diff options
93 files changed, 9420 insertions, 736 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/SubmittingPatches b/Documentation/SubmittingPatches index 9ccb8f72ed..318b04fdeb 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -4,8 +4,8 @@ it for the core GIT to make sure people understand what they are doing when they write "Signed-off-by" line. But the patch submission requirements are a lot more relaxed -here, because the core GIT is thousand times smaller ;-). So -here is only the relevant bits. +here on the technical/contents front, because the core GIT is +thousand times smaller ;-). So here is only the relevant bits. (1) Make separate commits for logically separate changes. @@ -18,13 +18,19 @@ repository. It is a good discipline. Describe the technical detail of the change(s). -If your description starts to get long, that's a sign that you +If your description starts to get too long, that's a sign that you probably need to split up your commit to finer grained pieces. +Oh, another thing. I am picky about whitespaces. Make sure your +changes do not trigger errors with the sample pre-commit hook shipped +in templates/hooks--pre-commit. -(2) Generate your patch using git/cogito out of your commits. -git diff tools generate unidiff which is the preferred format. +(2) Generate your patch using git tools out of your commits. + +git based diff tools (git, Cogito, and StGIT included) generate +unidiff which is the preferred format. + You do not have to be afraid to use -M option to "git diff" or "git format-patch", if your patch involves file renames. The receiving end can handle them just fine. @@ -33,20 +39,22 @@ Please make sure your patch does not include any extra files which do not belong in a patch submission. Make sure to review your patch after generating it, to ensure accuracy. Before sending out, please make sure it cleanly applies to the "master" -branch head. +branch head. If you are preparing a work based on "next" branch, +that is fine, but please mark it as such. (3) Sending your patches. -People on the git mailing list needs to be able to read and +People on the git mailing list need to be able to read and comment on the changes you are submitting. It is important for a developer to be able to "quote" your changes, using standard e-mail tools, so that they may comment on specific portions of -your code. For this reason, all patches should be submitting -e-mail "inline". WARNING: Be wary of your MUAs word-wrap -corrupting your patch. Do not cut-n-paste your patch. +your code. For this reason, all patches should be submited +"inline". WARNING: Be wary of your MUAs word-wrap +corrupting your patch. Do not cut-n-paste your patch; you can +lose tabs that way if you are not careful. -It is common convention to prefix your subject line with +It is a common convention to prefix your subject line with [PATCH]. This lets people easily distinguish patches from other e-mail discussions. diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index 5b1b4d3780..214ed235c5 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -85,27 +85,12 @@ OPTIONS <file>...:: Files to be committed. The meaning of these is different between `--include` and `--only`. Without - either, it defaults `--include` semantics. + either, it defaults `--only` semantics. If you make a commit and then found a mistake immediately after that, you can recover from it with gitlink:git-reset[1]. -WARNING -------- - -The 1.2.0 and its maintenance series 1.2.X will keep the -traditional `--include` semantics as the default when neither -`--only` nor `--include` is specified and `paths...` are given. -This *will* change during the development towards 1.3.0 in the -'master' branch of `git.git` repository. If you are using this -command in your scripts, and you depend on the traditional -`--include` semantics, please update them to explicitly ask for -`--include` semantics. Also if you are used to making partial -commit using `--include` semantics, please train your fingers to -say `git commit --include paths...` (or `git commit -i paths...`). - - Discussion ---------- @@ -121,7 +106,7 @@ even the command is invoked from a subdirectory. That is, update the specified paths to the index and then commit the whole tree. -`git commit --only paths...` largely bypasses the index file and +`git commit paths...` largely bypasses the index file and commits only the changes made to the specified paths. It has however several safety valves to prevent confusion. diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt new file mode 100644 index 0000000000..19c9c51cff --- /dev/null +++ b/Documentation/git-cvsserver.txt @@ -0,0 +1,113 @@ +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 + +Eclipse CVS Client Notes +------------------------ + +To get a checkout with the Eclipse CVS client: + +1. Create a new project from CVS checkout, giving it repository and module +2. Context Menu->Team->Share Project... +3. Enter the repository and module information again and click Finish +4. The Synchronize view appears. Untick "launch commit wizard" to avoid +committing the .project file, and select HEAD as the tag to synchronize to. +Update all incoming changes. + +Note that most versions of Eclipse ignore CVS_SERVER (which you can set in +the Preferences->Team->CVS->ExtConnection pane), so you may have to +rename, alias or symlink git-cvsserver to 'cvs' on the server. + +Clients known to work +--------------------- + +CVS 1.12.9 on Debian +CVS 1.11.17 on MacOSX (from Fink package) +Eclipse 3.0, 3.1.2 on MacOSX (see Eclipse CVS Client Notes) +TortoiseCVS + +Operations supported +-------------------- + +All the operations required for normal use are supported, including +checkout, diff, status, update, log, add, remove, commit. +Legacy monitoring operations are not supported (edit, watch and related). +Exports and tagging (tags and branches) are not supported at this stage. + +The server will set the -k mode to binary when relevant. In proper GIT +tradition, the contents of the files are always respected. +No keyword expansion or newline munging is supported. + +Dependencies +------------ + +git-cvsserver depends on DBD::SQLite. + +Copyright and Authors +--------------------- + +This program is copyright The Open University UK - 2006. + +Authors: Martyn Smith <martyn@catalyst.net.nz> + Martin Langhoff <martin@catalyst.net.nz> + with ideas and patches from participants of the git-list <git@vger.kernel.org>. + +Documentation +-------------- +Documentation by Martyn Smith <martyn@catalyst.net.nz> and Martin Langhoff <martin@catalyst.net.nz>Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-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-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-rev-parse.txt b/Documentation/git-rev-parse.txt index 1662e06561..29b578978a 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -80,7 +80,7 @@ OPTIONS --git-dir:: Show `$GIT_DIR` if defined else show the path to the .git directory. ---short, short=number:: +--short, --short=number:: Instead of outputting the full SHA1 values of object names try to abbriviate them to a shorter unique name. When no length is specified 7 is used. The minimum length is 4. diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt new file mode 100644 index 0000000000..401bfb2d9c --- /dev/null +++ b/Documentation/git-rm.txt @@ -0,0 +1,89 @@ +git-rm(1) +========= + +NAME +---- +git-rm - Remove files from the working tree and from the index. + +SYNOPSIS +-------- +'git-rm' [-f] [-n] [-v] [--] <file>... + +DESCRIPTION +----------- +A convenience wrapper for git-update-index --remove. For those coming +from cvs, git-rm provides an operation similar to "cvs rm" or "cvs +remove". + + +OPTIONS +------- +<file>...:: + Files to remove from the index and optionally, from the + working tree as well. + +-f:: + Remove files from the working tree as well as from the index. + +-n:: + Don't actually remove the file(s), just show if they exist in + the index. + +-v:: + Be verbose. + +--:: + This option can be used to separate command-line options from + the list of files, (useful when filenames might be mistaken + for command-line options). + + +DISCUSSION +---------- + +The list of <file> given to the command is fed to `git-ls-files` +command to list files that are registered in the index and +are not ignored/excluded by `$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-send-email.txt b/Documentation/git-send-email.txt index 00537d8907..8c58685e28 100644 --- a/Documentation/git-send-email.txt +++ b/Documentation/git-send-email.txt @@ -24,6 +24,9 @@ OPTIONS ------- The options available are: +--cc:: + Specify a starting "Cc:" value for each email. + --chain-reply-to, --no-chain-reply-to:: If this is set, each email will be sent as a reply to the previous email sent. If disabled with "--no-chain-reply-to", all emails after @@ -48,6 +51,9 @@ The options available are: Only necessary if --compose is also set. If --compose is not set, this will be prompted for. +--no-signed-off-by-cc:: + Do not add emails foudn in Signed-off-by: lines to the cc list. + --quiet:: Make git-send-email less verbose. One line per email should be all that is output. @@ -61,6 +67,10 @@ The options available are: Only necessary if --compose is also set. If --compose is not set, this will be prompted for. +--suppress-from:: + Do not add the From: address to the cc: list, if it shows up in a From: + line. + --to:: Specify the primary recipient of the emails generated. Generally, this will be the upstream maintainer of the diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt index 63e28b89d5..a1588138ea 100644 --- a/Documentation/git-svnimport.txt +++ b/Documentation/git-svnimport.txt @@ -10,10 +10,11 @@ git-svnimport - Import a SVN repository into git SYNOPSIS -------- 'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ] - [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] - [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] - [ -s start_chg ] [ -m ] [ -M regex ] - <SVN_repository_URL> [ <path> ] + [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] + [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] + [ -s start_chg ] [ -m ] [ -r ] [ -M regex ] + [ -I <ignorefile_name> ] [ -A <author_file> ] + <SVN_repository_URL> [ <path> ] DESCRIPTION @@ -61,6 +62,31 @@ When importing incrementally, you might need to edit the .git/svn2git file. the git repository. Use this option if you want to import into a different branch. +-r:: + Prepend 'rX: ' to commit messages, where X is the imported + subversion revision. + +-I <ignorefile_name>:: + Import the svn:ignore directory property to files with this + name in each directory. (The Subversion and GIT ignore + syntaxes are similar enough that using the Subversion patterns + directly with "-I .gitignore" will almost always just work.) + +-A <author_file>:: + Read a file with lines on the form + + username = User's Full Name <email@addr.es> + + and use "User's Full Name <email@addr.es>" as the GIT + author and committer for Subversion commits made by + "username". If encountering a commit made by a user not in the + list, abort. + + For convenience, this data is saved to $GIT_DIR/svn-authors + each time the -A option is provided, and read from that same + file each time git-svnimport is run with an existing GIT + repository without -A. + -m:: Attempt to detect merges based on the commit message. This option will enable default regexes that try to capture the name source diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt index e8892bb0b0..e1c76c600d 100644 --- a/Documentation/git-tag.txt +++ b/Documentation/git-tag.txt @@ -8,11 +8,13 @@ git-tag - Create a tag object signed with GPG SYNOPSIS -------- +[verse] 'git-tag' [-a | -s | -u <key-id>] [-f | -d] [-m <msg>] <name> [<head>] +'git-tag' -l [<pattern>] DESCRIPTION ----------- -Adds a 'tag' reference in .git/refs/tags/ +Adds a 'tag' reference in `.git/refs/tags/` Unless `-f` is given, the tag must not yet exist in `.git/refs/tags/` directory. @@ -32,6 +34,9 @@ GnuPG key for signing. `-d <tag>` deletes the tag. +`-l <pattern>` lists tags that match the given pattern (or all +if no pattern is given). + OPTIONS ------- -a:: @@ -49,6 +54,9 @@ OPTIONS -d:: Delete an existing tag with the given name +-l <pattern>:: + List tags that match the given pattern (or all if no pattern is given). + -m <msg>:: Use the given tag message (instead of prompting) 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 -------- @@ -53,6 +53,13 @@ all: # Define NO_SOCKADDR_STORAGE if your platform does not have struct # sockaddr_storage. # +# 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. @@ -70,6 +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 @@ -80,7 +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= @@ -107,7 +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 \ @@ -117,6 +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 = \ @@ -129,7 +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$X # ... and all the rest that could be moved out of bindir to gitexecdir @@ -139,9 +153,9 @@ PROGRAMS = \ git-convert-objects$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$X \ @@ -151,7 +165,7 @@ PROGRAMS = \ git-upload-pack$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) @@ -182,7 +196,8 @@ LIB_H = \ DIFF_OBJS = \ diff.o diffcore-break.o diffcore-order.o diffcore-pathspec.o \ - diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o + diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o \ + diffcore-delta.o LIB_OBJS = \ blob.o commit.o connect.o count-delta.o csum-file.o \ @@ -197,12 +212,6 @@ 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 # @@ -210,28 +219,28 @@ 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 NEEDS_LIBICONV = YesPlease ## fink - ALL_CFLAGS += -I/sw/include - ALL_LDFLAGS += -L/sw/lib + ifeq ($(shell test -d /sw/lib && echo y),y) + ALL_CFLAGS += -I/sw/include + ALL_LDFLAGS += -L/sw/lib + endif ## darwinports - ALL_CFLAGS += -I/opt/local/include - ALL_LDFLAGS += -L/opt/local/lib + ifeq ($(shell test -d /opt/local/lib && echo y),y) + ALL_CFLAGS += -I/opt/local/include + ALL_LDFLAGS += -L/opt/local/lib + endif 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 @@ -271,6 +280,16 @@ 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 @@ -280,8 +299,10 @@ 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 @@ -380,6 +401,10 @@ else endif endif +ifdef NO_ICONV + ALL_CFLAGS += -DNO_ICONV +endif + ifdef PPC_SHA1 SHA1_HEADER = "ppc/sha1.h" LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o @@ -397,8 +422,25 @@ else endif endif endif +ifdef NO_ACCURATE_DIFF + ALL_CFLAGS += -DNO_ACCURATE_DIFF +endif + +# Shell quote (do not use $(call) to accomodate ancient setups); -ALL_CFLAGS += -DSHA1_HEADER=$(call shellquote,$(SHA1_HEADER)) $(COMPAT_CFLAGS) +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) + +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 += $(COMPAT_OBJS) export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir ### Build rules @@ -417,23 +459,24 @@ git$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 $@ @@ -459,32 +502,42 @@ git$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) @@ -499,6 +552,12 @@ 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 @@ -516,13 +575,13 @@ 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 @@ -1232,6 +1232,14 @@ 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; @@ -1399,7 +1407,7 @@ 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); @@ -10,7 +10,7 @@ #define deflateBound(c,s) ((s) + (((s) + 7) >> 3) + (((s) + 63) >> 6) + 11) #endif -#if defined(DT_UNKNOWN) && !NO_D_TYPE_IN_DIRENT +#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT) #define DTYPE(de) ((de)->d_type) #else #undef DT_UNKNOWN @@ -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); @@ -162,6 +163,7 @@ extern void rollback_index_file(struct cache_file *); /* Environment bits from configuration mechanism */ extern int trust_executable_bit; +extern int assume_unchanged; extern int only_use_symrefs; extern int diff_rename_limit_default; extern int shared_repository; @@ -324,7 +326,7 @@ extern int num_packed_objects(const struct packed_git *p); extern int nth_packed_object_sha1(const struct packed_git *, int, unsigned char*); extern int find_pack_entry_one(const unsigned char *, struct pack_entry *, struct packed_git *); extern void *unpack_entry_gently(struct pack_entry *, char *, unsigned long *); -extern void packed_object_info_detail(struct pack_entry *, char *, unsigned long *, unsigned long *, int *, unsigned char *); +extern void packed_object_info_detail(struct pack_entry *, char *, unsigned long *, unsigned long *, unsigned int *, unsigned char *); /* Dumb servers support */ extern int update_server_info(int); diff --git a/cat-file.c b/cat-file.c index 96d66b4304..1a613f3ee5 100644 --- a/cat-file.c +++ b/cat-file.c @@ -4,6 +4,92 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "exec_cmd.h" + +static void flush_buffer(const char *buf, unsigned long size) +{ + while (size > 0) { + long ret = xwrite(1, buf, size); + if (ret < 0) { + /* Ignore epipe */ + if (errno == EPIPE) + break; + die("git-cat-file: %s", strerror(errno)); + } else if (!ret) { + die("git-cat-file: disk full?"); + } + size -= ret; + buf += ret; + } +} + +static int pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size) +{ + /* the parser in tag.c is useless here. */ + const char *endp = buf + size; + const char *cp = buf; + + while (cp < endp) { + char c = *cp++; + if (c != '\n') + continue; + if (7 <= endp - cp && !memcmp("tagger ", cp, 7)) { + const char *tagger = cp; + + /* Found the tagger line. Copy out the contents + * of the buffer so far. + */ + flush_buffer(buf, cp - buf); + + /* + * Do something intelligent, like pretty-printing + * the date. + */ + while (cp < endp) { + if (*cp++ == '\n') { + /* tagger to cp is a line + * that has ident and time. + */ + const char *sp = tagger; + char *ep; + unsigned long date; + long tz; + while (sp < cp && *sp != '>') + sp++; + if (sp == cp) { + /* give up */ + flush_buffer(tagger, + cp - tagger); + break; + } + while (sp < cp && + !('0' <= *sp && *sp <= '9')) + sp++; + flush_buffer(tagger, sp - tagger); + date = strtoul(sp, &ep, 10); + tz = strtol(ep, NULL, 10); + sp = show_date(date, tz); + flush_buffer(sp, strlen(sp)); + xwrite(1, "\n", 1); + break; + } + } + break; + } + if (cp < endp && *cp == '\n') + /* end of header */ + break; + } + /* At this point, we have copied out the header up to the end of + * the tagger line and cp points at one past \n. It could be the + * next header line after the tagger line, or it could be another + * \n that marks the end of the headers. We need to copy out the + * remainder as is. + */ + if (cp < endp) + flush_buffer(cp, endp - cp); + return 0; +} int main(int argc, char **argv) { @@ -15,7 +101,7 @@ int main(int argc, char **argv) setup_git_directory(); if (argc != 3 || get_sha1(argv[2], sha1)) - usage("git-cat-file [-t|-s|-e|<type>] <sha1>"); + usage("git-cat-file [-t|-s|-e|-p|<type>] <sha1>"); opt = 0; if ( argv[1][0] == '-' ) { @@ -43,6 +129,23 @@ int main(int argc, char **argv) case 'e': return !has_sha1_file(sha1); + case 'p': + if (get_sha1(argv[2], sha1) || + sha1_object_info(sha1, type, NULL)) + die("Not a valid object name %s", argv[2]); + + /* custom pretty-print here */ + if (!strcmp(type, "tree")) + return execl_git_cmd("ls-tree", argv[2], NULL); + + buf = read_sha1_file(sha1, type, &size); + if (!buf) + die("Cannot read object %s", argv[2]); + if (!strcmp(type, "tag")) + return pprint_tag(sha1, buf, size); + + /* otherwise just spit out the data */ + break; case 0: buf = read_object_with_reference(sha1, argv[1], &size, NULL); break; @@ -54,18 +157,6 @@ int main(int argc, char **argv) if (!buf) die("git-cat-file %s: bad file", argv[2]); - while (size > 0) { - long ret = xwrite(1, buf, size); - if (ret < 0) { - /* Ignore epipe */ - if (errno == EPIPE) - break; - die("git-cat-file: %s", strerror(errno)); - } else if (!ret) { - die("git-cat-file: disk full?"); - } - size -= ret; - buf += ret; - } + flush_buffer(buf, size); return 0; } 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) { @@ -572,7 +572,7 @@ int count_parents(struct commit * commit) /* * Performs an in-place topological sort on the list supplied. */ -void sort_in_topological_order(struct commit_list ** list) +void sort_in_topological_order(struct commit_list ** list, int lifo) { struct commit_list * next = *list; struct commit_list * work = NULL, **insert; @@ -631,7 +631,10 @@ void sort_in_topological_order(struct commit_list ** list) } next=next->next; } + /* process the list in topological order */ + if (!lifo) + sort_by_date(&work); while (work) { struct commit * work_item = pop_commit(&work); struct sort_node * work_node = (struct sort_node *)work_item->object.util; @@ -648,8 +651,12 @@ void sort_in_topological_order(struct commit_list ** list) * guaranteeing topological order. */ pn->indegree--; - if (!pn->indegree) - commit_list_insert(parent, &work); + if (!pn->indegree) { + if (!lifo) + insert_by_date(parent, &work); + else + commit_list_insert(parent, &work); + } } parents=parents->next; } @@ -72,6 +72,8 @@ int count_parents(struct commit * commit); * Post-conditions: * invariant of resulting list is: * a reachable from b => ord(b) < ord(a) + * in addition, when lifo == 0, commits on parallel tracks are + * sorted in the dates order. */ -void sort_in_topological_order(struct commit_list ** list); +void sort_in_topological_order(struct commit_list ** list, int lifo); #endif /* COMMIT_H */ @@ -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/README b/contrib/README new file mode 100644 index 0000000000..e1c0a01ff3 --- /dev/null +++ b/contrib/README @@ -0,0 +1,44 @@ +Contributed Software + +Although these pieces are available as part of the official git +source tree, they are in somewhat different status. The +intention is to keep interesting tools around git here, maybe +even experimental ones, to give users an easier access to them, +and to give tools wider exposure, so that they can be improved +faster. + +I am not expecting to touch these myself that much. As far as +my day-to-day operation is concerned, these subdirectories are +owned by their respective primary authors. I am willing to help +if users of these components and the contrib/ subtree "owners" +have technical/design issues to resolve, but the initiative to +fix and/or enhance things _must_ be on the side of the subtree +owners. IOW, I won't be actively looking for bugs and rooms for +enhancements in them as the git maintainer -- I may only do so +just as one of the users when I want to scratch my own itch. If +you have patches to things in contrib/ area, the patch should be +first sent to the primary author, and then the primary author +should ack and forward it to me (git pull request is nicer). +This is the same way as how I have been treating gitk, and to a +lesser degree various foreign SCM interfaces, so you know the +drill. + +I expect that things that start their life in the contrib/ area +to graduate out of contrib/ once they mature, either by becoming +projects on their own, or moving to the toplevel directory. On +the other hand, I expect I'll be proposing removal of disused +and inactive ones from time to time. + +If you have new things to add to this area, please first propose +it on the git mailing list, and after a list discussion proves +there are some general interests (it does not have to be a +list-wide consensus for a tool targeted to a relatively narrow +audience -- for example I do not work with projects whose +upstream is svn, so I have no use for git-svn myself, but it is +of general interest for people who need to interoperate with SVN +repositories in a way git-svn works better than git-svnimport), +submit a patch to create a subdirectory of contrib/ and put your +stuff there. + +-jc + diff --git a/contrib/emacs/git.el b/contrib/emacs/git.el new file mode 100644 index 0000000000..8f234772b0 --- /dev/null +++ b/contrib/emacs/git.el @@ -0,0 +1,956 @@ +;;; git.el --- A user interface for git + +;; Copyright (C) 2005, 2006 Alexandre Julliard <julliard@winehq.org> + +;; Version: 1.0 + +;; This program is free software; you can redistribute it and/or +;; modify it under the terms of the GNU General Public License as +;; published by the Free Software Foundation; either version 2 of +;; the License, or (at your option) any later version. +;; +;; This program is distributed in the hope that it will be +;; useful, but WITHOUT ANY WARRANTY; without even the implied +;; warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR +;; PURPOSE. See the GNU General Public License for more details. +;; +;; You should have received a copy of the GNU General Public +;; License along with this program; if not, write to the Free +;; Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, +;; MA 02111-1307 USA + +;;; Commentary: + +;; This file contains an interface for the git version control +;; system. It provides easy access to the most frequently used git +;; commands. The user interface is as far as possible identical to +;; that of the PCL-CVS mode. +;; +;; To install: put this file on the load-path and place the following +;; in your .emacs file: +;; +;; (require 'git) +;; +;; To start: `M-x git-status' +;; +;; TODO +;; - portability to XEmacs +;; - better handling of subprocess errors +;; - hook into file save (after-save-hook) +;; - diff against other branch +;; - renaming files from the status buffer +;; - support for appending signed-off-by +;; - creating tags +;; - fetch/pull +;; - switching branches +;; - revlist browser +;; - git-show-branch browser +;; - customize support +;; - menus +;; + +(eval-when-compile (require 'cl)) +(require 'ewoc) + + +;;;; Faces +;;;; ------------------------------------------------------------ + +(defface git-status-face + '((((class color) (background light)) (:foreground "purple"))) + "Git mode face used to highlight added and modified files.") + +(defface git-unmerged-face + '((((class color) (background light)) (:foreground "red" :bold t))) + "Git mode face used to highlight unmerged files.") + +(defface git-unknown-face + '((((class color) (background light)) (:foreground "goldenrod" :bold t))) + "Git mode face used to highlight unknown files.") + +(defface git-uptodate-face + '((((class color) (background light)) (:foreground "grey60"))) + "Git mode face used to highlight up-to-date files.") + +(defface git-ignored-face + '((((class color) (background light)) (:foreground "grey60"))) + "Git mode face used to highlight ignored files.") + +(defface git-mark-face + '((((class color) (background light)) (:foreground "red" :bold t))) + "Git mode face used for the file marks.") + +(defface git-header-face + '((((class color) (background light)) (:foreground "blue"))) + "Git mode face used for commit headers.") + +(defface git-separator-face + '((((class color) (background light)) (:foreground "brown"))) + "Git mode face used for commit separator.") + +(defface git-permission-face + '((((class color) (background light)) (:foreground "green" :bold t))) + "Git mode face used for permission changes.") + +(defvar git-committer-name nil + "*User name to use for commits. +If not set, fall back to `add-log-full-name' and then `user-full-name'.") + +(defvar git-committer-email nil + "*Email address to use for commits. +If not set, fall back to `add-log-mailing-address' and then `user-mail-address'.") + +(defvar git-commits-coding-system 'utf-8 + "Default coding system for git commits.") + +(defconst git-log-msg-separator "--- log message follows this line ---") + +(defconst git-per-dir-ignore-file ".gitignore" + "Name of the per-directory ignore file.") + + +;;;; Utilities +;;;; ------------------------------------------------------------ + +(defun git-get-env-strings (env) + "Build a list of NAME=VALUE strings from a list of environment strings." + (mapcar (lambda (entry) (concat (car entry) "=" (cdr entry))) env)) + +(defun git-call-process-env (buffer env &rest args) + "Wrapper for call-process that sets environment strings." + (if env + (apply #'call-process "env" nil buffer nil + (append (git-get-env-strings env) (list "git") args)) + (apply #'call-process "git" nil buffer nil args))) + +(defun git-run-process-region (buffer start end program args) + "Run a git process with a buffer region as input." + (let ((output-buffer (current-buffer)) + (dir default-directory)) + (with-current-buffer buffer + (cd dir) + (apply #'call-process-region start end program + nil (list output-buffer nil) nil args)))) + +(defun git-run-command-buffer (buffer-name &rest args) + "Run a git command, sending the output to a buffer named BUFFER-NAME." + (let ((dir default-directory) + (buffer (get-buffer-create buffer-name))) + (message "Running git %s..." (car args)) + (with-current-buffer buffer + (let ((default-directory dir) + (buffer-read-only nil)) + (erase-buffer) + (apply #'git-call-process-env buffer nil args))) + (message "Running git %s...done" (car args)) + buffer)) + +(defun git-run-command (buffer env &rest args) + (message "Running git %s..." (car args)) + (apply #'git-call-process-env buffer env args) + (message "Running git %s...done" (car args))) + +(defun git-run-command-region (buffer start end env &rest args) + "Run a git command with specified buffer region as input." + (message "Running git %s..." (car args)) + (unless (eq 0 (if env + (git-run-process-region + buffer start end "env" + (append (git-get-env-strings env) (list "git") args)) + (git-run-process-region + buffer start end "git" args))) + (error "Failed to run \"git %s\":\n%s" (mapconcat (lambda (x) x) args " ") (buffer-string))) + (message "Running git %s...done" (car args))) + +(defun git-get-string-sha1 (string) + "Read a SHA1 from the specified string." + (let ((pos (string-match "[0-9a-f]\\{40\\}" string))) + (and pos (substring string pos (match-end 0))))) + +(defun git-get-committer-name () + "Return the name to use as GIT_COMMITTER_NAME." + ; copied from log-edit + (or git-committer-name + (and (boundp 'add-log-full-name) add-log-full-name) + (and (fboundp 'user-full-name) (user-full-name)) + (and (boundp 'user-full-name) user-full-name))) + +(defun git-get-committer-email () + "Return the email address to use as GIT_COMMITTER_EMAIL." + ; copied from log-edit + (or git-committer-email + (and (boundp 'add-log-mailing-address) add-log-mailing-address) + (and (fboundp 'user-mail-address) (user-mail-address)) + (and (boundp 'user-mail-address) user-mail-address))) + +(defun git-escape-file-name (name) + "Escape a file name if necessary." + (if (string-match "[\n\t\"\\]" name) + (concat "\"" + (mapconcat (lambda (c) + (case c + (?\n "\\n") + (?\t "\\t") + (?\\ "\\\\") + (?\" "\\\"") + (t (char-to-string c)))) + name "") + "\"") + name)) + +(defun git-get-top-dir (dir) + "Retrieve the top-level directory of a git tree." + (let ((cdup (with-output-to-string + (with-current-buffer standard-output + (cd dir) + (unless (eq 0 (call-process "git" nil t nil "rev-parse" "--show-cdup")) + (error "cannot find top-level git tree for %s." dir)))))) + (expand-file-name (concat (file-name-as-directory dir) + (car (split-string cdup "\n")))))) + +;stolen from pcl-cvs +(defun git-append-to-ignore (file) + "Add a file name to the ignore file in its directory." + (let* ((fullname (expand-file-name file)) + (dir (file-name-directory fullname)) + (name (file-name-nondirectory fullname))) + (save-window-excursion + (set-buffer (find-file-noselect (expand-file-name git-per-dir-ignore-file dir))) + (goto-char (point-max)) + (unless (zerop (current-column)) (insert "\n")) + (insert name "\n") + (sort-lines nil (point-min) (point-max)) + (save-buffer)))) + + +;;;; Wrappers for basic git commands +;;;; ------------------------------------------------------------ + +(defun git-rev-parse (rev) + "Parse a revision name and return its SHA1." + (git-get-string-sha1 + (with-output-to-string + (with-current-buffer standard-output + (git-call-process-env t nil "rev-parse" rev))))) + +(defun git-symbolic-ref (ref) + "Wrapper for the git-symbolic-ref command." + (car + (split-string + (with-output-to-string + (with-current-buffer standard-output + (git-call-process-env t nil "symbolic-ref" ref))) + "\n"))) + +(defun git-update-ref (ref val &optional oldval) + "Update a reference by calling git-update-ref." + (apply #'git-call-process-env nil nil "update-ref" ref val (if oldval (list oldval)))) + +(defun git-read-tree (tree &optional index-file) + "Read a tree into the index file." + (apply #'git-call-process-env nil + (if index-file `(("GIT_INDEX_FILE" . ,index-file)) nil) + "read-tree" (if tree (list tree)))) + +(defun git-write-tree (&optional index-file) + "Call git-write-tree and return the resulting tree SHA1 as a string." + (git-get-string-sha1 + (with-output-to-string + (with-current-buffer standard-output + (git-call-process-env t + (if index-file `(("GIT_INDEX_FILE" . ,index-file)) nil) + "write-tree"))))) + +(defun git-commit-tree (buffer tree head) + "Call git-commit-tree with buffer as input and return the resulting commit SHA1." + (let ((author-name (git-get-committer-name)) + (author-email (git-get-committer-email)) + author-date log-start log-end args) + (when head + (push "-p" args) + (push head args)) + (with-current-buffer buffer + (goto-char (point-min)) + (if + (setq log-start (re-search-forward (concat "^" git-log-msg-separator "\n") nil t)) + (save-restriction + (narrow-to-region (point-min) log-start) + (goto-char (point-min)) + (when (re-search-forward "^Author: +\\(.*?\\) *<\\(.*\\)> *$" nil t) + (setq author-name (match-string 1) + author-email (match-string 2))) + (goto-char (point-min)) + (when (re-search-forward "^Date: +\\(.*\\)$" nil t) + (setq author-date (match-string 1))) + (goto-char (point-min)) + (while (re-search-forward "^Parent: +\\([0-9a-f]+\\)" nil t) + (unless (string-equal head (match-string 1)) + (push "-p" args) + (push (match-string 1) args)))) + (setq log-start (point-min))) + (setq log-end (point-max))) + (git-get-string-sha1 + (with-output-to-string + (with-current-buffer standard-output + (let ((coding-system-for-write git-commits-coding-system) + (env `(("GIT_AUTHOR_NAME" . ,author-name) + ("GIT_AUTHOR_EMAIL" . ,author-email) + ("GIT_COMMITTER_NAME" . ,(git-get-committer-name)) + ("GIT_COMMITTER_EMAIL" . ,(git-get-committer-email))))) + (when author-date (push `("GIT_AUTHOR_DATE" . ,author-date) env)) + (apply #'git-run-command-region + buffer log-start log-end env + "commit-tree" tree (nreverse args)))))))) + +(defun git-empty-db-p () + "Check if the git db is empty (no commit done yet)." + (not (eq 0 (call-process "git" nil nil nil "rev-parse" "--verify" "HEAD")))) + +(defun git-get-merge-heads () + "Retrieve the merge heads from the MERGE_HEAD file if present." + (let (heads) + (when (file-readable-p ".git/MERGE_HEAD") + (with-temp-buffer + (insert-file-contents ".git/MERGE_HEAD" nil nil nil t) + (goto-char (point-min)) + (while (re-search-forward "[0-9a-f]\\{40\\}" nil t) + (push (match-string 0) heads)))) + (nreverse heads))) + +;;;; File info structure +;;;; ------------------------------------------------------------ + +; fileinfo structure stolen from pcl-cvs +(defstruct (git-fileinfo + (:copier nil) + (:constructor git-create-fileinfo (state name &optional old-perm new-perm rename-state orig-name marked)) + (:conc-name git-fileinfo->)) + marked ;; t/nil + state ;; current state + name ;; file name + old-perm new-perm ;; permission flags + rename-state ;; rename or copy state + orig-name ;; original name for renames or copies + needs-refresh) ;; whether file needs to be refreshed + +(defvar git-status nil) + +(defun git-clear-status (status) + "Remove everything from the status list." + (ewoc-filter status (lambda (info) nil))) + +(defun git-set-files-state (files state) + "Set the state of a list of files." + (dolist (info files) + (unless (eq (git-fileinfo->state info) state) + (setf (git-fileinfo->state info) state) + (setf (git-fileinfo->rename-state info) nil) + (setf (git-fileinfo->orig-name info) nil) + (setf (git-fileinfo->needs-refresh info) t)))) + +(defun git-state-code (code) + "Convert from a string to a added/deleted/modified state." + (case (string-to-char code) + (?M 'modified) + (?? 'unknown) + (?A 'added) + (?D 'deleted) + (?U 'unmerged) + (t nil))) + +(defun git-status-code-as-string (code) + "Format a git status code as string." + (case code + ('modified (propertize "Modified" 'face 'git-status-face)) + ('unknown (propertize "Unknown " 'face 'git-unknown-face)) + ('added (propertize "Added " 'face 'git-status-face)) + ('deleted (propertize "Deleted " 'face 'git-status-face)) + ('unmerged (propertize "Unmerged" 'face 'git-unmerged-face)) + ('uptodate (propertize "Uptodate" 'face 'git-uptodate-face)) + ('ignored (propertize "Ignored " 'face 'git-ignored-face)) + (t "? "))) + +(defun git-rename-as-string (info) + "Return a string describing the copy or rename associated with INFO, or an empty string if none." + (let ((state (git-fileinfo->rename-state info))) + (if state + (propertize + (concat " (" + (if (eq state 'copy) "copied from " + (if (eq (git-fileinfo->state info) 'added) "renamed to " + "renamed from ")) + (git-escape-file-name (git-fileinfo->orig-name info)) + ")") 'face 'git-status-face) + ""))) + +(defun git-permissions-as-string (old-perm new-perm) + "Format a permission change as string." + (propertize + (if (or (not old-perm) + (not new-perm) + (eq 0 (logand #O111 (logxor old-perm new-perm)))) + " " + (if (eq 0 (logand #O111 old-perm)) "+x" "-x")) + 'face 'git-permission-face)) + +(defun git-fileinfo-prettyprint (info) + "Pretty-printer for the git-fileinfo structure." + (insert (format " %s %s %s %s%s" + (if (git-fileinfo->marked info) (propertize "*" 'face 'git-mark-face) " ") + (git-status-code-as-string (git-fileinfo->state info)) + (git-permissions-as-string (git-fileinfo->old-perm info) (git-fileinfo->new-perm info)) + (git-escape-file-name (git-fileinfo->name info)) + (git-rename-as-string info)))) + +(defun git-parse-status (status) + "Parse the output of git-diff-index in the current buffer." + (goto-char (point-min)) + (while (re-search-forward + ":\\([0-7]\\{6\\}\\) \\([0-7]\\{6\\}\\) [0-9a-f]\\{40\\} [0-9a-f]\\{40\\} \\(\\([ADMU]\\)\0\\([^\0]+\\)\\|\\([CR]\\)[0-9]*\0\\([^\0]+\\)\0\\([^\0]+\\)\\)\0" + nil t 1) + (let ((old-perm (string-to-number (match-string 1) 8)) + (new-perm (string-to-number (match-string 2) 8)) + (state (or (match-string 4) (match-string 6))) + (name (or (match-string 5) (match-string 7))) + (new-name (match-string 8))) + (if new-name ; copy or rename + (if (eq ?C (string-to-char state)) + (ewoc-enter-last status (git-create-fileinfo 'added new-name old-perm new-perm 'copy name)) + (ewoc-enter-last status (git-create-fileinfo 'deleted name 0 0 'rename new-name)) + (ewoc-enter-last status (git-create-fileinfo 'added new-name old-perm new-perm 'rename name))) + (ewoc-enter-last status (git-create-fileinfo (git-state-code state) name old-perm new-perm)))))) + +(defun git-find-status-file (status file) + "Find a given file in the status ewoc and return its node." + (let ((node (ewoc-nth status 0))) + (while (and node (not (string= file (git-fileinfo->name (ewoc-data node))))) + (setq node (ewoc-next status node))) + node)) + +(defun git-parse-ls-files (status default-state &optional skip-existing) + "Parse the output of git-ls-files in the current buffer." + (goto-char (point-min)) + (let (infolist) + (while (re-search-forward "\\([HMRCK?]\\) \\([^\0]*\\)\0" nil t 1) + (let ((state (match-string 1)) + (name (match-string 2))) + (unless (and skip-existing (git-find-status-file status name)) + (push (git-create-fileinfo (or (git-state-code state) default-state) name) infolist)))) + (dolist (info (nreverse infolist)) + (ewoc-enter-last status info)))) + +(defun git-parse-ls-unmerged (status) + "Parse the output of git-ls-files -u in the current buffer." + (goto-char (point-min)) + (let (files) + (while (re-search-forward "[0-7]\\{6\\} [0-9a-f]\\{40\\} [123]\t\\([^\0]+\\)\0" nil t) + (let ((node (git-find-status-file status (match-string 1)))) + (when node (push (ewoc-data node) files)))) + (git-set-files-state files 'unmerged))) + +(defun git-add-status-file (state name) + "Add a new file to the status list (if not existing already) and return its node." + (unless git-status (error "Not in git-status buffer.")) + (or (git-find-status-file git-status name) + (ewoc-enter-last git-status (git-create-fileinfo state name)))) + +(defun git-marked-files () + "Return a list of all marked files, or if none a list containing just the file at cursor position." + (unless git-status (error "Not in git-status buffer.")) + (or (ewoc-collect git-status (lambda (info) (git-fileinfo->marked info))) + (list (ewoc-data (ewoc-locate git-status))))) + +(defun git-marked-files-state (&rest states) + "Return marked files that are in the specified states." + (let ((files (git-marked-files)) + result) + (dolist (info files) + (when (memq (git-fileinfo->state info) states) + (push info result))) + result)) + +(defun git-refresh-files () + "Refresh all files that need it and clear the needs-refresh flag." + (unless git-status (error "Not in git-status buffer.")) + (ewoc-map + (lambda (info) + (let ((refresh (git-fileinfo->needs-refresh info))) + (setf (git-fileinfo->needs-refresh info) nil) + refresh)) + git-status) + ; move back to goal column + (when goal-column (move-to-column goal-column))) + +(defun git-refresh-ewoc-hf (status) + "Refresh the ewoc header and footer." + (let ((branch (git-symbolic-ref "HEAD")) + (head (if (git-empty-db-p) "Nothing committed yet" + (substring (git-rev-parse "HEAD") 0 10))) + (merge-heads (git-get-merge-heads))) + (ewoc-set-hf status + (format "Directory: %s\nBranch: %s\nHead: %s%s\n" + default-directory + (if (string-match "^refs/heads/" branch) + (substring branch (match-end 0)) + branch) + head + (if merge-heads + (concat "\nMerging: " + (mapconcat (lambda (str) (substring str 0 10)) merge-heads " ")) + "")) + (if (ewoc-nth status 0) "" " No changes.")))) + +(defun git-get-filenames (files) + (mapcar (lambda (info) (git-fileinfo->name info)) files)) + +(defun git-update-index (index-file files) + "Run git-update-index on a list of files." + (let ((env (and index-file `(("GIT_INDEX_FILE" . ,index-file)))) + added deleted modified) + (dolist (info files) + (case (git-fileinfo->state info) + ('added (push info added)) + ('deleted (push info deleted)) + ('modified (push info modified)))) + (when added + (apply #'git-run-command nil env "update-index" "--add" "--" (git-get-filenames added))) + (when deleted + (apply #'git-run-command nil env "update-index" "--remove" "--" (git-get-filenames deleted))) + (when modified + (apply #'git-run-command nil env "update-index" "--" (git-get-filenames modified))))) + +(defun git-do-commit () + "Perform the actual commit using the current buffer as log message." + (interactive) + (let ((buffer (current-buffer)) + (index-file (make-temp-file "gitidx"))) + (with-current-buffer log-edit-parent-buffer + (if (git-marked-files-state 'unmerged) + (message "You cannot commit unmerged files, resolve them first.") + (unwind-protect + (let ((files (git-marked-files-state 'added 'deleted 'modified)) + head head-tree) + (unless (git-empty-db-p) + (setq head (git-rev-parse "HEAD") + head-tree (git-rev-parse "HEAD^{tree}"))) + (if files + (progn + (git-read-tree head-tree index-file) + (git-update-index nil files) ;update both the default index + (git-update-index index-file files) ;and the temporary one + (let ((tree (git-write-tree index-file))) + (if (or (not (string-equal tree head-tree)) + (yes-or-no-p "The tree was not modified, do you really want to perform an empty commit? ")) + (let ((commit (git-commit-tree buffer tree head))) + (git-update-ref "HEAD" commit head) + (condition-case nil (delete-file ".git/MERGE_HEAD") (error nil)) + (with-current-buffer buffer (erase-buffer)) + (git-set-files-state files 'uptodate) + (git-refresh-files) + (git-refresh-ewoc-hf git-status) + (message "Committed %s." commit)) + (message "Commit aborted.")))) + (message "No files to commit."))) + (delete-file index-file)))))) + + +;;;; Interactive functions +;;;; ------------------------------------------------------------ + +(defun git-mark-file () + "Mark the file that the cursor is on and move to the next one." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let* ((pos (ewoc-locate git-status)) + (info (ewoc-data pos))) + (setf (git-fileinfo->marked info) t) + (ewoc-invalidate git-status pos) + (ewoc-goto-next git-status 1))) + +(defun git-unmark-file () + "Unmark the file that the cursor is on and move to the next one." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let* ((pos (ewoc-locate git-status)) + (info (ewoc-data pos))) + (setf (git-fileinfo->marked info) nil) + (ewoc-invalidate git-status pos) + (ewoc-goto-next git-status 1))) + +(defun git-unmark-file-up () + "Unmark the file that the cursor is on and move to the previous one." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let* ((pos (ewoc-locate git-status)) + (info (ewoc-data pos))) + (setf (git-fileinfo->marked info) nil) + (ewoc-invalidate git-status pos) + (ewoc-goto-prev git-status 1))) + +(defun git-mark-all () + "Mark all files." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (ewoc-map (lambda (info) (setf (git-fileinfo->marked info) t) t) git-status) + ; move back to goal column after invalidate + (when goal-column (move-to-column goal-column))) + +(defun git-unmark-all () + "Unmark all files." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (ewoc-map (lambda (info) (setf (git-fileinfo->marked info) nil) t) git-status) + ; move back to goal column after invalidate + (when goal-column (move-to-column goal-column))) + +(defun git-toggle-all-marks () + "Toggle all file marks." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (ewoc-map (lambda (info) (setf (git-fileinfo->marked info) (not (git-fileinfo->marked info))) t) git-status) + ; move back to goal column after invalidate + (when goal-column (move-to-column goal-column))) + +(defun git-next-file (&optional n) + "Move the selection down N files." + (interactive "p") + (unless git-status (error "Not in git-status buffer.")) + (ewoc-goto-next git-status n)) + +(defun git-prev-file (&optional n) + "Move the selection up N files." + (interactive "p") + (unless git-status (error "Not in git-status buffer.")) + (ewoc-goto-prev git-status n)) + +(defun git-add-file () + "Add marked file(s) to the index cache." + (interactive) + (let ((files (git-marked-files-state 'unknown))) + (unless files + (push (ewoc-data + (git-add-status-file 'added (file-relative-name + (read-file-name "File to add: " nil nil t)))) + files)) + (apply #'git-run-command nil nil "update-index" "--info-only" "--add" "--" (git-get-filenames files)) + (git-set-files-state files 'added) + (git-refresh-files))) + +(defun git-ignore-file () + "Add marked file(s) to the ignore list." + (interactive) + (let ((files (git-marked-files-state 'unknown))) + (unless files + (push (ewoc-data + (git-add-status-file 'unknown (file-relative-name + (read-file-name "File to ignore: " nil nil t)))) + files)) + (dolist (info files) (git-append-to-ignore (git-fileinfo->name info))) + (git-set-files-state files 'ignored) + (git-refresh-files))) + +(defun git-remove-file () + "Remove the marked file(s)." + (interactive) + (let ((files (git-marked-files-state 'added 'modified 'unknown 'uptodate))) + (unless files + (push (ewoc-data + (git-add-status-file 'unknown (file-relative-name + (read-file-name "File to remove: " nil nil t)))) + files)) + (if (yes-or-no-p + (format "Remove %d file%s? " (length files) (if (> (length files) 1) "s" ""))) + (progn + (dolist (info files) + (let ((name (git-fileinfo->name info))) + (when (file-exists-p name) (delete-file name)))) + (apply #'git-run-command nil nil "update-index" "--info-only" "--remove" "--" (git-get-filenames files)) + ; remove unknown files from the list, set the others to deleted + (ewoc-filter git-status + (lambda (info files) + (not (and (memq info files) (eq (git-fileinfo->state info) 'unknown)))) + files) + (git-set-files-state files 'deleted) + (git-refresh-files) + (unless (ewoc-nth git-status 0) ; refresh header if list is empty + (git-refresh-ewoc-hf git-status))) + (message "Aborting")))) + +(defun git-revert-file () + "Revert changes to the marked file(s)." + (interactive) + (let ((files (git-marked-files)) + added modified) + (when (and files + (yes-or-no-p + (format "Revert %d file%s? " (length files) (if (> (length files) 1) "s" "")))) + (dolist (info files) + (case (git-fileinfo->state info) + ('added (push info added)) + ('deleted (push info modified)) + ('unmerged (push info modified)) + ('modified (push info modified)))) + (when added + (apply #'git-run-command nil nil "update-index" "--force-remove" "--" (git-get-filenames added)) + (git-set-files-state added 'unknown)) + (when modified + (apply #'git-run-command nil nil "checkout" "HEAD" (git-get-filenames modified)) + (git-set-files-state modified 'uptodate)) + (git-refresh-files)))) + +(defun git-resolve-file () + "Resolve conflicts in marked file(s)." + (interactive) + (let ((files (git-marked-files-state 'unmerged))) + (when files + (apply #'git-run-command nil nil "update-index" "--info-only" "--" (git-get-filenames files)) + (git-set-files-state files 'modified) + (git-refresh-files)))) + +(defun git-remove-handled () + "Remove handled files from the status list." + (interactive) + (ewoc-filter git-status + (lambda (info) + (not (or (eq (git-fileinfo->state info) 'ignored) + (eq (git-fileinfo->state info) 'uptodate))))) + (unless (ewoc-nth git-status 0) ; refresh header if list is empty + (git-refresh-ewoc-hf git-status))) + +(defun git-setup-diff-buffer (buffer) + "Setup a buffer for displaying a diff." + (with-current-buffer buffer + (diff-mode) + (goto-char (point-min)) + (setq buffer-read-only t)) + (display-buffer buffer) + (shrink-window-if-larger-than-buffer)) + +(defun git-diff-file () + "Diff the marked file(s) against HEAD." + (interactive) + (let ((files (git-marked-files))) + (git-setup-diff-buffer + (apply #'git-run-command-buffer "*git-diff*" "diff-index" "-p" "-M" "HEAD" "--" (git-get-filenames files))))) + +(defun git-diff-unmerged-file (stage) + "Diff the marked unmerged file(s) against the specified stage." + (let ((files (git-marked-files))) + (git-setup-diff-buffer + (apply #'git-run-command-buffer "*git-diff*" "diff-files" "-p" stage "--" (git-get-filenames files))))) + +(defun git-diff-file-base () + "Diff the marked unmerged file(s) against the common base file." + (interactive) + (git-diff-unmerged-file "-1")) + +(defun git-diff-file-mine () + "Diff the marked unmerged file(s) against my pre-merge version." + (interactive) + (git-diff-unmerged-file "-2")) + +(defun git-diff-file-other () + "Diff the marked unmerged file(s) against the other's pre-merge version." + (interactive) + (git-diff-unmerged-file "-3")) + +(defun git-diff-file-combined () + "Do a combined diff of the marked unmerged file(s)." + (interactive) + (git-diff-unmerged-file "-c")) + +(defun git-diff-file-idiff () + "Perform an interactive diff on the current file." + (interactive) + (error "Interactive diffs not implemented yet.")) + +(defun git-log-file () + "Display a log of changes to the marked file(s)." + (interactive) + (let* ((files (git-marked-files)) + (coding-system-for-read git-commits-coding-system) + (buffer (apply #'git-run-command-buffer "*git-log*" "rev-list" "--pretty" "HEAD" "--" (git-get-filenames files)))) + (with-current-buffer buffer + ; (git-log-mode) FIXME: implement log mode + (goto-char (point-min)) + (setq buffer-read-only t)) + (display-buffer buffer))) + +(defun git-log-edit-files () + "Return a list of marked files for use in the log-edit buffer." + (with-current-buffer log-edit-parent-buffer + (git-get-filenames (git-marked-files-state 'added 'deleted 'modified)))) + +(defun git-commit-file () + "Commit the marked file(s), asking for a commit message." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let ((buffer (get-buffer-create "*git-commit*")) + (merge-heads (git-get-merge-heads)) + (dir default-directory)) + (with-current-buffer buffer + (when (eq 0 (buffer-size)) + (cd dir) + (erase-buffer) + (insert + (propertize + (format "Author: %s <%s>\n%s" + (git-get-committer-name) (git-get-committer-email) + (if merge-heads + (format "Parent: %s\n%s\n" + (git-rev-parse "HEAD") + (mapconcat (lambda (str) (concat "Parent: " str)) merge-heads "\n")) + "")) + 'face 'git-header-face) + (propertize git-log-msg-separator 'face 'git-separator-face) + "\n") + (when (and merge-heads (file-readable-p ".git/MERGE_MSG")) + (insert-file-contents ".git/MERGE_MSG")))) + (log-edit #'git-do-commit nil #'git-log-edit-files buffer))) + +(defun git-find-file () + "Visit the current file in its own buffer." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let ((info (ewoc-data (ewoc-locate git-status)))) + (find-file (git-fileinfo->name info)) + (when (eq 'unmerged (git-fileinfo->state info)) + (smerge-mode)))) + +(defun git-find-file-imerge () + "Visit the current file in interactive merge mode." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let ((info (ewoc-data (ewoc-locate git-status)))) + (find-file (git-fileinfo->name info)) + (smerge-ediff))) + +(defun git-view-file () + "View the current file in its own buffer." + (interactive) + (unless git-status (error "Not in git-status buffer.")) + (let ((info (ewoc-data (ewoc-locate git-status)))) + (view-file (git-fileinfo->name info)))) + +(defun git-refresh-status () + "Refresh the git status buffer." + (interactive) + (let* ((status git-status) + (pos (ewoc-locate status)) + (cur-name (and pos (git-fileinfo->name (ewoc-data pos))))) + (unless status (error "Not in git-status buffer.")) + (git-clear-status status) + (git-run-command nil nil "update-index" "--info-only" "--refresh") + (if (git-empty-db-p) + ; we need some special handling for an empty db + (with-temp-buffer + (git-run-command t nil "ls-files" "-z" "-t" "-c") + (git-parse-ls-files status 'added)) + (with-temp-buffer + (git-run-command t nil "diff-index" "-z" "-M" "HEAD") + (git-parse-status status))) + (with-temp-buffer + (git-run-command t nil "ls-files" "-z" "-u") + (git-parse-ls-unmerged status)) + (when (file-readable-p ".git/info/exclude") + (with-temp-buffer + (git-run-command t nil "ls-files" "-z" "-t" "-o" + "--exclude-from=.git/info/exclude" + (concat "--exclude-per-directory=" git-per-dir-ignore-file)) + (git-parse-ls-files status 'unknown))) + (git-refresh-files) + (git-refresh-ewoc-hf status) + ; move point to the current file name if any + (let ((node (and cur-name (git-find-status-file status cur-name)))) + (when node (ewoc-goto-node status node))))) + +(defun git-status-quit () + "Quit git-status mode." + (interactive) + (bury-buffer)) + +;;;; Major Mode +;;;; ------------------------------------------------------------ + +(defvar git-status-mode-hook nil + "Run after `git-status-mode' is setup.") + +(defvar git-status-mode-map nil + "Keymap for git major mode.") + +(defvar git-status nil + "List of all files managed by the git-status mode.") + +(unless git-status-mode-map + (let ((map (make-keymap)) + (diff-map (make-sparse-keymap))) + (suppress-keymap map) + (define-key map " " 'git-next-file) + (define-key map "a" 'git-add-file) + (define-key map "c" 'git-commit-file) + (define-key map "d" diff-map) + (define-key map "=" 'git-diff-file) + (define-key map "f" 'git-find-file) + (define-key map [RET] 'git-find-file) + (define-key map "g" 'git-refresh-status) + (define-key map "i" 'git-ignore-file) + (define-key map "l" 'git-log-file) + (define-key map "m" 'git-mark-file) + (define-key map "M" 'git-mark-all) + (define-key map "n" 'git-next-file) + (define-key map "p" 'git-prev-file) + (define-key map "q" 'git-status-quit) + (define-key map "r" 'git-remove-file) + (define-key map "R" 'git-resolve-file) + (define-key map "T" 'git-toggle-all-marks) + (define-key map "u" 'git-unmark-file) + (define-key map "U" 'git-revert-file) + (define-key map "v" 'git-view-file) + (define-key map "x" 'git-remove-handled) + (define-key map "\C-?" 'git-unmark-file-up) + (define-key map "\M-\C-?" 'git-unmark-all) + ; the diff submap + (define-key diff-map "b" 'git-diff-file-base) + (define-key diff-map "c" 'git-diff-file-combined) + (define-key diff-map "=" 'git-diff-file) + (define-key diff-map "e" 'git-diff-file-idiff) + (define-key diff-map "E" 'git-find-file-imerge) + (define-key diff-map "m" 'git-diff-file-mine) + (define-key diff-map "o" 'git-diff-file-other) + (setq git-status-mode-map map))) + +;; git mode should only run in the *git status* buffer +(put 'git-status-mode 'mode-class 'special) + +(defun git-status-mode () + "Major mode for interacting with Git. +Commands: +\\{git-status-mode-map}" + (kill-all-local-variables) + (buffer-disable-undo) + (setq mode-name "git status" + major-mode 'git-status-mode + goal-column 17 + buffer-read-only t) + (use-local-map git-status-mode-map) + (let ((buffer-read-only nil)) + (erase-buffer) + (let ((status (ewoc-create 'git-fileinfo-prettyprint "" ""))) + (set (make-local-variable 'git-status) status)) + (run-hooks 'git-status-mode-hook))) + +(defun git-status (dir) + "Entry point into git-status mode." + (interactive "DSelect directory: ") + (setq dir (git-get-top-dir dir)) + (if (file-directory-p (concat (file-name-as-directory dir) ".git")) + (let ((buffer (create-file-buffer (expand-file-name "*git-status*" dir)))) + (switch-to-buffer buffer) + (git-status-mode) + (cd dir) + (git-refresh-status) + (goto-char (point-min))) + (message "%s is not a git working tree." dir))) + +(provide 'git) +;;; git.el ends here 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.perl b/contrib/git-svn/git-svn.perl new file mode 100755 index 0000000000..0b7416526d --- /dev/null +++ b/contrib/git-svn/git-svn.perl @@ -0,0 +1,967 @@ +#!/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 + $SVN_URL $SVN_INFO $SVN_WC + $GIT_SVN_INDEX $GIT_SVN + $GIT_DIR $REV_DIR/; +$AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; +$VERSION = '0.10.0'; +$GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git"; +$GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn'; +$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index"; +$ENV{GIT_DIR} ||= $GIT_DIR; +$SVN_URL = undef; +$REV_DIR = "$GIT_DIR/$GIT_SVN/revs"; +$SVN_WC = "$GIT_DIR/$GIT_SVN/tree"; + +# make sure the svn binary gives consistent output between locales and TZs: +$ENV{TZ} = 'UTC'; +$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. +# use eval { require SVN::... } to make it lazy load +use Carp qw/croak/; +use IO::File qw//; +use File::Basename qw/dirname basename/; +use File::Path qw/mkpath/; +use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; +use File::Spec qw//; +use POSIX qw/strftime/; +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, + $_find_copies_harder, $_l, $_version); + +GetOptions( 'revision|r=s' => \$_revision, + 'no-ignore-externals' => \$_no_ignore_ext, + 'stdin|' => \$_stdin, + 'edit|e' => \$_edit, + 'rmdir' => \$_rmdir, + 'help|H|h' => \$_help, + '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)"], + commit => [ \&commit, "Commit git revisions to SVN" ], + 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings" ], + rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)" ], + help => [ \&usage, "Show help" ], +); +my $cmd; +for (my $i = 0; $i < @ARGV; $i++) { + if (defined $cmd{$ARGV[$i]}) { + $cmd = $ARGV[$i]; + splice @ARGV, $i, 1; + last; + } +}; + +# we may be called as git-svn-(command), or git-svn(command). +foreach (keys %cmd) { + if (/git\-svn\-?($_)(?:\.\w+)?$/) { + $cmd = $1; + last; + } +} +usage(0) if $_help; +version() if $_version; +usage(1) unless (defined $cmd); +svn_check_ignore_externals(); +$cmd{$cmd}->[0]->(@ARGV); +exit 0; + +####################### primary functions ###################### +sub usage { + my $exit = shift || 0; + my $fd = $exit ? \*STDERR : \*STDOUT; + print $fd <<""; +git-svn - bidirectional operations between a single Subversion tree and git +Usage: $0 <command> [options] [arguments]\n +Available commands: + + foreach (sort keys %cmd) { + print $fd ' ',pack('A10',$_),$cmd{$_}->[1],"\n"; + } + print $fd <<""; +\nGIT_SVN_ID may be set in the environment to an arbitrary identifier if +you're tracking multiple SVN branches/repositories in one git repository +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; + my $newest_rev = 0; + + my $pid = open(my $rev_list,'-|'); + defined $pid or croak $!; + if ($pid == 0) { + exec("git-rev-list","$GIT_SVN-HEAD") or croak $!; + } + my $first; + while (<$rev_list>) { + chomp; + my $c = $_; + croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o; + my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`); + next if (!@commit); # skip merges + my $id = $commit[$#commit]; + my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) + \s([a-f\d\-]+)$/x); + if (!$rev || !$uuid || !$url) { + # some of the original repositories I made had + # indentifiers like this: + ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+) + \@([a-f\d\-]+)/x); + if (!$rev || !$uuid) { + croak "Unable to extract revision or UUID from ", + "$c, $id\n"; + } + } + print "r$rev = $c\n"; + unless (defined $first) { + if (!$SVN_URL && !$url) { + croak "SVN repository location required: $url\n"; + } + $SVN_URL ||= $url; + $repo_uuid = setup_git_svn(); + $first = $rev; + } + if ($uuid ne $repo_uuid) { + croak "Repository UUIDs do not match!\ngot: $uuid\n", + "expected: $repo_uuid\n"; + } + assert_revision_eq_or_unknown($rev, $c); + sys('git-update-ref',"$GIT_SVN/revs/$rev",$c); + $newest_rev = $rev if ($rev > $newest_rev); + } + close $rev_list or croak $?; + if (!chdir $SVN_WC) { + my @svn_co = ('svn','co',"-r$first"); + push @svn_co, '--ignore-externals' unless $_no_ignore_ext; + sys(@svn_co, $SVN_URL, $SVN_WC); + chdir $SVN_WC or croak $!; + } + + $pid = fork; + defined $pid or croak $!; + if ($pid == 0) { + my @svn_up = qw(svn up); + push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + sys(@svn_up,"-r$newest_rev"); + $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; + git_addremove(); + exec('git-write-tree'); + } + waitpid $pid, 0; +} + +sub init { + $SVN_URL = shift or croak "SVN repository location required\n"; + unless (-d $GIT_DIR) { + sys('git-init-db'); + } + setup_git_svn(); +} + +sub fetch { + my (@parents) = @_; + $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); + my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL); + unless ($_revision) { + $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD'; + } + push @log_args, "-r$_revision"; + push @log_args, '--stop-on-copy' unless $_no_stop_copy; + + my $svn_log = svn_log_raw(@log_args); + @$svn_log = sort { $a->{revision} <=> $b->{revision} } @$svn_log; + + my $base = shift @$svn_log or croak "No base revision!\n"; + my $last_commit = undef; + unless (-d $SVN_WC) { + my @svn_co = ('svn','co',"-r$base->{revision}"); + push @svn_co,'--ignore-externals' unless $_no_ignore_ext; + sys(@svn_co, $SVN_URL, $SVN_WC); + chdir $SVN_WC or croak $!; + $last_commit = git_commit($base, @parents); + unless (-f "$GIT_DIR/refs/heads/master") { + sys(qw(git-update-ref refs/heads/master),$last_commit); + } + assert_svn_wc_clean($base->{revision}, $last_commit); + } else { + chdir $SVN_WC or croak $!; + $last_commit = file_to_s("$REV_DIR/$base->{revision}"); + } + my @svn_up = qw(svn up); + push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + my $last_rev = $base->{revision}; + foreach my $log_msg (@$svn_log) { + assert_svn_wc_clean($last_rev, $last_commit); + $last_rev = $log_msg->{revision}; + sys(@svn_up,"-r$last_rev"); + $last_commit = git_commit($log_msg, $last_commit, @parents); + } + assert_svn_wc_clean($last_rev, $last_commit); + return pop @$svn_log; +} + +sub commit { + my (@commits) = @_; + if ($_stdin || !@commits) { + print "Reading from stdin...\n"; + @commits = (); + while (<STDIN>) { + if (/\b([a-f\d]{6,40})\b/) { + unshift @commits, $1; + } + } + } + my @revs; + 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; + + fetch(); + chdir $SVN_WC or croak $!; + my $svn_current_rev = svn_info('.')->{'Last Changed Rev'}; + foreach my $c (@revs) { + print "Committing $c\n"; + 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"; + +} + +sub show_ignore { + require File::Find or die $!; + my $exclude_file = "$GIT_DIR/info/exclude"; + open my $fh, '<', $exclude_file or croak $!; + chomp(my @excludes = (<$fh>)); + close $fh or croak $!; + + $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); + chdir $SVN_WC or croak $!; + my %ign; + File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ + s#^\./##; + @{$ign{$_}} = safe_qx(qw(svn propget svn:ignore),$_); + }}, no_chdir=>1},'.'); + + print "\n# /\n"; + foreach (@{$ign{'.'}}) { print '/',$_ if /\S/ } + delete $ign{'.'}; + foreach my $i (sort keys %ign) { + print "\n# ",$i,"\n"; + foreach (@{$ign{$i}}) { print '/',$i,'/',$_ if /\S/ } + } +} + +########################### utility functions ######################### + +sub setup_git_svn { + defined $SVN_URL or croak "SVN repository location required\n"; + unless (-d $GIT_DIR) { + croak "GIT_DIR=$GIT_DIR does not exist!\n"; + } + mkpath(["$GIT_DIR/$GIT_SVN"]); + mkpath(["$GIT_DIR/$GIT_SVN/info"]); + mkpath([$REV_DIR]); + s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url"); + my $uuid = svn_info($SVN_URL)->{'Repository UUID'} or + croak "Repository UUID unreadable\n"; + s_to_file($uuid,"$GIT_DIR/$GIT_SVN/info/uuid"); + + open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!; + print $fd '.svn',"\n"; + close $fd or croak $!; + return $uuid; +} + +sub assert_svn_wc_clean { + my ($svn_rev, $treeish) = @_; + croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/); + 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", + $svn_info->{'Last Changed Rev'},"\n"; + } + my @status = grep(!/^Performing status on external/,(`svn status`)); + @status = grep(!/^\s*$/,@status); + if (scalar @status) { + print STDERR "Tree ($SVN_WC) is not clean:\n"; + print STDERR $_ foreach @status; + croak; + } + assert_tree($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"; + } +} + +sub parse_diff_tree { + my $diff_fh = shift; + local $/ = "\0"; + my $state = 'meta'; + my @mods; + while (<$diff_fh>) { + chomp $_; # this gets rid of the trailing "\0" + if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s + $sha1\s($sha1)\s([MTCRAD])\d*$/xo) { + push @mods, { mode_a => $1, mode_b => $2, + sha1_b => $3, chg => $4 }; + if ($4 =~ /^(?:C|R)$/) { + $state = 'file_a'; + } else { + $state = 'file_b'; + } + } elsif ($state eq 'file_a') { + my $x = $mods[$#mods] or croak "Empty array\n"; + if ($x->{chg} !~ /^(?:C|R)$/) { + croak "Error parsing $_, $x->{chg}\n"; + } + $x->{file_a} = $_; + $state = 'file_b'; + } elsif ($state eq 'file_b') { + my $x = $mods[$#mods] or croak "Empty array\n"; + if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) { + croak "Error parsing $_, $x->{chg}\n"; + } + if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) { + croak "Error parsing $_, $x->{chg}\n"; + } + $x->{file_b} = $_; + $state = 'meta'; + } else { + croak "Error parsing $_\n"; + } + } + close $diff_fh or croak $!; + + return \@mods; +} + +sub svn_check_prop_executable { + my $m = shift; + return if -l $m->{file_b}; + if ($m->{mode_b} =~ /755$/) { + chmod((0755 &~ umask),$m->{file_b}) or croak $!; + if ($m->{mode_a} !~ /755$/) { + sys(qw(svn propset svn:executable 1), $m->{file_b}); + } + -x $m->{file_b} or croak "$m->{file_b} is not executable!\n"; + } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { + sys(qw(svn propdel svn:executable), $m->{file_b}); + chmod((0644 &~ umask),$m->{file_b}) or croak $!; + -x $m->{file_b} and croak "$m->{file_b} is executable!\n"; + } +} + +sub svn_ensure_parent_path { + my $dir_b = dirname(shift); + svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir); + mkpath([$dir_b]) unless (-d $dir_b); + sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn"); +} + +sub precommit_check { + my $mods = shift; + my (%rm_file, %rmdir_check, %added_check); + + my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 ); + foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { + if ($m->{chg} eq 'R') { + if (-d $m->{file_b}) { + err_dir_to_file("$m->{file_a} => $m->{file_b}"); + } + # dir/$file => dir/file/$file + my $dirname = dirname($m->{file_b}); + while ($dirname ne File::Spec->curdir) { + if ($dirname ne $m->{file_a}) { + $dirname = dirname($dirname); + next; + } + err_file_to_dir("$m->{file_a} => $m->{file_b}"); + } + # baz/zzz => baz (baz is a file) + $dirname = dirname($m->{file_a}); + while ($dirname ne File::Spec->curdir) { + if ($dirname ne $m->{file_b}) { + $dirname = dirname($dirname); + next; + } + err_dir_to_file("$m->{file_a} => $m->{file_b}"); + } + } + if ($m->{chg} =~ /^(D|R)$/) { + my $t = $1 eq 'D' ? 'file_b' : 'file_a'; + $rm_file{ $m->{$t} } = 1; + my $dirname = dirname( $m->{$t} ); + my $basename = basename( $m->{$t} ); + $rmdir_check{$dirname}->{$basename} = 1; + } elsif ($m->{chg} =~ /^(?:A|C)$/) { + if (-d $m->{file_b}) { + err_dir_to_file($m->{file_b}); + } + my $dirname = dirname( $m->{file_b} ); + my $basename = basename( $m->{file_b} ); + $added_check{$dirname}->{$basename} = 1; + while ($dirname ne File::Spec->curdir) { + if ($rm_file{$dirname}) { + err_file_to_dir($m->{file_b}); + } + $dirname = dirname $dirname; + } + } + } + return (\%rmdir_check, \%added_check); + + sub err_dir_to_file { + my $file = shift; + print STDERR "Node change from directory to file ", + "is not supported by Subversion: ",$file,"\n"; + exit 1; + } + sub err_file_to_dir { + my $file = shift; + print STDERR "Node change from file to directory ", + "is not supported by Subversion: ",$file,"\n"; + exit 1; + } +} + +sub svn_checkout_tree { + my ($svn_rev, $treeish) = @_; + my $from = file_to_s("$REV_DIR/$svn_rev"); + assert_svn_wc_clean($svn_rev,$from); + print "diff-tree '$from' '$treeish'\n"; + my $pid = open my $diff_fh, '-|'; + defined $pid or croak $!; + if ($pid == 0) { + my @diff_tree = qw(git-diff-tree -z -r -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 $mods; + } + my ($rm, $add) = precommit_check($mods); + + my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); + foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { + if ($m->{chg} eq 'C') { + svn_ensure_parent_path( $m->{file_b} ); + sys(qw(svn cp), $m->{file_a}, $m->{file_b}); + apply_mod_line_blob($m); + svn_check_prop_executable($m); + } elsif ($m->{chg} eq 'D') { + sys(qw(svn rm --force), $m->{file_b}); + } elsif ($m->{chg} eq 'R') { + svn_ensure_parent_path( $m->{file_b} ); + sys(qw(svn mv --force), $m->{file_a}, $m->{file_b}); + apply_mod_line_blob($m); + svn_check_prop_executable($m); + } elsif ($m->{chg} eq 'M') { + apply_mod_line_blob($m); + svn_check_prop_executable($m); + } elsif ($m->{chg} eq 'T') { + sys(qw(svn rm --force),$m->{file_b}); + apply_mod_line_blob($m); + sys(qw(svn add --force), $m->{file_b}); + svn_check_prop_executable($m); + } elsif ($m->{chg} eq 'A') { + svn_ensure_parent_path( $m->{file_b} ); + apply_mod_line_blob($m); + sys(qw(svn add --force), $m->{file_b}); + svn_check_prop_executable($m); + } else { + croak "Invalid chg: $m->{chg}\n"; + } + } + + assert_tree($treeish); + if ($_rmdir) { # remove empty directories + handle_rmdir($rm, $add); + } + assert_tree($treeish); + return $mods; +} + +# svn ls doesn't work with respect to the current working tree, but what's +# in the repository. There's not even an option for it... *sigh* +# (added files don't show up and removed files remain in the ls listing) +sub svn_ls_current { + my ($dir, $rm, $add) = @_; + chomp(my @ls = safe_qx('svn','ls',$dir)); + my @ret = (); + foreach (@ls) { + s#/$##; # trailing slashes are evil + push @ret, $_ unless $rm->{$dir}->{$_}; + } + if (exists $add->{$dir}) { + push @ret, keys %{$add->{$dir}}; + } + return \@ret; +} + +sub handle_rmdir { + my ($rm, $add) = @_; + + foreach my $dir (sort {length $b <=> length $a} keys %$rm) { + my $ls = svn_ls_current($dir, $rm, $add); + next if (scalar @$ls); + sys(qw(svn rm --force),$dir); + + my $dn = dirname $dir; + $rm->{ $dn }->{ basename $dir } = 1; + $ls = svn_ls_current($dn, $rm, $add); + while (scalar @$ls == 0 && $dn ne File::Spec->curdir) { + sys(qw(svn rm --force),$dn); + $dir = basename $dn; + $dn = dirname $dn; + $rm->{ $dn }->{ $dir } = 1; + $ls = svn_ls_current($dn, $rm, $add); + } + } +} + +sub svn_commit_tree { + my ($svn_rev, $commit) = @_; + my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$"; + my %log_msg = ( msg => '' ); + open my $msg, '>', $commit_msg or croak $!; + + chomp(my $type = `git-cat-file -t $commit`); + if ($type eq 'commit') { + my $pid = open my $msg_fh, '-|'; + defined $pid or croak $!; + + if ($pid == 0) { + exec(qw(git-cat-file commit), $commit) or croak $!; + } + my $in_msg = 0; + while (<$msg_fh>) { + if (!$in_msg) { + $in_msg = 1 if (/^\s*$/); + } else { + $log_msg{msg} .= $_; + print $msg $_ or croak $!; + } + } + close $msg_fh or croak $!; + } + close $msg or croak $!; + + if ($_edit || ($type eq 'tree')) { + my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi'; + system($editor, $commit_msg); + } + my @ci_output = safe_qx(qw(svn commit -F),$commit_msg); + my ($committed) = grep(/^Committed revision \d+\./,@ci_output); + unlink $commit_msg; + defined $committed or croak + "Commit output failed to parse committed revision!\n", + join("\n",@ci_output),"\n"; + my ($rev_committed) = ($committed =~ /^Committed revision (\d+)\./); + + my @svn_up = qw(svn up); + push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + if ($rev_committed == ($svn_rev + 1)) { + push @svn_up, "-r$rev_committed"; + sys(@svn_up); + my $info = svn_info('.'); + my $date = $info->{'Last Changed Date'} or die "Missing date\n"; + if ($info->{'Last Changed Rev'} != $rev_committed) { + croak "$info->{'Last Changed Rev'} != $rev_committed\n" + } + my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ + /(\d{4})\-(\d\d)\-(\d\d)\s + (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) + or croak "Failed to parse date: $date\n"; + $log_msg{date} = "$tz $Y-$m-$d $H:$M:$S"; + $log_msg{author} = $info->{'Last Changed Author'}; + $log_msg{revision} = $rev_committed; + $log_msg{msg} .= "\n"; + my $parent = file_to_s("$REV_DIR/$svn_rev"); + git_commit(\%log_msg, $parent, $commit); + return $rev_committed; + } + # resync immediately + push @svn_up, "-r$svn_rev"; + sys(@svn_up); + return fetch("$rev_committed=$commit")->{revision}; +} + +sub svn_log_raw { + my (@log_args) = @_; + my $pid = open my $log_fh,'-|'; + defined $pid or croak $!; + + if ($pid == 0) { + exec (qw(svn log), @log_args) or croak $! + } + + my @svn_log; + 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, $lines) = split(/\s*\|\s*/, $_, 3); + ($lines) = ($lines =~ /(\d+)/); + my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ + /(\d{4})\-(\d\d)\-(\d\d)\s + (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) + or croak "Failed to parse date: $date\n"; + my %log_msg = ( revision => $rev, + date => "$tz $Y-$m-$d $H:$M:$S", + author => $author, + lines => $lines, + msg => '' ); + push @svn_log, \%log_msg; + $state = 'msg_start'; + next; + } + # skip the first blank line of the message: + if ($state eq 'msg_start' && /^$/) { + $state = 'msg'; + } elsif ($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"; + } + } + } + close $log_fh or croak $?; + return \@svn_log; +} + +sub svn_info { + my $url = shift || $SVN_URL; + + my $pid = open my $info_fh, '-|'; + defined $pid or croak $!; + + if ($pid == 0) { + exec(qw(svn info),$url) or croak $!; + } + + my $ret = {}; + # only single-lines seem to exist in svn info output + while (<$info_fh>) { + chomp $_; + if (m#^([^:]+)\s*:\s*(\S.*)$#) { + $ret->{$1} = $2; + push @{$ret->{-order}}, $1; + } + } + close $info_fh or croak $!; + return $ret; +} + +sub sys { system(@_) == 0 or croak $? } + +sub git_addremove { + system( "git-diff-files --name-only -z ". + " | git-update-index --remove -z --stdin && ". + "git-ls-files -z --others ". + "'--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude'". + " | git-update-index --add -z --stdin" + ) == 0 or croak $? +} + +sub s_to_file { + my ($str, $file, $mode) = @_; + open my $fd,'>',$file or croak $!; + print $fd $str,"\n" or croak $!; + close $fd or croak $!; + chmod ($mode &~ umask, $file) if (defined $mode); +} + +sub file_to_s { + my $file = shift; + open my $fd,'<',$file or croak "$!: file: $file\n"; + local $/; + my $ret = <$fd>; + close $fd or croak $!; + $ret =~ s/\s*$//s; + return $ret; +} + +sub assert_revision_unknown { + my $revno = shift; + if (-f "$REV_DIR/$revno") { + croak "$REV_DIR/$revno already exists! ", + "Why are we refetching it?"; + } +} + +sub assert_revision_eq_or_unknown { + my ($revno, $commit) = @_; + if (-f "$REV_DIR/$revno") { + my $current = file_to_s("$REV_DIR/$revno"); + if ($commit ne $current) { + croak "$REV_DIR/$revno already exists!\n", + "current: $current\nexpected: $commit\n"; + } + return; + } +} + +sub git_commit { + my ($log_msg, @parents) = @_; + assert_revision_unknown($log_msg->{revision}); + my $out_fh = IO::File->new_tmpfile or croak $!; + my $info = svn_info('.'); + my $uuid = $info->{'Repository UUID'}; + defined $uuid or croak "Unable to get Repository UUID\n"; + + # commit parents can be conditionally bound to a particular + # svn revision via: "svn_revno=commit_sha1", filter them out here: + my @exec_parents; + foreach my $p (@parents) { + next unless defined $p; + if ($p =~ /^(\d+)=($sha1_short)$/o) { + if ($1 == $log_msg->{revision}) { + push @exec_parents, $2; + } + } else { + push @exec_parents, $p if $p =~ /$sha1_short/o; + } + } + + my $pid = fork; + defined $pid or croak $!; + if ($pid == 0) { + $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; + git_addremove(); + chomp(my $tree = `git-write-tree`); + croak if $?; + my $msg_fh = IO::File->new_tmpfile or croak $!; + print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ", + "$SVN_URL\@$log_msg->{revision}", + " $uuid\n" or croak $!; + $msg_fh->flush == 0 or croak $!; + seek $msg_fh, 0, 0 or croak $!; + + $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = + $log_msg->{author}; + $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = + $log_msg->{author}."\@$uuid"; + $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = + $log_msg->{date}; + my @exec = ('git-commit-tree',$tree); + push @exec, '-p', $_ foreach @exec_parents; + open STDIN, '<&', $msg_fh or croak $!; + open STDOUT, '>&', $out_fh or croak $!; + exec @exec or croak $!; + } + waitpid($pid,0); + croak if $?; + + $out_fh->flush == 0 or croak $!; + seek $out_fh, 0, 0 or croak $!; + chomp(my $commit = do { local $/; <$out_fh> }); + if ($commit !~ /^$sha1$/o) { + croak "Failed to commit, invalid sha1: $commit\n"; + } + my @update_ref = ('git-update-ref',"refs/heads/$GIT_SVN-HEAD",$commit); + if (my $primary_parent = shift @exec_parents) { + push @update_ref, $primary_parent; + } + sys(@update_ref); + sys('git-update-ref',"$GIT_SVN/revs/$log_msg->{revision}",$commit); + print "r$log_msg->{revision} = $commit\n"; + 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 $!; +} + +sub blob_to_file { + my ($blob, $file) = @_; + defined $file or croak "\$file not defined!\n"; + croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; + if (-l $file || -f _) { + unlink $file or croak $!; + } + + open my $blob_fh, '>', $file or croak "$!: $file\n"; + my $pid = fork; + defined $pid or croak $!; + + if ($pid == 0) { + open STDOUT, '>&', $blob_fh or croak $!; + exec('git-cat-file','blob',$blob); + } + waitpid $pid, 0; + croak $? if $?; + + close $blob_fh or croak $!; +} + +sub safe_qx { + my $pid = open my $child, '-|'; + defined $pid or croak $!; + if ($pid == 0) { + exec(@_) or croak $?; + } + my @ret = (<$child>); + close $child or croak $?; + die $? if $?; # just in case close didn't error out + return wantarray ? @ret : join('',@ret); +} + +sub svn_check_ignore_externals { + return if $_no_ignore_ext; + unless (grep /ignore-externals/,(safe_qx(qw(svn co -h)))) { + print STDERR "W: Installed svn version does not support ", + "--ignore-externals\n"; + $_no_ignore_ext = 1; + } +} +__END__ + +Data structures: + +@svn_log = array of log_msg hashes + +$log_msg hash +{ + msg => 'whitespace-formatted log entry +', # trailing newline is preserved + revision => '8', # integer + date => '2004-02-24T17:01:44.108345Z', # commit date + author => 'committer name' +}; + + +@mods = array of diff-index line hashes, each element represents one line + of diff-index output + +diff-index line ($m hash) +{ + mode_a => first column of diff-index output, no leading ':', + mode_b => second column of diff-index output, + sha1_b => sha1sum of the final blob, + chg => change type [MCRAD], + file_a => original file name of a file (iff chg is 'C' or 'R') + file_b => new/current file name of a file (any chg) +} +; diff --git a/contrib/git-svn/git-svn.txt b/contrib/git-svn/git-svn.txt new file mode 100644 index 0000000000..b29073997c --- /dev/null +++ b/contrib/git-svn/git-svn.txt @@ -0,0 +1,236 @@ +git-svn(1) +========== + +NAME +---- +git-svn - bidirectional operation between a single Subversion branch and git + +SYNOPSIS +-------- +'git-svn' <command> [options] [arguments] + +DESCRIPTION +----------- +git-svn is a simple conduit for changesets between a single Subversion +branch and git. + +git-svn is not to be confused with git-svnimport. The were designed +with very different goals in mind. + +git-svn is designed for an individual developer who wants a +bidirectional flow of changesets between a single branch in Subversion +and an arbitrary number of branches in git. git-svnimport is designed +for read-only operation on repositories that match a particular layout +(albeit the recommended one by SVN developers). + +For importing svn, git-svnimport is potentially more powerful when +operating on repositories organized under the recommended +trunk/branch/tags structure, and should be faster, too. + +git-svn completely ignores the very limited view of branching that +Subversion has. This allows git-svn to be much easier to use, +especially on repositories that are not organized in a manner that +git-svnimport is designed for. + +COMMANDS +-------- +init:: + Creates an empty git repository with additional metadata + directories for git-svn. The SVN_URL must be specified + at this point. + +fetch:: + Fetch unfetched revisions from the SVN_URL we are tracking. + refs/heads/git-svn-HEAD will be updated to the latest revision. + + Note: You should never attempt to modify the git-svn-HEAD branch + outside of git-svn. Instead, create a branch from git-svn-HEAD + and work on that branch. Use the 'commit' command (see below) + to write git commits back to git-svn-HEAD. + +commit:: + Commit specified commit or tree objects to SVN. This relies on + your imported fetch data being up-to-date. This makes + absolutely no attempts to do patching when committing to SVN, it + simply overwrites files with those specified in the tree or + commit. All merging is assumed to have taken place + independently of git-svn functions. + +rebuild:: + Not a part of daily usage, but this is a useful command if + you've just cloned a repository (using git-clone) that was + tracked with git-svn. Unfortunately, git-clone does not clone + git-svn metadata and the svn working tree that git-svn uses for + its operations. This rebuilds the metadata so git-svn can + resume fetch operations. SVN_URL may be optionally specified if + the directory/repository you're tracking has moved or changed + protocols. + +show-ignore:: + Recursively finds and lists the svn:ignore property on + directories. The output is suitable for appending to + the $GIT_DIR/info/exclude file. + +OPTIONS +------- +-r <ARG>:: +--revision <ARG>:: + Only used with the 'fetch' command. + + Takes any valid -r<argument> svn would accept and passes it + directly to svn. -r<ARG1>:<ARG2> ranges and "{" DATE "}" syntax + is also supported. This is passed directly to svn, see svn + documentation for more details. + + This can allow you to make partial mirrors when running fetch. + +-:: +--stdin:: + Only used with the 'commit' command. + + Read a list of commits from stdin and commit them in reverse + order. Only the leading sha1 is read from each line, so + git-rev-list --pretty=oneline output can be used. + +--rmdir:: + Only used with the 'commit' command. + + Remove directories from the SVN tree if there are no files left + behind. SVN can version empty directories, and they are not + removed by default if there are no files left in them. git + cannot version empty directories. Enabling this flag will make + the commit to SVN act like git. + +-e:: +--edit:: + Only used with the 'commit' command. + + Edit the commit message before committing to SVN. This is off by + default for objects that are commits, and forced on when committing + tree objects. + +-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:: + Only used with the 'fetch' and 'rebuild' command. + + By default, git-svn passes --ignore-externals to svn to avoid + fetching svn:external trees into git. Pass this flag to enable + externals tracking directly via git. + + Versions of svn that do not support --ignore-externals are + automatically detected and this flag will be automatically + enabled for them. + + Otherwise, do not enable this flag unless you know what you're + doing. + +--no-stop-on-copy:: + Only used with the 'fetch' command. + + By default, git-svn passes --stop-on-copy to avoid dealing with + the copied/renamed branch directory problem entirely. A + copied/renamed branch is the result of a <SVN_URL> being created + in the past from a different source. These are problematic to + deal with even when working purely with svn if you work inside + subdirectories. + + Do not use this flag unless you know exactly what you're getting + yourself into. You have been warned. + +Examples +~~~~~~~~ + +Tracking and contributing to an Subversion managed-project: + +# Initialize a tree (like git init-db):: + git-svn init http://svn.foo.org/project/trunk +# Fetch remote revisions:: + git-svn fetch +# Create your own branch to hack on:: + git checkout -b my-branch git-svn-HEAD +# Commit only the git commits you want to SVN:: + git-svn commit <tree-ish> [<tree-ish_2> ...] +# Commit all the git commits from my-branch that don't exist in SVN:: + git-svn commit git-svn-HEAD..my-branch +# Something is committed to SVN, pull the latest into your branch:: + git-svn fetch && git pull . git-svn-HEAD +# Append svn:ignore settings to the default git exclude file: + git-svn show-ignore >> .git/info/exclude + +DESIGN PHILOSOPHY +----------------- +Merge tracking in Subversion is lacking and doing branched development +with Subversion is cumbersome as a result. git-svn completely forgoes +any automated merge/branch tracking on the Subversion side and leaves it +entirely up to the user on the git side. It's simply not worth it to do +a useful translation when the the original signal is weak. + +TRACKING MULTIPLE REPOSITORIES OR BRANCHES +------------------------------------------ +This is for advanced users, most users should ignore this section. + +Because git-svn does not care about relationships between different +branches or directories in a Subversion repository, git-svn has a simple +hack to allow it to track an arbitrary number of related _or_ unrelated +SVN repositories via one git repository. Simply set the GIT_SVN_ID +environment variable to a name other other than "git-svn" (the default) +and git-svn will ignore the contents of the $GIT_DIR/git-svn directory +and instead do all of its work in $GIT_DIR/$GIT_SVN_ID for that +invocation. The interface branch will be $GIT_SVN_ID-HEAD, instead of +git-svn-HEAD. Any $GIT_SVN_ID-HEAD branch should never be modified +by the user outside of git-svn commands. + +ADDITIONAL FETCH ARGUMENTS +-------------------------- +This is for advanced users, most users should ignore this section. + +Unfetched SVN revisions may be imported as children of existing commits +by specifying additional arguments to 'fetch'. Additional parents may +optionally be specified in the form of sha1 hex sums at the +command-line. Unfetched SVN revisions may also be tied to particular +git commits with the following syntax: + + svn_revision_number=git_commit_sha1 + +This allows you to tie unfetched SVN revision 375 to your current HEAD:: + + git-svn fetch 375=$(git-rev-parse HEAD) + +BUGS +---- +If somebody commits a conflicting changeset to SVN at a bad moment +(right before you commit) causing a conflict and your commit to fail, +your svn working tree ($GIT_DIR/git-svn/tree) may be dirtied. The +easiest thing to do is probably just to rm -rf $GIT_DIR/git-svn/tree and +run 'rebuild'. + +We ignore all SVN properties except svn:executable. Too difficult to +map them since we rely heavily on git write-tree being _exactly_ the +same on both the SVN and git working trees and I prefer not to clutter +working trees with metadata files. + +svn:keywords can't be ignored in Subversion (at least I don't know of +a way to ignore them). + +Renamed and copied directories are not detected by git and hence not +tracked when committing to SVN. I do not plan on adding support for +this as it's quite difficult and time-consuming to get working for all +the possible corner cases (git doesn't do it, either). Renamed and +copied files are fully supported if they're similar enough for git to +detect them. + +Author +------ +Written by Eric Wong <normalperson@yhbt.net>. + +Documentation +------------- +Written by Eric Wong <normalperson@yhbt.net>. diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh new file mode 100644 index 0000000000..181dfe008b --- /dev/null +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -0,0 +1,216 @@ +#!/bin/sh +# +# Copyright (c) 2006 Eric Wong +# + + +PATH=$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 new file mode 100755 index 0000000000..de9f3f3c72 --- /dev/null +++ b/contrib/gitview/gitview @@ -0,0 +1,1000 @@ +#! /usr/bin/env python + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. + +""" gitview +GUI browser for git repository +This program is based on bzrk by Scott James Remnant <scott@ubuntu.com> +""" +__copyright__ = "Copyright (C) 2006 Hewlett-Packard Development Company, L.P." +__author__ = "Aneesh Kumar K.V <aneesh.kumar@hp.com>" + + +import sys +import os +import gtk +import pygtk +import pango +import re +import time +import gobject +import cairo +import math +import string + +try: + import gtksourceview + have_gtksourceview = True +except ImportError: + have_gtksourceview = False + print "Running without gtksourceview module" + +re_ident = re.compile('(author|committer) (?P<ident>.*) (?P<epoch>\d+) (?P<tz>[+-]\d{4})') + +def list_to_string(args, skip): + count = len(args) + i = skip + str_arg=" " + while (i < count ): + str_arg = str_arg + args[i] + str_arg = str_arg + " " + i = i+1 + + return str_arg + +def show_date(epoch, tz): + secs = float(epoch) + tzsecs = float(tz[1:3]) * 3600 + tzsecs += float(tz[3:5]) * 60 + if (tz[0] == "+"): + secs += tzsecs + else: + secs -= tzsecs + + return time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(secs)) + + +class CellRendererGraph(gtk.GenericCellRenderer): + """Cell renderer for directed graph. + + This module contains the implementation of a custom GtkCellRenderer that + draws part of the directed graph based on the lines suggested by the code + in graph.py. + + Because we're shiny, we use Cairo to do this, and because we're naughty + we cheat and draw over the bits of the TreeViewColumn that are supposed to + just be for the background. + + Properties: + node (column, colour, [ names ]) tuple to draw revision node, + in_lines (start, end, colour) tuple list to draw inward lines, + out_lines (start, end, colour) tuple list to draw outward lines. + """ + + __gproperties__ = { + "node": ( gobject.TYPE_PYOBJECT, "node", + "revision node instruction", + gobject.PARAM_WRITABLE + ), + "in-lines": ( gobject.TYPE_PYOBJECT, "in-lines", + "instructions to draw lines into the cell", + gobject.PARAM_WRITABLE + ), + "out-lines": ( gobject.TYPE_PYOBJECT, "out-lines", + "instructions to draw lines out of the cell", + gobject.PARAM_WRITABLE + ), + } + + def do_set_property(self, property, value): + """Set properties from GObject properties.""" + if property.name == "node": + self.node = value + elif property.name == "in-lines": + self.in_lines = value + elif property.name == "out-lines": + self.out_lines = value + else: + raise AttributeError, "no such property: '%s'" % property.name + + def box_size(self, widget): + """Calculate box size based on widget's font. + + Cache this as it's probably expensive to get. It ensures that we + draw the graph at least as large as the text. + """ + try: + return self._box_size + except AttributeError: + pango_ctx = widget.get_pango_context() + font_desc = widget.get_style().font_desc + metrics = pango_ctx.get_metrics(font_desc) + + ascent = pango.PIXELS(metrics.get_ascent()) + descent = pango.PIXELS(metrics.get_descent()) + + self._box_size = ascent + descent + 6 + return self._box_size + + def set_colour(self, ctx, colour, bg, fg): + """Set the context source colour. + + Picks a distinct colour based on an internal wheel; the bg + parameter provides the value that should be assigned to the 'zero' + colours and the fg parameter provides the multiplier that should be + applied to the foreground colours. + """ + colours = [ + ( 1.0, 0.0, 0.0 ), + ( 1.0, 1.0, 0.0 ), + ( 0.0, 1.0, 0.0 ), + ( 0.0, 1.0, 1.0 ), + ( 0.0, 0.0, 1.0 ), + ( 1.0, 0.0, 1.0 ), + ] + + colour %= len(colours) + red = (colours[colour][0] * fg) or bg + green = (colours[colour][1] * fg) or bg + blue = (colours[colour][2] * fg) or bg + + ctx.set_source_rgb(red, green, blue) + + def on_get_size(self, widget, cell_area): + """Return the size we need for this cell. + + Each cell is drawn individually and is only as wide as it needs + to be, we let the TreeViewColumn take care of making them all + line up. + """ + box_size = self.box_size(widget) + + cols = self.node[0] + for start, end, colour in self.in_lines + self.out_lines: + 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) + + width = box_size * (cols + 1 ) + names_len + height = box_size + + # FIXME I have no idea how to use cell_area properly + return (0, 0, width, height) + + def on_render(self, window, widget, bg_area, cell_area, exp_area, flags): + """Render an individual cell. + + Draws the cell contents using cairo, taking care to clip what we + do to within the background area so we don't draw over other cells. + Note that we're a bit naughty there and should really be drawing + in the cell_area (or even the exposed area), but we explicitly don't + want any gutter. + + We try and be a little clever, if the line we need to draw is going + to cross other columns we actually draw it as in the .---' style + instead of a pure diagonal ... this reduces confusion by an + incredible amount. + """ + ctx = window.cairo_create() + ctx.rectangle(bg_area.x, bg_area.y, bg_area.width, bg_area.height) + ctx.clip() + + box_size = self.box_size(widget) + + ctx.set_line_width(box_size / 8) + ctx.set_line_cap(cairo.LINE_CAP_SQUARE) + + # Draw lines into the cell + for start, end, colour in self.in_lines: + ctx.move_to(cell_area.x + box_size * start + box_size / 2, + bg_area.y - bg_area.height / 2) + + if start - end > 1: + ctx.line_to(cell_area.x + box_size * start, bg_area.y) + ctx.line_to(cell_area.x + box_size * end + box_size, bg_area.y) + elif start - end < -1: + ctx.line_to(cell_area.x + box_size * start + box_size, + bg_area.y) + ctx.line_to(cell_area.x + box_size * end, bg_area.y) + + ctx.line_to(cell_area.x + box_size * end + box_size / 2, + bg_area.y + bg_area.height / 2) + + self.set_colour(ctx, colour, 0.0, 0.65) + ctx.stroke() + + # Draw lines out of the cell + for start, end, colour in self.out_lines: + ctx.move_to(cell_area.x + box_size * start + box_size / 2, + bg_area.y + bg_area.height / 2) + + if start - end > 1: + ctx.line_to(cell_area.x + box_size * start, + bg_area.y + bg_area.height) + ctx.line_to(cell_area.x + box_size * end + box_size, + bg_area.y + bg_area.height) + elif start - end < -1: + ctx.line_to(cell_area.x + box_size * start + box_size, + bg_area.y + bg_area.height) + ctx.line_to(cell_area.x + box_size * end, + bg_area.y + bg_area.height) + + ctx.line_to(cell_area.x + box_size * end + box_size / 2, + bg_area.y + bg_area.height / 2 + bg_area.height) + + self.set_colour(ctx, colour, 0.0, 0.65) + ctx.stroke() + + # Draw the revision node in the right column + (column, colour, names) = self.node + ctx.arc(cell_area.x + box_size * column + box_size / 2, + cell_area.y + cell_area.height / 2, + box_size / 4, 0, 2 * math.pi) + + + self.set_colour(ctx, colour, 0.0, 0.5) + ctx.stroke_preserve() + + self.set_colour(ctx, colour, 0.5, 1.0) + ctx.fill_preserve() + + if (len(names) != 0): + name = " " + for item in names: + name = name + item + " " + + ctx.set_font_size(13) + if (flags & 1): + self.set_colour(ctx, colour, 0.5, 1.0) + else: + self.set_colour(ctx, colour, 0.0, 0.5) + ctx.show_text(name) + +class Commit: + """ This represent a commit object obtained after parsing the git-rev-list + output """ + + children_sha1 = {} + + def __init__(self, commit_lines): + self.message = "" + self.author = "" + self.date = "" + self.committer = "" + self.commit_date = "" + self.commit_sha1 = "" + self.parent_sha1 = [ ] + self.parse_commit(commit_lines) + + + def parse_commit(self, commit_lines): + + # First line is the sha1 lines + line = string.strip(commit_lines[0]) + sha1 = re.split(" ", line) + self.commit_sha1 = sha1[0] + self.parent_sha1 = sha1[1:] + + #build the child list + for parent_id in self.parent_sha1: + try: + Commit.children_sha1[parent_id].append(self.commit_sha1) + except KeyError: + Commit.children_sha1[parent_id] = [self.commit_sha1] + + # IF we don't have parent + if (len(self.parent_sha1) == 0): + self.parent_sha1 = [0] + + for line in commit_lines[1:]: + m = re.match("^ ", line) + if (m != None): + # First line of the commit message used for short log + if self.message == "": + self.message = string.strip(line) + continue + + m = re.match("tree", line) + if (m != None): + continue + + m = re.match("parent", line) + if (m != None): + continue + + m = re_ident.match(line) + if (m != None): + date = show_date(m.group('epoch'), m.group('tz')) + if m.group(1) == "author": + self.author = m.group('ident') + self.date = date + elif m.group(1) == "committer": + self.committer = m.group('ident') + self.commit_date = date + + continue + + def get_message(self, with_diff=0): + if (with_diff == 1): + message = self.diff_tree() + else: + fp = os.popen("git cat-file commit " + self.commit_sha1) + message = fp.read() + fp.close() + + return message + + def diff_tree(self): + fp = os.popen("git diff-tree --pretty --cc -v -p --always " + self.commit_sha1) + diff = fp.read() + fp.close() + return diff + +class DiffWindow: + """Diff window. + This object represents and manages a single window containing the + differences between two revisions on a branch. + """ + + def __init__(self): + self.window = gtk.Window(gtk.WINDOW_TOPLEVEL) + self.window.set_border_width(0) + self.window.set_title("Git repository browser diff window") + + # Use two thirds of the screen by default + screen = self.window.get_screen() + monitor = screen.get_monitor_geometry(0) + width = int(monitor.width * 0.66) + height = int(monitor.height * 0.66) + self.window.set_default_size(width, height) + + self.construct() + + def construct(self): + """Construct the window contents.""" + vbox = gtk.VBox() + self.window.add(vbox) + vbox.show() + + menu_bar = gtk.MenuBar() + save_menu = gtk.ImageMenuItem(gtk.STOCK_SAVE) + save_menu.connect("activate", self.save_menu_response, "save") + save_menu.show() + menu_bar.append(save_menu) + vbox.pack_start(menu_bar, expand=False, fill=True) + menu_bar.show() + + scrollwin = gtk.ScrolledWindow() + scrollwin.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_AUTOMATIC) + scrollwin.set_shadow_type(gtk.SHADOW_IN) + vbox.pack_start(scrollwin, expand=True, fill=True) + scrollwin.show() + + if have_gtksourceview: + self.buffer = gtksourceview.SourceBuffer() + slm = gtksourceview.SourceLanguagesManager() + gsl = slm.get_language_from_mime_type("text/x-patch") + self.buffer.set_highlight(True) + self.buffer.set_language(gsl) + sourceview = gtksourceview.SourceView(self.buffer) + else: + self.buffer = gtk.TextBuffer() + sourceview = gtk.TextView(self.buffer) + + sourceview.set_editable(False) + sourceview.modify_font(pango.FontDescription("Monospace")) + scrollwin.add(sourceview) + sourceview.show() + + + def set_diff(self, commit_sha1, parent_sha1, encoding): + """Set the differences showed by this window. + Compares the two trees and populates the window with the + differences. + """ + # Diff with the first commit or the last commit shows nothing + if (commit_sha1 == 0 or parent_sha1 == 0 ): + return + + fp = os.popen("git diff-tree -p " + parent_sha1 + " " + commit_sha1) + self.buffer.set_text(unicode(fp.read(), encoding).encode('utf-8')) + fp.close() + self.window.show() + + def save_menu_response(self, widget, string): + dialog = gtk.FileChooserDialog("Save..", None, gtk.FILE_CHOOSER_ACTION_SAVE, + (gtk.STOCK_CANCEL, gtk.RESPONSE_CANCEL, + gtk.STOCK_SAVE, gtk.RESPONSE_OK)) + dialog.set_default_response(gtk.RESPONSE_OK) + response = dialog.run() + if response == gtk.RESPONSE_OK: + patch_buffer = self.buffer.get_text(self.buffer.get_start_iter(), + self.buffer.get_end_iter()) + fp = open(dialog.get_filename(), "w") + fp.write(patch_buffer) + fp.close() + dialog.destroy() + +class GitView: + """ This is the main class + """ + version = "0.7" + + def __init__(self, with_diff=0): + self.with_diff = with_diff + self.window = gtk.Window(gtk.WINDOW_TOPLEVEL) + self.window.set_border_width(0) + self.window.set_title("Git repository browser") + + self.get_encoding() + self.get_bt_sha1() + + # Use three-quarters of the screen by default + screen = self.window.get_screen() + monitor = screen.get_monitor_geometry(0) + width = int(monitor.width * 0.75) + height = int(monitor.height * 0.75) + self.window.set_default_size(width, height) + + # FIXME AndyFitz! + icon = self.window.render_icon(gtk.STOCK_INDEX, gtk.ICON_SIZE_BUTTON) + self.window.set_icon(icon) + + self.accel_group = gtk.AccelGroup() + self.window.add_accel_group(self.accel_group) + + self.construct() + + def get_bt_sha1(self): + """ Update the bt_sha1 dictionary with the + respective sha1 details """ + + self.bt_sha1 = { } + 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 get_encoding(self): + fp = os.popen("git repo-config --get i18n.commitencoding") + self.encoding=string.strip(fp.readline()) + fp.close() + if (self.encoding == ""): + self.encoding = "utf-8" + + + def construct(self): + """Construct the window contents.""" + vbox = gtk.VBox() + paned = gtk.VPaned() + paned.pack1(self.construct_top(), resize=False, shrink=True) + paned.pack2(self.construct_bottom(), resize=False, shrink=True) + menu_bar = gtk.MenuBar() + menu_bar.set_pack_direction(gtk.PACK_DIRECTION_RTL) + help_menu = gtk.MenuItem("Help") + menu = gtk.Menu() + about_menu = gtk.MenuItem("About") + menu.append(about_menu) + about_menu.connect("activate", self.about_menu_response, "about") + about_menu.show() + help_menu.set_submenu(menu) + help_menu.show() + menu_bar.append(help_menu) + menu_bar.show() + vbox.pack_start(menu_bar, expand=False, fill=True) + vbox.pack_start(paned, expand=True, fill=True) + self.window.add(vbox) + paned.show() + vbox.show() + + + def construct_top(self): + """Construct the top-half of the window.""" + vbox = gtk.VBox(spacing=6) + vbox.set_border_width(12) + vbox.show() + + + scrollwin = gtk.ScrolledWindow() + scrollwin.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_AUTOMATIC) + scrollwin.set_shadow_type(gtk.SHADOW_IN) + vbox.pack_start(scrollwin, expand=True, fill=True) + scrollwin.show() + + self.treeview = gtk.TreeView() + self.treeview.set_rules_hint(True) + self.treeview.set_search_column(4) + self.treeview.connect("cursor-changed", self._treeview_cursor_cb) + scrollwin.add(self.treeview) + self.treeview.show() + + cell = CellRendererGraph() + column = gtk.TreeViewColumn() + 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) + self.treeview.append_column(column) + + cell = gtk.CellRendererText() + cell.set_property("width-chars", 65) + cell.set_property("ellipsize", pango.ELLIPSIZE_END) + column = gtk.TreeViewColumn("Message") + column.set_resizable(True) + column.pack_start(cell, expand=True) + column.add_attribute(cell, "text", 4) + self.treeview.append_column(column) + + cell = gtk.CellRendererText() + cell.set_property("width-chars", 40) + cell.set_property("ellipsize", pango.ELLIPSIZE_END) + column = gtk.TreeViewColumn("Author") + column.set_resizable(True) + column.pack_start(cell, expand=True) + column.add_attribute(cell, "text", 5) + self.treeview.append_column(column) + + cell = gtk.CellRendererText() + cell.set_property("ellipsize", pango.ELLIPSIZE_END) + column = gtk.TreeViewColumn("Date") + column.set_resizable(True) + column.pack_start(cell, expand=True) + column.add_attribute(cell, "text", 6) + self.treeview.append_column(column) + + return vbox + + def about_menu_response(self, widget, string): + dialog = gtk.AboutDialog() + dialog.set_name("Gitview") + dialog.set_version(GitView.version) + dialog.set_authors(["Aneesh Kumar K.V <aneesh.kumar@hp.com>"]) + dialog.set_website("http://www.kernel.org/pub/software/scm/git/") + dialog.set_copyright("Use and distribute under the terms of the GNU General Public License") + dialog.set_wrap_license(True) + dialog.run() + dialog.destroy() + + + def construct_bottom(self): + """Construct the bottom half of the window.""" + vbox = gtk.VBox(False, spacing=6) + vbox.set_border_width(12) + (width, height) = self.window.get_size() + vbox.set_size_request(width, int(height / 2.5)) + vbox.show() + + self.table = gtk.Table(rows=4, columns=4) + self.table.set_row_spacings(6) + self.table.set_col_spacings(6) + vbox.pack_start(self.table, expand=False, fill=True) + self.table.show() + + align = gtk.Alignment(0.0, 0.5) + label = gtk.Label() + label.set_markup("<b>Revision:</b>") + align.add(label) + self.table.attach(align, 0, 1, 0, 1, gtk.FILL, gtk.FILL) + label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + self.revid_label = gtk.Label() + self.revid_label.set_selectable(True) + align.add(self.revid_label) + self.table.attach(align, 1, 2, 0, 1, gtk.EXPAND | gtk.FILL, gtk.FILL) + self.revid_label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + label = gtk.Label() + label.set_markup("<b>Committer:</b>") + align.add(label) + self.table.attach(align, 0, 1, 1, 2, gtk.FILL, gtk.FILL) + label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + self.committer_label = gtk.Label() + self.committer_label.set_selectable(True) + align.add(self.committer_label) + self.table.attach(align, 1, 2, 1, 2, gtk.EXPAND | gtk.FILL, gtk.FILL) + self.committer_label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + label = gtk.Label() + label.set_markup("<b>Timestamp:</b>") + align.add(label) + self.table.attach(align, 0, 1, 2, 3, gtk.FILL, gtk.FILL) + label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + self.timestamp_label = gtk.Label() + self.timestamp_label.set_selectable(True) + align.add(self.timestamp_label) + self.table.attach(align, 1, 2, 2, 3, gtk.EXPAND | gtk.FILL, gtk.FILL) + self.timestamp_label.show() + align.show() + + align = gtk.Alignment(0.0, 0.5) + label = gtk.Label() + label.set_markup("<b>Parents:</b>") + align.add(label) + self.table.attach(align, 0, 1, 3, 4, gtk.FILL, gtk.FILL) + label.show() + align.show() + self.parents_widgets = [] + + align = gtk.Alignment(0.0, 0.5) + label = gtk.Label() + label.set_markup("<b>Children:</b>") + align.add(label) + self.table.attach(align, 2, 3, 3, 4, gtk.FILL, gtk.FILL) + label.show() + align.show() + self.children_widgets = [] + + scrollwin = gtk.ScrolledWindow() + scrollwin.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_AUTOMATIC) + scrollwin.set_shadow_type(gtk.SHADOW_IN) + vbox.pack_start(scrollwin, expand=True, fill=True) + scrollwin.show() + + if have_gtksourceview: + self.message_buffer = gtksourceview.SourceBuffer() + slm = gtksourceview.SourceLanguagesManager() + gsl = slm.get_language_from_mime_type("text/x-patch") + self.message_buffer.set_highlight(True) + self.message_buffer.set_language(gsl) + sourceview = gtksourceview.SourceView(self.message_buffer) + else: + self.message_buffer = gtk.TextBuffer() + sourceview = gtk.TextView(self.message_buffer) + + sourceview.set_editable(False) + sourceview.modify_font(pango.FontDescription("Monospace")) + scrollwin.add(sourceview) + sourceview.show() + + return vbox + + def _treeview_cursor_cb(self, *args): + """Callback for when the treeview cursor changes.""" + (path, col) = self.treeview.get_cursor() + commit = self.model[path][0] + + if commit.committer is not None: + committer = commit.committer + timestamp = commit.commit_date + message = commit.get_message(self.with_diff) + revid_label = commit.commit_sha1 + else: + committer = "" + timestamp = "" + message = "" + revid_label = "" + + self.revid_label.set_text(revid_label) + self.committer_label.set_text(committer) + self.timestamp_label.set_text(timestamp) + self.message_buffer.set_text(unicode(message, self.encoding).encode('utf-8')) + + for widget in self.parents_widgets: + self.table.remove(widget) + + self.parents_widgets = [] + self.table.resize(4 + len(commit.parent_sha1) - 1, 4) + for idx, parent_id in enumerate(commit.parent_sha1): + self.table.set_row_spacing(idx + 3, 0) + + align = gtk.Alignment(0.0, 0.0) + self.parents_widgets.append(align) + self.table.attach(align, 1, 2, idx + 3, idx + 4, + gtk.EXPAND | gtk.FILL, gtk.FILL) + align.show() + + hbox = gtk.HBox(False, 0) + align.add(hbox) + hbox.show() + + label = gtk.Label(parent_id) + label.set_selectable(True) + hbox.pack_start(label, expand=False, fill=True) + label.show() + + image = gtk.Image() + image.set_from_stock(gtk.STOCK_JUMP_TO, gtk.ICON_SIZE_MENU) + image.show() + + button = gtk.Button() + button.add(image) + button.set_relief(gtk.RELIEF_NONE) + button.connect("clicked", self._go_clicked_cb, parent_id) + hbox.pack_start(button, expand=False, fill=True) + button.show() + + image = gtk.Image() + image.set_from_stock(gtk.STOCK_FIND, gtk.ICON_SIZE_MENU) + image.show() + + button = gtk.Button() + button.add(image) + button.set_relief(gtk.RELIEF_NONE) + button.set_sensitive(True) + button.connect("clicked", self._show_clicked_cb, + commit.commit_sha1, parent_id, self.encoding) + hbox.pack_start(button, expand=False, fill=True) + button.show() + + # Populate with child details + for widget in self.children_widgets: + self.table.remove(widget) + + self.children_widgets = [] + try: + child_sha1 = Commit.children_sha1[commit.commit_sha1] + except KeyError: + # We don't have child + child_sha1 = [ 0 ] + + if ( len(child_sha1) > len(commit.parent_sha1)): + self.table.resize(4 + len(child_sha1) - 1, 4) + + for idx, child_id in enumerate(child_sha1): + self.table.set_row_spacing(idx + 3, 0) + + align = gtk.Alignment(0.0, 0.0) + self.children_widgets.append(align) + self.table.attach(align, 3, 4, idx + 3, idx + 4, + gtk.EXPAND | gtk.FILL, gtk.FILL) + align.show() + + hbox = gtk.HBox(False, 0) + align.add(hbox) + hbox.show() + + label = gtk.Label(child_id) + label.set_selectable(True) + hbox.pack_start(label, expand=False, fill=True) + label.show() + + image = gtk.Image() + image.set_from_stock(gtk.STOCK_JUMP_TO, gtk.ICON_SIZE_MENU) + image.show() + + button = gtk.Button() + button.add(image) + button.set_relief(gtk.RELIEF_NONE) + button.connect("clicked", self._go_clicked_cb, child_id) + hbox.pack_start(button, expand=False, fill=True) + button.show() + + image = gtk.Image() + image.set_from_stock(gtk.STOCK_FIND, gtk.ICON_SIZE_MENU) + image.show() + + button = gtk.Button() + button.add(image) + button.set_relief(gtk.RELIEF_NONE) + button.set_sensitive(True) + button.connect("clicked", self._show_clicked_cb, + child_id, commit.commit_sha1) + hbox.pack_start(button, expand=False, fill=True) + button.show() + + def _destroy_cb(self, widget): + """Callback for when a window we manage is destroyed.""" + self.quit() + + + def quit(self): + """Stop the GTK+ main loop.""" + gtk.main_quit() + + def run(self, args): + self.set_branch(args) + self.window.connect("destroy", self._destroy_cb) + self.window.show() + gtk.main() + + def set_branch(self, args): + """Fill in different windows with info from the reposiroty""" + fp = os.popen("git rev-parse --sq --default HEAD " + list_to_string(args, 1)) + git_rev_list_cmd = fp.read() + fp.close() + fp = os.popen("git rev-list --header --topo-order --parents " + git_rev_list_cmd) + self.update_window(fp) + + def update_window(self, fp): + commit_lines = [] + + self.model = gtk.ListStore(gobject.TYPE_PYOBJECT, gobject.TYPE_PYOBJECT, + gobject.TYPE_PYOBJECT, gobject.TYPE_PYOBJECT, str, str, str) + + # used for cursor positioning + self.index = {} + + self.colours = {} + self.nodepos = {} + self.incomplete_line = {} + self.commits = [] + + index = 0 + last_colour = 0 + last_nodepos = -1 + out_line = [] + input_line = fp.readline() + while (input_line != ""): + # The commit header ends with '\0' + # This NULL is immediately followed by the sha1 of the + # next commit + if (input_line[0] != '\0'): + commit_lines.append(input_line) + input_line = fp.readline() + continue; + + commit = Commit(commit_lines) + if (commit != None ): + self.commits.append(commit) + + # Skip the '\0 + commit_lines = [] + commit_lines.append(input_line[1:]) + input_line = fp.readline() + + 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() + + def draw_graph(self, commit, index, out_line, last_colour, last_nodepos): + in_line=[] + + # | -> outline + # X + # |\ <- inline + + # Reset nodepostion + if (last_nodepos > 5): + last_nodepos = -1 + + # Add the incomplete lines of the last cell in this + try: + colour = self.colours[commit.commit_sha1] + except KeyError: + 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: + 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: + # check we alreay have the value + tmp_node_pos = self.nodepos[commit.parent_sha1[0]] + except KeyError: + self.colours[commit.parent_sha1[0]] = colour + self.nodepos[commit.parent_sha1[0]] = node_pos + + 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] + + + 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] + except KeyError: + branch_tag = [ ] + + + node = (node_pos, colour, branch_tag) + + self.model.append([commit, node, out_line, in_line, + commit.message, commit.author, commit.date]) + + return (in_line, last_colour, last_nodepos) + + 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.""" + try: + self.treeview.set_cursor(self.index[revid]) + except KeyError: + print "Revision %s not present in the list" % revid + # revid == 0 is the parent of the first commit + if (revid != 0 ): + print "Try running gitview without any options" + + self.treeview.grab_focus() + + def _show_clicked_cb(self, widget, commit_sha1, parent_sha1, encoding): + """Callback for when the show button for a parent is clicked.""" + window = DiffWindow() + window.set_diff(commit_sha1, parent_sha1, encoding) + self.treeview.grab_focus() + +if __name__ == "__main__": + without_diff = 0 + + if (len(sys.argv) > 1 ): + if (sys.argv[1] == "--without-diff"): + without_diff = 1 + + view = GitView( without_diff != 1) + view.run(sys.argv[without_diff:]) + + diff --git a/contrib/gitview/gitview.txt b/contrib/gitview/gitview.txt new file mode 100644 index 0000000000..fcf759c307 --- /dev/null +++ b/contrib/gitview/gitview.txt @@ -0,0 +1,38 @@ +gitview(1) +========== + +NAME +---- +gitview - A GTK based repository browser for git + +SYNOPSIS +-------- +'gitview' [options] [args] + +DESCRIPTION +--------- + +Dependencies + +* Python 2.4 +* PyGTK 2.8 or later +* PyCairo 1.0 or later + +OPTIONS +------ + --without-diff + If the user doesn't want to list the commit diffs in the main window. This may speed up the repository browsing. + + <args> + All the valid option for git-rev-list(1) + +EXAMPLES +------ + gitview v2.6.12.. include/scsi drivers/scsi + Show as the changes since version v2.6.12 that changed any file in the include/scsi + or drivers/scsi subdirectories + + gitview --since=2.weeks.ago + Show the changes during the last two weeks + + diff --git a/diff-delta.c b/diff-delta.c index c2f656ae39..2ed5984b1c 100644 --- a/diff-delta.c +++ b/diff-delta.c @@ -19,8 +19,9 @@ */ #include <stdlib.h> +#include <string.h> +#include <zlib.h> #include "delta.h" -#include "zlib.h" /* block size: min = 16, max = 64k, power of 2 */ @@ -29,149 +30,87 @@ #define MIN(a, b) ((a) < (b) ? (a) : (b)) #define GR_PRIME 0x9e370001 -#define HASH(v, b) (((unsigned int)(v) * GR_PRIME) >> (32 - (b))) - -static unsigned int hashbits(unsigned int size) -{ - unsigned int val = 1, bits = 0; - while (val < size && bits < 32) { - val <<= 1; - bits++; - } - return bits ? bits: 1; -} - -typedef struct s_chanode { - struct s_chanode *next; - int icurr; -} chanode_t; - -typedef struct s_chastore { - int isize, nsize; - chanode_t *ancur; -} chastore_t; - -static void cha_init(chastore_t *cha, int isize, int icount) -{ - cha->isize = isize; - cha->nsize = icount * isize; - cha->ancur = NULL; -} - -static void *cha_alloc(chastore_t *cha) -{ - chanode_t *ancur; - void *data; +#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift)) - ancur = cha->ancur; - if (!ancur || ancur->icurr == cha->nsize) { - ancur = malloc(sizeof(chanode_t) + cha->nsize); - if (!ancur) - return NULL; - ancur->icurr = 0; - ancur->next = cha->ancur; - cha->ancur = ancur; - } - - data = (void *)ancur + sizeof(chanode_t) + ancur->icurr; - ancur->icurr += cha->isize; - return data; -} - -static void cha_free(chastore_t *cha) -{ - chanode_t *cur = cha->ancur; - while (cur) { - chanode_t *tmp = cur; - cur = cur->next; - free(tmp); - } -} - -typedef struct s_bdrecord { - struct s_bdrecord *next; - unsigned int fp; +struct index { const unsigned char *ptr; -} bdrecord_t; - -typedef struct s_bdfile { - chastore_t cha; - unsigned int fphbits; - bdrecord_t **fphash; -} bdfile_t; + unsigned int val; + struct index *next; +}; -static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf) +static struct index ** delta_index(const unsigned char *buf, + unsigned long bufsize, + unsigned int *hash_shift) { - unsigned int fphbits; - int i, hsize; - const unsigned char *data, *top; - bdrecord_t *brec; - bdrecord_t **fphash; - - fphbits = hashbits(bufsize / BLK_SIZE + 1); - hsize = 1 << fphbits; - fphash = malloc(hsize * sizeof(bdrecord_t *)); - if (!fphash) - return -1; - for (i = 0; i < hsize; i++) - fphash[i] = NULL; - cha_init(&bdf->cha, sizeof(bdrecord_t), hsize / 4 + 1); - - top = buf + bufsize; - data = buf + (bufsize / BLK_SIZE) * BLK_SIZE; - if (data == top) + unsigned int hsize, hshift, entries, blksize, i; + const unsigned char *data; + struct index *entry, **hash; + void *mem; + + /* determine index hash size */ + entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE; + hsize = entries / 4; + for (i = 4; (1 << i) < hsize && i < 16; i++); + hsize = 1 << i; + hshift = 32 - i; + *hash_shift = hshift; + + /* allocate lookup index */ + mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry)); + if (!mem) + return NULL; + hash = mem; + entry = mem + hsize * sizeof(*hash); + memset(hash, 0, hsize * sizeof(*hash)); + + /* then populate it */ + data = buf + entries * BLK_SIZE - BLK_SIZE; + blksize = bufsize - (data - buf); + while (data >= buf) { + unsigned int val = adler32(0, data, blksize); + i = HASH(val, hshift); + entry->ptr = data; + entry->val = val; + entry->next = hash[i]; + hash[i] = entry++; + blksize = BLK_SIZE; data -= BLK_SIZE; + } - for ( ; data >= buf; data -= BLK_SIZE) { - brec = cha_alloc(&bdf->cha); - if (!brec) { - cha_free(&bdf->cha); - free(fphash); - return -1; - } - brec->fp = adler32(0, data, MIN(BLK_SIZE, top - data)); - brec->ptr = data; - i = HASH(brec->fp, fphbits); - brec->next = fphash[i]; - fphash[i] = brec; - } - - bdf->fphbits = fphbits; - bdf->fphash = fphash; - - return 0; -} - -static void delta_cleanup(bdfile_t *bdf) -{ - free(bdf->fphash); - cha_free(&bdf->cha); + return hash; } +/* provide the size of the copy opcode given the block offset and size */ #define COPYOP_SIZE(o, s) \ (!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \ !!(s & 0xff) + !!(s & 0xff00) + 1) +/* the maximum size for any opcode */ +#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff) + void *diff_delta(void *from_buf, unsigned long from_size, void *to_buf, unsigned long to_size, unsigned long *delta_size, unsigned long max_size) { - int i, outpos, outsize, inscnt, csize, msize, moff; - unsigned int fp; - const unsigned char *ref_data, *ref_top, *data, *top, *ptr1, *ptr2; - unsigned char *out, *orig; - bdrecord_t *brec; - bdfile_t bdf; + unsigned int i, outpos, outsize, inscnt, hash_shift; + const unsigned char *ref_data, *ref_top, *data, *top; + unsigned char *out; + struct index *entry, **hash; - if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf)) + if (!from_size || !to_size) + return NULL; + hash = delta_index(from_buf, from_size, &hash_shift); + if (!hash) return NULL; - + outpos = 0; outsize = 8192; + if (max_size && outsize >= max_size) + outsize = max_size + MAX_OP_SIZE + 1; out = malloc(outsize); if (!out) { - delta_cleanup(&bdf); + free(hash); return NULL; } @@ -199,28 +138,32 @@ void *diff_delta(void *from_buf, unsigned long from_size, } inscnt = 0; - moff = 0; - while (data < top) { - msize = 0; - fp = adler32(0, data, MIN(top - data, BLK_SIZE)); - i = HASH(fp, bdf.fphbits); - for (brec = bdf.fphash[i]; brec; brec = brec->next) { - if (brec->fp == fp) { - csize = ref_top - brec->ptr; - if (csize > top - data) - csize = top - data; - for (ptr1 = brec->ptr, ptr2 = data; - csize && *ptr1 == *ptr2; - csize--, ptr1++, ptr2++); - csize = ptr1 - brec->ptr; - if (csize > msize) { - moff = brec->ptr - ref_data; - msize = csize; - if (msize >= 0x10000) { - msize = 0x10000; - break; - } + while (data < top) { + unsigned int moff = 0, msize = 0; + unsigned int blksize = MIN(top - data, BLK_SIZE); + unsigned int val = adler32(0, data, blksize); + i = HASH(val, hash_shift); + for (entry = hash[i]; entry; entry = entry->next) { + const unsigned char *ref = entry->ptr; + const unsigned char *src = data; + unsigned int ref_size = ref_top - ref; + if (entry->val != val) + continue; + if (ref_size > top - src) + ref_size = top - src; + while (ref_size && *src++ == *ref) { + ref++; + ref_size--; + } + ref_size = ref - entry->ptr; + if (ref_size > msize) { + /* this is our best match so far */ + moff = entry->ptr - ref_data; + msize = ref_size; + if (msize >= 0x10000) { + msize = 0x10000; + break; } } } @@ -235,13 +178,15 @@ void *diff_delta(void *from_buf, unsigned long from_size, inscnt = 0; } } else { + unsigned char *op; + if (inscnt) { out[outpos - inscnt - 1] = inscnt; inscnt = 0; } data += msize; - orig = out + outpos++; + op = out + outpos++; i = 0x80; if (moff & 0xff) { out[outpos++] = moff; i |= 0x01; } @@ -256,23 +201,21 @@ void *diff_delta(void *from_buf, unsigned long from_size, msize >>= 8; if (msize & 0xff) { out[outpos++] = msize; i |= 0x20; } - *orig = i; - } - - if (max_size && outpos > max_size) { - free(out); - delta_cleanup(&bdf); - return NULL; + *op = i; } - /* next time around the largest possible output is 1 + 4 + 3 */ - if (outpos > outsize - 8) { + if (outpos >= outsize - MAX_OP_SIZE) { void *tmp = out; outsize = outsize * 3 / 2; - out = realloc(out, outsize); + if (max_size && outsize >= max_size) + outsize = max_size + MAX_OP_SIZE + 1; + if (max_size && outpos > max_size) + out = NULL; + else + out = realloc(out, outsize); if (!out) { free(tmp); - delta_cleanup(&bdf); + free(hash); return NULL; } } @@ -281,7 +224,7 @@ void *diff_delta(void *from_buf, unsigned long from_size, if (inscnt) out[outpos - inscnt - 1] = inscnt; - delta_cleanup(&bdf); + free(hash); *delta_size = outpos; return out; } 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 && @@ -178,11 +178,12 @@ static void emit_rewrite_diff(const char *name_a, copy_file('+', temp[1].name); } -static void builtin_diff(const char *name_a, +static const char *builtin_diff(const char *name_a, const char *name_b, struct diff_tempfile *temp, const char *xfrm_msg, - int complete_rewrite) + int complete_rewrite, + const char **args) { int i, next_at, cmd_size; const char *const diff_cmd = "diff -L%s -L%s"; @@ -242,19 +243,24 @@ static void builtin_diff(const char *name_a, } if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); + /* + * we do not run diff between different kind + * of objects. + */ if (strncmp(temp[0].mode, temp[1].mode, 3)) - /* we do not run diff between different kind - * of objects. - */ - exit(0); + return NULL; if (complete_rewrite) { - fflush(NULL); emit_rewrite_diff(name_a, name_b, temp); - exit(0); + return NULL; } } - fflush(NULL); - execlp("/bin/sh","sh", "-c", cmd, NULL); + + /* This is disgusting */ + *args++ = "sh"; + *args++ = "-c"; + *args++ = cmd; + *args = NULL; + return "/bin/sh"; } struct diff_filespec *alloc_filespec(const char *path) @@ -311,7 +317,7 @@ 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, @@ -559,6 +565,40 @@ static void remove_tempfile_on_signal(int signo) raise(signo); } +static int spawn_prog(const char *pgm, const char **arg) +{ + pid_t pid; + int status; + + fflush(NULL); + pid = fork(); + if (pid < 0) + die("unable to fork"); + if (!pid) { + execvp(pgm, (char *const*) arg); + exit(255); + } + + while (waitpid(pid, &status, 0) < 0) { + if (errno == EINTR) + continue; + return -1; + } + + /* Earlier we did not check the exit status because + * diff exits non-zero if files are different, and + * we are not interested in knowing that. It was a + * mistake which made it harder to quit a diff-* + * session that uses the git-apply-patch-script as + * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF + * should also exit non-zero only when it wants to + * abort the entire diff-* session. + */ + if (WIFEXITED(status) && !WEXITSTATUS(status)) + return 0; + return -1; +} + /* An external diff command takes: * * diff-cmd name infile1 infile1-sha1 infile1-mode \ @@ -573,9 +613,9 @@ static void run_external_diff(const char *pgm, const char *xfrm_msg, int complete_rewrite) { + const char *spawn_arg[10]; struct diff_tempfile *temp = diff_temp; - pid_t pid; - int status; + int retval; static int atexit_asked = 0; const char *othername; @@ -592,59 +632,41 @@ static void run_external_diff(const char *pgm, signal(SIGINT, remove_tempfile_on_signal); } - fflush(NULL); - pid = fork(); - if (pid < 0) - die("unable to fork"); - if (!pid) { - if (pgm) { - if (one && two) { - const char *exec_arg[10]; - const char **arg = &exec_arg[0]; - *arg++ = pgm; - *arg++ = name; - *arg++ = temp[0].name; - *arg++ = temp[0].hex; - *arg++ = temp[0].mode; - *arg++ = temp[1].name; - *arg++ = temp[1].hex; - *arg++ = temp[1].mode; - if (other) { - *arg++ = other; - *arg++ = xfrm_msg; - } - *arg = NULL; - execvp(pgm, (char *const*) exec_arg); + if (pgm) { + const char **arg = &spawn_arg[0]; + if (one && two) { + *arg++ = pgm; + *arg++ = name; + *arg++ = temp[0].name; + *arg++ = temp[0].hex; + *arg++ = temp[0].mode; + *arg++ = temp[1].name; + *arg++ = temp[1].hex; + *arg++ = temp[1].mode; + if (other) { + *arg++ = other; + *arg++ = xfrm_msg; } - else - execlp(pgm, pgm, name, NULL); + } else { + *arg++ = pgm; + *arg++ = name; } - /* - * otherwise we use the built-in one. - */ - if (one && two) - builtin_diff(name, othername, temp, xfrm_msg, - complete_rewrite); - else + *arg = NULL; + } else { + if (one && two) { + pgm = builtin_diff(name, othername, temp, xfrm_msg, complete_rewrite, spawn_arg); + } else printf("* Unmerged path %s\n", name); - exit(0); } - if (waitpid(pid, &status, 0) < 0 || - !WIFEXITED(status) || WEXITSTATUS(status)) { - /* Earlier we did not check the exit status because - * diff exits non-zero if files are different, and - * we are not interested in knowing that. It was a - * mistake which made it harder to quit a diff-* - * session that uses the git-apply-patch-script as - * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF - * should also exit non-zero only when it wants to - * abort the entire diff-* session. - */ - remove_tempfile(); + + retval = 0; + if (pgm) + retval = spawn_prog(pgm, spawn_arg); + remove_tempfile(); + if (retval) { fprintf(stderr, "external diff died, stopping at %s.\n", name); exit(1); } - remove_tempfile(); } static void diff_fill_sha1_info(struct diff_filespec *one) diff --git a/diffcore-break.c b/diffcore-break.c index 95b5eb492e..0fc2b860be 100644 --- a/diffcore-break.c +++ b/diffcore-break.c @@ -4,8 +4,6 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include "delta.h" -#include "count-delta.h" static int should_break(struct diff_filespec *src, struct diff_filespec *dst, @@ -47,7 +45,6 @@ static int should_break(struct diff_filespec *src, * The value we return is 1 if we want the pair to be broken, * or 0 if we do not. */ - void *delta; unsigned long delta_size, base_size, src_copied, literal_added; int to_break = 0; @@ -69,19 +66,11 @@ static int should_break(struct diff_filespec *src, if (base_size < MINIMUM_BREAK_SIZE) return 0; /* we do not break too small filepair */ - delta = diff_delta(src->data, src->size, - dst->data, dst->size, - &delta_size, 0); - if (!delta) - return 0; /* error but caught downstream */ - - /* Estimate the edit size by interpreting delta. */ - if (count_delta(delta, delta_size, - &src_copied, &literal_added)) { - free(delta); - return 0; /* we cannot tell */ - } - free(delta); + if (diffcore_count_changes(src->data, src->size, + dst->data, dst->size, + 0, + &src_copied, &literal_added)) + return 0; /* Compute merge-score, which is "how much is removed * from the source material". The clean-up stage will diff --git a/diffcore-delta.c b/diffcore-delta.c new file mode 100644 index 0000000000..1e6a6911ec --- /dev/null +++ b/diffcore-delta.c @@ -0,0 +1,43 @@ +#include "cache.h" +#include "diff.h" +#include "diffcore.h" +#include "delta.h" +#include "count-delta.h" + +static int diffcore_count_changes_1(void *src, unsigned long src_size, + void *dst, unsigned long dst_size, + unsigned long delta_limit, + unsigned long *src_copied, + unsigned long *literal_added) +{ + void *delta; + unsigned long delta_size; + + delta = diff_delta(src, src_size, + dst, dst_size, + &delta_size, delta_limit); + if (!delta) + /* If delta_limit is exceeded, we have too much differences */ + return -1; + + /* Estimate the edit size by interpreting delta. */ + if (count_delta(delta, delta_size, src_copied, literal_added)) { + free(delta); + return -1; + } + free(delta); + return 0; +} + +int diffcore_count_changes(void *src, unsigned long src_size, + void *dst, unsigned long dst_size, + unsigned long delta_limit, + unsigned long *src_copied, + unsigned long *literal_added) +{ + return diffcore_count_changes_1(src, src_size, + dst, dst_size, + delta_limit, + src_copied, + literal_added); +} diff --git a/diffcore-rename.c b/diffcore-rename.c index ffd126af0d..55cf1c37f3 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -4,8 +4,6 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include "delta.h" -#include "count-delta.h" /* Table of rename/copy destinations */ @@ -135,7 +133,6 @@ static int estimate_similarity(struct diff_filespec *src, * match than anything else; the destination does not even * call into this function in that case. */ - void *delta; unsigned long delta_size, base_size, src_copied, literal_added; unsigned long delta_limit; int score; @@ -165,28 +162,13 @@ static int estimate_similarity(struct diff_filespec *src, if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0)) return 0; /* error but caught downstream */ - delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE; - delta = diff_delta(src->data, src->size, - dst->data, dst->size, - &delta_size, delta_limit); - if (!delta) - /* If delta_limit is exceeded, we have too much differences */ - return 0; - - /* 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) { - free(delta); - return 0; - } - /* Estimate the edit size by interpreting delta. */ - if (count_delta(delta, delta_size, &src_copied, &literal_added)) { - free(delta); + delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE; + if (diffcore_count_changes(src->data, src->size, + dst->data, dst->size, + delta_limit, + &src_copied, &literal_added)) return 0; - } - free(delta); /* Extent of damage */ if (src->size + literal_added < src_copied) diff --git a/diffcore.h b/diffcore.h index 12cd816591..dba4f17658 100644 --- a/diffcore.h +++ b/diffcore.h @@ -101,4 +101,10 @@ void diff_debug_queue(const char *, struct diff_queue_struct *); #define diff_debug_queue(a,b) do {} while(0) #endif +extern int diffcore_count_changes(void *src, unsigned long src_size, + void *dst, unsigned long dst_size, + unsigned long delta_limit, + unsigned long *src_copied, + unsigned long *literal_added); + #endif @@ -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 73e4b1c8b7..16c08f0697 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/exec_cmd.c b/exec_cmd.c index 55af33bb7e..b5e59a9ae9 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -13,7 +13,7 @@ void git_set_exec_path(const char *exec_path) /* Returns the highest-priority, location to look for git programs. */ -const char *git_exec_path() +const char *git_exec_path(void) { const char *env; diff --git a/fetch-pack.c b/fetch-pack.c index aa6f42ae1b..535de10660 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) { @@ -82,7 +82,7 @@ static void mark_common(struct commit *commit, Get the next rev to send, ignoring the common. */ -static const unsigned char* get_rev() +static const unsigned char* get_rev(void) { struct commit *commit = NULL; @@ -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/fsck-objects.c b/fsck-objects.c index 6439d55126..4ddd67699c 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -20,7 +20,7 @@ static int check_strict = 0; static int keep_cache_objects = 0; static unsigned char head_sha1[20]; -#if NO_D_INO_IN_DIRENT +#ifdef NO_D_INO_IN_DIRENT #define SORT_DIRENT 0 #define DIRENT_SORT_HINT(de) 0 #else diff --git a/git-add.sh b/git-add.sh index 611f152dac..d6a4bc7d09 100755 --- a/git-add.sh +++ b/git-add.sh @@ -28,6 +28,17 @@ while : ; do shift done +# Check misspelled pathspec +case "$#" in +0) ;; +*) + git-ls-files --error-unmatch --others --cached -- "$@" >/dev/null || { + echo >&2 "Maybe you misspelled it?" + exit 1 + } + ;; +esac + if test -f "$GIT_DIR/info/exclude" then git-ls-files -z \ diff --git a/git-annotate.perl b/git-annotate.perl new file mode 100755 index 0000000000..cd476c7629 --- /dev/null +++ b/git-annotate.perl @@ -0,0 +1,495 @@ +#!/usr/bin/perl +# Copyright 2006, Ryan Anderson <ryan@michonline.com> +# +# GPL v2 (See COPYING) +# +# This file is licensed under the GPL v2, or a later version +# at the discretion of Linus Torvalds. + +use warnings; +use strict; +use Getopt::Long; +use POSIX qw(strftime gmtime); + +sub usage() { + print STDERR 'Usage: ${\basename $0} [-s] [-S revs-file] file [ revision ] + -l, --long + Show long rev (Defaults off) + -r, --rename + Follow renames (Defaults on). + -S, --rev-file revs-file + use revs from revs-file instead of calling git-rev-list + -h, --help + This message. +'; + + exit(1); +} + +our ($help, $longrev, $rename, $starting_rev, $rev_file) = (0, 0, 1); + +my $rc = GetOptions( "long|l" => \$longrev, + "help|h" => \$help, + "rename|r" => \$rename, + "rev-file|S=s" => \$rev_file); +if (!$rc or $help) { + usage(); +} + +my $filename = shift @ARGV; +if (@ARGV) { + $starting_rev = shift @ARGV; +} + +my @stack = ( + { + 'rev' => defined $starting_rev ? $starting_rev : "HEAD", + 'filename' => $filename, + }, +); + +our @filelines = (); + +if (defined $starting_rev) { + @filelines = git_cat_file($starting_rev, $filename); +} else { + open(F,"<",$filename) + or die "Failed to open filename: $!"; + + while(<F>) { + chomp; + push @filelines, $_; + } + close(F); + +} + +our %revs; +our @revqueue; +our $head; + +my $revsprocessed = 0; +while (my $bound = pop @stack) { + my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'}); + foreach my $revinst (@revisions) { + my ($rev, @parents) = @$revinst; + $head ||= $rev; + + if (!defined($rev)) { + $rev = ""; + } + $revs{$rev}{'filename'} = $bound->{'filename'}; + if (scalar @parents > 0) { + $revs{$rev}{'parents'} = \@parents; + next; + } + + if (!$rename) { + next; + } + + my $newbound = find_parent_renames($rev, $bound->{'filename'}); + if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) { + push @stack, $newbound; + $revs{$rev}{'parents'} = [$newbound->{'rev'}]; + } + } +} +push @revqueue, $head; +init_claim( defined $starting_rev ? $starting_rev : 'dirty'); +unless (defined $starting_rev) { + my $diff = open_pipe("git","diff","-R", "HEAD", "--",$filename) + or die "Failed to call git diff to check for dirty state: $!"; + + _git_diff_parse($diff, $head, "dirty", ( + 'author' => gitvar_name("GIT_AUTHOR_IDENT"), + 'author_date' => sprintf("%s +0000",time()), + ) + ); + close($diff); +} +handle_rev(); + + +my $i = 0; +foreach my $l (@filelines) { + my ($output, $rev, $committer, $date); + if (ref $l eq 'ARRAY') { + ($output, $rev, $committer, $date) = @$l; + if (!$longrev && length($rev) > 8) { + $rev = substr($rev,0,8); + } + } else { + $output = $l; + ($rev, $committer, $date) = ('unknown', 'unknown', 'unknown'); + } + + printf("%s\t(%10s\t%10s\t%d)%s\n", $rev, $committer, + format_date($date), $i++, $output); +} + +sub init_claim { + my ($rev) = @_; + for (my $i = 0; $i < @filelines; $i++) { + $filelines[$i] = [ $filelines[$i], '', '', '', 1]; + # line, + # rev, + # author, + # date, + # 1 <-- belongs to the original file. + } + $revs{$rev}{'lines'} = \@filelines; +} + + +sub handle_rev { + my $i = 0; + my %seen; + while (my $rev = shift @revqueue) { + next if $seen{$rev}++; + + 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) = @_; + + my $revlist; + if ($rev_file) { + open($revlist, '<' . $rev_file) + or die "Failed to open $rev_file : $!"; + } else { + $revlist = open_pipe("git-rev-list","--parents","--remove-empty",$rev,"--",$file) + or die "Failed to exec git-rev-list: $!"; + } + + my @revs; + while(my $line = <$revlist>) { + chomp $line; + my ($rev, @parents) = split /\s+/, $line; + push @revs, [ $rev, @parents ]; + } + close($revlist); + + printf("0 revs found for rev %s (%s)\n", $rev, $file) if (@revs == 0); + return @revs; +} + +sub find_parent_renames { + my ($rev, $file) = @_; + + my $patch = open_pipe("git-diff-tree", "-M50", "-r","--name-status", "-z","$rev") + or die "Failed to exec git-diff: $!"; + + local $/ = "\0"; + my %bound; + my $junk = <$patch>; + while (my $change = <$patch>) { + chomp $change; + my $filename = <$patch>; + chomp $filename; + + if ($change =~ m/^[AMD]$/ ) { + next; + } elsif ($change =~ m/^R/ ) { + my $oldfilename = $filename; + $filename = <$patch>; + chomp $filename; + if ( $file eq $filename ) { + my $parent = git_find_parent($rev, $oldfilename); + @bound{'rev','filename'} = ($parent, $oldfilename); + last; + } + } + } + close($patch); + + return \%bound; +} + + +sub git_find_parent { + my ($rev, $filename) = @_; + + my $revparent = open_pipe("git-rev-list","--remove-empty", "--parents","--max-count=1","$rev","--",$filename) + or die "Failed to open git-rev-list to find a single parent: $!"; + + my $parentline = <$revparent>; + chomp $parentline; + my ($revfound,$parent) = split m/\s+/, $parentline; + + close($revparent); + + return $parent; +} + + +# Get a diff between the current revision and a parent. +# Record the commit information that results. +sub git_diff_parse { + my ($parent, $rev, %revinfo) = @_; + + my $diff = open_pipe("git-diff-tree","-M","-p",$rev,$parent,"--", + $revs{$rev}{'filename'}, $revs{$parent}{'filename'}) + or die "Failed to call git-diff for annotation: $!"; + + _git_diff_parse($diff, $parent, $rev, %revinfo); + + close($diff); +} + +sub _git_diff_parse { + my ($diff, $parent, $rev, %revinfo) = @_; + + my ($ri, $pi) = (0,0); + my $slines = $revs{$rev}{'lines'}; + my @plines; + + my $gotheader = 0; + my ($remstart); + my ($hunk_start, $hunk_index); + while(<$diff>) { + chomp; + if (m/^@@ -(\d+),(\d+) \+(\d+),(\d+)/) { + $remstart = $1; + # Adjust for 0-based arrays + $remstart--; + # 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); + } + $ri++; + + } elsif (m/^\\/) { + ; + # Skip \No newline at end of file. + # But this can be internationalized, so only look + # for an initial \ + + } else { + if (substr($_,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++; + } + 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 ($rev, $filename) = @_; + return () unless defined $rev && defined $filename; + + my $blob = git_ls_tree($rev, $filename); + + my $catfile = open_pipe("git","cat-file", "blob", $blob) + or die "Failed to git-cat-file blob $blob (rev $rev, file $filename): " . $!; + + my @lines; + while(<$catfile>) { + chomp; + push @lines, $_; + } + close($catfile); + + return @lines; +} + +sub git_ls_tree { + my ($rev, $filename) = @_; + + my $lstree = open_pipe("git","ls-tree",$rev,$filename) + or die "Failed to call git ls-tree: $!"; + + my ($mode, $type, $blob, $tfilename); + while(<$lstree>) { + ($mode, $type, $blob, $tfilename) = split(/\s+/, $_, 4); + last if ($tfilename eq $filename); + } + close($lstree); + + return $blob if $filename eq $filename; + die "git-ls-tree failed to find blob for $filename"; + +} + + + +sub claim_line { + my ($floffset, $rev, $lines, %revinfo) = @_; + my $oline = get_line($lines, $floffset); + @{$lines->[$floffset]} = ( $oline, $rev, + $revinfo{'author'}, $revinfo{'author_date'} ); + #printf("Claiming line %d with rev %s: '%s'\n", + # $floffset, $rev, $oline) if 1; +} + +sub git_commit_info { + my ($rev) = @_; + my $commit = open_pipe("git-cat-file", "commit", $rev) + or die "Failed to call git-cat-file: $!"; + + my %info; + while(<$commit>) { + chomp; + last if (length $_ == 0); + + if (m/^author (.*) <(.*)> (.*)$/) { + $info{'author'} = $1; + $info{'author_email'} = $2; + $info{'author_date'} = $3; + } elsif (m/^committer (.*) <(.*)> (.*)$/) { + $info{'committer'} = $1; + $info{'committer_email'} = $2; + $info{'committer_date'} = $3; + } + } + close($commit); + + return %info; +} + +sub format_date { + my ($timestamp, $timezone) = split(' ', $_[0]); + + return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($timestamp)); +} + +# Copied from git-send-email.perl - We need a Git.pm module.. +sub gitvar { + my ($var) = @_; + my $fh; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-var', $var) or die "$!"; + } + my ($val) = <$fh>; + close $fh or die "$!"; + chomp($val); + return $val; +} + +sub gitvar_name { + my ($name) = @_; + my $val = gitvar($name); + my @field = split(/\s+/, $val); + return join(' ', @field[0...(@field-4)]); +} + +sub open_pipe { + if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { + return open_pipe_activestate(@_); + } else { + return open_pipe_normal(@_); + } +} + +sub open_pipe_activestate { + tie *fh, "Git::ActiveStatePipe", @_; + return *fh; +} + +sub open_pipe_normal { + my (@execlist) = @_; + + my $pid = open my $kid, "-|"; + defined $pid or die "Cannot fork: $!"; + + unless ($pid) { + exec @execlist; + die "Cannot exec @execlist: $!"; + } + + return $kid; +} + +package Git::ActiveStatePipe; +use strict; + +sub TIEHANDLE { + my ($class, @params) = @_; + my $cmdline = join " ", @params; + my @data = qx{$cmdline}; + bless { i => 0, data => \@data }, $class; +} + +sub READLINE { + my $self = shift; + if ($self->{i} >= scalar @{$self->{data}}) { + return undef; + } + return $self->{'data'}->[ $self->{i}++ ]; +} + +sub CLOSE { + my $self = shift; + delete $self->{data}; + delete $self->{i}; +} + +sub EOF { + my $self = shift; + return ($self->{i} >= scalar @{$self->{data}}); +} diff --git a/git-bisect.sh b/git-bisect.sh index 07502536ce..03df1433ef 100755 --- a/git-bisect.sh +++ b/git-bisect.sh @@ -49,9 +49,16 @@ bisect_start() { die "Bad HEAD - I need a symbolic ref" case "$head" in refs/heads/bisect*) - git checkout master || exit + if [ -s "$GIT_DIR/head-name" ]; then + branch=`cat "$GIT_DIR/head-name"` + else + branch=master + fi + git checkout $branch || exit ;; refs/heads/*) + [ -s "$GIT_DIR/head-name" ] && die "won't bisect on seeked tree" + echo "$head" | sed 's#^refs/heads/##' >"$GIT_DIR/head-name" ;; *) die "Bad HEAD - strange symbolic ref" @@ -159,7 +166,11 @@ bisect_visualize() { bisect_reset() { case "$#" in - 0) branch=master ;; + 0) if [ -s "$GIT_DIR/head-name" ]; then + branch=`cat "$GIT_DIR/head-name"` + else + branch=master + fi ;; 1) test -f "$GIT_DIR/refs/heads/$1" || { echo >&2 "$1 does not seem to be a valid branch" exit 1 @@ -170,7 +181,7 @@ bisect_reset() { esac git checkout "$branch" && rm -fr "$GIT_DIR/refs/bisect" - rm -f "$GIT_DIR/refs/heads/bisect" + rm -f "$GIT_DIR/refs/heads/bisect" "$GIT_DIR/head-name" rm -f "$GIT_DIR/BISECT_LOG" rm -f "$GIT_DIR/BISECT_NAMES" } diff --git a/git-clone.sh b/git-clone.sh index 89c15d7a65..4ed861d576 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -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 "$GIT_DIR/objects/info" diff --git a/git-commit.sh b/git-commit.sh index 59551d99f9..f7ee1aadee 100755 --- a/git-commit.sh +++ b/git-commit.sh @@ -3,7 +3,7 @@ # Copyright (c) 2005 Linus Torvalds # Copyright (c) 2006 Junio C Hamano -USAGE='[-a] [-i] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>] [-e] [--author <author>] [<path>...]' +USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>] [-e] [--author <author>] [[-i | -o] <path>...]' SUBDIRECTORY_OK=Yes . git-sh-setup @@ -180,6 +180,7 @@ verify=t verbose= signoff= force_author= +only_include_assumed= while case "$#" in 0) break;; esac do case "$1" in @@ -340,15 +341,8 @@ case "$#,$also$only" in 0,) ;; *,) - echo >&2 "assuming --include paths..." - also=t - # Later when switch the defaults, we will replace them with these: - # echo >&2 "assuming --only paths..." - # also= - - # If we are going to launch an editor, the message won't be - # shown without this... - test -z "$log_given$status_only" && sleep 1 + only_include_assumed="# Explicit paths specified without -i nor -o; assuming --only paths..." + also= ;; esac unset only @@ -383,6 +377,8 @@ t,) ;; ,t) save_index && + git-ls-files --error-unmatch -- "$@" >/dev/null || exit + git-diff-files --name-only -z -- "$@" | ( cd "$TOP" @@ -411,7 +407,7 @@ t,) refuse_partial "Different in index and the last commit: $dirty_in_index" fi - commit_only=`git-ls-files -- "$@"` + commit_only=`git-ls-files --error-unmatch -- "$@"` || exit # Build the temporary index and update the real index # the same way. @@ -572,7 +568,10 @@ else PARENTS="" fi -run_status >>"$GIT_DIR"/COMMIT_EDITMSG +{ + test -z "$only_include_assumed" || echo "$only_include_assumed" + run_status +} >>"$GIT_DIR"/COMMIT_EDITMSG if [ "$?" != "0" -a ! -f "$GIT_DIR/MERGE_HEAD" ] then rm -f "$GIT_DIR/COMMIT_EDITMSG" 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..3c588c9d64 --- /dev/null +++ b/git-cvsserver.perl @@ -0,0 +1,2487 @@ +#!/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, + 'Questionable' => \&req_Questionable, + '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, + 'rlog' => \&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"); +} + +# Questionable filename \n +# Response expected: no. Additional data: no. +# Tell the server to check whether filename should be ignored, +# and if not, next time the server sends responses, send (in +# a M response) `?' followed by the directory and filename. +# filename must not contain `/'; it needs to be a file in the +# directory named by the most recent Directory request. +sub req_Questionable +{ + my ( $cmd, $data ) = @_; + + $state->{entries}{$state->{directory}.$data}{questionable} = 1; + + #$log->debug("req_Questionable : $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} ) and $git->{dir} ne "./" ? $git->{dir} . "/" : "" ) . "\n"; + + print $state->{CVSROOT} . "/$module/" . ( defined ( $git->{dir} ) and $git->{dir} ne "./" ? $git->{dir} . "/" : "" ) . "$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) ? $data : "[NULL]" )); + + argsplit("update"); + + # + # It may just be a client exploring the available heads/modukles + # in that case, list them as top level directories and leave it + # at that. Eclipse uses this technique to offer you a list of + # projects (heads in this case) to checkout. + # + if ($state->{module} eq '') { + print "E cvs update: Updating .\n"; + opendir HEADS, $state->{CVSROOT} . '/refs/heads'; + while (my $head = readdir(HEADS)) { + if (-f $state->{CVSROOT} . '/refs/heads/' . $head) { + print "E cvs update: New directory `$head'\n"; + } + } + closedir HEADS; + print "ok\n"; + return 1; + } + + + # 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(' ',@_).": $! $?"; + } else { + exec(@_) or die "$! $?"; # exec() can fail the executable can't be found + } + return wantarray ? @output : join('',@output); +} + + +1; diff --git a/git-fetch.sh b/git-fetch.sh index fcc24f85c3..0346d4a45c 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -164,6 +164,7 @@ fast_forward_local () { ;; *,$local) echo >&2 "* $1: fast forward to $3" + echo >&2 " from $local to $2" git-update-ref "$1" "$2" "$local" ;; *) @@ -320,7 +321,7 @@ 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 diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl index 0467a387e1..dae383f231 100755 --- a/git-fmt-merge-msg.perl +++ b/git-fmt-merge-msg.perl @@ -28,37 +28,30 @@ 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 $val; } -sub mergebase { - my ($other) = @_; - my $fh; - open $fh, '-|', 'git-merge-base', '--all', 'HEAD', $other or die "$!"; - my (@mb) = map { chomp; $_ } <$fh>; - close $fh or die "$!"; - return @mb; +sub current_branch { + my ($bra) = qx{git-symbolic-ref HEAD}; + chomp($bra); + $bra =~ s|^refs/heads/||; + if ($bra ne 'master') { + $bra = " into $bra"; + } else { + $bra = ""; + } + return $bra; } sub shortlog { - my ($tip, $limit, @base) = @_; - my ($fh, @result); - open $fh, '-|', ('git-log', "--max-count=$limit", '--topo-order', - '--pretty=oneline', $tip, map { "^$_" } @base) - 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; } @@ -140,7 +133,10 @@ for my $src (@src) { } push @msg, $this; } -print "Merge ", join("; ", @msg), "\n"; + +my $into = current_branch(); + +print "Merge ", join("; ", @msg), $into, "\n"; if (!repoconfig) { exit(0); @@ -151,8 +147,7 @@ my $limit = 20; for (@origin) { my ($sha1, $name) = @$_; - my @mb = mergebase($sha1); - my @log = shortlog($sha1, $limit + 1, @mb); + my @log = shortlog($sha1); if ($limit + 1 <= @log) { print "\n* $name: (" . scalar(@log) . " commits)\n"; } diff --git a/git-format-patch.sh b/git-format-patch.sh index eb75de4601..2bd26395ec 100755 --- a/git-format-patch.sh +++ b/git-format-patch.sh @@ -174,7 +174,7 @@ titleScript=' process_one () { perl -w -e ' my ($keep_subject, $num, $signoff, $commsg) = @ARGV; -my ($signoff_pattern, $done_header, $done_subject, $signoff_seen, +my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen, $last_was_signoff); if ($signoff) { @@ -228,6 +228,11 @@ while (<FH>) { $done_subject = 1; next; } + unless ($done_separator) { + print "\n"; + $done_separator = 1; + next if (/^$/); + } $last_was_signoff = 0; if (/Signed-off-by:/i) { diff --git a/git-merge.sh b/git-merge.sh index c258ea78bc..7be9e81f1f 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -13,6 +13,10 @@ LF=' all_strategies='recursive octopus resolve stupid ours' default_strategies='recursive' use_strategies= +if test "@@NO_PYTHON@@"; then + all_strategies='resolve octopus stupid ours' + default_strategies='resolve' +fi dropsave() { rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" \ diff --git a/git-mv.perl b/git-mv.perl index f3e859ae48..fe9c40e1b9 100755 --- a/git-mv.perl +++ b/git-mv.perl @@ -90,6 +90,15 @@ while(scalar @srcArgs > 0) { $dst = shift @dstArgs; $bad = ""; + for ($src, $dst) { + # Be nicer to end-users by doing ".//a/./b/.//./c" ==> "a/b/c" + s|^\./||; + s|/\./|/| while (m|/\./|); + s|//+|/|g; + # Also "a/b/../c" ==> "a/c" + 1 while (s,(^|/)[^/]+/\.\./,$1,); + } + if ($opt_v) { print "Checking rename of '$src' to '$dst'\n"; } 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 16d4359830..5956f0654e 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -3,10 +3,52 @@ # Copyright (c) 2005 Junio C Hamano. # -USAGE='<upstream> [<head>]' +USAGE='[--onto <newbase>] <upstream> [<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 + +The result of the following command: + + git-rebase --onto master~1 master topic + + would be: + + A'\''--B'\''--C'\'' topic + / + D---E---F---G master +' + . git-sh-setup -case $# in 1|2) ;; *) usage ;; esac +unset newbase +while case "$#" in 0) break ;; esac +do + case "$1" in + --onto) + test 2 -le "$#" || usage + newbase="$2" + shift + ;; + -*) + usage + ;; + *) + break + ;; + esac + shift +done # Make sure we do not have .dotest if mkdir .dotest @@ -30,37 +72,61 @@ case "$diff" in ;; esac -# The other head is given. Make sure it is valid. -other=$(git-rev-parse --verify "$1^0") || usage +# The upstream head must be given. Make sure it is valid. +upstream_name="$1" +upstream=`git rev-parse --verify "${upstream_name}^0"` || + die "invalid upstream $upstream_name" -# Make sure the branch to rebase is valid. -head=$(git-rev-parse --verify "${2-HEAD}^0") || exit +# If a hook exists, give it a chance to interrupt +if test -x "$GIT_DIR/hooks/pre-rebase" +then + "$GIT_DIR/hooks/pre-rebase" ${1+"$@"} || { + echo >&2 "The pre-rebase hook refused to rebase." + exit 1 + } +fi # If the branch to rebase is given, first switch to it. case "$#" in 2) + branch_name="$2" git-checkout "$2" || usage + ;; +*) + branch_name=`git symbolic-ref HEAD` || die "No current branch" + branch_name=`expr "$branch_name" : 'refs/heads/\(.*\)'` + ;; esac +branch=$(git-rev-parse --verify "${branch_name}^0") || exit + +# Make sure the branch to rebase onto is valid. +onto_name=${newbase-"$upstream_name"} +onto=$(git-rev-parse --verify "${onto_name}^0") || exit -mb=$(git-merge-base "$other" "$head") +# Now we are rebasing commits $upstream..$branch on top of $onto -# Check if we are already based on $other. -if test "$mb" = "$other" +# Check if we are already based on $onto, but this should be +# done only when upstream and onto are the same. +if test "$upstream" = "onto" then - echo >&2 "Current branch `git-symbolic-ref HEAD` is up to date." - exit 0 + mb=$(git-merge-base "$onto" "$branch") + if test "$mb" = "$onto" + then + echo >&2 "Current branch $branch_name is up to date." + exit 0 + fi fi -# Rewind the head to "$other" -git-reset --hard "$other" +# Rewind the head to "$onto"; this saves our current head in ORIG_HEAD. +git-reset --hard "$onto" -# If the $other is a proper descendant of the tip of the branch, then +# If the $onto is a proper descendant of the tip of the branch, then # we just fast forwarded. -if test "$mb" = "$head" +if test "$mb" = "$onto" then - echo >&2 "Fast-forwarded $head to $other." + echo >&2 "Fast-forwarded $branch to $newbase." exit 0 fi -git-format-patch -k --stdout --full-index "$other" ORIG_HEAD | +git-format-patch -k --stdout --full-index "$upstream" ORIG_HEAD | git am --binary -3 -k 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-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 3f1b3ca788..b0d095b4e9 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -31,10 +31,10 @@ sub cleanup_compose_files(); my $compose_filename = ".msg.$$"; # Variables we fill in automatically, or via prompting: -my (@to,@cc,$initial_reply_to,$initial_subject,@files,$from,$compose); +my (@to,@cc,@initial_cc,$initial_reply_to,$initial_subject,@files,$from,$compose); # Behavior modification variables -my ($chain_reply_to, $smtp_server, $quiet) = (1, "localhost", 0); +my ($chain_reply_to, $smtp_server, $quiet, $suppress_from, $no_signed_off_cc) = (1, "localhost", 0, 0, 0); # Example reply to: #$initial_reply_to = ''; #<20050203173208.GA23964@foobar.com>'; @@ -48,32 +48,40 @@ my $rc = GetOptions("from=s" => \$from, "in-reply-to=s" => \$initial_reply_to, "subject=s" => \$initial_subject, "to=s" => \@to, + "cc=s" => \@initial_cc, "chain-reply-to!" => \$chain_reply_to, "smtp-server=s" => \$smtp_server, "compose" => \$compose, "quiet" => \$quiet, + "suppress-from" => \$suppress_from, + "no-signed-off-cc" => \$no_signed_off_cc, ); # 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) { @@ -197,6 +205,9 @@ Options: --to Specify the primary "To:" line of the email. + --cc Specify an initial "Cc:" list for the entire series + of emails. + --compose Use \$EDITOR to edit an introductory message for the patch series. @@ -212,13 +223,19 @@ Options: email sent, rather than to the first email sent. Defaults to on. + --no-signed-off-cc Suppress the automatic addition of email addresses + that appear in a Signed-off-by: line, to the cc: list. + Note: Using this option is not recommended. + --smtp-server If set, specifies the outgoing SMTP server to use. Defaults to localhost. + --suppress-from Supress sending emails to yourself if your address + appears in a From: line. + --quiet Make git-send-email less verbose. One line per email should be all that is output. - Error: Please specify a file or a directory on the command line. EOT exit(1); @@ -290,7 +307,7 @@ $subject = $initial_subject; foreach my $t (@files) { open(F,"<",$t) or die "can't open file $t"; - @cc = (); + @cc = @initial_cc; my $found_mbox = 0; my $header_done = 0; $message = ""; @@ -304,6 +321,7 @@ foreach my $t (@files) { $subject = $1; } elsif (/^(Cc|From):\s+(.*)$/) { + next if ($2 eq $from && $suppress_from); printf("(mbox) Adding cc: %s from line '%s'\n", $2, $_) unless $quiet; push @cc, $2; @@ -332,7 +350,7 @@ foreach my $t (@files) { } } else { $message .= $_; - if (/^Signed-off-by: (.*)$/i) { + if (/^Signed-off-by: (.*)$/i && !$no_signed_off_cc) { my $c = $1; chomp $c; push @cc, $c; diff --git a/git-svnimport.perl b/git-svnimport.perl index f17d5a27c8..639aa41861 100755 --- a/git-svnimport.perl +++ b/git-svnimport.perl @@ -10,10 +10,10 @@ # 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; +use File::Copy; use File::Spec; use File::Temp qw(tempfile); use File::Path qw(mkpath); @@ -30,19 +30,21 @@ die "Need SVN:Core 1.2.1 or better" if $SVN::Core::VERSION lt "1.2.1"; $SIG{'PIPE'}="IGNORE"; $ENV{'TZ'}="UTC"; -our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_s,$opt_l,$opt_d,$opt_D); +our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T, + $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D); sub usage() { print STDERR <<END; Usage: ${\basename $0} # fetch/update GIT from SVN [-o branch-for-HEAD] [-h] [-v] [-l max_rev] [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname] - [-d|-D] [-i] [-u] [-s start_chg] [-m] [-M regex] [SVN_URL] + [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg] + [-m] [-M regex] [-A author_file] [SVN_URL] END exit(1); } -getopts("b:C:dDhil:mM:o:s:t:T:uv") or usage(); +getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage(); usage if $opt_h; my $tag_name = $opt_t || "tags"; @@ -67,6 +69,25 @@ if ($opt_M) { push (@mergerx, qr/$opt_M/); } +# Absolutize filename now, since we will have chdir'ed by the time we +# get around to opening it. +$opt_A = File::Spec->rel2abs($opt_A) if $opt_A; + +our %users = (); +our $users_file = undef; +sub read_users($) { + $users_file = File::Spec->rel2abs(@_); + die "Cannot open $users_file\n" unless -f $users_file; + open(my $authors,$users_file); + while(<$authors>) { + chomp; + next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; + (my $user,my $name,my $email) = ($1,$2,$3); + $users{$user} = [$name,$email]; + } + close($authors); +} + select(STDERR); $|=1; select(STDOUT); @@ -113,16 +134,40 @@ sub file { DIR => File::Spec->tmpdir(), UNLINK => 1); print "... $rev $path ...\n" if $opt_v; - my $pool = SVN::Pool->new(); - eval { $self->{'svn'}->get_file($path,$rev,$fh,$pool); }; - $pool->clear; + my (undef, $properties); + eval { (undef, $properties) + = $self->{'svn'}->get_file($path,$rev,$fh); }; if($@) { return undef if $@ =~ /Attempted to get checksum/; die $@; } + my $mode; + if (exists $properties->{'svn:executable'}) { + $mode = '0755'; + } else { + $mode = '0644'; + } close ($fh); - return $name; + return ($name, $mode); +} + +sub ignore { + my($self,$path,$rev) = @_; + + print "... $rev $path ...\n" if $opt_v; + my (undef,undef,$properties) + = $self->{'svn'}->get_dir($path,$rev,undef); + if (exists $properties->{'svn:ignore'}) { + my ($fh, $name) = tempfile('gitsvn.XXXXXX', + DIR => File::Spec->tmpdir(), + UNLINK => 1); + print $fh $properties->{'svn:ignore'}; + close($fh); + return $name; + } else { + return undef; + } } package main; @@ -264,6 +309,14 @@ EOM -d $git_dir or die "Could not create git subdir ($git_dir).\n"; +my $default_authors = "$git_dir/svn-authors"; +if ($opt_A) { + read_users($opt_A); + copy($opt_A,$default_authors) or die "Copy failed: $!"; +} else { + read_users($default_authors) if -f $default_authors; +} + open BRANCHES,">>", "$git_dir/svn2git"; sub node_kind($$$) { @@ -297,7 +350,7 @@ sub get_file($$$) { my $svnpath = revert_split_path($branch,$path); # now get it - my $name; + my ($name,$mode); if($opt_d) { my($req,$res); @@ -317,21 +370,53 @@ sub get_file($$$) { return undef if $res->code == 301; # directory? die $res->status_line." at $url\n"; } + $mode = '0644'; # can't obtain mode via direct http request? } else { - $name = $svn->file("$svnpath",$rev); + ($name,$mode) = $svn->file("$svnpath",$rev); 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; unlink $name; - my $mode = "0644"; # SV does not seem to store any file modes return [$mode, $sha, $path]; } +sub get_ignore($$$$$) { + my($new,$old,$rev,$branch,$path) = @_; + + return unless $opt_I; + my $svnpath = revert_split_path($branch,$path); + my $name = $svn->ignore("$svnpath",$rev); + if ($path eq '/') { + $path = $opt_I; + } else { + $path = File::Spec->catfile($path,$opt_I); + } + if (defined $name) { + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $name) + or die "Cannot create object: $!\n"; + } + my $sha = <$F>; + chomp $sha; + close $F; + unlink $name; + push(@$new,['0644',$sha,$path]); + } else { + push(@$old,$path); + } +} + sub split_path($$) { my($rev,$path) = @_; my $branch; @@ -398,7 +483,12 @@ 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; @@ -423,6 +513,10 @@ sub commit { if (not defined $author) { $author_name = $author_email = "unknown"; + } elsif (defined $users_file) { + die "User $author is not listed in $users_file\n" + unless exists $users{$author}; + ($author_name,$author_email) = @{$users{$author}}; } elsif ($author =~ /^(.*?)\s+<(.*)>$/) { ($author_name, $author_email) = ($1, $2); } else { @@ -532,6 +626,9 @@ sub commit { my $opath = $action->[3]; print STDERR "$revision: $branch: could not fetch '$opath'\n"; } + } elsif ($node_kind eq $SVN::Node::dir) { + get_ignore(\@new, \@old, $revision, + $branch,$path); } } elsif ($action->[0] eq "D") { push(@old,$path); @@ -540,6 +637,9 @@ sub commit { if ($node_kind eq $SVN::Node::file) { my $f = get_file($revision,$branch,$path); push(@new,$f) if $f; + } elsif ($node_kind eq $SVN::Node::dir) { + get_ignore(\@new, \@old, $revision, + $branch,$path); } } else { die "$revision: unknown action '".$action->[0]."' for $path\n"; @@ -554,7 +654,11 @@ 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>) { @@ -650,6 +754,7 @@ sub commit { $pr->reader(); $message =~ s/[\s\n]+\z//; + $message = "r$revision: $message" if $opt_r; print $pw "$message\n" or die "Error writing to git-commit-tree: $!\n"; diff --git a/git-tag.sh b/git-tag.sh index c74e1b4151..76e51ed174 100755 --- a/git-tag.sh +++ b/git-tag.sh @@ -1,7 +1,7 @@ #!/bin/sh # Copyright (c) 2005 Linus Torvalds -USAGE='[-a | -s | -u <key-id>] [-f | -d] [-m <msg>] <tagname> [<head>]' +USAGE='-l [<pattern>] | [-a | -s | -u <key-id>] [-f | -d] [-m <msg>] <tagname> [<head>]' SUBDIRECTORY_OK='Yes' . git-sh-setup @@ -10,6 +10,7 @@ signed= force= message= username= +list= while case "$#" in 0) break ;; esac do case "$1" in @@ -23,6 +24,17 @@ do -f) force=1 ;; + -l) + cd "$GIT_DIR/refs" && + case "$#" in + 1) + find tags -type f -print ;; + *) + shift + find tags -type f -print | grep "$@" ;; + esac + exit $? + ;; -m) annotate=1 shift diff --git a/git-verify-tag.sh b/git-verify-tag.sh index 726b1e706b..36f171b302 100755 --- a/git-verify-tag.sh +++ b/git-verify-tag.sh @@ -4,9 +4,21 @@ USAGE='<tag>' SUBDIRECTORY_OK='Yes' . git-sh-setup +verbose= +while case $# in 0) break;; esac +do + case "$1" in + -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) + verbose=t ;; + *) + break ;; + esac + shift +done + if [ "$#" != "1" ] then - usage + usage fi type="$(git-cat-file -t "$1" 2>/dev/null)" || @@ -15,6 +27,13 @@ type="$(git-cat-file -t "$1" 2>/dev/null)" || test "$type" = tag || die "$1: cannot verify a non-tag object of type $type." +case "$verbose" in +t) + git-cat-file -p "$1" | + sed -n -e '/^-----BEGIN PGP SIGNATURE-----/q' -e p + ;; +esac + git-cat-file tag "$1" >"$GIT_DIR/.tmp-vtag" || exit 1 cat "$GIT_DIR/.tmp-vtag" | sed '/-----BEGIN PGP/Q' | @@ -230,62 +230,141 @@ static void show_man_page(char *git_cmd) execlp("man", "man", page, NULL); } +static int cmd_version(int argc, char **argv, char **envp) +{ + printf("git version %s\n", GIT_VERSION); + return 0; +} + +static int cmd_help(int argc, char **argv, char **envp) +{ + char *help_cmd = argv[1]; + if (!help_cmd) + cmd_usage(git_exec_path(), NULL); + show_man_page(help_cmd); + return 0; +} + +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +static void handle_internal_command(int argc, char **argv, char **envp) +{ + const char *cmd = argv[0]; + static struct cmd_struct { + const char *cmd; + int (*fn)(int, char **, char **); + } commands[] = { + { "version", cmd_version }, + { "help", cmd_help }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(commands); i++) { + struct cmd_struct *p = commands+i; + if (strcmp(p->cmd, cmd)) + continue; + exit(p->fn(argc, argv, envp)); + } +} + int main(int argc, char **argv, char **envp) { + char *cmd = argv[0]; + char *slash = strrchr(cmd, '/'); char git_command[PATH_MAX + 1]; - char wd[PATH_MAX + 1]; - int i, show_help = 0; - const char *exec_path; + const char *exec_path = NULL; + + /* + * Take the basename of argv[0] as the command + * name, and the dirname as the default exec_path + * if it's an absolute path and we don't have + * anything better. + */ + if (slash) { + *slash++ = 0; + if (*cmd == '/') + exec_path = cmd; + cmd = slash; + } - getcwd(wd, PATH_MAX); + /* + * "git-xxxx" is the same as "git xxxx", but we obviously: + * + * - cannot take flags in between the "git" and the "xxxx". + * - cannot execute it externally (since it would just do + * the same thing over again) + * + * So we just directly call the internal command handler, and + * die if that one cannot handle it. + */ + if (!strncmp(cmd, "git-", 4)) { + cmd += 4; + argv[0] = cmd; + handle_internal_command(argc, argv, envp); + die("cannot handle %s internally", cmd); + } - for (i = 1; i < argc; i++) { - char *arg = argv[i]; + /* Default command: "help" */ + cmd = "help"; - if (!strcmp(arg, "help")) { - show_help = 1; - continue; - } + /* Look for flags.. */ + while (argc > 1) { + cmd = *++argv; + argc--; - if (strncmp(arg, "--", 2)) + if (strncmp(cmd, "--", 2)) break; - arg += 2; + cmd += 2; + + /* + * For legacy reasons, the "version" and "help" + * commands can be written with "--" prepended + * to make them look like flags. + */ + if (!strcmp(cmd, "help")) + break; + if (!strcmp(cmd, "version")) + break; - if (!strncmp(arg, "exec-path", 9)) { - arg += 9; - if (*arg == '=') { - exec_path = arg + 1; - git_set_exec_path(exec_path); - } else { - puts(git_exec_path()); - exit(0); + /* + * Check remaining flags (which by now must be + * "--exec-path", but maybe we will accept + * other arguments some day) + */ + if (!strncmp(cmd, "exec-path", 9)) { + cmd += 9; + if (*cmd == '=') { + git_set_exec_path(cmd + 1); + continue; } - } - else if (!strcmp(arg, "version")) { - printf("git version %s\n", GIT_VERSION); + puts(git_exec_path()); exit(0); } - else if (!strcmp(arg, "help")) - show_help = 1; - else if (!show_help) - cmd_usage(NULL, NULL); - } - - if (i >= argc || show_help) { - if (i >= argc) - cmd_usage(git_exec_path(), NULL); - - show_man_page(argv[i]); + cmd_usage(NULL, NULL); } - + argv[0] = cmd; + + /* + * We search for git commands in the following order: + * - git_exec_path() + * - the path of the "git" command if we could find it + * in $0 + * - the regular PATH. + */ + if (exec_path) + prepend_to_path(exec_path, strlen(exec_path)); exec_path = git_exec_path(); prepend_to_path(exec_path, strlen(exec_path)); - execv_git_cmd(argv + i); + /* See if it's an internal command */ + handle_internal_command(argc, argv, envp); + + /* .. then try the external ones */ + execv_git_cmd(argv); if (errno == ENOENT) - cmd_usage(exec_path, "'%s' is not a git-command", argv[i]); + cmd_usage(exec_path, "'%s' is not a git-command", cmd); fprintf(stderr, "Failed to run command '%s': %s\n", git_command, strerror(errno)); @@ -1936,7 +1936,7 @@ proc findfiles {} { global selectedline numcommits lineid ctext global ffileline finddidsel parents nparents global findinprogress findstartline findinsertpos - global treediffs fdiffids fdiffsneeded fdiffpos + global treediffs fdiffid fdiffsneeded fdiffpos global findmergefiles if {$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/ls-files.c b/ls-files.c index 7024cf18e1..df25c8c012 100644 --- a/ls-files.c +++ b/ls-files.c @@ -20,11 +20,14 @@ 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; static const char *prefix = NULL; static const char **pathspec = NULL; +static int error_unmatch = 0; +static char *ps_matched = NULL; static const char *tag_cached = ""; static const char *tag_unmerged = ""; @@ -276,8 +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; @@ -325,7 +331,8 @@ static int cmp_name(const void *p1, const void *p2) * Match a pathspec against a filename. The first "len" characters * are the common prefix */ -static int match(const char **spec, const char *filename, int len) +static int match(const char **spec, char *ps_matched, + const char *filename, int len) { const char *m; @@ -333,17 +340,24 @@ static int match(const char **spec, const char *filename, int len) int matchlen = strlen(m + len); if (!matchlen) - return 1; + goto matched; if (!strncmp(m + len, filename + len, matchlen)) { if (m[len + matchlen - 1] == '/') - return 1; + goto matched; switch (filename[len + matchlen]) { case '/': case '\0': - return 1; + goto matched; } } if (!fnmatch(m + len, filename + len, 0)) - return 1; + goto matched; + if (ps_matched) + ps_matched++; + continue; + matched: + if (ps_matched) + *ps_matched = 1; + return 1; } return 0; } @@ -356,7 +370,7 @@ static void show_dir_entry(const char *tag, struct nond_on_fs *ent) if (len >= ent->len) die("git-ls-files: internal error - directory entry not superset of prefix"); - if (pathspec && !match(pathspec, ent->name, len)) + if (pathspec && !match(pathspec, ps_matched, ent->name, len)) return; fputs(tag, stdout); @@ -444,9 +458,26 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) if (len >= ce_namelen(ce)) die("git-ls-files: internal error - cache entry not superset of prefix"); - if (pathspec && !match(pathspec, ce->name, len)) + 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, @@ -523,7 +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); } } @@ -596,7 +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>]*"; @@ -621,13 +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")) { @@ -699,6 +732,10 @@ int main(int argc, const char **argv) prefix_offset = 0; continue; } + if (!strcmp(arg, "--error-unmatch")) { + error_unmatch = 1; + continue; + } if (*arg == '-') usage(ls_files_usage); break; @@ -710,6 +747,14 @@ int main(int argc, const char **argv) if (pathspec) verify_pathspec(); + /* Treat unmatching pathspec elements as errors */ + if (pathspec && error_unmatch) { + int num; + for (num = 0; pathspec[num]; num++) + ; + ps_matched = xcalloc(1, num); + } + if (show_ignored && !exc_given) { fprintf(stderr, "%s: --ignored needs some exclude pattern\n", argv[0]); @@ -725,5 +770,21 @@ int main(int argc, const char **argv) if (prefix) prune_cache(); show_files(); + + if (ps_matched) { + /* We need to make sure all pathspec matched otherwise + * it is an error. + */ + int num, errors = 0; + for (num = 0; pathspec[num]; num++) { + if (ps_matched[num]) + continue; + error("pathspec '%s' did not match any.", + pathspec[num] + prefix_offset); + errors++; + } + return errors ? 1 : 0; + } + return 0; } diff --git a/mailinfo.c b/mailinfo.c index ff2d4d4038..3c56f8c108 100644 --- a/mailinfo.c +++ b/mailinfo.c @@ -7,7 +7,9 @@ #include <stdlib.h> #include <string.h> #include <ctype.h> +#ifndef NO_ICONV #include <iconv.h> +#endif #include "git-compat-util.h" #include "cache.h" @@ -469,6 +471,7 @@ static int decode_b_segment(char *in, char *ot, char *ep) static void convert_to_utf8(char *line, char *charset) { +#ifndef NO_ICONV char *in, *out; size_t insize, outsize, nrc; char outbuf[4096]; /* cheat */ @@ -501,6 +504,7 @@ static void convert_to_utf8(char *line, char *charset) return; *out = 0; strcpy(line, outbuf); +#endif } static void decode_header_bq(char *it) 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-check.c b/pack-check.c index 67a7ecdf16..eca32b6cab 100644 --- a/pack-check.c +++ b/pack-check.c @@ -84,7 +84,7 @@ static void show_pack_info(struct packed_git *p) char type[20]; unsigned long size; unsigned long store_size; - int delta_chain_length; + unsigned int delta_chain_length; if (nth_packed_object_sha1(p, i, sha1)) die("internal error pack-check nth-packed-object"); @@ -98,7 +98,7 @@ static void show_pack_info(struct packed_git *p) if (!delta_chain_length) printf("%-6s %lu %u\n", type, size, e.offset); else - printf("%-6s %lu %u %d %s\n", type, size, e.offset, + printf("%-6s %lu %u %u %s\n", type, size, e.offset, delta_chain_length, sha1_to_hex(base_sha1)); } diff --git a/pack-objects.c b/pack-objects.c index 8f352aa6c1..136a7f5aad 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -3,6 +3,7 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "diff.h" #include <sys/time.h> #include <signal.h> @@ -27,6 +28,13 @@ struct object_entry { 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. + */ }; /* @@ -49,7 +57,7 @@ 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; @@ -91,7 +99,7 @@ static int reused_delta = 0; static int pack_revindex_ix(struct packed_git *p) { - unsigned int ui = (unsigned int) p; + unsigned long ui = (unsigned long)p; int i; ui = ui ^ (ui >> 16); /* defeat structure alignment */ @@ -231,7 +239,8 @@ 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]; @@ -241,6 +250,9 @@ static unsigned long write_object(struct sha1file *f, struct object_entry *entry enum object_type obj_type; int to_reuse = 0; + if (entry->preferred_base) + return 0; + obj_type = entry->type; if (! entry->in_pack) to_reuse = 0; /* can't reuse what we don't have */ @@ -335,20 +347,22 @@ static void write_pack_file(void) do_progress = progress; } if (do_progress) - fprintf(stderr, "Writing %d objects.\n", nr_objects); + 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); + 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_objects; + unsigned percent = written * 100 / nr_result; if (progress_update || percent != last_percent) { fprintf(stderr, "%4u%% (%u/%u) done\r", - percent, written, nr_objects); + percent, written, nr_result); progress_update = 0; last_percent = percent; } @@ -356,16 +370,17 @@ static void write_pack_file(void) } if (do_progress) fputc('\n', stderr); - + done: sha1close(f, pack_file_sha1, 1); } 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]; /* @@ -390,7 +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); @@ -400,27 +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; - - 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; + int ix, status = 0; + + 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; @@ -428,45 +555,94 @@ 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; - if (found_pack) { - entry->in_pack = found_pack; - entry->in_pack_offset = found_offset; + + 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; } - nr_objects = idx+1; - return 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 int locate_object_entry_hash(unsigned char *sha1) +static void add_pbase_tree(struct tree_desc *tree, struct name_path *up) { - 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; + 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); + } + } } - return -1 - i; } -static struct object_entry *locate_object_entry(unsigned char *sha1) +static void add_preferred_base(unsigned char *sha1) { - int i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; + 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 (entry->in_pack) { + if (entry->in_pack && !entry->preferred_base) { unsigned char base[20]; unsigned long size; struct object_entry *base_entry; @@ -485,7 +661,8 @@ static void check_object(struct object_entry *entry) */ if (!no_reuse_delta && entry->in_pack_type == OBJ_DELTA && - (base_entry = locate_object_entry(base))) { + (base_entry = locate_object_entry(base)) && + (!base_entry->preferred_base)) { /* Depth value does not matter - find_deltas() * will never consider reused delta as the @@ -523,25 +700,6 @@ static void check_object(struct object_entry *entry) sha1_to_hex(entry->sha1), type); } -static void hash_objects(void) -{ - int i; - struct object_entry *oe; - - object_ix_hashsz = nr_objects * 2; - object_ix = xcalloc(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) { - error("the same object '%s' added twice", - sha1_to_hex(oe->sha1)); - continue; - } - ix = -1 - ix; - object_ix[ix] = i + 1; - } -} - static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { struct object_entry *child = me->delta_child; @@ -560,14 +718,26 @@ static void get_object_details(void) int i; struct object_entry *entry; - hash_objects(); prepare_pack_ix(); for (i = 0, entry = objects; i < nr_objects; i++, entry++) check_object(entry); - for (i = 0, entry = objects; i < nr_objects; i++, entry++) - if (!entry->delta && entry->delta_child) - entry->delta_limit = - check_delta_limit(entry, 1); + + 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 *); @@ -598,6 +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(void) +{ + 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) @@ -608,6 +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) @@ -632,6 +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; @@ -640,9 +834,15 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de if (cur_entry->type != old_entry->type) return -1; - /* If the current object is at edge, take the depth the objects - * that depend on the current object into account -- otherwise - * they would become too deep. + /* 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) @@ -651,11 +851,10 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de } size = cur_entry->size; - if (size < 50) - return -1; 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; @@ -668,8 +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, @@ -679,6 +897,7 @@ 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; } @@ -701,7 +920,7 @@ static void find_deltas(struct object_entry **list, int window, int depth) i = nr_objects; idx = 0; if (progress) - fprintf(stderr, "Deltifying %d objects.\n", nr_objects); + fprintf(stderr, "Deltifying %d objects.\n", nr_result); while (--i >= 0) { struct object_entry *entry = list[i]; @@ -710,12 +929,14 @@ static void find_deltas(struct object_entry **list, int window, int depth) char type[10]; int j; - processed++; + if (!entry->preferred_base) + processed++; + if (progress) { - unsigned percent = processed * 100 / nr_objects; + unsigned percent = processed * 100 / nr_result; if (percent != last_percent || progress_update) { fprintf(stderr, "%4u%% (%u/%u) done\r", - percent, processed, nr_objects); + percent, processed, nr_result); progress_update = 0; last_percent = percent; } @@ -895,44 +1116,40 @@ int main(int argc, char **argv) } while (fgets(line, sizeof(line), stdin) != NULL) { - unsigned int hash; - char *p; unsigned char sha1[20]; - if (progress_update) { - fprintf(stderr, "Counting objects...%d\r", nr_objects); - progress_update = 0; + 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,},}; @@ -948,6 +1165,6 @@ int main(int argc, char **argv) } if (progress) fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", - nr_objects, written, written_delta, reused, reused_delta); + nr_result, written, written_delta, reused, reused_delta); return 0; } diff --git a/pack-redundant.c b/pack-redundant.c index 1869b38b72..cd81f5a66e 100644 --- a/pack-redundant.c +++ b/pack-redundant.c @@ -45,7 +45,7 @@ static inline void llist_item_put(struct llist_item *item) free_nodes = item; } -static inline struct llist_item *llist_item_get() +static inline struct llist_item *llist_item_get(void) { struct llist_item *new; if ( free_nodes ) { @@ -275,7 +275,7 @@ static void cmp_two_packs(struct pack_list *p1, struct pack_list *p2) } } -void pll_free(struct pll *l) +static void pll_free(struct pll *l) { struct pll *old; struct pack_list *opl; 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 da0fcf035e..c56b572d05 100644 --- a/read-tree.c +++ b/read-tree.c @@ -404,7 +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; @@ -151,10 +151,15 @@ static int do_for_each_ref(const char *base, int (*fn)(const char *path, const u break; continue; } - if (read_ref(git_path("%s", path), sha1) < 0) + if (read_ref(git_path("%s", path), sha1) < 0) { + fprintf(stderr, "%s points nowhere!", path); continue; - if (!has_sha1_file(sha1)) + } + if (!has_sha1_file(sha1)) { + fprintf(stderr, "%s does not point to a valid " + "commit object!", path); continue; + } retval = fn(path, sha1); if (retval) break; diff --git a/rev-list.c b/rev-list.c index 63391fc113..67d2a483fc 100644 --- a/rev-list.c +++ b/rev-list.c @@ -27,9 +27,10 @@ static const char rev_list_usage[] = " ordering output:\n" " --merge-order [ --show-breaks ]\n" " --topo-order\n" +" --date-order\n" " formatting output:\n" " --parents\n" -" --objects\n" +" --objects | --objects-edge\n" " --unpacked\n" " --header | --pretty\n" " --abbrev=nr | --no-abbrev\n" @@ -43,6 +44,7 @@ static int bisect_list = 0; static int tag_objects = 0; static int tree_objects = 0; static int blob_objects = 0; +static int edge_hint = 0; static int verbose_header = 0; static int abbrev = DEFAULT_ABBREV; static int show_parents = 0; @@ -56,10 +58,41 @@ static int merge_order = 0; static int show_breaks = 0; static int stop_traversal = 0; static int topo_order = 0; +static int lifo = 1; static int no_merges = 0; static const char **paths = NULL; static int remove_empty_trees = 0; +struct name_path { + struct name_path *up; + int elem_len; + const char *elem; +}; + +static char *path_name(struct name_path *path, const char *name) +{ + struct name_path *p; + char *n, *m; + int nlen = strlen(name); + int len = nlen + 1; + + for (p = path; p; p = p->up) { + if (p->elem_len) + len += p->elem_len + 1; + } + n = xmalloc(len); + m = n + len - (nlen + 1); + strcpy(m, name); + for (p = path; p; p = p->up) { + if (p->elem_len) { + m -= p->elem_len + 1; + memcpy(m, p->elem, p->elem_len); + m[p->elem_len] = '/'; + } + } + return n; +} + static void show_commit(struct commit *commit) { commit->object.flags |= SHOWN; @@ -171,17 +204,23 @@ static int process_commit(struct commit * commit) return CONTINUE; } -static struct object_list **add_object(struct object *obj, struct object_list **p, const char *name) +static struct object_list **add_object(struct object *obj, + struct object_list **p, + struct name_path *path, + const char *name) { struct object_list *entry = xmalloc(sizeof(*entry)); entry->item = obj; entry->next = *p; - entry->name = name; + entry->name = path_name(path, name); *p = entry; return &entry->next; } -static struct object_list **process_blob(struct blob *blob, struct object_list **p, const char *name) +static struct object_list **process_blob(struct blob *blob, + struct object_list **p, + struct name_path *path, + const char *name) { struct object *obj = &blob->object; @@ -190,13 +229,17 @@ static struct object_list **process_blob(struct blob *blob, struct object_list * if (obj->flags & (UNINTERESTING | SEEN)) return p; obj->flags |= SEEN; - return add_object(obj, p, name); + return add_object(obj, p, path, name); } -static struct object_list **process_tree(struct tree *tree, struct object_list **p, const char *name) +static struct object_list **process_tree(struct tree *tree, + struct object_list **p, + struct name_path *path, + const char *name) { struct object *obj = &tree->object; struct tree_entry_list *entry; + struct name_path me; if (!tree_objects) return p; @@ -205,15 +248,18 @@ static struct object_list **process_tree(struct tree *tree, struct object_list * if (parse_tree(tree) < 0) die("bad tree object %s", sha1_to_hex(obj->sha1)); obj->flags |= SEEN; - p = add_object(obj, p, name); + p = add_object(obj, p, path, name); + me.up = path; + me.elem = name; + me.elem_len = strlen(name); entry = tree->entries; tree->entries = NULL; while (entry) { struct tree_entry_list *next = entry->next; if (entry->directory) - p = process_tree(entry->item.tree, p, entry->name); + p = process_tree(entry->item.tree, p, &me, entry->name); else - p = process_blob(entry->item.blob, p, entry->name); + p = process_blob(entry->item.blob, p, &me, entry->name); free(entry); entry = next; } @@ -228,7 +274,7 @@ static void show_commit_list(struct commit_list *list) while (list) { struct commit *commit = pop_most_recent_commit(&list, SEEN); - p = process_tree(commit->tree, p, ""); + p = process_tree(commit->tree, p, NULL, ""); if (process_commit(commit) == STOP) break; } @@ -239,22 +285,22 @@ static void show_commit_list(struct commit_list *list) continue; if (obj->type == tag_type) { obj->flags |= SEEN; - p = add_object(obj, p, name); + p = add_object(obj, p, NULL, name); continue; } if (obj->type == tree_type) { - p = process_tree((struct tree *)obj, p, name); + p = process_tree((struct tree *)obj, p, NULL, name); continue; } if (obj->type == blob_type) { - p = process_blob((struct blob *)obj, p, name); + p = process_blob((struct blob *)obj, p, NULL, name); continue; } 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) { @@ -428,16 +474,32 @@ static struct commit_list *find_bisection(struct commit_list *list) return best; } +static void mark_edge_parents_uninteresting(struct commit *commit) +{ + struct commit_list *parents; + + for (parents = commit->parents; parents; parents = parents->next) { + struct commit *parent = parents->item; + if (!(parent->object.flags & UNINTERESTING)) + continue; + mark_tree_uninteresting(parent->tree); + if (edge_hint && !(parent->object.flags & SHOWN)) { + parent->object.flags |= SHOWN; + printf("-%s\n", sha1_to_hex(parent->object.sha1)); + } + } +} + static void mark_edges_uninteresting(struct commit_list *list) { for ( ; list; list = list->next) { - struct commit_list *parents = list->item->parents; + struct commit *commit = list->item; - for ( ; parents; parents = parents->next) { - struct commit *commit = parents->item; - if (commit->object.flags & UNINTERESTING) - mark_tree_uninteresting(commit->tree); + if (commit->object.flags & UNINTERESTING) { + mark_tree_uninteresting(commit->tree); + continue; } + mark_edge_parents_uninteresting(commit); } } @@ -655,7 +717,7 @@ static struct commit_list *limit_list(struct commit_list *list) static void add_pending_object(struct object *obj, const char *name) { - add_object(obj, &pending_objects, name); + add_object(obj, &pending_objects, NULL, name); } static struct commit *get_commit_reference(const char *name, const unsigned char *sha1, unsigned int flags) @@ -841,6 +903,13 @@ int main(int argc, const char **argv) blob_objects = 1; continue; } + if (!strcmp(arg, "--objects-edge")) { + tag_objects = 1; + tree_objects = 1; + blob_objects = 1; + edge_hint = 1; + continue; + } if (!strcmp(arg, "--unpacked")) { unpacked = 1; limited = 1; @@ -856,6 +925,13 @@ int main(int argc, const char **argv) } if (!strcmp(arg, "--topo-order")) { topo_order = 1; + lifo = 1; + limited = 1; + continue; + } + if (!strcmp(arg, "--date-order")) { + topo_order = 1; + lifo = 0; limited = 1; continue; } @@ -940,7 +1016,7 @@ int main(int argc, const char **argv) if (limited) list = limit_list(list); if (topo_order) - sort_in_topological_order(&list); + sort_in_topological_order(&list, lifo); show_commit_list(list); } else { #ifndef NO_OPENSSL diff --git a/rev-parse.c b/rev-parse.c index 70a82714ca..610eacb35a 100644 --- a/rev-parse.c +++ b/rev-parse.c @@ -43,11 +43,13 @@ static int is_rev_argument(const char *arg) "--min-age=", "--no-merges", "--objects", + "--objects-edge", "--parents", "--pretty", "--show-breaks", "--sparse", "--topo-order", + "--date-order", "--unpacked", NULL }; 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 aa09b4646a..a80d849f15 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -864,7 +864,7 @@ void packed_object_info_detail(struct pack_entry *e, char *type, unsigned long *size, unsigned long *store_size, - int *delta_chain_length, + unsigned int *delta_chain_length, unsigned char *base_sha1) { struct packed_git *p = e->p; @@ -878,7 +878,7 @@ void packed_object_info_detail(struct pack_entry *e, if (kind != OBJ_DELTA) *delta_chain_length = 0; else { - int chain_length = 0; + unsigned int chain_length = 0; memcpy(base_sha1, pack, 20); do { struct pack_entry base_ent; diff --git a/show-branch.c b/show-branch.c index 511fd3b656..5a86ae2f9e 100644 --- a/show-branch.c +++ b/show-branch.c @@ -535,6 +535,7 @@ int main(int ac, char **av) int num_rev, i, extra = 0; int all_heads = 0, all_tags = 0; int all_mask, all_revs; + int lifo = 1; char head_path[128]; const char *head_path_p; int head_path_len; @@ -544,7 +545,6 @@ int main(int ac, char **av) int no_name = 0; int sha1_name = 0; int shown_merge_point = 0; - int topo_order = 0; int with_current_branch = 0; int head_at = -1; @@ -586,7 +586,9 @@ int main(int ac, char **av) else if (!strcmp(arg, "--independent")) independent = 1; else if (!strcmp(arg, "--topo-order")) - topo_order = 1; + lifo = 1; + else if (!strcmp(arg, "--date-order")) + lifo = 0; else usage(show_branch_usage); ac--; av++; @@ -710,8 +712,7 @@ int main(int ac, char **av) exit(0); /* Sort topologically */ - if (topo_order) - sort_in_topological_order(&seen); + sort_in_topological_order(&seen, lifo); /* Give names to commits */ if (!sha1_name && !no_name) 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/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/t8001-annotate.sh b/t/t8001-annotate.sh new file mode 100755 index 0000000000..cae179436c --- /dev/null +++ b/t/t8001-annotate.sh @@ -0,0 +1,89 @@ +#!/bin/sh + +test_description='git-annotate' +. ./test-lib.sh + +test_expect_success \ + 'prepare reference tree' \ + 'echo "1A quick brown fox jumps over the" >file && + echo "lazy dog" >>file && + git add file + GIT_AUTHOR_NAME="A" git commit -a -m "Initial."' + +test_expect_success \ + 'check all lines blamed on A' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "A") == 2 ]' + +test_expect_success \ + 'Setup new lines blamed on B' \ + 'echo "2A quick brown fox jumps over the" >>file && + echo "lazy dog" >> file && + GIT_AUTHOR_NAME="B" git commit -a -m "Second."' + +test_expect_success \ + 'Two lines blamed on A' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "A") == 2 ]' + +test_expect_success \ + 'Two lines blamed on B' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "B") == 2 ]' + +test_expect_success \ + 'merge-setup part 1' \ + 'git checkout -b branch1 master && + echo "3A slow green fox jumps into the" >> file && + echo "well." >> file && + GIT_AUTHOR_NAME="B1" git commit -a -m "Branch1-1"' + +test_expect_success \ + 'Two lines blamed on A' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]' + +test_expect_success \ + 'Two lines blamed on B' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 2 ]' + +test_expect_success \ + 'Two lines blamed on B1' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B1$") == 2 ]' + +test_expect_success \ + 'merge-setup part 2' \ + 'git checkout -b branch2 master && + sed -i -e "s/2A quick brown/4A quick brown lazy dog/" file && + GIT_AUTHOR_NAME="B2" git commit -a -m "Branch2-1"' + +test_expect_success \ + 'Two lines blamed on A' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]' + +test_expect_success \ + 'One line blamed on B' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 1 ]' + +test_expect_success \ + 'One line blamed on B2' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B2$") == 1 ]' + + +test_expect_success \ + 'merge-setup part 3' \ + 'git pull . branch1' + +test_expect_success \ + 'Two lines blamed on A' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]' + +test_expect_success \ + 'One line blamed on B' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 1 ]' + +test_expect_success \ + 'Two lines blamed on B1' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B1$") == 2 ]' + +test_expect_success \ + 'One line blamed on B2' \ + '[ $(git annotate file | awk "{print \$3}" | grep -c "^B2$") == 1 ]' + +test_done 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/templates/hooks--pre-rebase b/templates/hooks--pre-rebase new file mode 100644 index 0000000000..981c454cda --- /dev/null +++ b/templates/hooks--pre-rebase @@ -0,0 +1,150 @@ +#!/bin/sh +# +# Copyright (c) 2006 Junio C Hamano +# + +publish=next +basebranch="$1" +if test "$#" = 2 +then + topic="refs/heads/$2" +else + topic=`git symbolic-ref HEAD` +fi + +case "$basebranch,$topic" in +master,refs/heads/??/*) + ;; +*) + exit 0 ;# we do not interrupt others. + ;; +esac + +# Now we are dealing with a topic branch being rebased +# on top of master. Is it OK to rebase it? + +# Is topic fully merged to master? +not_in_master=`git-rev-list --pretty=oneline ^master "$topic"` +if test -z "$not_in_master" +then + echo >&2 "$topic is fully merged to master; better remove it." + exit 1 ;# we could allow it, but there is no point. +fi + +# Is topic ever merged to next? If so you should not be rebasing it. +only_next_1=`git-rev-list ^master "^$topic" ${publish} | sort` +only_next_2=`git-rev-list ^master ${publish} | sort` +if test "$only_next_1" = "$only_next_2" +then + not_in_topic=`git-rev-list "^$topic" master` + if test -z "$not_in_topic" + then + echo >&2 "$topic is already up-to-date with master" + exit 1 ;# we could allow it, but there is no point. + else + exit 0 + fi +else + not_in_next=`git-rev-list --pretty=oneline ^${publish} "$topic"` + perl -e ' + my $topic = $ARGV[0]; + my $msg = "* $topic has commits already merged to public branch:\n"; + my (%not_in_next) = map { + /^([0-9a-f]+) /; + ($1 => 1); + } split(/\n/, $ARGV[1]); + for my $elem (map { + /^([0-9a-f]+) (.*)$/; + [$1 => $2]; + } split(/\n/, $ARGV[2])) { + if (!exists $not_in_next{$elem->[0]}) { + if ($msg) { + print STDERR $msg; + undef $msg; + } + print STDERR " $elem->[1]\n"; + } + } + ' "$topic" "$not_in_next" "$not_in_master" + exit 1 +fi + +exit 0 + +################################################################ + +This sample hook safeguards topic branches that have been +published from being rewound. + +The workflow assumed here is: + + * Once a topic branch forks from "master", "master" is never + merged into it again (either directly or indirectly). + + * Once a topic branch is fully cooked and merged into "master", + it is deleted. If you need to build on top of it to correct + earlier mistakes, a new topic branch is created by forking at + the tip of the "master". This is not strictly necessary, but + it makes it easier to keep your history simple. + + * Whenever you need to test or publish your changes to topic + branches, merge them into "next" branch. + +The script, being an example, hardcodes the publish branch name +to be "next", but it is trivial to make it configurable via +$GIT_DIR/config mechanism. + +With this workflow, you would want to know: + +(1) ... if a topic branch has ever been merged to "next". Young + topic branches can have stupid mistakes you would rather + clean up before publishing, and things that have not been + merged into other branches can be easily rebased without + affecting other people. But once it is published, you would + not want to rewind it. + +(2) ... if a topic branch has been fully merged to "master". + Then you can delete it. More importantly, you should not + build on top of it -- other people may already want to + change things related to the topic as patches against your + "master", so if you need further changes, it is better to + fork the topic (perhaps with the same name) afresh from the + tip of "master". + +Let's look at this example: + + o---o---o---o---o---o---o---o---o---o "next" + / / / / + / a---a---b A / / + / / / / + / / c---c---c---c B / + / / / \ / + / / / b---b C \ / + / / / / \ / + ---o---o---o---o---o---o---o---o---o---o---o "master" + + +A, B and C are topic branches. + + * A has one fix since it was merged up to "next". + + * B has finished. It has been fully merged up to "master" and "next", + and is ready to be deleted. + + * C has not merged to "next" at all. + +We would want to allow C to be rebased, refuse A, and encourage +B to be deleted. + +To compute (1): + + git-rev-list ^master ^topic next + git-rev-list ^master next + + if these match, topic has not merged in next at all. + +To compute (2): + + git-rev-list master..topic + + if this is empty, it is fully merged to "master". 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) 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; |