemented, +the automatic merge will generally give this effect. diff --git a/Documentation/tutorial-2.txt b/Documentation/tutorial-2.txt new file mode 100644 index 0000000000..af8d43bd12 --- /dev/null +++ b/Documentation/tutorial-2.txt @@ -0,0 +1,403 @@ +A tutorial introduction to git: part two +======================================== + +You should work through link:tutorial.html[A tutorial introduction to +git] before reading this tutorial. + +The goal of this tutorial is to introduce two fundamental pieces of +git's architecture--the object database and the index file--and to +provide the reader with everything necessary to understand the rest +of the git documentation. + +The git object database +----------------------- + +Let's start a new project and create a small amount of history: + +------------------------------------------------ +$ mkdir test-project +$ cd test-project +$ git init +Initialized empty Git repository in .git/ +$ echo 'hello world' > file.txt +$ git add . +$ git commit -a -m "initial commit" +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 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 +such a 40-digit hex name. That name is the SHA1 hash of the object's +contents; among other things, this ensures that git will never store +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. 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 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 +a file. In addition, a tree can also refer to other tree objects, +thus creating a directory hierarchy. You can examine the contents of +any tree using ls-tree (remember that a long enough initial portion +of the SHA1 will also work): + +------------------------------------------------ +$ git ls-tree 92b8b694 +100644 blob 3b18e512dba79e4c8300dd08aeb37f8e728b8dad file.txt +------------------------------------------------ + +Thus we see that this tree has one file in it. The SHA1 hash is a +reference to that file's data: + +------------------------------------------------ +$ git cat-file -t 3b18e512 +blob +------------------------------------------------ + +A "blob" is just file data, which we can also examine with cat-file: + +------------------------------------------------ +$ git cat-file blob 3b18e512 +hello world +------------------------------------------------ + +Note that this is the old file data; so the object that git named in +its response to the initial tree was a tree with a snapshot of the +directory state that was recorded by the first commit. + +All of these objects are stored under their SHA1 names inside the git +directory: + +------------------------------------------------ +$ find .git/objects/ +.git/objects/ +.git/objects/pack +.git/objects/info +.git/objects/3b +.git/objects/3b/18e512dba79e4c8300dd08aeb37f8e728b8dad +.git/objects/92 +.git/objects/92/b8b694ffb1675e5975148e1121810081dbdffe +.git/objects/54 +.git/objects/54/196cc2703dc165cbd373a65a4dcf22d50ae7f7 +.git/objects/a0 +.git/objects/a0/423896973644771497bdc03eb99d5281615b51 +.git/objects/d0 +.git/objects/d0/492b368b66bdabf2ac1fd8c92b39d3db916e59 +.git/objects/c4 +.git/objects/c4/d59f390b9cfd4318117afde11d601c1085f241 +------------------------------------------------ + +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. + +The simplest commit to find is the HEAD commit, which we can find +from .git/HEAD: + +------------------------------------------------ +$ cat .git/HEAD +ref: refs/heads/master +------------------------------------------------ + +As you can see, this tells us which branch we're currently on, and it +tells us this by naming a file under the .git directory, which itself +contains a SHA1 name referring to a commit object, which we can +examine with cat-file: + +------------------------------------------------ +$ cat .git/refs/heads/master +c4d59f390b9cfd4318117afde11d601c1085f241 +$ git cat-file -t c4d59f39 +commit +$ git cat-file commit c4d59f39 +tree d0492b368b66bdabf2ac1fd8c92b39d3db916e59 +parent 54196cc2703dc165cbd373a65a4dcf22d50ae7f7 +author J. Bruce Fields <bfields@puzzle.fieldses.org> 1143418702 -0500 +committer J. Bruce Fields <bfields@puzzle.fieldses.org> 1143418702 -0500 + +add emphasis +------------------------------------------------ + +The "tree" object here refers to the new state of the tree: + +------------------------------------------------ +$ git ls-tree d0492b36 +100644 blob a0423896973644771497bdc03eb99d5281615b51 file.txt +$ git cat-file blob a0423896 +hello world! +------------------------------------------------ + +and the "parent" object refers to the previous 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 +------------------------------------------------ + +The tree object is the tree we examined first, and this commit is +unusual in that it lacks any parent. + +Most commits have only one parent, but it is also common for a commit +to have multiple parents. In that case the commit represents a +merge, with the parent references pointing to the heads of the merged +branches. + +Besides blobs, trees, and commits, the only remaining type of object +is a "tag", which we won't discuss here; refer to gitlink:git-tag[1] +for details. + +So now we know how git uses the object database to represent a +project's history: + + * "commit" objects refer to "tree" objects representing the + snapshot of a directory tree at a particular point in the + history, and refer to "parent" commits to show how they're + connected into the project history. + * "tree" objects represent the state of a single directory, + associating directory names to "blob" objects containing file + data and "tree" objects containing subdirectory information. + * "blob" objects contain file data without any other structure. + * References to commit objects at the head of each branch are + stored in files under .git/refs/heads/. + * The name of the current branch is stored in .git/HEAD. + +Note, by the way, that lots of commands take a tree as an argument. +But as we can see above, a tree can be referred to in many different +ways--by the SHA1 name for that tree, by the name of a commit that +refers to the tree, by the name of a branch whose head refers to that +tree, etc.--and most such commands can accept any of these names. + +In command synopses, the word "tree-ish" is sometimes used to +designate such an argument. + +The index file +-------------- + +The primary tool we've been using to create commits is "git commit +-a", which creates a commit including every change you've made to +your working tree. But what if you want to commit changes only to +certain files? Or only certain changes to certain files? + +If we look at the way commits are created under the cover, we'll see +that there are more flexible ways creating commits. + +Continuing with our test-project, let's modify file.txt again: + +------------------------------------------------ +$ echo "hello world, again" >>file.txt +------------------------------------------------ + +but this time instead of immediately making the commit, let's take an +intermediate step, and ask for diffs along the way to keep track of +what's happening: + +------------------------------------------------ +$ git diff +--- a/file.txt ++++ b/file.txt +@@ -1 +1,2 @@ + hello world! ++hello world, again +$ git add file.txt +$ git diff +------------------------------------------------ + +The last diff is empty, but no new commits have been made, and the +head still doesn't contain the new line: + +------------------------------------------------ +$ git-diff HEAD +diff --git a/file.txt b/file.txt +index a042389..513feba 100644 +--- a/file.txt ++++ b/file.txt +@@ -1 +1,2 @@ + hello world! ++hello world, again +------------------------------------------------ + +So "git diff" is comparing against something other than the head. +The thing that it's comparing against is actually the index file, +which is stored in .git/index in a binary format, but whose contents +we can examine with ls-files: + +------------------------------------------------ +$ git ls-files --stage +100644 513feba2e53ebbd2532419ded848ba19de88ba00 0 file.txt +$ git cat-file -t 513feba2 +blob +$ git cat-file blob 513feba2 +hello world! +hello world, again +------------------------------------------------ + +So what our "git add" did was store a new blob and then put +a reference to it in the index file. If we modify the file again, +we'll see that the new modifications are reflected in the "git-diff" +output: + +------------------------------------------------ +$ echo 'again?' >>file.txt +$ git diff +index 513feba..ba3da7b 100644 +--- a/file.txt ++++ b/file.txt +@@ -1,2 +1,3 @@ + hello world! + hello world, again ++again? +------------------------------------------------ + +With the right arguments, git diff can also show us the difference +between the working directory and the last commit, or between the +index and the last commit: + +------------------------------------------------ +$ git diff HEAD +diff --git a/file.txt b/file.txt +index a042389..ba3da7b 100644 +--- a/file.txt ++++ b/file.txt +@@ -1 +1,3 @@ + hello world! ++hello world, again ++again? +$ git diff --cached +diff --git a/file.txt b/file.txt +index a042389..513feba 100644 +--- a/file.txt ++++ b/file.txt +@@ -1 +1,2 @@ + hello world! ++hello world, again +------------------------------------------------ + +At any time, we can create a new commit using "git commit" (without +the -a option), and verify that the state committed only includes the +changes stored in the index file, not the additional change that is +still only in our working tree: + +------------------------------------------------ +$ git commit -m "repeat" +$ git diff HEAD +diff --git a/file.txt b/file.txt +index 513feba..ba3da7b 100644 +--- a/file.txt ++++ b/file.txt +@@ -1,2 +1,3 @@ + hello world! + hello world, again ++again? +------------------------------------------------ + +So by default "git commit" uses the index to create the commit, not +the working tree; the -a option to commit tells it to first update +the index with all changes in the working tree. + +Finally, it's worth looking at the effect of "git add" on the index +file: + +------------------------------------------------ +$ echo "goodbye, world" >closing.txt +$ git add closing.txt +------------------------------------------------ + +The effect of the "git add" was to add one entry to the index file: + +------------------------------------------------ +$ git ls-files --stage +100644 8b9743b20d4b15be3955fc8d5cd2b09cd2336138 0 closing.txt +100644 513feba2e53ebbd2532419ded848ba19de88ba00 0 file.txt +------------------------------------------------ + +And, as you can see with cat-file, this new entry refers to the +current contents of the file: + +------------------------------------------------ +$ git cat-file blob 8b9743b2 +goodbye, world +------------------------------------------------ + +The "status" command is a useful way to get a quick summary of the +situation: + +------------------------------------------------ +$ git status +# On branch master +# Changes to be committed: +# (use "git reset HEAD <file>..." to unstage) +# +# new file: closing.txt +# +# Changed but not updated: +# (use "git add <file>..." to update what will be committed) +# +# modified: file.txt +# +------------------------------------------------ + +Since the current state of closing.txt is cached in the index file, +it is listed as "Changes to be 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 +commit" would create a commit that added closing.txt (with its new +contents), but that didn't modify file.txt. + +Also, note that a bare "git diff" shows the changes to file.txt, but +not the addition of closing.txt, because the version of closing.txt +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.html[core tutorial] and the relevant man +pages for details. + +What next? +---------- + +At this point you should know everything necessary to read the man +pages for any of the git commands; one good place to start would be +with the commands mentioned in link:everyday.html[Everyday git]. You +should be able to find any unknown jargon in the +link:glossary.html[Glossary]. + +The link:cvs-migration.html[CVS migration] document explains how to +import a CVS repository into git, and shows how to use git in a +CVS-like way. + +For some interesting examples of git use, see the +link:howto-index.html[howtos]. + +For git developers, the link:core-tutorial.html[Core tutorial] goes +into detail on the lower-level git mechanisms involved in, for +example, creating a new commit. diff --git a/Documentation/tutorial.txt b/Documentation/tutorial.txt new file mode 100644 index 0000000000..129c5c5f5b --- /dev/null +++ b/Documentation/tutorial.txt @@ -0,0 +1,584 @@ +A tutorial introduction to git +============================== + +This tutorial explains how to import a new project into git, make +changes to it, and share changes with other developers. + +First, note that you can get documentation for a command such as "git +diff" with: + +------------------------------------------------ +$ man git-diff +------------------------------------------------ + +It is a good idea to introduce yourself to git with your name and +public email address before doing any operation. The easiest +way to do so is: + +------------------------------------------------ +$ git config --global user.name "Your Name Comes Here" +$ git config --global user.email you@yourdomain.example.com +------------------------------------------------ + + +Importing a new project +----------------------- + +Assume you have a tarball project.tar.gz with your initial work. You +can place it under git revision control as follows. + +------------------------------------------------ +$ tar xzf project.tar.gz +$ cd project +$ git init +------------------------------------------------ + +Git will reply + +------------------------------------------------ +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 (note the '.') with: + +------------------------------------------------ +$ git add . +------------------------------------------------ + +Finally, + +------------------------------------------------ +$ 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, 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 +------------------------------------------------ + +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 +commit in the body. + + +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'. + + +Viewing the changelog +--------------------- + +At any point you can view the history of your changes using + +------------------------------------------------ +$ git log +------------------------------------------------ + +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 +----------------- + +A single git repository can maintain multiple branches of +development. To create a new branch named "experimental", use + +------------------------------------------------ +$ git branch experimental +------------------------------------------------ + +If you now run + +------------------------------------------------ +$ git branch +------------------------------------------------ + +you'll get a list of all existing branches: + +------------------------------------------------ + experimental +* master +------------------------------------------------ + +The "experimental" branch is the one you just created, and the +"master" branch is a default branch that was created for you +automatically. The asterisk marks the branch you are currently on; +type + +------------------------------------------------ +$ git checkout experimental +------------------------------------------------ + +to switch to the experimental branch. Now edit a file, commit the +change, and switch back to the master branch: + +------------------------------------------------ +(edit file) +$ git commit -a +$ git checkout master +------------------------------------------------ + +Check that the change you made is no longer visible, since it was +made on the experimental branch and you're back on the master branch. + +You can make a different change on the master branch: + +------------------------------------------------ +(edit file) +$ git commit -a +------------------------------------------------ + +at this point the two branches have diverged, with different changes +made in each. To merge the changes made in experimental into master, run + +------------------------------------------------ +$ git merge experimental +------------------------------------------------ + +If the changes don't conflict, you're done. If there are conflicts, +markers will be left in the problematic files showing the conflict; + +------------------------------------------------ +$ git diff +------------------------------------------------ + +will show this. Once you've edited the files to resolve the +conflicts, + +------------------------------------------------ +$ git commit -a +------------------------------------------------ + +will commit the result of the merge. Finally, + +------------------------------------------------ +$ 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 + +------------------------------------- +$ git branch -D crazy-idea +------------------------------------- + +Branches are cheap and easy, so this is a good way to try something +out. + +Using git for collaboration +--------------------------- + +Suppose that Alice has started a new project with a git repository in +/home/alice/project, and that Bob, who has a home directory on the +same machine, wants to contribute. + +Bob begins with: + +------------------------------------------------ +$ git clone /home/alice/project myrepo +------------------------------------------------ + +This creates a new directory "myrepo" containing a clone of Alice's +repository. The clone is on an equal footing with the original +project, possessing its own copy of the original project's history. + +Bob then makes some changes and commits them: + +------------------------------------------------ +(edit files) +$ git commit -a +(repeat as necessary) +------------------------------------------------ + +When he's ready, he tells Alice to pull changes from the repository +at /home/bob/myrepo. She does this with: + +------------------------------------------------ +$ cd /home/alice/project +$ git pull /home/bob/myrepo master +------------------------------------------------ + +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.) + +The "pull" command thus performs two operations: it fetches changes +from a remote branch, then merges them into the current branch. + +When you are working in a small closely knit group, it is not +unusual to interact with the same repository over and over +again. By defining 'remote' repository shorthand, you can make +it easier: + +------------------------------------------------ +$ git remote add bob /home/bob/myrepo +------------------------------------------------ + +With this, you can perform the first operation alone using the +"git fetch" command without merging them with her own branch, +using: + +------------------------------------- +$ git fetch bob +------------------------------------- + +Unlike the longhand form, when Alice fetches from Bob using a +remote repository shorthand set up with `git remote`, what was +fetched is stored in a remote tracking branch, in this case +`bob/master`. So after this: + +------------------------------------- +$ git log -p master..bob/master +------------------------------------- + +shows a list of all the changes that Bob made since he branched from +Alice's master branch. + +After examining those changes, Alice +could merge the changes into her master branch: + +------------------------------------- +$ git merge bob/master +------------------------------------- + +This `merge` can also be done by 'pulling from her own remote +tracking branch', like this: + +------------------------------------- +$ git pull . remotes/bob/master +------------------------------------- + +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 + +------------------------------------- +$ 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 repository configuration, and that location is +used for pulls: + +------------------------------------- +$ git config --get remote.origin.url +/home/bob/myrepo +------------------------------------- + +(The complete configuration created by git-clone is visible using +"git config -l", and the gitlink:git-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: + +------------------------------------- +$ git clone alice.org:/home/alice/project myrepo +------------------------------------- + +Alternatively, git has a native protocol, or can use rsync or http; +see gitlink:git-pull[1] for details. + +Git can also be used in a CVS-like mode, with a central repository +that various users push changes to; see gitlink:git-push[1] and +link:cvs-migration.html[git for CVS users]. + +Exploring history +----------------- + +Git history is represented as a series of interrelated commits. We +have already seen that the git log command can list those commits. +Note that first line of each git log entry also gives a name for the +commit: + +------------------------------------- +$ git log +commit c82a22c39cbc32576f64f5c6b3f24b99ea8149c7 +Author: Junio C Hamano <junkio@cox.net> +Date: Tue May 16 17:18:22 2006 -0700 + + merge-base: Clarify the comments on post processing. +------------------------------------- + +We can give this name to git show to see the details about this +commit. + +------------------------------------- +$ git show c82a22c39cbc32576f64f5c6b3f24b99ea8149c7 +------------------------------------- + +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: + +------------------------------------- +$ git show c82a22c39c # the first few characters of the name are + # usually enough +$ git show HEAD # the tip of the current branch +$ git show experimental # the tip of the "experimental" branch +------------------------------------- + +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 +$ git show HEAD^^ # to see the grandparent of HEAD +$ git show HEAD~4 # to see the great-great grandparent of HEAD +------------------------------------- + +Note that merge commits may have more than one parent: + +------------------------------------- +$ git show HEAD^1 # show the first parent of HEAD (same as HEAD^) +$ git show HEAD^2 # show the second parent of HEAD +------------------------------------- + +You can also give commits names of your own; after running + +------------------------------------- +$ git-tag v2.5 1b2e1d63ff +------------------------------------- + +you can refer to 1b2e1d63ff by the name "v2.5". If you intend to +share this name with other people (for example, to identify a release +version), you should create a "tag" object, and perhaps sign it; see +gitlink:git-tag[1] for details. + +Any git command that needs to know a commit can take any of these +names. For example: + +------------------------------------- +$ git diff v2.5 HEAD # compare the current HEAD to v2.5 +$ git branch stable v2.5 # start a new branch named "stable" based + # at v2.5 +$ git reset --hard HEAD^ # reset your current branch and working + # directory to its state at HEAD^ +------------------------------------- + +Be careful with that last command: in addition to losing any changes +in the working directory, it will also remove all later commits from +this branch. If this branch is the only branch containing those +commits, they will be lost. Also, don't use "git reset" on a +publicly-visible branch that other developers pull from, as it will +force needless merges on other developers to clean up the history. +If you need to undo changes that you have pushed, use gitlink:git-revert[1] +instead. + +The git grep command can search for strings in any version of your +project, so + +------------------------------------- +$ git grep "hello" v2.5 +------------------------------------- + +searches for all occurrences of "hello" in v2.5. + +If you leave out the commit name, git grep will search any of the +files it manages in your current directory. So + +------------------------------------- +$ git grep "hello" +------------------------------------- + +is a quick way to search just the files that are tracked by git. + +Many git commands also take sets of commits, which can be specified +in a number of ways. Here are some examples with git log: + +------------------------------------- +$ git log v2.5..v2.6 # commits between v2.5 and v2.6 +$ git log v2.5.. # commits since v2.5 +$ git log --since="2 weeks ago" # commits from the last 2 weeks +$ git log v2.5.. Makefile # commits since v2.5 which modify + # Makefile +------------------------------------- + +You can also give git log a "range" of commits where the first is not +necessarily an ancestor of the second; for example, if the tips of +the branches "stable-release" and "master" diverged from a common +commit some time ago, then + +------------------------------------- +$ git log stable..experimental +------------------------------------- + +will list commits made in the experimental branch but not in the +stable branch, while + +------------------------------------- +$ git log experimental..stable +------------------------------------- + +will show the list of commits made on the stable branch but not +the experimental branch. + +The "git log" command has a weakness: it must present commits in a +list. When the history has lines of development that diverged and +then merged back together, the order in which "git log" presents +those commits is meaningless. + +Most projects with multiple contributors (such as the linux kernel, +or git itself) have frequent merges, and gitk does a better job of +visualizing their history. For example, + +------------------------------------- +$ gitk --since="2 weeks ago" drivers/ +------------------------------------- + +allows you to browse any commits from the last 2 weeks of commits +that modified files under the "drivers" directory. (Note: you can +adjust gitk's fonts by holding down the control key while pressing +"-" or "+".) + +Finally, most commands that take filenames will optionally allow you +to precede any filename by a commit, to specify a particular version +of the file: + +------------------------------------- +$ git diff v2.5:Makefile HEAD:Makefile.in +------------------------------------- + +You can also use "git show" to see any such file: + +------------------------------------- +$ git show v2.5:Makefile +------------------------------------- + +Next Steps +---------- + +This tutorial should be enough to perform basic distributed revision +control for your projects. However, to fully understand the depth +and power of git you need to understand two simple ideas on which it +is based: + + * The object database is the rather elegant system used to + store the history of your project--files, directories, and + commits. + + * The index file is a cache of the state of a directory tree, + used to create commits, check out working directories, and + hold the various trees involved in a merge. + +link:tutorial-2.html[Part two of this tutorial] explains the object +database, the index file, and a few other odds and ends that you'll +need to make the most of git. + +If you don't want to consider with that right away, a few other +digressions that may be interesting at this point are: + + * gitlink:git-format-patch[1], gitlink:git-am[1]: These convert + series of git commits into emailed patches, and vice versa, + useful for projects such as the linux kernel which rely heavily + on emailed patches. + + * gitlink:git-bisect[1]: When there is a regression in your + project, one way to track down the bug is by searching through + the history to find the exact commit that's to blame. Git bisect + can help you perform a binary search for that commit. It is + smart enough to perform a close-to-optimal search even in the + case of complex non-linear history with lots of merged branches. + + * link:everyday.html[Everyday GIT with 20 Commands Or So] + + * link:cvs-migration.html[git for CVS users]. diff --git a/Documentation/urls.txt b/Documentation/urls.txt new file mode 100644 index 0000000000..745f9677d0 --- /dev/null +++ b/Documentation/urls.txt @@ -0,0 +1,88 @@ +GIT URLS[[URLS]] +---------------- + +One of the following notations can be used +to name the remote repository: + +=============================================================== +- rsync://host.xz/path/to/repo.git/ +- http://host.xz/path/to/repo.git/ +- https://host.xz/path/to/repo.git/ +- git://host.xz/path/to/repo.git/ +- git://host.xz/~user/path/to/repo.git/ +- ssh://{startsb}user@{endsb}host.xz/path/to/repo.git/ +- ssh://{startsb}user@{endsb}host.xz/~user/path/to/repo.git/ +- ssh://{startsb}user@{endsb}host.xz/~/path/to/repo.git +=============================================================== + +SSH is the default transport protocol. You can optionally specify +which user to log-in as, and an alternate, scp-like syntax is also +supported. Both syntaxes support username expansion, +as does the native git protocol. The following three are +identical to the last three above, respectively: + +=============================================================== +- {startsb}user@{endsb}host.xz:/path/to/repo.git/ +- {startsb}user@{endsb}host.xz:~user/path/to/repo.git/ +- {startsb}user@{endsb}host.xz:path/to/repo.git +=============================================================== + +To sync with a local directory, use: + +=============================================================== +- /path/to/repo.git/ +=============================================================== + +REMOTES +------- + +In addition to the above, as a short-hand, the name of a +file in `$GIT_DIR/remotes` directory can be given; the +named file should be in the following format: + +------------ + URL: one of the above URL format + Push: <refspec> + Pull: <refspec> + +------------ + +Then such a short-hand is specified in place of +<repository> without <refspec> parameters on the command +line, <refspec> specified on `Push:` lines or `Pull:` +lines are used for `git-push` and `git-fetch`/`git-pull`, +respectively. Multiple `Push:` and `Pull:` lines may +be specified for additional branch mappings. + +Or, equivalently, in the `$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 `$GIT_DIR/branches` directory can be +specified as an older notation short-hand; the named +file should contain a single line, a URL in one of the +above formats, optionally followed by a hash `#` and the +name of remote head (URL fragment notation). +`$GIT_DIR/branches/<remote>` file that stores a <url> +without the fragment is equivalent to have this in the +corresponding file in the `$GIT_DIR/remotes/` directory. + +------------ + URL: <url> + Pull: refs/heads/master:<remote> + +------------ + +while having `<url>#<head>` is equivalent to + +------------ + URL: <url> + Pull: refs/heads/<head>:<remote> +------------ diff --git a/Documentation/user-manual.conf b/Documentation/user-manual.conf new file mode 100644 index 0000000000..92b01ecf71 --- /dev/null +++ b/Documentation/user-manual.conf @@ -0,0 +1,21 @@ +[titles] + underlines="__","==","--","~~","^^" + +[attributes] +caret=^ +startsb=[ +endsb=] +tilde=~ + +[gitlink-inlinemacro] +<ulink url="{target}.html">{target}{0?({0})}</ulink> + +ifdef::backend-docbook[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout> +{title#}</example> +endif::backend-docbook[] diff --git a/Documentation/user-manual.txt b/Documentation/user-manual.txt new file mode 100644 index 0000000000..d7b227e647 --- /dev/null +++ b/Documentation/user-manual.txt @@ -0,0 +1,3071 @@ +Git User's Manual +_________________ + +This manual is designed to be readable by someone with basic unix +command-line skills, but no previous knowledge of git. + +Chapter 1 gives a brief overview of git commands, without any +explanation; you may prefer to skip to chapter 2 on a first reading. + +Chapters 2 and 3 explain how to fetch and study a project using +git--the tools you'd need to build and test a particular version of a +software project, to search for regressions, and so on. + +Chapter 4 explains how to do development with git, and chapter 5 how +to share that development with others. + +Further chapters cover more specialized topics. + +Comprehensive reference documentation is available through the man +pages. For a command such as "git clone", just use + +------------------------------------------------ +$ man git-clone +------------------------------------------------ + +Git Quick Start +=============== + +This is a quick summary of the major commands; the following chapters +will explain how these work in more detail. + +Creating a new repository +------------------------- + +From a tarball: + +----------------------------------------------- +$ tar xzf project.tar.gz +$ cd project +$ git init +Initialized empty Git repository in .git/ +$ git add . +$ git commit +----------------------------------------------- + +From a remote repository: + +----------------------------------------------- +$ git clone git://example.com/pub/project.git +$ cd project +----------------------------------------------- + +Managing branches +----------------- + +----------------------------------------------- +$ git branch # list all branches in this repo +$ git checkout test # switch working directory to branch "test" +$ git branch new # create branch "new" starting at current HEAD +$ git branch -d new # delete branch "new" +----------------------------------------------- + +Instead of basing new branch on current HEAD (the default), use: + +----------------------------------------------- +$ git branch new test # branch named "test" +$ git branch new v2.6.15 # tag named v2.6.15 +$ git branch new HEAD^ # commit before the most recent +$ git branch new HEAD^^ # commit before that +$ git branch new test~10 # ten commits before tip of branch "test" +----------------------------------------------- + +Create and switch to a new branch at the same time: + +----------------------------------------------- +$ git checkout -b new v2.6.15 +----------------------------------------------- + +Update and examine branches from the repository you cloned from: + +----------------------------------------------- +$ git fetch # update +$ git branch -r # list + origin/master + origin/next + ... +$ git branch checkout -b masterwork origin/master +----------------------------------------------- + +Fetch a branch from a different repository, and give it a new +name in your repository: + +----------------------------------------------- +$ git fetch git://example.com/project.git theirbranch:mybranch +$ git fetch git://example.com/project.git v2.6.15:mybranch +----------------------------------------------- + +Keep a list of repositories you work with regularly: + +----------------------------------------------- +$ git remote add example git://example.com/project.git +$ git remote # list remote repositories +example +origin +$ git remote show example # get details +* remote example + URL: git://example.com/project.git + Tracked remote branches + master next ... +$ git fetch example # update branches from example +$ git branch -r # list all remote branches +----------------------------------------------- + + +Exploring history +----------------- + +----------------------------------------------- +$ gitk # visualize and browse history +$ git log # list all commits +$ git log src/ # ...modifying src/ +$ git log v2.6.15..v2.6.16 # ...in v2.6.16, not in v2.6.15 +$ git log master..test # ...in branch test, not in branch master +$ git log test..master # ...in branch master, but not in test +$ git log test...master # ...in one branch, not in both +$ git log -S'foo()' # ...where difference contain "foo()" +$ git log --since="2 weeks ago" +$ git log -p # show patches as well +$ git show # most recent commit +$ git diff v2.6.15..v2.6.16 # diff between two tagged versions +$ git diff v2.6.15..HEAD # diff with current head +$ git grep "foo()" # search working directory for "foo()" +$ git grep v2.6.15 "foo()" # search old tree for "foo()" +$ git show v2.6.15:a.txt # look at old version of a.txt +----------------------------------------------- + +Search for regressions: + +----------------------------------------------- +$ git bisect start +$ git bisect bad # current version is bad +$ git bisect good v2.6.13-rc2 # last known good revision +Bisecting: 675 revisions left to test after this + # test here, then: +$ git bisect good # if this revision is good, or +$ git bisect bad # if this revision is bad. + # repeat until done. +----------------------------------------------- + +Making changes +-------------- + +Make sure git knows who to blame: + +------------------------------------------------ +$ cat >~/.gitconfig <<\EOF +[user] +name = Your Name Comes Here +email = you@yourdomain.example.com +EOF +------------------------------------------------ + +Select file contents to include in the next commit, then make the +commit: + +----------------------------------------------- +$ git add a.txt # updated file +$ git add b.txt # new file +$ git rm c.txt # old file +$ git commit +----------------------------------------------- + +Or, prepare and create the commit in one step: + +----------------------------------------------- +$ git commit d.txt # use latest content only of d.txt +$ git commit -a # use latest content of all tracked files +----------------------------------------------- + +Merging +------- + +----------------------------------------------- +$ git merge test # merge branch "test" into the current branch +$ git pull git://example.com/project.git master + # fetch and merge in remote branch +$ git pull . test # equivalent to git merge test +----------------------------------------------- + +Sharing your changes +-------------------- + +Importing or exporting patches: + +----------------------------------------------- +$ git format-patch origin..HEAD # format a patch for each commit + # in HEAD but not in origin +$ git-am mbox # import patches from the mailbox "mbox" +----------------------------------------------- + +Fetch a branch in a different git repository, then merge into the +current branch: + +----------------------------------------------- +$ git pull git://example.com/project.git theirbranch +----------------------------------------------- + +Store the fetched branch into a local branch before merging into the +current branch: + +----------------------------------------------- +$ git pull git://example.com/project.git theirbranch:mybranch +----------------------------------------------- + +After creating commits on a local branch, update the remote +branch with your commits: + +----------------------------------------------- +$ git push ssh://example.com/project.git mybranch:theirbranch +----------------------------------------------- + +When remote and local branch are both named "test": + +----------------------------------------------- +$ git push ssh://example.com/project.git test +----------------------------------------------- + +Shortcut version for a frequently used remote repository: + +----------------------------------------------- +$ git remote add example ssh://example.com/project.git +$ git push example test +----------------------------------------------- + +Repository maintenance +---------------------- + +Check for corruption: + +----------------------------------------------- +$ git fsck +----------------------------------------------- + +Recompress, remove unused cruft: + +----------------------------------------------- +$ git gc +----------------------------------------------- + +Repositories and Branches +========================= + +How to get a git repository +--------------------------- + +It will be useful to have a git repository to experiment with as you +read this manual. + +The best way to get one is by using the gitlink:git-clone[1] command +to download a copy of an existing repository for a project that you +are interested in. If you don't already have a project in mind, here +are some interesting examples: + +------------------------------------------------ + # git itself (approx. 10MB download): +$ git clone git://git.kernel.org/pub/scm/git/git.git + # the linux kernel (approx. 150MB download): +$ git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git +------------------------------------------------ + +The initial clone may be time-consuming for a large project, but you +will only need to clone once. + +The clone command creates a new directory named after the project +("git" or "linux-2.6" in the examples above). After you cd into this +directory, you will see that it contains a copy of the project files, +together with a special top-level directory named ".git", which +contains all the information about the history of the project. + +In most of the following, examples will be taken from one of the two +repositories above. + +How to check out a different version of a project +------------------------------------------------- + +Git is best thought of as a tool for storing the history of a +collection of files. It stores the history as a compressed +collection of interrelated snapshots (versions) of the project's +contents. + +A single git repository may contain multiple branches. Each branch +is a bookmark referencing a particular point in the project history. +The gitlink:git-branch[1] command shows you the list of branches: + +------------------------------------------------ +$ git branch +* master +------------------------------------------------ + +A freshly cloned repository contains a single branch, named "master", +and the working directory contains the version of the project +referred to by the master branch. + +Most projects also use tags. Tags, like branches, are references +into the project's history, and can be listed using the +gitlink:git-tag[1] command: + +------------------------------------------------ +$ git tag -l +v2.6.11 +v2.6.11-tree +v2.6.12 +v2.6.12-rc2 +v2.6.12-rc3 +v2.6.12-rc4 +v2.6.12-rc5 +v2.6.12-rc6 +v2.6.13 +... +------------------------------------------------ + +Tags are expected to always point at the same version of a project, +while branches are expected to advance as development progresses. + +Create a new branch pointing to one of these versions and check it +out using gitlink:git-checkout[1]: + +------------------------------------------------ +$ git checkout -b new v2.6.13 +------------------------------------------------ + +The working directory then reflects the contents that the project had +when it was tagged v2.6.13, and gitlink:git-branch[1] shows two +branches, with an asterisk marking the currently checked-out branch: + +------------------------------------------------ +$ git branch + master +* new +------------------------------------------------ + +If you decide that you'd rather see version 2.6.17, you can modify +the current branch to point at v2.6.17 instead, with + +------------------------------------------------ +$ git reset --hard v2.6.17 +------------------------------------------------ + +Note that if the current branch was your only reference to a +particular point in history, then resetting that branch may leave you +with no way to find the history it used to point to; so use this +command carefully. + +Understanding History: Commits +------------------------------ + +Every change in the history of a project is represented by a commit. +The gitlink:git-show[1] command shows the most recent commit on the +current branch: + +------------------------------------------------ +$ git show +commit 2b5f6dcce5bf94b9b119e9ed8d537098ec61c3d2 +Author: Jamal Hadi Salim <hadi@cyberus.ca> +Date: Sat Dec 2 22:22:25 2006 -0800 + + [XFRM]: Fix aevent structuring to be more complete. + + aevents can not uniquely identify an SA. We break the ABI with this + patch, but consensus is that since it is not yet utilized by any + (known) application then it is fine (better do it now than later). + + Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> + Signed-off-by: David S. Miller <davem@davemloft.net> + +diff --git a/Documentation/networking/xfrm_sync.txt b/Documentation/networking/xfrm_sync.txt +index 8be626f..d7aac9d 100644 +--- a/Documentation/networking/xfrm_sync.txt ++++ b/Documentation/networking/xfrm_sync.txt +@@ -47,10 +47,13 @@ aevent_id structure looks like: + + struct xfrm_aevent_id { + struct xfrm_usersa_id sa_id; ++ xfrm_address_t saddr; + __u32 flags; ++ __u32 reqid; + }; +... +------------------------------------------------ + +As you can see, a commit shows who made the latest change, what they +did, and why. + +Every commit has a 40-hexdigit id, sometimes called the "object name" or the +"SHA1 id", shown on the first line of the "git show" output. You can usually +refer to a commit by a shorter name, such as a tag or a branch name, but this +longer name can also be useful. Most importantly, it is a globally unique +name for this commit: so if you tell somebody else the object name (for +example in email), then you are guaranteed that name will refer to the same +commit in their repository that it does in yours (assuming their repository +has that commit at all). Since the object name is computed as a hash over the +contents of the commit, you are guaranteed that the commit can never change +without its name also changing. + +In fact, in <<git-internals>> we shall see that everything stored in git +history, including file data and directory contents, is stored in an object +with a name that is a hash of its contents. + +Understanding history: commits, parents, and reachability +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Every commit (except the very first commit in a project) also has a +parent commit which shows what happened before this commit. +Following the chain of parents will eventually take you back to the +beginning of the project. + +However, the commits do not form a simple list; git allows lines of +development to diverge and then reconverge, and the point where two +lines of development reconverge is called a "merge". The commit +representing a merge can therefore have more than one parent, with +each parent representing the most recent commit on one of the lines +of development leading to that point. + +The best way to see how this works is using the gitlink:gitk[1] +command; running gitk now on a git repository and looking for merge +commits will help understand how the git organizes history. + +In the following, we say that commit X is "reachable" from commit Y +if commit X is an ancestor of commit Y. Equivalently, you could say +that Y is a descendent of X, or that there is a chain of parents +leading from commit Y to commit X. + +Understanding history: History diagrams +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +We will sometimes represent git history using diagrams like the one +below. Commits are shown as "o", and the links between them with +lines drawn with - / and \. Time goes left to right: + + +................................................ + o--o--o <-- Branch A + / + o--o--o <-- master + \ + o--o--o <-- Branch B +................................................ + +If we need to talk about a particular commit, the character "o" may +be replaced with another letter or number. + +Understanding history: What is a branch? +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Though we've been using the word "branch" to mean a kind of reference +to a particular commit, the word branch is also commonly used to +refer to the line of commits leading up to that point. In the +example above, git may think of the branch named "A" as just a +pointer to one particular commit, but we may refer informally to the +line of three commits leading up to that point as all being part of +"branch A". + +If we need to make it clear that we're just talking about the most +recent commit on the branch, we may refer to that commit as the +"head" of the branch. + +Manipulating branches +--------------------- + +Creating, deleting, and modifying branches is quick and easy; here's +a summary of the commands: + +git branch:: + list all branches +git branch <branch>:: + create a new branch named <branch>, referencing the same + point in history as the current branch +git branch <branch> <start-point>:: + create a new branch named <branch>, referencing + <start-point>, which may be specified any way you like, + including using a branch name or a tag name +git branch -d <branch>:: + delete the branch <branch>; if the branch you are deleting + points to a commit which is not reachable from this branch, + this command will fail with a warning. +git branch -D <branch>:: + even if the branch points to a commit not reachable + from the current branch, you may know that that commit + is still reachable from some other branch or tag. In that + case it is safe to use this command to force git to delete + the branch. +git checkout <branch>:: + make the current branch <branch>, updating the working + directory to reflect the version referenced by <branch> +git checkout -b <new> <start-point>:: + create a new branch <new> referencing <start-point>, and + check it out. + +It is also useful to know that the special symbol "HEAD" can always +be used to refer to the current branch. + +Examining branches from a remote repository +------------------------------------------- + +The "master" branch that was created at the time you cloned is a copy +of the HEAD in the repository that you cloned from. That repository +may also have had other branches, though, and your local repository +keeps branches which track each of those remote branches, which you +can view using the "-r" option to gitlink:git-branch[1]: + +------------------------------------------------ +$ git branch -r + origin/HEAD + origin/html + origin/maint + origin/man + origin/master + origin/next + origin/pu + origin/todo +------------------------------------------------ + +You cannot check out these remote-tracking branches, but you can +examine them on a branch of your own, just as you would a tag: + +------------------------------------------------ +$ git checkout -b my-todo-copy origin/todo +------------------------------------------------ + +Note that the name "origin" is just the name that git uses by default +to refer to the repository that you cloned from. + +[[how-git-stores-references]] +Naming branches, tags, and other references +------------------------------------------- + +Branches, remote-tracking branches, and tags are all references to +commits. All references are named with a slash-separated path name +starting with "refs"; the names we've been using so far are actually +shorthand: + + - The branch "test" is short for "refs/heads/test". + - The tag "v2.6.18" is short for "refs/tags/v2.6.18". + - "origin/master" is short for "refs/remotes/origin/master". + +The full name is occasionally useful if, for example, there ever +exists a tag and a branch with the same name. + +As another useful shortcut, if the repository "origin" posesses only +a single branch, you can refer to that branch as just "origin". + +More generally, if you have defined a remote repository named +"example", you can refer to the branch in that repository as +"example". And for a repository with multiple branches, this will +refer to the branch designated as the "HEAD" branch. + +For the complete list of paths which git checks for references, and +the order it uses to decide which to choose when there are multiple +references with the same shorthand name, see the "SPECIFYING +REVISIONS" section of gitlink:git-rev-parse[1]. + +[[Updating-a-repository-with-git-fetch]] +Updating a repository with git fetch +------------------------------------ + +Eventually the developer cloned from will do additional work in her +repository, creating new commits and advancing the branches to point +at the new commits. + +The command "git fetch", with no arguments, will update all of the +remote-tracking branches to the latest version found in her +repository. It will not touch any of your own branches--not even the +"master" branch that was created for you on clone. + +Fetching branches from other repositories +----------------------------------------- + +You can also track branches from repositories other than the one you +cloned from, using gitlink:git-remote[1]: + +------------------------------------------------- +$ git remote add linux-nfs git://linux-nfs.org/pub/nfs-2.6.git +$ git fetch +* refs/remotes/linux-nfs/master: storing branch 'master' ... + commit: bf81b46 +------------------------------------------------- + +New remote-tracking branches will be stored under the shorthand name +that you gave "git remote add", in this case linux-nfs: + +------------------------------------------------- +$ git branch -r +linux-nfs/master +origin/master +------------------------------------------------- + +If you run "git fetch <remote>" later, the tracking branches for the +named <remote> will be updated. + +If you examine the file .git/config, you will see that git has added +a new stanza: + +------------------------------------------------- +$ cat .git/config +... +[remote "linux-nfs"] + url = git://linux-nfs.org/pub/nfs-2.6.git + fetch = +refs/heads/*:refs/remotes/linux-nfs/* +... +------------------------------------------------- + +This is what causes git to track the remote's branches; you may modify +or delete these configuration options by editing .git/config with a +text editor. (See the "CONFIGURATION FILE" section of +gitlink:git-config[1] for details.) + +Exploring git history +===================== + +Git is best thought of as a tool for storing the history of a +collection of files. It does this by storing compressed snapshots of +the contents of a file heirarchy, together with "commits" which show +the relationships between these snapshots. + +Git provides extremely flexible and fast tools for exploring the +history of a project. + +We start with one specialized tool that is useful for finding the +commit that introduced a bug into a project. + +How to use bisect to find a regression +-------------------------------------- + +Suppose version 2.6.18 of your project worked, but the version at +"master" crashes. Sometimes the best way to find the cause of such a +regression is to perform a brute-force search through the project's +history to find the particular commit that caused the problem. The +gitlink:git-bisect[1] command can help you do this: + +------------------------------------------------- +$ git bisect start +$ git bisect good v2.6.18 +$ git bisect bad master +Bisecting: 3537 revisions left to test after this +[65934a9a028b88e83e2b0f8b36618fe503349f8e] BLOCK: Make USB storage depend on SCSI rather than selecting it [try #6] +------------------------------------------------- + +If you run "git branch" at this point, you'll see that git has +temporarily moved you to a new branch named "bisect". This branch +points to a commit (with commit id 65934...) that is reachable from +v2.6.19 but not from v2.6.18. Compile and test it, and see whether +it crashes. Assume it does crash. Then: + +------------------------------------------------- +$ git bisect bad +Bisecting: 1769 revisions left to test after this +[7eff82c8b1511017ae605f0c99ac275a7e21b867] i2c-core: Drop useless bitmaskings +------------------------------------------------- + +checks out an older version. Continue like this, telling git at each +stage whether the version it gives you is good or bad, and notice +that the number of revisions left to test is cut approximately in +half each time. + +After about 13 tests (in this case), it will output the commit id of +the guilty commit. You can then examine the commit with +gitlink:git-show[1], find out who wrote it, and mail them your bug +report with the commit id. Finally, run + +------------------------------------------------- +$ git bisect reset +------------------------------------------------- + +to return you to the branch you were on before and delete the +temporary "bisect" branch. + +Note that the version which git-bisect checks out for you at each +point is just a suggestion, and you're free to try a different +version if you think it would be a good idea. For example, +occasionally you may land on a commit that broke something unrelated; +run + +------------------------------------------------- +$ git bisect-visualize +------------------------------------------------- + +which will run gitk and label the commit it chose with a marker that +says "bisect". Chose a safe-looking commit nearby, note its commit +id, and check it out with: + +------------------------------------------------- +$ git reset --hard fb47ddb2db... +------------------------------------------------- + +then test, run "bisect good" or "bisect bad" as appropriate, and +continue. + +Naming commits +-------------- + +We have seen several ways of naming commits already: + + - 40-hexdigit object name + - branch name: refers to the commit at the head of the given + branch + - tag name: refers to the commit pointed to by the given tag + (we've seen branches and tags are special cases of + <<how-git-stores-references,references>>). + - HEAD: refers to the head of the current branch + +There are many more; see the "SPECIFYING REVISIONS" section of the +gitlink:git-rev-parse[1] man page for the complete list of ways to +name revisions. Some examples: + +------------------------------------------------- +$ git show fb47ddb2 # the first few characters of the object name + # are usually enough to specify it uniquely +$ git show HEAD^ # the parent of the HEAD commit +$ git show HEAD^^ # the grandparent +$ git show HEAD~4 # the great-great-grandparent +------------------------------------------------- + +Recall that merge commits may have more than one parent; by default, +^ and ~ follow the first parent listed in the commit, but you can +also choose: + +------------------------------------------------- +$ git show HEAD^1 # show the first parent of HEAD +$ git show HEAD^2 # show the second parent of HEAD +------------------------------------------------- + +In addition to HEAD, there are several other special names for +commits: + +Merges (to be discussed later), as well as operations such as +git-reset, which change the currently checked-out commit, generally +set ORIG_HEAD to the value HEAD had before the current operation. + +The git-fetch operation always stores the head of the last fetched +branch in FETCH_HEAD. For example, if you run git fetch without +specifying a local branch as the target of the operation + +------------------------------------------------- +$ git fetch git://example.com/proj.git theirbranch +------------------------------------------------- + +the fetched commits will still be available from FETCH_HEAD. + +When we discuss merges we'll also see the special name MERGE_HEAD, +which refers to the other branch that we're merging in to the current +branch. + +The gitlink:git-rev-parse[1] command is a low-level command that is +occasionally useful for translating some name for a commit to the object +name for that commit: + +------------------------------------------------- +$ git rev-parse origin +e05db0fd4f31dde7005f075a84f96b360d05984b +------------------------------------------------- + +Creating tags +------------- + +We can also create a tag to refer to a particular commit; after +running + +------------------------------------------------- +$ git-tag stable-1 1b2e1d63ff +------------------------------------------------- + +You can use stable-1 to refer to the commit 1b2e1d63ff. + +This creates a "lightweight" tag. If the tag is a tag you wish to +share with others, and possibly sign cryptographically, then you +should create a tag object instead; see the gitlink:git-tag[1] man +page for details. + +Browsing revisions +------------------ + +The gitlink:git-log[1] command can show lists of commits. On its +own, it shows all commits reachable from the parent commit; but you +can also make more specific requests: + +------------------------------------------------- +$ git log v2.5.. # commits since (not reachable from) v2.5 +$ git log test..master # commits reachable from master but not test +$ git log master..test # ...reachable from test but not master +$ git log master...test # ...reachable from either test or master, + # but not both +$ git log --since="2 weeks ago" # commits from the last 2 weeks +$ git log Makefile # commits which modify Makefile +$ git log fs/ # ... which modify any file under fs/ +$ git log -S'foo()' # commits which add or remove any file data + # matching the string 'foo()' +------------------------------------------------- + +And of course you can combine all of these; the following finds +commits since v2.5 which touch the Makefile or any file under fs: + +------------------------------------------------- +$ git log v2.5.. Makefile fs/ +------------------------------------------------- + +You can also ask git log to show patches: + +------------------------------------------------- +$ git log -p +------------------------------------------------- + +See the "--pretty" option in the gitlink:git-log[1] man page for more +display options. + +Note that git log starts with the most recent commit and works +backwards through the parents; however, since git history can contain +multiple independent lines of development, the particular order that +commits are listed in may be somewhat arbitrary. + +Generating diffs +---------------- + +You can generate diffs between any two versions using +gitlink:git-diff[1]: + +------------------------------------------------- +$ git diff master..test +------------------------------------------------- + +Sometimes what you want instead is a set of patches: + +------------------------------------------------- +$ git format-patch master..test +------------------------------------------------- + +will generate a file with a patch for each commit reachable from test +but not from master. Note that if master also has commits which are +not reachable from test, then the combined result of these patches +will not be the same as the diff produced by the git-diff example. + +Viewing old file versions +------------------------- + +You can always view an old version of a file by just checking out the +correct revision first. But sometimes it is more convenient to be +able to view an old version of a single file without checking +anything out; this command does that: + +------------------------------------------------- +$ git show v2.5:fs/locks.c +------------------------------------------------- + +Before the colon may be anything that names a commit, and after it +may be any path to a file tracked by git. + +Examples +-------- + +Check whether two branches point at the same history +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Suppose you want to check whether two branches point at the same point +in history. + +------------------------------------------------- +$ git diff origin..master +------------------------------------------------- + +will tell you whether the contents of the project are the same at the +two branches; in theory, however, it's possible that the same project +contents could have been arrived at by two different historical +routes. You could compare the object names: + +------------------------------------------------- +$ git rev-list origin +e05db0fd4f31dde7005f075a84f96b360d05984b +$ git rev-list master +e05db0fd4f31dde7005f075a84f96b360d05984b +------------------------------------------------- + +Or you could recall that the ... operator selects all commits +contained reachable from either one reference or the other but not +both: so + +------------------------------------------------- +$ git log origin...master +------------------------------------------------- + +will return no commits when the two branches are equal. + +Find first tagged version including a given fix +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Suppose you know that the commit e05db0fd fixed a certain problem. +You'd like to find the earliest tagged release that contains that +fix. + +Of course, there may be more than one answer--if the history branched +after commit e05db0fd, then there could be multiple "earliest" tagged +releases. + +You could just visually inspect the commits since e05db0fd: + +------------------------------------------------- +$ gitk e05db0fd.. +------------------------------------------------- + +Or you can use gitlink:git-name-rev[1], which will give the commit a +name based on any tag it finds pointing to one of the commit's +descendants: + +------------------------------------------------- +$ git name-rev e05db0fd +e05db0fd tags/v1.5.0-rc1^0~23 +------------------------------------------------- + +The gitlink:git-describe[1] command does the opposite, naming the +revision using a tag on which the given commit is based: + +------------------------------------------------- +$ git describe e05db0fd +v1.5.0-rc0-ge05db0f +------------------------------------------------- + +but that may sometimes help you guess which tags might come after the +given commit. + +If you just want to verify whether a given tagged version contains a +given commit, you could use gitlink:git-merge-base[1]: + +------------------------------------------------- +$ git merge-base e05db0fd v1.5.0-rc1 +e05db0fd4f31dde7005f075a84f96b360d05984b +------------------------------------------------- + +The merge-base command finds a common ancestor of the given commits, +and always returns one or the other in the case where one is a +descendant of the other; so the above output shows that e05db0fd +actually is an ancestor of v1.5.0-rc1. + +Alternatively, note that + +------------------------------------------------- +$ git log v1.5.0-rc1..e05db0fd +------------------------------------------------- + +will produce empty output if and only if v1.5.0-rc1 includes e05db0fd, +because it outputs only commits that are not reachable from v1.5.0-rc1. + +As yet another alternative, the gitlink:git-show-branch[1] command lists +the commits reachable from its arguments with a display on the left-hand +side that indicates which arguments that commit is reachable from. So, +you can run something like + +------------------------------------------------- +$ git show-branch e05db0fd v1.5.0-rc0 v1.5.0-rc1 v1.5.0-rc2 +! [e05db0fd] Fix warnings in sha1_file.c - use C99 printf format if +available + ! [v1.5.0-rc0] GIT v1.5.0 preview + ! [v1.5.0-rc1] GIT v1.5.0-rc1 + ! [v1.5.0-rc2] GIT v1.5.0-rc2 +... +------------------------------------------------- + +then search for a line that looks like + +------------------------------------------------- ++ ++ [e05db0fd] Fix warnings in sha1_file.c - use C99 printf format if +available +------------------------------------------------- + +Which shows that e05db0fd is reachable from itself, from v1.5.0-rc1, and +from v1.5.0-rc2, but not from v1.5.0-rc0. + + +Developing with git +=================== + +Telling git your name +--------------------- + +Before creating any commits, you should introduce yourself to git. The +easiest way to do so is: + +------------------------------------------------ +$ cat >~/.gitconfig <<\EOF +[user] + name = Your Name Comes Here + email = you@yourdomain.example.com +EOF +------------------------------------------------ + +(See the "CONFIGURATION FILE" section of gitlink:git-config[1] for +details on the configuration file.) + + +Creating a new repository +------------------------- + +Creating a new repository from scratch is very easy: + +------------------------------------------------- +$ mkdir project +$ cd project +$ git init +------------------------------------------------- + +If you have some initial content (say, a tarball): + +------------------------------------------------- +$ tar -xzvf project.tar.gz +$ cd project +$ git init +$ git add . # include everything below ./ in the first commit: +$ git commit +------------------------------------------------- + +[[how-to-make-a-commit]] +how to make a commit +-------------------- + +Creating a new commit takes three steps: + + 1. Making some changes to the working directory using your + favorite editor. + 2. Telling git about your changes. + 3. Creating the commit using the content you told git about + in step 2. + +In practice, you can interleave and repeat steps 1 and 2 as many +times as you want: in order to keep track of what you want committed +at step 3, git maintains a snapshot of the tree's contents in a +special staging area called "the index." + +At the beginning, the content of the index will be identical to +that of the HEAD. The command "git diff --cached", which shows +the difference between the HEAD and the index, should therefore +produce no output at that point. + +Modifying the index is easy: + +To update the index with the new contents of a modified file, use + +------------------------------------------------- +$ git add path/to/file +------------------------------------------------- + +To add the contents of a new file to the index, use + +------------------------------------------------- +$ git add path/to/file +------------------------------------------------- + +To remove a file from the index and from the working tree, + +------------------------------------------------- +$ git rm path/to/file +------------------------------------------------- + +After each step you can verify that + +------------------------------------------------- +$ git diff --cached +------------------------------------------------- + +always shows the difference between the HEAD and the index file--this +is what you'd commit if you created the commit now--and that + +------------------------------------------------- +$ git diff +------------------------------------------------- + +shows the difference between the working tree and the index file. + +Note that "git add" always adds just the current contents of a file +to the index; further changes to the same file will be ignored unless +you run git-add on the file again. + +When you're ready, just run + +------------------------------------------------- +$ git commit +------------------------------------------------- + +and git will prompt you for a commit message and then create the new +commit. Check to make sure it looks like what you expected with + +------------------------------------------------- +$ git show +------------------------------------------------- + +As a special shortcut, + +------------------------------------------------- +$ git commit -a +------------------------------------------------- + +will update the index with any files that you've modified or removed +and create a commit, all in one step. + +A number of commands are useful for keeping track of what you're +about to commit: + +------------------------------------------------- +$ git diff --cached # difference between HEAD and the index; what + # would be commited if you ran "commit" now. +$ git diff # difference between the index file and your + # working directory; changes that would not + # be included if you ran "commit" now. +$ git status # a brief per-file summary of the above. +------------------------------------------------- + +creating good 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 commit in the +body. + +how to merge +------------ + +You can rejoin two diverging branches of development using +gitlink:git-merge[1]: + +------------------------------------------------- +$ git merge branchname +------------------------------------------------- + +merges the development in the branch "branchname" into the current +branch. If there are conflicts--for example, if the same file is +modified in two different ways in the remote branch and the local +branch--then you are warned; the output may look something like this: + +------------------------------------------------- +$ git merge next + 100% (4/4) done +Auto-merged file.txt +CONFLICT (content): Merge conflict in file.txt +Automatic merge failed; fix conflicts and then commit the result. +------------------------------------------------- + +Conflict markers are left in the problematic files, and after +you resolve the conflicts manually, you can update the index +with the contents and run git commit, as you normally would when +creating a new file. + +If you examine the resulting commit using gitk, you will see that it +has two parents, one pointing to the top of the current branch, and +one to the top of the other branch. + +In more detail: + +[[resolving-a-merge]] +Resolving a merge +----------------- + +When a merge isn't resolved automatically, git leaves the index and +the working tree in a special state that gives you all the +information you need to help resolve the merge. + +Files with conflicts are marked specially in the index, so until you +resolve the problem and update the index, gitlink:git-commit[1] will +fail: + +------------------------------------------------- +$ git commit +file.txt: needs merge +------------------------------------------------- + +Also, gitlink:git-status[1] will list those files as "unmerged", and the +files with conflicts will have conflict markers added, like this: + +------------------------------------------------- +<<<<<<< HEAD:file.txt +Hello world +======= +Goodbye +>>>>>>> 77976da35a11db4580b80ae27e8d65caf5208086:file.txt +------------------------------------------------- + +All you need to do is edit the files to resolve the conflicts, and then + +------------------------------------------------- +$ git add file.txt +$ git commit +------------------------------------------------- + +Note that the commit message will already be filled in for you with +some information about the merge. Normally you can just use this +default message unchanged, but you may add additional commentary of +your own if desired. + +The above is all you need to know to resolve a simple merge. But git +also provides more information to help resolve conflicts: + +Getting conflict-resolution help during a merge +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +All of the changes that git was able to merge automatically are +already added to the index file, so gitlink:git-diff[1] shows only +the conflicts. It uses an unusual syntax: + +------------------------------------------------- +$ git diff +diff --cc file.txt +index 802992c,2b60207..0000000 +--- a/file.txt ++++ b/file.txt +@@@ -1,1 -1,1 +1,5 @@@ +++<<<<<<< HEAD:file.txt + +Hello world +++======= ++ Goodbye +++>>>>>>> 77976da35a11db4580b80ae27e8d65caf5208086:file.txt +------------------------------------------------- + +Recall that the commit which will be commited after we resolve this +conflict will have two parents instead of the usual one: one parent +will be HEAD, the tip of the current branch; the other will be the +tip of the other branch, which is stored temporarily in MERGE_HEAD. + +During the merge, the index holds three versions of each file. Each of +these three "file stages" represents a different version of the file: + +------------------------------------------------- +$ git show :1:file.txt # the file in a common ancestor of both branches +$ git show :2:file.txt # the version from HEAD, but including any + # nonconflicting changes from MERGE_HEAD +$ git show :3:file.txt # the version from MERGE_HEAD, but including any + # nonconflicting changes from HEAD. +------------------------------------------------- + +Since the stage 2 and stage 3 versions have already been updated with +nonconflicting changes, the only remaining differences between them are +the important ones; thus gitlink:git-diff[1] can use the information in +the index to show only those conflicts. + +The diff above shows the differences between the working-tree version of +file.txt and the stage 2 and stage 3 versions. So instead of preceding +each line by a single "+" or "-", it now uses two columns: the first +column is used for differences between the first parent and the working +directory copy, and the second for differences between the second parent +and the working directory copy. (See the "COMBINED DIFF FORMAT" section +of gitlink:git-diff-files[1] for a details of the format.) + +After resolving the conflict in the obvious way (but before updating the +index), the diff will look like: + +------------------------------------------------- +$ git diff +diff --cc file.txt +index 802992c,2b60207..0000000 +--- a/file.txt ++++ b/file.txt +@@@ -1,1 -1,1 +1,1 @@@ +- Hello world + -Goodbye +++Goodbye world +------------------------------------------------- + +This shows that our resolved version deleted "Hello world" from the +first parent, deleted "Goodbye" from the second parent, and added +"Goodbye world", which was previously absent from both. + +Some special diff options allow diffing the working directory against +any of these stages: + +------------------------------------------------- +$ git diff -1 file.txt # diff against stage 1 +$ git diff --base file.txt # same as the above +$ git diff -2 file.txt # diff against stage 2 +$ git diff --ours file.txt # same as the above +$ git diff -3 file.txt # diff against stage 3 +$ git diff --theirs file.txt # same as the above. +------------------------------------------------- + +The gitlink:git-log[1] and gitk[1] commands also provide special help +for merges: + +------------------------------------------------- +$ git log --merge +$ gitk --merge +------------------------------------------------- + +These will display all commits which exist only on HEAD or on +MERGE_HEAD, and which touch an unmerged file. + +Each time you resolve the conflicts in a file and update the index: + +------------------------------------------------- +$ git add file.txt +------------------------------------------------- + +the different stages of that file will be "collapsed", after which +git-diff will (by default) no longer show diffs for that file. + +[[undoing-a-merge]] +undoing a merge +--------------- + +If you get stuck and decide to just give up and throw the whole mess +away, you can always return to the pre-merge state with + +------------------------------------------------- +$ git reset --hard HEAD +------------------------------------------------- + +Or, if you've already commited the merge that you want to throw away, + +------------------------------------------------- +$ git reset --hard ORIG_HEAD +------------------------------------------------- + +However, this last command can be dangerous in some cases--never +throw away a commit you have already committed if that commit may +itself have been merged into another branch, as doing so may confuse +further merges. + +Fast-forward merges +------------------- + +There is one special case not mentioned above, which is treated +differently. Normally, a merge results in a merge commit, with two +parents, one pointing at each of the two lines of development that +were merged. + +However, if one of the two lines of development is completely +contained within the other--so every commit present in the one is +already contained in the other--then git just performs a +<<fast-forwards,fast forward>>; the head of the current branch is +moved forward to point at the head of the merged-in branch, without +any new commits being created. + +Fixing mistakes +--------------- + +If you've messed up the working tree, but haven't yet committed your +mistake, you can return the entire working tree to the last committed +state with + +------------------------------------------------- +$ git reset --hard HEAD +------------------------------------------------- + +If you make a commit that you later wish you hadn't, there are two +fundamentally different ways to fix the problem: + + 1. You can create a new commit that undoes whatever was done + by the previous commit. This is the correct thing if your + mistake has already been made public. + + 2. You can go back and modify the old commit. You should + never do this if you have already made the history public; + git does not normally expect the "history" of a project to + change, and cannot correctly perform repeated merges from + a branch that has had its history changed. + +Fixing a mistake with a new commit +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Creating a new commit that reverts an earlier change is very easy; +just pass the gitlink:git-revert[1] command a reference to the bad +commit; for example, to revert the most recent commit: + +------------------------------------------------- +$ git revert HEAD +------------------------------------------------- + +This will create a new commit which undoes the change in HEAD. You +will be given a chance to edit the commit message for the new commit. + +You can also revert an earlier change, for example, the next-to-last: + +------------------------------------------------- +$ git revert HEAD^ +------------------------------------------------- + +In this case git will attempt to undo the old change while leaving +intact any changes made since then. If more recent changes overlap +with the changes to be reverted, then you will be asked to fix +conflicts manually, just as in the case of <<resolving-a-merge, +resolving a merge>>. + +[[fixing-a-mistake-by-editing-history]] +Fixing a mistake by editing history +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +If the problematic commit is the most recent commit, and you have not +yet made that commit public, then you may just +<<undoing-a-merge,destroy it using git-reset>>. + +Alternatively, you +can edit the working directory and update the index to fix your +mistake, just as if you were going to <<how-to-make-a-commit,create a +new commit>>, then run + +------------------------------------------------- +$ git commit --amend +------------------------------------------------- + +which will replace the old commit by a new commit incorporating your +changes, giving you a chance to edit the old commit message first. + +Again, you should never do this to a commit that may already have +been merged into another branch; use gitlink:git-revert[1] instead in +that case. + +It is also possible to edit commits further back in the history, but +this is an advanced topic to be left for +<<cleaning-up-history,another chapter>>. + +Checking out an old version of a file +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +In the process of undoing a previous bad change, you may find it +useful to check out an older version of a particular file using +gitlink:git-checkout[1]. We've used git checkout before to switch +branches, but it has quite different behavior if it is given a path +name: the command + +------------------------------------------------- +$ git checkout HEAD^ path/to/file +------------------------------------------------- + +replaces path/to/file by the contents it had in the commit HEAD^, and +also updates the index to match. It does not change branches. + +If you just want to look at an old version of the file, without +modifying the working directory, you can do that with +gitlink:git-show[1]: + +------------------------------------------------- +$ git show HEAD^:path/to/file +------------------------------------------------- + +which will display the given version of the file. + +Ensuring good performance +------------------------- + +On large repositories, git depends on compression to keep the history +information from taking up to much space on disk or in memory. + +This compression is not performed automatically. Therefore you +should occasionally run gitlink:git-gc[1]: + +------------------------------------------------- +$ git gc +------------------------------------------------- + +to recompress the archive. This can be very time-consuming, so +you may prefer to run git-gc when you are not doing other work. + +Ensuring reliability +-------------------- + +Checking the repository for corruption +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The gitlink:git-fsck[1] command runs a number of self-consistency checks +on the repository, and reports on any problems. This may take some +time. The most common warning by far is about "dangling" objects: + +------------------------------------------------- +$ git fsck +dangling commit 7281251ddd2a61e38657c827739c57015671a6b3 +dangling commit 2706a059f258c6b245f298dc4ff2ccd30ec21a63 +dangling commit 13472b7c4b80851a1bc551779171dcb03655e9b5 +dangling blob 218761f9d90712d37a9c5e36f406f92202db07eb +dangling commit bf093535a34a4d35731aa2bd90fe6b176302f14f +dangling commit 8e4bec7f2ddaa268bef999853c25755452100f8e +dangling tree d50bb86186bf27b681d25af89d3b5b68382e4085 +dangling tree b24c2473f1fd3d91352a624795be026d64c8841f +... +------------------------------------------------- + +Dangling objects are objects that are harmless, but also unnecessary; +you can remove them at any time with gitlink:git-prune[1] or the --prune +option to gitlink:git-gc[1]: + +------------------------------------------------- +$ git gc --prune +------------------------------------------------- + +This may be time-consuming. Unlike most other git operations (including +git-gc when run without any options), it is not safe to prune while +other git operations are in progress in the same repository. + +For more about dangling objects, see <<dangling-objects>>. + + +Recovering lost changes +~~~~~~~~~~~~~~~~~~~~~~~ + +Reflogs +^^^^^^^ + +Say you modify a branch with gitlink:git-reset[1] --hard, and then +realize that the branch was the only reference you had to that point in +history. + +Fortunately, git also keeps a log, called a "reflog", of all the +previous values of each branch. So in this case you can still find the +old history using, for example, + +------------------------------------------------- +$ git log master@{1} +------------------------------------------------- + +This lists the commits reachable from the previous version of the head. +This syntax can be used to with any git command that accepts a commit, +not just with git log. Some other examples: + +------------------------------------------------- +$ git show master@{2} # See where the branch pointed 2, +$ git show master@{3} # 3, ... changes ago. +$ gitk master@{yesterday} # See where it pointed yesterday, +$ gitk master@{"1 week ago"} # ... or last week +------------------------------------------------- + +The reflogs are kept by default for 30 days, after which they may be +pruned. See gitlink:git-reflog[1] and gitlink:git-gc[1] to learn +how to control this pruning, and see the "SPECIFYING REVISIONS" +section of gitlink:git-rev-parse[1] for details. + +Note that the reflog history is very different from normal git history. +While normal history is shared by every repository that works on the +same project, the reflog history is not shared: it tells you only about +how the branches in your local repository have changed over time. + +Examining dangling objects +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In some situations the reflog may not be able to save you. For +example, suppose you delete a branch, then realize you need the history +it contained. The reflog is also deleted; however, if you have not +yet pruned the repository, then you may still be able to find +the lost commits; run git-fsck and watch for output that mentions +"dangling commits": + +------------------------------------------------- +$ git fsck +dangling commit 7281251ddd2a61e38657c827739c57015671a6b3 +dangling commit 2706a059f258c6b245f298dc4ff2ccd30ec21a63 +dangling commit 13472b7c4b80851a1bc551779171dcb03655e9b5 +... +------------------------------------------------- + +You can examine +one of those dangling commits with, for example, + +------------------------------------------------ +$ gitk 7281251ddd --not --all +------------------------------------------------ + +which does what it sounds like: it says that you want to see the commit +history that is described by the dangling commit(s), but not the +history that is described by all your existing branches and tags. Thus +you get exactly the history reachable from that commit that is lost. +(And notice that it might not be just one commit: we only report the +"tip of the line" as being dangling, but there might be a whole deep +and complex commit history that was dropped.) + +If you decide you want the history back, you can always create a new +reference pointing to it, for example, a new branch: + +------------------------------------------------ +$ git branch recovered-branch 7281251ddd +------------------------------------------------ + + +Sharing development with others +=============================== + +[[getting-updates-with-git-pull]] +Getting updates with git pull +----------------------------- + +After you clone a repository and make a few changes of your own, you +may wish to check the original repository for updates and merge them +into your own work. + +We have already seen <<Updating-a-repository-with-git-fetch,how to +keep remote tracking branches up to date>> with gitlink:git-fetch[1], +and how to merge two branches. So you can merge in changes from the +original repository's master branch with: + +------------------------------------------------- +$ git fetch +$ git merge origin/master +------------------------------------------------- + +However, the gitlink:git-pull[1] command provides a way to do this in +one step: + +------------------------------------------------- +$ git pull origin master +------------------------------------------------- + +In fact, "origin" is normally the default repository to pull from, +and the default branch is normally the HEAD of the remote repository, +so often you can accomplish the above with just + +------------------------------------------------- +$ git pull +------------------------------------------------- + +See the descriptions of the branch.<name>.remote and +branch.<name>.merge options in gitlink:git-config[1] to learn +how to control these defaults depending on the current branch. + +In addition to saving you keystrokes, "git pull" also helps you by +producing a default commit message documenting the branch and +repository that you pulled from. + +(But note that no such commit will be created in the case of a +<<fast-forwards,fast forward>>; instead, your branch will just be +updated to point to the latest commit from the upstream branch.) + +The git-pull command can also be given "." as the "remote" repository, +in which case it just merges in a branch from the current repository; so +the commands + +------------------------------------------------- +$ git pull . branch +$ git merge branch +------------------------------------------------- + +are roughly equivalent. The former is actually very commonly used. + +Submitting patches to a project +------------------------------- + +If you just have a few changes, the simplest way to submit them may +just be to send them as patches in email: + +First, use gitlink:git-format-patch[1]; for example: + +------------------------------------------------- +$ git format-patch origin +------------------------------------------------- + +will produce a numbered series of files in the current directory, one +for each patch in the current branch but not in origin/HEAD. + +You can then import these into your mail client and send them by +hand. However, if you have a lot to send at once, you may prefer to +use the gitlink:git-send-email[1] script to automate the process. +Consult the mailing list for your project first to determine how they +prefer such patches be handled. + +Importing patches to a project +------------------------------ + +Git also provides a tool called gitlink:git-am[1] (am stands for +"apply mailbox"), for importing such an emailed series of patches. +Just save all of the patch-containing messages, in order, into a +single mailbox file, say "patches.mbox", then run + +------------------------------------------------- +$ git am -3 patches.mbox +------------------------------------------------- + +Git will apply each patch in order; if any conflicts are found, it +will stop, and you can fix the conflicts as described in +"<<resolving-a-merge,Resolving a merge>>". (The "-3" option tells +git to perform a merge; if you would prefer it just to abort and +leave your tree and index untouched, you may omit that option.) + +Once the index is updated with the results of the conflict +resolution, instead of creating a new commit, just run + +------------------------------------------------- +$ git am --resolved +------------------------------------------------- + +and git will create the commit for you and continue applying the +remaining patches from the mailbox. + +The final result will be a series of commits, one for each patch in +the original mailbox, with authorship and commit log message each +taken from the message containing each patch. + +[[setting-up-a-public-repository]] +Setting up a public repository +------------------------------ + +Another way to submit changes to a project is to simply tell the +maintainer of that project to pull from your repository, exactly as +you did in the section "<<getting-updates-with-git-pull, Getting +updates with git pull>>". + +If you and maintainer both have accounts on the same machine, then +then you can just pull changes from each other's repositories +directly; note that all of the commands (gitlink:git-clone[1], +git-fetch[1], git-pull[1], etc.) that accept a URL as an argument +will also accept a local file patch; so, for example, you can +use + +------------------------------------------------- +$ git clone /path/to/repository +$ git pull /path/to/other/repository +------------------------------------------------- + +If this sort of setup is inconvenient or impossible, another (more +common) option is to set up a public repository on a public server. +This also allows you to cleanly separate private work in progress +from publicly visible work. + +You will continue to do your day-to-day work in your personal +repository, but periodically "push" changes from your personal +repository into your public repository, allowing other developers to +pull from that repository. So the flow of changes, in a situation +where there is one other developer with a public repository, looks +like this: + + you push + your personal repo ------------------> your public repo + ^ | + | | + | you pull | they pull + | | + | | + | they push V + their public repo <------------------- their repo + +Now, assume your personal repository is in the directory ~/proj. We +first create a new clone of the repository: + +------------------------------------------------- +$ git clone --bare proj-clone.git +------------------------------------------------- + +The resulting directory proj-clone.git will contains a "bare" git +repository--it is just the contents of the ".git" directory, without +a checked-out copy of a working directory. + +Next, copy proj-clone.git to the server where you plan to host the +public repository. You can use scp, rsync, or whatever is most +convenient. + +If somebody else maintains the public server, they may already have +set up a git service for you, and you may skip to the section +"<<pushing-changes-to-a-public-repository,Pushing changes to a public +repository>>", below. + +Otherwise, the following sections explain how to export your newly +created public repository: + +[[exporting-via-http]] +Exporting a git repository via http +----------------------------------- + +The git protocol gives better performance and reliability, but on a +host with a web server set up, http exports may be simpler to set up. + +All you need to do is place the newly created bare git repository in +a directory that is exported by the web server, and make some +adjustments to give web clients some extra information they need: + +------------------------------------------------- +$ mv proj.git /home/you/public_html/proj.git +$ cd proj.git +$ git update-server-info +$ chmod a+x hooks/post-update +------------------------------------------------- + +(For an explanation of the last two lines, see +gitlink:git-update-server-info[1], and the documentation +link:hooks.txt[Hooks used by git].) + +Advertise the url of proj.git. Anybody else should then be able to +clone or pull from that url, for example with a commandline like: + +------------------------------------------------- +$ git clone http://yourserver.com/~you/proj.git +------------------------------------------------- + +(See also +link:howto/setup-git-server-over-http.txt[setup-git-server-over-http] +for a slightly more sophisticated setup using WebDAV which also +allows pushing over http.) + +[[exporting-via-git]] +Exporting a git repository via the git protocol +----------------------------------------------- + +This is the preferred method. + +For now, we refer you to the gitlink:git-daemon[1] man page for +instructions. (See especially the examples section.) + +[[pushing-changes-to-a-public-repository]] +Pushing changes to a public repository +-------------------------------------- + +Note that the two techniques outline above (exporting via +<<exporting-via-http,http>> or <<exporting-via-git,git>>) allow other +maintainers to fetch your latest changes, but they do not allow write +access, which you will need to update the public repository with the +latest changes created in your private repository. + +The simplest way to do this is using gitlink:git-push[1] and ssh; to +update the remote branch named "master" with the latest state of your +branch named "master", run + +------------------------------------------------- +$ git push ssh://yourserver.com/~you/proj.git master:master +------------------------------------------------- + +or just + +------------------------------------------------- +$ git push ssh://yourserver.com/~you/proj.git master +------------------------------------------------- + +As with git-fetch, git-push will complain if this does not result in +a <<fast-forwards,fast forward>>. Normally this is a sign of +something wrong. However, if you are sure you know what you're +doing, you may force git-push to perform the update anyway by +proceeding the branch name by a plus sign: + +------------------------------------------------- +$ git push ssh://yourserver.com/~you/proj.git +master +------------------------------------------------- + +As with git-fetch, you may also set up configuration options to +save typing; so, for example, after + +------------------------------------------------- +$ cat >.git/config <<EOF +[remote "public-repo"] + url = ssh://yourserver.com/~you/proj.git +EOF +------------------------------------------------- + +you should be able to perform the above push with just + +------------------------------------------------- +$ git push public-repo master +------------------------------------------------- + +See the explanations of the remote.<name>.url, branch.<name>.remote, +and remote.<name>.push options in gitlink:git-config[1] for +details. + +Setting up a shared repository +------------------------------ + +Another way to collaborate is by using a model similar to that +commonly used in CVS, where several developers with special rights +all push to and pull from a single shared repository. See +link:cvs-migration.txt[git for CVS users] for instructions on how to +set this up. + +Allow web browsing of a repository +---------------------------------- + +The gitweb cgi script provides users an easy way to browse your +project's files and history without having to install git; see the file +gitweb/README in the git source tree for instructions on setting it up. + +Examples +-------- + +TODO: topic branches, typical roles as in everyday.txt, ? + + +[[cleaning-up-history]] +Rewriting history and maintaining patch series +============================================== + +Normally commits are only added to a project, never taken away or +replaced. Git is designed with this assumption, and violating it will +cause git's merge machinery (for example) to do the wrong thing. + +However, there is a situation in which it can be useful to violate this +assumption. + +Creating the perfect patch series +--------------------------------- + +Suppose you are a contributor to a large project, and you want to add a +complicated feature, and to present it to the other developers in a way +that makes it easy for them to read your changes, verify that they are +correct, and understand why you made each change. + +If you present all of your changes as a single patch (or commit), they +may find that it is too much to digest all at once. + +If you present them with the entire history of your work, complete with +mistakes, corrections, and dead ends, they may be overwhelmed. + +So the ideal is usually to produce a series of patches such that: + + 1. Each patch can be applied in order. + + 2. Each patch includes a single logical change, together with a + message explaining the change. + + 3. No patch introduces a regression: after applying any initial + part of the series, the resulting project still compiles and + works, and has no bugs that it didn't have before. + + 4. The complete series produces the same end result as your own + (probably much messier!) development process did. + +We will introduce some tools that can help you do this, explain how to +use them, and then explain some of the problems that can arise because +you are rewriting history. + +Keeping a patch series up to date using git-rebase +-------------------------------------------------- + +Suppose that you create a branch "mywork" on a remote-tracking branch +"origin", and create some commits on top of it: + +------------------------------------------------- +$ git checkout -b mywork origin +$ vi file.txt +$ git commit +$ vi otherfile.txt +$ git commit +... +------------------------------------------------- + +You have performed no merges into mywork, so it is just a simple linear +sequence of patches on top of "origin": + +................................................ + o--o--o <-- origin + \ + o--o--o <-- mywork +................................................ + +Some more interesting work has been done in the upstream project, and +"origin" has advanced: + +................................................ + o--o--O--o--o--o <-- origin + \ + a--b--c <-- mywork +................................................ + +At this point, you could use "pull" to merge your changes back in; +the result would create a new merge commit, like this: + +................................................ + o--o--O--o--o--o <-- origin + \ \ + a--b--c--m <-- mywork +................................................ + +However, if you prefer to keep the history in mywork a simple series of +commits without any merges, you may instead choose to use +gitlink:git-rebase[1]: + +------------------------------------------------- +$ git checkout mywork +$ git rebase origin +------------------------------------------------- + +This will remove each of your commits from mywork, temporarily saving +them as patches (in a directory named ".dotest"), update mywork to +point at the latest version of origin, then apply each of the saved +patches to the new mywork. The result will look like: + + +................................................ + o--o--O--o--o--o <-- origin + \ + a'--b'--c' <-- mywork +................................................ + +In the process, it may discover conflicts. In that case it will stop +and allow you to fix the conflicts; after fixing conflicts, use "git +add" to update the index with those contents, and then, instead of +running git-commit, just run + +------------------------------------------------- +$ git rebase --continue +------------------------------------------------- + +and git will continue applying the rest of the patches. + +At any point you may use the --abort option to abort this process and +return mywork to the state it had before you started the rebase: + +------------------------------------------------- +$ git rebase --abort +------------------------------------------------- + +Modifying a single commit +------------------------- + +We saw in <<fixing-a-mistake-by-editing-history>> that you can replace the +most recent commit using + +------------------------------------------------- +$ git commit --amend +------------------------------------------------- + +which will replace the old commit by a new commit incorporating your +changes, giving you a chance to edit the old commit message first. + +You can also use a combination of this and gitlink:git-rebase[1] to edit +commits further back in your history. First, tag the problematic commit with + +------------------------------------------------- +$ git tag bad mywork~5 +------------------------------------------------- + +(Either gitk or git-log may be useful for finding the commit.) + +Then check out a new branch at that commit, edit it, and rebase the rest of +the series on top of it: + +------------------------------------------------- +$ git checkout -b TMP bad +$ # make changes here and update the index +$ git commit --amend +$ git rebase --onto TMP bad mywork +------------------------------------------------- + +When you're done, you'll be left with mywork checked out, with the top patches +on mywork reapplied on top of the modified commit you created in TMP. You can +then clean up with + +------------------------------------------------- +$ git branch -d TMP +$ git tag -d bad +------------------------------------------------- + +Note that the immutable nature of git history means that you haven't really +"modified" existing commits; instead, you have replaced the old commits with +new commits having new object names. + +Reordering or selecting from a patch series +------------------------------------------- + +Given one existing commit, the gitlink:git-cherry-pick[1] command +allows you to apply the change introduced by that commit and create a +new commit that records it. So, for example, if "mywork" points to a +series of patches on top of "origin", you might do something like: + +------------------------------------------------- +$ git checkout -b mywork-new origin +$ gitk origin..mywork & +------------------------------------------------- + +And browse through the list of patches in the mywork branch using gitk, +applying them (possibly in a different order) to mywork-new using +cherry-pick, and possibly modifying them as you go using commit +--amend. + +Another technique is to use git-format-patch to create a series of +patches, then reset the state to before the patches: + +------------------------------------------------- +$ git format-patch origin +$ git reset --hard origin +------------------------------------------------- + +Then modify, reorder, or eliminate patches as preferred before applying +them again with gitlink:git-am[1]. + +Other tools +----------- + +There are numerous other tools, such as stgit, which exist for the +purpose of maintaining a patch series. These are outside of the scope of +this manual. + +Problems with rewriting history +------------------------------- + +The primary problem with rewriting the history of a branch has to do +with merging. Suppose somebody fetches your branch and merges it into +their branch, with a result something like this: + +................................................ + o--o--O--o--o--o <-- origin + \ \ + t--t--t--m <-- their branch: +................................................ + +Then suppose you modify the last three commits: + +................................................ + o--o--o <-- new head of origin + / + o--o--O--o--o--o <-- old head of origin +................................................ + +If we examined all this history together in one repository, it will +look like: + +................................................ + o--o--o <-- new head of origin + / + o--o--O--o--o--o <-- old head of origin + \ \ + t--t--t--m <-- their branch: +................................................ + +Git has no way of knowing that the new head is an updated version of +the old head; it treats this situation exactly the same as it would if +two developers had independently done the work on the old and new heads +in parallel. At this point, if someone attempts to merge the new head +in to their branch, git will attempt to merge together the two (old and +new) lines of development, instead of trying to replace the old by the +new. The results are likely to be unexpected. + +You may still choose to publish branches whose history is rewritten, +and it may be useful for others to be able to fetch those branches in +order to examine or test them, but they should not attempt to pull such +branches into their own work. + +For true distributed development that supports proper merging, +published branches should never be rewritten. + +Advanced branch management +========================== + +Fetching individual branches +---------------------------- + +Instead of using gitlink:git-remote[1], you can also choose just +to update one branch at a time, and to store it locally under an +arbitrary name: + +------------------------------------------------- +$ git fetch origin todo:my-todo-work +------------------------------------------------- + +The first argument, "origin", just tells git to fetch from the +repository you originally cloned from. The second argument tells git +to fetch the branch named "todo" from the remote repository, and to +store it locally under the name refs/heads/my-todo-work. + +You can also fetch branches from other repositories; so + +------------------------------------------------- +$ git fetch git://example.com/proj.git master:example-master +------------------------------------------------- + +will create a new branch named "example-master" and store in it the +branch named "master" from the repository at the given URL. If you +already have a branch named example-master, it will attempt to +"fast-forward" to the commit given by example.com's master branch. So +next we explain what a fast-forward is: + +[[fast-forwards]] +Understanding git history: fast-forwards +---------------------------------------- + +In the previous example, when updating an existing branch, "git +fetch" checks to make sure that the most recent commit on the remote +branch is a descendant of the most recent commit on your copy of the +branch before updating your copy of the branch to point at the new +commit. Git calls this process a "fast forward". + +A fast forward looks something like this: + +................................................ + o--o--o--o <-- old head of the branch + \ + o--o--o <-- new head of the branch +................................................ + + +In some cases it is possible that the new head will *not* actually be +a descendant of the old head. For example, the developer may have +realized she made a serious mistake, and decided to backtrack, +resulting in a situation like: + +................................................ + o--o--o--o--a--b <-- old head of the branch + \ + o--o--o <-- new head of the branch +................................................ + +In this case, "git fetch" will fail, and print out a warning. + +In that case, you can still force git to update to the new head, as +described in the following section. However, note that in the +situation above this may mean losing the commits labeled "a" and "b", +unless you've already created a reference of your own pointing to +them. + +Forcing git fetch to do non-fast-forward updates +------------------------------------------------ + +If git fetch fails because the new head of a branch is not a +descendant of the old head, you may force the update with: + +------------------------------------------------- +$ git fetch git://example.com/proj.git +master:refs/remotes/example/master +------------------------------------------------- + +Note the addition of the "+" sign. Be aware that commits that the +old version of example/master pointed at may be lost, as we saw in +the previous section. + +Configuring remote branches +--------------------------- + +We saw above that "origin" is just a shortcut to refer to the +repository that you originally cloned from. This information is +stored in git configuration variables, which you can see using +gitlink:git-config[1]: + +------------------------------------------------- +$ git config -l +core.repositoryformatversion=0 +core.filemode=true +core.logallrefupdates=true +remote.origin.url=git://git.kernel.org/pub/scm/git/git.git +remote.origin.fetch=+refs/heads/*:refs/remotes/origin/* +branch.master.remote=origin +branch.master.merge=refs/heads/master +------------------------------------------------- + +If there are other repositories that you also use frequently, you can +create similar configuration options to save typing; for example, +after + +------------------------------------------------- +$ git config remote.example.url git://example.com/proj.git +------------------------------------------------- + +then the following two commands will do the same thing: + +------------------------------------------------- +$ git fetch git://example.com/proj.git master:refs/remotes/example/master +$ git fetch example master:refs/remotes/example/master +------------------------------------------------- + +Even better, if you add one more option: + +------------------------------------------------- +$ git config remote.example.fetch master:refs/remotes/example/master +------------------------------------------------- + +then the following commands will all do the same thing: + +------------------------------------------------- +$ git fetch git://example.com/proj.git master:ref/remotes/example/master +$ git fetch example master:ref/remotes/example/master +$ git fetch example example/master +$ git fetch example +------------------------------------------------- + +You can also add a "+" to force the update each time: + +------------------------------------------------- +$ git config remote.example.fetch +master:ref/remotes/example/master +------------------------------------------------- + +Don't do this unless you're sure you won't mind "git fetch" possibly +throwing away commits on mybranch. + +Also note that all of the above configuration can be performed by +directly editing the file .git/config instead of using +gitlink:git-config[1]. + +See gitlink:git-config[1] for more details on the configuration +options mentioned above. + + +[[git-internals]] +Git internals +============= + +There are two object abstractions: the "object database", and the +"current directory cache" aka "index". + +The Object Database +------------------- + +The object database is literally just a content-addressable collection +of objects. All objects are named by their content, which is +approximated by the SHA1 hash of the object itself. Objects may refer +to other objects (by referencing their SHA1 hash), and so you can +build up a hierarchy of objects. + +All objects have a statically determined "type" aka "tag", which is +determined at object creation time, and which identifies the format of +the object (i.e. how it is used, and how it can refer to other +objects). There are currently four different object types: "blob", +"tree", "commit" and "tag". + +A "blob" object cannot refer to any other object, and is, like the type +implies, a pure storage object containing some user data. It is used to +actually store the file data, i.e. a blob object is associated with some +particular version of some file. + +A "tree" object is an object that ties one or more "blob" objects into a +directory structure. In addition, a tree object can refer to other tree +objects, thus creating a directory hierarchy. + +A "commit" object ties such directory hierarchies together into +a DAG of revisions - each "commit" is associated with exactly one tree +(the directory hierarchy at the time of the commit). In addition, a +"commit" refers to one or more "parent" commit objects that describe the +history of how we arrived at that directory hierarchy. + +As a special case, a commit object with no parents is called the "root" +object, and is the point of an initial project commit. Each project +must have at least one root, and while you can tie several different +root objects together into one project by creating a commit object which +has two or more separate roots as its ultimate parents, that's probably +just going to confuse people. So aim for the notion of "one root object +per project", even if git itself does not enforce that. + +A "tag" object symbolically identifies and can be used to sign other +objects. It contains the identifier and type of another object, a +symbolic name (of course!) and, optionally, a signature. + +Regardless of object type, all objects share the following +characteristics: they are all deflated with zlib, and have a header +that not only specifies their type, but also provides size information +about the data in the object. It's worth noting that the SHA1 hash +that is used to name the object is the hash of the original data +plus this header, so `sha1sum` 'file' does not match the object name +for 'file'. +(Historical note: in the dawn of the age of git the hash +was the sha1 of the 'compressed' object.) + +As a result, the general consistency of an object can always be tested +independently of the contents or the type of the object: all objects can +be validated by verifying that (a) their hashes match the content of the +file and (b) the object successfully inflates to a stream of bytes that +forms a sequence of <ascii type without space> + <space> + <ascii decimal +size> + <byte\0> + <binary object data>. + +The structured objects can further have their structure and +connectivity to other objects verified. This is generally done with +the `git-fsck` program, which generates a full dependency graph +of all objects, and verifies their internal consistency (in addition +to just verifying their superficial consistency through the hash). + +The object types in some more detail: + +Blob Object +----------- + +A "blob" object is nothing but a binary blob of data, and doesn't +refer to anything else. There is no signature or any other +verification of the data, so while the object is consistent (it 'is' +indexed by its sha1 hash, so the data itself is certainly correct), it +has absolutely no other attributes. No name associations, no +permissions. It is purely a blob of data (i.e. normally "file +contents"). + +In particular, since the blob is entirely defined by its data, if two +files in a directory tree (or in multiple different versions of the +repository) have the same contents, they will share the same blob +object. The object is totally independent of its location in the +directory tree, and renaming a file does not change the object that +file is associated with in any way. + +A blob is typically created when gitlink:git-update-index[1] +is run, and its data can be accessed by gitlink:git-cat-file[1]. + +Tree Object +----------- + +The next hierarchical object type is the "tree" object. A tree object +is a list of mode/name/blob data, sorted by name. Alternatively, the +mode data may specify a directory mode, in which case instead of +naming a blob, that name is associated with another TREE object. + +Like the "blob" object, a tree object is uniquely determined by the +set contents, and so two separate but identical trees will always +share the exact same object. This is true at all levels, i.e. it's +true for a "leaf" tree (which does not refer to any other trees, only +blobs) as well as for a whole subdirectory. + +For that reason a "tree" object is just a pure data abstraction: it +has no history, no signatures, no verification of validity, except +that since the contents are again protected by the hash itself, we can +trust that the tree is immutable and its contents never change. + +So you can trust the contents of a tree to be valid, the same way you +can trust the contents of a blob, but you don't know where those +contents 'came' from. + +Side note on trees: since a "tree" object is a sorted list of +"filename+content", you can create a diff between two trees without +actually having to unpack two trees. Just ignore all common parts, +and your diff will look right. In other words, you can effectively +(and efficiently) tell the difference between any two random trees by +O(n) where "n" is the size of the difference, rather than the size of +the tree. + +Side note 2 on trees: since the name of a "blob" depends entirely and +exclusively on its contents (i.e. there are no names or permissions +involved), you can see trivial renames or permission changes by +noticing that the blob stayed the same. However, renames with data +changes need a smarter "diff" implementation. + +A tree is created with gitlink:git-write-tree[1] and +its data can be accessed by gitlink:git-ls-tree[1]. +Two trees can be compared with gitlink:git-diff-tree[1]. + +Commit Object +------------- + +The "commit" object is an object that introduces the notion of +history into the picture. In contrast to the other objects, it +doesn't just describe the physical state of a tree, it describes how +we got there, and why. + +A "commit" is defined by the tree-object that it results in, the +parent commits (zero, one or more) that led up to that point, and a +comment on what happened. Again, a commit is not trusted per se: +the contents are well-defined and "safe" due to the cryptographically +strong signatures at all levels, but there is no reason to believe +that the tree is "good" or that the merge information makes sense. +The parents do not have to actually have any relationship with the +result, for example. + +Note on commits: unlike real SCM's, commits do not contain +rename information or file mode change information. All of that is +implicit in the trees involved (the result tree, and the result trees +of the parents), and describing that makes no sense in this idiotic +file manager. + +A commit is created with gitlink:git-commit-tree[1] and +its data can be accessed by gitlink:git-cat-file[1]. + +Trust +----- + +An aside on the notion of "trust". Trust is really outside the scope +of "git", but it's worth noting a few things. First off, since +everything is hashed with SHA1, you 'can' trust that an object is +intact and has not been messed with by external sources. So the name +of an object uniquely identifies a known state - just not a state that +you may want to trust. + +Furthermore, since the SHA1 signature of a commit refers to the +SHA1 signatures of the tree it is associated with and the signatures +of the parent, a single named commit specifies uniquely a whole set +of history, with full contents. You can't later fake any step of the +way once you have the name of a commit. + +So to introduce some real trust in the system, the only thing you need +to do is to digitally sign just 'one' special note, which includes the +name of a top-level commit. Your digital signature shows others +that you trust that commit, and the immutability of the history of +commits tells others that they can trust the whole history. + +In other words, you can easily validate a whole archive by just +sending out a single email that tells the people the name (SHA1 hash) +of the top commit, and digitally sign that email using something +like GPG/PGP. + +To assist in this, git also provides the tag object... + +Tag Object +---------- + +Git provides the "tag" object to simplify creating, managing and +exchanging symbolic and signed tokens. The "tag" object at its +simplest simply symbolically identifies another object by containing +the sha1, type and symbolic name. + +However it can optionally contain additional signature information +(which git doesn't care about as long as there's less than 8k of +it). This can then be verified externally to git. + +Note that despite the tag features, "git" itself only handles content +integrity; the trust framework (and signature provision and +verification) has to come from outside. + +A tag is created with gitlink:git-mktag[1], +its data can be accessed by gitlink:git-cat-file[1], +and the signature can be verified by +gitlink:git-verify-tag[1]. + + +The "index" aka "Current Directory Cache" +----------------------------------------- + +The index is a simple binary file, which contains an efficient +representation of a virtual directory content at some random time. It +does so by a simple array that associates a set of names, dates, +permissions and content (aka "blob") objects together. The cache is +always kept ordered by name, and names are unique (with a few very +specific rules) at any point in time, but the cache has no long-term +meaning, and can be partially updated at any time. + +In particular, the index certainly does not need to be consistent with +the current directory contents (in fact, most operations will depend on +different ways to make the index 'not' be consistent with the directory +hierarchy), but it has three very important attributes: + +'(a) it can re-generate the full state it caches (not just the +directory structure: it contains pointers to the "blob" objects so +that it can regenerate the data too)' + +As a special case, there is a clear and unambiguous one-way mapping +from a current directory cache to a "tree object", which can be +efficiently created from just the current directory cache without +actually looking at any other data. So a directory cache at any one +time uniquely specifies one and only one "tree" object (but has +additional data to make it easy to match up that tree object with what +has happened in the directory) + +'(b) it has efficient methods for finding inconsistencies between that +cached state ("tree object waiting to be instantiated") and the +current state.' + +'(c) it can additionally efficiently represent information about merge +conflicts between different tree objects, allowing each pathname to be +associated with sufficient information about the trees involved that +you can create a three-way merge between them.' + +Those are the ONLY three things that the directory cache does. It's a +cache, and the normal operation is to re-generate it completely from a +known tree object, or update/compare it with a live tree that is being +developed. If you blow the directory cache away entirely, you generally +haven't lost any information as long as you have the name of the tree +that it described. + +At the same time, the index is at the same time also the +staging area for creating new trees, and creating a new tree always +involves a controlled modification of the index file. In particular, +the index file can have the representation of an intermediate tree that +has not yet been instantiated. So the index can be thought of as a +write-back cache, which can contain dirty information that has not yet +been written back to the backing store. + + + +The Workflow +------------ + +Generally, all "git" operations work on the index file. Some operations +work *purely* on the index file (showing the current state of the +index), but most operations move data to and from the index file. Either +from the database or from the working directory. Thus there are four +main combinations: + +working directory -> index +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You update the index with information from the working directory with +the gitlink:git-update-index[1] command. You +generally update the index information by just specifying the filename +you want to update, like so: + +------------------------------------------------- +$ git-update-index filename +------------------------------------------------- + +but to avoid common mistakes with filename globbing etc, the command +will not normally add totally new entries or remove old entries, +i.e. it will normally just update existing cache entries. + +To tell git that yes, you really do realize that certain files no +longer exist, or that new files should be added, you +should use the `--remove` and `--add` flags respectively. + +NOTE! A `--remove` flag does 'not' mean that subsequent filenames will +necessarily be removed: if the files still exist in your directory +structure, the index will be updated with their new status, not +removed. The only thing `--remove` means is that update-cache will be +considering a removed file to be a valid thing, and if the file really +does not exist any more, it will update the index accordingly. + +As a special case, you can also do `git-update-index --refresh`, which +will refresh the "stat" information of each index to match the current +stat information. It will 'not' update the object status itself, and +it will only update the fields that are used to quickly test whether +an object still matches its old backing store object. + +index -> object database +~~~~~~~~~~~~~~~~~~~~~~~~ + +You write your current index file to a "tree" object with the program + +------------------------------------------------- +$ git-write-tree +------------------------------------------------- + +that doesn't come with any options - it will just write out the +current index into the set of tree objects that describe that state, +and it will return the name of the resulting top-level tree. You can +use that tree to re-generate the index at any time by going in the +other direction: + +object database -> index +~~~~~~~~~~~~~~~~~~~~~~~~ + +You read a "tree" file from the object database, and use that to +populate (and overwrite - don't do this if your index contains any +unsaved state that you might want to restore later!) your current +index. Normal operation is just + +------------------------------------------------- +$ git-read-tree <sha1 of tree> +------------------------------------------------- + +and your index file will now be equivalent to the tree that you saved +earlier. However, that is only your 'index' file: your working +directory contents have not been modified. + +index -> working directory +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You update your working directory from the index by "checking out" +files. This is not a very common operation, since normally you'd just +keep your files updated, and rather than write to your working +directory, you'd tell the index files about the changes in your +working directory (i.e. `git-update-index`). + +However, if you decide to jump to a new version, or check out somebody +else's version, or just restore a previous tree, you'd populate your +index file with read-tree, and then you need to check out the result +with + +------------------------------------------------- +$ git-checkout-index filename +------------------------------------------------- + +or, if you want to check out all of the index, use `-a`. + +NOTE! git-checkout-index normally refuses to overwrite old files, so +if you have an old version of the tree already checked out, you will +need to use the "-f" flag ('before' the "-a" flag or the filename) to +'force' the checkout. + + +Finally, there are a few odds and ends which are not purely moving +from one representation to the other: + +Tying it all together +~~~~~~~~~~~~~~~~~~~~~ + +To commit a tree you have instantiated with "git-write-tree", you'd +create a "commit" object that refers to that tree and the history +behind it - most notably the "parent" commits that preceded it in +history. + +Normally a "commit" has one parent: the previous state of the tree +before a certain change was made. However, sometimes it can have two +or more parent commits, in which case we call it a "merge", due to the +fact that such a commit brings together ("merges") two or more +previous states represented by other commits. + +In other words, while a "tree" represents a particular directory state +of a working directory, a "commit" represents that state in "time", +and explains how we got there. + +You create a commit object by giving it the tree that describes the +state at the time of the commit, and a list of parents: + +------------------------------------------------- +$ git-commit-tree <tree> -p <parent> [-p <parent2> ..] +------------------------------------------------- + +and then giving the reason for the commit on stdin (either through +redirection from a pipe or file, or by just typing it at the tty). + +git-commit-tree will return the name of the object that represents +that commit, and you should save it away for later use. Normally, +you'd commit a new `HEAD` state, and while git doesn't care where you +save the note about that state, in practice we tend to just write the +result to the file pointed at by `.git/HEAD`, so that we can always see +what the last committed state was. + +Here is an ASCII art by Jon Loeliger that illustrates how +various pieces fit together. + +------------ + + commit-tree + commit obj + +----+ + | | + | | + V V + +-----------+ + | Object DB | + | Backing | + | Store | + +-----------+ + ^ + write-tree | | + tree obj | | + | | read-tree + | | tree obj + V + +-----------+ + | Index | + | "cache" | + +-----------+ + update-index ^ + blob obj | | + | | + checkout-index -u | | checkout-index + stat | | blob obj + V + +-----------+ + | Working | + | Directory | + +-----------+ + +------------ + + +Examining the data +------------------ + +You can examine the data represented in the object database and the +index with various helper tools. For every object, you can use +gitlink:git-cat-file[1] to examine details about the +object: + +------------------------------------------------- +$ git-cat-file -t <objectname> +------------------------------------------------- + +shows the type of the object, and once you have the type (which is +usually implicit in where you find the object), you can use + +------------------------------------------------- +$ git-cat-file blob|tree|commit|tag <objectname> +------------------------------------------------- + +to show its contents. NOTE! Trees have binary content, and as a result +there is a special helper for showing that content, called +`git-ls-tree`, which turns the binary content into a more easily +readable form. + +It's especially instructive to look at "commit" objects, since those +tend to be small and fairly self-explanatory. In particular, if you +follow the convention of having the top commit name in `.git/HEAD`, +you can do + +------------------------------------------------- +$ git-cat-file commit HEAD +------------------------------------------------- + +to see what the top commit was. + +Merging multiple trees +---------------------- + +Git helps you do a three-way merge, which you can expand to n-way by +repeating the merge procedure arbitrary times until you finally +"commit" the state. The normal situation is that you'd only do one +three-way merge (two parents), and commit it, but if you like to, you +can do multiple parents in one go. + +To do a three-way merge, you need the two sets of "commit" objects +that you want to merge, use those to find the closest common parent (a +third "commit" object), and then use those commit objects to find the +state of the directory ("tree" object) at these points. + +To get the "base" for the merge, you first look up the common parent +of two commits with + +------------------------------------------------- +$ git-merge-base <commit1> <commit2> +------------------------------------------------- + +which will return you the commit they are both based on. You should +now look up the "tree" objects of those commits, which you can easily +do with (for example) + +------------------------------------------------- +$ git-cat-file commit <commitname> | head -1 +------------------------------------------------- + +since the tree object information is always the first line in a commit +object. + +Once you know the three trees you are going to merge (the one "original" +tree, aka the common case, and the two "result" trees, aka the branches +you want to merge), you do a "merge" read into the index. This will +complain if it has to throw away your old index contents, so you should +make sure that you've committed those - in fact you would normally +always do a merge against your last commit (which should thus match what +you have in your current index anyway). + +To do the merge, do + +------------------------------------------------- +$ git-read-tree -m -u <origtree> <yourtree> <targettree> +------------------------------------------------- + +which will do all trivial merge operations for you directly in the +index file, and you can just write the result out with +`git-write-tree`. + + +Merging multiple trees, continued +--------------------------------- + +Sadly, many merges aren't trivial. If there are files that have +been added.moved or removed, or if both branches have modified the +same file, you will be left with an index tree that contains "merge +entries" in it. Such an index tree can 'NOT' be written out to a tree +object, and you will have to resolve any such merge clashes using +other tools before you can write out the result. + +You can examine such index state with `git-ls-files --unmerged` +command. An example: + +------------------------------------------------ +$ git-read-tree -m $orig HEAD $target +$ git-ls-files --unmerged +100644 263414f423d0e4d70dae8fe53fa34614ff3e2860 1 hello.c +100644 06fa6a24256dc7e560efa5687fa84b51f0263c3a 2 hello.c +100644 cc44c73eb783565da5831b4d820c962954019b69 3 hello.c +------------------------------------------------ + +Each line of the `git-ls-files --unmerged` output begins with +the blob mode bits, blob SHA1, 'stage number', and the +filename. The 'stage number' is git's way to say which tree it +came from: stage 1 corresponds to `$orig` tree, stage 2 `HEAD` +tree, and stage3 `$target` tree. + +Earlier we said that trivial merges are done inside +`git-read-tree -m`. For example, if the file did not change +from `$orig` to `HEAD` nor `$target`, or if the file changed +from `$orig` to `HEAD` and `$orig` to `$target` the same way, +obviously the final outcome is what is in `HEAD`. What the +above example shows is that file `hello.c` was changed from +`$orig` to `HEAD` and `$orig` to `$target` in a different way. +You could resolve this by running your favorite 3-way merge +program, e.g. `diff3` or `merge`, on the blob objects from +these three stages yourself, like this: + +------------------------------------------------ +$ git-cat-file blob 263414f... >hello.c~1 +$ git-cat-file blob 06fa6a2... >hello.c~2 +$ git-cat-file blob cc44c73... >hello.c~3 +$ merge hello.c~2 hello.c~1 hello.c~3 +------------------------------------------------ + +This would leave the merge result in `hello.c~2` file, along +with conflict markers if there are conflicts. After verifying +the merge result makes sense, you can tell git what the final +merge result for this file is by: + +------------------------------------------------- +$ mv -f hello.c~2 hello.c +$ git-update-index hello.c +------------------------------------------------- + +When a path is in unmerged state, running `git-update-index` for +that path tells git to mark the path resolved. + +The above is the description of a git merge at the lowest level, +to help you understand what conceptually happens under the hood. +In practice, nobody, not even git itself, uses three `git-cat-file` +for this. There is `git-merge-index` program that extracts the +stages to temporary files and calls a "merge" script on it: + +------------------------------------------------- +$ git-merge-index git-merge-one-file hello.c +------------------------------------------------- + +and that is what higher level `git merge -s resolve` is implemented with. + +How git stores objects efficiently: pack files +---------------------------------------------- + +We've seen how git stores each object in a file named after the +object's SHA1 hash. + +Unfortunately this system becomes inefficient once a project has a +lot of objects. Try this on an old project: + +------------------------------------------------ +$ git count-objects +6930 objects, 47620 kilobytes +------------------------------------------------ + +The first number is the number of objects which are kept in +individual files. The second is the amount of space taken up by +those "loose" objects. + +You can save space and make git faster by moving these loose objects in +to a "pack file", which stores a group of objects in an efficient +compressed format; the details of how pack files are formatted can be +found in link:technical/pack-format.txt[technical/pack-format.txt]. + +To put the loose objects into a pack, just run git repack: + +------------------------------------------------ +$ git repack +Generating pack... +Done counting 6020 objects. +Deltifying 6020 objects. + 100% (6020/6020) done +Writing 6020 objects. + 100% (6020/6020) done +Total 6020, written 6020 (delta 4070), reused 0 (delta 0) +Pack pack-3e54ad29d5b2e05838c75df582c65257b8d08e1c created. +------------------------------------------------ + +You can then run + +------------------------------------------------ +$ git prune +------------------------------------------------ + +to remove any of the "loose" objects that are now contained in the +pack. This will also remove any unreferenced objects (which may be +created when, for example, you use "git reset" to remove a commit). +You can verify that the loose objects are gone by looking at the +.git/objects directory or by running + +------------------------------------------------ +$ git count-objects +0 objects, 0 kilobytes +------------------------------------------------ + +Although the object files are gone, any commands that refer to those +objects will work exactly as they did before. + +The gitlink:git-gc[1] command performs packing, pruning, and more for +you, so is normally the only high-level command you need. + +[[dangling-objects]] +Dangling objects +---------------- + +The gitlink:git-fsck[1] command will sometimes complain about dangling +objects. They are not a problem. + +The most common cause of dangling objects is that you've rebased a +branch, or you have pulled from somebody else who rebased a branch--see +<<cleaning-up-history>>. In that case, the old head of the original +branch still exists, as does obviously everything it pointed to. The +branch pointer itself just doesn't, since you replaced it with another +one. + +There are also other situations too that cause dangling objects. For +example, a "dangling blob" may arise because you did a "git add" of a +file, but then, before you actually committed it and made it part of the +bigger picture, you changed something else in that file and committed +that *updated* thing - the old state that you added originally ends up +not being pointed to by any commit or tree, so it's now a dangling blob +object. + +Similarly, when the "recursive" merge strategy runs, and finds that +there are criss-cross merges and thus more than one merge base (which is +fairly unusual, but it does happen), it will generate one temporary +midway tree (or possibly even more, if you had lots of criss-crossing +merges and more than two merge bases) as a temporary internal merge +base, and again, those are real objects, but the end result will not end +up pointing to them, so they end up "dangling" in your repository. + +Generally, dangling objects aren't anything to worry about. They can +even be very useful: if you screw something up, the dangling objects can +be how you recover your old tree (say, you did a rebase, and realized +that you really didn't want to - you can look at what dangling objects +you have, and decide to reset your head to some old dangling state). + +For commits, the most useful thing to do with dangling objects tends to +be to do a simple + +------------------------------------------------ +$ gitk <dangling-commit-sha-goes-here> --not --all +------------------------------------------------ + +For blobs and trees, you can't do the same, but you can examine them. +You can just do + +------------------------------------------------ +$ git show <dangling-blob/tree-sha-goes-here> +------------------------------------------------ + +to show what the contents of the blob were (or, for a tree, basically +what the "ls" for that directory was), and that may give you some idea +of what the operation was that left that dangling object. + +Usually, dangling blobs and trees aren't very interesting. They're +almost always the result of either being a half-way mergebase (the blob +will often even have the conflict markers from a merge in it, if you +have had conflicting merges that you fixed up by hand), or simply +because you interrupted a "git fetch" with ^C or something like that, +leaving _some_ of the new objects in the object database, but just +dangling and useless. + +Anyway, once you are sure that you're not interested in any dangling +state, you can just prune all unreachable objects: + +------------------------------------------------ +$ git prune +------------------------------------------------ + +and they'll be gone. But you should only run "git prune" on a quiescent +repository - it's kind of like doing a filesystem fsck recovery: you +don't want to do that while the filesystem is mounted. + +(The same is true of "git-fsck" itself, btw - but since +git-fsck never actually *changes* the repository, it just reports +on what it found, git-fsck itself is never "dangerous" to run. +Running it while somebody is actually changing the repository can cause +confusing and scary messages, but it won't actually do anything bad. In +contrast, running "git prune" while somebody is actively changing the +repository is a *BAD* idea). + +Glossary of git terms +===================== + +include::glossary.txt[] + +Notes and todo list for this manual +=================================== + +This is a work in progress. + +The basic requirements: + - It must be readable in order, from beginning to end, by + someone intelligent with a basic grasp of the unix + commandline, but without any special knowledge of git. If + necessary, any other prerequisites should be specifically + mentioned as they arise. + - Whenever possible, section headings should clearly describe + the task they explain how to do, in language that requires + no more knowledge than necessary: for example, "importing + patches into a project" rather than "the git-am command" + +Think about how to create a clear chapter dependency graph that will +allow people to get to important topics without necessarily reading +everything in between. + +Say something about .gitignore. + +Scan Documentation/ for other stuff left out; in particular: + howto's + some of technical/? + hooks + list of commands in gitlink:git[1] + +Scan email archives for other stuff left out + +Scan man pages to see if any assume more background than this manual +provides. + +Simplify beginning by suggesting disconnected head instead of +temporary branch creation? + +Add more good examples. Entire sections of just cookbook examples +might be a good idea; maybe make an "advanced examples" section a +standard end-of-chapter section? + +Include cross-references to the glossary, where appropriate. + +Document shallow clones? See draft 1.5.0 release notes for some +documentation. + +Add a section on working with other version control systems, including +CVS, Subversion, and just imports of series of release tarballs. + +More details on gitweb? + +Write a chapter on using plumbing and writing scripts. |