diff options
78 files changed, 5716 insertions, 584 deletions
diff --git a/.gitignore b/.gitignore index d7e8d2ac0d..5be239a4aa 100644 --- a/.gitignore +++ b/.gitignore @@ -2,6 +2,7 @@ GIT-VERSION-FILE git git-add git-am +git-annotate git-apply git-applymbox git-applypatch @@ -22,6 +23,7 @@ git-convert-objects git-count-objects git-cvsexportcommit git-cvsimport +git-cvsserver git-daemon git-diff git-diff-files @@ -53,6 +55,7 @@ git-mailsplit git-merge git-merge-base git-merge-index +git-merge-tree git-merge-octopus git-merge-one-file git-merge-ours @@ -60,6 +63,7 @@ git-merge-recursive git-merge-resolve git-merge-stupid git-mktag +git-mktree git-name-rev git-mv git-pack-redundant @@ -84,6 +88,7 @@ git-resolve git-rev-list git-rev-parse git-revert +git-rm git-send-email git-send-pack git-sh-setup diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 89e461402e..7e293834d1 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -7,7 +7,7 @@ git-add - Add files to the index file. SYNOPSIS -------- -'git-add' [-n] [-v] <file>... +'git-add' [-n] [-v] [--] <file>... DESCRIPTION ----------- @@ -26,6 +26,11 @@ OPTIONS -v:: Be verbose. +--:: + This option can be used to separate command-line options from + the list of files, (useful when filenames might be mistaken + for command-line options). + DISCUSSION ---------- diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt new file mode 100644 index 0000000000..88f07ff15d --- /dev/null +++ b/Documentation/git-cvsserver.txt @@ -0,0 +1,89 @@ +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 gitcvs only works over ssh connections. + + +INSTALLATION +------------ +1. Put server.pl somewhere useful on the same machine that is hosting your git repos + +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 + logfile=/path/to/logfile + + n.b. you need to ensure each user that is going to invoke server.pl has + write access to the log file. + +5. On each 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. + CVS_SERVER should be set to the server.pl script that has been put on the + remote machine. + +6. Clients should now be able to check out modules (where modules are the names + of branches in git). + $ cvs co -d mylocaldir master + +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-ls-files.txt b/Documentation/git-ls-files.txt index fe5341295c..e813f84202 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -8,12 +8,14 @@ git-ls-files - Information about files in the index/working directory SYNOPSIS -------- -'git-ls-files' [-z] [-t] +[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] [--] [<file>]\* DESCRIPTION @@ -72,6 +74,10 @@ OPTIONS 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: @@ -82,6 +88,10 @@ OPTIONS 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 diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 2d67d3911e..4cb2e83faa 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -8,7 +8,10 @@ git-pack-objects - Create a packed archive of objects. SYNOPSIS -------- -'git-pack-objects' [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list +[verse] +'git-pack-objects' [-q] [--no-reuse-delta] [--non-empty] + [--local] [--incremental] [--window=N] [--depth=N] + {--stdout | base-name} < object-list DESCRIPTION @@ -32,6 +35,10 @@ 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 ------- @@ -74,6 +81,18 @@ base-name:: Only create a packed archive if it would contain at least one object. +-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. + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 5b891105b2..6f4a48a109 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -43,6 +43,12 @@ 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. ++ Some short-cut notations are also supported. + * `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 16c158f439..f037d1280e 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -7,14 +7,54 @@ git-rebase - Rebase local commits to new upstream head. SYNOPSIS -------- -'git-rebase' <upstream> [<head>] +'git-rebase' [--onto <newbase>] <upstream> [<branch>] DESCRIPTION ----------- -Rebases local commits to the new head of the upstream tree. +git-rebase applies to <upstream> (or optionally to <newbase>) commits +from <branch> that do not appear in <upstream>. When <branch> is not +specified it defaults to the current branch (HEAD). + +When git-rebase is complete, <branch> will be updated to point to the +newly created line of commit objects, so the previous line will not be +accessible unless there are other references to it already. + +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 the following commands: + + git-rebase master + git-rebase master topic + +would be: + + A'--B'--C' topic + / + D---E---F---G master + +While, starting from the same point, the result of the following +commands: + + git-rebase --onto master~1 master + git-rebase --onto master~1 master topic + +would be: + + A'--B'--C' topic + / + D---E---F---G master OPTIONS ------- +<newbase>:: + Starting point at which to create the new commits. If the + --onto option is not specified, the starting point is + <upstream>. + <upstream>:: Upstream branch to compare against. diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 9060fe8897..6c0f792dad 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -9,7 +9,7 @@ objects into pack files. SYNOPSIS -------- -'git-repack' [-a] [-d] [-l] [-n] +'git-repack' [-a] [-d] [-f] [-l] [-n] [-q] DESCRIPTION ----------- @@ -43,6 +43,14 @@ OPTIONS 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`. diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt new file mode 100644 index 0000000000..401bfb2d9c --- /dev/null +++ b/Documentation/git-rm.txt @@ -0,0 +1,89 @@ +git-rm(1) +========= + +NAME +---- +git-rm - Remove files from the working tree and from the index. + +SYNOPSIS +-------- +'git-rm' [-f] [-n] [-v] [--] <file>... + +DESCRIPTION +----------- +A convenience wrapper for git-update-index --remove. For those coming +from cvs, git-rm provides an operation similar to "cvs rm" or "cvs +remove". + + +OPTIONS +------- +<file>...:: + Files to remove from the index and optionally, from the + working tree as well. + +-f:: + Remove files from the working tree as well as from the index. + +-n:: + Don't actually remove the file(s), just show if they exist in + the index. + +-v:: + Be verbose. + +--:: + This option can be used to separate command-line options from + the list of files, (useful when filenames might be mistaken + for command-line options). + + +DISCUSSION +---------- + +The list of <file> given to the command is fed to `git-ls-files` +command to list files that are registered in the index and +are not ignored/excluded by `$GIT_DIR/info/exclude` file or +`.gitignore` file in each directory. This means two things: + +. You can put the name of a directory on the command line, and the + command will remove all files in it and its subdirectories (the + directories themselves are never removed from the working tree); + +. Giving the name of a file that is not in the index does not + remove that file. + + +EXAMPLES +-------- +git-rm Documentation/\\*.txt:: + + Removes all `\*.txt` files from the index that are under the + `Documentation` directory and any of its subdirectories. The + files are not removed from the working tree. ++ +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. The files + are removed from the index, and (because of the -f option), + from the working tree as well. Because this example lets the + shell expand the asterisk (i.e. you are listing the files + explicitly), it does not remove `subdir/git-foo.sh`. + + +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-update-index.txt b/Documentation/git-update-index.txt index c74311dabd..0a1b0ad56d 100644 --- a/Documentation/git-update-index.txt +++ b/Documentation/git-update-index.txt @@ -8,11 +8,14 @@ git-update-index - Modifies the index or directory cache 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] [--info-only] [--index-info] [-z] [--stdin] [--verbose] @@ -65,6 +68,18 @@ OPTIONS --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). + --info-only:: Do not create objects in the object database for all <file> arguments that follow this flag; just insert @@ -193,6 +208,37 @@ $ git ls-files -s ------------ +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: @@ -201,6 +247,35 @@ 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 ------------- @@ -213,6 +288,9 @@ 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=`. +The command looks at `core.ignorestat` configuration variable. See +'Using "assume unchanged" bit' section above. + See Also -------- @@ -55,6 +55,11 @@ all: # # Define NO_ICONV if your libc does not properly support iconv. # +# Define NO_ACCURATE_DIFF if your diff program at least sometimes misses +# a missing newline at the end of the file. +# +# Define NO_PYTHON if you want to loose all benefits of the recursive merge. +# # Define COLLISION_CHECK below if you believe that SHA1's # 1461501637330902918203684832716283019655932542976 hashes do not give you # sufficient guarantee that no collisions between objects will ever happen. @@ -72,6 +77,12 @@ GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE @$(SHELL_PATH) ./GIT-VERSION-GEN -include GIT-VERSION-FILE +uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') +uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') +uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') +uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') +uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') + # CFLAGS and LDFLAGS are for the users to override from the command line. CFLAGS = -g -O2 -Wall @@ -82,7 +93,7 @@ STRIP ?= strip prefix = $(HOME) bindir = $(prefix)/bin -gitexecdir = $(prefix)/bin +gitexecdir = $(bindir) template_dir = $(prefix)/share/git-core/templates/ GIT_PYTHON_DIR = $(prefix)/share/git-core/python # DESTDIR= @@ -109,7 +120,7 @@ SCRIPT_SH = \ git-merge-one-file.sh git-parse-remote.sh \ git-prune.sh git-pull.sh git-push.sh git-rebase.sh \ git-repack.sh git-request-pull.sh git-reset.sh \ - git-resolve.sh git-revert.sh git-sh-setup.sh \ + git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \ git-tag.sh git-verify-tag.sh git-whatchanged.sh \ git-applymbox.sh git-applypatch.sh git-am.sh \ git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \ @@ -119,6 +130,7 @@ SCRIPT_SH = \ SCRIPT_PERL = \ git-archimport.perl git-cvsimport.perl git-relink.perl \ git-shortlog.perl git-fmt-merge-msg.perl git-rerere.perl \ + git-annotate.perl git-cvsserver.perl \ git-svnimport.perl git-mv.perl git-cvsexportcommit.perl SCRIPT_PYTHON = \ @@ -131,7 +143,7 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ # The ones that do not have to link with lcrypto nor lz. SIMPLE_PROGRAMS = \ - git-get-tar-commit-id$X git-mailinfo$X git-mailsplit$X \ + git-get-tar-commit-id$X git-mailsplit$X \ git-stripspace$X git-daemon$X # ... and all the rest that could be moved out of bindir to gitexecdir @@ -141,9 +153,9 @@ PROGRAMS = \ git-convert-objects$X git-diff-files$X \ git-diff-index$X git-diff-stages$X \ git-diff-tree$X git-fetch-pack$X git-fsck-objects$X \ - git-hash-object$X git-index-pack$X git-init-db$X \ - git-local-fetch$X git-ls-files$X git-ls-tree$X git-merge-base$X \ - git-merge-index$X git-mktag$X git-pack-objects$X git-patch-id$X \ + git-hash-object$X git-index-pack$X git-init-db$X git-local-fetch$X \ + git-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \ + git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \ git-peek-remote$X git-prune-packed$X git-read-tree$X \ git-receive-pack$X git-rev-list$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ @@ -153,7 +165,7 @@ PROGRAMS = \ git-upload-pack$X git-verify-pack$X git-write-tree$X \ git-update-ref$X git-symbolic-ref$X git-check-ref-format$X \ git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \ - git-describe$X + git-describe$X git-merge-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -199,12 +211,6 @@ LIB_OBJS = \ LIBS = $(LIB_FILE) LIBS += -lz -# Shell quote; -# Result of this needs to be placed inside '' -shq = $(subst ','\'',$(1)) -# This has surrounding '' -shellquote = '$(call shq,$(1))' - # # Platform specific tweaks # @@ -212,10 +218,6 @@ shellquote = '$(call shq,$(1))' # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... -uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') -uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') -uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') -uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') ifeq ($(uname_S),Darwin) NEEDS_SSL_WITH_CRYPTO = YesPlease @@ -230,10 +232,10 @@ endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease NEEDS_NSL = YesPlease - NEEDS_LIBICONV = YesPlease SHELL_PATH = /bin/bash NO_STRCASESTR = YesPlease ifeq ($(uname_R),5.8) + NEEDS_LIBICONV = YesPlease NO_UNSETENV = YesPlease NO_SETENV = YesPlease endif @@ -273,6 +275,16 @@ ifeq ($(uname_S),AIX) NO_STRCASESTR=YesPlease NEEDS_LIBICONV=YesPlease endif +ifeq ($(uname_S),IRIX64) + NO_IPV6=YesPlease + NO_SETENV=YesPlease + NO_STRCASESTR=YesPlease + NO_SOCKADDR_STORAGE=YesPlease + SHELL_PATH=/usr/gnu/bin/bash + ALL_CFLAGS += -DPATH_MAX=1024 + # for now, build 32-bit version + ALL_LDFLAGS += -L/usr/lib32 +endif ifneq (,$(findstring arm,$(uname_M))) ARM_SHA1 = YesPlease endif @@ -282,8 +294,10 @@ endif ifdef WITH_OWN_SUBPROCESS_PY PYMODULES += compat/subprocess.py else - ifneq ($(shell $(PYTHON_PATH) -c 'import subprocess;print"OK"' 2>/dev/null),OK) - PYMODULES += compat/subprocess.py + ifeq ($(NO_PYTHON),) + ifneq ($(shell $(PYTHON_PATH) -c 'import subprocess;print"OK"' 2>/dev/null),OK) + PYMODULES += compat/subprocess.py + endif endif endif @@ -403,8 +417,25 @@ else endif endif endif +ifdef NO_ACCURATE_DIFF + ALL_CFLAGS += -DNO_ACCURATE_DIFF +endif + +# Shell quote (do not use $(call) to accomodate ancient setups); + +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) -ALL_CFLAGS += -DSHA1_HEADER=$(call shellquote,$(SHA1_HEADER)) $(COMPAT_CFLAGS) +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +gitexecdir_SQ = $(subst ','\'',$(gitexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) + +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH)) +GIT_PYTHON_DIR_SQ = $(subst ','\'',$(GIT_PYTHON_DIR)) + +ALL_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS) LIB_OBJS += $(COMPAT_OBJS) export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir ### Build rules @@ -423,23 +454,24 @@ git$X: git.c $(LIB_FILE) $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh rm -f $@ - sed -e '1s|#!.*/sh|#!$(call shq,$(SHELL_PATH))|' \ + sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ + -e 's/@@NO_PYTHON@@/$(NO_PYTHON)/g' \ $@.sh >$@ chmod +x $@ $(patsubst %.perl,%,$(SCRIPT_PERL)) : % : %.perl rm -f $@ - sed -e '1s|#!.*perl|#!$(call shq,$(PERL_PATH))|' \ + sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ $@.perl >$@ chmod +x $@ $(patsubst %.py,%,$(SCRIPT_PYTHON)) : % : %.py rm -f $@ - sed -e '1s|#!.*python|#!$(call shq,$(PYTHON_PATH))|' \ - -e 's|@@GIT_PYTHON_PATH@@|$(call shq,$(GIT_PYTHON_DIR))|g' \ + sed -e '1s|#!.*python|#!$(PYTHON_PATH_SQ)|' \ + -e 's|@@GIT_PYTHON_PATH@@|$(GIT_PYTHON_DIR_SQ)|g' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ $@.py >$@ chmod +x $@ @@ -465,32 +497,42 @@ git$X git.spec \ %.o: %.S $(CC) -o $*.o -c $(ALL_CFLAGS) $< -exec_cmd.o: ALL_CFLAGS += -DGIT_EXEC_PATH=\"$(gitexecdir)\" +exec_cmd.o: exec_cmd.c + $(CC) -o $*.o -c $(ALL_CFLAGS) '-DGIT_EXEC_PATH="$(gitexecdir_SQ)"' $< git-%$X: %.o $(LIB_FILE) $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) -git-mailinfo$X : SIMPLE_LIB += $(LIB_4_ICONV) $(SIMPLE_PROGRAMS) : $(LIB_FILE) $(SIMPLE_PROGRAMS) : git-%$X : %.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ $(LIB_FILE) $(SIMPLE_LIB) -git-http-fetch$X: fetch.o http.o -git-http-push$X: http.o +git-mailinfo$X: mailinfo.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIB_FILE) $(SIMPLE_LIB) $(LIB_4_ICONV) + git-local-fetch$X: fetch.o git-ssh-fetch$X: rsh.o fetch.o git-ssh-upload$X: rsh.o git-ssh-pull$X: rsh.o fetch.o git-ssh-push$X: rsh.o -git-http-fetch$X: LIBS += $(CURL_LIBCURL) -git-http-push$X: LIBS += $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) -git-rev-list$X: LIBS += $(OPENSSL_LIBSSL) +git-http-fetch$X: fetch.o http.o http-fetch.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(CURL_LIBCURL) + +git-http-push$X: http.o http-push.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) + +git-rev-list$X: rev-list.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(OPENSSL_LIBSSL) init-db.o: init-db.c $(CC) -c $(ALL_CFLAGS) \ - -DDEFAULT_GIT_TEMPLATE_DIR=$(call shellquote,"$(template_dir)") $*.c + -DDEFAULT_GIT_TEMPLATE_DIR='"$(template_dir_SQ)"' $*.c $(LIB_OBJS): $(LIB_H) $(patsubst git-%$X,%.o,$(PROGRAMS)): $(LIB_H) @@ -505,6 +547,12 @@ doc: ### Testing rules +# GNU make supports exporting all variables by "export" without parameters. +# However, the environment gets quite big, and some programs have problems +# with that. + +export NO_PYTHON + test: all $(MAKE) -C t/ all @@ -522,13 +570,13 @@ check: ### Installation rules install: all - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(bindir)) - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(gitexecdir)) - $(INSTALL) $(ALL_PROGRAMS) $(call shellquote,$(DESTDIR)$(gitexecdir)) - $(INSTALL) git$X gitk $(call shellquote,$(DESTDIR)$(bindir)) + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(gitexecdir_SQ)' + $(INSTALL) $(ALL_PROGRAMS) '$(DESTDIR_SQ)$(gitexecdir_SQ)' + $(INSTALL) git$X gitk '$(DESTDIR_SQ)$(bindir_SQ)' $(MAKE) -C templates install - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(GIT_PYTHON_DIR)) - $(INSTALL) $(PYMODULES) $(call shellquote,$(DESTDIR)$(GIT_PYTHON_DIR)) + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' + $(INSTALL) $(PYMODULES) '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' install-doc: $(MAKE) -C Documentation install @@ -1142,6 +1142,14 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) size -= len; } +#ifdef NO_ACCURATE_DIFF + if (oldsize > 0 && old[oldsize - 1] == '\n' && + newsize > 0 && new[newsize - 1] == '\n') { + oldsize--; + newsize--; + } +#endif + offset = find_offset(buf, desc->size, old, oldsize, frag->newpos); if (offset >= 0) { int diff = newsize - oldsize; @@ -1309,7 +1317,7 @@ static int check_patch(struct patch *patch) return -1; } - changed = ce_match_stat(active_cache[pos], &st); + changed = ce_match_stat(active_cache[pos], &st, 1); if (changed) return error("%s: does not match index", old_name); @@ -91,6 +91,7 @@ struct cache_entry { #define CE_NAMEMASK (0x0fff) #define CE_STAGEMASK (0x3000) #define CE_UPDATE (0x4000) +#define CE_VALID (0x8000) #define CE_STAGESHIFT 12 #define create_ce_flags(len, stage) htons((len) | ((stage) << CE_STAGESHIFT)) @@ -144,8 +145,8 @@ extern int add_cache_entry(struct cache_entry *ce, int option); extern int remove_cache_entry_at(int pos); extern int remove_file_from_cache(const char *path); extern int ce_same_name(struct cache_entry *a, struct cache_entry *b); -extern int ce_match_stat(struct cache_entry *ce, struct stat *st); -extern int ce_modified(struct cache_entry *ce, struct stat *st); +extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int); +extern int ce_modified(struct cache_entry *ce, struct stat *st, int); extern int ce_path_match(const struct cache_entry *ce, const char **pathspec); extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type); extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object); @@ -161,6 +162,7 @@ extern int commit_index_file(struct cache_file *); extern void rollback_index_file(struct cache_file *); extern int trust_executable_bit; +extern int assume_unchanged; extern int only_use_symrefs; extern int diff_rename_limit_default; extern int shared_repository; @@ -246,8 +248,8 @@ void datestamp(char *buf, int bufsize); unsigned long approxidate(const char *); extern int setup_ident(void); -extern const char *git_author_info(void); -extern const char *git_committer_info(void); +extern const char *git_author_info(int); +extern const char *git_committer_info(int); struct checkout { const char *base_dir; diff --git a/checkout-index.c b/checkout-index.c index 53dd8cba6f..957b4a86b0 100644 --- a/checkout-index.c +++ b/checkout-index.c @@ -116,6 +116,7 @@ int main(int argc, char **argv) int all = 0; prefix = setup_git_directory(); + git_config(git_default_config); prefix_length = prefix ? strlen(prefix) : 0; if (read_cache() < 0) { diff --git a/commit-tree.c b/commit-tree.c index b1c8dca48d..88871b022d 100644 --- a/commit-tree.c +++ b/commit-tree.c @@ -118,8 +118,8 @@ int main(int argc, char **argv) add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i])); /* Person/date information */ - add_buffer(&buffer, &size, "author %s\n", git_author_info()); - add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info()); + add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); + add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1)); /* And add the comment */ while (fgets(comment, sizeof(comment), stdin) != NULL) @@ -212,7 +212,8 @@ int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) if (memcmp(bufptr, "tree ", 5)) return error("bogus commit object %s", sha1_to_hex(item->object.sha1)); if (get_sha1_hex(bufptr + 5, parent) < 0) - return error("bad tree pointer in commit %s\n", sha1_to_hex(item->object.sha1)); + return error("bad tree pointer in commit %s", + sha1_to_hex(item->object.sha1)); item->tree = lookup_tree(parent); if (item->tree) n_refs++; @@ -222,6 +222,11 @@ int git_default_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.ignorestat")) { + assume_unchanged = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "core.symrefsonly")) { only_use_symrefs = git_config_bool(var, value); return 0; diff --git a/contrib/git-svn/.gitignore b/contrib/git-svn/.gitignore new file mode 100644 index 0000000000..d8d87e3af9 --- /dev/null +++ b/contrib/git-svn/.gitignore @@ -0,0 +1,4 @@ +git-svn +git-svn.xml +git-svn.html +git-svn.1 diff --git a/contrib/git-svn/Makefile b/contrib/git-svn/Makefile new file mode 100644 index 0000000000..a330c617d2 --- /dev/null +++ b/contrib/git-svn/Makefile @@ -0,0 +1,32 @@ +all: git-svn + +prefix?=$(HOME) +bindir=$(prefix)/bin +mandir=$(prefix)/man +man1=$(mandir)/man1 +INSTALL?=install +doc_conf=../../Documentation/asciidoc.conf +-include ../../config.mak + +git-svn: git-svn.perl + cp $< $@ + chmod +x $@ + +install: all + $(INSTALL) -d -m755 $(DESTDIR)$(bindir) + $(INSTALL) git-svn $(DESTDIR)$(bindir) + +install-doc: doc + $(INSTALL) git-svn.1 $(DESTDIR)$(man1) + +doc: git-svn.1 +git-svn.1 : git-svn.xml + xmlto man git-svn.xml +git-svn.xml : git-svn.txt + asciidoc -b docbook -d manpage \ + -f ../../Documentation/asciidoc.conf $< +test: + cd t && $(SHELL) ./t0000-contrib-git-svn.sh + +clean: + rm -f git-svn *.xml *.html *.1 diff --git a/contrib/git-svn/git-svn b/contrib/git-svn/git-svn.perl index 71a8b3b2e6..a32ce15701 100755 --- a/contrib/git-svn/git-svn +++ b/contrib/git-svn/git-svn.perl @@ -1,4 +1,6 @@ #!/usr/bin/env perl +# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net> +# License: GPL v2 or later use warnings; use strict; use vars qw/ $AUTHOR $VERSION @@ -6,7 +8,7 @@ use vars qw/ $AUTHOR $VERSION $GIT_SVN_INDEX $GIT_SVN $GIT_DIR $REV_DIR/; $AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; -$VERSION = '0.9.0'; +$VERSION = '0.9.1'; $GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git"; $GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn'; $GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index"; @@ -21,7 +23,7 @@ $ENV{LC_ALL} = 'C'; # If SVN:: library support is added, please make the dependencies # optional and preserve the capability to use the command-line client. -# See what I do with XML::Simple to make the dependency optional. +# use eval { require SVN::... } to make it lazy load use Carp qw/croak/; use IO::File qw//; use File::Basename qw/dirname basename/; @@ -30,7 +32,8 @@ use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use File::Spec qw//; my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{6,40}/; -my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit); +my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, + $_find_copies_harder, $_l, $_version); GetOptions( 'revision|r=s' => \$_revision, 'no-ignore-externals' => \$_no_ignore_ext, @@ -38,7 +41,10 @@ GetOptions( 'revision|r=s' => \$_revision, 'edit|e' => \$_edit, 'rmdir' => \$_rmdir, 'help|H|h' => \$_help, - 'no-stop-copy' => \$_no_stop_copy ); + 'find-copies-harder' => \$_find_copies_harder, + 'l=i' => \$_l, + 'version|V' => \$_version, + 'no-stop-on-copy' => \$_no_stop_copy ); my %cmd = ( fetch => [ \&fetch, "Download new revisions from SVN" ], init => [ \&init, "Initialize and fetch (import)"], @@ -63,6 +69,7 @@ foreach (keys %cmd) { } } usage(0) if $_help; +version() if $_version; usage(1) unless (defined $cmd); svn_check_ignore_externals(); $cmd{$cmd}->[0]->(@ARGV); @@ -88,6 +95,11 @@ and want to keep them separate. exit $exit; } +sub version { + print "git-svn version $VERSION\n"; + exit 0; +} + sub rebuild { $SVN_URL = shift or undef; my $repo_uuid; @@ -174,8 +186,7 @@ sub fetch { push @log_args, "-r$_revision"; push @log_args, '--stop-on-copy' unless $_no_stop_copy; - eval { require XML::Simple or croak $! }; - my $svn_log = $@ ? svn_log_raw(@log_args) : svn_log_xml(@log_args); + my $svn_log = svn_log_raw(@log_args); @$svn_log = sort { $a->{revision} <=> $b->{revision} } @$svn_log; my $base = shift @$svn_log or croak "No base revision!\n"; @@ -213,14 +224,21 @@ sub commit { print "Reading from stdin...\n"; @commits = (); while (<STDIN>) { - if (/^([a-f\d]{6,40})\b/) { + if (/\b([a-f\d]{6,40})\b/) { unshift @commits, $1; } } } my @revs; - foreach (@commits) { - push @revs, (safe_qx('git-rev-parse',$_)); + foreach my $c (@commits) { + chomp(my @tmp = safe_qx('git-rev-parse',$c)); + if (scalar @tmp == 1) { + push @revs, $tmp[0]; + } elsif (scalar @tmp > 1) { + push @revs, reverse (safe_qx('git-rev-list',@tmp)); + } else { + die "Failed to rev-parse $c\n"; + } } chomp @revs; @@ -229,7 +247,11 @@ sub commit { my $svn_current_rev = svn_info('.')->{'Last Changed Rev'}; foreach my $c (@revs) { print "Committing $c\n"; - svn_checkout_tree($svn_current_rev, $c); + my $mods = svn_checkout_tree($svn_current_rev, $c); + if (scalar @$mods == 0) { + print "Skipping, no changes detected\n"; + next; + } $svn_current_rev = svn_commit_tree($svn_current_rev, $c); } print "Done committing ",scalar @revs," revisions to SVN\n"; @@ -258,9 +280,9 @@ sub setup_git_svn { } sub assert_svn_wc_clean { - my ($svn_rev, $commit) = @_; + my ($svn_rev, $treeish) = @_; croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/); - croak "$commit is not a sha1!\n" unless ($commit =~ /^$sha1$/o); + croak "$treeish is not a sha1!\n" unless ($treeish =~ /^$sha1$/o); my $svn_info = svn_info('.'); if ($svn_rev != $svn_info->{'Last Changed Rev'}) { croak "Expected r$svn_rev, got r", @@ -273,12 +295,42 @@ sub assert_svn_wc_clean { print STDERR $_ foreach @status; croak; } - my ($tree_a) = grep(/^tree $sha1$/o,`git-cat-file commit $commit`); - $tree_a =~ s/^tree //; - chomp $tree_a; - chomp(my $tree_b = `GIT_INDEX_FILE=$GIT_SVN_INDEX git-write-tree`); - if ($tree_a ne $tree_b) { - croak "$svn_rev != $commit, $tree_a != $tree_b\n"; + assert_tree($treeish); +} + +sub assert_tree { + my ($treeish) = @_; + croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o; + chomp(my $type = `git-cat-file -t $treeish`); + my $expected; + while ($type eq 'tag') { + chomp(($treeish, $type) = `git-cat-file tag $treeish`); + } + if ($type eq 'commit') { + $expected = (grep /^tree /,`git-cat-file commit $treeish`)[0]; + ($expected) = ($expected =~ /^tree ($sha1)$/); + die "Unable to get tree from $treeish\n" unless $expected; + } elsif ($type eq 'tree') { + $expected = $treeish; + } else { + die "$treeish is a $type, expected tree, tag or commit\n"; + } + + my $old_index = $ENV{GIT_INDEX_FILE}; + my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp'; + if (-e $tmpindex) { + unlink $tmpindex or croak $!; + } + $ENV{GIT_INDEX_FILE} = $tmpindex; + git_addremove(); + chomp(my $tree = `git-write-tree`); + if ($old_index) { + $ENV{GIT_INDEX_FILE} = $old_index; + } else { + delete $ENV{GIT_INDEX_FILE}; + } + if ($tree ne $expected) { + croak "Tree mismatch, Got: $tree, Expected: $expected\n"; } } @@ -289,7 +341,6 @@ sub parse_diff_tree { my @mods; while (<$diff_fh>) { chomp $_; # this gets rid of the trailing "\0" - print $_,"\n"; if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s $sha1\s($sha1)\s([MTCRAD])\d*$/xo) { push @mods, { mode_a => $1, mode_b => $2, @@ -300,36 +351,44 @@ sub parse_diff_tree { $state = 'file_b'; } } elsif ($state eq 'file_a') { - my $x = $mods[$#mods] or croak __LINE__,": Empty array\n"; + my $x = $mods[$#mods] or croak "Empty array\n"; if ($x->{chg} !~ /^(?:C|R)$/) { - croak __LINE__,": Error parsing $_, $x->{chg}\n"; + croak "Error parsing $_, $x->{chg}\n"; } $x->{file_a} = $_; $state = 'file_b'; } elsif ($state eq 'file_b') { - my $x = $mods[$#mods] or croak __LINE__,": Empty array\n"; + my $x = $mods[$#mods] or croak "Empty array\n"; if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) { - croak __LINE__,": Error parsing $_, $x->{chg}\n"; + croak "Error parsing $_, $x->{chg}\n"; } if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) { - croak __LINE__,": Error parsing $_, $x->{chg}\n"; + croak "Error parsing $_, $x->{chg}\n"; } $x->{file_b} = $_; $state = 'meta'; } else { - croak __LINE__,": Error parsing $_\n"; + croak "Error parsing $_\n"; } } close $diff_fh or croak $!; + return \@mods; } sub svn_check_prop_executable { my $m = shift; - if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) { - sys(qw(svn propset svn:executable 1), $m->{file_b}); + return if -l $m->{file_b}; + if ($m->{mode_b} =~ /755$/) { + chmod((0755 &~ umask),$m->{file_b}) or croak $!; + if ($m->{mode_a} !~ /755$/) { + sys(qw(svn propset svn:executable 1), $m->{file_b}); + } + -x $m->{file_b} or croak "$m->{file_b} is not executable!\n"; } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { sys(qw(svn propdel svn:executable), $m->{file_b}); + chmod((0644 &~ umask),$m->{file_b}) or croak $!; + -x $m->{file_b} and croak "$m->{file_b} is executable!\n"; } } @@ -340,81 +399,166 @@ sub svn_ensure_parent_path { sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn"); } +sub precommit_check { + my $mods = shift; + my (%rm_file, %rmdir_check, %added_check); + + my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 ); + foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { + if ($m->{chg} eq 'R') { + if (-d $m->{file_b}) { + err_dir_to_file("$m->{file_a} => $m->{file_b}"); + } + # dir/$file => dir/file/$file + my $dirname = dirname($m->{file_b}); + while ($dirname ne File::Spec->curdir) { + if ($dirname ne $m->{file_a}) { + $dirname = dirname($dirname); + next; + } + err_file_to_dir("$m->{file_a} => $m->{file_b}"); + } + # baz/zzz => baz (baz is a file) + $dirname = dirname($m->{file_a}); + while ($dirname ne File::Spec->curdir) { + if ($dirname ne $m->{file_b}) { + $dirname = dirname($dirname); + next; + } + err_dir_to_file("$m->{file_a} => $m->{file_b}"); + } + } + if ($m->{chg} =~ /^(D|R)$/) { + my $t = $1 eq 'D' ? 'file_b' : 'file_a'; + $rm_file{ $m->{$t} } = 1; + my $dirname = dirname( $m->{$t} ); + my $basename = basename( $m->{$t} ); + $rmdir_check{$dirname}->{$basename} = 1; + } elsif ($m->{chg} =~ /^(?:A|C)$/) { + if (-d $m->{file_b}) { + err_dir_to_file($m->{file_b}); + } + my $dirname = dirname( $m->{file_b} ); + my $basename = basename( $m->{file_b} ); + $added_check{$dirname}->{$basename} = 1; + while ($dirname ne File::Spec->curdir) { + if ($rm_file{$dirname}) { + err_file_to_dir($m->{file_b}); + } + $dirname = dirname $dirname; + } + } + } + return (\%rmdir_check, \%added_check); + + sub err_dir_to_file { + my $file = shift; + print STDERR "Node change from directory to file ", + "is not supported by Subversion: ",$file,"\n"; + exit 1; + } + sub err_file_to_dir { + my $file = shift; + print STDERR "Node change from file to directory ", + "is not supported by Subversion: ",$file,"\n"; + exit 1; + } +} + sub svn_checkout_tree { - my ($svn_rev, $commit) = @_; + my ($svn_rev, $treeish) = @_; my $from = file_to_s("$REV_DIR/$svn_rev"); assert_svn_wc_clean($svn_rev,$from); - print "diff-tree '$from' '$commit'\n"; + print "diff-tree '$from' '$treeish'\n"; my $pid = open my $diff_fh, '-|'; defined $pid or croak $!; if ($pid == 0) { - exec(qw(git-diff-tree -z -r -C), $from, $commit) or croak $!; + my @diff_tree = qw(git-diff-tree -z -r -C); + push @diff_tree, '--find-copies-harder' if $_find_copies_harder; + push @diff_tree, "-l$_l" if defined $_l; + exec(@diff_tree, $from, $treeish) or croak $!; } my $mods = parse_diff_tree($diff_fh); unless (@$mods) { # git can do empty commits, SVN doesn't allow it... - return $svn_rev; + return $mods; } - my %rm; - foreach my $m (@$mods) { + my ($rm, $add) = precommit_check($mods); + + my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); + foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { if ($m->{chg} eq 'C') { svn_ensure_parent_path( $m->{file_b} ); sys(qw(svn cp), $m->{file_a}, $m->{file_b}); - blob_to_file( $m->{sha1_b}, $m->{file_b}); + apply_mod_line_blob($m); svn_check_prop_executable($m); } elsif ($m->{chg} eq 'D') { - $rm{dirname $m->{file_b}}->{basename $m->{file_b}} = 1; sys(qw(svn rm --force), $m->{file_b}); } elsif ($m->{chg} eq 'R') { svn_ensure_parent_path( $m->{file_b} ); sys(qw(svn mv --force), $m->{file_a}, $m->{file_b}); - blob_to_file( $m->{sha1_b}, $m->{file_b}); + apply_mod_line_blob($m); svn_check_prop_executable($m); - $rm{dirname $m->{file_a}}->{basename $m->{file_a}} = 1; } elsif ($m->{chg} eq 'M') { - if ($m->{mode_b} =~ /^120/ && $m->{mode_a} =~ /^120/) { - unlink $m->{file_b} or croak $!; - blob_to_symlink($m->{sha1_b}, $m->{file_b}); - } else { - blob_to_file($m->{sha1_b}, $m->{file_b}); - } + apply_mod_line_blob($m); svn_check_prop_executable($m); } elsif ($m->{chg} eq 'T') { sys(qw(svn rm --force),$m->{file_b}); - if ($m->{mode_b} =~ /^120/ && $m->{mode_a} =~ /^100/) { - blob_to_symlink($m->{sha1_b}, $m->{file_b}); - } else { - blob_to_file($m->{sha1_b}, $m->{file_b}); - } - svn_check_prop_executable($m); + apply_mod_line_blob($m); sys(qw(svn add --force), $m->{file_b}); + svn_check_prop_executable($m); } elsif ($m->{chg} eq 'A') { svn_ensure_parent_path( $m->{file_b} ); - blob_to_file( $m->{sha1_b}, $m->{file_b}); - if ($m->{mode_b} =~ /755$/) { - chmod 0755, $m->{file_b}; - } + apply_mod_line_blob($m); sys(qw(svn add --force), $m->{file_b}); + svn_check_prop_executable($m); } else { croak "Invalid chg: $m->{chg}\n"; } } - if ($_rmdir) { - my $old_index = $ENV{GIT_INDEX_FILE}; - $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; - foreach my $dir (keys %rm) { - my $files = $rm{$dir}; - my @files; - foreach (safe_qx('svn','ls',$dir)) { - chomp; - push @files, $_ unless $files->{$_}; - } - sys(qw(svn rm),$dir) unless @files; - } - if ($old_index) { - $ENV{GIT_INDEX_FILE} = $old_index; - } else { - delete $ENV{GIT_INDEX_FILE}; + + assert_tree($treeish); + if ($_rmdir) { # remove empty directories + handle_rmdir($rm, $add); + } + assert_tree($treeish); + return $mods; +} + +# svn ls doesn't work with respect to the current working tree, but what's +# in the repository. There's not even an option for it... *sigh* +# (added files don't show up and removed files remain in the ls listing) +sub svn_ls_current { + my ($dir, $rm, $add) = @_; + chomp(my @ls = safe_qx('svn','ls',$dir)); + my @ret = (); + foreach (@ls) { + s#/$##; # trailing slashes are evil + push @ret, $_ unless $rm->{$dir}->{$_}; + } + if (exists $add->{$dir}) { + push @ret, keys %{$add->{$dir}}; + } + return \@ret; +} + +sub handle_rmdir { + my ($rm, $add) = @_; + + foreach my $dir (sort {length $b <=> length $a} keys %$rm) { + my $ls = svn_ls_current($dir, $rm, $add); + next if (scalar @$ls); + sys(qw(svn rm --force),$dir); + + my $dn = dirname $dir; + $rm->{ $dn }->{ basename $dir } = 1; + $ls = svn_ls_current($dn, $rm, $add); + while (scalar @$ls == 0 && $dn ne File::Spec->curdir) { + sys(qw(svn rm --force),$dn); + $dir = basename $dn; + $dn = dirname $dn; + $rm->{ $dn }->{ $dir } = 1; + $ls = svn_ls_current($dn, $rm, $add); } } } @@ -463,49 +607,6 @@ sub svn_commit_tree { return fetch("$rev_committed=$commit")->{revision}; } -sub svn_log_xml { - my (@log_args) = @_; - my $log_fh = IO::File->new_tmpfile or croak $!; - - my $pid = fork; - defined $pid or croak $!; - - if ($pid == 0) { - open STDOUT, '>&', $log_fh or croak $!; - exec (qw(svn log --xml), @log_args) or croak $! - } - - waitpid $pid, 0; - croak $? if $?; - - seek $log_fh, 0, 0; - my @svn_log; - my $log = XML::Simple::XMLin( $log_fh, - ForceArray => ['path','revision','logentry'], - KeepRoot => 0, - KeyAttr => { logentry => '+revision', - paths => '+path' }, - )->{logentry}; - foreach my $r (sort {$a <=> $b} keys %$log) { - my $log_msg = $log->{$r}; - my ($Y,$m,$d,$H,$M,$S) = ($log_msg->{date} =~ - /(\d{4})\-(\d\d)\-(\d\d)T - (\d\d)\:(\d\d)\:(\d\d)\.\d+Z$/x) - or croak "Failed to parse date: ", - $log->{$r}->{date}; - $log_msg->{date} = "+0000 $Y-$m-$d $H:$M:$S"; - - # XML::Simple can't handle <msg></msg> as a string: - if (ref $log_msg->{msg} eq 'HASH') { - $log_msg->{msg} = "\n"; - } else { - $log_msg->{msg} .= "\n"; - } - push @svn_log, $log->{$r}; - } - return \@svn_log; -} - sub svn_log_raw { my (@log_args) = @_; my $pid = open my $log_fh,'-|'; @@ -516,21 +617,42 @@ sub svn_log_raw { } my @svn_log; - my $state; + my $state = 'sep'; while (<$log_fh>) { chomp; if (/^\-{72}$/) { + if ($state eq 'msg') { + if ($svn_log[$#svn_log]->{lines}) { + $svn_log[$#svn_log]->{msg} .= $_."\n"; + unless(--$svn_log[$#svn_log]->{lines}) { + $state = 'sep'; + } + } else { + croak "Log parse error at: $_\n", + $svn_log[$#svn_log]->{revision}, + "\n"; + } + next; + } + if ($state ne 'sep') { + croak "Log parse error at: $_\n", + "state: $state\n", + $svn_log[$#svn_log]->{revision}, + "\n"; + } $state = 'rev'; # if we have an empty log message, put something there: if (@svn_log) { $svn_log[$#svn_log]->{msg} ||= "\n"; + delete $svn_log[$#svn_log]->{lines}; } next; } if ($state eq 'rev' && s/^r(\d+)\s*\|\s*//) { my $rev = $1; - my ($author, $date) = split(/\s*\|\s*/, $_, 2); + my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3); + ($lines) = ($lines =~ /(\d+)/); my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ /(\d{4})\-(\d\d)\-(\d\d)\s (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) @@ -538,6 +660,7 @@ sub svn_log_raw { my %log_msg = ( revision => $rev, date => "$tz $Y-$m-$d $H:$M:$S", author => $author, + lines => $lines, msg => '' ); push @svn_log, \%log_msg; $state = 'msg_start'; @@ -547,7 +670,15 @@ sub svn_log_raw { if ($state eq 'msg_start' && /^$/) { $state = 'msg'; } elsif ($state eq 'msg') { - $svn_log[$#svn_log]->{msg} .= $_."\n"; + if ($svn_log[$#svn_log]->{lines}) { + $svn_log[$#svn_log]->{msg} .= $_."\n"; + unless (--$svn_log[$#svn_log]->{lines}) { + $state = 'sep'; + } + } else { + croak "Log parse error at: $_\n", + $svn_log[$#svn_log]->{revision},"\n"; + } } } close $log_fh or croak $?; @@ -581,10 +712,10 @@ sub sys { system(@_) == 0 or croak $? } sub git_addremove { system( "git-diff-files --name-only -z ". - " | git-update-index --remove -z --stdin; ". + " | git-update-index --remove -z --stdin && ". "git-ls-files -z --others ". "'--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude'". - " | git-update-index --add -z --stdin; " + " | git-update-index --add -z --stdin" ) == 0 or croak $? } @@ -693,10 +824,23 @@ sub git_commit { return $commit; } +sub apply_mod_line_blob { + my $m = shift; + if ($m->{mode_b} =~ /^120/) { + blob_to_symlink($m->{sha1_b}, $m->{file_b}); + } else { + blob_to_file($m->{sha1_b}, $m->{file_b}); + } +} + sub blob_to_symlink { my ($blob, $link) = @_; defined $link or croak "\$link not defined!\n"; croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; + if (-l $link || -f _) { + unlink $link or croak $!; + } + my $dest = `git-cat-file blob $blob`; # no newline, so no chomp symlink $dest, $link or croak $!; } @@ -705,6 +849,10 @@ sub blob_to_file { my ($blob, $file) = @_; defined $file or croak "\$file not defined!\n"; croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; + if (-l $file || -f _) { + unlink $file or croak $!; + } + open my $blob_fh, '>', $file or croak "$!: $file\n"; my $pid = fork; defined $pid or croak $!; diff --git a/contrib/git-svn/git-svn.txt b/contrib/git-svn/git-svn.txt index 4b79fb0be6..cf098d733a 100644 --- a/contrib/git-svn/git-svn.txt +++ b/contrib/git-svn/git-svn.txt @@ -99,6 +99,13 @@ OPTIONS default for objects that are commits, and forced on when committing tree objects. +-l<num>:: +--find-copies-harder:: + Both of these are only used with the 'commit' command. + + They are both passed directly to git-diff-tree see + git-diff-tree(1) for more information. + COMPATIBILITY OPTIONS --------------------- --no-ignore-externals:: @@ -142,7 +149,7 @@ Tracking and contributing to an Subversion managed-project: # Commit only the git commits you want to SVN:: git-svn commit <tree-ish> [<tree-ish_2> ...] # Commit all the git commits from my-branch that don't exist in SVN:: - git rev-list --pretty=oneline git-svn-HEAD..my-branch | git-svn commit + git commit git-svn-HEAD..my-branch # Something is committed to SVN, pull the latest into your branch:: git-svn fetch && git pull . git-svn-HEAD @@ -199,6 +206,13 @@ working trees with metadata files. svn:keywords can't be ignored in Subversion (at least I don't know of a way to ignore them). +Renamed and copied directories are not detected by git and hence not +tracked when committing to SVN. I do not plan on adding support for +this as it's quite difficult and time-consuming to get working for all +the possible corner cases (git doesn't do it, either). Renamed and +copied files are fully supported if they're similar enough for git to +detect them. + Author ------ Written by Eric Wong <normalperson@yhbt.net>. diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh new file mode 100644 index 0000000000..181dfe008b --- /dev/null +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -0,0 +1,216 @@ +#!/bin/sh +# +# Copyright (c) 2006 Eric Wong +# + + +PATH=$PWD/../:$PATH +test_description='git-svn tests' +if test -d ../../../t +then + cd ../../../t +else + echo "Must be run in contrib/git-svn/t" >&2 + exit 1 +fi + +. ./test-lib.sh + +GIT_DIR=$PWD/.git +GIT_SVN_DIR=$GIT_DIR/git-svn +SVN_TREE=$GIT_SVN_DIR/tree + +svnadmin >/dev/null 2>&1 +if test $? != 1 +then + test_expect_success 'skipping contrib/git-svn test' : + test_done + exit +fi + +svn >/dev/null 2>&1 +if test $? != 1 +then + test_expect_success 'skipping contrib/git-svn test' : + test_done + exit +fi + +svnrepo=$PWD/svnrepo + +set -e + +svnadmin create $svnrepo +svnrepo="file://$svnrepo/test-git-svn" + +mkdir import + +cd import + +echo foo > foo +ln -s foo foo.link +mkdir -p dir/a/b/c/d/e +echo 'deep dir' > dir/a/b/c/d/e/file +mkdir -p bar +echo 'zzz' > bar/zzz +echo '#!/bin/sh' > exec.sh +chmod +x exec.sh +svn import -m 'import for git-svn' . $svnrepo >/dev/null + +cd .. + +rm -rf import + +test_expect_success \ + 'initialize git-svn' \ + "git-svn init $svnrepo" + +test_expect_success \ + 'import an SVN revision into git' \ + 'git-svn fetch' + + +name='try a deep --rmdir with a commit' +git checkout -b mybranch git-svn-HEAD +mv dir/a/b/c/d/e/file dir/file +cp dir/file file +git update-index --add --remove dir/a/b/c/d/e/file dir/file file +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch && + test -d $SVN_TREE/dir && test ! -d $SVN_TREE/dir/a" + + +name='detect node change from file to directory #1' +mkdir dir/new_file +mv dir/file dir/new_file/file +mv dir/new_file dir/file +git update-index --remove dir/file +git update-index --add dir/file/file +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch' \ + || true + + +name='detect node change from directory to file #1' +rm -rf dir $GIT_DIR/index +git checkout -b mybranch2 git-svn-HEAD +mv bar/zzz zzz +rm -rf bar +mv zzz bar +git update-index --remove -- bar/zzz +git update-index --add -- bar +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch2' \ + || true + + +name='detect node change from file to directory #2' +rm -f $GIT_DIR/index +git checkout -b mybranch3 git-svn-HEAD +rm bar/zzz +git-update-index --remove bar/zzz +mkdir bar/zzz +echo yyy > bar/zzz/yyy +git-update-index --add bar/zzz/yyy +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch3' \ + || true + + +name='detect node change from directory to file #2' +rm -f $GIT_DIR/index +git checkout -b mybranch4 git-svn-HEAD +rm -rf dir +git update-index --remove -- dir/file +touch dir +echo asdf > dir +git update-index --add -- dir +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch4' \ + || true + + +name='remove executable bit from a file' +rm -f $GIT_DIR/index +git checkout -b mybranch5 git-svn-HEAD +chmod -x exec.sh +git update-index exec.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 && + test ! -x $SVN_TREE/exec.sh" + + +name='add executable bit back file' +chmod +x exec.sh +git update-index exec.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 && + test -x $SVN_TREE/exec.sh" + + + +name='executable file becomes a symlink to bar/zzz (file)' +rm exec.sh +ln -s bar/zzz exec.sh +git update-index exec.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 && + test -L $SVN_TREE/exec.sh" + + + +name='new symlink is added to a file that was also just made executable' +chmod +x bar/zzz +ln -s bar/zzz exec-2.sh +git update-index --add bar/zzz exec-2.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 && + test -x $SVN_TREE/bar/zzz && + test -L $SVN_TREE/exec-2.sh" + + + +name='modify a symlink to become a file' +git help > help || true +rm exec-2.sh +cp help exec-2.sh +git update-index exec-2.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 && + test -f $SVN_TREE/exec-2.sh && + test ! -L $SVN_TREE/exec-2.sh && + diff -u help $SVN_TREE/exec-2.sh" + + + +name='test fetch functionality (svn => git) with alternate GIT_SVN_ID' +GIT_SVN_ID=alt +export GIT_SVN_ID +test_expect_success "$name" \ + "git-svn init $svnrepo && git-svn fetch -v && + git-rev-list --pretty=raw git-svn-HEAD | grep ^tree | uniq > a && + git-rev-list --pretty=raw alt-HEAD | grep ^tree | uniq > b && + diff -u a b" + +test_done + diff --git a/contrib/gitview/gitview b/contrib/gitview/gitview index 5862fcca41..4e3847d8bf 100755 --- a/contrib/gitview/gitview +++ b/contrib/gitview/gitview @@ -56,20 +56,6 @@ def show_date(epoch, tz): return time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(secs)) -def get_sha1_from_tags(line): - fp = os.popen("git cat-file -t " + line) - entry = string.strip(fp.readline()) - fp.close() - if (entry == "commit"): - return line - elif (entry == "tag"): - fp = os.popen("git cat-file tag "+ line) - entry = string.strip(fp.readline()) - fp.close() - obj = re.split(" ", entry) - if (obj[0] == "object"): - return obj[1] - return None class CellRendererGraph(gtk.GenericCellRenderer): """Cell renderer for directed graph. @@ -168,15 +154,15 @@ class CellRendererGraph(gtk.GenericCellRenderer): cols = self.node[0] for start, end, colour in self.in_lines + self.out_lines: - cols = max(cols, start, end) + cols = int(max(cols, start, end)) (column, colour, names) = self.node names_len = 0 if (len(names) != 0): for item in names: - names_len += len(item)/3 + names_len += len(item) - width = box_size * (cols + 1 + names_len ) + width = box_size * (cols + 1 ) + names_len height = box_size # FIXME I have no idea how to use cell_area properly @@ -258,6 +244,8 @@ class CellRendererGraph(gtk.GenericCellRenderer): for item in names: name = name + item + " " + ctx.select_font_face("Monospace") + ctx.set_font_size(13) ctx.text_path(name) self.set_colour(ctx, colour, 0.0, 0.5) @@ -434,7 +422,7 @@ class DiffWindow: class GitView: """ This is the main class """ - version = "0.6" + version = "0.7" def __init__(self, with_diff=0): self.with_diff = with_diff @@ -465,32 +453,20 @@ class GitView: respective sha1 details """ self.bt_sha1 = { } - git_dir = os.getenv("GIT_DIR") - if (git_dir == None): - git_dir = ".git" - - #FIXME the path seperator - ref_files = os.listdir(git_dir + "/refs/tags") - for file in ref_files: - fp = open(git_dir + "/refs/tags/"+file) - sha1 = get_sha1_from_tags(string.strip(fp.readline())) - try: - self.bt_sha1[sha1].append(file) - except KeyError: - self.bt_sha1[sha1] = [file] - fp.close() - - - #FIXME the path seperator - ref_files = os.listdir(git_dir + "/refs/heads") - for file in ref_files: - fp = open(git_dir + "/refs/heads/" + file) - sha1 = get_sha1_from_tags(string.strip(fp.readline())) - try: - self.bt_sha1[sha1].append(file) - except KeyError: - self.bt_sha1[sha1] = [file] - fp.close() + ls_remote = re.compile('^(.{40})\trefs/([^^]+)(?:\\^(..))?$'); + fp = os.popen('git ls-remote "${GIT_DIR-.git}"') + while 1: + line = string.strip(fp.readline()) + if line == '': + break + m = ls_remote.match(line) + if not m: + continue + (sha1, name) = (m.group(1), m.group(2)) + if not self.bt_sha1.has_key(sha1): + self.bt_sha1[sha1] = [] + self.bt_sha1[sha1].append(name) + fp.close() def construct(self): @@ -537,8 +513,8 @@ class GitView: cell = CellRendererGraph() column = gtk.TreeViewColumn() - column.set_resizable(False) - column.pack_start(cell, expand=False) + column.set_resizable(True) + column.pack_start(cell, expand=True) column.add_attribute(cell, "node", 1) column.add_attribute(cell, "in-lines", 2) column.add_attribute(cell, "out-lines", 3) @@ -847,6 +823,7 @@ class GitView: self.colours = {} self.nodepos = {} self.incomplete_line = {} + self.commits = [] index = 0 last_colour = 0 @@ -864,12 +841,7 @@ class GitView: commit = Commit(commit_lines) if (commit != None ): - (out_line, last_colour, last_nodepos) = self.draw_graph(commit, - index, out_line, - last_colour, - last_nodepos) - self.index[commit.commit_sha1] = index - index += 1 + self.commits.append(commit) # Skip the '\0 commit_lines = [] @@ -878,6 +850,14 @@ class GitView: fp.close() + for commit in self.commits: + (out_line, last_colour, last_nodepos) = self.draw_graph(commit, + index, out_line, + last_colour, + last_nodepos) + self.index[commit.commit_sha1] = index + index += 1 + self.treeview.set_model(self.model) self.treeview.show() @@ -890,28 +870,22 @@ class GitView: # Reset nodepostion if (last_nodepos > 5): - last_nodepos = 0 + last_nodepos = -1 # Add the incomplete lines of the last cell in this - for sha1 in self.incomplete_line.keys(): - if ( sha1 != commit.commit_sha1): - for pos in self.incomplete_line[sha1]: - in_line.append((pos, pos, self.colours[sha1])) - else: - del self.incomplete_line[sha1] - try: colour = self.colours[commit.commit_sha1] except KeyError: - last_colour +=1 - self.colours[commit.commit_sha1] = last_colour - colour = last_colour + self.colours[commit.commit_sha1] = last_colour+1 + last_colour = self.colours[commit.commit_sha1] + colour = self.colours[commit.commit_sha1] + try: node_pos = self.nodepos[commit.commit_sha1] except KeyError: - last_nodepos +=1 - self.nodepos[commit.commit_sha1] = last_nodepos - node_pos = last_nodepos + self.nodepos[commit.commit_sha1] = last_nodepos+1 + last_nodepos = self.nodepos[commit.commit_sha1] + node_pos = self.nodepos[commit.commit_sha1] #The first parent always continue on the same line try: @@ -921,25 +895,26 @@ class GitView: self.colours[commit.parent_sha1[0]] = colour self.nodepos[commit.parent_sha1[0]] = node_pos - in_line.append((node_pos, self.nodepos[commit.parent_sha1[0]], - self.colours[commit.parent_sha1[0]])) - - self.add_incomplete_line(commit.parent_sha1[0], index+1) + for sha1 in self.incomplete_line.keys(): + if (sha1 != commit.commit_sha1): + self.draw_incomplete_line(sha1, node_pos, + out_line, in_line, index) + else: + del self.incomplete_line[sha1] - if (len(commit.parent_sha1) > 1): - for parent_id in commit.parent_sha1[1:]: - try: - tmp_node_pos = self.nodepos[parent_id] - except KeyError: - last_colour += 1; - self.colours[parent_id] = last_colour - last_nodepos +=1 - self.nodepos[parent_id] = last_nodepos - in_line.append((node_pos, self.nodepos[parent_id], - self.colours[parent_id])) - self.add_incomplete_line(parent_id, index+1) + for parent_id in commit.parent_sha1: + try: + tmp_node_pos = self.nodepos[parent_id] + except KeyError: + self.colours[parent_id] = last_colour+1 + last_colour = self.colours[parent_id] + self.nodepos[parent_id] = last_nodepos+1 + last_nodepos = self.nodepos[parent_id] + in_line.append((node_pos, self.nodepos[parent_id], + self.colours[parent_id])) + self.add_incomplete_line(parent_id) try: branch_tag = self.bt_sha1[commit.commit_sha1] @@ -954,12 +929,31 @@ class GitView: return (in_line, last_colour, last_nodepos) - def add_incomplete_line(self, sha1, index): + def add_incomplete_line(self, sha1): try: self.incomplete_line[sha1].append(self.nodepos[sha1]) except KeyError: self.incomplete_line[sha1] = [self.nodepos[sha1]] + def draw_incomplete_line(self, sha1, node_pos, out_line, in_line, index): + for idx, pos in enumerate(self.incomplete_line[sha1]): + if(pos == node_pos): + #remove the straight line and add a slash + if ((pos, pos, self.colours[sha1]) in out_line): + out_line.remove((pos, pos, self.colours[sha1])) + out_line.append((pos, pos+0.5, self.colours[sha1])) + self.incomplete_line[sha1][idx] = pos = pos+0.5 + try: + next_commit = self.commits[index+1] + if (next_commit.commit_sha1 == sha1 and pos != int(pos)): + # join the line back to the node point + # This need to be done only if we modified it + in_line.append((pos, pos-0.5, self.colours[sha1])) + continue; + except IndexError: + pass + in_line.append((pos, pos, self.colours[sha1])) + def _go_clicked_cb(self, widget, revid): """Callback for when the go button for a parent is clicked.""" diff --git a/diff-files.c b/diff-files.c index 0c3f80046b..b1c05b325a 100644 --- a/diff-files.c +++ b/diff-files.c @@ -193,7 +193,7 @@ int main(int argc, const char **argv) show_file('-', ce); continue; } - changed = ce_match_stat(ce, &st); + changed = ce_match_stat(ce, &st, 0); if (!changed && !diff_options.find_copies_harder) continue; oldmode = ntohl(ce->ce_mode); diff --git a/diff-index.c b/diff-index.c index f8a102ec16..12a9418d6b 100644 --- a/diff-index.c +++ b/diff-index.c @@ -33,7 +33,7 @@ static int get_stat_data(struct cache_entry *ce, } return -1; } - changed = ce_match_stat(ce, &st); + changed = ce_match_stat(ce, &st, 0); if (changed) { mode = create_ce_mode(st.st_mode); if (!trust_executable_bit && @@ -311,7 +311,7 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) ce = active_cache[pos]; if ((lstat(name, &st) < 0) || !S_ISREG(st.st_mode) || /* careful! */ - ce_match_stat(ce, &st) || + ce_match_stat(ce, &st, 0) || memcmp(sha1, ce->sha1, 20)) return 0; /* we return 1 only when we can stat, it is a regular file, diff --git a/diffcore-rename.c b/diffcore-rename.c index 39d9126cb9..ffd126af0d 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -176,8 +176,10 @@ static int estimate_similarity(struct diff_filespec *src, /* A delta that has a lot of literal additions would have * big delta_size no matter what else it does. */ - if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) + if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) { + free(delta); return 0; + } /* Estimate the edit size by interpreting delta. */ if (count_delta(delta, delta_size, &src_copied, &literal_added)) { @@ -123,7 +123,7 @@ int checkout_entry(struct cache_entry *ce, struct checkout *state) strcpy(path + len, ce->name); if (!lstat(path, &st)) { - unsigned changed = ce_match_stat(ce, &st); + unsigned changed = ce_match_stat(ce, &st, 1); if (!changed) return 0; if (!state->force) { diff --git a/environment.c b/environment.c index 0596fc647b..251e53ca09 100644 --- a/environment.c +++ b/environment.c @@ -12,6 +12,7 @@ char git_default_email[MAX_GITNAME]; char git_default_name[MAX_GITNAME]; int trust_executable_bit = 1; +int assume_unchanged = 0; int only_use_symrefs = 0; int repository_format_version = 0; char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; diff --git a/fetch-pack.c b/fetch-pack.c index aa6f42ae1b..09738fee91 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -8,7 +8,7 @@ static int keep_pack; static int quiet; static int verbose; static const char fetch_pack_usage[] = -"git-fetch-pack [-q] [-v] [-k] [--exec=upload-pack] [host:]directory <refs>..."; +"git-fetch-pack [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; static const char *exec = "git-upload-pack"; #define COMPLETE (1U << 0) @@ -18,7 +18,7 @@ static const char *exec = "git-upload-pack"; #define POPPED (1U << 4) static struct commit_list *rev_list = NULL; -static int non_common_revs = 0, multi_ack = 0; +static int non_common_revs = 0, multi_ack = 0, use_thin_pack = 0; static void rev_list_push(struct commit *commit, int mark) { @@ -156,8 +156,9 @@ static int find_common(int fd[2], unsigned char *result_sha1, continue; } - packet_write(fd[1], "want %s%s\n", sha1_to_hex(remote), - multi_ack ? " multi_ack" : ""); + packet_write(fd[1], "want %s%s%s\n", sha1_to_hex(remote), + (multi_ack ? " multi_ack" : ""), + (use_thin_pack ? " thin-pack" : "")); fetching++; } packet_flush(fd[1]); @@ -421,6 +422,10 @@ int main(int argc, char **argv) keep_pack = 1; continue; } + if (!strcmp("--thin", arg)) { + use_thin_pack = 1; + continue; + } if (!strcmp("-v", arg)) { verbose = 1; continue; @@ -434,6 +439,8 @@ int main(int argc, char **argv) } if (!dest) usage(fetch_pack_usage); + if (keep_pack) + use_thin_pack = 0; pid = git_connect(fd, dest, exec); if (pid < 0) return 1; diff --git a/git-add.sh b/git-add.sh index 13fad820d4..d6a4bc7d09 100755 --- a/git-add.sh +++ b/git-add.sh @@ -14,6 +14,10 @@ while : ; do -v) verbose=--verbose ;; + --) + shift + break + ;; -*) usage ;; @@ -1,11 +1,13 @@ #!/bin/sh # -# +# Copyright (c) 2005, 2006 Junio C Hamano USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox> or, when resuming [--skip | --resolved]' . git-sh-setup +git var GIT_COMMITTER_IDENT >/dev/null || exit + stop_here () { echo "$1" >"$dotest/next" exit 1 @@ -298,7 +300,7 @@ do } >"$dotest/final-commit" ;; *) - case "$resolved,$interactive" in + case "$resolved$interactive" in tt) # This is used only for interactive view option. git-diff-index -p --cached HEAD >"$dotest/patch" @@ -362,6 +364,12 @@ do # trust what the user has in the index file and the # working tree. resolved= + changed="$(git-diff-index --cached --name-only HEAD)" + if test '' = "$changed" + then + echo "No changes - did you forget update-index?" + stop_here $this + fi apply_status=0 ;; esac @@ -372,7 +380,7 @@ do then # Applying the patch to an earlier tree and merging the # result may have produced the same tree as ours. - changed="$(git-diff-index --cached --name-only -z HEAD)" + changed="$(git-diff-index --cached --name-only HEAD)" if test '' = "$changed" then echo No changes -- Patch already applied. diff --git a/git-annotate.perl b/git-annotate.perl new file mode 100755 index 0000000000..3800c4654b --- /dev/null +++ b/git-annotate.perl @@ -0,0 +1,356 @@ +#!/usr/bin/perl +# Copyright 2006, Ryan Anderson <ryan@michonline.com> +# +# GPL v2 (See COPYING) +# +# This file is licensed under the GPL v2, or a later version +# at the discretion of Linus Torvalds. + +use warnings; +use strict; +use Getopt::Std; +use POSIX qw(strftime gmtime); + +sub usage() { + print STDERR 'Usage: ${\basename $0} [-s] [-S revs-file] file + + -l show long rev + -r follow renames + -S commit use revs from revs-file instead of calling git-rev-list +'; + + exit(1); +} + +our ($opt_h, $opt_l, $opt_r, $opt_S); +getopts("hlrS:") or usage(); +$opt_h && usage(); + +my $filename = shift @ARGV; + +my @stack = ( + { + 'rev' => "HEAD", + 'filename' => $filename, + }, +); + +our (@lineoffsets, @pendinglineoffsets); +our @filelines = (); +open(F,"<",$filename) + or die "Failed to open filename: $!"; + +while(<F>) { + chomp; + push @filelines, $_; +} +close(F); +our $leftover_lines = @filelines; +our %revs; +our @revqueue; +our $head; + +my $revsprocessed = 0; +while (my $bound = pop @stack) { + my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'}); + foreach my $revinst (@revisions) { + my ($rev, @parents) = @$revinst; + $head ||= $rev; + + if (!defined($rev)) { + $rev = ""; + } + $revs{$rev}{'filename'} = $bound->{'filename'}; + if (scalar @parents > 0) { + $revs{$rev}{'parents'} = \@parents; + next; + } + + if (!$opt_r) { + next; + } + + my $newbound = find_parent_renames($rev, $bound->{'filename'}); + if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) { + push @stack, $newbound; + $revs{$rev}{'parents'} = [$newbound->{'rev'}]; + } + } +} +push @revqueue, $head; +init_claim($head); +$revs{$head}{'lineoffsets'} = {}; +handle_rev(); + + +my $i = 0; +foreach my $l (@filelines) { + my ($output, $rev, $committer, $date); + if (ref $l eq 'ARRAY') { + ($output, $rev, $committer, $date) = @$l; + if (!$opt_l && length($rev) > 8) { + $rev = substr($rev,0,8); + } + } else { + $output = $l; + ($rev, $committer, $date) = ('unknown', 'unknown', 'unknown'); + } + + printf("%s\t(%10s\t%10s\t%d)%s\n", $rev, $committer, + format_date($date), $i++, $output); +} + +sub init_claim { + my ($rev) = @_; + my %revinfo = git_commit_info($rev); + for (my $i = 0; $i < @filelines; $i++) { + $filelines[$i] = [ $filelines[$i], '', '', '', 1]; + # line, + # rev, + # author, + # date, + # 1 <-- belongs to the original file. + } + $revs{$rev}{'lines'} = \@filelines; +} + + +sub handle_rev { + my $i = 0; + while (my $rev = shift @revqueue) { + + my %revinfo = git_commit_info($rev); + + foreach my $p (@{$revs{$rev}{'parents'}}) { + + git_diff_parse($p, $rev, %revinfo); + push @revqueue, $p; + } + + + if (scalar @{$revs{$rev}{parents}} == 0) { + # We must be at the initial rev here, so claim everything that is left. + for (my $i = 0; $i < @{$revs{$rev}{lines}}; $i++) { + if (ref ${$revs{$rev}{lines}}[$i] eq '' || ${$revs{$rev}{lines}}[$i][1] eq '') { + claim_line($i, $rev, $revs{$rev}{lines}, %revinfo); + } + } + } + } +} + + +sub git_rev_list { + my ($rev, $file) = @_; + + if ($opt_S) { + open(P, '<' . $opt_S); + } else { + open(P,"-|","git-rev-list","--parents","--remove-empty",$rev,"--",$file) + or die "Failed to exec git-rev-list: $!"; + } + + my @revs; + while(my $line = <P>) { + chomp $line; + my ($rev, @parents) = split /\s+/, $line; + push @revs, [ $rev, @parents ]; + } + close(P); + + printf("0 revs found for rev %s (%s)\n", $rev, $file) if (@revs == 0); + return @revs; +} + +sub find_parent_renames { + my ($rev, $file) = @_; + + open(P,"-|","git-diff-tree", "-M50", "-r","--name-status", "-z","$rev") + or die "Failed to exec git-diff: $!"; + + local $/ = "\0"; + my %bound; + my $junk = <P>; + while (my $change = <P>) { + chomp $change; + my $filename = <P>; + chomp $filename; + + if ($change =~ m/^[AMD]$/ ) { + next; + } elsif ($change =~ m/^R/ ) { + my $oldfilename = $filename; + $filename = <P>; + chomp $filename; + if ( $file eq $filename ) { + my $parent = git_find_parent($rev, $oldfilename); + @bound{'rev','filename'} = ($parent, $oldfilename); + last; + } + } + } + close(P); + + return \%bound; +} + + +sub git_find_parent { + my ($rev, $filename) = @_; + + open(REVPARENT,"-|","git-rev-list","--remove-empty", "--parents","--max-count=1","$rev","--",$filename) + or die "Failed to open git-rev-list to find a single parent: $!"; + + my $parentline = <REVPARENT>; + chomp $parentline; + my ($revfound,$parent) = split m/\s+/, $parentline; + + close(REVPARENT); + + return $parent; +} + + +# Get a diff between the current revision and a parent. +# Record the commit information that results. +sub git_diff_parse { + my ($parent, $rev, %revinfo) = @_; + + my ($ri, $pi) = (0,0); + open(DIFF,"-|","git-diff-tree","-M","-p",$rev,$parent,"--", + $revs{$rev}{'filename'}, $revs{$parent}{'filename'}) + or die "Failed to call git-diff for annotation: $!"; + + my $slines = $revs{$rev}{'lines'}; + my @plines; + + my $gotheader = 0; + my ($remstart, $remlength, $addstart, $addlength); + my ($hunk_start, $hunk_index, $hunk_adds); + while(<DIFF>) { + chomp; + if (m/^@@ -(\d+),(\d+) \+(\d+),(\d+)/) { + ($remstart, $remlength, $addstart, $addlength) = ($1, $2, $3, $4); + # Adjust for 0-based arrays + $remstart--; + $addstart--; + # Reinit hunk tracking. + $hunk_start = $remstart; + $hunk_index = 0; + $gotheader = 1; + + for (my $i = $ri; $i < $remstart; $i++) { + $plines[$pi++] = $slines->[$i]; + $ri++; + } + next; + } elsif (!$gotheader) { + next; + } + + if (m/^\+(.*)$/) { + my $line = $1; + $plines[$pi++] = [ $line, '', '', '', 0 ]; + next; + + } elsif (m/^-(.*)$/) { + my $line = $1; + if (get_line($slines, $ri) eq $line) { + # Found a match, claim + claim_line($ri, $rev, $slines, %revinfo); + } else { + die sprintf("Sync error: %d/%d\n|%s\n|%s\n%s => %s\n", + $ri, $hunk_start + $hunk_index, + $line, + get_line($slines, $ri), + $rev, $parent); + } + $ri++; + + } else { + if (substr($_,1) ne get_line($slines,$ri) ) { + die sprintf("Line %d (%d) does not match:\n|%s\n|%s\n%s => %s\n", + $hunk_start + $hunk_index, $ri, + substr($_,1), + get_line($slines,$ri), + $rev, $parent); + } + $plines[$pi++] = $slines->[$ri++]; + } + $hunk_index++; + } + close(DIFF); + for (my $i = $ri; $i < @{$slines} ; $i++) { + push @plines, $slines->[$ri++]; + } + + $revs{$parent}{lines} = \@plines; + return; +} + +sub get_line { + my ($lines, $index) = @_; + + return ref $lines->[$index] ne '' ? $lines->[$index][0] : $lines->[$index]; +} + +sub git_cat_file { + my ($parent, $filename) = @_; + return () unless defined $parent && defined $filename; + my $blobline = `git-ls-tree $parent $filename`; + my ($mode, $type, $blob, $tfilename) = split(/\s+/, $blobline, 4); + + open(C,"-|","git-cat-file", "blob", $blob) + or die "Failed to git-cat-file blob $blob (rev $parent, file $filename): " . $!; + + my @lines; + while(<C>) { + chomp; + push @lines, $_; + } + close(C); + + return @lines; +} + + +sub claim_line { + my ($floffset, $rev, $lines, %revinfo) = @_; + my $oline = get_line($lines, $floffset); + @{$lines->[$floffset]} = ( $oline, $rev, + $revinfo{'author'}, $revinfo{'author_date'} ); + #printf("Claiming line %d with rev %s: '%s'\n", + # $floffset, $rev, $oline) if 1; +} + +sub git_commit_info { + my ($rev) = @_; + open(COMMIT, "-|","git-cat-file", "commit", $rev) + or die "Failed to call git-cat-file: $!"; + + my %info; + while(<COMMIT>) { + chomp; + last if (length $_ == 0); + + if (m/^author (.*) <(.*)> (.*)$/) { + $info{'author'} = $1; + $info{'author_email'} = $2; + $info{'author_date'} = $3; + } elsif (m/^committer (.*) <(.*)> (.*)$/) { + $info{'committer'} = $1; + $info{'committer_email'} = $2; + $info{'committer_date'} = $3; + } + } + close(COMMIT); + + return %info; +} + +sub format_date { + my ($timestamp, $timezone) = split(' ', $_[0]); + + return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($timestamp)); +} + diff --git a/git-applymbox.sh b/git-applymbox.sh index 61c8c024c6..5569fdcc34 100755 --- a/git-applymbox.sh +++ b/git-applymbox.sh @@ -21,6 +21,8 @@ USAGE='[-u] [-k] [-q] [-m] (-c .dotest/<num> | mbox) [signoff]' . git-sh-setup +git var GIT_COMMITTER_IDENT >/dev/null || exit + keep_subject= query_apply= continue= utf8= resume=t while case "$#" in 0) break ;; esac do diff --git a/git-clone.sh b/git-clone.sh index d184ceb7a6..4ed861d576 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -118,7 +118,7 @@ dir="$2" [ -e "$dir" ] && echo "$dir already exists." && usage mkdir -p "$dir" && D=$(cd "$dir" && pwd) && -trap 'err=$?; rm -r $D; exit $err' exit +trap 'err=$?; cd ..; rm -r "$D"; exit $err' exit case "$bare" in yes) GIT_DIR="$D" ;; *) GIT_DIR="$D/.git" ;; @@ -154,7 +154,7 @@ yes,yes) fi && rm -f "$GIT_DIR/objects/sample" && cd "$repo" && - find objects -depth -print | cpio -puamd$l "$GIT_DIR/" || exit 1 + find objects -depth -print | cpio -pumd$l "$GIT_DIR/" || exit 1 ;; yes) mkdir -p "$GIT_DIR/objects/info" @@ -253,7 +253,7 @@ Pull: $head_points_at:$origin" && case "$no_checkout" in '') - git checkout + git-read-tree -m -u -v HEAD HEAD esac fi diff --git a/git-cvsimport.perl b/git-cvsimport.perl index 24f9834342..b46469ab32 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -846,8 +846,12 @@ while(<CVS>) { print "Drop $fn\n" if $opt_v; } else { print "".($init ? "New" : "Update")." $fn: $size bytes\n" if $opt_v; - open my $F, '-|', "git-hash-object -w $tmpname" + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $tmpname) or die "Cannot create object: $!\n"; + } my $sha = <$F>; chomp $sha; close $F; diff --git a/git-cvsserver.perl b/git-cvsserver.perl new file mode 100755 index 0000000000..d20d1a8c4b --- /dev/null +++ b/git-cvsserver.perl @@ -0,0 +1,2449 @@ +#!/usr/bin/perl + +#### +#### This application is a CVS emulation layer for git. +#### It is intended for clients to connect over SSH. +#### See the documentation for more details. +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### +#### Released under the GNU Public License, version 2. +#### +#### + +use strict; +use warnings; + +use Fcntl; +use File::Temp qw/tempdir tempfile/; +use File::Basename; + +my $log = GITCVS::log->new(); +my $cfg; + +my $DATE_LIST = { + Jan => "01", + Feb => "02", + Mar => "03", + Apr => "04", + May => "05", + Jun => "06", + Jul => "07", + Aug => "08", + Sep => "09", + Oct => "10", + Nov => "11", + Dec => "12", +}; + +# Enable autoflush for STDOUT (otherwise the whole thing falls apart) +$| = 1; + +#### Definition and mappings of functions #### + +my $methods = { + 'Root' => \&req_Root, + 'Valid-responses' => \&req_Validresponses, + 'valid-requests' => \&req_validrequests, + 'Directory' => \&req_Directory, + 'Entry' => \&req_Entry, + 'Modified' => \&req_Modified, + 'Unchanged' => \&req_Unchanged, + 'Argument' => \&req_Argument, + 'Argumentx' => \&req_Argument, + 'expand-modules' => \&req_expandmodules, + 'add' => \&req_add, + 'remove' => \&req_remove, + 'co' => \&req_co, + 'update' => \&req_update, + 'ci' => \&req_ci, + 'diff' => \&req_diff, + 'log' => \&req_log, + 'tag' => \&req_CATCHALL, + 'status' => \&req_status, + 'admin' => \&req_CATCHALL, + 'history' => \&req_CATCHALL, + 'watchers' => \&req_CATCHALL, + 'editors' => \&req_CATCHALL, + 'annotate' => \&req_annotate, + 'Global_option' => \&req_Globaloption, + #'annotate' => \&req_CATCHALL, +}; + +############################################## + + +# $state holds all the bits of information the clients sends us that could +# potentially be useful when it comes to actually _doing_ something. +my $state = {}; +$log->info("--------------- STARTING -----------------"); + +my $TEMP_DIR = tempdir( CLEANUP => 1 ); +$log->debug("Temporary directory is '$TEMP_DIR'"); + +# Keep going until the client closes the connection +while (<STDIN>) +{ + chomp; + + # Check to see if we've seen this method, and call appropiate function. + if ( /^([\w-]+)(?:\s+(.*))?$/ and defined($methods->{$1}) ) + { + # use the $methods hash to call the appropriate sub for this command + #$log->info("Method : $1"); + &{$methods->{$1}}($1,$2); + } else { + # log fatal because we don't understand this function. If this happens + # we're fairly screwed because we don't know if the client is expecting + # a response. If it is, the client will hang, we'll hang, and the whole + # thing will be custard. + $log->fatal("Don't understand command $_\n"); + die("Unknown command $_"); + } +} + +$log->debug("Processing time : user=" . (times)[0] . " system=" . (times)[1]); +$log->info("--------------- FINISH -----------------"); + +# Magic catchall method. +# This is the method that will handle all commands we haven't yet +# implemented. It simply sends a warning to the log file indicating a +# command that hasn't been implemented has been invoked. +sub req_CATCHALL +{ + my ( $cmd, $data ) = @_; + $log->warn("Unhandled command : req_$cmd : $data"); +} + + +# Root pathname \n +# Response expected: no. Tell the server which CVSROOT to use. Note that +# pathname is a local directory and not a fully qualified CVSROOT variable. +# pathname must already exist; if creating a new root, use the init +# request, not Root. pathname does not include the hostname of the server, +# how to access the server, etc.; by the time the CVS protocol is in use, +# connection, authentication, etc., are already taken care of. The Root +# request must be sent only once, and it must be sent before any requests +# other than Valid-responses, valid-requests, UseUnchanged, Set or init. +sub req_Root +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Root : $data"); + + $state->{CVSROOT} = $data; + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + + foreach my $line ( `git-var -l` ) + { + next unless ( $line =~ /^(.*?)\.(.*?)=(.*)$/ ); + $cfg->{$1}{$2} = $3; + } + + unless ( defined ( $cfg->{gitcvs}{enabled} ) and $cfg->{gitcvs}{enabled} =~ /^\s*(1|true|yes)\s*$/i ) + { + print "E GITCVS emulation needs to be enabled on this repo\n"; + print "E the repo config file needs a [gitcvs] section added, and the parameter 'enabled' set to 1\n"; + print "E \n"; + print "error 1 GITCVS emulation disabled\n"; + } + + if ( defined ( $cfg->{gitcvs}{logfile} ) ) + { + $log->setfile($cfg->{gitcvs}{logfile}); + } else { + $log->nofile(); + } +} + +# Global_option option \n +# Response expected: no. Transmit one of the global options `-q', `-Q', +# `-l', `-t', `-r', or `-n'. option must be one of those strings, no +# variations (such as combining of options) are allowed. For graceful +# handling of valid-requests, it is probably better to make new global +# options separate requests, rather than trying to add them to this +# request. +sub req_Globaloption +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Globaloption : $data"); + + # TODO : is this data useful ??? +} + +# Valid-responses request-list \n +# Response expected: no. Tell the server what responses the client will +# accept. request-list is a space separated list of tokens. +sub req_Validresponses +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Validrepsonses : $data"); + + # TODO : re-enable this, currently it's not particularly useful + #$state->{validresponses} = [ split /\s+/, $data ]; +} + +# valid-requests \n +# Response expected: yes. Ask the server to send back a Valid-requests +# response. +sub req_validrequests +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_validrequests"); + + $log->debug("SEND : Valid-requests " . join(" ",keys %$methods)); + $log->debug("SEND : ok"); + + print "Valid-requests " . join(" ",keys %$methods) . "\n"; + print "ok\n"; +} + +# Directory local-directory \n +# Additional data: repository \n. Response expected: no. Tell the server +# what directory to use. The repository should be a directory name from a +# previous server response. Note that this both gives a default for Entry +# and Modified and also for ci and the other commands; normal usage is to +# send Directory for each directory in which there will be an Entry or +# Modified, and then a final Directory for the original directory, then the +# command. The local-directory is relative to the top level at which the +# command is occurring (i.e. the last Directory which is sent before the +# command); to indicate that top level, `.' should be sent for +# local-directory. +sub req_Directory +{ + my ( $cmd, $data ) = @_; + + my $repository = <STDIN>; + chomp $repository; + + + $state->{localdir} = $data; + $state->{repository} = $repository; + $state->{directory} = $repository; + $state->{directory} =~ s/^$state->{CVSROOT}\///; + $state->{module} = $1 if ($state->{directory} =~ s/^(.*?)(\/|$)//); + $state->{directory} .= "/" if ( $state->{directory} =~ /\S/ ); + + $log->debug("req_Directory : localdir=$data repository=$repository directory=$state->{directory} module=$state->{module}"); +} + +# Entry entry-line \n +# Response expected: no. Tell the server what version of a file is on the +# local machine. The name in entry-line is a name relative to the directory +# most recently specified with Directory. If the user is operating on only +# some files in a directory, Entry requests for only those files need be +# included. If an Entry request is sent without Modified, Is-modified, or +# Unchanged, it means the file is lost (does not exist in the working +# directory). If both Entry and one of Modified, Is-modified, or Unchanged +# are sent for the same file, Entry must be sent first. For a given file, +# one can send Modified, Is-modified, or Unchanged, but not more than one +# of these three. +sub req_Entry +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_Entry : $data"); + + my @data = split(/\//, $data); + + $state->{entries}{$state->{directory}.$data[1]} = { + revision => $data[2], + conflict => $data[3], + options => $data[4], + tag_or_date => $data[5], + }; +} + +# add \n +# Response expected: yes. Add a file or directory. This uses any previous +# Argument, Directory, Entry, or Modified requests, if they have been sent. +# The last Directory sent specifies the working directory at the time of +# the operation. To add a directory, send the directory to be added using +# Directory and Argument requests. +sub req_add +{ + my ( $cmd, $data ) = @_; + + argsplit("add"); + + my $addcount = 0; + + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + unless ( defined ( $state->{entries}{$filename}{modified_filename} ) ) + { + print "E cvs add: nothing known about `$filename'\n"; + next; + } + # TODO : check we're not squashing an already existing file + if ( defined ( $state->{entries}{$filename}{revision} ) ) + { + print "E cvs add: `$filename' has already been entered\n"; + next; + } + + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + print "E cvs add: scheduling file `$filename' for addition\n"; + + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/0///\n"; + + $addcount++; + } + + if ( $addcount == 1 ) + { + print "E cvs add: use `cvs commit' to add this file permanently\n"; + } + elsif ( $addcount > 1 ) + { + print "E cvs add: use `cvs commit' to add these files permanently\n"; + } + + print "ok\n"; +} + +# remove \n +# Response expected: yes. Remove a file. This uses any previous Argument, +# Directory, Entry, or Modified requests, if they have been sent. The last +# Directory sent specifies the working directory at the time of the +# operation. Note that this request does not actually do anything to the +# repository; the only effect of a successful remove request is to supply +# the client with a new entries line containing `-' to indicate a removed +# file. In fact, the client probably could perform this operation without +# contacting the server, although using remove may cause the server to +# perform a few more checks. The client sends a subsequent ci request to +# actually record the removal in the repository. +sub req_remove +{ + my ( $cmd, $data ) = @_; + + argsplit("remove"); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + #$log->debug("add state : " . Dumper($state)); + + my $rmcount = 0; + + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + if ( defined ( $state->{entries}{$filename}{unchanged} ) or defined ( $state->{entries}{$filename}{modified_filename} ) ) + { + print "E cvs remove: file `$filename' still in working directory\n"; + next; + } + + my $meta = $updater->getmeta($filename); + my $wrev = revparse($filename); + + unless ( defined ( $wrev ) ) + { + print "E cvs remove: nothing known about `$filename'\n"; + next; + } + + if ( defined($wrev) and $wrev < 0 ) + { + print "E cvs remove: file `$filename' already scheduled for removal\n"; + next; + } + + unless ( $wrev == $meta->{revision} ) + { + # TODO : not sure if the format of this message is quite correct. + print "E cvs remove: Up to date check failed for `$filename'\n"; + next; + } + + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + print "E cvs remove: scheduling `$filename' for removal\n"; + + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/-1.$wrev///\n"; + + $rmcount++; + } + + if ( $rmcount == 1 ) + { + print "E cvs remove: use `cvs commit' to remove this file permanently\n"; + } + elsif ( $rmcount > 1 ) + { + print "E cvs remove: use `cvs commit' to remove these files permanently\n"; + } + + print "ok\n"; +} + +# Modified filename \n +# Response expected: no. Additional data: mode, \n, file transmission. Send +# the server a copy of one locally modified file. filename is a file within +# the most recent directory sent with Directory; it must not contain `/'. +# If the user is operating on only some files in a directory, only those +# files need to be included. This can also be sent without Entry, if there +# is no entry for the file. +sub req_Modified +{ + my ( $cmd, $data ) = @_; + + my $mode = <STDIN>; + chomp $mode; + my $size = <STDIN>; + chomp $size; + + # Grab config information + my $blocksize = 8192; + my $bytesleft = $size; + my $tmp; + + # Get a filehandle/name to write it to + my ( $fh, $filename ) = tempfile( DIR => $TEMP_DIR ); + + # Loop over file data writing out to temporary file. + while ( $bytesleft ) + { + $blocksize = $bytesleft if ( $bytesleft < $blocksize ); + read STDIN, $tmp, $blocksize; + print $fh $tmp; + $bytesleft -= $blocksize; + } + + close $fh; + + # Ensure we have something sensible for the file mode + if ( $mode =~ /u=(\w+)/ ) + { + $mode = $1; + } else { + $mode = "rw"; + } + + # Save the file data in $state + $state->{entries}{$state->{directory}.$data}{modified_filename} = $filename; + $state->{entries}{$state->{directory}.$data}{modified_mode} = $mode; + $state->{entries}{$state->{directory}.$data}{modified_hash} = `git-hash-object $filename`; + $state->{entries}{$state->{directory}.$data}{modified_hash} =~ s/\s.*$//s; + + #$log->debug("req_Modified : file=$data mode=$mode size=$size"); +} + +# Unchanged filename \n +# Response expected: no. Tell the server that filename has not been +# modified in the checked out directory. The filename is a file within the +# most recent directory sent with Directory; it must not contain `/'. +sub req_Unchanged +{ + my ( $cmd, $data ) = @_; + + $state->{entries}{$state->{directory}.$data}{unchanged} = 1; + + #$log->debug("req_Unchanged : $data"); +} + +# Argument text \n +# Response expected: no. Save argument for use in a subsequent command. +# Arguments accumulate until an argument-using command is given, at which +# point they are forgotten. +# Argumentx text \n +# Response expected: no. Append \n followed by text to the current argument +# being saved. +sub req_Argument +{ + my ( $cmd, $data ) = @_; + + # TODO : Not quite sure how Argument and Argumentx differ, but I assume + # it's for multi-line arguments ... somehow ... + + $log->debug("$cmd : $data"); + + push @{$state->{arguments}}, $data; +} + +# expand-modules \n +# Response expected: yes. Expand the modules which are specified in the +# arguments. Returns the data in Module-expansion responses. Note that the +# server can assume that this is checkout or export, not rtag or rdiff; the +# latter do not access the working directory and thus have no need to +# expand modules on the client side. Expand may not be the best word for +# what this request does. It does not necessarily tell you all the files +# contained in a module, for example. Basically it is a way of telling you +# which working directories the server needs to know about in order to +# handle a checkout of the specified modules. For example, suppose that the +# server has a module defined by +# aliasmodule -a 1dir +# That is, one can check out aliasmodule and it will take 1dir in the +# repository and check it out to 1dir in the working directory. Now suppose +# the client already has this module checked out and is planning on using +# the co request to update it. Without using expand-modules, the client +# would have two bad choices: it could either send information about all +# working directories under the current directory, which could be +# unnecessarily slow, or it could be ignorant of the fact that aliasmodule +# stands for 1dir, and neglect to send information for 1dir, which would +# lead to incorrect operation. With expand-modules, the client would first +# ask for the module to be expanded: +sub req_expandmodules +{ + my ( $cmd, $data ) = @_; + + argsplit(); + + $log->debug("req_expandmodules : " . ( defined($data) ? $data : "[NULL]" ) ); + + unless ( ref $state->{arguments} eq "ARRAY" ) + { + print "ok\n"; + return; + } + + foreach my $module ( @{$state->{arguments}} ) + { + $log->debug("SEND : Module-expansion $module"); + print "Module-expansion $module\n"; + } + + print "ok\n"; + statecleanup(); +} + +# co \n +# Response expected: yes. Get files from the repository. This uses any +# previous Argument, Directory, Entry, or Modified requests, if they have +# been sent. Arguments to this command are module names; the client cannot +# know what directories they correspond to except by (1) just sending the +# co request, and then seeing what directory names the server sends back in +# its responses, and (2) the expand-modules request. +sub req_co +{ + my ( $cmd, $data ) = @_; + + argsplit("co"); + + my $module = $state->{args}[0]; + my $checkout_path = $module; + + # use the user specified directory if we're given it + $checkout_path = $state->{opt}{d} if ( exists ( $state->{opt}{d} ) ); + + $log->debug("req_co : " . ( defined($data) ? $data : "[NULL]" ) ); + + $log->info("Checking out module '$module' ($state->{CVSROOT}) to '$checkout_path'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $module, $log); + $updater->update(); + + # instruct the client that we're checking out to $checkout_path + print "E cvs server: updating $checkout_path\n"; + + foreach my $git ( @{$updater->gethead} ) + { + # Don't want to check out deleted files + next if ( $git->{filehash} eq "deleted" ); + + ( $git->{name}, $git->{dir} ) = filenamesplit($git->{name}); + + # modification time of this file + print "Mod-time $git->{modified}\n"; + + # print some information to the client + print "MT +updated\n"; + print "MT text U\n"; + if ( defined ( $git->{dir} ) and $git->{dir} ne "./" ) + { + print "MT fname $checkout_path/$git->{dir}$git->{name}\n"; + } else { + print "MT fname $checkout_path/$git->{name}\n"; + } + print "MT newline\n"; + print "MT -updated\n"; + + # instruct client we're sending a file to put in this path + print "Created $checkout_path/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "\n"; + + print $state->{CVSROOT} . "/$module/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "$git->{name}\n"; + + # this is an "entries" line + print "/$git->{name}/1.$git->{revision}///\n"; + # permissions + print "u=$git->{mode},g=$git->{mode},o=$git->{mode}\n"; + + # transmit file + transmitfile($git->{filehash}); + } + + print "ok\n"; + + statecleanup(); +} + +# update \n +# Response expected: yes. Actually do a cvs update command. This uses any +# previous Argument, Directory, Entry, or Modified requests, if they have +# been sent. The last Directory sent specifies the working directory at the +# time of the operation. The -I option is not used--files which the client +# can decide whether to ignore are not mentioned and the client sends the +# Questionable request for others. +sub req_update +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_update : " . ( defined($data) ? $data : "[NULL]" )); + + argsplit("update"); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + #$log->debug("update state : " . Dumper($state)); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + # if we have a -C we should pretend we never saw modified stuff + if ( exists ( $state->{opt}{C} ) ) + { + delete $state->{entries}{$filename}{modified_hash}; + delete $state->{entries}{$filename}{modified_filename}; + $state->{entries}{$filename}{unchanged} = 1; + } + + my $meta; + if ( defined($state->{opt}{r}) and $state->{opt}{r} =~ /^1\.(\d+)/ ) + { + $meta = $updater->getmeta($filename, $1); + } else { + $meta = $updater->getmeta($filename); + } + + next unless ( $meta->{revision} ); + + my $oldmeta = $meta; + + my $wrev = revparse($filename); + + # If the working copy is an old revision, lets get that version too for comparison. + if ( defined($wrev) and $wrev != $meta->{revision} ) + { + $oldmeta = $updater->getmeta($filename, $wrev); + } + + #$log->debug("Target revision is $meta->{revision}, current working revision is $wrev"); + + # Files are up to date if the working copy and repo copy have the same revision, and the working copy is unmodified _and_ the user hasn't specified -C + next if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} and $state->{entries}{$filename}{unchanged} and not exists ( $state->{opt}{C} ) ); + + if ( $meta->{filehash} eq "deleted" ) + { + my ( $filepart, $dirpart ) = filenamesplit($filename); + + $log->info("Removing '$filename' from working copy (no longer in the repo)"); + + print "E cvs update: `$filename' is no longer in the repository\n"; + print "Removed $dirpart\n"; + print "$filepart\n"; + } + elsif ( not defined ( $state->{entries}{$filename}{modified_hash} ) or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} ) + { + $log->info("Updating '$filename'"); + # normal update, just send the new revision (either U=Update, or A=Add, or R=Remove) + print "MT +updated\n"; + print "MT text U\n"; + print "MT fname $filename\n"; + print "MT newline\n"; + print "MT -updated\n"; + + my ( $filepart, $dirpart ) = filenamesplit($filename); + $dirpart =~ s/^$state->{directory}//; + + if ( defined ( $wrev ) ) + { + # instruct client we're sending a file to put in this path as a replacement + print "Update-existing $dirpart\n"; + $log->debug("Updating existing file 'Update-existing $dirpart'"); + } else { + # instruct client we're sending a file to put in this path as a new file + print "Created $dirpart\n"; + $log->debug("Creating new file 'Created $dirpart'"); + } + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + + # this is an "entries" line + $log->debug("/$filepart/1.$meta->{revision}///"); + print "/$filepart/1.$meta->{revision}///\n"; + + # permissions + $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}"); + print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n"; + + # transmit file + transmitfile($meta->{filehash}); + } else { + my ( $filepart, $dirpart ) = filenamesplit($meta->{name}); + + my $dir = tempdir( DIR => $TEMP_DIR, CLEANUP => 1 ) . "/"; + + chdir $dir; + my $file_local = $filepart . ".mine"; + system("ln","-s",$state->{entries}{$filename}{modified_filename}, $file_local); + my $file_old = $filepart . "." . $oldmeta->{revision}; + transmitfile($oldmeta->{filehash}, $file_old); + my $file_new = $filepart . "." . $meta->{revision}; + transmitfile($meta->{filehash}, $file_new); + + # we need to merge with the local changes ( M=successful merge, C=conflict merge ) + $log->info("Merging $file_local, $file_old, $file_new"); + + $log->debug("Temporary directory for merge is $dir"); + + my $return = system("merge", $file_local, $file_old, $file_new); + $return >>= 8; + + if ( $return == 0 ) + { + $log->info("Merged successfully"); + print "M M $filename\n"; + $log->debug("Update-existing $dirpart"); + print "Update-existing $dirpart\n"; + $log->debug($state->{CVSROOT} . "/$state->{module}/$filename"); + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + $log->debug("/$filepart/1.$meta->{revision}///"); + print "/$filepart/1.$meta->{revision}///\n"; + } + elsif ( $return == 1 ) + { + $log->info("Merged with conflicts"); + print "M C $filename\n"; + print "Update-existing $dirpart\n"; + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + print "/$filepart/1.$meta->{revision}/+//\n"; + } + else + { + $log->warn("Merge failed"); + next; + } + + # permissions + $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}"); + print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n"; + + # transmit file, format is single integer on a line by itself (file + # size) followed by the file contents + # TODO : we should copy files in blocks + my $data = `cat $file_local`; + $log->debug("File size : " . length($data)); + print length($data) . "\n"; + print $data; + + chdir "/"; + } + + } + + print "ok\n"; +} + +sub req_ci +{ + my ( $cmd, $data ) = @_; + + argsplit("ci"); + + #$log->debug("State : " . Dumper($state)); + + $log->info("req_ci : " . ( defined($data) ? $data : "[NULL]" )); + + if ( -e $state->{CVSROOT} . "/index" ) + { + print "error 1 Index already exists in git repo\n"; + exit; + } + + my $lockfile = "$state->{CVSROOT}/refs/heads/$state->{module}.lock"; + unless ( sysopen(LOCKFILE,$lockfile,O_EXCL|O_CREAT|O_WRONLY) ) + { + print "error 1 Lock file '$lockfile' already exists, please try again\n"; + exit; + } + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + my $tmpdir = tempdir ( DIR => $TEMP_DIR ); + my ( undef, $file_index ) = tempfile ( DIR => $TEMP_DIR, OPEN => 0 ); + $log->info("Lock successful, basing commit on '$tmpdir', index file is '$file_index'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + $ENV{GIT_INDEX_FILE} = $file_index; + + chdir $tmpdir; + + # populate the temporary index based + system("git-read-tree", $state->{module}); + unless ($? == 0) + { + die "Error running git-read-tree $state->{module} $file_index $!"; + } + $log->info("Created index '$file_index' with for head $state->{module} - exit status $?"); + + + my @committedfiles = (); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + next unless ( exists $state->{entries}{$filename}{modified_filename} or not $state->{entries}{$filename}{unchanged} ); + + my $meta = $updater->getmeta($filename); + + my $wrev = revparse($filename); + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + # do a checkout of the file if it part of this tree + if ($wrev) { + system('git-checkout-index', '-f', '-u', $filename); + unless ($? == 0) { + die "Error running git-checkout-index -f -u $filename : $!"; + } + } + + my $addflag = 0; + my $rmflag = 0; + $rmflag = 1 if ( defined($wrev) and $wrev < 0 ); + $addflag = 1 unless ( -e $filename ); + + # Do up to date checking + unless ( $addflag or $wrev == $meta->{revision} or ( $rmflag and -$wrev == $meta->{revision} ) ) + { + # fail everything if an up to date check fails + print "error 1 Up to date check failed for $filename\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + exit; + } + + push @committedfiles, $filename; + $log->info("Committing $filename"); + + system("mkdir","-p",$dirpart) unless ( -d $dirpart ); + + unless ( $rmflag ) + { + $log->debug("rename $state->{entries}{$filename}{modified_filename} $filename"); + rename $state->{entries}{$filename}{modified_filename},$filename; + + # Calculate modes to remove + my $invmode = ""; + foreach ( qw (r w x) ) { $invmode .= $_ unless ( $state->{entries}{$filename}{modified_mode} =~ /$_/ ); } + + $log->debug("chmod u+" . $state->{entries}{$filename}{modified_mode} . "-" . $invmode . " $filename"); + system("chmod","u+" . $state->{entries}{$filename}{modified_mode} . "-" . $invmode, $filename); + } + + if ( $rmflag ) + { + $log->info("Removing file '$filename'"); + unlink($filename); + system("git-update-index", "--remove", $filename); + } + elsif ( $addflag ) + { + $log->info("Adding file '$filename'"); + system("git-update-index", "--add", $filename); + } else { + $log->info("Updating file '$filename'"); + system("git-update-index", $filename); + } + } + + unless ( scalar(@committedfiles) > 0 ) + { + print "E No files to commit\n"; + print "ok\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + return; + } + + my $treehash = `git-write-tree`; + my $parenthash = `cat $ENV{GIT_DIR}refs/heads/$state->{module}`; + chomp $treehash; + chomp $parenthash; + + $log->debug("Treehash : $treehash, Parenthash : $parenthash"); + + # write our commit message out if we have one ... + my ( $msg_fh, $msg_filename ) = tempfile( DIR => $TEMP_DIR ); + print $msg_fh $state->{opt}{m};# if ( exists ( $state->{opt}{m} ) ); + print $msg_fh "\n\nvia git-CVS emulator\n"; + close $msg_fh; + + my $commithash = `git-commit-tree $treehash -p $parenthash < $msg_filename`; + $log->info("Commit hash : $commithash"); + + unless ( $commithash =~ /[a-zA-Z0-9]{40}/ ) + { + $log->warn("Commit failed (Invalid commit hash)"); + print "error 1 Commit failed (unknown reason)\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + exit; + } + + open FILE, ">", "$ENV{GIT_DIR}refs/heads/$state->{module}"; + print FILE $commithash; + close FILE; + + $updater->update(); + + # foreach file specified on the commandline ... + foreach my $filename ( @committedfiles ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + $log->debug("Checked-in $dirpart : $filename"); + + if ( $meta->{filehash} eq "deleted" ) + { + print "Remove-entry $dirpart\n"; + print "$filename\n"; + } else { + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/1.$meta->{revision}///\n"; + } + } + + close LOCKFILE; + unlink($lockfile); + chdir "/"; + + print "ok\n"; +} + +sub req_status +{ + my ( $cmd, $data ) = @_; + + argsplit("status"); + + $log->info("req_status : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + my $oldmeta = $meta; + + my $wrev = revparse($filename); + + # If the working copy is an old revision, lets get that version too for comparison. + if ( defined($wrev) and $wrev != $meta->{revision} ) + { + $oldmeta = $updater->getmeta($filename, $wrev); + } + + # TODO : All possible statuses aren't yet implemented + my $status; + # Files are up to date if the working copy and repo copy have the same revision, and the working copy is unmodified + $status = "Up-to-date" if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} + and + ( ( $state->{entries}{$filename}{unchanged} and ( not defined ( $state->{entries}{$filename}{conflict} ) or $state->{entries}{$filename}{conflict} !~ /^\+=/ ) ) + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $meta->{filehash} ) ) + ); + + # Need checkout if the working copy has an older revision than the repo copy, and the working copy is unmodified + $status ||= "Needs Checkout" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and $meta->{revision} > $wrev + and + ( $state->{entries}{$filename}{unchanged} + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} ) ) + ); + + # Need checkout if it exists in the repo but doesn't have a working copy + $status ||= "Needs Checkout" if ( not defined ( $wrev ) and defined ( $meta->{revision} ) ); + + # Locally modified if working copy and repo copy have the same revision but there are local changes + $status ||= "Locally Modified" if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} and $state->{entries}{$filename}{modified_filename} ); + + # Needs Merge if working copy revision is less than repo copy and there are local changes + $status ||= "Needs Merge" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and $meta->{revision} > $wrev and $state->{entries}{$filename}{modified_filename} ); + + $status ||= "Locally Added" if ( defined ( $state->{entries}{$filename}{revision} ) and not defined ( $meta->{revision} ) ); + $status ||= "Locally Removed" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and -$wrev == $meta->{revision} ); + $status ||= "Unresolved Conflict" if ( defined ( $state->{entries}{$filename}{conflict} ) and $state->{entries}{$filename}{conflict} =~ /^\+=/ ); + $status ||= "File had conflicts on merge" if ( 0 ); + + $status ||= "Unknown"; + + print "M ===================================================================\n"; + print "M File: $filename\tStatus: $status\n"; + if ( defined($state->{entries}{$filename}{revision}) ) + { + print "M Working revision:\t" . $state->{entries}{$filename}{revision} . "\n"; + } else { + print "M Working revision:\tNo entry for $filename\n"; + } + if ( defined($meta->{revision}) ) + { + print "M Repository revision:\t1." . $meta->{revision} . "\t$state->{repository}/$filename,v\n"; + print "M Sticky Tag:\t\t(none)\n"; + print "M Sticky Date:\t\t(none)\n"; + print "M Sticky Options:\t\t(none)\n"; + } else { + print "M Repository revision:\tNo revision control file\n"; + } + print "M\n"; + } + + print "ok\n"; +} + +sub req_diff +{ + my ( $cmd, $data ) = @_; + + argsplit("diff"); + + $log->debug("req_diff : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + my ($revision1, $revision2); + if ( defined ( $state->{opt}{r} ) and ref $state->{opt}{r} eq "ARRAY" ) + { + $revision1 = $state->{opt}{r}[0]; + $revision2 = $state->{opt}{r}[1]; + } else { + $revision1 = $state->{opt}{r}; + } + + $revision1 =~ s/^1\.// if ( defined ( $revision1 ) ); + $revision2 =~ s/^1\.// if ( defined ( $revision2 ) ); + + $log->debug("Diffing revisions " . ( defined($revision1) ? $revision1 : "[NULL]" ) . " and " . ( defined($revision2) ? $revision2 : "[NULL]" ) ); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my ( $fh, $file1, $file2, $meta1, $meta2, $filediff ); + + my $wrev = revparse($filename); + + # We need _something_ to diff against + next unless ( defined ( $wrev ) ); + + # if we have a -r switch, use it + if ( defined ( $revision1 ) ) + { + ( undef, $file1 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta1 = $updater->getmeta($filename, $revision1); + unless ( defined ( $meta1 ) and $meta1->{filehash} ne "deleted" ) + { + print "E File $filename at revision 1.$revision1 doesn't exist\n"; + next; + } + transmitfile($meta1->{filehash}, $file1); + } + # otherwise we just use the working copy revision + else + { + ( undef, $file1 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta1 = $updater->getmeta($filename, $wrev); + transmitfile($meta1->{filehash}, $file1); + } + + # if we have a second -r switch, use it too + if ( defined ( $revision2 ) ) + { + ( undef, $file2 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta2 = $updater->getmeta($filename, $revision2); + + unless ( defined ( $meta2 ) and $meta2->{filehash} ne "deleted" ) + { + print "E File $filename at revision 1.$revision2 doesn't exist\n"; + next; + } + + transmitfile($meta2->{filehash}, $file2); + } + # otherwise we just use the working copy + else + { + $file2 = $state->{entries}{$filename}{modified_filename}; + } + + # if we have been given -r, and we don't have a $file2 yet, lets get one + if ( defined ( $revision1 ) and not defined ( $file2 ) ) + { + ( undef, $file2 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta2 = $updater->getmeta($filename, $wrev); + transmitfile($meta2->{filehash}, $file2); + } + + # We need to have retrieved something useful + next unless ( defined ( $meta1 ) ); + + # Files to date if the working copy and repo copy have the same revision, and the working copy is unmodified + next if ( not defined ( $meta2 ) and $wrev == $meta1->{revision} + and + ( ( $state->{entries}{$filename}{unchanged} and ( not defined ( $state->{entries}{$filename}{conflict} ) or $state->{entries}{$filename}{conflict} !~ /^\+=/ ) ) + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $meta1->{filehash} ) ) + ); + + # Apparently we only show diffs for locally modified files + next unless ( defined($meta2) or defined ( $state->{entries}{$filename}{modified_filename} ) ); + + print "M Index: $filename\n"; + print "M ===================================================================\n"; + print "M RCS file: $state->{CVSROOT}/$state->{module}/$filename,v\n"; + print "M retrieving revision 1.$meta1->{revision}\n" if ( defined ( $meta1 ) ); + print "M retrieving revision 1.$meta2->{revision}\n" if ( defined ( $meta2 ) ); + print "M diff "; + foreach my $opt ( keys %{$state->{opt}} ) + { + if ( ref $state->{opt}{$opt} eq "ARRAY" ) + { + foreach my $value ( @{$state->{opt}{$opt}} ) + { + print "-$opt $value "; + } + } else { + print "-$opt "; + print "$state->{opt}{$opt} " if ( defined ( $state->{opt}{$opt} ) ); + } + } + print "$filename\n"; + + $log->info("Diffing $filename -r $meta1->{revision} -r " . ( $meta2->{revision} or "workingcopy" )); + + ( $fh, $filediff ) = tempfile ( DIR => $TEMP_DIR ); + + if ( exists $state->{opt}{u} ) + { + system("diff -u -L '$filename revision 1.$meta1->{revision}' -L '$filename " . ( defined($meta2->{revision}) ? "revision 1.$meta2->{revision}" : "working copy" ) . "' $file1 $file2 > $filediff"); + } else { + system("diff $file1 $file2 > $filediff"); + } + + while ( <$fh> ) + { + print "M $_"; + } + close $fh; + } + + print "ok\n"; +} + +sub req_log +{ + my ( $cmd, $data ) = @_; + + argsplit("log"); + + $log->debug("req_log : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("log state : " . Dumper($state)); + + my ( $minrev, $maxrev ); + if ( defined ( $state->{opt}{r} ) and $state->{opt}{r} =~ /([\d.]+)?(::?)([\d.]+)?/ ) + { + my $control = $2; + $minrev = $1; + $maxrev = $3; + $minrev =~ s/^1\.// if ( defined ( $minrev ) ); + $maxrev =~ s/^1\.// if ( defined ( $maxrev ) ); + $minrev++ if ( defined($minrev) and $control eq "::" ); + } + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $headmeta = $updater->getmeta($filename); + + my $revisions = $updater->getlog($filename); + my $totalrevisions = scalar(@$revisions); + + if ( defined ( $minrev ) ) + { + $log->debug("Removing revisions less than $minrev"); + while ( scalar(@$revisions) > 0 and $revisions->[-1]{revision} < $minrev ) + { + pop @$revisions; + } + } + if ( defined ( $maxrev ) ) + { + $log->debug("Removing revisions greater than $maxrev"); + while ( scalar(@$revisions) > 0 and $revisions->[0]{revision} > $maxrev ) + { + shift @$revisions; + } + } + + next unless ( scalar(@$revisions) ); + + print "M \n"; + print "M RCS file: $state->{CVSROOT}/$state->{module}/$filename,v\n"; + print "M Working file: $filename\n"; + print "M head: 1.$headmeta->{revision}\n"; + print "M branch:\n"; + print "M locks: strict\n"; + print "M access list:\n"; + print "M symbolic names:\n"; + print "M keyword substitution: kv\n"; + print "M total revisions: $totalrevisions;\tselected revisions: " . scalar(@$revisions) . "\n"; + print "M description:\n"; + + foreach my $revision ( @$revisions ) + { + print "M ----------------------------\n"; + print "M revision 1.$revision->{revision}\n"; + # reformat the date for log output + $revision->{modified} = sprintf('%04d/%02d/%02d %s', $3, $DATE_LIST->{$2}, $1, $4 ) if ( $revision->{modified} =~ /(\d+)\s+(\w+)\s+(\d+)\s+(\S+)/ and defined($DATE_LIST->{$2}) ); + $revision->{author} =~ s/\s+.*//; + $revision->{author} =~ s/^(.{8}).*/$1/; + print "M date: $revision->{modified}; author: $revision->{author}; state: " . ( $revision->{filehash} eq "deleted" ? "dead" : "Exp" ) . "; lines: +2 -3\n"; + my $commitmessage = $updater->commitmessage($revision->{commithash}); + $commitmessage =~ s/^/M /mg; + print $commitmessage . "\n"; + } + print "M =============================================================================\n"; + } + + print "ok\n"; +} + +sub req_annotate +{ + my ( $cmd, $data ) = @_; + + argsplit("annotate"); + + $log->info("req_annotate : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing annotate on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # we'll need a temporary checkout dir + my $tmpdir = tempdir ( DIR => $TEMP_DIR ); + my ( undef, $file_index ) = tempfile ( DIR => $TEMP_DIR, OPEN => 0 ); + $log->info("Temp checkoutdir creation successful, basing annotate session work on '$tmpdir', index file is '$file_index'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + $ENV{GIT_INDEX_FILE} = $file_index; + + chdir $tmpdir; + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + + next unless ( $meta->{revision} ); + + # get all the commits that this file was in + # in dense format -- aka skip dead revisions + my $revisions = $updater->gethistorydense($filename); + my $lastseenin = $revisions->[0][2]; + + # populate the temporary index based on the latest commit were we saw + # the file -- but do it cheaply without checking out any files + # TODO: if we got a revision from the client, use that instead + # to look up the commithash in sqlite (still good to default to + # the current head as we do now) + system("git-read-tree", $lastseenin); + unless ($? == 0) + { + die "Error running git-read-tree $lastseenin $file_index $!"; + } + $log->info("Created index '$file_index' with commit $lastseenin - exit status $?"); + + # do a checkout of the file + system('git-checkout-index', '-f', '-u', $filename); + unless ($? == 0) { + die "Error running git-checkout-index -f -u $filename : $!"; + } + + $log->info("Annotate $filename"); + + # Prepare a file with the commits from the linearized + # history that annotate should know about. This prevents + # git-jsannotate telling us about commits we are hiding + # from the client. + + open(ANNOTATEHINTS, ">$tmpdir/.annotate_hints") or die "Error opening > $tmpdir/.annotate_hints $!"; + for (my $i=0; $i < @$revisions; $i++) + { + print ANNOTATEHINTS $revisions->[$i][2]; + if ($i+1 < @$revisions) { # have we got a parent? + print ANNOTATEHINTS ' ' . $revisions->[$i+1][2]; + } + print ANNOTATEHINTS "\n"; + } + + print ANNOTATEHINTS "\n"; + close ANNOTATEHINTS; + + my $annotatecmd = 'git-annotate'; + open(ANNOTATE, "-|", $annotatecmd, '-l', '-S', "$tmpdir/.annotate_hints", $filename) + or die "Error invoking $annotatecmd -l -S $tmpdir/.annotate_hints $filename : $!"; + my $metadata = {}; + print "E Annotations for $filename\n"; + print "E ***************\n"; + while ( <ANNOTATE> ) + { + if (m/^([a-zA-Z0-9]{40})\t\([^\)]*\)(.*)$/i) + { + my $commithash = $1; + my $data = $2; + unless ( defined ( $metadata->{$commithash} ) ) + { + $metadata->{$commithash} = $updater->getmeta($filename, $commithash); + $metadata->{$commithash}{author} =~ s/\s+.*//; + $metadata->{$commithash}{author} =~ s/^(.{8}).*/$1/; + $metadata->{$commithash}{modified} = sprintf("%02d-%s-%02d", $1, $2, $3) if ( $metadata->{$commithash}{modified} =~ /^(\d+)\s(\w+)\s\d\d(\d\d)/ ); + } + printf("M 1.%-5d (%-8s %10s): %s\n", + $metadata->{$commithash}{revision}, + $metadata->{$commithash}{author}, + $metadata->{$commithash}{modified}, + $data + ); + } else { + $log->warn("Error in annotate output! LINE: $_"); + print "E Annotate error \n"; + next; + } + } + close ANNOTATE; + } + + # done; get out of the tempdir + chdir "/"; + + print "ok\n"; + +} + +# This method takes the state->{arguments} array and produces two new arrays. +# The first is $state->{args} which is everything before the '--' argument, and +# the second is $state->{files} which is everything after it. +sub argsplit +{ + return unless( defined($state->{arguments}) and ref $state->{arguments} eq "ARRAY" ); + + my $type = shift; + + $state->{args} = []; + $state->{files} = []; + $state->{opt} = {}; + + if ( defined($type) ) + { + my $opt = {}; + $opt = { A => 0, N => 0, P => 0, R => 0, c => 0, f => 0, l => 0, n => 0, p => 0, s => 0, r => 1, D => 1, d => 1, k => 1, j => 1, } if ( $type eq "co" ); + $opt = { v => 0, l => 0, R => 0 } if ( $type eq "status" ); + $opt = { A => 0, P => 0, C => 0, d => 0, f => 0, l => 0, R => 0, p => 0, k => 1, r => 1, D => 1, j => 1, I => 1, W => 1 } if ( $type eq "update" ); + $opt = { l => 0, R => 0, k => 1, D => 1, D => 1, r => 2 } if ( $type eq "diff" ); + $opt = { c => 0, R => 0, l => 0, f => 0, F => 1, m => 1, r => 1 } if ( $type eq "ci" ); + $opt = { k => 1, m => 1 } if ( $type eq "add" ); + $opt = { f => 0, l => 0, R => 0 } if ( $type eq "remove" ); + $opt = { l => 0, b => 0, h => 0, R => 0, t => 0, N => 0, S => 0, r => 1, d => 1, s => 1, w => 1 } if ( $type eq "log" ); + + + while ( scalar ( @{$state->{arguments}} ) > 0 ) + { + my $arg = shift @{$state->{arguments}}; + + next if ( $arg eq "--" ); + next unless ( $arg =~ /\S/ ); + + # if the argument looks like a switch + if ( $arg =~ /^-(\w)(.*)/ ) + { + # if it's a switch that takes an argument + if ( $opt->{$1} ) + { + # If this switch has already been provided + if ( $opt->{$1} > 1 and exists ( $state->{opt}{$1} ) ) + { + $state->{opt}{$1} = [ $state->{opt}{$1} ]; + if ( length($2) > 0 ) + { + push @{$state->{opt}{$1}},$2; + } else { + push @{$state->{opt}{$1}}, shift @{$state->{arguments}}; + } + } else { + # if there's extra data in the arg, use that as the argument for the switch + if ( length($2) > 0 ) + { + $state->{opt}{$1} = $2; + } else { + $state->{opt}{$1} = shift @{$state->{arguments}}; + } + } + } else { + $state->{opt}{$1} = undef; + } + } + else + { + push @{$state->{args}}, $arg; + } + } + } + else + { + my $mode = 0; + + foreach my $value ( @{$state->{arguments}} ) + { + if ( $value eq "--" ) + { + $mode++; + next; + } + push @{$state->{args}}, $value if ( $mode == 0 ); + push @{$state->{files}}, $value if ( $mode == 1 ); + } + } +} + +# This method uses $state->{directory} to populate $state->{args} with a list of filenames +sub argsfromdir +{ + my $updater = shift; + + $state->{args} = []; + + foreach my $file ( @{$updater->gethead} ) + { + next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) ); + next unless ( $file->{name} =~ s/^$state->{directory}// ); + push @{$state->{args}}, $file->{name}; + } +} + +# This method cleans up the $state variable after a command that uses arguments has run +sub statecleanup +{ + $state->{files} = []; + $state->{args} = []; + $state->{arguments} = []; + $state->{entries} = {}; +} + +sub revparse +{ + my $filename = shift; + + return undef unless ( defined ( $state->{entries}{$filename}{revision} ) ); + + return $1 if ( $state->{entries}{$filename}{revision} =~ /^1\.(\d+)/ ); + return -$1 if ( $state->{entries}{$filename}{revision} =~ /^-1\.(\d+)/ ); + + return undef; +} + +# This method takes a file hash and does a CVS "file transfer" which transmits the +# size of the file, and then the file contents. +# If a second argument $targetfile is given, the file is instead written out to +# a file by the name of $targetfile +sub transmitfile +{ + my $filehash = shift; + my $targetfile = shift; + + if ( defined ( $filehash ) and $filehash eq "deleted" ) + { + $log->warn("filehash is 'deleted'"); + return; + } + + die "Need filehash" unless ( defined ( $filehash ) and $filehash =~ /^[a-zA-Z0-9]{40}$/ ); + + my $type = `git-cat-file -t $filehash`; + chomp $type; + + die ( "Invalid type '$type' (expected 'blob')" ) unless ( defined ( $type ) and $type eq "blob" ); + + my $size = `git-cat-file -s $filehash`; + chomp $size; + + $log->debug("transmitfile($filehash) size=$size, type=$type"); + + if ( open my $fh, '-|', "git-cat-file", "blob", $filehash ) + { + if ( defined ( $targetfile ) ) + { + open NEWFILE, ">", $targetfile or die("Couldn't open '$targetfile' for writing : $!"); + print NEWFILE $_ while ( <$fh> ); + close NEWFILE; + } else { + print "$size\n"; + print while ( <$fh> ); + } + close $fh or die ("Couldn't close filehandle for transmitfile()"); + } else { + die("Couldn't execute git-cat-file"); + } +} + +# This method takes a file name, and returns ( $dirpart, $filepart ) which +# refers to the directory porition and the file portion of the filename +# respectively +sub filenamesplit +{ + my $filename = shift; + + my ( $filepart, $dirpart ) = ( $filename, "." ); + ( $filepart, $dirpart ) = ( $2, $1 ) if ( $filename =~ /(.*)\/(.*)/ ); + $dirpart .= "/"; + + return ( $filepart, $dirpart ); +} + +sub filecleanup +{ + my $filename = shift; + + return undef unless(defined($filename)); + if ( $filename =~ /^\// ) + { + print "E absolute filenames '$filename' not supported by server\n"; + return undef; + } + + $filename =~ s/^\.\///g; + $filename = $state->{directory} . $filename; + + return $filename; +} + +package GITCVS::log; + +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### + +use strict; +use warnings; + +=head1 NAME + +GITCVS::log + +=head1 DESCRIPTION + +This module provides very crude logging with a similar interface to +Log::Log4perl + +=head1 METHODS + +=cut + +=head2 new + +Creates a new log object, optionally you can specify a filename here to +indicate the file to log to. If no log file is specified, you can specifiy one +later with method setfile, or indicate you no longer want logging with method +nofile. + +Until one of these methods is called, all log calls will buffer messages ready +to write out. + +=cut +sub new +{ + my $class = shift; + my $filename = shift; + + my $self = {}; + + bless $self, $class; + + if ( defined ( $filename ) ) + { + open $self->{fh}, ">>", $filename or die("Couldn't open '$filename' for writing : $!"); + } + + return $self; +} + +=head2 setfile + +This methods takes a filename, and attempts to open that file as the log file. +If successful, all buffered data is written out to the file, and any further +logging is written directly to the file. + +=cut +sub setfile +{ + my $self = shift; + my $filename = shift; + + if ( defined ( $filename ) ) + { + open $self->{fh}, ">>", $filename or die("Couldn't open '$filename' for writing : $!"); + } + + return unless ( defined ( $self->{buffer} ) and ref $self->{buffer} eq "ARRAY" ); + + while ( my $line = shift @{$self->{buffer}} ) + { + print {$self->{fh}} $line; + } +} + +=head2 nofile + +This method indicates no logging is going to be used. It flushes any entries in +the internal buffer, and sets a flag to ensure no further data is put there. + +=cut +sub nofile +{ + my $self = shift; + + $self->{nolog} = 1; + + return unless ( defined ( $self->{buffer} ) and ref $self->{buffer} eq "ARRAY" ); + + $self->{buffer} = []; +} + +=head2 _logopen + +Internal method. Returns true if the log file is open, false otherwise. + +=cut +sub _logopen +{ + my $self = shift; + + return 1 if ( defined ( $self->{fh} ) and ref $self->{fh} eq "GLOB" ); + return 0; +} + +=head2 debug info warn fatal + +These four methods are wrappers to _log. They provide the actual interface for +logging data. + +=cut +sub debug { my $self = shift; $self->_log("debug", @_); } +sub info { my $self = shift; $self->_log("info" , @_); } +sub warn { my $self = shift; $self->_log("warn" , @_); } +sub fatal { my $self = shift; $self->_log("fatal", @_); } + +=head2 _log + +This is an internal method called by the logging functions. It generates a +timestamp and pushes the logged line either to file, or internal buffer. + +=cut +sub _log +{ + my $self = shift; + my $level = shift; + + return if ( $self->{nolog} ); + + my @time = localtime; + my $timestring = sprintf("%4d-%02d-%02d %02d:%02d:%02d : %-5s", + $time[5] + 1900, + $time[4] + 1, + $time[3], + $time[2], + $time[1], + $time[0], + uc $level, + ); + + if ( $self->_logopen ) + { + print {$self->{fh}} $timestring . " - " . join(" ",@_) . "\n"; + } else { + push @{$self->{buffer}}, $timestring . " - " . join(" ",@_) . "\n"; + } +} + +=head2 DESTROY + +This method simply closes the file handle if one is open + +=cut +sub DESTROY +{ + my $self = shift; + + if ( $self->_logopen ) + { + close $self->{fh}; + } +} + +package GITCVS::updater; + +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### + +use strict; +use warnings; +use DBI; + +=head1 METHODS + +=cut + +=head2 new + +=cut +sub new +{ + my $class = shift; + my $config = shift; + my $module = shift; + my $log = shift; + + die "Need to specify a git repository" unless ( defined($config) and -d $config ); + die "Need to specify a module" unless ( defined($module) ); + + $class = ref($class) || $class; + + my $self = {}; + + bless $self, $class; + + $self->{dbdir} = $config . "/"; + die "Database dir '$self->{dbdir}' isn't a directory" unless ( defined($self->{dbdir}) and -d $self->{dbdir} ); + + $self->{module} = $module; + $self->{file} = $self->{dbdir} . "/gitcvs.$module.sqlite"; + + $self->{git_path} = $config . "/"; + + $self->{log} = $log; + + die "Git repo '$self->{git_path}' doesn't exist" unless ( -d $self->{git_path} ); + + $self->{dbh} = DBI->connect("dbi:SQLite:dbname=" . $self->{file},"",""); + + $self->{tables} = {}; + foreach my $table ( $self->{dbh}->tables ) + { + $table =~ s/^"//; + $table =~ s/"$//; + $self->{tables}{$table} = 1; + } + + # Construct the revision table if required + unless ( $self->{tables}{revision} ) + { + $self->{dbh}->do(" + CREATE TABLE revision ( + name TEXT NOT NULL, + revision INTEGER NOT NULL, + filehash TEXT NOT NULL, + commithash TEXT NOT NULL, + author TEXT NOT NULL, + modified TEXT NOT NULL, + mode TEXT NOT NULL + ) + "); + } + + # Construct the revision table if required + unless ( $self->{tables}{head} ) + { + $self->{dbh}->do(" + CREATE TABLE head ( + name TEXT NOT NULL, + revision INTEGER NOT NULL, + filehash TEXT NOT NULL, + commithash TEXT NOT NULL, + author TEXT NOT NULL, + modified TEXT NOT NULL, + mode TEXT NOT NULL + ) + "); + } + + # Construct the properties table if required + unless ( $self->{tables}{properties} ) + { + $self->{dbh}->do(" + CREATE TABLE properties ( + key TEXT NOT NULL PRIMARY KEY, + value TEXT + ) + "); + } + + # Construct the commitmsgs table if required + unless ( $self->{tables}{commitmsgs} ) + { + $self->{dbh}->do(" + CREATE TABLE commitmsgs ( + key TEXT NOT NULL PRIMARY KEY, + value TEXT + ) + "); + } + + return $self; +} + +=head2 update + +=cut +sub update +{ + my $self = shift; + + # first lets get the commit list + $ENV{GIT_DIR} = $self->{git_path}; + + # prepare database queries + my $db_insert_rev = $self->{dbh}->prepare_cached("INSERT INTO revision (name, revision, filehash, commithash, modified, author, mode) VALUES (?,?,?,?,?,?,?)",{},1); + my $db_insert_mergelog = $self->{dbh}->prepare_cached("INSERT INTO commitmsgs (key, value) VALUES (?,?)",{},1); + my $db_delete_head = $self->{dbh}->prepare_cached("DELETE FROM head",{},1); + my $db_insert_head = $self->{dbh}->prepare_cached("INSERT INTO head (name, revision, filehash, commithash, modified, author, mode) VALUES (?,?,?,?,?,?,?)",{},1); + + my $commitinfo = `git-cat-file commit $self->{module} 2>&1`; + unless ( $commitinfo =~ /tree\s+[a-zA-Z0-9]{40}/ ) + { + die("Invalid module '$self->{module}'"); + } + + + my $git_log; + my $lastcommit = $self->_get_prop("last_commit"); + + # Start exclusive lock here... + $self->{dbh}->begin_work() or die "Cannot lock database for BEGIN"; + + # TODO: log processing is memory bound + # if we can parse into a 2nd file that is in reverse order + # we can probably do something really efficient + my @git_log_params = ('--parents', '--topo-order'); + + if (defined $lastcommit) { + push @git_log_params, "$lastcommit..$self->{module}"; + } else { + push @git_log_params, $self->{module}; + } + open(GITLOG, '-|', 'git-log', @git_log_params) or die "Cannot call git-log: $!"; + + my @commits; + + my %commit = (); + + while ( <GITLOG> ) + { + chomp; + if (m/^commit\s+(.*)$/) { + # on ^commit lines put the just seen commit in the stack + # and prime things for the next one + if (keys %commit) { + my %copy = %commit; + unshift @commits, \%copy; + %commit = (); + } + my @parents = split(m/\s+/, $1); + $commit{hash} = shift @parents; + $commit{parents} = \@parents; + } elsif (m/^(\w+?):\s+(.*)$/ && !exists($commit{message})) { + # on rfc822-like lines seen before we see any message, + # lowercase the entry and put it in the hash as key-value + $commit{lc($1)} = $2; + } else { + # message lines - skip initial empty line + # and trim whitespace + if (!exists($commit{message}) && m/^\s*$/) { + # define it to mark the end of headers + $commit{message} = ''; + next; + } + s/^\s+//; s/\s+$//; # trim ws + $commit{message} .= $_ . "\n"; + } + } + close GITLOG; + + unshift @commits, \%commit if ( keys %commit ); + + # Now all the commits are in the @commits bucket + # ordered by time DESC. for each commit that needs processing, + # determine whether it's following the last head we've seen or if + # it's on its own branch, grab a file list, and add whatever's changed + # NOTE: $lastcommit refers to the last commit from previous run + # $lastpicked is the last commit we picked in this run + my $lastpicked; + my $head = {}; + if (defined $lastcommit) { + $lastpicked = $lastcommit; + } + + my $committotal = scalar(@commits); + my $commitcount = 0; + + # Load the head table into $head (for cached lookups during the update process) + foreach my $file ( @{$self->gethead()} ) + { + $head->{$file->{name}} = $file; + } + + foreach my $commit ( @commits ) + { + $self->{log}->debug("GITCVS::updater - Processing commit $commit->{hash} (" . (++$commitcount) . " of $committotal)"); + if (defined $lastpicked) + { + if (!in_array($lastpicked, @{$commit->{parents}})) + { + # skip, we'll see this delta + # as part of a merge later + # warn "skipping off-track $commit->{hash}\n"; + next; + } elsif (@{$commit->{parents}} > 1) { + # it is a merge commit, for each parent that is + # not $lastpicked, see if we can get a log + # from the merge-base to that parent to put it + # in the message as a merge summary. + my @parents = @{$commit->{parents}}; + foreach my $parent (@parents) { + # git-merge-base can potentially (but rarely) throw + # several candidate merge bases. let's assume + # that the first one is the best one. + if ($parent eq $lastpicked) { + next; + } + open my $p, 'git-merge-base '. $lastpicked . ' ' + . $parent . '|'; + my @output = (<$p>); + close $p; + my $base = join('', @output); + chomp $base; + if ($base) { + my @merged; + # print "want to log between $base $parent \n"; + open(GITLOG, '-|', 'git-log', "$base..$parent") + or die "Cannot call git-log: $!"; + my $mergedhash; + while (<GITLOG>) { + chomp; + if (!defined $mergedhash) { + if (m/^commit\s+(.+)$/) { + $mergedhash = $1; + } else { + next; + } + } else { + # grab the first line that looks non-rfc822 + # aka has content after leading space + if (m/^\s+(\S.*)$/) { + my $title = $1; + $title = substr($title,0,100); # truncate + unshift @merged, "$mergedhash $title"; + undef $mergedhash; + } + } + } + close GITLOG; + if (@merged) { + $commit->{mergemsg} = $commit->{message}; + $commit->{mergemsg} .= "\nSummary of merged commits:\n\n"; + foreach my $summary (@merged) { + $commit->{mergemsg} .= "\t$summary\n"; + } + $commit->{mergemsg} .= "\n\n"; + # print "Message for $commit->{hash} \n$commit->{mergemsg}"; + } + } + } + } + } + + # convert the date to CVS-happy format + $commit->{date} = "$2 $1 $4 $3 $5" if ( $commit->{date} =~ /^\w+\s+(\w+)\s+(\d+)\s+(\d+:\d+:\d+)\s+(\d+)\s+([+-]\d+)$/ ); + + if ( defined ( $lastpicked ) ) + { + my $filepipe = open(FILELIST, '-|', 'git-diff-tree', '-r', $lastpicked, $commit->{hash}) or die("Cannot call git-diff-tree : $!"); + while ( <FILELIST> ) + { + unless ( /^:\d{6}\s+\d{3}(\d)\d{2}\s+[a-zA-Z0-9]{40}\s+([a-zA-Z0-9]{40})\s+(\w)\s+(.*)$/o ) + { + die("Couldn't process git-diff-tree line : $_"); + } + + # $log->debug("File mode=$1, hash=$2, change=$3, name=$4"); + + my $git_perms = ""; + $git_perms .= "r" if ( $1 & 4 ); + $git_perms .= "w" if ( $1 & 2 ); + $git_perms .= "x" if ( $1 & 1 ); + $git_perms = "rw" if ( $git_perms eq "" ); + + if ( $3 eq "D" ) + { + #$log->debug("DELETE $4"); + $head->{$4} = { + name => $4, + revision => $head->{$4}{revision} + 1, + filehash => "deleted", + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + elsif ( $3 eq "M" ) + { + #$log->debug("MODIFIED $4"); + $head->{$4} = { + name => $4, + revision => $head->{$4}{revision} + 1, + filehash => $2, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + elsif ( $3 eq "A" ) + { + #$log->debug("ADDED $4"); + $head->{$4} = { + name => $4, + revision => 1, + filehash => $2, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + else + { + $log->warn("UNKNOWN FILE CHANGE mode=$1, hash=$2, change=$3, name=$4"); + die; + } + } + close FILELIST; + } else { + # this is used to detect files removed from the repo + my $seen_files = {}; + + my $filepipe = open(FILELIST, '-|', 'git-ls-tree', '-r', $commit->{hash}) or die("Cannot call git-ls-tree : $!"); + while ( <FILELIST> ) + { + unless ( /^(\d+)\s+(\w+)\s+([a-zA-Z0-9]+)\s+(.*)$/o ) + { + die("Couldn't process git-ls-tree line : $_"); + } + + my ( $git_perms, $git_type, $git_hash, $git_filename ) = ( $1, $2, $3, $4 ); + + $seen_files->{$git_filename} = 1; + + my ( $oldhash, $oldrevision, $oldmode ) = ( + $head->{$git_filename}{filehash}, + $head->{$git_filename}{revision}, + $head->{$git_filename}{mode} + ); + + if ( $git_perms =~ /^\d\d\d(\d)\d\d/o ) + { + $git_perms = ""; + $git_perms .= "r" if ( $1 & 4 ); + $git_perms .= "w" if ( $1 & 2 ); + $git_perms .= "x" if ( $1 & 1 ); + } else { + $git_perms = "rw"; + } + + # unless the file exists with the same hash, we need to update it ... + unless ( defined($oldhash) and $oldhash eq $git_hash and defined($oldmode) and $oldmode eq $git_perms ) + { + my $newrevision = ( $oldrevision or 0 ) + 1; + + $head->{$git_filename} = { + name => $git_filename, + revision => $newrevision, + filehash => $git_hash, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + + + $db_insert_rev->execute($git_filename, $newrevision, $git_hash, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + } + close FILELIST; + + # Detect deleted files + foreach my $file ( keys %$head ) + { + unless ( exists $seen_files->{$file} or $head->{$file}{filehash} eq "deleted" ) + { + $head->{$file}{revision}++; + $head->{$file}{filehash} = "deleted"; + $head->{$file}{commithash} = $commit->{hash}; + $head->{$file}{modified} = $commit->{date}; + $head->{$file}{author} = $commit->{author}; + + $db_insert_rev->execute($file, $head->{$file}{revision}, $head->{$file}{filehash}, $commit->{hash}, $commit->{date}, $commit->{author}, $head->{$file}{mode}); + } + } + # END : "Detect deleted files" + } + + + if (exists $commit->{mergemsg}) + { + $db_insert_mergelog->execute($commit->{hash}, $commit->{mergemsg}); + } + + $lastpicked = $commit->{hash}; + + $self->_set_prop("last_commit", $commit->{hash}); + } + + $db_delete_head->execute(); + foreach my $file ( keys %$head ) + { + $db_insert_head->execute( + $file, + $head->{$file}{revision}, + $head->{$file}{filehash}, + $head->{$file}{commithash}, + $head->{$file}{modified}, + $head->{$file}{author}, + $head->{$file}{mode}, + ); + } + # invalidate the gethead cache + $self->{gethead_cache} = undef; + + + # Ending exclusive lock here + $self->{dbh}->commit() or die "Failed to commit changes to SQLite"; +} + +sub _headrev +{ + my $self = shift; + my $filename = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT filehash, revision, mode FROM head WHERE name=?",{},1); + $db_query->execute($filename); + my ( $hash, $revision, $mode ) = $db_query->fetchrow_array; + + return ( $hash, $revision, $mode ); +} + +sub _get_prop +{ + my $self = shift; + my $key = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT value FROM properties WHERE key=?",{},1); + $db_query->execute($key); + my ( $value ) = $db_query->fetchrow_array; + + return $value; +} + +sub _set_prop +{ + my $self = shift; + my $key = shift; + my $value = shift; + + my $db_query = $self->{dbh}->prepare_cached("UPDATE properties SET value=? WHERE key=?",{},1); + $db_query->execute($value, $key); + + unless ( $db_query->rows ) + { + $db_query = $self->{dbh}->prepare_cached("INSERT INTO properties (key, value) VALUES (?,?)",{},1); + $db_query->execute($key, $value); + } + + return $value; +} + +=head2 gethead + +=cut + +sub gethead +{ + my $self = shift; + + return $self->{gethead_cache} if ( defined ( $self->{gethead_cache} ) ); + + my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, mode, revision, modified, commithash, author FROM head",{},1); + $db_query->execute(); + + my $tree = []; + while ( my $file = $db_query->fetchrow_hashref ) + { + push @$tree, $file; + } + + $self->{gethead_cache} = $tree; + + return $tree; +} + +=head2 getlog + +=cut + +sub getlog +{ + my $self = shift; + my $filename = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, author, mode, revision, modified, commithash FROM revision WHERE name=? ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + my $tree = []; + while ( my $file = $db_query->fetchrow_hashref ) + { + push @$tree, $file; + } + + return $tree; +} + +=head2 getmeta + +This function takes a filename (with path) argument and returns a hashref of +metadata for that file. + +=cut + +sub getmeta +{ + my $self = shift; + my $filename = shift; + my $revision = shift; + + my $db_query; + if ( defined($revision) and $revision =~ /^\d+$/ ) + { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM revision WHERE name=? AND revision=?",{},1); + $db_query->execute($filename, $revision); + } + elsif ( defined($revision) and $revision =~ /^[a-zA-Z0-9]{40}$/ ) + { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM revision WHERE name=? AND commithash=?",{},1); + $db_query->execute($filename, $revision); + } else { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM head WHERE name=?",{},1); + $db_query->execute($filename); + } + + return $db_query->fetchrow_hashref; +} + +=head2 commitmessage + +this function takes a commithash and returns the commit message for that commit + +=cut +sub commitmessage +{ + my $self = shift; + my $commithash = shift; + + die("Need commithash") unless ( defined($commithash) and $commithash =~ /^[a-zA-Z0-9]{40}$/ ); + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT value FROM commitmsgs WHERE key=?",{},1); + $db_query->execute($commithash); + + my ( $message ) = $db_query->fetchrow_array; + + if ( defined ( $message ) ) + { + $message .= " " if ( $message =~ /\n$/ ); + return $message; + } + + my @lines = safe_pipe_capture("git-cat-file", "commit", $commithash); + shift @lines while ( $lines[0] =~ /\S/ ); + $message = join("",@lines); + $message .= " " if ( $message =~ /\n$/ ); + return $message; +} + +=head2 gethistory + +This function takes a filename (with path) argument and returns an arrayofarrays +containing revision,filehash,commithash ordered by revision descending + +=cut +sub gethistory +{ + my $self = shift; + my $filename = shift; + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT revision, filehash, commithash FROM revision WHERE name=? ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + return $db_query->fetchall_arrayref; +} + +=head2 gethistorydense + +This function takes a filename (with path) argument and returns an arrayofarrays +containing revision,filehash,commithash ordered by revision descending. + +This version of gethistory skips deleted entries -- so it is useful for annotate. +The 'dense' part is a reference to a '--dense' option available for git-rev-list +and other git tools that depend on it. + +=cut +sub gethistorydense +{ + my $self = shift; + my $filename = shift; + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT revision, filehash, commithash FROM revision WHERE name=? AND filehash!='deleted' ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + return $db_query->fetchall_arrayref; +} + +=head2 in_array() + +from Array::PAT - mimics the in_array() function +found in PHP. Yuck but works for small arrays. + +=cut +sub in_array +{ + my ($check, @array) = @_; + my $retval = 0; + foreach my $test (@array){ + if($check eq $test){ + $retval = 1; + } + } + return $retval; +} + +=head2 safe_pipe_capture + +an alterative to `command` that allows input to be passed as an array +to work around shell problems with weird characters in arguments + +=cut +sub safe_pipe_capture { + + my @output; + + if (my $pid = open my $child, '-|') { + @output = (<$child>); + close $child or die join(' ',@_).": $! $?"; + } else { + exec(@_) or die "$! $?"; # exec() can fail the executable can't be found + } + return wantarray ? @output : join('',@output); +} + + +1; diff --git a/git-fetch.sh b/git-fetch.sh index b4325d9d98..de4f011e26 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -320,7 +320,7 @@ fetch_main () { ( : subshell because we muck with IFS IFS=" $LF" ( - git-fetch-pack $exec $keep "$remote" $rref || echo failed "$remote" + git-fetch-pack $exec $keep --thin "$remote" $rref || echo failed "$remote" ) | while read sha1 remote_name do @@ -368,20 +368,25 @@ fetch_main "$reflist" # automated tag following case "$no_tags$tags" in '') - taglist=$(IFS=" " && - git-ls-remote $upload_pack --tags "$remote" | - sed -ne 's|^\([0-9a-f]*\)[ ]\(refs/tags/.*\)^{}$|\1 \2|p' | - while read sha1 name - do - test -f "$GIT_DIR/$name" && continue - git-check-ref-format "$name" || { - echo >&2 "warning: tag ${name} ignored" - continue - } - git-cat-file -t "$sha1" >/dev/null 2>&1 || continue - echo >&2 "Auto-following $name" - echo ".${name}:${name}" - done) + case "$reflist" in + *:refs/*) + # effective only when we are following remote branch + # using local tracking branch. + taglist=$(IFS=" " && + git-ls-remote $upload_pack --tags "$remote" | + sed -ne 's|^\([0-9a-f]*\)[ ]\(refs/tags/.*\)^{}$|\1 \2|p' | + while read sha1 name + do + test -f "$GIT_DIR/$name" && continue + git-check-ref-format "$name" || { + echo >&2 "warning: tag ${name} ignored" + continue + } + git-cat-file -t "$sha1" >/dev/null 2>&1 || continue + echo >&2 "Auto-following $name" + echo ".${name}:${name}" + done) + esac case "$taglist" in '') ;; ?*) diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl index c34ddc5d5e..dae383f231 100755 --- a/git-fmt-merge-msg.perl +++ b/git-fmt-merge-msg.perl @@ -28,21 +28,12 @@ sub andjoin { } sub repoconfig { - my $fh; - my $val; - eval { - open $fh, '-|', 'git-repo-config', '--get', 'merge.summary' - or die "$!"; - ($val) = <$fh>; - close $fh; - }; + my ($val) = qx{git-repo-config --get merge.summary}; return $val; } sub current_branch { - my $fh; - open $fh, '-|', 'git-symbolic-ref', 'HEAD' or die "$!"; - my ($bra) = <$fh>; + my ($bra) = qx{git-symbolic-ref HEAD}; chomp($bra); $bra =~ s|^refs/heads/||; if ($bra ne 'master') { @@ -50,21 +41,17 @@ sub current_branch { } else { $bra = ""; } - return $bra; } sub shortlog { - my ($tip, $limit) = @_; - my ($fh, @result); - open $fh, '-|', ('git-log', "--max-count=$limit", '--topo-order', - '--pretty=oneline', $tip, '^HEAD') - or die "$!"; - while (<$fh>) { + my ($tip) = @_; + my @result; + foreach ( qx{git-log --topo-order --pretty=oneline $tip ^HEAD} ) { s/^[0-9a-f]{40}\s+//; push @result, $_; } - close $fh or die "$!"; + die "git-log failed\n" if $?; return @result; } @@ -160,7 +147,7 @@ my $limit = 20; for (@origin) { my ($sha1, $name) = @$_; - my @log = shortlog($sha1, $limit + 1); + my @log = shortlog($sha1); if ($limit + 1 <= @log) { print "\n* $name: (" . scalar(@log) . " commits)\n"; } diff --git a/git-format-patch.sh b/git-format-patch.sh index e54c9e4a94..eb75de4601 100755 --- a/git-format-patch.sh +++ b/git-format-patch.sh @@ -189,7 +189,7 @@ my @month_names = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); sub show_date { my ($time, $tz) = @_; my $minutes = abs($tz); - $minutes = ($minutes / 100) * 60 + ($minutes % 100); + $minutes = int($minutes / 100) * 60 + ($minutes % 100); if ($tz < 0) { $minutes = -$minutes; } diff --git a/git-merge.sh b/git-merge.sh index 74f07610fa..7be9e81f1f 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -13,6 +13,10 @@ LF=' all_strategies='recursive octopus resolve stupid ours' default_strategies='recursive' use_strategies= +if test "@@NO_PYTHON@@"; then + all_strategies='resolve octopus stupid ours' + default_strategies='resolve' +fi dropsave() { rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" \ @@ -130,7 +134,7 @@ case "$#,$common,$no_commit" in echo "Updating from $head to $1." git-update-index --refresh 2>/dev/null new_head=$(git-rev-parse --verify "$1^0") && - git-read-tree -u -m $head "$new_head" && + git-read-tree -u -v -m $head "$new_head" && finish "$new_head" "Fast forward" dropsave exit 0 @@ -142,9 +146,11 @@ case "$#,$common,$no_commit" in 1,*,) # We are not doing octopus, not fast forward, and have only # one common. See if it is really trivial. + git var GIT_COMMITTER_IDENT >/dev/null || exit + echo "Trying really trivial in-index merge..." git-update-index --refresh 2>/dev/null - if git-read-tree --trivial -m -u $common $head "$1" && + if git-read-tree --trivial -m -u -v $common $head "$1" && result_tree=$(git-write-tree) then echo "Wonderful." @@ -179,6 +185,9 @@ case "$#,$common,$no_commit" in ;; esac +# We are going to make a new commit. +git var GIT_COMMITTER_IDENT >/dev/null || exit + case "$use_strategies" in '') case "$#" in diff --git a/git-push.sh b/git-push.sh index 706db9933e..73dcf067cb 100755 --- a/git-push.sh +++ b/git-push.sh @@ -8,6 +8,7 @@ USAGE='[--all] [--tags] [--force] <repository> [<refspec>...]' has_all= has_force= has_exec= +has_thin= remote= do_tags= @@ -22,6 +23,8 @@ do has_force=--force ;; --exec=*) has_exec="$1" ;; + --thin) + has_thin="$1" ;; -*) usage ;; *) @@ -72,6 +75,7 @@ set x "$remote" "$@"; shift test "$has_all" && set x "$has_all" "$@" && shift test "$has_force" && set x "$has_force" "$@" && shift test "$has_exec" && set x "$has_exec" "$@" && shift +test "$has_thin" && set x "$has_thin" "$@" && shift case "$remote" in http://* | https://*) diff --git a/git-rebase.sh b/git-rebase.sh index 21c3d83c3a..5956f0654e 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -4,24 +4,28 @@ # USAGE='[--onto <newbase>] <upstream> [<branch>]' -LONG_USAGE='If <branch> is specified, switch to that branch first. Then, -extract commits in the current branch that are not in <upstream>, -and reconstruct the current on top of <upstream>, discarding the original -development history. If --onto <newbase> is specified, the history is -reconstructed on top of <newbase>, instead of <upstream>. For example, -while on "topic" branch: +LONG_USAGE='git-rebase applies to <upstream> (or optionally to <newbase>) commits +from <branch> that do not appear in <upstream>. When <branch> is not +specified it defaults to the current branch (HEAD). + +When git-rebase is complete, <branch> will be updated to point to the +newly created line of commit objects, so the previous line will not be +accessible unless there are other references to it already. + +Assuming the following history: A---B---C topic / D---E---F---G master - $ '"$0"' --onto master~1 master topic +The result of the following command: -would rewrite the history to look like this: + git-rebase --onto master~1 master topic + would be: - A'\''--B'\''--C'\'' topic - / + A'\''--B'\''--C'\'' topic + / D---E---F---G master ' @@ -71,7 +75,7 @@ esac # The upstream head must be given. Make sure it is valid. upstream_name="$1" upstream=`git rev-parse --verify "${upstream_name}^0"` || - die "invalid upsteram $upstream_name" + die "invalid upstream $upstream_name" # If a hook exists, give it a chance to interrupt if test -x "$GIT_DIR/hooks/pre-rebase" diff --git a/git-repack.sh b/git-repack.sh index 1fafb6ecf6..3d6fec1c9a 100755 --- a/git-repack.sh +++ b/git-repack.sh @@ -3,17 +3,20 @@ # Copyright (c) 2005 Linus Torvalds # -USAGE='[-a] [-d] [-l] [-n]' +USAGE='[-a] [-d] [-f] [-l] [-n] [-q]' . git-sh-setup -no_update_info= all_into_one= remove_redundant= local= +no_update_info= all_into_one= remove_redundant= +local= quiet= no_reuse_delta= while case "$#" in 0) break ;; esac do case "$1" in -n) no_update_info=t ;; -a) all_into_one=t ;; -d) remove_redundant=t ;; - -l) local=t ;; + -q) quiet=-q ;; + -f) no_reuse_delta=--no-reuse-delta ;; + -l) local=--local ;; *) usage ;; esac shift @@ -39,9 +42,7 @@ case ",$all_into_one," in find . -type f \( -name '*.pack' -o -name '*.idx' \) -print` ;; esac -if [ "$local" ]; then - pack_objects="$pack_objects --local" -fi +pack_objects="$pack_objects $local $quiet $no_reuse_delta" name=$(git-rev-list --objects $rev_list $(git-rev-parse $rev_parse) 2>&1 | git-pack-objects --non-empty $pack_objects .tmp-pack) || exit 1 diff --git a/git-rerere.perl b/git-rerere.perl index df119517fe..d3664ff491 100755 --- a/git-rerere.perl +++ b/git-rerere.perl @@ -131,7 +131,11 @@ sub record_preimage { sub find_conflict { my $in; local $/ = "\0"; - open $in, '-|', qw(git ls-files -z -u) or die "$!: ls-files"; + my $pid = open($in, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec(qw(git ls-files -z -u)) or die "$!: ls-files"; + } my %path = (); my @path = (); while (<$in>) { diff --git a/git-resolve.sh b/git-resolve.sh index 9263070054..b53ede8d87 100755 --- a/git-resolve.sh +++ b/git-resolve.sh @@ -50,6 +50,9 @@ case "$common" in ;; esac +# We are going to make a new commit. +git var GIT_COMMITTER_IDENT >/dev/null || exit + # Find an optimum merge base if there are more than one candidates. LF=' ' diff --git a/git-revert.sh b/git-revert.sh index 2c5870684c..c19d3a6916 100755 --- a/git-revert.sh +++ b/git-revert.sh @@ -141,8 +141,9 @@ git-read-tree -m -u $base $head $next && result=$(git-write-tree 2>/dev/null) || { echo >&2 "Simple $me fails; trying Automatic $me." git-merge-index -o git-merge-one-file -a || { - echo >&2 "Automatic $me failed. After fixing it up," - echo >&2 "you can use \"git commit -F .msg\"" + echo >&2 "Automatic $me failed. After resolving the conflicts," + echo >&2 "mark the corrected paths with 'git-update-index <paths>'" + echo >&2 "and commit with 'git commit -F .msg'" case "$me" in cherry-pick) echo >&2 "You may choose to use the following when making" diff --git a/git-rm.sh b/git-rm.sh new file mode 100755 index 0000000000..fda4541c76 --- /dev/null +++ b/git-rm.sh @@ -0,0 +1,70 @@ +#!/bin/sh + +USAGE='[-f] [-n] [-v] [--] <file>...' +SUBDIRECTORY_OK='Yes' +. git-sh-setup + +remove_files= +show_only= +verbose= +while : ; do + case "$1" in + -f) + remove_files=true + ;; + -n) + show_only=true + ;; + -v) + verbose=--verbose + ;; + --) + shift; break + ;; + -*) + usage + ;; + *) + break + ;; + esac + shift +done + +# This is typo-proofing. If some paths match and some do not, we want +# to do nothing. +case "$#" in +0) ;; +*) + git-ls-files --error-unmatch -- "$@" >/dev/null || { + echo >&2 "Maybe you misspelled it?" + exit 1 + } + ;; +esac + +if test -f "$GIT_DIR/info/exclude" +then + git-ls-files -z \ + --exclude-from="$GIT_DIR/info/exclude" \ + --exclude-per-directory=.gitignore -- "$@" +else + git-ls-files -z \ + --exclude-per-directory=.gitignore -- "$@" +fi | +case "$show_only,$remove_files" in +true,*) + xargs -0 echo + ;; +*,true) + xargs -0 sh -c " + while [ \$# -gt 0 ]; do + file=\$1; shift + rm -- \"\$file\" && git-update-index --remove $verbose \"\$file\" + done + " inline + ;; +*) + git-update-index --force-remove $verbose -z --stdin + ;; +esac diff --git a/git-send-email.perl b/git-send-email.perl index 13b85dddd1..b0d095b4e9 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -59,24 +59,29 @@ my $rc = GetOptions("from=s" => \$from, # Now, let's fill any that aren't set in with defaults: -open(GITVAR,"-|","git-var","-l") - or die "Failed to open pipe from git-var: $!"; - -my ($author,$committer); -while(<GITVAR>) { - chomp; - my ($var,$data) = split /=/,$_,2; - my @fields = split /\s+/, $data; - - my $ident = join(" ", @fields[0...(@fields-3)]); +sub gitvar { + my ($var) = @_; + my $fh; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-var', $var) or die "$!"; + } + my ($val) = <$fh>; + close $fh or die "$!"; + chomp($val); + return $val; +} - if ($var eq 'GIT_AUTHOR_IDENT') { - $author = $ident; - } elsif ($var eq 'GIT_COMMITTER_IDENT') { - $committer = $ident; - } +sub gitvar_ident { + my ($name) = @_; + my $val = gitvar($name); + my @field = split(/\s+/, $val); + return join(' ', @field[0...(@field-3)]); } -close(GITVAR); + +my ($author) = gitvar_ident('GIT_AUTHOR_IDENT'); +my ($committer) = gitvar_ident('GIT_COMMITTER_IDENT'); my $prompting = 0; if (!defined $from) { diff --git a/git-svnimport.perl b/git-svnimport.perl index c536d7026d..ee2940f480 100755 --- a/git-svnimport.perl +++ b/git-svnimport.perl @@ -10,7 +10,6 @@ # The head revision is on branch "origin" by default. # You can change that with the '-o' option. -require 5.008; # for shell-safe open("-|",LIST) use strict; use warnings; use Getopt::Std; @@ -322,8 +321,12 @@ sub get_file($$$) { return undef unless defined $name; } - open my $F, '-|', "git-hash-object", "-w", $name + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $name) or die "Cannot create object: $!\n"; + } my $sha = <$F>; chomp $sha; close $F; @@ -398,7 +401,12 @@ sub copy_path($$$$$$$$) { $srcpath =~ s#/*$#/#; } - open my $f,"-|","git-ls-tree","-r","-z",$gitrev,$srcpath; + my $pid = open my $f,'-|'; + die $! unless defined $pid; + if (!$pid) { + exec("git-ls-tree","-r","-z",$gitrev,$srcpath) + or die $!; + } local $/ = "\0"; while(<$f>) { chomp; @@ -554,7 +562,11 @@ sub commit { @o1 = @old; @old = (); } - open my $F, "-|", "git-ls-files", "-z", @o1 or die $!; + my $pid = open my $F, "-|"; + die "$!" unless defined $pid; + if (!$pid) { + exec("git-ls-files", "-z", @o1) or die $!; + } @o1 = (); local $/ = "\0"; while(<$F>) { @@ -1936,7 +1936,7 @@ proc findfiles {} { global selectedline numcommits lineid ctext global ffileline finddidsel parents nparents global findinprogress findstartline findinsertpos - global treediffs fdiffids fdiffsneeded fdiffpos + global treediffs fdiffid fdiffsneeded fdiffpos global findmergefiles if {$numcommits == 0} return @@ -1953,11 +1953,9 @@ proc findfiles {} { while 1 { set id $lineid($l) if {$findmergefiles || $nparents($id) == 1} { - foreach p $parents($id) { - if {![info exists treediffs([list $id $p])]} { - append diffsneeded "$id $p\n" - lappend fdiffsneeded [list $id $p] - } + if {![info exists treediffs($id)]} { + append diffsneeded "$id\n" + lappend fdiffsneeded $id } } if {[incr l] >= $numcommits} { @@ -1974,7 +1972,7 @@ proc findfiles {} { error_popup "Error starting search process: $err" return } - catch {unset fdiffids} + catch {unset fdiffid} set fdiffpos 0 fconfigure $df -blocking 0 fileevent $df readable [list readfilediffs $df] @@ -1983,16 +1981,15 @@ proc findfiles {} { set finddidsel 0 set findinsertpos end set id $lineid($l) - set p [lindex $parents($id) 0] . config -cursor watch settextcursor watch set findinprogress 1 - findcont [list $id $p] + findcont $id update } proc readfilediffs {df} { - global findids fdiffids fdiffs + global findid fdiffid fdiffs set n [gets $df line] if {$n < 0} { @@ -2002,19 +1999,19 @@ proc readfilediffs {df} { stopfindproc bell error_popup "Error in git-diff-tree: $err" - } elseif {[info exists findids]} { - set ids $findids + } elseif {[info exists findid]} { + set id $findid stopfindproc bell - error_popup "Couldn't find diffs for {$ids}" + error_popup "Couldn't find diffs for $id" } } return } - if {[regexp {^([0-9a-f]{40}) \(from ([0-9a-f]{40})\)} $line match id p]} { + if {[regexp {^([0-9a-f]{40})$} $line match id]} { # start of a new string of diffs donefilediff - set fdiffids [list $id $p] + set fdiffid $id set fdiffs {} } elseif {[string match ":*" $line]} { lappend fdiffs [lindex $line 5] @@ -2022,53 +2019,50 @@ proc readfilediffs {df} { } proc donefilediff {} { - global fdiffids fdiffs treediffs findids + global fdiffid fdiffs treediffs findid global fdiffsneeded fdiffpos - if {[info exists fdiffids]} { - while {[lindex $fdiffsneeded $fdiffpos] ne $fdiffids + if {[info exists fdiffid]} { + while {[lindex $fdiffsneeded $fdiffpos] ne $fdiffid && $fdiffpos < [llength $fdiffsneeded]} { # git-diff-tree doesn't output anything for a commit # which doesn't change anything - set nullids [lindex $fdiffsneeded $fdiffpos] - set treediffs($nullids) {} - if {[info exists findids] && $nullids eq $findids} { - unset findids - findcont $nullids + set nullid [lindex $fdiffsneeded $fdiffpos] + set treediffs($nullid) {} + if {[info exists findid] && $nullid eq $findid} { + unset findid + findcont $nullid } incr fdiffpos } incr fdiffpos - if {![info exists treediffs($fdiffids)]} { - set treediffs($fdiffids) $fdiffs + if {![info exists treediffs($fdiffid)]} { + set treediffs($fdiffid) $fdiffs } - if {[info exists findids] && $fdiffids eq $findids} { - unset findids - findcont $fdiffids + if {[info exists findid] && $fdiffid eq $findid} { + unset findid + findcont $fdiffid } } } -proc findcont {ids} { - global findids treediffs parents nparents +proc findcont {id} { + global findid treediffs parents nparents global ffileline findstartline finddidsel global lineid numcommits matchinglines findinprogress global findmergefiles - set id [lindex $ids 0] - set p [lindex $ids 1] - set pi [lsearch -exact $parents($id) $p] set l $ffileline while 1 { if {$findmergefiles || $nparents($id) == 1} { - if {![info exists treediffs($ids)]} { - set findids $ids + if {![info exists treediffs($id)]} { + set findid $id set ffileline $l return } set doesmatch 0 - foreach f $treediffs($ids) { + foreach f $treediffs($id) { set x [findmatches $f] if {$x != {}} { set doesmatch 1 @@ -2077,21 +2071,13 @@ proc findcont {ids} { } if {$doesmatch} { insertmatch $l $id - set pi $nparents($id) } - } else { - set pi $nparents($id) } - if {[incr pi] >= $nparents($id)} { - set pi 0 - if {[incr l] >= $numcommits} { - set l 0 - } - if {$l == $findstartline} break - set id $lineid($l) + if {[incr l] >= $numcommits} { + set l 0 } - set p [lindex $parents($id) $pi] - set ids [list $id $p] + if {$l == $findstartline} break + set id $lineid($l) } stopfindproc if {!$finddidsel} { diff --git a/http-fetch.c b/http-fetch.c index ce3df5f35c..8fd9de081f 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -130,7 +130,7 @@ static void start_object_request(struct object_request *obj_req) if (obj_req->local < 0) { obj_req->state = ABORTED; - error("Couldn't create temporary file %s for %s: %s\n", + error("Couldn't create temporary file %s for %s: %s", obj_req->tmpfile, obj_req->filename, strerror(errno)); return; } @@ -830,9 +830,9 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) obj_req->errorstr, obj_req->curl_result, obj_req->http_code, hex); } else if (obj_req->zret != Z_STREAM_END) { - ret = error("File %s (%s) corrupt\n", hex, obj_req->url); + ret = error("File %s (%s) corrupt", hex, obj_req->url); } else if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) { - ret = error("File %s has bad hash\n", hex); + ret = error("File %s has bad hash", hex); } else if (obj_req->rename < 0) { ret = error("unable to write sha1 filename %s", obj_req->filename); @@ -854,7 +854,7 @@ int fetch(unsigned char *sha1) fetch_alternates(alt->base); altbase = altbase->next; } - return error("Unable to find %s under %s\n", sha1_to_hex(sha1), + return error("Unable to find %s under %s", sha1_to_hex(sha1), alt->base); } @@ -156,8 +156,18 @@ static int copy(char *buf, int size, int offset, const char *src) return offset; } +static const char au_env[] = "GIT_AUTHOR_NAME"; +static const char co_env[] = "GIT_COMMITTER_NAME"; +static const char *env_hint = +"\n*** Environment problem:\n" +"*** Your name cannot be determined from your system services (gecos).\n" +"*** You would need to set %s and %s\n" +"*** environment variables; otherwise you won't be able to perform\n" +"*** certain operations because of \"empty ident\" errors.\n" +"*** Alternatively, you can use user.name configuration variable.\n\n"; + static const char *get_ident(const char *name, const char *email, - const char *date_str) + const char *date_str, int error_on_no_name) { static char buffer[1000]; char date[50]; @@ -168,9 +178,14 @@ static const char *get_ident(const char *name, const char *email, if (!email) email = git_default_email; - if (!*name || !*email) - die("empty ident %s <%s> not allowed", - name, email); + if (!*name) { + if (name == git_default_name && env_hint) { + fprintf(stderr, env_hint, au_env, co_env); + env_hint = NULL; /* warn only once, for "git-var -l" */ + } + if (error_on_no_name) + die("empty ident %s <%s> not allowed", name, email); + } strcpy(date, git_default_date); if (date_str) @@ -187,16 +202,18 @@ static const char *get_ident(const char *name, const char *email, return buffer; } -const char *git_author_info(void) +const char *git_author_info(int error_on_no_name) { return get_ident(getenv("GIT_AUTHOR_NAME"), getenv("GIT_AUTHOR_EMAIL"), - getenv("GIT_AUTHOR_DATE")); + getenv("GIT_AUTHOR_DATE"), + error_on_no_name); } -const char *git_committer_info(void) +const char *git_committer_info(int error_on_no_name) { return get_ident(getenv("GIT_COMMITTER_NAME"), getenv("GIT_COMMITTER_EMAIL"), - getenv("GIT_COMMITTER_DATE")); + getenv("GIT_COMMITTER_DATE"), + error_on_no_name); } diff --git a/ls-files.c b/ls-files.c index df93cf2263..df25c8c012 100644 --- a/ls-files.c +++ b/ls-files.c @@ -20,6 +20,7 @@ static int show_unmerged = 0; static int show_modified = 0; static int show_killed = 0; static int show_other_directories = 0; +static int show_valid_bit = 0; static int line_terminator = '\n'; static int prefix_len = 0, prefix_offset = 0; @@ -278,8 +279,11 @@ static void read_directory(const char *path, const char *base, int baselen) continue; len = strlen(de->d_name); memcpy(fullname + baselen, de->d_name, len+1); - if (excluded(fullname) != show_ignored) - continue; + if (excluded(fullname) != show_ignored) { + if (!show_ignored || DTYPE(de) != DT_DIR) { + continue; + } + } switch (DTYPE(de)) { struct stat st; @@ -457,6 +461,23 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) if (pathspec && !match(pathspec, ps_matched, ce->name, len)) return; + if (tag && *tag && show_valid_bit && + (ce->ce_flags & htons(CE_VALID))) { + static char alttag[4]; + memcpy(alttag, tag, 3); + if (isalpha(tag[0])) + alttag[0] = tolower(tag[0]); + else if (tag[0] == '?') + alttag[0] = '!'; + else { + alttag[0] = 'v'; + alttag[1] = tag[0]; + alttag[2] = ' '; + alttag[3] = 0; + } + tag = alttag; + } + if (!show_stage) { fputs(tag, stdout); write_name_quoted("", 0, ce->name + offset, @@ -533,7 +554,7 @@ static void show_files(void) err = lstat(ce->name, &st); if (show_deleted && err) show_ce_entry(tag_removed, ce); - if (show_modified && ce_modified(ce, &st)) + if (show_modified && ce_modified(ce, &st, 0)) show_ce_entry(tag_modified, ce); } } @@ -606,7 +627,7 @@ static void verify_pathspec(void) } static const char ls_files_usage[] = - "git-ls-files [-z] [-t] (--[cached|deleted|others|stage|unmerged|killed|modified])* " + "git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* " "[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] " "[ --exclude-per-directory=<filename> ] [--full-name] [--] [<file>]*"; @@ -631,13 +652,15 @@ int main(int argc, const char **argv) line_terminator = 0; continue; } - if (!strcmp(arg, "-t")) { + if (!strcmp(arg, "-t") || !strcmp(arg, "-v")) { tag_cached = "H "; tag_unmerged = "M "; tag_removed = "R "; tag_modified = "C "; tag_other = "? "; tag_killed = "K "; + if (arg[1] == 'v') + show_valid_bit = 1; continue; } if (!strcmp(arg, "-c") || !strcmp(arg, "--cached")) { @@ -758,6 +781,7 @@ int main(int argc, const char **argv) continue; error("pathspec '%s' did not match any.", pathspec[num] + prefix_offset); + errors++; } return errors ? 1 : 0; } diff --git a/merge-tree.c b/merge-tree.c new file mode 100644 index 0000000000..768d83a7c2 --- /dev/null +++ b/merge-tree.c @@ -0,0 +1,272 @@ +#include "cache.h" +#include "diff.h" + +static const char merge_tree_usage[] = "git-merge-tree <base-tree> <branch1> <branch2>"; +static int resolve_directories = 1; + +static void merge_trees(struct tree_desc t[3], const char *base); + +static void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1) +{ + unsigned long size = 0; + void *buf = NULL; + + if (sha1) { + buf = read_object_with_reference(sha1, "tree", &size, NULL); + if (!buf) + die("unable to read tree %s", sha1_to_hex(sha1)); + } + desc->size = size; + desc->buf = buf; + return buf; +} + +struct name_entry { + const unsigned char *sha1; + const char *path; + unsigned int mode; + int pathlen; +}; + +static void entry_clear(struct name_entry *a) +{ + memset(a, 0, sizeof(*a)); +} + +static int entry_compare(struct name_entry *a, struct name_entry *b) +{ + return base_name_compare( + a->path, a->pathlen, a->mode, + b->path, b->pathlen, b->mode); +} + +static void entry_extract(struct tree_desc *t, struct name_entry *a) +{ + a->sha1 = tree_entry_extract(t, &a->path, &a->mode); + a->pathlen = strlen(a->path); +} + +/* An empty entry never compares same, not even to another empty entry */ +static int same_entry(struct name_entry *a, struct name_entry *b) +{ + return a->sha1 && + b->sha1 && + !memcmp(a->sha1, b->sha1, 20) && + a->mode == b->mode; +} + +static const char *sha1_to_hex_zero(const unsigned char *sha1) +{ + if (sha1) + return sha1_to_hex(sha1); + return "0000000000000000000000000000000000000000"; +} + +static void resolve(const char *base, struct name_entry *branch1, struct name_entry *result) +{ + char branch1_sha1[50]; + + /* If it's already branch1, don't bother showing it */ + if (!branch1) + return; + memcpy(branch1_sha1, sha1_to_hex_zero(branch1->sha1), 41); + + printf("0 %06o->%06o %s->%s %s%s\n", + branch1->mode, result->mode, + branch1_sha1, sha1_to_hex_zero(result->sha1), + base, result->path); +} + +static int unresolved_directory(const char *base, struct name_entry n[3]) +{ + int baselen; + char *newbase; + struct name_entry *p; + struct tree_desc t[3]; + void *buf0, *buf1, *buf2; + + if (!resolve_directories) + return 0; + p = n; + if (!p->mode) { + p++; + if (!p->mode) + p++; + } + if (!S_ISDIR(p->mode)) + return 0; + baselen = strlen(base); + newbase = xmalloc(baselen + p->pathlen + 2); + memcpy(newbase, base, baselen); + memcpy(newbase + baselen, p->path, p->pathlen); + memcpy(newbase + baselen + p->pathlen, "/", 2); + + buf0 = fill_tree_descriptor(t+0, n[0].sha1); + buf1 = fill_tree_descriptor(t+1, n[1].sha1); + buf2 = fill_tree_descriptor(t+2, n[2].sha1); + merge_trees(t, newbase); + + free(buf0); + free(buf1); + free(buf2); + free(newbase); + return 1; +} + +static void unresolved(const char *base, struct name_entry n[3]) +{ + if (unresolved_directory(base, n)) + return; + if (n[0].sha1) + printf("1 %06o %s %s%s\n", n[0].mode, sha1_to_hex(n[0].sha1), base, n[0].path); + if (n[1].sha1) + printf("2 %06o %s %s%s\n", n[1].mode, sha1_to_hex(n[1].sha1), base, n[1].path); + if (n[2].sha1) + printf("3 %06o %s %s%s\n", n[2].mode, sha1_to_hex(n[2].sha1), base, n[2].path); +} + +typedef void (*traverse_callback_t)(int n, unsigned long mask, struct name_entry *entry, const char *base); + +static void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback) +{ + struct name_entry *entry = xmalloc(n*sizeof(*entry)); + + for (;;) { + struct name_entry entry[3]; + unsigned long mask = 0; + int i, last; + + last = -1; + for (i = 0; i < n; i++) { + if (!t[i].size) + continue; + entry_extract(t+i, entry+i); + if (last >= 0) { + int cmp = entry_compare(entry+i, entry+last); + + /* + * Is the new name bigger than the old one? + * Ignore it + */ + if (cmp > 0) + continue; + /* + * Is the new name smaller than the old one? + * Ignore all old ones + */ + if (cmp < 0) + mask = 0; + } + mask |= 1ul << i; + last = i; + } + if (!mask) + break; + + /* + * Update the tree entries we've walked, and clear + * all the unused name-entries. + */ + for (i = 0; i < n; i++) { + if (mask & (1ul << i)) { + update_tree_entry(t+i); + continue; + } + entry_clear(entry + i); + } + callback(n, mask, entry, base); + } + free(entry); +} + +/* + * Merge two trees together (t[1] and t[2]), using a common base (t[0]) + * as the origin. + * + * This walks the (sorted) trees in lock-step, checking every possible + * name. Note that directories automatically sort differently from other + * files (see "base_name_compare"), so you'll never see file/directory + * conflicts, because they won't ever compare the same. + * + * IOW, if a directory changes to a filename, it will automatically be + * seen as the directory going away, and the filename being created. + * + * Think of this as a three-way diff. + * + * The output will be either: + * - successful merge + * "0 mode sha1 filename" + * NOTE NOTE NOTE! FIXME! We really really need to walk the index + * in parallel with this too! + * + * - conflict: + * "1 mode sha1 filename" + * "2 mode sha1 filename" + * "3 mode sha1 filename" + * where not all of the 1/2/3 lines may exist, of course. + * + * The successful merge rules are the same as for the three-way merge + * in git-read-tree. + */ +static void threeway_callback(int n, unsigned long mask, struct name_entry *entry, const char *base) +{ + /* Same in both? */ + if (same_entry(entry+1, entry+2)) { + if (entry[0].sha1) { + resolve(base, NULL, entry+1); + return; + } + } + + if (same_entry(entry+0, entry+1)) { + if (entry[2].sha1 && !S_ISDIR(entry[2].mode)) { + resolve(base, entry+1, entry+2); + return; + } + } + + if (same_entry(entry+0, entry+2)) { + if (entry[1].sha1 && !S_ISDIR(entry[1].mode)) { + resolve(base, NULL, entry+1); + return; + } + } + + unresolved(base, entry); +} + +static void merge_trees(struct tree_desc t[3], const char *base) +{ + traverse_trees(3, t, base, threeway_callback); +} + +static void *get_tree_descriptor(struct tree_desc *desc, const char *rev) +{ + unsigned char sha1[20]; + void *buf; + + if (get_sha1(rev, sha1) < 0) + die("unknown rev %s", rev); + buf = fill_tree_descriptor(desc, sha1); + if (!buf) + die("%s is not a tree", rev); + return buf; +} + +int main(int argc, char **argv) +{ + struct tree_desc t[3]; + void *buf1, *buf2, *buf3; + + if (argc < 4) + usage(merge_tree_usage); + + buf1 = get_tree_descriptor(t+0, argv[1]); + buf2 = get_tree_descriptor(t+1, argv[2]); + buf3 = get_tree_descriptor(t+2, argv[3]); + merge_trees(t, ""); + free(buf1); + free(buf2); + free(buf3); + return 0; +} diff --git a/mktree.c b/mktree.c new file mode 100644 index 0000000000..f85358522b --- /dev/null +++ b/mktree.c @@ -0,0 +1,137 @@ +/* + * GIT - the stupid content tracker + * + * Copyright (c) Junio C Hamano, 2006 + */ +#include "cache.h" +#include "strbuf.h" +#include "quote.h" + +static struct treeent { + unsigned mode; + unsigned char sha1[20]; + int len; + char name[FLEX_ARRAY]; +} **entries; +static int alloc, used; + +static void append_to_tree(unsigned mode, unsigned char *sha1, char *path) +{ + struct treeent *ent; + int len = strlen(path); + if (strchr(path, '/')) + die("path %s contains slash", path); + + if (alloc <= used) { + alloc = alloc_nr(used); + entries = xrealloc(entries, sizeof(*entries) * alloc); + } + ent = entries[used++] = xmalloc(sizeof(**entries) + len + 1); + ent->mode = mode; + ent->len = len; + memcpy(ent->sha1, sha1, 20); + memcpy(ent->name, path, len+1); +} + +static int ent_compare(const void *a_, const void *b_) +{ + struct treeent *a = *(struct treeent **)a_; + struct treeent *b = *(struct treeent **)b_; + return base_name_compare(a->name, a->len, a->mode, + b->name, b->len, b->mode); +} + +static void write_tree(unsigned char *sha1) +{ + char *buffer; + unsigned long size, offset; + int i; + + qsort(entries, used, sizeof(*entries), ent_compare); + size = 100; + for (size = i = 0; i < used; i++) + size += 32 + entries[i]->len; + buffer = xmalloc(size); + offset = 0; + + for (i = 0; i < used; i++) { + struct treeent *ent = entries[i]; + + if (offset + ent->len + 100 < size) { + size = alloc_nr(offset + ent->len + 100); + buffer = xrealloc(buffer, size); + } + offset += sprintf(buffer + offset, "%o ", ent->mode); + offset += sprintf(buffer + offset, "%s", ent->name); + buffer[offset++] = 0; + memcpy(buffer + offset, ent->sha1, 20); + offset += 20; + } + write_sha1_file(buffer, offset, "tree", sha1); +} + +static const char mktree_usage[] = "mktree [-z]"; + +int main(int ac, char **av) +{ + struct strbuf sb; + unsigned char sha1[20]; + int line_termination = '\n'; + + setup_git_directory(); + + while ((1 < ac) && av[1][0] == '-') { + char *arg = av[1]; + if (!strcmp("-z", arg)) + line_termination = 0; + else + usage(mktree_usage); + ac--; + av++; + } + + strbuf_init(&sb); + while (1) { + int len; + char *ptr, *ntr; + unsigned mode; + char type[20]; + char *path; + + read_line(&sb, stdin, line_termination); + if (sb.eof) + break; + len = sb.len; + ptr = sb.buf; + /* Input is non-recursive ls-tree output format + * mode SP type SP sha1 TAB name + */ + mode = strtoul(ptr, &ntr, 8); + if (ptr == ntr || !ntr || *ntr != ' ') + die("input format error: %s", sb.buf); + ptr = ntr + 1; /* type */ + ntr = strchr(ptr, ' '); + if (!ntr || sb.buf + len <= ntr + 41 || + ntr[41] != '\t' || + get_sha1_hex(ntr + 1, sha1)) + die("input format error: %s", sb.buf); + if (sha1_object_info(sha1, type, NULL)) + die("object %s unavailable", sha1_to_hex(sha1)); + *ntr++ = 0; /* now at the beginning of SHA1 */ + if (strcmp(ptr, type)) + die("object type %s mismatch (%s)", ptr, type); + ntr += 41; /* at the beginning of name */ + if (line_termination && ntr[0] == '"') + path = unquote_c_style(ntr, NULL); + else + path = ntr; + + append_to_tree(mode, sha1, path); + + if (path != ntr) + free(path); + } + write_tree(sha1); + puts(sha1_to_hex(sha1)); + exit(0); +} diff --git a/pack-objects.c b/pack-objects.c index c5a5e61605..be7a2008c5 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -3,31 +3,196 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "diff.h" #include <sys/time.h> +#include <signal.h> -static const char pack_usage[] = "git-pack-objects [-q] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; +static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; struct object_entry { unsigned char sha1[20]; - unsigned long size; - unsigned long offset; - unsigned int depth; - unsigned int hash; + unsigned long size; /* uncompressed size */ + unsigned long offset; /* offset into the final pack file; + * nonzero if already written. + */ + unsigned int depth; /* delta depth */ + unsigned int delta_limit; /* base adjustment for in-pack delta */ + unsigned int hash; /* name hint hash */ enum object_type type; - unsigned long delta_size; - struct object_entry *delta; + enum object_type in_pack_type; /* could be delta */ + unsigned long delta_size; /* delta data size (uncompressed) */ + struct object_entry *delta; /* delta base object */ + struct packed_git *in_pack; /* already in pack */ + unsigned int in_pack_offset; + struct object_entry *delta_child; /* delitified objects who bases me */ + struct object_entry *delta_sibling; /* other deltified objects who + * uses the same base as me + */ + int preferred_base; /* we do not pack this, but is encouraged to + * be used as the base objectto delta huge + * objects against. + */ + int based_on_preferred; /* current delta candidate is a preferred + * one, or delta against a preferred one. + */ }; +/* + * Objects we are going to pack are colected in objects array (dynamically + * expanded). nr_objects & nr_alloc controls this array. They are stored + * in the order we see -- typically rev-list --objects order that gives us + * nice "minimum seek" order. + * + * sorted-by-sha ans sorted-by-type are arrays of pointers that point at + * elements in the objects array. The former is used to build the pack + * index (lists object names in the ascending order to help offset lookup), + * and the latter is used to group similar things together by try_delta() + * heuristics. + */ + static unsigned char object_list_sha1[20]; static int non_empty = 0; +static int no_reuse_delta = 0; static int local = 0; static int incremental = 0; static struct object_entry **sorted_by_sha, **sorted_by_type; static struct object_entry *objects = NULL; -static int nr_objects = 0, nr_alloc = 0; +static int nr_objects = 0, nr_alloc = 0, nr_result = 0; static const char *base_name; static unsigned char pack_file_sha1[20]; static int progress = 1; +static volatile int progress_update = 0; + +/* + * The object names in objects array are hashed with this hashtable, + * to help looking up the entry by object name. Binary search from + * sorted_by_sha is also possible but this was easier to code and faster. + * This hashtable is built after all the objects are seen. + */ +static int *object_ix = NULL; +static int object_ix_hashsz = 0; + +/* + * Pack index for existing packs give us easy access to the offsets into + * corresponding pack file where each object's data starts, but the entries + * do not store the size of the compressed representation (uncompressed + * size is easily available by examining the pack entry header). We build + * a hashtable of existing packs (pack_revindex), and keep reverse index + * here -- pack index file is sorted by object name mapping to offset; this + * pack_revindex[].revindex array is an ordered list of offsets, so if you + * know the offset of an object, next offset is where its packed + * representation ends. + */ +struct pack_revindex { + struct packed_git *p; + unsigned long *revindex; +} *pack_revindex = NULL; +static int pack_revindex_hashsz = 0; + +/* + * stats + */ +static int written = 0; +static int written_delta = 0; +static int reused = 0; +static int reused_delta = 0; + +static int pack_revindex_ix(struct packed_git *p) +{ + unsigned int ui = (unsigned int) p; + int i; + + ui = ui ^ (ui >> 16); /* defeat structure alignment */ + i = (int)(ui % pack_revindex_hashsz); + while (pack_revindex[i].p) { + if (pack_revindex[i].p == p) + return i; + if (++i == pack_revindex_hashsz) + i = 0; + } + return -1 - i; +} + +static void prepare_pack_ix(void) +{ + int num; + struct packed_git *p; + for (num = 0, p = packed_git; p; p = p->next) + num++; + if (!num) + return; + pack_revindex_hashsz = num * 11; + pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz); + for (p = packed_git; p; p = p->next) { + num = pack_revindex_ix(p); + num = - 1 - num; + pack_revindex[num].p = p; + } + /* revindex elements are lazily initialized */ +} + +static int cmp_offset(const void *a_, const void *b_) +{ + unsigned long a = *(unsigned long *) a_; + unsigned long b = *(unsigned long *) b_; + if (a < b) + return -1; + else if (a == b) + return 0; + else + return 1; +} + +/* + * Ordered list of offsets of objects in the pack. + */ +static void prepare_pack_revindex(struct pack_revindex *rix) +{ + struct packed_git *p = rix->p; + int num_ent = num_packed_objects(p); + int i; + void *index = p->index_base + 256; + + rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); + for (i = 0; i < num_ent; i++) { + long hl = *((long *)(index + 24 * i)); + rix->revindex[i] = ntohl(hl); + } + /* This knows the pack format -- the 20-byte trailer + * follows immediately after the last object data. + */ + rix->revindex[num_ent] = p->pack_size - 20; + qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); +} + +static unsigned long find_packed_object_size(struct packed_git *p, + unsigned long ofs) +{ + int num; + int lo, hi; + struct pack_revindex *rix; + unsigned long *revindex; + num = pack_revindex_ix(p); + if (num < 0) + die("internal error: pack revindex uninitialized"); + rix = &pack_revindex[num]; + if (!rix->revindex) + prepare_pack_revindex(rix); + revindex = rix->revindex; + lo = 0; + hi = num_packed_objects(p) + 1; + do { + int mi = (lo + hi) / 2; + if (revindex[mi] == ofs) { + return revindex[mi+1] - ofs; + } + else if (ofs < revindex[mi]) + hi = mi; + else + lo = mi + 1; + } while (lo < hi); + die("internal error: pack revindex corrupt"); +} static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) { @@ -74,39 +239,77 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha return n; } -static unsigned long write_object(struct sha1file *f, struct object_entry *entry) +static unsigned long write_object(struct sha1file *f, + struct object_entry *entry) { unsigned long size; char type[10]; - void *buf = read_sha1_file(entry->sha1, type, &size); + void *buf; unsigned char header[10]; unsigned hdrlen, datalen; enum object_type obj_type; + int to_reuse = 0; - if (!buf) - die("unable to read %s", sha1_to_hex(entry->sha1)); - if (size != entry->size) - die("object %s size inconsistency (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); + if (entry->preferred_base) + return 0; - /* - * The object header is a byte of 'type' followed by zero or - * more bytes of length. For deltas, the 20 bytes of delta sha1 - * follows that. - */ obj_type = entry->type; - if (entry->delta) { - buf = delta_against(buf, size, entry); - size = entry->delta_size; - obj_type = OBJ_DELTA; - } - hdrlen = encode_header(obj_type, size, header); - sha1write(f, header, hdrlen); - if (entry->delta) { - sha1write(f, entry->delta, 20); - hdrlen += 20; - } - datalen = sha1write_compressed(f, buf, size); - free(buf); + if (! entry->in_pack) + to_reuse = 0; /* can't reuse what we don't have */ + else if (obj_type == OBJ_DELTA) + to_reuse = 1; /* check_object() decided it for us */ + else if (obj_type != entry->in_pack_type) + to_reuse = 0; /* pack has delta which is unusable */ + else if (entry->delta) + to_reuse = 0; /* we want to pack afresh */ + else + to_reuse = 1; /* we have it in-pack undeltified, + * and we do not need to deltify it. + */ + + if (! to_reuse) { + buf = read_sha1_file(entry->sha1, type, &size); + if (!buf) + die("unable to read %s", sha1_to_hex(entry->sha1)); + if (size != entry->size) + die("object %s size inconsistency (%lu vs %lu)", + sha1_to_hex(entry->sha1), size, entry->size); + if (entry->delta) { + buf = delta_against(buf, size, entry); + size = entry->delta_size; + obj_type = OBJ_DELTA; + } + /* + * The object header is a byte of 'type' followed by zero or + * more bytes of length. For deltas, the 20 bytes of delta + * sha1 follows that. + */ + hdrlen = encode_header(obj_type, size, header); + sha1write(f, header, hdrlen); + + if (entry->delta) { + sha1write(f, entry->delta, 20); + hdrlen += 20; + } + datalen = sha1write_compressed(f, buf, size); + free(buf); + } + else { + struct packed_git *p = entry->in_pack; + use_packed_git(p); + + datalen = find_packed_object_size(p, entry->in_pack_offset); + buf = p->pack_base + entry->in_pack_offset; + sha1write(f, buf, datalen); + unuse_packed_git(p); + hdrlen = 0; /* not really */ + if (obj_type == OBJ_DELTA) + reused_delta++; + reused++; + } + if (obj_type == OBJ_DELTA) + written_delta++; + written++; return hdrlen + datalen; } @@ -132,32 +335,52 @@ static void write_pack_file(void) int i; struct sha1file *f; unsigned long offset; - unsigned long mb; struct pack_header hdr; + unsigned last_percent = 999; + int do_progress = 0; if (!base_name) f = sha1fd(1, "<stdout>"); - else - f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack"); + else { + f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "pack"); + do_progress = progress; + } + if (do_progress) + fprintf(stderr, "Writing %d objects.\n", nr_result); + hdr.hdr_signature = htonl(PACK_SIGNATURE); hdr.hdr_version = htonl(PACK_VERSION); - hdr.hdr_entries = htonl(nr_objects); + hdr.hdr_entries = htonl(nr_result); sha1write(f, &hdr, sizeof(hdr)); offset = sizeof(hdr); - for (i = 0; i < nr_objects; i++) + if (!nr_result) + goto done; + for (i = 0; i < nr_objects; i++) { offset = write_one(f, objects + i, offset); - + if (do_progress) { + unsigned percent = written * 100 / nr_result; + if (progress_update || percent != last_percent) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, written, nr_result); + progress_update = 0; + last_percent = percent; + } + } + } + if (do_progress) + fputc('\n', stderr); + done: sha1close(f, pack_file_sha1, 1); - mb = offset >> 20; - offset &= 0xfffff; } static void write_index_file(void) { int i; - struct sha1file *f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "idx"); + struct sha1file *f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "idx"); struct object_entry **list = sorted_by_sha; - struct object_entry **last = list + nr_objects; + struct object_entry **last = list + nr_result; unsigned int array[256]; /* @@ -182,7 +405,7 @@ static void write_index_file(void) * Write the actual SHA1 entries.. */ list = sorted_by_sha; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < nr_result; i++) { struct object_entry *entry = *list++; unsigned int offset = htonl(entry->offset); sha1write(f, &offset, 4); @@ -192,25 +415,139 @@ static void write_index_file(void) sha1close(f, NULL, 1); } -static int add_object_entry(unsigned char *sha1, unsigned int hash) +static int locate_object_entry_hash(const unsigned char *sha1) +{ + int i; + unsigned int ui; + memcpy(&ui, sha1, sizeof(unsigned int)); + i = ui % object_ix_hashsz; + while (0 < object_ix[i]) { + if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) + return i; + if (++i == object_ix_hashsz) + i = 0; + } + return -1 - i; +} + +static struct object_entry *locate_object_entry(const unsigned char *sha1) +{ + int i; + + if (!object_ix_hashsz) + return NULL; + + i = locate_object_entry_hash(sha1); + if (0 <= i) + return &objects[object_ix[i]-1]; + return NULL; +} + +static void rehash_objects(void) +{ + int i; + struct object_entry *oe; + + object_ix_hashsz = nr_objects * 3; + if (object_ix_hashsz < 1024) + object_ix_hashsz = 1024; + object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); + object_ix = memset(object_ix, 0, sizeof(int) * object_ix_hashsz); + for (i = 0, oe = objects; i < nr_objects; i++, oe++) { + int ix = locate_object_entry_hash(oe->sha1); + if (0 <= ix) + continue; + ix = -1 - ix; + object_ix[ix] = i + 1; + } +} + +struct name_path { + struct name_path *up; + const char *elem; + int len; +}; + +#define DIRBITS 12 + +static unsigned name_hash(struct name_path *path, const char *name) +{ + struct name_path *p = path; + const char *n = name + strlen(name); + unsigned hash = 0, name_hash = 0, name_done = 0; + + if (n != name && n[-1] == '\n') + n--; + while (name <= --n) { + unsigned char c = *n; + if (c == '/' && !name_done) { + name_hash = hash; + name_done = 1; + hash = 0; + } + hash = hash * 11 + c; + } + if (!name_done) { + name_hash = hash; + hash = 0; + } + for (p = path; p; p = p->up) { + hash = hash * 11 + '/'; + n = p->elem + p->len; + while (p->elem <= --n) { + unsigned char c = *n; + hash = hash * 11 + c; + } + } + /* + * Make sure "Makefile" and "t/Makefile" are hashed separately + * but close enough. + */ + hash = (name_hash<<DIRBITS) | (hash & ((1U<<DIRBITS )-1)); + + if (0) { /* debug */ + n = name + strlen(name); + if (n != name && n[-1] == '\n') + n--; + while (name <= --n) + fputc(*n, stderr); + for (p = path; p; p = p->up) { + fputc('/', stderr); + n = p->elem + p->len; + while (p->elem <= --n) + fputc(*n, stderr); + } + fprintf(stderr, "\t%08x\n", hash); + } + return hash; +} + +static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude) { unsigned int idx = nr_objects; struct object_entry *entry; + struct packed_git *p; + unsigned int found_offset = 0; + struct packed_git *found_pack = NULL; + int ix, status = 0; - if (incremental || local) { - struct packed_git *p; - + if (!exclude) { for (p = packed_git; p; p = p->next) { struct pack_entry e; - if (find_pack_entry_one(sha1, &e, p)) { if (incremental) return 0; if (local && !p->pack_local) return 0; + if (!found_pack) { + found_offset = e.offset; + found_pack = e.p; + } } } } + if ((entry = locate_object_entry(sha1)) != NULL) + goto already_added; if (idx >= nr_alloc) { unsigned int needed = (idx + 1024) * 3 / 2; @@ -218,42 +555,189 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash) nr_alloc = needed; } entry = objects + idx; + nr_objects = idx + 1; memset(entry, 0, sizeof(*entry)); memcpy(entry->sha1, sha1, 20); entry->hash = hash; - nr_objects = idx+1; - return 1; + + if (object_ix_hashsz * 3 <= nr_objects * 4) + rehash_objects(); + else { + ix = locate_object_entry_hash(entry->sha1); + if (0 <= ix) + die("internal error in object hashing."); + object_ix[-1 - ix] = idx + 1; + } + status = 1; + + already_added: + if (progress_update) { + fprintf(stderr, "Counting objects...%d\r", nr_objects); + progress_update = 0; + } + if (exclude) + entry->preferred_base = 1; + else { + if (found_pack) { + entry->in_pack = found_pack; + entry->in_pack_offset = found_offset; + } + } + return status; +} + +static void add_pbase_tree(struct tree_desc *tree, struct name_path *up) +{ + while (tree->size) { + const unsigned char *sha1; + const char *name; + unsigned mode, hash; + unsigned long size; + char type[20]; + + sha1 = tree_entry_extract(tree, &name, &mode); + update_tree_entry(tree); + if (!has_sha1_file(sha1)) + continue; + if (sha1_object_info(sha1, type, &size)) + continue; + + hash = name_hash(up, name); + if (!add_object_entry(sha1, hash, 1)) + continue; + + if (!strcmp(type, "tree")) { + struct tree_desc sub; + void *elem; + struct name_path me; + + elem = read_sha1_file(sha1, type, &sub.size); + sub.buf = elem; + if (sub.buf) { + me.up = up; + me.elem = name; + me.len = strlen(name); + add_pbase_tree(&sub, &me); + free(elem); + } + } + } +} + +static void add_preferred_base(unsigned char *sha1) +{ + struct tree_desc tree; + void *elem; + + elem = read_object_with_reference(sha1, "tree", &tree.size, NULL); + tree.buf = elem; + if (!tree.buf) + return; + if (add_object_entry(sha1, name_hash(NULL, ""), 1)) + add_pbase_tree(&tree, NULL); + free(elem); } static void check_object(struct object_entry *entry) { char type[20]; - if (!sha1_object_info(entry->sha1, type, &entry->size)) { - if (!strcmp(type, "commit")) { - entry->type = OBJ_COMMIT; - } else if (!strcmp(type, "tree")) { - entry->type = OBJ_TREE; - } else if (!strcmp(type, "blob")) { - entry->type = OBJ_BLOB; - } else if (!strcmp(type, "tag")) { - entry->type = OBJ_TAG; - } else - die("unable to pack object %s of type %s", - sha1_to_hex(entry->sha1), type); + if (entry->in_pack && !entry->preferred_base) { + unsigned char base[20]; + unsigned long size; + struct object_entry *base_entry; + + /* We want in_pack_type even if we do not reuse delta. + * There is no point not reusing non-delta representations. + */ + check_reuse_pack_delta(entry->in_pack, + entry->in_pack_offset, + base, &size, + &entry->in_pack_type); + + /* Check if it is delta, and the base is also an object + * we are going to pack. If so we will reuse the existing + * delta. + */ + if (!no_reuse_delta && + entry->in_pack_type == OBJ_DELTA && + (base_entry = locate_object_entry(base)) && + (!base_entry->preferred_base)) { + + /* Depth value does not matter - find_deltas() + * will never consider reused delta as the + * base object to deltify other objects + * against, in order to avoid circular deltas. + */ + + /* uncompressed size of the delta data */ + entry->size = entry->delta_size = size; + entry->delta = base_entry; + entry->type = OBJ_DELTA; + + entry->delta_sibling = base_entry->delta_child; + base_entry->delta_child = entry; + + return; + } + /* Otherwise we would do the usual */ } - else + + if (sha1_object_info(entry->sha1, type, &entry->size)) die("unable to get type of object %s", sha1_to_hex(entry->sha1)); + + if (!strcmp(type, "commit")) { + entry->type = OBJ_COMMIT; + } else if (!strcmp(type, "tree")) { + entry->type = OBJ_TREE; + } else if (!strcmp(type, "blob")) { + entry->type = OBJ_BLOB; + } else if (!strcmp(type, "tag")) { + entry->type = OBJ_TAG; + } else + die("unable to pack object %s of type %s", + sha1_to_hex(entry->sha1), type); +} + +static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) +{ + struct object_entry *child = me->delta_child; + unsigned int m = n; + while (child) { + unsigned int c = check_delta_limit(child, n + 1); + if (m < c) + m = c; + child = child->delta_sibling; + } + return m; } static void get_object_details(void) { int i; - struct object_entry *entry = objects; + struct object_entry *entry; - for (i = 0; i < nr_objects; i++) - check_object(entry++); + prepare_pack_ix(); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + check_object(entry); + + if (nr_objects == nr_result) { + /* + * Depth of objects that depend on the entry -- this + * is subtracted from depth-max to break too deep + * delta chain because of delta data reusing. + * However, we loosen this restriction when we know we + * are creating a thin pack -- it will have to be + * expanded on the other end anyway, so do not + * artificially cut the delta chain and let it go as + * deep as it wants. + */ + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + if (!entry->delta && entry->delta_child) + entry->delta_limit = + check_delta_limit(entry, 1); + } } typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); @@ -284,6 +768,24 @@ static int sha1_sort(const struct object_entry *a, const struct object_entry *b) return memcmp(a->sha1, b->sha1, 20); } +static struct object_entry **create_final_object_list() +{ + struct object_entry **list; + int i, j; + + for (i = nr_result = 0; i < nr_objects; i++) + if (!objects[i].preferred_base) + nr_result++; + list = xmalloc(nr_result * sizeof(struct object_entry *)); + for (i = j = 0; i < nr_objects; i++) { + if (!objects[i].preferred_base) + list[j++] = objects + i; + } + current_sort = sha1_sort; + qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator); + return list; +} + static int type_size_sort(const struct object_entry *a, const struct object_entry *b) { if (a->type < b->type) @@ -294,6 +796,10 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr return -1; if (a->hash > b->hash) return 1; + if (a->preferred_base < b->preferred_base) + return -1; + if (a->preferred_base > b->preferred_base) + return 1; if (a->size < b->size) return -1; if (a->size > b->size) @@ -318,6 +824,8 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de { struct object_entry *cur_entry = cur->entry; struct object_entry *old_entry = old->entry; + int old_preferred = (old_entry->preferred_base || + old_entry->based_on_preferred); unsigned long size, oldsize, delta_size, sizediff; long max_size; void *delta_buf; @@ -326,12 +834,27 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de if (cur_entry->type != old_entry->type) return -1; - size = cur_entry->size; - if (size < 50) + /* We do not compute delta to *create* objects we are not + * going to pack. + */ + if (cur_entry->preferred_base) return -1; + + /* If the current object is at pack edge, take the depth the + * objects that depend on the current object into account -- + * otherwise they would become too deep. + */ + if (cur_entry->delta_child) { + if (max_depth <= cur_entry->delta_limit) + return 0; + max_depth -= cur_entry->delta_limit; + } + + size = cur_entry->size; oldsize = old_entry->size; sizediff = oldsize > size ? oldsize - size : size - oldsize; - if (sizediff > size / 8) + + if (size < 50) return -1; if (old_entry->depth >= max_depth) return 0; @@ -344,8 +867,27 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de * delete). */ max_size = size / 2 - 20; - if (cur_entry->delta) - max_size = cur_entry->delta_size-1; + if (cur_entry->delta) { + if (cur_entry->based_on_preferred) { + if (old_preferred) + max_size = cur_entry->delta_size-1; + else + /* trying with non-preferred one when we + * already have a delta based on preferred + * one is pointless. + */ + return -1; + } + else if (!old_preferred) + max_size = cur_entry->delta_size-1; + else + /* otherwise... even if delta with a + * preferred one produces a bigger result than + * what we currently have, which is based on a + * non-preferred one, it is OK. + */ + ; + } if (sizediff >= max_size) return -1; delta_buf = diff_delta(old->data, oldsize, @@ -355,21 +897,30 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de cur_entry->delta = old_entry; cur_entry->delta_size = delta_size; cur_entry->depth = old_entry->depth + 1; + cur_entry->based_on_preferred = old_preferred; free(delta_buf); return 0; } +static void progress_interval(int signum) +{ + signal(SIGALRM, progress_interval); + progress_update = 1; +} + static void find_deltas(struct object_entry **list, int window, int depth) { int i, idx; unsigned int array_size = window * sizeof(struct unpacked); struct unpacked *array = xmalloc(array_size); - int eye_candy; + unsigned processed = 0; + unsigned last_percent = 999; memset(array, 0, array_size); i = nr_objects; idx = 0; - eye_candy = i - (nr_objects / 20); + if (progress) + fprintf(stderr, "Deltifying %d objects.\n", nr_result); while (--i >= 0) { struct object_entry *entry = list[i]; @@ -378,15 +929,31 @@ static void find_deltas(struct object_entry **list, int window, int depth) char type[10]; int j; - if (progress && i <= eye_candy) { - eye_candy -= nr_objects / 20; - fputc('.', stderr); + if (!entry->preferred_base) + processed++; + + if (progress) { + unsigned percent = processed * 100 / nr_result; + if (percent != last_percent || progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, processed, nr_result); + progress_update = 0; + last_percent = percent; + } } + + if (entry->delta) + /* This happens if we decided to reuse existing + * delta from a pack. "!no_reuse_delta &&" is implied. + */ + continue; + free(n->data); n->entry = entry; n->data = read_sha1_file(entry->sha1, type, &size); if (size != entry->size) die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); + j = window; while (--j > 0) { unsigned int other_idx = idx + j; @@ -404,6 +971,9 @@ static void find_deltas(struct object_entry **list, int window, int depth) idx = 0; } + if (progress) + fputc('\n', stderr); + for (i = 0; i < window; ++i) free(array[i].data); free(array); @@ -412,15 +982,9 @@ static void find_deltas(struct object_entry **list, int window, int depth) static void prepare_pack(int window, int depth) { get_object_details(); - - if (progress) - fprintf(stderr, "Packing %d objects", nr_objects); sorted_by_type = create_sorted_list(type_size_sort); if (window && depth) find_deltas(sorted_by_type, window+1, depth); - if (progress) - fputc('\n', stderr); - write_pack_file(); } static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) @@ -443,8 +1007,9 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) } } - fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, - sha1_to_hex(sha1)); + if (progress) + fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, + sha1_to_hex(sha1)); if (pack_to_stdout) { if (copy_fd(ifd, 1)) @@ -483,10 +1048,6 @@ int main(int argc, char **argv) int window = 10, depth = 10, pack_to_stdout = 0; struct object_entry **list; int i; - struct timeval prev_tv; - int eye_candy = 0; - int eye_candy_incr = 500; - setup_git_directory(); @@ -524,6 +1085,10 @@ int main(int argc, char **argv) progress = 0; continue; } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } if (!strcmp("--stdout", arg)) { pack_to_stdout = 1; continue; @@ -539,65 +1104,67 @@ int main(int argc, char **argv) usage(pack_usage); prepare_packed_git(); + if (progress) { + struct itimerval v; + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + signal(SIGALRM, progress_interval); + setitimer(ITIMER_REAL, &v, NULL); fprintf(stderr, "Generating pack...\n"); - gettimeofday(&prev_tv, NULL); } + while (fgets(line, sizeof(line), stdin) != NULL) { - unsigned int hash; - char *p; unsigned char sha1[20]; - if (progress && (eye_candy <= nr_objects)) { - fprintf(stderr, "Counting objects...%d\r", nr_objects); - if (eye_candy && (50 <= eye_candy_incr)) { - struct timeval tv; - int time_diff; - gettimeofday(&tv, NULL); - time_diff = (tv.tv_sec - prev_tv.tv_sec); - time_diff <<= 10; - time_diff += (tv.tv_usec - prev_tv.tv_usec); - if ((1 << 9) < time_diff) - eye_candy_incr += 50; - else if (50 < eye_candy_incr) - eye_candy_incr -= 50; - } - eye_candy += eye_candy_incr; + if (line[0] == '-') { + if (get_sha1_hex(line+1, sha1)) + die("expected edge sha1, got garbage:\n %s", + line+1); + add_preferred_base(sha1); + continue; } if (get_sha1_hex(line, sha1)) die("expected sha1, got garbage:\n %s", line); - hash = 0; - p = line+40; - while (*p) { - unsigned char c = *p++; - if (isspace(c)) - continue; - hash = hash * 11 + c; - } - add_object_entry(sha1, hash); + add_object_entry(sha1, name_hash(NULL, line+41), 0); } if (progress) fprintf(stderr, "Done counting %d objects.\n", nr_objects); - if (non_empty && !nr_objects) + sorted_by_sha = create_final_object_list(); + if (non_empty && !nr_result) return 0; - sorted_by_sha = create_sorted_list(sha1_sort); SHA1_Init(&ctx); list = sorted_by_sha; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < nr_result; i++) { struct object_entry *entry = *list++; SHA1_Update(&ctx, entry->sha1, 20); } SHA1_Final(object_list_sha1, &ctx); + if (progress && (nr_objects != nr_result)) + fprintf(stderr, "Result has %d objects.\n", nr_result); if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) ; else { - prepare_pack(window, depth); + if (nr_result) + prepare_pack(window, depth); + if (progress && pack_to_stdout) { + /* the other end usually displays progress itself */ + struct itimerval v = {{0,},}; + setitimer(ITIMER_REAL, &v, NULL); + signal(SIGALRM, SIG_IGN ); + progress_update = 0; + } + write_pack_file(); if (!pack_to_stdout) { write_index_file(); puts(sha1_to_hex(object_list_sha1)); } } + if (progress) + fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", + nr_result, written, written_delta, reused, reused_delta); return 0; } @@ -29,5 +29,7 @@ struct pack_header { }; extern int verify_pack(struct packed_git *, int); - +extern int check_reuse_pack_delta(struct packed_git *, unsigned long, + unsigned char *, unsigned long *, + enum object_type *); #endif diff --git a/read-cache.c b/read-cache.c index c5474d4975..f97f92d90a 100644 --- a/read-cache.c +++ b/read-cache.c @@ -27,6 +27,9 @@ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) ce->ce_uid = htonl(st->st_uid); ce->ce_gid = htonl(st->st_gid); ce->ce_size = htonl(st->st_size); + + if (assume_unchanged) + ce->ce_flags |= htons(CE_VALID); } static int ce_compare_data(struct cache_entry *ce, struct stat *st) @@ -146,9 +149,18 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) return changed; } -int ce_match_stat(struct cache_entry *ce, struct stat *st) +int ce_match_stat(struct cache_entry *ce, struct stat *st, int ignore_valid) { - unsigned int changed = ce_match_stat_basic(ce, st); + unsigned int changed; + + /* + * If it's marked as always valid in the index, it's + * valid whatever the checked-out copy says. + */ + if (!ignore_valid && (ce->ce_flags & htons(CE_VALID))) + return 0; + + changed = ce_match_stat_basic(ce, st); /* * Within 1 second of this sequence: @@ -164,7 +176,7 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st) * effectively mean we can make at most one commit per second, * which is not acceptable. Instead, we check cache entries * whose mtime are the same as the index file timestamp more - * careful than others. + * carefully than others. */ if (!changed && index_file_timestamp && @@ -174,10 +186,10 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st) return changed; } -int ce_modified(struct cache_entry *ce, struct stat *st) +int ce_modified(struct cache_entry *ce, struct stat *st, int really) { int changed, changed_fs; - changed = ce_match_stat(ce, st); + changed = ce_match_stat(ce, st, really); if (!changed) return 0; /* @@ -233,6 +245,11 @@ int cache_name_compare(const char *name1, int flags1, const char *name2, int fla return -1; if (len1 > len2) return 1; + + /* Compare stages */ + flags1 &= CE_STAGEMASK; + flags2 &= CE_STAGEMASK; + if (flags1 < flags2) return -1; if (flags1 > flags2) @@ -430,6 +447,7 @@ int add_cache_entry(struct cache_entry *ce, int option) int ok_to_add = option & ADD_CACHE_OK_TO_ADD; int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE; int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK; + pos = cache_name_pos(ce->name, ntohs(ce->ce_flags)); /* existing match? Just replace it. */ diff --git a/read-tree.c b/read-tree.c index 5580f15ba2..f39fe5ca65 100644 --- a/read-tree.c +++ b/read-tree.c @@ -9,6 +9,8 @@ #include "object.h" #include "tree.h" +#include <sys/time.h> +#include <signal.h> static int merge = 0; static int update = 0; @@ -16,6 +18,8 @@ static int index_only = 0; static int nontrivial_merge = 0; static int trivial_merges_only = 0; static int aggressive = 0; +static int verbose_update = 0; +static volatile int progress_update = 0; static int head_idx = -1; static int merge_size = 0; @@ -267,6 +271,12 @@ static void unlink_entry(char *name) } } +static void progress_interval(int signum) +{ + signal(SIGALRM, progress_interval); + progress_update = 1; +} + static void check_updates(struct cache_entry **src, int nr) { static struct checkout state = { @@ -276,8 +286,49 @@ static void check_updates(struct cache_entry **src, int nr) .refresh_cache = 1, }; unsigned short mask = htons(CE_UPDATE); + unsigned last_percent = 200, cnt = 0, total = 0; + + if (update && verbose_update) { + struct itimerval v; + + for (total = cnt = 0; cnt < nr; cnt++) { + struct cache_entry *ce = src[cnt]; + if (!ce->ce_mode || ce->ce_flags & mask) + total++; + } + + /* Don't bother doing this for very small updates */ + if (total < 250) + total = 0; + + if (total) { + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + signal(SIGALRM, progress_interval); + setitimer(ITIMER_REAL, &v, NULL); + fprintf(stderr, "Checking files out...\n"); + progress_update = 1; + } + cnt = 0; + } + while (nr--) { struct cache_entry *ce = *src++; + + if (total) { + if (!ce->ce_mode || ce->ce_flags & mask) { + unsigned percent; + cnt++; + percent = (cnt * 100) / total; + if (percent != last_percent || + progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, cnt, total); + last_percent = percent; + } + } + } if (!ce->ce_mode) { if (update) unlink_entry(ce->name); @@ -289,6 +340,10 @@ static void check_updates(struct cache_entry **src, int nr) checkout_entry(ce, &state); } } + if (total) { + fputc('\n', stderr); + signal(SIGALRM, SIG_IGN); + } } static int unpack_trees(merge_fn_t fn) @@ -349,7 +404,7 @@ static void verify_uptodate(struct cache_entry *ce) return; if (!lstat(ce->name, &st)) { - unsigned changed = ce_match_stat(ce, &st); + unsigned changed = ce_match_stat(ce, &st, 1); if (!changed) return; errno = 0; @@ -564,7 +619,7 @@ static int twoway_merge(struct cache_entry **src) struct cache_entry *oldtree = src[1], *newtree = src[2]; if (merge_size != 2) - return error("Cannot do a twoway merge of %d trees\n", + return error("Cannot do a twoway merge of %d trees", merge_size); if (current) { @@ -616,7 +671,7 @@ static int oneway_merge(struct cache_entry **src) struct cache_entry *a = src[1]; if (merge_size != 1) - return error("Cannot do a oneway merge of %d trees\n", + return error("Cannot do a oneway merge of %d trees", merge_size); if (!a) @@ -680,6 +735,11 @@ int main(int argc, char **argv) continue; } + if (!strcmp(arg, "-v")) { + verbose_update = 1; + continue; + } + /* "-i" means "index only", meaning that a merge will * not even look at the working tree. */ diff --git a/receive-pack.c b/receive-pack.c index eae31e370d..2a3db16d68 100644 --- a/receive-pack.c +++ b/receive-pack.c @@ -92,7 +92,7 @@ static int run_update_hook(const char *refname, case -ERR_RUN_COMMAND_WAITPID_WRONG_PID: return error("waitpid is confused"); case -ERR_RUN_COMMAND_WAITPID_SIGNAL: - return error("%s died of signal\n", update_hook); + return error("%s died of signal", update_hook); case -ERR_RUN_COMMAND_WAITPID_NOEXIT: return error("%s died strangely", update_hook); default: @@ -158,7 +158,7 @@ static int update(struct command *cmd) if (run_update_hook(name, old_hex, new_hex)) { unlink(lock_name); cmd->error_string = "hook declined"; - return error("hook declined to update %s\n", name); + return error("hook declined to update %s", name); } else if (rename(lock_name, name) < 0) { unlink(lock_name); @@ -268,7 +268,7 @@ static int write_ref_file(const char *filename, char term = '\n'; if (write(fd, hex, 40) < 40 || write(fd, &term, 1) < 1) { - error("Couldn't write %s\n", filename); + error("Couldn't write %s", filename); close(fd); return -1; } diff --git a/rev-list.c b/rev-list.c index dda6fcaa96..67d2a483fc 100644 --- a/rev-list.c +++ b/rev-list.c @@ -299,8 +299,8 @@ static void show_commit_list(struct commit_list *list) die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); } while (objects) { - /* An object with name "foo\n0000000000000000000000000000000000000000" - * can be used confuse downstream git-pack-objects very badly. + /* An object with name "foo\n0000000..." can be used to + * confuse downstream git-pack-objects very badly. */ const char *ep = strchr(objects->name, '\n'); if (ep) { diff --git a/send-pack.c b/send-pack.c index 990be3f1a3..f558386143 100644 --- a/send-pack.c +++ b/send-pack.c @@ -12,6 +12,7 @@ static const char *exec = "git-receive-pack"; static int verbose = 0; static int send_all = 0; static int force_update = 0; +static int use_thin_pack = 0; static int is_zero_sha1(const unsigned char *sha1) { @@ -37,26 +38,47 @@ static void exec_pack_objects(void) static void exec_rev_list(struct ref *refs) { + struct ref *ref; static char *args[1000]; - int i = 0; + int i = 0, j; args[i++] = "rev-list"; /* 0 */ - args[i++] = "--objects"; /* 1 */ - while (refs) { - char *buf = malloc(100); - if (i > 900) + if (use_thin_pack) /* 1 */ + args[i++] = "--objects-edge"; + else + args[i++] = "--objects"; + + /* First send the ones we care about most */ + for (ref = refs; ref; ref = ref->next) { + if (900 < i) die("git-rev-list environment overflow"); - if (!is_zero_sha1(refs->old_sha1) && - has_sha1_file(refs->old_sha1)) { + if (!is_zero_sha1(ref->new_sha1)) { + char *buf = malloc(100); args[i++] = buf; - snprintf(buf, 50, "^%s", sha1_to_hex(refs->old_sha1)); + snprintf(buf, 50, "%s", sha1_to_hex(ref->new_sha1)); buf += 50; + if (!is_zero_sha1(ref->old_sha1) && + has_sha1_file(ref->old_sha1)) { + args[i++] = buf; + snprintf(buf, 50, "^%s", + sha1_to_hex(ref->old_sha1)); + } } - if (!is_zero_sha1(refs->new_sha1)) { + } + + /* Then a handful of the remainder + * NEEDSWORK: we would be better off if used the newer ones first. + */ + for (ref = refs, j = i + 16; + i < 900 && i < j && ref; + ref = ref->next) { + if (is_zero_sha1(ref->new_sha1) && + !is_zero_sha1(ref->old_sha1) && + has_sha1_file(ref->old_sha1)) { + char *buf = malloc(42); args[i++] = buf; - snprintf(buf, 50, "%s", sha1_to_hex(refs->new_sha1)); + snprintf(buf, 42, "^%s", sha1_to_hex(ref->old_sha1)); } - refs = refs->next; } args[i] = NULL; execv_git_cmd(args); @@ -361,6 +383,10 @@ int main(int argc, char **argv) verbose = 1; continue; } + if (!strcmp(arg, "--thin")) { + use_thin_pack = 1; + continue; + } usage(send_pack_usage); } if (!dest) { diff --git a/sha1_file.c b/sha1_file.c index 1d799f793a..a80d849f15 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -247,6 +247,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, for ( ; cp < ep && *cp != sep; cp++) ; if (last != cp) { + struct stat st; struct alternate_object_database *alt; /* 43 = 40-byte + 2 '/' + terminating NUL */ int pfxlen = cp - last; @@ -269,9 +270,19 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, } else memcpy(ent->base, last, pfxlen); + ent->name = ent->base + pfxlen + 1; - ent->base[pfxlen] = ent->base[pfxlen + 3] = '/'; - ent->base[entlen-1] = 0; + ent->base[pfxlen + 3] = '/'; + ent->base[pfxlen] = ent->base[entlen-1] = 0; + + /* Detect cases where alternate disappeared */ + if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) { + error("object directory %s does not exist; " + "check .git/objects/info/alternates.", + ent->base); + goto bad; + } + ent->base[pfxlen] = '/'; /* Prevent the common mistake of listing the same * thing twice, or object directory itself. @@ -552,7 +563,9 @@ static void prepare_packed_git_one(char *objdir, int local) len = strlen(path); dir = opendir(path); if (!dir) { - fprintf(stderr, "unable to open object pack directory: %s: %s\n", path, strerror(errno)); + if (errno != ENOENT) + error("unable to open object pack directory: %s: %s", + path, strerror(errno)); return; } path[len++] = '/'; @@ -828,6 +841,25 @@ static unsigned long unpack_object_header(struct packed_git *p, unsigned long of return offset; } +int check_reuse_pack_delta(struct packed_git *p, unsigned long offset, + unsigned char *base, unsigned long *sizep, + enum object_type *kindp) +{ + unsigned long ptr; + int status = -1; + + use_packed_git(p); + ptr = offset; + ptr = unpack_object_header(p, ptr, kindp, sizep); + if (*kindp != OBJ_DELTA) + goto done; + memcpy(base, p->pack_base + ptr, 20); + status = 0; + done: + unuse_packed_git(p); + return status; +} + void packed_object_info_detail(struct pack_entry *e, char *type, unsigned long *size, @@ -1481,7 +1513,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, local = mkstemp(tmpfile); if (local < 0) - return error("Couldn't open %s for %s\n", tmpfile, sha1_to_hex(sha1)); + return error("Couldn't open %s for %s", + tmpfile, sha1_to_hex(sha1)); memset(&stream, 0, sizeof(stream)); @@ -1529,7 +1562,7 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, } if (memcmp(sha1, real_sha1, 20)) { unlink(tmpfile); - return error("File %s has bad hash\n", sha1_to_hex(sha1)); + return error("File %s has bad hash", sha1_to_hex(sha1)); } return move_temp_to_file(tmpfile, sha1_file_name(sha1)); diff --git a/t/Makefile b/t/Makefile index 5c5a620126..fe65f53c5f 100644 --- a/t/Makefile +++ b/t/Makefile @@ -8,17 +8,18 @@ SHELL_PATH ?= $(SHELL) TAR ?= $(TAR) # Shell quote; -# Result of this needs to be placed inside '' -shq = $(subst ','\'',$(1)) -# This has surrounding '' -shellquote = '$(call shq,$(1))' +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) +ifdef NO_PYTHON + GIT_TEST_OPTS += --no-python +endif + all: $(T) clean $(T): - @echo "*** $@ ***"; $(call shellquote,$(SHELL_PATH)) $@ $(GIT_TEST_OPTS) + @echo "*** $@ ***"; '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) clean: rm -fr trash diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index c339a366f4..6729a18266 100755 --- a/t/t0000-basic.sh +++ b/t/t0000-basic.sh @@ -42,7 +42,7 @@ fi . ./test-lib.sh -"$PYTHON" -c 'import subprocess' || { +test "$no_python" || "$PYTHON" -c 'import subprocess' || { echo >&2 'Your python seem to lack "subprocess" module. Please check INSTALL document.' exit 1 diff --git a/t/t3020-ls-files-error-unmatch.sh b/t/t3020-ls-files-error-unmatch.sh new file mode 100755 index 0000000000..d55559e553 --- /dev/null +++ b/t/t3020-ls-files-error-unmatch.sh @@ -0,0 +1,27 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='git-ls-files test for --error-unmatch option + +This test runs git-ls-files --error-unmatch to ensure it correctly +returns an error when a non-existent path is provided on the command +line. +' +. ./test-lib.sh + +touch foo bar +git-update-index --add foo bar +git-commit -m "add foo bar" + +test_expect_failure \ + 'git-ls-files --error-unmatch should fail with unmatched path.' \ + 'git-ls-files --error-unmatch foo bar-does-not-match' + +test_expect_success \ + 'git-ls-files --error-unmatch should succeed eith matched paths.' \ + 'git-ls-files --error-unmatch foo bar' + +test_done +1 diff --git a/t/t3600-rm.sh b/t/t3600-rm.sh new file mode 100755 index 0000000000..cabfadd56d --- /dev/null +++ b/t/t3600-rm.sh @@ -0,0 +1,60 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='Test of the various options to git-rm.' + +. ./test-lib.sh + +# Setup some files to be removed, some with funny characters +touch -- foo bar baz 'space embedded' 'tab embedded' 'newline +embedded' -q +git-add -- foo bar baz 'space embedded' 'tab embedded' 'newline +embedded' -q +git-commit -m "add files" + +test_expect_success \ + 'Pre-check that foo exists and is in index before git-rm foo' \ + '[ -f foo ] && git-ls-files --error-unmatch foo' + +test_expect_success \ + 'Test that git-rm foo succeeds' \ + 'git-rm foo' + +test_expect_success \ + 'Post-check that foo exists but is not in index after git-rm foo' \ + '[ -f foo ] && ! git-ls-files --error-unmatch foo' + +test_expect_success \ + 'Pre-check that bar exists and is in index before "git-rm -f bar"' \ + '[ -f bar ] && git-ls-files --error-unmatch bar' + +test_expect_success \ + 'Test that "git-rm -f bar" succeeds' \ + 'git-rm -f bar' + +test_expect_success \ + 'Post-check that bar does not exist and is not in index after "git-rm -f bar"' \ + '! [ -f bar ] && ! git-ls-files --error-unmatch bar' + +test_expect_success \ + 'Test that "git-rm -- -q" succeeds (remove a file that looks like an option)' \ + 'git-rm -- -q' + +test_expect_success \ + "Test that \"git-rm -f\" succeeds with embedded space, tab, or newline characters." \ + "git-rm -f 'space embedded' 'tab embedded' 'newline +embedded'" + +chmod u-w . +test_expect_failure \ + 'Test that "git-rm -f" fails if its rm fails' \ + 'git-rm -f baz' +chmod u+w . + +test_expect_success \ + 'When the rm in "git-rm -f" fails, it should not remove the file from the index' \ + 'git-ls-files --error-unmatch baz' + +test_done diff --git a/t/t3700-add.sh b/t/t3700-add.sh new file mode 100755 index 0000000000..6cd05c3d90 --- /dev/null +++ b/t/t3700-add.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='Test of git-add, including the -- option.' + +. ./test-lib.sh + +test_expect_success \ + 'Test of git-add' \ + 'touch foo && git-add foo' + +test_expect_success \ + 'Post-check that foo is in the index' \ + 'git-ls-files foo | grep foo' + +test_expect_success \ + 'Test that "git-add -- -q" works' \ + 'touch -- -q && git-add -- -q' + +test_done diff --git a/t/t5600-clone-fail-cleanup.sh b/t/t5600-clone-fail-cleanup.sh new file mode 100755 index 0000000000..0c6a363be9 --- /dev/null +++ b/t/t5600-clone-fail-cleanup.sh @@ -0,0 +1,36 @@ +#!/bin/sh +# +# Copyright (C) 2006 Carl D. Worth <cworth@cworth.org> +# + +test_description='test git-clone to cleanup after failure + +This test covers the fact that if git-clone fails, it should remove +the directory it created, to avoid the user having to manually +remove the directory before attempting a clone again.' + +. ./test-lib.sh + +test_expect_failure \ + 'clone of non-existent source should fail' \ + 'git-clone foo bar' + +test_expect_failure \ + 'failed clone should not leave a directory' \ + 'cd bar' + +# Need a repo to clone +test_create_repo foo + +# clone doesn't like it if there is no HEAD. Is that a bug? +(cd foo && touch file && git add file && git commit -m 'add file' >/dev/null 2>&1) + +test_expect_success \ + 'clone should work now that source exists' \ + 'git-clone foo bar' + +test_expect_success \ + 'successfull clone must leave the directory' \ + 'cd bar' + +test_done diff --git a/t/t6021-merge-criss-cross.sh b/t/t6021-merge-criss-cross.sh index e8606c751d..262381379f 100755 --- a/t/t6021-merge-criss-cross.sh +++ b/t/t6021-merge-criss-cross.sh @@ -10,6 +10,12 @@ test_description='Test criss-cross merge' . ./test-lib.sh +if test "$no_python"; then + echo "Skipping: no python => no recursive merge" + test_done + exit 0 +fi + test_expect_success 'prepare repository' \ 'echo "1 2 diff --git a/t/t6022-merge-rename.sh b/t/t6022-merge-rename.sh index 1292cafd7f..a2d24b5ca9 100755 --- a/t/t6022-merge-rename.sh +++ b/t/t6022-merge-rename.sh @@ -3,6 +3,12 @@ test_description='Merge-recursive merging renames' . ./test-lib.sh +if test "$no_python"; then + echo "Skipping: no python => no recursive merge" + test_done + exit 0 +fi + test_expect_success setup \ ' cat >A <<\EOF && diff --git a/t/test-lib.sh b/t/test-lib.sh index 66f62b9c6f..05f6e79560 100755 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -63,6 +63,8 @@ do exit 0 ;; -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) verbose=t; shift ;; + --no-python) + no_python=t; shift ;; *) break ;; esac diff --git a/update-index.c b/update-index.c index afec98dd48..ce1db38d16 100644 --- a/update-index.c +++ b/update-index.c @@ -23,6 +23,10 @@ static int quiet; /* --refresh needing update is not error */ static int info_only; static int force_remove; static int verbose; +static int mark_valid_only = 0; +#define MARK_VALID 1 +#define UNMARK_VALID 2 + /* Three functions to allow overloaded pointer return; see linux/err.h */ static inline void *ERR_PTR(long error) @@ -53,6 +57,25 @@ static void report(const char *fmt, ...) va_end(vp); } +static int mark_valid(const char *path) +{ + int namelen = strlen(path); + int pos = cache_name_pos(path, namelen); + if (0 <= pos) { + switch (mark_valid_only) { + case MARK_VALID: + active_cache[pos]->ce_flags |= htons(CE_VALID); + break; + case UNMARK_VALID: + active_cache[pos]->ce_flags &= ~htons(CE_VALID); + break; + } + active_cache_changed = 1; + return 0; + } + return -1; +} + static int add_file_to_cache(const char *path) { int size, namelen, option, status; @@ -94,6 +117,7 @@ static int add_file_to_cache(const char *path) ce = xmalloc(size); memset(ce, 0, size); memcpy(ce->name, path, namelen); + ce->ce_flags = htons(namelen); fill_stat_cache_info(ce, &st); ce->ce_mode = create_ce_mode(st.st_mode); @@ -105,7 +129,6 @@ static int add_file_to_cache(const char *path) if (0 <= pos) ce->ce_mode = active_cache[pos]->ce_mode; } - ce->ce_flags = htons(namelen); if (index_path(ce->sha1, path, &st, !info_only)) return -1; @@ -128,7 +151,7 @@ static int add_file_to_cache(const char *path) * For example, you'd want to do this after doing a "git-read-tree", * to link up the stat cache details with the proper files. */ -static struct cache_entry *refresh_entry(struct cache_entry *ce) +static struct cache_entry *refresh_entry(struct cache_entry *ce, int really) { struct stat st; struct cache_entry *updated; @@ -137,21 +160,36 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce) if (lstat(ce->name, &st) < 0) return ERR_PTR(-errno); - changed = ce_match_stat(ce, &st); - if (!changed) - return NULL; + changed = ce_match_stat(ce, &st, really); + if (!changed) { + if (really && assume_unchanged && + !(ce->ce_flags & htons(CE_VALID))) + ; /* mark this one VALID again */ + else + return NULL; + } - if (ce_modified(ce, &st)) + if (ce_modified(ce, &st, really)) return ERR_PTR(-EINVAL); size = ce_size(ce); updated = xmalloc(size); memcpy(updated, ce, size); fill_stat_cache_info(updated, &st); + + /* In this case, if really is not set, we should leave + * CE_VALID bit alone. Otherwise, paths marked with + * --no-assume-unchanged (i.e. things to be edited) will + * reacquire CE_VALID bit automatically, which is not + * really what we want. + */ + if (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID))) + updated->ce_flags &= ~htons(CE_VALID); + return updated; } -static int refresh_cache(void) +static int refresh_cache(int really) { int i; int has_errors = 0; @@ -171,12 +209,19 @@ static int refresh_cache(void) continue; } - new = refresh_entry(ce); + new = refresh_entry(ce, really); if (!new) continue; if (IS_ERR(new)) { if (not_new && PTR_ERR(new) == -ENOENT) continue; + if (really && PTR_ERR(new) == -EINVAL) { + /* If we are doing --really-refresh that + * means the index is not valid anymore. + */ + ce->ce_flags &= ~htons(CE_VALID); + active_cache_changed = 1; + } if (quiet) continue; printf("%s: needs update\n", ce->name); @@ -274,6 +319,8 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, memcpy(ce->name, path, len); ce->ce_flags = create_ce_flags(len, stage); ce->ce_mode = create_ce_mode(mode); + if (assume_unchanged) + ce->ce_flags |= htons(CE_VALID); option = allow_add ? ADD_CACHE_OK_TO_ADD : 0; option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0; if (add_cache_entry(ce, option)) @@ -317,6 +364,12 @@ static void update_one(const char *path, const char *prefix, int prefix_length) fprintf(stderr, "Ignoring path %s\n", path); return; } + if (mark_valid_only) { + if (mark_valid(p)) + die("Unable to mark file %s", path); + return; + } + if (force_remove) { if (remove_file_from_cache(p)) die("git-update-index: unable to remove %s", path); @@ -467,7 +520,11 @@ int main(int argc, const char **argv) continue; } if (!strcmp(path, "--refresh")) { - has_errors |= refresh_cache(); + has_errors |= refresh_cache(0); + continue; + } + if (!strcmp(path, "--really-refresh")) { + has_errors |= refresh_cache(1); continue; } if (!strcmp(path, "--cacheinfo")) { @@ -493,6 +550,14 @@ int main(int argc, const char **argv) die("git-update-index: %s cannot chmod %s", path, argv[i]); continue; } + if (!strcmp(path, "--assume-unchanged")) { + mark_valid_only = MARK_VALID; + continue; + } + if (!strcmp(path, "--no-assume-unchanged")) { + mark_valid_only = UNMARK_VALID; + continue; + } if (!strcmp(path, "--info-only")) { info_only = 1; continue; diff --git a/upload-pack.c b/upload-pack.c index 3606529f61..635abb371d 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -14,6 +14,7 @@ static const char upload_pack_usage[] = "git-upload-pack [--strict] [--timeout=n #define MAX_HAS 256 #define MAX_NEEDS 256 static int nr_has = 0, nr_needs = 0, multi_ack = 0, nr_our_refs = 0; +static int use_thin_pack = 0; static unsigned char has_sha1[MAX_HAS][20]; static unsigned char needs_sha1[MAX_NEEDS][20]; static unsigned int timeout = 0; @@ -49,8 +50,10 @@ static void create_pack_file(void) char *buf; char **p; - if (create_full_pack) + if (create_full_pack) { args = 10; + use_thin_pack = 0; /* no point doing it */ + } else args = nr_has + nr_needs + 5; argv = xmalloc(args * sizeof(char *)); @@ -62,7 +65,7 @@ static void create_pack_file(void) close(fd[0]); close(fd[1]); *p++ = "rev-list"; - *p++ = "--objects"; + *p++ = use_thin_pack ? "--objects-edge" : "--objects"; if (create_full_pack || MAX_NEEDS <= nr_needs) *p++ = "--all"; else { @@ -192,6 +195,8 @@ static int receive_needs(void) "expected to get sha, not '%s'", line); if (strstr(line+45, "multi_ack")) multi_ack = 1; + if (strstr(line+45, "thin-pack")) + use_thin_pack = 1; /* We have sent all our refs already, and the other end * should have chosen out of them; otherwise they are @@ -213,7 +218,7 @@ static int receive_needs(void) static int send_ref(const char *refname, const unsigned char *sha1) { - static char *capabilities = "multi_ack"; + static char *capabilities = "multi_ack thin-pack"; struct object *o = parse_object(sha1); if (!o) @@ -12,7 +12,7 @@ static const char var_usage[] = "git-var [-l | <variable>]"; struct git_var { const char *name; - const char *(*read)(void); + const char *(*read)(int); }; static struct git_var git_vars[] = { { "GIT_COMMITTER_IDENT", git_committer_info }, @@ -24,7 +24,7 @@ static void list_vars(void) { struct git_var *ptr; for(ptr = git_vars; ptr->read; ptr++) { - printf("%s=%s\n", ptr->name, ptr->read()); + printf("%s=%s\n", ptr->name, ptr->read(0)); } } @@ -35,7 +35,7 @@ static const char *read_var(const char *var) val = NULL; for(ptr = git_vars; ptr->read; ptr++) { if (strcmp(var, ptr->name) == 0) { - val = ptr->read(); + val = ptr->read(1); break; } } diff --git a/write-tree.c b/write-tree.c index f866059f24..addb5de3b6 100644 --- a/write-tree.c +++ b/write-tree.c @@ -111,7 +111,7 @@ int main(int argc, char **argv) funny = 0; for (i = 0; i < entries; i++) { struct cache_entry *ce = active_cache[i]; - if (ntohs(ce->ce_flags) & ~CE_NAMEMASK) { + if (ce_stage(ce)) { if (10 < ++funny) { fprintf(stderr, "...\n"); break; |