diff options
246 files changed, 20303 insertions, 4961 deletions
@@ -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 @@ -40,6 +42,7 @@ git-grep git-hash-object git-http-fetch git-http-push +git-imap-send git-index-pack git-init-db git-local-fetch @@ -53,6 +56,7 @@ 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 +64,7 @@ git-merge-recursive git-merge-resolve git-merge-stupid git-mktag +git-mktree git-name-rev git-mv git-pack-redundant @@ -84,6 +89,7 @@ git-resolve git-rev-list git-rev-parse git-revert +git-rm git-send-email git-send-pack git-sh-setup @@ -116,12 +122,13 @@ git-write-tree git-core-*/?* test-date test-delta +common-cmds.h *.tar.gz *.dsc *.deb git-core.spec *.exe -libgit.a -*.o +*.[ao] *.py[co] config.mak +git-blame diff --git a/Documentation/Makefile b/Documentation/Makefile index a3bca86..f4cbf7e 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -1,4 +1,7 @@ -MAN1_TXT=$(wildcard git-*.txt) gitk.txt +MAN1_TXT= \ + $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \ + $(wildcard git-*.txt)) \ + gitk.txt MAN7_TXT=git.txt DOC_HTML=$(patsubst %.txt,%.html,$(MAN1_TXT) $(MAN7_TXT)) @@ -11,6 +14,7 @@ ARTICLES += howto-index ARTICLES += repository-layout ARTICLES += hooks ARTICLES += everyday +ARTICLES += git-tools # with their own formatting rules. SP_ARTICLES = glossary howto/revert-branch-rebase diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 9ccb8f7..318b04f 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/asciidoc.conf b/Documentation/asciidoc.conf index fa0877d..7ce7151 100644 --- a/Documentation/asciidoc.conf +++ b/Documentation/asciidoc.conf @@ -18,6 +18,16 @@ ifdef::backend-docbook[] {0#</citerefentry>} endif::backend-docbook[] +ifdef::backend-docbook[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout> +{title#}</example> +endif::backend-docbook[] + ifdef::backend-xhtml11[] [gitlink-inlinemacro] <a href="{target}.html">{target}{0?({0})}</a> diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 7e29383..ae24547 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -3,7 +3,7 @@ git-add(1) NAME ---- -git-add - Add files to the index file. +git-add - Add files to the index file SYNOPSIS -------- @@ -65,6 +65,9 @@ git-add git-*.sh:: (i.e. you are listing the files explicitly), it does not add `subdir/git-foo.sh` to the index. +See Also +-------- +gitlink:git-rm[1] Author ------ diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt index 02cabc9..910457d 100644 --- a/Documentation/git-am.txt +++ b/Documentation/git-am.txt @@ -9,7 +9,8 @@ git-am - Apply a series of patches in a mailbox SYNOPSIS -------- [verse] -'git-am' [--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox>... +'git-am' [--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] + [--interactive] [--whitespace=<option>] <mbox>... 'git-am' [--skip | --resolved] DESCRIPTION @@ -46,6 +47,10 @@ OPTIONS Skip the current patch. This is only meaningful when restarting an aborted patch. +--whitespace=<option>:: + This flag is passed to the `git-apply` program that applies + the patch. + --interactive:: Run interactively, just like git-applymbox. @@ -80,7 +85,7 @@ names. SEE ALSO -------- -gitlink:git-applymbox[1], gitlink:git-applypatch[1]. +gitlink:git-applymbox[1], gitlink:git-applypatch[1], gitlink:git-apply[1]. Author diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt index 75076b6..1c64a1a 100644 --- a/Documentation/git-apply.txt +++ b/Documentation/git-apply.txt @@ -11,6 +11,7 @@ SYNOPSIS [verse] 'git-apply' [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] + [--whitespace=<nowarn|warn|error|error-all|strip>] [<patch>...] DESCRIPTION @@ -97,6 +98,35 @@ OPTIONS result. This allows binary files to be patched in a very limited way. +--whitespace=<option>:: + When applying a patch, detect a new or modified line + that ends with trailing whitespaces (this includes a + line that solely consists of whitespaces). By default, + the command outputs warning messages and applies the + patch. + When `git-apply` is used for statistics and not applying a + patch, it defaults to `nowarn`. + You can use different `<option>` to control this + behaviour: ++ +* `nowarn` turns off the trailing whitespace warning. +* `warn` outputs warnings for a few such errors, but applies the + patch (default). +* `error` outputs warnings for a few such errors, and refuses + to apply the patch. +* `error-all` is similar to `error` but shows all errors. +* `strip` outputs warnings for a few such errors, strips out the + trailing whitespaces and applies the patch. + + +Configuration +------------- + +apply.whitespace:: + When no `--whitespace` flag is given from the command + line, this configuration item is used as the default. + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-applypatch.txt b/Documentation/git-applypatch.txt index 5b9037d..2b1ff14 100644 --- a/Documentation/git-applypatch.txt +++ b/Documentation/git-applypatch.txt @@ -3,7 +3,7 @@ git-applypatch(1) NAME ---- -git-applypatch - Apply one patch extracted from an e-mail. +git-applypatch - Apply one patch extracted from an e-mail SYNOPSIS diff --git a/Documentation/git-archimport.txt b/Documentation/git-archimport.txt index 023d3ae..5a13187 100644 --- a/Documentation/git-archimport.txt +++ b/Documentation/git-archimport.txt @@ -9,7 +9,7 @@ git-archimport - Import an Arch repository into git SYNOPSIS -------- [verse] -`git-archimport` [-h] [-v] [-o] [-a] [-f] [-T] [-D depth] [-t tempdir] +'git-archimport' [-h] [-v] [-o] [-a] [-f] [-T] [-D depth] [-t tempdir] <archive/branch> [ <archive/branch> ] DESCRIPTION diff --git a/Documentation/git-branch.txt b/Documentation/git-branch.txt index b1bc827..71ecd85 100644 --- a/Documentation/git-branch.txt +++ b/Documentation/git-branch.txt @@ -3,20 +3,24 @@ git-branch(1) NAME ---- -git-branch - Create a new branch, or remove an old one. +git-branch - Create a new branch, or remove an old one SYNOPSIS -------- -'git-branch' [(-d | -D) <branchname>] | [[-f] <branchname> [<start-point>]] +[verse] +'git-branch' [[-f] <branchname> [<start-point>]] +'git-branch' (-d | -D) <branchname> DESCRIPTION ----------- If no argument is provided, show available branches and mark current branch with star. Otherwise, create a new branch of name <branchname>. - If a starting point is also specified, that will be where the branch is created, otherwise it will be created at the current HEAD. +With a `-d` or `-D` option, `<branchname>` will be deleted. + + OPTIONS ------- -d:: @@ -39,7 +43,7 @@ OPTIONS Examples ~~~~~~~~ -Start development off of a know tag:: +Start development off of a known tag:: + ------------ $ git clone git://git.kernel.org/pub/scm/.../linux-2.6 my2.6 diff --git a/Documentation/git-check-ref-format.txt b/Documentation/git-check-ref-format.txt index f7f84c6..7dc1bdb 100644 --- a/Documentation/git-check-ref-format.txt +++ b/Documentation/git-check-ref-format.txt @@ -3,7 +3,7 @@ git-check-ref-format(1) NAME ---- -git-check-ref-format - Make sure ref name is well formed. +git-check-ref-format - Make sure ref name is well formed SYNOPSIS -------- diff --git a/Documentation/git-checkout-index.txt b/Documentation/git-checkout-index.txt index 2a1e526..09bd6a5 100644 --- a/Documentation/git-checkout-index.txt +++ b/Documentation/git-checkout-index.txt @@ -10,7 +10,10 @@ SYNOPSIS -------- [verse] 'git-checkout-index' [-u] [-q] [-a] [-f] [-n] [--prefix=<string>] - [--stage=<number>] [--] <file>... + [--stage=<number>|all] + [--temp] + [-z] [--stdin] + [--] [<file>]\* DESCRIPTION ----------- @@ -41,9 +44,24 @@ OPTIONS When creating files, prepend <string> (usually a directory including a trailing /) ---stage=<number>:: +--stage=<number>|all:: Instead of checking out unmerged entries, copy out the files from named stage. <number> must be between 1 and 3. + Note: --stage=all automatically implies --temp. + +--temp:: + Instead of copying the files to the working directory + write the content to temporary files. The temporary name + associations will be written to stdout. + +--stdin:: + Instead of taking list of paths from the command line, + read list of paths from the standard input. Paths are + separated by LF (i.e. one path per line) by default. + +-z:: + Only meaningful with `--stdin`; paths are separated with + NUL character instead of LF. --:: Do not interpret any more arguments as options. @@ -64,13 +82,58 @@ $ find . -name '*.h' -print0 | xargs -0 git-checkout-index -f -- which will force all existing `*.h` files to be replaced with their cached copies. If an empty command line implied "all", then this would -force-refresh everything in the index, which was not the point. +force-refresh everything in the index, which was not the point. But +since git-checkout-index accepts --stdin it would be faster to use: + +---------------- +$ find . -name '*.h' -print0 | git-checkout-index -f -z --stdin +---------------- The `--` is just a good idea when you know the rest will be filenames; it will prevent problems with a filename of, for example, `-a`. Using `--` is probably a good policy in scripts. +Using --temp or --stage=all +--------------------------- +When `--temp` is used (or implied by `--stage=all`) +`git-checkout-index` will create a temporary file for each index +entry being checked out. The index will not be updated with stat +information. These options can be useful if the caller needs all +stages of all unmerged entries so that the unmerged files can be +processed by an external merge tool. + +A listing will be written to stdout providing the association of +temporary file names to tracked path names. The listing format +has two variations: + + . tempname TAB path RS ++ +The first format is what gets used when `--stage` is omitted or +is not `--stage=all`. The field tempname is the temporary file +name holding the file content and path is the tracked path name in +the index. Only the requested entries are output. + + . stage1temp SP stage2temp SP stage3tmp TAB path RS ++ +The second format is what gets used when `--stage=all`. The three +stage temporary fields (stage1temp, stage2temp, stage3temp) list the +name of the temporary file if there is a stage entry in the index +or `.` if there is no stage entry. Paths which only have a stage 0 +entry will always be omitted from the output. + +In both formats RS (the record separator) is newline by default +but will be the null byte if -z was passed on the command line. +The temporary file names are always safe strings; they will never +contain directory separators or whitespace characters. The path +field is always relative to the current directory and the temporary +file names are always relative to the top level directory. + +If the object being copied out to a temporary file is a symbolic +link the content of the link will be written to a normal file. It is +up to the end-user or the Porcelain to make use of this information. + + EXAMPLES -------- To update and refresh only the files already checked out:: diff --git a/Documentation/git-checkout.txt b/Documentation/git-checkout.txt index df9a618..985bb2f 100644 --- a/Documentation/git-checkout.txt +++ b/Documentation/git-checkout.txt @@ -3,19 +3,22 @@ git-checkout(1) NAME ---- -git-checkout - Checkout and switch to a branch. +git-checkout - Checkout and switch to a branch SYNOPSIS -------- -'git-checkout' [-f] [-b <new_branch>] [-m] [<branch>] [<paths>...] +[verse] +'git-checkout' [-f] [-b <new_branch>] [-m] [<branch>] +'git-checkout' [-m] [<branch>] <paths>... DESCRIPTION ----------- -When <paths> are not given, this command switches branches, by +When <paths> are not given, this command switches branches by updating the index and working tree to reflect the specified branch, <branch>, and updating HEAD to be <branch> or, if -specified, <new_branch>. +specified, <new_branch>. Using -b will cause <new_branch> to +be created. When <paths> are given, this command does *not* switch branches. It updates the named paths in the working tree from @@ -29,17 +32,17 @@ given paths before updating the working tree. OPTIONS ------- -f:: - Force an re-read of everything. + Force a re-read of everything. -b:: Create a new branch and start it at <branch>. -m:: - If you have local modifications to a file that is - different between the current branch and the branch you - are switching to, the command refuses to switch - branches, to preserve your modifications in context. - With this option, a three-way merge between the current + If you have local modifications to one or more files that + are different between the current branch and the branch to + which you are switching, the command refuses to switch + branches in order to preserve your modifications in context. + However, with this option, a three-way merge between the current branch, your working tree contents, and the new branch is done, and you will be on the new branch. + @@ -82,7 +85,7 @@ $ git checkout -- hello.c ------------ . After working in a wrong branch, switching to the correct -branch you would want to is done with: +branch would be done using: + ------------ $ git checkout mytopic diff --git a/Documentation/git-cherry-pick.txt b/Documentation/git-cherry-pick.txt index 4f323fa..bfa950c 100644 --- a/Documentation/git-cherry-pick.txt +++ b/Documentation/git-cherry-pick.txt @@ -3,7 +3,7 @@ git-cherry-pick(1) NAME ---- -git-cherry-pick - Apply the change introduced by an existing commit. +git-cherry-pick - Apply the change introduced by an existing commit SYNOPSIS -------- diff --git a/Documentation/git-cherry.txt b/Documentation/git-cherry.txt index af87966..9a5e371 100644 --- a/Documentation/git-cherry.txt +++ b/Documentation/git-cherry.txt @@ -3,7 +3,7 @@ git-cherry(1) NAME ---- -git-cherry - Find commits not merged upstream. +git-cherry - Find commits not merged upstream SYNOPSIS -------- diff --git a/Documentation/git-clone-pack.txt b/Documentation/git-clone-pack.txt index 39906fc..09f43ee 100644 --- a/Documentation/git-clone-pack.txt +++ b/Documentation/git-clone-pack.txt @@ -3,7 +3,7 @@ git-clone-pack(1) NAME ---- -git-clone-pack - Clones a repository by receiving packed objects. +git-clone-pack - Clones a repository by receiving packed objects SYNOPSIS diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt index 684e4bd..9ac54c2 100644 --- a/Documentation/git-clone.txt +++ b/Documentation/git-clone.txt @@ -3,7 +3,7 @@ git-clone(1) NAME ---- -git-clone - Clones a repository. +git-clone - Clones a repository SYNOPSIS diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index 5b1b4d3..d04b342 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -18,6 +18,10 @@ Updates the index file for given paths, or all modified files if VISUAL and EDITOR environment variables to edit the commit log message. +Several environment variable are used during commits. They are +documented in gitlink:git-commit-tree[1]. + + This command can run `commit-msg`, `pre-commit`, and `post-commit` hooks. See link:hooks.html[hooks] for more information. @@ -85,27 +89,12 @@ 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 +110,7 @@ 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-count-objects.txt b/Documentation/git-count-objects.txt index 36888d9..47216f4 100644 --- a/Documentation/git-count-objects.txt +++ b/Documentation/git-count-objects.txt @@ -3,7 +3,7 @@ git-count-objects(1) NAME ---- -git-count-objects - Reports on unpacked objects. +git-count-objects - Reports on unpacked objects SYNOPSIS -------- diff --git a/Documentation/git-cvsimport.txt b/Documentation/git-cvsimport.txt index dfe86ce..b0c6d7c 100644 --- a/Documentation/git-cvsimport.txt +++ b/Documentation/git-cvsimport.txt @@ -22,6 +22,12 @@ repository, or incrementally import into an existing one. Splitting the CVS log into patch sets is done by 'cvsps'. At least version 2.1 is required. +You should *never* do any work of your own on the branches that are +created by git-cvsimport. The initial import will create and populate a +"master" branch from the CVS repository's main branch which you're free +to work with; after that, you need to 'git merge' incremental imports, or +any CVS branches, yourself. + OPTIONS ------- -d <CVSROOT>:: @@ -93,21 +99,24 @@ If you need to pass multiple options, separate them with a comma. CVS by default uses the unix username when writing its commit logs. Using this option and an author-conv-file in this format - ++ +--------- exon=Andreas Ericsson <ae@op5.se> spawn=Simon Pawn <spawn@frog-pond.org> - git-cvsimport will make it appear as those authors had - their GIT_AUTHOR_NAME and GIT_AUTHOR_EMAIL set properly - all along. - - For convenience, this data is saved to $GIT_DIR/cvs-authors - each time the -A option is provided and read from that same - file each time git-cvsimport is run. - - It is not recommended to use this feature if you intend to - export changes back to CVS again later with - git-link[1]::git-cvsexportcommit. +--------- ++ +git-cvsimport will make it appear as those authors had +their GIT_AUTHOR_NAME and GIT_AUTHOR_EMAIL set properly +all along. ++ +For convenience, this data is saved to $GIT_DIR/cvs-authors +each time the -A option is provided and read from that same +file each time git-cvsimport is run. ++ +It is not recommended to use this feature if you intend to +export changes back to CVS again later with +git-link[1]::git-cvsexportcommit. OUTPUT ------ diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt new file mode 100644 index 0000000..4dc13c3 --- /dev/null +++ b/Documentation/git-cvsserver.txt @@ -0,0 +1,148 @@ +git-cvsserver(1) +================ + +NAME +---- +git-cvsserver - A CVS server emulator for git + +SYNOPSIS +-------- +[verse] +export CVS_SERVER=git-cvsserver +'cvs' -d :ext:user@server/path/repo.git co <HEAD_name> + +DESCRIPTION +----------- + +This application is a CVS emulation layer for git. + +It is highly functional. However, not all methods are implemented, +and for those methods that are implemented, +not all switches are implemented. + +Testing has been done using both the CLI CVS client, and the Eclipse CVS +plugin. Most functionality works fine with both of these clients. + +LIMITATIONS +----------- + +Currently cvsserver works over SSH connections for read/write clients, and +over pserver for anonymous CVS access. + +CVS clients cannot tag, branch or perform GIT merges. + +INSTALLATION +------------ + +1. If you are going to offer anonymous CVS access via pserver, add a line in + /etc/inetd.conf like + + cvspserver stream tcp nowait nobody git-cvsserver pserver + + Note: In some cases, you need to pass the 'pserver' argument twice for + git-cvsserver to see it. So the line would look like + + cvspserver stream tcp nowait nobody git-cvsserver pserver pserver + + No special setup is needed for SSH access, other than having GIT tools + in the PATH. If you have clients that do not accept the CVS_SERVER + env variable, you can rename git-cvsserver to cvs. + +2. For each repo that you want accessible from CVS you need to edit config in + the repo and add the following section. + + [gitcvs] + enabled=1 + # optional for debugging + logfile=/path/to/logfile + + Note: you need to ensure each user that is going to invoke git-cvsserver has + write access to the log file and to the git repository. When offering anon + access via pserver, this means that the nobody user should have write access + to at least the sqlite database at the root of the repository. + +3. On the client machine you need to set the following variables. + CVSROOT should be set as per normal, but the directory should point at the + appropriate git repo. For example: + + For SSH access, CVS_SERVER should be set to git-cvsserver + + Example: + + export CVSROOT=:ext:user@server:/var/git/project.git + export CVS_SERVER=git-cvsserver + +4. For SSH clients that will make commits, make sure their .bashrc file + sets the GIT_AUTHOR and GIT_COMMITTER variables. + +5. Clients should now be able to check out the project. Use the CVS 'module' + name to indicate what GIT 'head' you want to check out. Example: + + cvs co -d project-master master + +Eclipse CVS Client Notes +------------------------ + +To get a checkout with the Eclipse CVS client: + +1. Select "Create a new project -> From CVS checkout" +2. Create a new location. See the notes below for details on how to choose the + right protocol. +3. Browse the 'modules' available. It will give you a list of the heads in + the repository. You will not be able to browse the tree from there. Only + the heads. +4. Pick 'HEAD' when it asks what branch/tag to check out. Untick the + "launch commit wizard" to avoid committing the .project file. + +Protocol notes: If you are using anonymous acces via pserver, just select that. +Those using SSH access should choose the 'ext' protocol, and configure 'ext' +access on the Preferences->Team->CVS->ExtConnection pane. Set CVS_SERVER to +'git-cvsserver'. Not that password support is not good when using 'ext', +you will definitely want to have SSH keys setup. + +Alternatively, you can just use the non-standard extssh protocol that Eclipse +offer. In that case CVS_SERVER is ignored, and you will have to replace +the cvs utility on the server with git-cvsserver or manipulate your .bashrc +so that calling 'cvs' effectively calls git-cvsserver. + +Clients known to work +--------------------- + +CVS 1.12.9 on Debian +CVS 1.11.17 on MacOSX (from Fink package) +Eclipse 3.0, 3.1.2 on MacOSX (see Eclipse CVS Client Notes) +TortoiseCVS + +Operations supported +-------------------- + +All the operations required for normal use are supported, including +checkout, diff, status, update, log, add, remove, commit. +Legacy monitoring operations are not supported (edit, watch and related). +Exports and tagging (tags and branches) are not supported at this stage. + +The server will set the -k mode to binary when relevant. In proper GIT +tradition, the contents of the files are always respected. +No keyword expansion or newline munging is supported. + +Dependencies +------------ + +git-cvsserver depends on DBD::SQLite. + +Copyright and Authors +--------------------- + +This program is copyright The Open University UK - 2006. + +Authors: Martyn Smith <martyn@catalyst.net.nz> + Martin Langhoff <martin@catalyst.net.nz> + with ideas and patches from participants of the git-list <git@vger.kernel.org>. + +Documentation +-------------- +Documentation by Martyn Smith <martyn@catalyst.net.nz> and Martin Langhoff <martin@catalyst.net.nz> Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-daemon.txt b/Documentation/git-daemon.txt index 2cc6075..924a676 100644 --- a/Documentation/git-daemon.txt +++ b/Documentation/git-daemon.txt @@ -3,7 +3,7 @@ git-daemon(1) NAME ---- -git-daemon - A really simple server for git repositories. +git-daemon - A really simple server for git repositories SYNOPSIS -------- diff --git a/Documentation/git-describe.txt b/Documentation/git-describe.txt index 0efe82a..7a253ea 100644 --- a/Documentation/git-describe.txt +++ b/Documentation/git-describe.txt @@ -3,7 +3,7 @@ git-describe(1) NAME ---- -git-describe - Show the most recent tag that is reachable from a commit. +git-describe - Show the most recent tag that is reachable from a commit SYNOPSIS diff --git a/Documentation/git-diff-stages.txt b/Documentation/git-diff-stages.txt index 28c60fc..3273918 100644 --- a/Documentation/git-diff-stages.txt +++ b/Documentation/git-diff-stages.txt @@ -3,7 +3,7 @@ git-diff-stages(1) NAME ---- -git-diff-stages - Compares content and mode of blobs between stages in an unmerged index file. +git-diff-stages - Compares content and mode of blobs between stages in an unmerged index file SYNOPSIS diff --git a/Documentation/git-diff.txt b/Documentation/git-diff.txt index ca41634..890931c 100644 --- a/Documentation/git-diff.txt +++ b/Documentation/git-diff.txt @@ -3,7 +3,7 @@ git-diff(1) NAME ---- -git-diff - Show changes between commits, commit and working tree, etc. +git-diff - Show changes between commits, commit and working tree, etc SYNOPSIS diff --git a/Documentation/git-fetch-pack.txt b/Documentation/git-fetch-pack.txt index b507e9b..bff9aa6 100644 --- a/Documentation/git-fetch-pack.txt +++ b/Documentation/git-fetch-pack.txt @@ -3,12 +3,12 @@ git-fetch-pack(1) NAME ---- -git-fetch-pack - Receive missing objects from another repository. +git-fetch-pack - Receive missing objects from another repository SYNOPSIS -------- -git-fetch-pack [-q] [-k] [--exec=<git-upload-pack>] [<host>:]<directory> [<refs>...] +'git-fetch-pack' [-q] [-k] [--exec=<git-upload-pack>] [<host>:]<directory> [<refs>...] DESCRIPTION ----------- diff --git a/Documentation/git-fetch.txt b/Documentation/git-fetch.txt index a67dc34..a9e86fd 100644 --- a/Documentation/git-fetch.txt +++ b/Documentation/git-fetch.txt @@ -3,7 +3,7 @@ git-fetch(1) NAME ---- -git-fetch - Download objects and a head from another repository. +git-fetch - Download objects and a head from another repository SYNOPSIS diff --git a/Documentation/git-format-patch.txt b/Documentation/git-format-patch.txt index 9ac0636..7cc7faf 100644 --- a/Documentation/git-format-patch.txt +++ b/Documentation/git-format-patch.txt @@ -3,13 +3,13 @@ git-format-patch(1) NAME ---- -git-format-patch - Prepare patches for e-mail submission. +git-format-patch - Prepare patches for e-mail submission SYNOPSIS -------- [verse] -'git-format-patch' [-n | -k] [-o <dir> | --stdout] [-s] [-c] +'git-format-patch' [-n | -k] [-o <dir> | --stdout] [--attach] [-s] [-c] [--diff-options] <his> [<mine>] DESCRIPTION @@ -60,6 +60,18 @@ OPTIONS standard output, instead of saving them into a file per patch and implies --mbox. +--attach:: + Create attachments instead of inlining patches. + + +CONFIGURATION +------------- +You can specify extra mail header lines to be added to each +message in the repository configuration as follows: + +[format] + headers = "Organization: git-foo\n" + EXAMPLES -------- diff --git a/Documentation/git-fsck-objects.txt b/Documentation/git-fsck-objects.txt index 387b435..93ce9dc 100644 --- a/Documentation/git-fsck-objects.txt +++ b/Documentation/git-fsck-objects.txt @@ -10,7 +10,7 @@ SYNOPSIS -------- [verse] 'git-fsck-objects' [--tags] [--root] [--unreachable] [--cache] - [--standalone | --full] [--strict] [<object>*] + [--full] [--strict] [<object>*] DESCRIPTION ----------- @@ -38,21 +38,14 @@ index file and all SHA1 references in .git/refs/* as heads. Consider any object recorded in the index also as a head node for an unreachability trace. ---standalone:: - Limit checks to the contents of GIT_OBJECT_DIRECTORY - ($GIT_DIR/objects), making sure that it is consistent and - complete without referring to objects found in alternate - object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES, - nor packed git archives found in $GIT_DIR/objects/pack; - cannot be used with --full. - --full:: Check not just objects in GIT_OBJECT_DIRECTORY ($GIT_DIR/objects), but also the ones found in alternate - object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES, + object pools listed in GIT_ALTERNATE_OBJECT_DIRECTORIES + or $GIT_DIR/objects/info/alternates, and in packed git archives found in $GIT_DIR/objects/pack and corresponding pack subdirectories in alternate - object pools; cannot be used with --standalone. + object pools. --strict:: Enable more strict checking, namely to catch a file mode diff --git a/Documentation/git-get-tar-commit-id.txt b/Documentation/git-get-tar-commit-id.txt index 30b1fbf..48805b6 100644 --- a/Documentation/git-get-tar-commit-id.txt +++ b/Documentation/git-get-tar-commit-id.txt @@ -3,7 +3,7 @@ git-get-tar-commit-id(1) NAME ---- -git-get-tar-commit-id - Extract commit ID from an archive created using git-tar-tree. +git-get-tar-commit-id - Extract commit ID from an archive created using git-tar-tree SYNOPSIS diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt index bf4b592..d55456a 100644 --- a/Documentation/git-grep.txt +++ b/Documentation/git-grep.txt @@ -3,7 +3,7 @@ git-grep(1) NAME ---- -git-grep - print lines matching a pattern +git-grep - Print lines matching a pattern SYNOPSIS @@ -24,13 +24,13 @@ OPTIONS <option>...:: Either an option to pass to `grep` or `git-ls-files`. - - The following are the specific `git-ls-files` options - that may be given: `-o`, `--cached`, `--deleted`, `--others`, - `--killed`, `--ignored`, `--modified`, `--exclude=*`, - `--exclude-from=*`, and `--exclude-per-directory=*`. - - All other options will be passed to `grep`. ++ +The following are the specific `git-ls-files` options +that may be given: `-o`, `--cached`, `--deleted`, `--others`, +`--killed`, `--ignored`, `--modified`, `--exclude=\*`, +`--exclude-from=\*`, and `--exclude-per-directory=\*`. ++ +All other options will be passed to `grep`. <pattern>:: The pattern to look for. The first non option is taken diff --git a/Documentation/git-hash-object.txt b/Documentation/git-hash-object.txt index 0924931..04e8d00 100644 --- a/Documentation/git-hash-object.txt +++ b/Documentation/git-hash-object.txt @@ -3,7 +3,7 @@ git-hash-object(1) NAME ---- -git-hash-object - Computes object ID and optionally creates a blob from a file. +git-hash-object - Computes object ID and optionally creates a blob from a file SYNOPSIS diff --git a/Documentation/git-http-push.txt b/Documentation/git-http-push.txt index c7066d6..7e1f894 100644 --- a/Documentation/git-http-push.txt +++ b/Documentation/git-http-push.txt @@ -3,7 +3,7 @@ git-http-push(1) NAME ---- -git-http-push - Push missing objects using HTTP/DAV. +git-http-push - Push missing objects using HTTP/DAV SYNOPSIS diff --git a/Documentation/git-init-db.txt b/Documentation/git-init-db.txt index ea4d849..aeb1115 100644 --- a/Documentation/git-init-db.txt +++ b/Documentation/git-init-db.txt @@ -14,7 +14,8 @@ SYNOPSIS OPTIONS ------- --template=<template_directory>:: - Provide the directory in from which templates will be used. + Provide the directory from which templates will be used. + The default template directory is `/usr/share/git-core/templates`. --shared:: Specify that the git repository is to be shared amongst several users. @@ -22,9 +23,17 @@ OPTIONS DESCRIPTION ----------- -This simply creates an empty git repository - basically a `.git` directory -and `.git/object/??/`, `.git/refs/heads` and `.git/refs/tags` directories, -and links `.git/HEAD` symbolically to `.git/refs/heads/master`. +This command creates an empty git repository - basically a `.git` directory +with subdirectories for `objects`, `refs/heads`, `refs/tags`, and +templated files. +An initial `HEAD` file that references the HEAD of the master branch +is also created. + +If `--template=<template_directory>` is specified, `<template_directory>` +is used as the source of the template files rather than the default. +The template files include some directory structure, some suggested +"exclude patterns", and copies of non-executing "hook" files. The +suggested patterns and hook files are all modifiable and extensible. If the `$GIT_DIR` environment variable is set then it specifies a path to use instead of `./.git` for the base of the repository. @@ -38,7 +47,6 @@ repository. When specifying `--shared` the config variable "core.sharedRepositor is set to 'true' so that directories under `$GIT_DIR` are made group writable (and g+sx, since the git group may be not the primary group of all users). - Running `git-init-db` in an existing repository is safe. It will not overwrite things that are already there. The primary reason for rerunning `git-init-db` is to pick up newly added templates. diff --git a/Documentation/git-lost-found.txt b/Documentation/git-lost-found.txt index 03156f2..f52a9d7 100644 --- a/Documentation/git-lost-found.txt +++ b/Documentation/git-lost-found.txt @@ -3,7 +3,7 @@ git-lost-found(1) NAME ---- -git-lost-found - Recover lost refs that luckily have not yet been pruned. +git-lost-found - Recover lost refs that luckily have not yet been pruned SYNOPSIS -------- diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt index fe53412..796d049 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -8,13 +8,15 @@ 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>] - [--full-name] [--] [<file>]\* + [--exclude-per-directory=<file>] + [--error-unmatch] + [--full-name] [--abbrev] [--] [<file>]\* DESCRIPTION ----------- @@ -50,6 +52,9 @@ OPTIONS If a whole directory is classified as "other", show just its name (with a trailing slash) and not its whole contents. +--no-empty-directory:: + Do not list empty directories. Has no effect without --directory. + -u|--unmerged:: Show unmerged files in the output (forces --stage) @@ -72,6 +77,10 @@ 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: @@ -82,12 +91,21 @@ 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 option forces paths to be output relative to the project top directory. +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + --:: Do not interpret any more arguments as options. diff --git a/Documentation/git-ls-remote.txt b/Documentation/git-ls-remote.txt index 66fe60f..ae4c1a2 100644 --- a/Documentation/git-ls-remote.txt +++ b/Documentation/git-ls-remote.txt @@ -3,7 +3,7 @@ git-ls-remote(1) NAME ---- -git-ls-remote - Look at references other repository has. +git-ls-remote - Look at references other repository has SYNOPSIS diff --git a/Documentation/git-ls-tree.txt b/Documentation/git-ls-tree.txt index b92a8b2..018c401 100644 --- a/Documentation/git-ls-tree.txt +++ b/Documentation/git-ls-tree.txt @@ -3,12 +3,14 @@ git-ls-tree(1) NAME ---- -git-ls-tree - Lists the contents of a tree object. +git-ls-tree - Lists the contents of a tree object SYNOPSIS -------- -'git-ls-tree' [-d] [-r] [-t] [-z] [--name-only] [--name-status] <tree-ish> [paths...] +'git-ls-tree' [-d] [-r] [-t] [-z] + [--name-only] [--name-status] [--full-name] [--abbrev=[<n>]] + <tree-ish> [paths...] DESCRIPTION ----------- @@ -40,6 +42,11 @@ OPTIONS --name-status:: List only filenames (instead of the "long" output), one per line. +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + paths:: When paths are given, show them (note that this isn't really raw pathnames, but rather a list of patterns to match). Otherwise diff --git a/Documentation/git-mailinfo.txt b/Documentation/git-mailinfo.txt index 8890754..ea0a065 100644 --- a/Documentation/git-mailinfo.txt +++ b/Documentation/git-mailinfo.txt @@ -3,7 +3,7 @@ git-mailinfo(1) NAME ---- -git-mailinfo - Extracts patch from a single e-mail message. +git-mailinfo - Extracts patch from a single e-mail message SYNOPSIS diff --git a/Documentation/git-mailsplit.txt b/Documentation/git-mailsplit.txt index e0703e9..209e36b 100644 --- a/Documentation/git-mailsplit.txt +++ b/Documentation/git-mailsplit.txt @@ -3,7 +3,7 @@ git-mailsplit(1) NAME ---- -git-mailsplit - Totally braindamaged mbox splitter program. +git-mailsplit - Totally braindamaged mbox splitter program SYNOPSIS -------- diff --git a/Documentation/git-mv.txt b/Documentation/git-mv.txt index d242b39..207c43a 100644 --- a/Documentation/git-mv.txt +++ b/Documentation/git-mv.txt @@ -3,7 +3,7 @@ git-mv(1) NAME ---- -git-mv - Script used to move or rename a file, directory or symlink. +git-mv - Move or rename a file, directory or symlink SYNOPSIS diff --git a/Documentation/git-name-rev.txt b/Documentation/git-name-rev.txt index e37b0b8..6870708 100644 --- a/Documentation/git-name-rev.txt +++ b/Documentation/git-name-rev.txt @@ -3,7 +3,7 @@ git-name-rev(1) NAME ---- -git-name-rev - Find symbolic names for given revs. +git-name-rev - Find symbolic names for given revs SYNOPSIS diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 4cb2e83..4991f88 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -3,7 +3,7 @@ git-pack-objects(1) NAME ---- -git-pack-objects - Create a packed archive of objects. +git-pack-objects - Create a packed archive of objects SYNOPSIS @@ -101,7 +101,7 @@ Documentation ------------- Documentation by Junio C Hamano -See-Also +See Also -------- gitlink:git-repack[1] gitlink:git-prune-packed[1] diff --git a/Documentation/git-pack-redundant.txt b/Documentation/git-pack-redundant.txt index 9fe86ae..8fb0659 100644 --- a/Documentation/git-pack-redundant.txt +++ b/Documentation/git-pack-redundant.txt @@ -3,12 +3,12 @@ git-pack-redundant(1) NAME ---- -git-pack-redundant - Program used to find redundant pack files. +git-pack-redundant - Program used to find redundant pack files SYNOPSIS -------- -'git-pack-redundant [ --verbose ] [ --alt-odb ] < --all | .pack filename ... >' +'git-pack-redundant' [ --verbose ] [ --alt-odb ] < --all | .pack filename ... > DESCRIPTION ----------- @@ -46,7 +46,7 @@ Documentation -------------- Documentation by Lukas Sandström <lukass@etek.chalmers.se> -See-Also +See Also -------- gitlink:git-pack-objects[1] gitlink:git-repack[1] diff --git a/Documentation/git-patch-id.txt b/Documentation/git-patch-id.txt index c8bd197..723b8cc 100644 --- a/Documentation/git-patch-id.txt +++ b/Documentation/git-patch-id.txt @@ -3,7 +3,7 @@ git-patch-id(1) NAME ---- -git-patch-id - Generate a patch ID. +git-patch-id - Generate a patch ID SYNOPSIS -------- diff --git a/Documentation/git-peek-remote.txt b/Documentation/git-peek-remote.txt index 915d3f8..a00060c 100644 --- a/Documentation/git-peek-remote.txt +++ b/Documentation/git-peek-remote.txt @@ -3,7 +3,7 @@ git-peek-remote(1) NAME ---- -git-peek-remote - Lists the references in a remote repository. +git-peek-remote - Lists the references in a remote repository SYNOPSIS diff --git a/Documentation/git-prune-packed.txt b/Documentation/git-prune-packed.txt index 37c53a9..2348826 100644 --- a/Documentation/git-prune-packed.txt +++ b/Documentation/git-prune-packed.txt @@ -40,7 +40,7 @@ Documentation -------------- Documentation by Ryan Anderson <ryan@michonline.com> -See-Also +See Also -------- gitlink:git-pack-objects[1] gitlink:git-repack[1] diff --git a/Documentation/git-pull.txt b/Documentation/git-pull.txt index 20175f4..51577fc 100644 --- a/Documentation/git-pull.txt +++ b/Documentation/git-pull.txt @@ -3,7 +3,7 @@ git-pull(1) NAME ---- -git-pull - Pull and merge from another repository. +git-pull - Pull and merge from another repository SYNOPSIS diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 6f4a48a..d5b5ca1 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -3,7 +3,7 @@ git-push(1) NAME ---- -git-push - Update remote refs along with associated objects. +git-push - Update remote refs along with associated objects SYNOPSIS diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt index 6fbd6d9..844cfda 100644 --- a/Documentation/git-read-tree.txt +++ b/Documentation/git-read-tree.txt @@ -8,7 +8,7 @@ git-read-tree - Reads tree information into the index SYNOPSIS -------- -'git-read-tree' (<tree-ish> | [[-m | --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) +'git-read-tree' (<tree-ish> | [[-m [--aggressive]| --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) DESCRIPTION @@ -50,6 +50,19 @@ OPTIONS trees that are not directly related to the current working tree status into a temporary index file. +--aggressive:: + Usually a three-way merge by `git-read-tree` resolves + the merge for really trivial cases and leaves other + cases unresolved in the index, so that Porcelains can + implement different merge policies. This flag makes the + command to resolve a few more cases internally: ++ +* when one side removes a path and the other side leaves the path + unmodified. The resolution is to remove that path. +* when both sides remove a path. The resolution is to remove that path. +* when both sides adds a path identically. The resolution + is to add that path. + <tree-ish#>:: The id of the tree object(s) to be read/merged. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 16c158f..4a7e67a 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -3,22 +3,74 @@ git-rebase(1) NAME ---- -git-rebase - Rebase local commits to new upstream head. +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 either 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 either 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 + +In case of conflict, git-rebase will stop at the first problematic commit +and leave conflict markers in the tree. After resolving the conflict manually +and updating the index with the desired resolution, you can continue the +rebasing process with + + git am --resolved --3way + +Alternatively, you can undo the git-rebase with + + git reset --hard ORIG_HEAD + rm -r .dotest 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. -<head>:: +<branch>:: Working branch; defaults to HEAD. Author diff --git a/Documentation/git-relink.txt b/Documentation/git-relink.txt index 6240535..aca6012 100644 --- a/Documentation/git-relink.txt +++ b/Documentation/git-relink.txt @@ -3,7 +3,7 @@ git-relink(1) NAME ---- -git-relink - Hardlink common objects in local repositories. +git-relink - Hardlink common objects in local repositories SYNOPSIS -------- diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 6c0f792..d2f9a44 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -63,7 +63,7 @@ Documentation -------------- Documentation by Ryan Anderson <ryan@michonline.com> -See-Also +See Also -------- gitlink:git-pack-objects[1] gitlink:git-prune-packed[1] diff --git a/Documentation/git-repo-config.txt b/Documentation/git-repo-config.txt index 33fcde4..26759a8 100644 --- a/Documentation/git-repo-config.txt +++ b/Documentation/git-repo-config.txt @@ -3,11 +3,12 @@ git-repo-config(1) NAME ---- -git-repo-config - Get and set options in .git/config. +git-repo-config - Get and set options in .git/config SYNOPSIS -------- +[verse] 'git-repo-config' [type] name [value [value_regex]] 'git-repo-config' [type] --replace-all name [value [value_regex]] 'git-repo-config' [type] --get name [value_regex] diff --git a/Documentation/git-request-pull.txt b/Documentation/git-request-pull.txt index 2463ec9..478a5fd 100644 --- a/Documentation/git-request-pull.txt +++ b/Documentation/git-request-pull.txt @@ -3,7 +3,7 @@ git-request-pull(1) NAME ---- -git-request-pull - Generates a summary of pending changes. +git-request-pull - Generates a summary of pending changes SYNOPSIS -------- diff --git a/Documentation/git-reset.txt b/Documentation/git-reset.txt index b4e737e..b7b9798 100644 --- a/Documentation/git-reset.txt +++ b/Documentation/git-reset.txt @@ -3,7 +3,7 @@ git-reset(1) NAME ---- -git-reset - Reset current HEAD to the specified state. +git-reset - Reset current HEAD to the specified state SYNOPSIS -------- diff --git a/Documentation/git-rev-list.txt b/Documentation/git-rev-list.txt index 1c6146c..8255ae1 100644 --- a/Documentation/git-rev-list.txt +++ b/Documentation/git-rev-list.txt @@ -16,9 +16,9 @@ SYNOPSIS [ \--no-merges ] [ \--remove-empty ] [ \--all ] - [ [ \--merge-order [ \--show-breaks ] ] | [ \--topo-order ] ] + [ \--topo-order ] [ \--parents ] - [ \--objects [ \--unpacked ] ] + [ [\--objects | \--objects-edge] [ \--unpacked ] ] [ \--pretty | \--header ] [ \--bisect ] <commit>... [ \-- <paths>... ] @@ -53,6 +53,14 @@ OPTIONS which I need to download if I have the commit object 'bar', but not 'foo'". +--objects-edge:: + Similar to `--objects`, but also print the IDs of + excluded commits refixed with a `-` character. This is + used by `git-pack-objects` to build 'thin' pack, which + records objects in deltified form based on objects + contained in these excluded commits to reduce network + traffic. + --unpacked:: Only useful with `--objects`; print the object IDs that are not in packs. @@ -94,57 +102,10 @@ OPTIONS topological order (i.e. descendant commits are shown before their parents). ---merge-order:: - When specified the commit history is decomposed into a unique - sequence of minimal, non-linear epochs and maximal, linear epochs. - Non-linear epochs are then linearised by sorting them into merge - order, which is described below. -+ -Maximal, linear epochs correspond to periods of sequential development. -Minimal, non-linear epochs correspond to periods of divergent development -followed by a converging merge. The theory of epochs is described in more -detail at -link:http://blackcubes.dyndns.org/epoch/[http://blackcubes.dyndns.org/epoch/]. -+ -The merge order for a non-linear epoch is defined as a linearisation for which -the following invariants are true: -+ - 1. if a commit P is reachable from commit N, commit P sorts after commit N - in the linearised list. - 2. if Pi and Pj are any two parents of a merge M (with i < j), then any - commit N, such that N is reachable from Pj but not reachable from Pi, - sorts before all commits reachable from Pi. -+ -Invariant 1 states that later commits appear before earlier commits they are -derived from. -+ -Invariant 2 states that commits unique to "later" parents in a merge, appear -before all commits from "earlier" parents of a merge. - ---show-breaks:: - Each item of the list is output with a 2-character prefix consisting - of one of: (|), (^), (=) followed by a space. -+ -Commits marked with (=) represent the boundaries of minimal, non-linear epochs -and correspond either to the start of a period of divergent development or to -the end of such a period. -+ -Commits marked with (|) are direct parents of commits immediately preceding -the marked commit in the list. -+ -Commits marked with (^) are not parents of the immediately preceding commit. -These "breaks" represent necessary discontinuities implied by trying to -represent an arbitrary DAG in a linear form. -+ -`--show-breaks` is only valid if `--merge-order` is also specified. - - Author ------ Written by Linus Torvalds <torvalds@osdl.org> -Original *--merge-order* logic by Jon Seymour <jon.seymour@gmail.com> - Documentation -------------- Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>. diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index 1662e06..8b95df0 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -3,7 +3,7 @@ git-rev-parse(1) NAME ---- -git-rev-parse - Pick out and massage parameters. +git-rev-parse - Pick out and massage parameters SYNOPSIS @@ -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-revert.txt b/Documentation/git-revert.txt index e27c680..71f7815 100644 --- a/Documentation/git-revert.txt +++ b/Documentation/git-revert.txt @@ -3,7 +3,7 @@ git-revert(1) NAME ---- -git-revert - Revert an existing commit. +git-revert - Revert an existing commit SYNOPSIS -------- diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt new file mode 100644 index 0000000..c9c3088 --- /dev/null +++ b/Documentation/git-rm.txt @@ -0,0 +1,92 @@ +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`. + +See Also +-------- +gitlink:git-add[1] + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-send-email.txt b/Documentation/git-send-email.txt index 00537d8..8c58685 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-send-pack.txt b/Documentation/git-send-pack.txt index 577f06a..08e0705 100644 --- a/Documentation/git-send-pack.txt +++ b/Documentation/git-send-pack.txt @@ -3,7 +3,7 @@ git-send-pack(1) NAME ---- -git-send-pack - Push missing objects packed. +git-send-pack - Push missing objects packed SYNOPSIS diff --git a/Documentation/git-sh-setup.txt b/Documentation/git-sh-setup.txt index 6ef59ac..6742c9b 100644 --- a/Documentation/git-sh-setup.txt +++ b/Documentation/git-sh-setup.txt @@ -3,7 +3,7 @@ git-sh-setup(1) NAME ---- -git-sh-setup - Common git shell script setup code. +git-sh-setup - Common git shell script setup code SYNOPSIS -------- diff --git a/Documentation/git-shell.txt b/Documentation/git-shell.txt index 3f4d804..cc4266d 100644 --- a/Documentation/git-shell.txt +++ b/Documentation/git-shell.txt @@ -8,7 +8,7 @@ git-shell - Restricted login shell for GIT over SSH only SYNOPSIS -------- -'git-shell -c <command> <argument>' +'git-shell' -c <command> <argument> DESCRIPTION ----------- diff --git a/Documentation/git-shortlog.txt b/Documentation/git-shortlog.txt index 65ca77f..54fb922 100644 --- a/Documentation/git-shortlog.txt +++ b/Documentation/git-shortlog.txt @@ -3,12 +3,12 @@ git-shortlog(1) NAME ---- -git-shortlog - Summarize 'git log' output. +git-shortlog - Summarize 'git log' output SYNOPSIS -------- -'git-log --pretty=short | git shortlog' +git-log --pretty=short | 'git-shortlog' DESCRIPTION ----------- diff --git a/Documentation/git-show-branch.txt b/Documentation/git-show-branch.txt index 7b1a9c9..f115b45 100644 --- a/Documentation/git-show-branch.txt +++ b/Documentation/git-show-branch.txt @@ -3,14 +3,14 @@ git-show-branch(1) NAME ---- -git-show-branch - Show branches and their commits. +git-show-branch - Show branches and their commits SYNOPSIS -------- [verse] -git-show-branch [--all] [--heads] [--tags] [--topo-order] [--current] - [--more=<n> | --list | --independent | --merge-base] - [--no-name | --sha1-name] [<rev> | <glob>]... +'git-show-branch' [--all] [--heads] [--tags] [--topo-order] [--current] + [--more=<n> | --list | --independent | --merge-base] + [--no-name | --sha1-name] [<rev> | <glob>]... DESCRIPTION ----------- @@ -141,7 +141,7 @@ it, having the following in the configuration file may help: ------------ -With this,`git show-branch` without extra parameters would show +With this, `git show-branch` without extra parameters would show only the primary branches. In addition, if you happen to be on your topic branch, it is shown as well. diff --git a/Documentation/git-show.txt b/Documentation/git-show.txt index 9c359a4..2b4df3f 100644 --- a/Documentation/git-show.txt +++ b/Documentation/git-show.txt @@ -3,7 +3,7 @@ git-show(1) NAME ---- -git-show - Show one commit with difference it introduces. +git-show - Show one commit with difference it introduces SYNOPSIS diff --git a/Documentation/git-status.txt b/Documentation/git-status.txt index 753fc08..e446f48 100644 --- a/Documentation/git-status.txt +++ b/Documentation/git-status.txt @@ -3,7 +3,7 @@ git-status(1) NAME ---- -git-status - Show working tree status. +git-status - Show working tree status SYNOPSIS diff --git a/Documentation/git-stripspace.txt b/Documentation/git-stripspace.txt index 528a1b6..3a03dd0 100644 --- a/Documentation/git-stripspace.txt +++ b/Documentation/git-stripspace.txt @@ -3,7 +3,7 @@ git-stripspace(1) NAME ---- -git-stripspace - Filter out empty lines. +git-stripspace - Filter out empty lines SYNOPSIS diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt index 63e28b8..b1b87c2 100644 --- a/Documentation/git-svnimport.txt +++ b/Documentation/git-svnimport.txt @@ -9,11 +9,13 @@ git-svnimport - Import a SVN repository into git SYNOPSIS -------- +[verse] 'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ] - [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] - [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] - [ -s start_chg ] [ -m ] [ -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 +63,34 @@ 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 e8892bb..45476c2 100644 --- a/Documentation/git-tag.txt +++ b/Documentation/git-tag.txt @@ -3,16 +3,18 @@ git-tag(1) NAME ---- -git-tag - Create a tag object signed with GPG +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-tools.txt b/Documentation/git-tools.txt new file mode 100644 index 0000000..00e57a6 --- /dev/null +++ b/Documentation/git-tools.txt @@ -0,0 +1,97 @@ +A short git tools survey +======================== + + +Introduction +------------ + +Apart from git contrib/ area there are some others third-party tools +you may want to look. + +This document presents a brief summary of each tool and the corresponding +link. + + +Alternative/Augmentative Procelains +----------------------------------- + + - *Cogito* (http://www.kernel.org/pub/software/scm/cogito/) + + Cogito is a version control system layered on top of the git tree history + storage system. It aims at seamless user interface and ease of use, + providing generally smoother user experience than the "raw" Core GIT + itself and indeed many other version control systems. + + + - *pg* (http://www.spearce.org/category/projects/scm/pg/) + + pg is a shell script wrapper around GIT to help the user manage a set of + patches to files. pg is somewhat like quilt or StGIT, but it does have a + slightly different feature set. + + + - *StGit* (http://www.procode.org/stgit/) + + Stacked GIT provides a quilt-like patch management functionality in the + GIT environment. You can easily manage your patches in the scope of GIT + until they get merged upstream. + + +History Viewers +--------------- + + - *gitk* (shipped with git-core) + + gitk is a simple TK GUI for browsing history of GIT repositories easily. + + + - *gitview* (contrib/) + + gitview is a GTK based repository browser for git + + + - *gitweb* (ftp://ftp.kernel.org/pub/software/scm/gitweb/) + + GITweb provides full-fledged web interface for GIT repositories. + + + - *qgit* (http://digilander.libero.it/mcostalba/) + + QGit is a git/StGIT GUI viewer built on Qt/C++. QGit could be used + to browse history and directory tree, view annotated files, commit + changes cherry picking single files or applying patches. + Currently it is the fastest and most feature rich among the git + viewers and commit tools. + + + +Foreign SCM interface +--------------------- + + - *git-svn* (contrib/) + + git-svn is a simple conduit for changesets between a single Subversion + branch and git. + + + - *quilt2git / git2quilt* (http://home-tj.org/wiki/index.php/Misc) + + These utilities convert patch series in a quilt repository and commit + series in git back and forth. + + +Others +------ + + - *(h)gct* (http://www.cyd.liu.se/users/~freku045/gct/) + + Commit Tool or (h)gct is a GUI enabled commit tool for git and + Mercurial (hg). It allows the user to view diffs, select which files + to committed (or ignored / reverted) write commit messages and + perform the commit itself. + + - *git.el* (contrib/) + + This is an Emacs interface for git. The user interface is modeled on + pcl-cvs. It has been developed on Emacs 21 and will probably need some + tweaking to work on XEmacs. diff --git a/Documentation/git-unpack-objects.txt b/Documentation/git-unpack-objects.txt index 31ea34d..1828062 100644 --- a/Documentation/git-unpack-objects.txt +++ b/Documentation/git-unpack-objects.txt @@ -3,7 +3,7 @@ git-unpack-objects(1) NAME ---- -git-unpack-objects - Unpack objects from a packed archive. +git-unpack-objects - Unpack objects from a packed archive SYNOPSIS diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt index c74311d..0a1b0ad 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 -------- diff --git a/Documentation/git-update-ref.txt b/Documentation/git-update-ref.txt index 69715aa..475237f 100644 --- a/Documentation/git-update-ref.txt +++ b/Documentation/git-update-ref.txt @@ -7,7 +7,7 @@ git-update-ref - update the object name stored in a ref safely SYNOPSIS -------- -`git-update-ref` <ref> <newvalue> [<oldvalue>] +'git-update-ref' <ref> <newvalue> [<oldvalue>] DESCRIPTION ----------- diff --git a/Documentation/git-upload-pack.txt b/Documentation/git-upload-pack.txt index 3d8f8ef..4795e98 100644 --- a/Documentation/git-upload-pack.txt +++ b/Documentation/git-upload-pack.txt @@ -3,7 +3,7 @@ git-upload-pack(1) NAME ---- -git-upload-pack - Send missing objects packed. +git-upload-pack - Send missing objects packed SYNOPSIS diff --git a/Documentation/git-var.txt b/Documentation/git-var.txt index c22d34f..90cb157 100644 --- a/Documentation/git-var.txt +++ b/Documentation/git-var.txt @@ -8,7 +8,7 @@ git-var - Print the git users identity SYNOPSIS -------- -git-var [ -l | <variable> ] +'git-var' [ -l | <variable> ] DESCRIPTION ----------- diff --git a/Documentation/git-verify-pack.txt b/Documentation/git-verify-pack.txt index d032280..4962d69 100644 --- a/Documentation/git-verify-pack.txt +++ b/Documentation/git-verify-pack.txt @@ -3,7 +3,7 @@ git-verify-pack(1) NAME ---- -git-verify-pack - Validate packed git archive files. +git-verify-pack - Validate packed git archive files SYNOPSIS diff --git a/Documentation/git-verify-tag.txt b/Documentation/git-verify-tag.txt index b8a73c4..0f9bdb5 100644 --- a/Documentation/git-verify-tag.txt +++ b/Documentation/git-verify-tag.txt @@ -3,7 +3,7 @@ git-verify-tag(1) NAME ---- -git-verify-tag - Check the GPG signature of tag. +git-verify-tag - Check the GPG signature of tag SYNOPSIS -------- diff --git a/Documentation/git-whatchanged.txt b/Documentation/git-whatchanged.txt index 6c150b0..641cb7e 100644 --- a/Documentation/git-whatchanged.txt +++ b/Documentation/git-whatchanged.txt @@ -3,7 +3,7 @@ git-whatchanged(1) NAME ---- -git-whatchanged - Show logs with difference each commit introduces. +git-whatchanged - Show logs with difference each commit introduces SYNOPSIS @@ -47,9 +47,9 @@ OPTIONS By default, differences for merge commits are not shown. With this flag, show differences to that commit from all of its parents. - - However, it is not very useful in general, although it - *is* useful on a file-by-file basis. ++ +However, it is not very useful in general, although it +*is* useful on a file-by-file basis. Examples -------- diff --git a/Documentation/git.txt b/Documentation/git.txt index 2d0ca9d..06b2e53 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -12,77 +12,65 @@ SYNOPSIS DESCRIPTION ----------- -'git' is both a program and a directory content tracker system. -The program 'git' is just a wrapper to reach the core git programs -(or a potty if you like, as it's not exactly porcelain but still -brings your stuff to the plumbing). +Git is a fast, scalable, distributed revision control system with an +unusually rich command set that provides both high-level operations +and full access to internals. + +See this link:tutorial.html[tutorial] to get started, then see +link:everyday.html[Everyday Git] for a useful minimum set of commands, and +"man git-commandname" for documentation of each command. CVS users may +also want to read link:cvs-migration.html[CVS migration]. OPTIONS ------- --version:: - prints the git suite version that the 'git' program came from. + Prints the git suite version that the 'git' program came from. --help:: - prints the synopsis and a list of available commands. - If a git command is named this option will bring up the - man-page for that command. + Prints the synopsis and a list of the most commonly used + commands. If a git command is named this option will bring up + the man-page for that command. If the option '--all' or '-a' is + given then all available commands are printed. --exec-path:: - path to wherever your core git programs are installed. + Path to wherever your core git programs are installed. This can also be controlled by setting the GIT_EXEC_PATH environment variable. If no path is given 'git' will print the current setting and then exit. -NOT LEARNING CORE GIT COMMANDS ------------------------------- - -This manual is intended to give complete background information -and internal workings of git, which may be too much for most -people. The <<Discussion>> section below contains much useful -definition and clarification - read that first. - -If you are interested in using git to manage (version control) -projects, use link:tutorial.html[The Tutorial] to get you started, -and then link:everyday.html[Everyday GIT] as a guide to the -minimum set of commands you need to know for day-to-day work. -Most likely, that will get you started, and you can go a long -way without knowing the low level details too much. - -The link:core-tutorial.html[Core tutorial] document covers how things -internally work. - -If you are migrating from CVS, link:cvs-migration.html[cvs -migration] document may be helpful after you finish the -tutorial. +FURTHER DOCUMENTATION +--------------------- -After you get the general feel from the tutorial and this -overview page, you may want to take a look at the -link:howto-index.html[howto] documents. +See the references above to get started using git. The following is +probably more detail than necessary for a first-time user. +The <<Discussion,Discussion>> section below and the +link:core-tutorial.html[Core tutorial] both provide introductions to the +underlying git architecture. -CORE GIT COMMANDS ------------------ +See also the link:howto-index.html[howto] documents for some useful +examples. -If you are writing your own Porcelain, you need to be familiar -with most of the low level commands --- I suggest starting from -gitlink:git-update-index[1] and gitlink:git-read-tree[1]. +GIT COMMANDS +------------ +We divide git into high level ("porcelain") commands and low level +("plumbing") commands. -Commands Overview ------------------ -The git commands can helpfully be split into those that manipulate -the repository, the index and the files in the working tree, those that -interrogate and compare them, and those that moves objects and -references between repositories. +Low-level commands (plumbing) +----------------------------- -In addition, git itself comes with a spartan set of porcelain -commands. They are usable but are not meant to compete with real -Porcelains. +Although git includes its +own porcelain layer, its low-level commands are sufficient to support +development of alternative porcelains. Developers of such porcelains +might start by reading about gitlink:git-update-index[1] and +gitlink:git-read-tree[1]. -There are also some ancillary programs that can be viewed as useful -aids for using the core commands but which are unlikely to be used by -SCMs layered over git. +We divide the low-level commands into commands that manipulate objects (in +the repository, index, and working tree), commands that interrogate and +compare objects, and commands that move objects and references between +repositories. Manipulation commands ~~~~~~~~~~~~~~~~~~~~~ @@ -247,8 +235,14 @@ gitlink:git-upload-pack[1]:: what are asked for. -Porcelain-ish Commands ----------------------- +High-level commands (porcelain) +------------------------------- + +We separate the porcelain commands into the main commands and some +ancillary user utilities. + +Main porcelain commands +~~~~~~~~~~~~~~~~~~~~~~~ gitlink:git-add[1]:: Add paths to the index. @@ -328,6 +322,9 @@ gitlink:git-revert[1]:: gitlink:git-shortlog[1]:: Summarizes 'git log' output. +gitlink:git-show[1]:: + Show one commit log and its diff. + gitlink:git-show-branch[1]:: Show branches and their commits. @@ -342,7 +339,7 @@ gitlink:git-whatchanged[1]:: Ancillary Commands ------------------- +~~~~~~~~~~~~~~~~~~ Manipulators: gitlink:git-applypatch[1]:: @@ -517,16 +514,14 @@ HEAD:: a valid head 'name' (i.e. the contents of `$GIT_DIR/refs/heads/<head>`). -<snap>:: - a valid snapshot 'name' - (i.e. the contents of `$GIT_DIR/refs/snap/<snap>`). - File/Directory Structure ------------------------ Please see link:repository-layout.html[repository layout] document. +Read link:hooks.html[hooks] for more details about each hook. + Higher level SCMs may provide and manage additional information in the `$GIT_DIR`. diff --git a/Documentation/hooks.txt b/Documentation/hooks.txt index 4ad1920..3824a95 100644 --- a/Documentation/hooks.txt +++ b/Documentation/hooks.txt @@ -97,16 +97,31 @@ send out a commit notification e-mail. update ------ -This hook is invoked by `git-receive-pack`, which is invoked -when a `git push` is done against the repository. It takes -three parameters, name of the ref being updated, old object name -stored in the ref, and the new objectname to be stored in the -ref. Exiting with non-zero status from this hook prevents -`git-receive-pack` from updating the ref. - -This can be used to prevent 'forced' update on certain refs by +This hook is invoked by `git-receive-pack` on the remote repository, +which is happens when a `git push` is done on a local repository. +Just before updating the ref on the remote repository, the update hook +is invoked. It's exit status determins the success or failure of +the ref update. + +The hook executes once for each ref to be updated, and takes +three parameters: + - the name of the ref being updated, + - the old object name stored in the ref, + - and the new objectname to be stored in the ref. + +A zero exit from the update hook allows the ref to be updated. +Exiting with a non-zero status prevents `git-receive-pack` +from updating the ref. + +This hook can be used to prevent 'forced' update on certain refs by making sure that the object name is a commit object that is a descendant of the commit object named by the old object name. +That is, to enforce a "fast forward only" policy. + +It could also be used to log the old..new status. However, it +does not know the entire set of branches, so it would end up +firing one e-mail per ref when used naively, though. + Another use suggested on the mailing list is to use this hook to implement access control which is finer grained than the one based on filesystem group. @@ -115,20 +130,30 @@ The standard output of this hook is sent to /dev/null; if you want to report something to the git-send-pack on the other end, you can redirect your output to your stderr. + post-update ----------- -This hook is invoked by `git-receive-pack`, which is invoked -when a `git push` is done against the repository. It takes -variable number of parameters; each of which is the name of ref -that was actually updated. +This hook is invoked by `git-receive-pack` on the remote repository, +which is happens when a `git push` is done on a local repository. +It executes on the remote repository once after all the refs have +been updated. + +It takes a variable number of parameters, each of which is the +name of ref that was actually updated. This hook is meant primarily for notification, and cannot affect the outcome of `git-receive-pack`. +The post-update hook can tell what are the heads that were pushed, +but it does not know what their original and updated values are, +so it is a poor place to do log old..new. + The default post-update hook, when enabled, runs `git-update-server-info` to keep the information used by dumb -transport up-to-date. +transports (eg, http) up-to-date. If you are publishing +a git repository that is accessible via http, you should +probably enable this hook. The standard output of this hook is sent to /dev/null; if you want to report something to the git-send-pack on the other end, diff --git a/Documentation/repository-layout.txt b/Documentation/repository-layout.txt index 1f19bf8..98fbe7d 100644 --- a/Documentation/repository-layout.txt +++ b/Documentation/repository-layout.txt @@ -89,6 +89,8 @@ hooks:: commands. A handful of sample hooks are installed when `git init-db` is run, but all of them are disabled by default. To enable, they need to be made executable. + Read link:hooks.html[hooks] for more details about + each hook. index:: The current index file for the repository. It is diff --git a/Documentation/tutorial.txt b/Documentation/tutorial.txt index 66680d7..fa79b01 100644 --- a/Documentation/tutorial.txt +++ b/Documentation/tutorial.txt @@ -309,7 +309,7 @@ git diff HEAD^^ HEAD^ ------------------------------------- shows the difference between that previous state and the state two -commits ago. Also, HEAD~5 can be used as a shorthand for HEAD^^^^^, +commits ago. Also, HEAD~5 can be used as a shorthand for HEAD{caret}{caret}{caret}{caret}{caret}, and more generally HEAD~n can refer to the nth previous commit. Commits representing merges have more than one parent, and you can specify which parent to follow in that case; see diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index 1056b7c..d2200ac 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,14 +1,17 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v1.2.GIT +DEF_VER=v1.3-rc2.GIT # First try git-describe, then see if there is a version file # (included in release tarballs), then default if VN=$(git-describe --abbrev=4 HEAD 2>/dev/null); then VN=$(echo "$VN" | sed -e 's/-/./g'); -else +elif test -f version +then VN=$(cat version) || VN="$DEF_VER" +else + VN="$DEF_VER" fi VN=$(expr "$VN" : v*'\(.*\)') @@ -40,9 +40,7 @@ Issues of note: If you don't have openssl, you can use one of the SHA1 libraries that come with git (git includes the one from Mozilla, and has - its own PowerPC-optimized one too - see the Makefile), and you - can avoid the bignum support by excising git-rev-list support - for "--merge-order" (by hand). + its own PowerPC and ARM optimized ones too - see the Makefile). - "libcurl" and "curl" executable. git-http-fetch and git-fetch use them. If you do not use http @@ -6,8 +6,8 @@ all: # on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default # choice) has very fast version optimized for i586. # -# Define NO_OPENSSL environment variable if you do not have OpenSSL. You will -# miss out git-rev-list --merge-order. This also implies MOZILLA_SHA1. +# Define NO_OPENSSL environment variable if you do not have OpenSSL. +# This also implies MOZILLA_SHA1. # # Define NO_CURL if you do not have curl installed. git-http-pull and # git-http-push are not built, and you cannot use http:// and https:// @@ -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 = \ @@ -127,9 +141,9 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ $(patsubst %.py,%,$(SCRIPT_PYTHON)) \ git-cherry-pick git-show git-status -# The ones that do not have to link with lcrypto nor lz. +# The ones that do not have to link with lcrypto, lz nor xdiff. 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 git-blame$X git-imap-send$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -174,34 +188,31 @@ PYMODULES = \ gitMergeCommon.py LIB_FILE=libgit.a +XDIFF_LIB=xdiff/lib.a LIB_H = \ - blob.h cache.h commit.h count-delta.h csum-file.h delta.h \ - diff.h epoch.h object.h pack.h pkt-line.h quote.h refs.h \ - run-command.h strbuf.h tag.h tree.h git-compat-util.h + blob.h cache.h commit.h csum-file.h delta.h \ + diff.h object.h pack.h pkt-line.h quote.h refs.h \ + run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \ + tree-walk.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 \ + blob.o commit.o connect.o csum-file.o \ date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \ object.o pack-check.o patch-delta.o path.o pkt-line.o \ quote.o read-cache.o refs.o run-command.o \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ - fetch-clone.o \ + fetch-clone.o revision.o pager.o tree-walk.o \ $(DIFF_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))' +GITLIBS = $(LIB_FILE) $(XDIFF_LIB) +LIBS = $(GITLIBS) -lz # # Platform specific tweaks @@ -210,28 +221,28 @@ shellquote = '$(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 +282,16 @@ 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 +301,10 @@ 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 @@ -308,7 +331,6 @@ ifndef NO_CURL endif ifndef NO_OPENSSL - LIB_OBJS += epoch.o OPENSSL_LIBSSL = -lssl ifdef OPENSSLDIR # Again this may be problematic -- gcc does not always want -R. @@ -380,6 +402,10 @@ 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 +423,25 @@ else endif endif endif +ifdef NO_ACCURATE_DIFF + ALL_CFLAGS += -DNO_ACCURATE_DIFF +endif + +# Shell quote (do not use $(call) to accomodate ancient setups); + +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) -ALL_CFLAGS += -DSHA1_HEADER=$(call shellquote,$(SHA1_HEADER)) $(COMPAT_CFLAGS) +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +gitexecdir_SQ = $(subst ','\'',$(gitexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) + +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH)) +GIT_PYTHON_DIR_SQ = $(subst ','\'',$(GIT_PYTHON_DIR)) + +ALL_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS) LIB_OBJS += $(COMPAT_OBJS) export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir ### Build rules @@ -411,29 +454,34 @@ all: strip: $(PROGRAMS) git$X $(STRIP) $(STRIP_OPTS) $(PROGRAMS) git$X -git$X: git.c $(LIB_FILE) +git$X: git.c common-cmds.h $(GITLIBS) $(CC) -DGIT_VERSION='"$(GIT_VERSION)"' \ - $(CFLAGS) $(COMPAT_CFLAGS) -o $@ $(filter %.c,$^) $(LIB_FILE) + $(ALL_CFLAGS) -o $@ $(filter %.c,$^) \ + $(ALL_LDFLAGS) $(LIBS) + +common-cmds.h: Documentation/git-*.txt + ./generate-cmdlist.sh > $@ $(patsubst %.sh,%,$(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 $@ @@ -459,46 +507,80 @@ git$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) +http.o: http.c + $(CC) -o $*.o -c $(ALL_CFLAGS) -DGIT_USER_AGENT='"git/$(GIT_VERSION)"' $< + +git-%$X: %.o $(GITLIBS) $(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 += $(OPENSSL_LIBSSL) +git-imap-send$X: imap-send.o $(LIB_FILE) + +git-http-fetch$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: revision.o 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)): $(LIB_H) +$(patsubst git-%$X,%.o,$(PROGRAMS)): $(GITLIBS) $(DIFF_OBJS): diffcore.h $(LIB_FILE): $(LIB_OBJS) $(AR) rcs $@ $(LIB_OBJS) +XDIFF_OBJS=xdiff/xdiffi.o xdiff/xprepare.o xdiff/xutils.o xdiff/xemit.o + +$(XDIFF_LIB): $(XDIFF_OBJS) + $(AR) rcs $@ $(XDIFF_OBJS) + + doc: $(MAKE) -C Documentation all +TAGS: + rm -f TAGS + find . -name '*.[hcS]' -print | xargs etags -a + +tags: + rm -f tags + find . -name '*.[hcS]' -print | xargs ctags -a ### 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 $(MAKE) -C t/ all @@ -506,7 +588,7 @@ test-date$X: test-date.c date.o ctype.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) test-date.c date.o ctype.o test-delta$X: test-delta.c diff-delta.o patch-delta.o - $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ -lz check: for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done @@ -516,13 +598,13 @@ 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 @@ -552,9 +634,10 @@ rpm: dist ### Cleaning rules clean: - rm -f *.o mozilla-sha1/*.o arm/*.o ppc/*.o compat/*.o $(LIB_FILE) + rm -f *.o mozilla-sha1/*.o arm/*.o ppc/*.o compat/*.o xdiff/*.o \ + $(LIB_FILE) $(XDIFF_LIB) rm -f $(ALL_PROGRAMS) git$X - rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo + rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags rm -rf $(GIT_TARNAME) rm -f $(GIT_TARNAME).tar.gz git-core_$(GIT_VERSION)-*.tar.gz $(MAKE) -C Documentation/ clean @@ -563,5 +646,5 @@ clean: rm -f GIT-VERSION-FILE .PHONY: all install clean strip -.PHONY: .FORCE-GIT-VERSION-FILE +.PHONY: .FORCE-GIT-VERSION-FILE TAGS tags @@ -9,6 +9,7 @@ #include <fnmatch.h> #include "cache.h" #include "quote.h" +#include "blob.h" // --check turns on checking that the working tree matches the // files that are being modified, but doesn't apply the patch @@ -32,7 +33,7 @@ static int no_add = 0; static int show_index_info = 0; static int line_termination = '\n'; static const char apply_usage[] = -"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] <patch>..."; +"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>..."; static enum whitespace_eol { nowarn_whitespace, @@ -651,7 +652,7 @@ static int parse_git_header(char *line, int len, unsigned int size, struct patch len = linelen(line, size); if (!len || line[len-1] != '\n') break; - for (i = 0; i < sizeof(optable) / sizeof(optable[0]); i++) { + for (i = 0; i < ARRAY_SIZE(optable); i++) { const struct opentry *p = optable + i; int oplen = strlen(p->str); if (len < oplen || memcmp(p->str, line, oplen)) @@ -693,7 +694,7 @@ static int parse_range(const char *line, int len, int offset, const char *expect line += digits; len -= digits; - *p2 = *p1; + *p2 = 1; if (*line == ',') { digits = parse_num(line+1, p2); if (!digits) @@ -834,7 +835,7 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s patch->new_name = NULL; } - if (patch->is_new != !oldlines) + if (patch->is_new && oldlines) return error("new file depends on old contents"); if (patch->is_delete != !newlines) { if (newlines) @@ -901,6 +902,8 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s break; } } + if (oldlines || newlines) + return -1; /* If a fragment ends with an incomplete line, we failed to include * it in the above loop because we hit oldlines == newlines == 0 * before seeing it. @@ -922,8 +925,7 @@ static int parse_single_patch(char *line, unsigned long size, struct patch *patc struct fragment *fragment; int len; - fragment = xmalloc(sizeof(*fragment)); - memset(fragment, 0, sizeof(*fragment)); + fragment = xcalloc(1, sizeof(*fragment)); len = parse_fragment(line, size, patch, fragment); if (len <= 0) die("corrupt patch at line %d", linenr); @@ -1232,6 +1234,14 @@ 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; @@ -1286,7 +1296,7 @@ static int apply_fragments(struct buffer_desc *desc, struct patch *patch) * applies to. */ write_sha1_file_prepare(desc->buffer, desc->size, - "blob", sha1, hdr, &hdrlen); + blob_type, sha1, hdr, &hdrlen); if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix)) return error("the patch applies to '%s' (%s), " "which does not match the " @@ -1394,12 +1404,13 @@ static int check_patch(struct patch *patch) costate.not_new = 0; costate.refresh_cache = 1; if (checkout_entry(active_cache[pos], - &costate) || + &costate, + NULL) || lstat(old_name, &st)) 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); @@ -1640,15 +1651,14 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned if (!write_index) return; - ce = xmalloc(ce_size); - memset(ce, 0, ce_size); + ce = xcalloc(1, ce_size); memcpy(ce->name, path, namelen); ce->ce_mode = create_ce_mode(mode); ce->ce_flags = htons(namelen); if (lstat(path, &st) < 0) die("unable to stat newly created file %s", path); fill_stat_cache_info(ce, &st); - if (write_sha1_file(buf, size, "blob", ce->sha1) < 0) + if (write_sha1_file(buf, size, blob_type, ce->sha1) < 0) die("unable to create backing store for newly created file %s", path); if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0) die("unable to add cache entry for %s", path); @@ -1797,8 +1807,7 @@ static int apply_patch(int fd, const char *filename) struct patch *patch; int nr; - patch = xmalloc(sizeof(*patch)); - memset(patch, 0, sizeof(*patch)); + patch = xcalloc(1, sizeof(*patch)); nr = parse_chunk(buffer + offset, size, patch); if (nr < 0) break; @@ -0,0 +1,892 @@ +/* + * Copyright (C) 2006, Fredrik Kuivinen <freku045@student.liu.se> + */ + +#include <assert.h> +#include <time.h> +#include <sys/time.h> +#include <math.h> + +#include "cache.h" +#include "refs.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "diff.h" +#include "diffcore.h" +#include "revision.h" + +#define DEBUG 0 + +static const char blame_usage[] = "[-c] [-l] [--] file [commit]\n" + " -c, --compability Use the same output mode as git-annotate (Default: off)\n" + " -l, --long Show long commit SHA1 (Default: off)\n" + " -h, --help This message"; + +static struct commit **blame_lines; +static int num_blame_lines; +static char* blame_contents; +static int blame_len; + +struct util_info { + int *line_map; + unsigned char sha1[20]; /* blob sha, not commit! */ + char *buf; + unsigned long size; + int num_lines; + const char* pathname; + + void* topo_data; +}; + +struct chunk { + int off1, len1; // --- + int off2, len2; // +++ +}; + +struct patch { + struct chunk *chunks; + int num; +}; + +static void get_blob(struct commit *commit); + +/* Only used for statistics */ +static int num_get_patch = 0; +static int num_commits = 0; +static int patch_time = 0; + +#define TEMPFILE_PATH_LEN 60 +static struct patch *get_patch(struct commit *commit, struct commit *other) +{ + struct patch *ret; + struct util_info *info_c = (struct util_info *)commit->object.util; + struct util_info *info_o = (struct util_info *)other->object.util; + char tmp_path1[TEMPFILE_PATH_LEN], tmp_path2[TEMPFILE_PATH_LEN]; + char diff_cmd[TEMPFILE_PATH_LEN*2 + 20]; + struct timeval tv_start, tv_end; + int fd; + FILE *fin; + char buf[1024]; + + ret = xmalloc(sizeof(struct patch)); + ret->chunks = NULL; + ret->num = 0; + + get_blob(commit); + get_blob(other); + + gettimeofday(&tv_start, NULL); + + fd = git_mkstemp(tmp_path1, TEMPFILE_PATH_LEN, "git-blame-XXXXXX"); + if (fd < 0) + die("unable to create temp-file: %s", strerror(errno)); + + if (xwrite(fd, info_c->buf, info_c->size) != info_c->size) + die("write failed: %s", strerror(errno)); + close(fd); + + fd = git_mkstemp(tmp_path2, TEMPFILE_PATH_LEN, "git-blame-XXXXXX"); + if (fd < 0) + die("unable to create temp-file: %s", strerror(errno)); + + if (xwrite(fd, info_o->buf, info_o->size) != info_o->size) + die("write failed: %s", strerror(errno)); + close(fd); + + sprintf(diff_cmd, "diff -U 0 %s %s", tmp_path1, tmp_path2); + fin = popen(diff_cmd, "r"); + if (!fin) + die("popen failed: %s", strerror(errno)); + + while (fgets(buf, sizeof(buf), fin)) { + struct chunk *chunk; + char *start, *sp; + + if (buf[0] != '@' || buf[1] != '@') + continue; + + if (DEBUG) + printf("chunk line: %s", buf); + ret->num++; + ret->chunks = xrealloc(ret->chunks, + sizeof(struct chunk) * ret->num); + chunk = &ret->chunks[ret->num - 1]; + + assert(!strncmp(buf, "@@ -", 4)); + + start = buf + 4; + sp = index(start, ' '); + *sp = '\0'; + if (index(start, ',')) { + int ret = + sscanf(start, "%d,%d", &chunk->off1, &chunk->len1); + assert(ret == 2); + } else { + int ret = sscanf(start, "%d", &chunk->off1); + assert(ret == 1); + chunk->len1 = 1; + } + *sp = ' '; + + start = sp + 1; + sp = index(start, ' '); + *sp = '\0'; + if (index(start, ',')) { + int ret = + sscanf(start, "%d,%d", &chunk->off2, &chunk->len2); + assert(ret == 2); + } else { + int ret = sscanf(start, "%d", &chunk->off2); + assert(ret == 1); + chunk->len2 = 1; + } + *sp = ' '; + + if (chunk->len1 == 0) + chunk->off1++; + if (chunk->len2 == 0) + chunk->off2++; + + if (chunk->off1 > 0) + chunk->off1--; + if (chunk->off2 > 0) + chunk->off2--; + + assert(chunk->off1 >= 0); + assert(chunk->off2 >= 0); + } + pclose(fin); + unlink(tmp_path1); + unlink(tmp_path2); + + gettimeofday(&tv_end, NULL); + patch_time += 1000000 * (tv_end.tv_sec - tv_start.tv_sec) + + tv_end.tv_usec - tv_start.tv_usec; + + num_get_patch++; + return ret; +} + +static void free_patch(struct patch *p) +{ + free(p->chunks); + free(p); +} + +static int get_blob_sha1_internal(unsigned char *sha1, const char *base, + int baselen, const char *pathname, + unsigned mode, int stage); + +static unsigned char blob_sha1[20]; +static const char* blame_file; +static int get_blob_sha1(struct tree *t, const char *pathname, + unsigned char *sha1) +{ + int i; + const char *pathspec[2]; + blame_file = pathname; + pathspec[0] = pathname; + pathspec[1] = NULL; + memset(blob_sha1, 0, sizeof(blob_sha1)); + read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal); + + for (i = 0; i < 20; i++) { + if (blob_sha1[i] != 0) + break; + } + + if (i == 20) + return -1; + + memcpy(sha1, blob_sha1, 20); + return 0; +} + +static int get_blob_sha1_internal(unsigned char *sha1, const char *base, + int baselen, const char *pathname, + unsigned mode, int stage) +{ + if (S_ISDIR(mode)) + return READ_TREE_RECURSIVE; + + if (strncmp(blame_file, base, baselen) || + strcmp(blame_file + baselen, pathname)) + return -1; + + memcpy(blob_sha1, sha1, 20); + return -1; +} + +static void get_blob(struct commit *commit) +{ + struct util_info *info = commit->object.util; + char type[20]; + + if (info->buf) + return; + + info->buf = read_sha1_file(info->sha1, type, &info->size); + + assert(!strcmp(type, blob_type)); +} + +/* For debugging only */ +static void print_patch(struct patch *p) +{ + int i; + printf("Num chunks: %d\n", p->num); + for (i = 0; i < p->num; i++) { + printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1, + p->chunks[i].off2, p->chunks[i].len2); + } +} + +#if DEBUG +/* For debugging only */ +static void print_map(struct commit *cmit, struct commit *other) +{ + struct util_info *util = cmit->object.util; + struct util_info *util2 = other->object.util; + + int i; + int max = + util->num_lines > + util2->num_lines ? util->num_lines : util2->num_lines; + int num; + + for (i = 0; i < max; i++) { + printf("i: %d ", i); + num = -1; + + if (i < util->num_lines) { + num = util->line_map[i]; + printf("%d\t", num); + } else + printf("\t"); + + if (i < util2->num_lines) { + int num2 = util2->line_map[i]; + printf("%d\t", num2); + if (num != -1 && num2 != num) + printf("---"); + } else + printf("\t"); + + printf("\n"); + } +} +#endif + +// p is a patch from commit to other. +static void fill_line_map(struct commit *commit, struct commit *other, + struct patch *p) +{ + struct util_info *util = commit->object.util; + struct util_info *util2 = other->object.util; + int *map = util->line_map; + int *map2 = util2->line_map; + int cur_chunk = 0; + int i1, i2; + + if (p->num && DEBUG) + print_patch(p); + + if (DEBUG) + printf("num lines 1: %d num lines 2: %d\n", util->num_lines, + util2->num_lines); + + for (i1 = 0, i2 = 0; i1 < util->num_lines; i1++, i2++) { + struct chunk *chunk = NULL; + if (cur_chunk < p->num) + chunk = &p->chunks[cur_chunk]; + + if (chunk && chunk->off1 == i1) { + if (DEBUG && i2 != chunk->off2) + printf("i2: %d off2: %d\n", i2, chunk->off2); + + assert(i2 == chunk->off2); + + i1--; + i2--; + if (chunk->len1 > 0) + i1 += chunk->len1; + + if (chunk->len2 > 0) + i2 += chunk->len2; + + cur_chunk++; + } else { + if (i2 >= util2->num_lines) + break; + + if (map[i1] != map2[i2] && map[i1] != -1) { + if (DEBUG) + printf("map: i1: %d %d %p i2: %d %d %p\n", + i1, map[i1], + i1 != -1 ? blame_lines[map[i1]] : NULL, + i2, map2[i2], + i2 != -1 ? blame_lines[map2[i2]] : NULL); + if (map2[i2] != -1 && + blame_lines[map[i1]] && + !blame_lines[map2[i2]]) + map[i1] = map2[i2]; + } + + if (map[i1] == -1 && map2[i2] != -1) + map[i1] = map2[i2]; + } + + if (DEBUG > 1) + printf("l1: %d l2: %d i1: %d i2: %d\n", + map[i1], map2[i2], i1, i2); + } +} + +static int map_line(struct commit *commit, int line) +{ + struct util_info *info = commit->object.util; + assert(line >= 0 && line < info->num_lines); + return info->line_map[line]; +} + +static struct util_info* get_util(struct commit *commit) +{ + struct util_info *util = commit->object.util; + + if (util) + return util; + + util = xmalloc(sizeof(struct util_info)); + util->buf = NULL; + util->size = 0; + util->line_map = NULL; + util->num_lines = -1; + util->pathname = NULL; + commit->object.util = util; + return util; +} + +static int fill_util_info(struct commit *commit) +{ + struct util_info *util = commit->object.util; + + assert(util); + assert(util->pathname); + + if (get_blob_sha1(commit->tree, util->pathname, util->sha1)) + return 1; + else + return 0; +} + +static void alloc_line_map(struct commit *commit) +{ + struct util_info *util = commit->object.util; + int i; + + if (util->line_map) + return; + + get_blob(commit); + + util->num_lines = 0; + for (i = 0; i < util->size; i++) { + if (util->buf[i] == '\n') + util->num_lines++; + } + if(util->buf[util->size - 1] != '\n') + util->num_lines++; + + util->line_map = xmalloc(sizeof(int) * util->num_lines); + + for (i = 0; i < util->num_lines; i++) + util->line_map[i] = -1; +} + +static void init_first_commit(struct commit* commit, const char* filename) +{ + struct util_info* util = commit->object.util; + int i; + + util->pathname = filename; + if (fill_util_info(commit)) + die("fill_util_info failed"); + + alloc_line_map(commit); + + util = commit->object.util; + + for (i = 0; i < util->num_lines; i++) + util->line_map[i] = i; +} + + +static void process_commits(struct rev_info *rev, const char *path, + struct commit** initial) +{ + int i; + struct util_info* util; + int lines_left; + int *blame_p; + int *new_lines; + int new_lines_len; + + struct commit* commit = get_revision(rev); + assert(commit); + init_first_commit(commit, path); + + util = commit->object.util; + num_blame_lines = util->num_lines; + blame_lines = xmalloc(sizeof(struct commit *) * num_blame_lines); + blame_contents = util->buf; + blame_len = util->size; + + for (i = 0; i < num_blame_lines; i++) + blame_lines[i] = NULL; + + lines_left = num_blame_lines; + blame_p = xmalloc(sizeof(int) * num_blame_lines); + new_lines = xmalloc(sizeof(int) * num_blame_lines); + do { + struct commit_list *parents; + int num_parents; + struct util_info *util; + + if (DEBUG) + printf("\nProcessing commit: %d %s\n", num_commits, + sha1_to_hex(commit->object.sha1)); + + if (lines_left == 0) + return; + + num_commits++; + memset(blame_p, 0, sizeof(int) * num_blame_lines); + new_lines_len = 0; + num_parents = 0; + for (parents = commit->parents; + parents != NULL; parents = parents->next) + num_parents++; + + if(num_parents == 0) + *initial = commit; + + if (fill_util_info(commit)) + continue; + + alloc_line_map(commit); + util = commit->object.util; + + for (parents = commit->parents; + parents != NULL; parents = parents->next) { + struct commit *parent = parents->item; + struct patch *patch; + + if (parse_commit(parent) < 0) + die("parse_commit error"); + + if (DEBUG) + printf("parent: %s\n", + sha1_to_hex(parent->object.sha1)); + + if (fill_util_info(parent)) { + num_parents--; + continue; + } + + patch = get_patch(parent, commit); + alloc_line_map(parent); + fill_line_map(parent, commit, patch); + + for (i = 0; i < patch->num; i++) { + int l; + for (l = 0; l < patch->chunks[i].len2; l++) { + int mapped_line = + map_line(commit, patch->chunks[i].off2 + l); + if (mapped_line != -1) { + blame_p[mapped_line]++; + if (blame_p[mapped_line] == num_parents) + new_lines[new_lines_len++] = mapped_line; + } + } + } + free_patch(patch); + } + + if (DEBUG) + printf("parents: %d\n", num_parents); + + for (i = 0; i < new_lines_len; i++) { + int mapped_line = new_lines[i]; + if (blame_lines[mapped_line] == NULL) { + blame_lines[mapped_line] = commit; + lines_left--; + if (DEBUG) + printf("blame: mapped: %d i: %d\n", + mapped_line, i); + } + } + } while ((commit = get_revision(rev)) != NULL); +} + + +static int compare_tree_path(struct rev_info* revs, + struct commit* c1, struct commit* c2) +{ + const char* paths[2]; + struct util_info* util = c2->object.util; + paths[0] = util->pathname; + paths[1] = NULL; + + diff_tree_setup_paths(get_pathspec(revs->prefix, paths)); + return rev_compare_tree(c1->tree, c2->tree); +} + + +static int same_tree_as_empty_path(struct rev_info *revs, struct tree* t1, + const char* path) +{ + const char* paths[2]; + paths[0] = path; + paths[1] = NULL; + + diff_tree_setup_paths(get_pathspec(revs->prefix, paths)); + return rev_same_tree_as_empty(t1); +} + +static const char* find_rename(struct commit* commit, struct commit* parent) +{ + struct util_info* cutil = commit->object.util; + struct diff_options diff_opts; + const char *paths[1]; + int i; + + if (DEBUG) { + printf("find_rename commit: %s ", + sha1_to_hex(commit->object.sha1)); + puts(sha1_to_hex(parent->object.sha1)); + } + + diff_setup(&diff_opts); + diff_opts.recursive = 1; + diff_opts.detect_rename = DIFF_DETECT_RENAME; + paths[0] = NULL; + diff_tree_setup_paths(paths); + if (diff_setup_done(&diff_opts) < 0) + die("diff_setup_done failed"); + + diff_tree_sha1(commit->tree->object.sha1, parent->tree->object.sha1, + "", &diff_opts); + diffcore_std(&diff_opts); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + + if (p->status == 'R' && !strcmp(p->one->path, cutil->pathname)) { + if (DEBUG) + printf("rename %s -> %s\n", p->one->path, p->two->path); + return p->two->path; + } + } + + return 0; +} + +static void simplify_commit(struct rev_info *revs, struct commit *commit) +{ + struct commit_list **pp, *parent; + + if (!commit->tree) + return; + + if (!commit->parents) { + struct util_info* util = commit->object.util; + if (!same_tree_as_empty_path(revs, commit->tree, + util->pathname)) + commit->object.flags |= TREECHANGE; + return; + } + + pp = &commit->parents; + while ((parent = *pp) != NULL) { + struct commit *p = parent->item; + + if (p->object.flags & UNINTERESTING) { + pp = &parent->next; + continue; + } + + parse_commit(p); + switch (compare_tree_path(revs, p, commit)) { + case REV_TREE_SAME: + parent->next = NULL; + commit->parents = parent; + get_util(p)->pathname = get_util(commit)->pathname; + return; + + case REV_TREE_NEW: + { + + struct util_info* util = commit->object.util; + if (revs->remove_empty_trees && + same_tree_as_empty_path(revs, p->tree, + util->pathname)) { + const char* new_name = find_rename(commit, p); + if (new_name) { + struct util_info* putil = get_util(p); + if (!putil->pathname) + putil->pathname = strdup(new_name); + } else { + *pp = parent->next; + continue; + } + } + } + + /* fallthrough */ + case REV_TREE_DIFFERENT: + pp = &parent->next; + if (!get_util(p)->pathname) + get_util(p)->pathname = + get_util(commit)->pathname; + continue; + } + die("bad tree compare for commit %s", + sha1_to_hex(commit->object.sha1)); + } + commit->object.flags |= TREECHANGE; +} + + +struct commit_info +{ + char* author; + char* author_mail; + unsigned long author_time; + char* author_tz; +}; + +static void get_commit_info(struct commit* commit, struct commit_info* ret) +{ + int len; + char* tmp; + static char author_buf[1024]; + + tmp = strstr(commit->buffer, "\nauthor ") + 8; + len = index(tmp, '\n') - tmp; + ret->author = author_buf; + memcpy(ret->author, tmp, len); + + tmp = ret->author; + tmp += len; + *tmp = 0; + while(*tmp != ' ') + tmp--; + ret->author_tz = tmp+1; + + *tmp = 0; + while(*tmp != ' ') + tmp--; + ret->author_time = strtoul(tmp, NULL, 10); + + *tmp = 0; + while(*tmp != ' ') + tmp--; + ret->author_mail = tmp + 1; + + *tmp = 0; +} + +static const char* format_time(unsigned long time, const char* tz_str) +{ + static char time_buf[128]; + time_t t = time; + int minutes, tz; + struct tm *tm; + + tz = atoi(tz_str); + minutes = tz < 0 ? -tz : tz; + minutes = (minutes / 100)*60 + (minutes % 100); + minutes = tz < 0 ? -minutes : minutes; + t = time + minutes * 60; + tm = gmtime(&t); + + strftime(time_buf, sizeof(time_buf), "%Y-%m-%d %H:%M:%S ", tm); + strcat(time_buf, tz_str); + return time_buf; +} + +static void topo_setter(struct commit* c, void* data) +{ + struct util_info* util = c->object.util; + util->topo_data = data; +} + +static void* topo_getter(struct commit* c) +{ + struct util_info* util = c->object.util; + return util->topo_data; +} + +int main(int argc, const char **argv) +{ + int i; + struct commit *initial = NULL; + unsigned char sha1[20]; + + const char *filename = NULL, *commit = NULL; + char filename_buf[256]; + int sha1_len = 8; + int compability = 0; + int options = 1; + struct commit* start_commit; + + const char* args[10]; + struct rev_info rev; + + struct commit_info ci; + const char *buf; + int max_digits; + int longest_file, longest_author; + int found_rename; + + const char* prefix = setup_git_directory(); + git_config(git_default_config); + + for(i = 1; i < argc; i++) { + if(options) { + if(!strcmp(argv[i], "-h") || + !strcmp(argv[i], "--help")) + usage(blame_usage); + else if(!strcmp(argv[i], "-l") || + !strcmp(argv[i], "--long")) { + sha1_len = 40; + continue; + } else if(!strcmp(argv[i], "-c") || + !strcmp(argv[i], "--compability")) { + compability = 1; + continue; + } else if(!strcmp(argv[i], "--")) { + options = 0; + continue; + } else if(argv[i][0] == '-') + usage(blame_usage); + else + options = 0; + } + + if(!options) { + if(!filename) + filename = argv[i]; + else if(!commit) + commit = argv[i]; + else + usage(blame_usage); + } + } + + if(!filename) + usage(blame_usage); + if(!commit) + commit = "HEAD"; + + if(prefix) + sprintf(filename_buf, "%s%s", prefix, filename); + else + strcpy(filename_buf, filename); + filename = filename_buf; + + if (get_sha1(commit, sha1)) + die("get_sha1 failed, commit '%s' not found", commit); + start_commit = lookup_commit_reference(sha1); + get_util(start_commit)->pathname = filename; + if (fill_util_info(start_commit)) { + printf("%s not found in %s\n", filename, commit); + return 1; + } + + + init_revisions(&rev); + rev.remove_empty_trees = 1; + rev.topo_order = 1; + rev.prune_fn = simplify_commit; + rev.topo_setter = topo_setter; + rev.topo_getter = topo_getter; + rev.limited = 1; + + commit_list_insert(start_commit, &rev.commits); + + args[0] = filename; + args[1] = NULL; + diff_tree_setup_paths(args); + prepare_revision_walk(&rev); + process_commits(&rev, filename, &initial); + + buf = blame_contents; + for (max_digits = 1, i = 10; i <= num_blame_lines + 1; max_digits++) + i *= 10; + + longest_file = 0; + longest_author = 0; + found_rename = 0; + for (i = 0; i < num_blame_lines; i++) { + struct commit *c = blame_lines[i]; + struct util_info* u; + if (!c) + c = initial; + u = c->object.util; + + if (!found_rename && strcmp(filename, u->pathname)) + found_rename = 1; + if (longest_file < strlen(u->pathname)) + longest_file = strlen(u->pathname); + get_commit_info(c, &ci); + if (longest_author < strlen(ci.author)) + longest_author = strlen(ci.author); + } + + for (i = 0; i < num_blame_lines; i++) { + struct commit *c = blame_lines[i]; + struct util_info* u; + + if (!c) + c = initial; + + u = c->object.util; + get_commit_info(c, &ci); + fwrite(sha1_to_hex(c->object.sha1), sha1_len, 1, stdout); + if(compability) { + printf("\t(%10s\t%10s\t%d)", ci.author, + format_time(ci.author_time, ci.author_tz), i+1); + } else { + if (found_rename) + printf(" %-*.*s", longest_file, longest_file, + u->pathname); + printf(" (%-*.*s %10s %*d) ", + longest_author, longest_author, ci.author, + format_time(ci.author_time, ci.author_tz), + max_digits, i+1); + } + + if(i == num_blame_lines - 1) { + fwrite(buf, blame_len - (buf - blame_contents), + 1, stdout); + if(blame_contents[blame_len-1] != '\n') + putc('\n', stdout); + } else { + char* next_buf = index(buf, '\n') + 1; + fwrite(buf, next_buf - buf, 1, stdout); + buf = next_buf; + } + } + + if (DEBUG) { + printf("num get patch: %d\n", num_get_patch); + printf("num commits: %d\n", num_commits); + printf("patch time: %f\n", patch_time / 1000000.0); + printf("initial: %s\n", sha1_to_hex(initial->object.sha1)); + } + + return 0; +} @@ -8,8 +8,7 @@ struct blob *lookup_blob(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - struct blob *ret = xmalloc(sizeof(struct blob)); - memset(ret, 0, sizeof(struct blob)); + struct blob *ret = xcalloc(1, sizeof(struct blob)); created_object(sha1, &ret->object); ret->object.type = blob_type; return ret; @@ -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)) @@ -105,6 +106,9 @@ static inline unsigned int create_ce_mode(unsigned int mode) return htonl(S_IFLNK); return htonl(S_IFREG | ce_permissions(mode)); } +#define canon_mode(mode) \ + (S_ISREG(mode) ? (S_IFREG | ce_permissions(mode)) : \ + S_ISLNK(mode) ? S_IFLNK : S_IFDIR) #define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7) @@ -144,8 +148,8 @@ 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); @@ -162,7 +166,9 @@ 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 warn_ambiguous_refs; extern int diff_rename_limit_default; extern int shared_repository; extern const char *apply_default_whitespace; @@ -260,7 +266,7 @@ struct checkout { refresh_cache:1; }; -extern int checkout_entry(struct cache_entry *ce, struct checkout *state); +extern int checkout_entry(struct cache_entry *ce, struct checkout *state, char *topath); extern struct alternate_object_database { struct alternate_object_database *next; @@ -324,7 +330,7 @@ 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); @@ -352,4 +358,7 @@ extern int copy_fd(int ifd, int ofd); extern int receive_unpack_pack(int fd[2], const char *me, int quiet); extern int receive_keep_pack(int fd[2], const char *me, int quiet); +/* pager.c */ +extern void setup_pager(void); + #endif /* CACHE_H */ @@ -4,6 +4,94 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "exec_cmd.h" +#include "tag.h" +#include "tree.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) { @@ -14,8 +102,9 @@ int main(int argc, char **argv) int opt; setup_git_directory(); + git_config(git_default_config); 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 +132,23 @@ 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_type)) + 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_type)) + 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 +160,6 @@ 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 53dd8cb..dd6a2d8 100644 --- a/checkout-index.c +++ b/checkout-index.c @@ -22,6 +22,10 @@ * * find . -name '*.h' -print0 | xargs -0 git-checkout-index -f -- * + * or: + * + * find . -name '*.h' -print0 | git-checkout-index -f -z --stdin + * * which will force all existing *.h files to be replaced with * their cached copies. If an empty command line implied "all", * then this would force-refresh everything in the cache, which @@ -33,10 +37,16 @@ * but get used to it in scripting!). */ #include "cache.h" +#include "strbuf.h" +#include "quote.h" +#define CHECKOUT_ALL 4 static const char *prefix; static int prefix_length; +static int line_termination = '\n'; static int checkout_stage; /* default to checkout stage0 */ +static int to_tempfile; +static char topath[4][MAXPATHLEN+1]; static struct checkout state = { .base_dir = "", @@ -47,11 +57,39 @@ static struct checkout state = { .refresh_cache = 0, }; +static void write_tempfile_record (const char *name) +{ + int i; + + if (CHECKOUT_ALL == checkout_stage) { + for (i = 1; i < 4; i++) { + if (i > 1) + putchar(' '); + if (topath[i][0]) + fputs(topath[i], stdout); + else + putchar('.'); + } + } else + fputs(topath[checkout_stage], stdout); + + putchar('\t'); + write_name_quoted("", 0, name + prefix_length, + line_termination, stdout); + putchar(line_termination); + + for (i = 0; i < 4; i++) { + topath[i][0] = 0; + } +} + static int checkout_file(const char *name) { int namelen = strlen(name); int pos = cache_name_pos(name, namelen); int has_same_name = 0; + int did_checkout = 0; + int errs = 0; if (pos < 0) pos = -pos - 1; @@ -62,9 +100,20 @@ static int checkout_file(const char *name) memcmp(ce->name, name, namelen)) break; has_same_name = 1; - if (checkout_stage == ce_stage(ce)) - return checkout_entry(ce, &state); pos++; + if (ce_stage(ce) != checkout_stage + && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) + continue; + did_checkout = 1; + if (checkout_entry(ce, &state, + to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) + errs++; + } + + if (did_checkout) { + if (to_tempfile) + write_tempfile_record(name); + return errs > 0 ? -1 : 0; } if (!state.quiet) { @@ -84,18 +133,29 @@ static int checkout_file(const char *name) static int checkout_all(void) { int i, errs = 0; + struct cache_entry* last_ce = NULL; for (i = 0; i < active_nr ; i++) { struct cache_entry *ce = active_cache[i]; - if (ce_stage(ce) != checkout_stage) + if (ce_stage(ce) != checkout_stage + && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) continue; if (prefix && *prefix && (ce_namelen(ce) <= prefix_length || memcmp(prefix, ce->name, prefix_length))) continue; - if (checkout_entry(ce, &state) < 0) + if (last_ce && to_tempfile) { + if (ce_namelen(last_ce) != ce_namelen(ce) + || memcmp(last_ce->name, ce->name, ce_namelen(ce))) + write_tempfile_record(last_ce->name); + } + if (checkout_entry(ce, &state, + to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) errs++; + last_ce = ce; } + if (last_ce && to_tempfile) + write_tempfile_record(last_ce->name); if (errs) /* we have already done our error reporting. * exit with the same code as die(). @@ -105,7 +165,7 @@ static int checkout_all(void) } static const char checkout_cache_usage[] = -"git-checkout-index [-u] [-q] [-a] [-f] [-n] [--stage=[123]] [--prefix=<string>] [--] <file>..."; +"git-checkout-index [-u] [-q] [-a] [-f] [-n] [--stage=[123]|all] [--prefix=<string>] [--temp] [--] <file>..."; static struct cache_file cache_file; @@ -114,8 +174,10 @@ int main(int argc, char **argv) int i; int newfd = -1; int all = 0; + int read_from_stdin = 0; prefix = setup_git_directory(); + git_config(git_default_config); prefix_length = prefix ? strlen(prefix) : 0; if (read_cache() < 0) { @@ -155,17 +217,37 @@ int main(int argc, char **argv) die("cannot open index.lock file."); continue; } + if (!strcmp(arg, "-z")) { + line_termination = 0; + continue; + } + if (!strcmp(arg, "--stdin")) { + if (i != argc - 1) + die("--stdin must be at the end"); + read_from_stdin = 1; + i++; /* do not consider arg as a file name */ + break; + } + if (!strcmp(arg, "--temp")) { + to_tempfile = 1; + continue; + } if (!strncmp(arg, "--prefix=", 9)) { state.base_dir = arg+9; state.base_dir_len = strlen(state.base_dir); continue; } if (!strncmp(arg, "--stage=", 8)) { - int ch = arg[8]; - if ('1' <= ch && ch <= '3') - checkout_stage = arg[8] - '0'; - else - die("stage should be between 1 and 3"); + if (!strcmp(arg + 8, "all")) { + to_tempfile = 1; + checkout_stage = CHECKOUT_ALL; + } else { + int ch = arg[8]; + if ('1' <= ch && ch <= '3') + checkout_stage = arg[8] - '0'; + else + die("stage should be between 1 and 3 or all"); + } continue; } if (arg[0] == '-') @@ -173,7 +255,7 @@ int main(int argc, char **argv) break; } - if (state.base_dir_len) { + if (state.base_dir_len || to_tempfile) { /* when --prefix is specified we do not * want to update cache. */ @@ -190,9 +272,31 @@ int main(int argc, char **argv) if (all) die("git-checkout-index: don't mix '--all' and explicit filenames"); + if (read_from_stdin) + die("git-checkout-index: don't mix '--stdin' and explicit filenames"); checkout_file(prefix_path(prefix, prefix_length, arg)); } + if (read_from_stdin) { + struct strbuf buf; + if (all) + die("git-checkout-index: don't mix '--all' and '--stdin'"); + strbuf_init(&buf); + while (1) { + char *path_name; + read_line(&buf, stdin, line_termination); + if (buf.eof) + break; + if (line_termination && buf.buf[0] == '"') + path_name = unquote_c_style(buf.buf, NULL); + else + path_name = buf.buf; + checkout_file(prefix_path(prefix, prefix_length, path_name)); + if (path_name != buf.buf) + free(path_name); + } + } + if (all) checkout_all(); diff --git a/combine-diff.c b/combine-diff.c index a23894d..7693884 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -1,5 +1,6 @@ #include "cache.h" #include "commit.h" +#include "blob.h" #include "diff.h" #include "diffcore.h" #include "quote.h" @@ -104,7 +105,7 @@ static char *grab_blob(const unsigned char *sha1, unsigned long *size) return xcalloc(1, 1); } blob = read_sha1_file(sha1, type, size); - if (strcmp(type, "blob")) + if (strcmp(type, blob_type)) die("object '%s' is not a blob!", sha1_to_hex(sha1)); return blob; } @@ -649,7 +650,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent, int len = st.st_size; int cnt = 0; - elem->mode = DIFF_FILE_CANON_MODE(st.st_mode); + elem->mode = canon_mode(st.st_mode); size = len; result = xmalloc(len + 1); while (cnt < len) { diff --git a/commit-tree.c b/commit-tree.c index 88871b0..2d86518 100644 --- a/commit-tree.c +++ b/commit-tree.c @@ -4,6 +4,8 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "commit.h" +#include "tree.h" #define BLOCKING (1ul << 14) @@ -93,13 +95,13 @@ int main(int argc, char **argv) if (argc < 2 || get_sha1_hex(argv[1], tree_sha1) < 0) usage(commit_tree_usage); - check_valid(tree_sha1, "tree"); + check_valid(tree_sha1, tree_type); for (i = 2; i < argc; i += 2) { char *a, *b; a = argv[i]; b = argv[i+1]; if (!b || strcmp(a, "-p") || get_sha1(b, parent_sha1[parents])) usage(commit_tree_usage); - check_valid(parent_sha1[parents], "commit"); + check_valid(parent_sha1[parents], commit_type); if (new_parent(parents)) parents++; } @@ -125,7 +127,10 @@ int main(int argc, char **argv) while (fgets(comment, sizeof(comment), stdin) != NULL) add_buffer(&buffer, &size, "%s", comment); - write_sha1_file(buffer, size, "commit", commit_sha1); - printf("%s\n", sha1_to_hex(commit_sha1)); - return 0; + if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) { + printf("%s\n", sha1_to_hex(commit_sha1)); + return 0; + } + else + return 1; } @@ -73,8 +73,7 @@ struct commit *lookup_commit(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - struct commit *ret = xmalloc(sizeof(struct commit)); - memset(ret, 0, sizeof(struct commit)); + struct commit *ret = xcalloc(1, sizeof(struct commit)); created_object(sha1, &ret->object); ret->object.type = commit_type; return ret; @@ -569,10 +568,28 @@ int count_parents(struct commit * commit) return count; } +void topo_sort_default_setter(struct commit *c, void *data) +{ + c->object.util = data; +} + +void *topo_sort_default_getter(struct commit *c) +{ + return c->object.util; +} + /* * 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) +{ + sort_in_topological_order_fn(list, lifo, topo_sort_default_setter, + topo_sort_default_getter); +} + +void sort_in_topological_order_fn(struct commit_list ** list, int lifo, + topo_sort_set_fn_t setter, + topo_sort_get_fn_t getter) { struct commit_list * next = *list; struct commit_list * work = NULL, **insert; @@ -596,7 +613,7 @@ void sort_in_topological_order(struct commit_list ** list) next=*list; while (next) { next_nodes->list_item = next; - next->item->object.util = next_nodes; + setter(next->item, next_nodes); next_nodes++; next = next->next; } @@ -606,8 +623,8 @@ void sort_in_topological_order(struct commit_list ** list) struct commit_list * parents = next->item->parents; while (parents) { struct commit * parent=parents->item; - struct sort_node * pn = (struct sort_node *)parent->object.util; - + struct sort_node * pn = (struct sort_node *) getter(parent); + if (pn) pn->indegree++; parents=parents->next; @@ -624,32 +641,39 @@ void sort_in_topological_order(struct commit_list ** list) next=*list; insert = &work; while (next) { - struct sort_node * node = (struct sort_node *)next->item->object.util; + struct sort_node * node = (struct sort_node *) getter(next->item); if (node->indegree == 0) { insert = &commit_list_insert(next->item, insert)->next; } 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; + struct sort_node * work_node = (struct sort_node *) getter(work_item); struct commit_list * parents = work_item->parents; while (parents) { struct commit * parent=parents->item; - struct sort_node * pn = (struct sort_node *)parent->object.util; - + struct sort_node * pn = (struct sort_node *) getter(parent); + if (pn) { - /* + /* * parents are only enqueued for emission * when all their children have been emitted thereby * 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; } @@ -660,7 +684,7 @@ void sort_in_topological_order(struct commit_list ** list) *pptr = work_node->list_item; pptr = &(*pptr)->next; *pptr = NULL; - work_item->object.util = NULL; + setter(work_item, NULL); } free(nodes); } @@ -65,13 +65,29 @@ int count_parents(struct commit * commit); /* * Performs an in-place topological sort of list supplied. * - * Pre-conditions: + * Pre-conditions for sort_in_topological_order: * all commits in input list and all parents of those * commits must have object.util == NULL - * - * Post-conditions: + * + * Pre-conditions for sort_in_topological_order_fn: + * all commits in input list and all parents of those + * commits must have getter(commit) == NULL + * + * 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); + +typedef void (*topo_sort_set_fn_t)(struct commit*, void *data); +typedef void* (*topo_sort_get_fn_t)(struct commit*); + +void topo_sort_default_setter(struct commit *c, void *data); +void *topo_sort_default_getter(struct commit *c); + +void sort_in_topological_order(struct commit_list ** list, int lifo); +void sort_in_topological_order_fn(struct commit_list ** list, int lifo, + topo_sort_set_fn_t setter, + topo_sort_get_fn_t getter); #endif /* COMMIT_H */ @@ -222,11 +222,21 @@ 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; } + if (!strcmp(var, "core.warnambiguousrefs")) { + warn_ambiguous_refs = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "user.name")) { strncpy(git_default_name, value, sizeof(git_default_name)); return 0; diff --git a/contrib/README b/contrib/README new file mode 100644 index 0000000..e1c0a01 --- /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/.gitignore b/contrib/emacs/.gitignore new file mode 100644 index 0000000..c531d98 --- /dev/null +++ b/contrib/emacs/.gitignore @@ -0,0 +1 @@ +*.elc diff --git a/contrib/emacs/Makefile b/contrib/emacs/Makefile new file mode 100644 index 0000000..d3619db --- /dev/null +++ b/contrib/emacs/Makefile @@ -0,0 +1,20 @@ +## Build and install stuff + +EMACS = emacs + +ELC = git.elc vc-git.elc +INSTALL = install +INSTALL_ELC = $(INSTALL) -m 644 +prefix = $(HOME) +emacsdir = $(prefix)/share/emacs/site-lisp + +all: $(ELC) + +install: all + $(INSTALL) -d $(emacsdir) + $(INSTALL_ELC) $(ELC) $(emacsdir) + +%.elc: %.el + $(EMACS) --batch --eval '(byte-compile-file "$<")' + +clean:; rm -f $(ELC) diff --git a/contrib/emacs/git.el b/contrib/emacs/git.el new file mode 100644 index 0000000..ebd00ef --- /dev/null +++ b/contrib/emacs/git.el @@ -0,0 +1,1012 @@ +;;; 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 +;; - creating tags +;; - fetch/pull +;; - switching branches +;; - revlist browser +;; - git-show-branch browser +;; - menus +;; + +(eval-when-compile (require 'cl)) +(require 'ewoc) + + +;;;; Customizations +;;;; ------------------------------------------------------------ + +(defgroup git nil + "Git user interface") + +(defcustom git-committer-name nil + "User name to use for commits. +The default is to fall back to the repository config, then to `add-log-full-name' and then to `user-full-name'." + :group 'git + :type '(choice (const :tag "Default" nil) + (string :tag "Name"))) + +(defcustom git-committer-email nil + "Email address to use for commits. +The default is to fall back to the git repository config, then to `add-log-mailing-address' and then to `user-mail-address'." + :group 'git + :type '(choice (const :tag "Default" nil) + (string :tag "Email"))) + +(defcustom git-commits-coding-system 'utf-8 + "Default coding system for the log message of git commits." + :group 'git + :type 'coding-system) + +(defcustom git-append-signed-off-by nil + "Whether to append a Signed-off-by line to the commit message before editing." + :group 'git + :type 'boolean) + +(defcustom git-per-dir-ignore-file ".gitignore" + "Name of the per-directory ignore file." + :group 'git + :type 'string) + +(defface git-status-face + '((((class color) (background light)) (:foreground "purple"))) + "Git mode face used to highlight added and modified files." + :group 'git) + +(defface git-unmerged-face + '((((class color) (background light)) (:foreground "red" :bold t))) + "Git mode face used to highlight unmerged files." + :group 'git) + +(defface git-unknown-face + '((((class color) (background light)) (:foreground "goldenrod" :bold t))) + "Git mode face used to highlight unknown files." + :group 'git) + +(defface git-uptodate-face + '((((class color) (background light)) (:foreground "grey60"))) + "Git mode face used to highlight up-to-date files." + :group 'git) + +(defface git-ignored-face + '((((class color) (background light)) (:foreground "grey60"))) + "Git mode face used to highlight ignored files." + :group 'git) + +(defface git-mark-face + '((((class color) (background light)) (:foreground "red" :bold t))) + "Git mode face used for the file marks." + :group 'git) + +(defface git-header-face + '((((class color) (background light)) (:foreground "blue"))) + "Git mode face used for commit headers." + :group 'git) + +(defface git-separator-face + '((((class color) (background light)) (:foreground "brown"))) + "Git mode face used for commit separator." + :group 'git) + +(defface git-permission-face + '((((class color) (background light)) (:foreground "green" :bold t))) + "Git mode face used for permission changes." + :group 'git) + + +;;;; Utilities +;;;; ------------------------------------------------------------ + +(defconst git-log-msg-separator "--- log message follows this line ---") + +(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-call-process-env-string (env &rest args) + "Wrapper for call-process that sets environment strings, and returns the process output as a string." + (with-temp-buffer + (and (eq 0 (apply #' git-call-process-env t env args)) + (buffer-string)))) + +(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." + (and string + (string-match "[0-9a-f]\\{40\\}" string) + (match-string 0 string))) + +(defun git-get-committer-name () + "Return the name to use as GIT_COMMITTER_NAME." + ; copied from log-edit + (or git-committer-name + (git-repo-config "user.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 + (git-repo-config "user.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)) + (ignore-name (expand-file-name git-per-dir-ignore-file dir)) + (created (not (file-exists-p ignore-name)))) + (save-window-excursion + (set-buffer (find-file-noselect ignore-name)) + (goto-char (point-max)) + (unless (zerop (current-column)) (insert "\n")) + (insert name "\n") + (sort-lines nil (point-min) (point-max)) + (save-buffer)) + (when created + (git-run-command nil nil "update-index" "--info-only" "--add" "--" (file-relative-name ignore-name))) + (git-add-status-file (if created 'added 'modified) (file-relative-name ignore-name)))) + + +;;;; Wrappers for basic git commands +;;;; ------------------------------------------------------------ + +(defun git-rev-parse (rev) + "Parse a revision name and return its SHA1." + (git-get-string-sha1 + (git-call-process-env-string nil "rev-parse" rev))) + +(defun git-repo-config (key) + "Retrieve the value associated to KEY in the git repository config file." + (let ((str (git-call-process-env-string nil "repo-config" key))) + (and str (car (split-string str "\n"))))) + +(defun git-symbolic-ref (ref) + "Wrapper for the git-symbolic-ref command." + (let ((str (git-call-process-env-string nil "symbolic-ref" ref))) + (and str (car (split-string str "\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 + (git-call-process-env-string (and index-file `(("GIT_INDEX_FILE" . ,index-file))) "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 "^" (regexp-quote 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 ?\111 (logxor old-perm new-perm)))) + " " + (if (eq 0 (logand ?\111 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-file-merge-head (arg) + "Diff the marked file(s) against the first merge head (or the nth one with a numeric prefix)." + (interactive "p") + (let ((files (git-marked-files)) + (merge-heads (git-get-merge-heads))) + (unless merge-heads (error "No merge in progress")) + (git-setup-diff-buffer + (apply #'git-run-command-buffer "*git-diff*" "diff-index" "-p" "-M" + (or (nth (1- arg) merge-heads) "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) + (sign-off git-append-signed-off-by)) + (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") + (cond ((and merge-heads (file-readable-p ".git/MERGE_MSG")) + (insert-file-contents ".git/MERGE_MSG")) + (sign-off + (insert (format "\n\nSigned-off-by: %s <%s>\n" + (git-get-committer-name) (git-get-committer-email))))))) + (let ((log-edit-font-lock-keywords + `(("^\\(Author:\\|Date:\\|Parent:\\|Signed-off-by:\\)\\(.*\\)" + (1 font-lock-keyword-face) + (2 font-lock-function-name-face)) + (,(concat "^\\(" (regexp-quote git-log-msg-separator) "\\)$") + (1 font-lock-comment-face))))) + (log-edit #'git-do-commit nil #'git-log-edit-files buffer)))) + +(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 "\r" '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 "h" 'git-diff-file-merge-head) + (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)) + (set (make-local-variable 'list-buffers-directory) default-directory) + (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) + (cd dir) + (git-status-mode) + (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/emacs/vc-git.el b/contrib/emacs/vc-git.el new file mode 100644 index 0000000..2453cdc --- /dev/null +++ b/contrib/emacs/vc-git.el @@ -0,0 +1,135 @@ +;;; vc-git.el --- VC backend for the git version control system + +;; Copyright (C) 2006 Alexandre Julliard + +;; 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 a VC backend for the git version control +;; system. +;; +;; To install: put this file on the load-path and add GIT to the list +;; of supported backends in `vc-handled-backends'. +;; +;; TODO +;; - changelog generation +;; - working with revisions other than HEAD +;; + +(defvar git-commits-coding-system 'utf-8 + "Default coding system for git commits.") + +(defun vc-git--run-command-string (file &rest args) + "Run a git command on FILE and return its output as string." + (let* ((ok t) + (str (with-output-to-string + (with-current-buffer standard-output + (unless (eq 0 (apply #'call-process "git" nil '(t nil) nil + (append args (list (file-relative-name file))))) + (setq ok nil)))))) + (and ok str))) + +(defun vc-git--run-command (file &rest args) + "Run a git command on FILE, discarding any output." + (let ((name (file-relative-name file))) + (eq 0 (apply #'call-process "git" nil (get-buffer "*Messages") nil (append args (list name)))))) + +(defun vc-git-registered (file) + "Check whether FILE is registered with git." + (with-temp-buffer + (let* ((dir (file-name-directory file)) + (name (file-relative-name file dir))) + (when dir (cd dir)) + (and (eq 0 (call-process "git" nil '(t nil) nil "ls-files" "-c" "-z" "--" name)) + (let ((str (buffer-string))) + (and (> (length str) (length name)) + (string= (substring str 0 (1+ (length name))) (concat name "\0")))))))) + +(defun vc-git-state (file) + "git-specific version of `vc-state'." + (let ((diff (vc-git--run-command-string file "diff-index" "-z" "HEAD" "--"))) + (if (and diff (string-match ":[0-7]\\{6\\} [0-7]\\{6\\} [0-9a-f]\\{40\\} [0-9a-f]\\{40\\} [ADMU]\0[^\0]+\0" diff)) + 'edited + 'up-to-date))) + +(defun vc-git-workfile-version (file) + "git-specific version of `vc-workfile-version'." + (let ((str (with-output-to-string + (with-current-buffer standard-output + (call-process "git" nil '(t nil) nil "symbolic-ref" "HEAD"))))) + (if (string-match "^\\(refs/heads/\\)?\\(.+\\)$" str) + (match-string 2 str) + str))) + +(defun vc-git-revert (file &optional contents-done) + "Revert FILE to the version stored in the git repository." + (if contents-done + (vc-git--run-command file "update-index" "--") + (vc-git--run-command file "checkout" "HEAD"))) + +(defun vc-git-checkout-model (file) + 'implicit) + +(defun vc-git-workfile-unchanged-p (file) + (let ((sha1 (vc-git--run-command-string file "hash-object" "--")) + (head (vc-git--run-command-string file "ls-tree" "-z" "HEAD" "--"))) + (and head + (string-match "[0-7]\\{6\\} blob \\([0-9a-f]\\{40\\}\\)\t[^\0]+\0" head) + (string= (car (split-string sha1 "\n")) (match-string 1 head))))) + +(defun vc-git-register (file &optional rev comment) + "Register FILE into the git version-control system." + (vc-git--run-command file "update-index" "--add" "--")) + +(defun vc-git-print-log (file) + (let ((name (file-relative-name file)) + (coding-system-for-read git-commits-coding-system)) + (vc-do-command nil 'async "git" name "rev-list" "--pretty" "HEAD" "--"))) + +(defun vc-git-diff (file &optional rev1 rev2) + (let ((name (file-relative-name file))) + (if (and rev1 rev2) + (vc-do-command "*vc-diff*" 0 "git" name "diff-tree" "-p" rev1 rev2 "--") + (vc-do-command "*vc-diff*" 0 "git" name "diff-index" "-p" (or rev1 "HEAD") "--")) + ; git-diff-index doesn't set exit status like diff does + (if (vc-git-workfile-unchanged-p file) 0 1))) + +(defun vc-git-checkin (file rev comment) + (let ((coding-system-for-write git-commits-coding-system)) + (vc-git--run-command file "commit" "-m" comment "--only" "--"))) + +(defun vc-git-checkout (file &optional editable rev destfile) + (vc-git--run-command file "checkout" (or rev "HEAD"))) + +(defun vc-git-annotate-command (file buf &optional rev) + ; FIXME: rev is ignored + (let ((name (file-relative-name file))) + (call-process "git" nil buf nil "annotate" name))) + +(defun vc-git-annotate-time () + (and (re-search-forward "[0-9a-f]+\t(.*\t\\([0-9]+\\)-\\([0-9]+\\)-\\([0-9]+\\) \\([0-9]+\\):\\([0-9]+\\):\\([0-9]+\\) \\([-+0-9]+\\)\t[0-9]+)" nil t) + (vc-annotate-convert-time + (apply #'encode-time (mapcar (lambda (match) (string-to-number (match-string match))) '(6 5 4 3 2 1 7)))))) + +;; Not really useful since we can't do anything with the revision yet +;;(defun vc-annotate-extract-revision-at-line () +;; (save-excursion +;; (move-beginning-of-line 1) +;; (and (looking-at "[0-9a-f]+") +;; (buffer-substring (match-beginning 0) (match-end 0))))) + +(provide 'vc-git) diff --git a/contrib/git-svn/.gitignore b/contrib/git-svn/.gitignore new file mode 100644 index 0000000..d8d87e3 --- /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 0000000..acedf73 --- /dev/null +++ b/contrib/git-svn/Makefile @@ -0,0 +1,35 @@ +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 $< +git-svn.html : git-svn.txt + asciidoc -b xhtml11 -d manpage \ + -f ../../Documentation/asciidoc.conf $< +test: git-svn + 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 0000000..7c44450 --- /dev/null +++ b/contrib/git-svn/git-svn.perl @@ -0,0 +1,1180 @@ +#!/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 $SVN_UUID + $GIT_SVN_INDEX $GIT_SVN + $GIT_DIR $REV_DIR/; +$AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; +$VERSION = '0.11.0'; + +use Cwd qw/abs_path/; +$GIT_DIR = abs_path($ENV{GIT_DIR} || '.git'); +$ENV{GIT_DIR} = $GIT_DIR; + +# 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 +# We don't use any modules not in the standard Perl distribution: +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]{4,40}/; +my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, + $_find_copies_harder, $_l, $_version, $_upgrade, $_authors); +my (@_branch_from, %tree_map, %users); +my $_svn_co_url_revs; + +my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, + 'branch|b=s' => \@_branch_from, + 'authors-file|A=s' => \$_authors ); +my %cmd = ( + fetch => [ \&fetch, "Download new revisions from SVN", + { 'revision|r=s' => \$_revision, %fc_opts } ], + init => [ \&init, "Initialize and fetch (import)", { } ], + commit => [ \&commit, "Commit git revisions to SVN", + { 'stdin|' => \$_stdin, + 'edit|e' => \$_edit, + 'rmdir' => \$_rmdir, + 'find-copies-harder' => \$_find_copies_harder, + 'l=i' => \$_l, + %fc_opts, + } ], + 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", { } ], + rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)", + { 'no-ignore-externals' => \$_no_ignore_ext, + 'upgrade' => \$_upgrade } ], +); +my $cmd; +for (my $i = 0; $i < @ARGV; $i++) { + if (defined $cmd{$ARGV[$i]}) { + $cmd = $ARGV[$i]; + splice @ARGV, $i, 1; + last; + } +}; + +my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd); + +# convert GetOpt::Long specs for use by git-repo-config +foreach my $o (keys %opts) { + my $v = $opts{$o}; + my ($key) = ($o =~ /^([a-z\-]+)/); + $key =~ s/-//g; + my $arg = 'git-repo-config'; + $arg .= ' --int' if ($o =~ /=i$/); + $arg .= ' --bool' if ($o !~ /=[sfi]$/); + if (ref $v eq 'ARRAY') { + chomp(my @tmp = `$arg --get-all svn.$key`); + @$v = @tmp if @tmp; + } else { + chomp(my $tmp = `$arg --get svn.$key`); + if ($tmp && !($arg =~ / --bool / && $tmp eq 'false')) { + $$v = $tmp; + } + } +} + +GetOptions(%opts, 'help|H|h' => \$_help, + 'version|V' => \$_version, + 'id|i=s' => \$GIT_SVN) or exit 1; + +$GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; +$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index"; +$SVN_URL = undef; +$REV_DIR = "$GIT_DIR/$GIT_SVN/revs"; +$SVN_WC = "$GIT_DIR/$GIT_SVN/tree"; + +usage(0) if $_help; +version() if $_version; +usage(1) unless defined $cmd; +load_authors() if $_authors; +svn_compat_check(); +$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 + + print $fd "Available commands:\n" unless $cmd; + + foreach (sort keys %cmd) { + next if $cmd && $cmd ne $_; + print $fd ' ',pack('A13',$_),$cmd{$_}->[1],"\n"; + foreach (keys %{$cmd{$_}->[2]}) { + # prints out arguments as they should be passed: + my $x = s#=s$## ? '<arg>' : s#=i$## ? '<num>' : ''; + print $fd ' ' x 17, join(', ', map { length $_ > 1 ? + "--$_" : "-$_" } + split /\|/,$_)," $x\n"; + } + } + print $fd <<""; +\nGIT_SVN_ID may be set in the environment or via the --id/-i switch to an +arbitrary identifier if you're tracking multiple SVN branches/repositories in +one git repository and want to keep them separate. See git-svn(1) for more +information. + + exit $exit; +} + +sub version { + print "git-svn version $VERSION\n"; + exit 0; +} + +sub rebuild { + $SVN_URL = shift or undef; + my $newest_rev = 0; + if ($_upgrade) { + sys('git-update-ref',"refs/remotes/$GIT_SVN","$GIT_SVN-HEAD"); + } else { + check_upgrade_needed(); + } + + my $pid = open(my $rev_list,'-|'); + defined $pid or croak $!; + if ($pid == 0) { + exec("git-rev-list","refs/remotes/$GIT_SVN") or croak $!; + } + my $latest; + while (<$rev_list>) { + chomp; + my $c = $_; + croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o; + my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`); + 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"; + } + } + + # if we merged or otherwise started elsewhere, this is + # how we break out of it + next if (defined $SVN_UUID && ($uuid ne $SVN_UUID)); + next if (defined $SVN_URL && defined $url && ($url ne $SVN_URL)); + + print "r$rev = $c\n"; + unless (defined $latest) { + if (!$SVN_URL && !$url) { + croak "SVN repository location required: $url\n"; + } + $SVN_URL ||= $url; + $SVN_UUID ||= $uuid; + setup_git_svn(); + $latest = $rev; + } + assert_revision_eq_or_unknown($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 $SVN_WC) { + svn_cmd_checkout($SVN_URL, $latest, $SVN_WC); + chdir $SVN_WC or croak $!; + } + + $pid = fork; + defined $pid or croak $!; + if ($pid == 0) { + my @svn_up = qw(svn up); + push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + sys(@svn_up,"-r$newest_rev"); + $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; + git_addremove(); + exec('git-write-tree'); + } + waitpid $pid, 0; + + if ($_upgrade) { + print STDERR <<""; +Keeping deprecated refs/head/$GIT_SVN-HEAD for now. Please remove it +when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN + + } +} + +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) = @_; + check_upgrade_needed(); + $SVN_URL ||= file_to_s("$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); + + my $base = next_log_entry($svn_log) or croak "No base revision!\n"; + my $last_commit = undef; + unless (-d $SVN_WC) { + svn_cmd_checkout($SVN_URL,$base->{revision},$SVN_WC); + chdir $SVN_WC or croak $!; + read_uuid(); + $last_commit = git_commit($base, @parents); + assert_svn_wc_clean($base->{revision}, $last_commit); + } else { + chdir $SVN_WC or croak $!; + read_uuid(); + $last_commit = file_to_s("$REV_DIR/$base->{revision}"); + } + my @svn_up = qw(svn up); + push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + my $last = $base; + while (my $log_msg = next_log_entry($svn_log)) { + assert_svn_wc_clean($last->{revision}, $last_commit); + if ($last->{revision} >= $log_msg->{revision}) { + croak "Out of order: last >= current: ", + "$last->{revision} >= $log_msg->{revision}\n"; + } + sys(@svn_up,"-r$log_msg->{revision}"); + $last_commit = git_commit($log_msg, $last_commit, @parents); + $last = $log_msg; + } + assert_svn_wc_clean($last->{revision}, $last_commit); + unless (-e "$GIT_DIR/refs/heads/master") { + sys(qw(git-update-ref refs/heads/master),$last_commit); + } + return $last; +} + +sub commit { + my (@commits) = @_; + check_upgrade_needed(); + if ($_stdin || !@commits) { + print "Reading from stdin...\n"; + @commits = (); + while (<STDIN>) { + if (/\b($sha1_short)\b/o) { + 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 $info = svn_info('.'); + read_uuid($info); + my $svn_current_rev = $info->{'Last Changed Rev'}; + foreach my $c (@revs) { + 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 read_uuid { + return if $SVN_UUID; + my $info = shift || svn_info('.'); + $SVN_UUID = $info->{'Repository UUID'} or + croak "Repository UUID unreadable\n"; + s_to_file($SVN_UUID,"$GIT_DIR/$GIT_SVN/info/uuid"); +} + +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"); + + open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!; + print $fd '.svn',"\n"; + close $fd or croak $!; +} + +sub assert_svn_wc_clean { + my ($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 $lcr = svn_info('.')->{'Last Changed Rev'}; + if ($svn_rev != $lcr) { + print STDERR "Checking for copy-tree ... "; + # use + my @diff = grep(/^Index: /,(safe_qx(qw(svn diff), + "-r$lcr:$svn_rev"))); + if (@diff) { + croak "Nope! Expected r$svn_rev, got r$lcr\n"; + } else { + print STDERR "OK!\n"; + } + } + my @status = grep(!/^Performing status on external/,(`svn status`)); + @status = grep(!/^\s*$/,@status); + if (scalar @status) { + print STDERR "Tree ($SVN_WC) is not clean:\n"; + print STDERR $_ foreach @status; + croak; + } + assert_tree($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, but 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) { + $in_msg = 1 if (/^\s*$/); + } elsif (/^git-svn-id: /) { + # skip this, we regenerate the correct one + # on re-fetch anyways + } else { + 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); + } + + # file_to_s removes all trailing newlines, so just use chomp() here: + open $msg, '<', $commit_msg or croak $!; + { local $/; chomp($log_msg{msg} = <$msg>); } + close $msg or croak $!; + + my ($oneline) = ($log_msg{msg} =~ /([^\n\r]+)/); + print "Committing $commit: $oneline\n"; + + my @ci_output = safe_qx(qw(svn commit -F),$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}; +} + +# read the entire log into a temporary file (which is removed ASAP) +# and store the file handle + parser state +sub svn_log_raw { + my (@log_args) = @_; + my $log_fh = IO::File->new_tmpfile or croak $!; + my $pid = fork; + defined $pid or croak $!; + if (!$pid) { + open STDOUT, '>&', $log_fh or croak $!; + exec (qw(svn log), @log_args) or croak $! + } + waitpid $pid, 0; + croak if $?; + seek $log_fh, 0, 0 or croak $!; + return { state => 'sep', fh => $log_fh }; +} + +sub next_log_entry { + my $log = shift; # retval of svn_log_raw() + my $ret = undef; + my $fh = $log->{fh}; + + while (<$fh>) { + chomp; + if (/^\-{72}$/) { + if ($log->{state} eq 'msg') { + if ($ret->{lines}) { + $ret->{msg} .= $_."\n"; + unless(--$ret->{lines}) { + $log->{state} = 'sep'; + } + } else { + croak "Log parse error at: $_\n", + $ret->{revision}, + "\n"; + } + next; + } + if ($log->{state} ne 'sep') { + croak "Log parse error at: $_\n", + "state: $log->{state}\n", + $ret->{revision}, + "\n"; + } + $log->{state} = 'rev'; + + # if we have an empty log message, put something there: + if ($ret) { + $ret->{msg} ||= "\n"; + delete $ret->{lines}; + return $ret; + } + next; + } + if ($log->{state} eq 'rev' && s/^r(\d+)\s*\|\s*//) { + my $rev = $1; + my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3); + ($lines) = ($lines =~ /(\d+)/); + my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ + /(\d{4})\-(\d\d)\-(\d\d)\s + (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) + or croak "Failed to parse date: $date\n"; + $ret = { revision => $rev, + date => "$tz $Y-$m-$d $H:$M:$S", + author => $author, + lines => $lines, + msg => '' }; + if (defined $_authors && ! defined $users{$author}) { + die "Author: $author not defined in ", + "$_authors file\n"; + } + $log->{state} = 'msg_start'; + next; + } + # skip the first blank line of the message: + if ($log->{state} eq 'msg_start' && /^$/) { + $log->{state} = 'msg'; + } elsif ($log->{state} eq 'msg') { + if ($ret->{lines}) { + $ret->{msg} .= $_."\n"; + unless (--$ret->{lines}) { + $log->{state} = 'sep'; + } + } else { + croak "Log parse error at: $_\n", + $ret->{revision},"\n"; + } + } + } + return $ret; +} + +sub svn_info { + my $url = shift || $SVN_URL; + + my $pid = open my $info_fh, '-|'; + defined $pid or croak $!; + + if ($pid == 0) { + exec(qw(svn info),$url) or croak $!; + } + + my $ret = {}; + # only single-lines seem to exist in svn info output + while (<$info_fh>) { + chomp $_; + if (m#^([^:]+)\s*:\s*(\S.*)$#) { + $ret->{$1} = $2; + push @{$ret->{-order}}, $1; + } + } + close $info_fh or croak $!; + return $ret; +} + +sub sys { system(@_) == 0 or croak $? } + +sub git_addremove { + system( "git-diff-files --name-only -z ". + " | git-update-index --remove -z --stdin && ". + "git-ls-files -z --others ". + "'--exclude-from=$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/$revno already exists! ", + "Why are we refetching it?"; + } +} + +sub trees_eq { + my ($x, $y) = @_; + my @x = safe_qx('git-cat-file','commit',$x); + my @y = safe_qx('git-cat-file','commit',$y); + if (($y[0] ne $x[0]) || $x[0] !~ /^tree $sha1\n$/ + || $y[0] !~ /^tree $sha1\n$/) { + print STDERR "Trees not equal: $y[0] != $x[0]\n"; + return 0 + } + return 1; +} + +sub assert_revision_eq_or_unknown { + my ($revno, $commit) = @_; + if (-f "$REV_DIR/$revno") { + my $current = file_to_s("$REV_DIR/$revno"); + if (($commit ne $current) && !trees_eq($commit, $current)) { + croak "$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 $!; + + map_tree_joins() if (@_branch_from && !%tree_map); + + # 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 $?; + if (exists $tree_map{$tree}) { + my %seen_parent = map { $_ => 1 } @exec_parents; + foreach (@{$tree_map{$tree}}) { + # MAXPARENT is defined to 16 in commit-tree.c: + if ($seen_parent{$_} || @exec_parents > 16) { + next; + } + push @exec_parents, $_; + $seen_parent{$_} = 1; + } + } + my $msg_fh = IO::File->new_tmpfile or croak $!; + print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ", + "$SVN_URL\@$log_msg->{revision}", + " $SVN_UUID\n" or croak $!; + $msg_fh->flush == 0 or croak $!; + seek $msg_fh, 0, 0 or croak $!; + + set_commit_env($log_msg); + + 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: $commit\n"; + } + my @update_ref = ('git-update-ref',"refs/remotes/$GIT_SVN",$commit); + if (my $primary_parent = shift @exec_parents) { + $pid = fork; + defined $pid or croak $!; + if (!$pid) { + close STDERR; + close STDOUT; + exec 'git-rev-parse','--verify', + "refs/remotes/$GIT_SVN^0"; + } + waitpid $pid, 0; + push @update_ref, $primary_parent unless $?; + } + sys(@update_ref); + sys('git-update-ref',"$GIT_SVN/revs/$log_msg->{revision}",$commit); + print "r$log_msg->{revision} = $commit\n"; + return $commit; +} + +sub set_commit_env { + my ($log_msg) = @_; + my $author = $log_msg->{author}; + my ($name,$email) = defined $users{$author} ? @{$users{$author}} + : ($author,"$author\@$SVN_UUID"); + $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name; + $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = $email; + $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_msg->{date}; +} + +sub apply_mod_line_blob { + my $m = shift; + if ($m->{mode_b} =~ /^120/) { + blob_to_symlink($m->{sha1_b}, $m->{file_b}); + } else { + blob_to_file($m->{sha1_b}, $m->{file_b}); + } +} + +sub blob_to_symlink { + my ($blob, $link) = @_; + defined $link or croak "\$link not defined!\n"; + croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; + if (-l $link || -f _) { + unlink $link or croak $!; + } + + my $dest = `git-cat-file blob $blob`; # no newline, so no chomp + symlink $dest, $link or croak $!; +} + +sub blob_to_file { + my ($blob, $file) = @_; + defined $file or croak "\$file not defined!\n"; + croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; + if (-l $file || -f _) { + unlink $file or croak $!; + } + + open my $blob_fh, '>', $file or croak "$!: $file\n"; + my $pid = fork; + defined $pid or croak $!; + + if ($pid == 0) { + open STDOUT, '>&', $blob_fh or croak $!; + exec('git-cat-file','blob',$blob); + } + waitpid $pid, 0; + croak $? if $?; + + close $blob_fh or croak $!; +} + +sub safe_qx { + my $pid = open my $child, '-|'; + defined $pid or croak $!; + if ($pid == 0) { + exec(@_) or croak $?; + } + my @ret = (<$child>); + close $child or croak $?; + die $? if $?; # just in case close didn't error out + return wantarray ? @ret : join('',@ret); +} + +sub svn_compat_check { + my @co_help = safe_qx(qw(svn co -h)); + unless (grep /ignore-externals/,@co_help) { + print STDERR "W: Installed svn version does not support ", + "--ignore-externals\n"; + $_no_ignore_ext = 1; + } + if (grep /usage: checkout URL\[\@REV\]/,@co_help) { + $_svn_co_url_revs = 1; + } + + # I really, really hope nobody hits this... + unless (grep /stop-on-copy/, (safe_qx(qw(svn log -h)))) { + print STDERR <<''; +W: The installed svn version does not support the --stop-on-copy flag in + the log command. + Lets hope the directory you're tracking is not a branch or tag + and was never moved within the repository... + + $_no_stop_copy = 1; + } +} + +# *sigh*, new versions of svn won't honor -r<rev> without URL@<rev>, +# (and they won't honor URL@<rev> without -r<rev>, too!) +sub svn_cmd_checkout { + my ($url, $rev, $dir) = @_; + my @cmd = ('svn','co', "-r$rev"); + push @cmd, '--ignore-externals' unless $_no_ignore_ext; + $url .= "\@$rev" if $_svn_co_url_revs; + sys(@cmd, $url, $dir); +} + +sub check_upgrade_needed { + my $old = eval { + my $pid = open my $child, '-|'; + defined $pid or croak $!; + if ($pid == 0) { + close STDERR; + exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $?; + } + my @ret = (<$child>); + close $child or croak $?; + die $? if $?; # just in case close didn't error out + return wantarray ? @ret : join('',@ret); + }; + return unless $old; + my $head = eval { safe_qx('git-rev-parse',"refs/remotes/$GIT_SVN") }; + if ($@ || !$head) { + print STDERR "Please run: $0 rebuild --upgrade\n"; + exit 1; + } +} + +# fills %tree_map with a reverse mapping of trees to commits. Useful +# for finding parents to commit on. +sub map_tree_joins { + foreach my $br (@_branch_from) { + my $pid = open my $pipe, '-|'; + defined $pid or croak $!; + if ($pid == 0) { + exec(qw(git-rev-list --pretty=raw), $br) or croak $?; + } + while (<$pipe>) { + if (/^commit ($sha1)$/o) { + my $commit = $1; + my ($tree) = (<$pipe> =~ /^tree ($sha1)$/o); + unless (defined $tree) { + die "Failed to parse commit $commit\n"; + } + push @{$tree_map{$tree}}, $commit; + } + } + close $pipe or croak $?; + } +} + +# '<svn username> = real-name <email address>' mapping based on git-svnimport: +sub load_authors { + open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; + while (<$authors>) { + chomp; + next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; + my ($user, $name, $email) = ($1, $2, $3); + $users{$user} = [$name, $email]; + } + close $authors or croak $!; +} + +__END__ + +Data structures: + +$svn_log hashref (as returned by svn_log_raw) +{ + fh => file handle of the log file, + state => state of the log file parser (sep/msg/rev/msg_start...) +} + +$log_msg hashref as returned by next_log_entry($svn_log) +{ + 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 [MCRADT], + 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 0000000..e18fcaf --- /dev/null +++ b/contrib/git-svn/git-svn.txt @@ -0,0 +1,296 @@ +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 mostly ignores the very limited view of branching that +Subversion has. This allows git-svn to be much easier to use, +especially on repositories that are not organized in a manner that +git-svnimport is designed for. + +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/remotes/git-svn will be updated to the latest revision. + + Note: You should never attempt to modify the remotes/git-svn branch + outside of git-svn. Instead, create a branch from remotes/git-svn + and work on that branch. Use the 'commit' command (see below) + to write git commits back to remotes/git-svn. + +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. + + repo-config key: svn.rmdir + +-e:: +--edit:: + Only used with the 'commit' command. + + Edit the commit message before committing to SVN. This is off by + default for objects that are commits, and forced on when committing + tree objects. + + repo-config key: svn.edit + +-l<num>:: +--find-copies-harder:: + Both of these are only used with the 'commit' command. + + They are both passed directly to git-diff-tree see + git-diff-tree(1) for more information. + + repo-config key: svn.l + repo-config key: svn.findcopiesharder + +ADVANCED OPTIONS +---------------- +-b<refname>:: +--branch <refname>:: + Used with 'fetch' or 'commit'. + + This can be used to join arbitrary git branches to remotes/git-svn + on new commits where the tree object is equivalent. + + When used with different GIT_SVN_ID values, tags and branches in + SVN can be tracked this way, as can some merges where the heads + end up having completely equivalent content. This can even be + used to track branches across multiple SVN _repositories_. + + This option may be specified multiple times, once for each + branch. + + repo-config key: svn.branch + +-i<GIT_SVN_ID>:: +--id <GIT_SVN_ID>:: + This sets GIT_SVN_ID (instead of using the environment). See + the section on "Tracking Multiple Repositories or Branches" for + more information on using GIT_SVN_ID. + +COMPATIBILITY OPTIONS +--------------------- +--upgrade:: + Only used with the 'rebuild' command. + + Run this if you used an old version of git-svn that used + "git-svn-HEAD" instead of "remotes/git-svn" as the branch + for tracking the remote. + +--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. + + repo-config key: svn.noignoreexternals + +Basic 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 remotes/git-svn +# Commit only the git commits you want to SVN: + git-svn commit <tree-ish> [<tree-ish_2> ...] +# Commit all the git commits from my-branch that don't exist in SVN: + git-svn commit remotes/git-svn..my-branch +# Something is committed to SVN, pull the latest into your branch: + git-svn fetch && git pull . remotes/git-svn +# 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 remotes/$GIT_SVN_ID, instead of +remotes/git-svn. Any remotes/$GIT_SVN_ID branch should never be modified +by the user outside of git-svn commands. + +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=$(git-rev-parse HEAD)` + +Advanced Example: Tracking a Reorganized Repository +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +If you're tracking a directory that has moved, or otherwise been +branched or tagged off of another directory in the repository and you +care about the full history of the project, then you can read this +section. + +This is how Yann Dirson tracked the trunk of the ufoai directory when +the /trunk directory of his repository was moved to /ufoai/trunk and +he needed to continue tracking /ufoai/trunk where /trunk left off. + +------------------------------------------------------------------------ + # This log message shows when the repository was reorganized: + r166 | ydirson | 2006-03-02 01:36:55 +0100 (Thu, 02 Mar 2006) | 1 line + Changed paths: + D /trunk + A /ufoai/trunk (from /trunk:165) + + # First we start tracking the old revisions: + GIT_SVN_ID=git-oldsvn git-svn init \ + https://svn.sourceforge.net/svnroot/ufoai/trunk + GIT_SVN_ID=git-oldsvn git-svn fetch -r1:165 + + # And now, we continue tracking the new revisions: + GIT_SVN_ID=git-newsvn git-svn init \ + https://svn.sourceforge.net/svnroot/ufoai/ufoai/trunk + GIT_SVN_ID=git-newsvn git-svn fetch \ + 166=`git-rev-parse refs/remotes/git-oldsvn` +------------------------------------------------------------------------ + +BUGS +---- +If somebody commits a conflicting changeset to SVN at a bad moment +(right before you commit) causing a conflict and your commit to fail, +your svn working tree ($GIT_DIR/git-svn/tree) may be dirtied. The +easiest thing to do is probably just to rm -rf $GIT_DIR/git-svn/tree and +run 'rebuild'. + +We ignore all SVN properties except svn:executable. Too difficult to +map them since we rely heavily on git write-tree being _exactly_ the +same on both the SVN and git working trees and I prefer not to clutter +working trees with metadata files. + +svn:keywords can't be ignored in Subversion (at least I don't know of +a way to ignore them). + +Renamed and copied directories are not detected by git and hence not +tracked when committing to SVN. I do not plan on adding support for +this as it's quite difficult and time-consuming to get working for all +the possible corner cases (git doesn't do it, either). Renamed and +copied files are fully supported if they're similar enough for git to +detect them. + +Author +------ +Written by Eric Wong <normalperson@yhbt.net>. + +Documentation +------------- +Written by Eric Wong <normalperson@yhbt.net>. diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh new file mode 100644 index 0000000..80ad357 --- /dev/null +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -0,0 +1,216 @@ +#!/bin/sh +# +# Copyright (c) 2006 Eric Wong +# + + +PATH=$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 $svnrepo" + +test_expect_success \ + 'import an SVN revision into git' \ + 'git-svn fetch' + + +name='try a deep --rmdir with a commit' +git checkout -b mybranch remotes/git-svn +mv dir/a/b/c/d/e/file dir/file +cp dir/file file +git update-index --add --remove dir/a/b/c/d/e/file dir/file file +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch && + 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 remotes/git-svn..mybranch' \ + || true + + +name='detect node change from directory to file #1' +rm -rf dir $GIT_DIR/index +git checkout -b mybranch2 remotes/git-svn +mv bar/zzz zzz +rm -rf bar +mv zzz bar +git update-index --remove -- bar/zzz +git update-index --add -- bar +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch2' \ + || true + + +name='detect node change from file to directory #2' +rm -f $GIT_DIR/index +git checkout -b mybranch3 remotes/git-svn +rm bar/zzz +git-update-index --remove bar/zzz +mkdir bar/zzz +echo yyy > bar/zzz/yyy +git-update-index --add bar/zzz/yyy +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch3' \ + || true + + +name='detect node change from directory to file #2' +rm -f $GIT_DIR/index +git checkout -b mybranch4 remotes/git-svn +rm -rf dir +git update-index --remove -- dir/file +touch dir +echo asdf > dir +git update-index --add -- dir +git commit -m "$name" + +test_expect_code 1 "$name" \ + 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch4' \ + || true + + +name='remove executable bit from a file' +rm -f $GIT_DIR/index +git checkout -b mybranch5 remotes/git-svn +chmod -x exec.sh +git update-index exec.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + test ! -x $SVN_TREE/exec.sh" + + +name='add executable bit back file' +chmod +x exec.sh +git update-index exec.sh +git commit -m "$name" + +test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + 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 remotes/git-svn..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 remotes/git-svn..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 remotes/git-svn..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 && + git-rev-list --pretty=raw remotes/git-svn | grep ^tree | uniq > a && + git-rev-list --pretty=raw remotes/alt | 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 0000000..781badb --- /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, self.encoding) + 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 0000000..fcf759c --- /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/convert-objects.c b/convert-objects.c index b49bce2..12aacef 100644 --- a/convert-objects.c +++ b/convert-objects.c @@ -2,6 +2,9 @@ #define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */ #include <time.h> #include "cache.h" +#include "blob.h" +#include "commit.h" +#include "tree.h" struct entry { unsigned char old_sha1[20]; @@ -18,8 +21,7 @@ static struct entry * convert_entry(unsigned char *sha1); static struct entry *insert_new(unsigned char *sha1, int pos) { - struct entry *new = xmalloc(sizeof(struct entry)); - memset(new, 0, sizeof(*new)); + struct entry *new = xcalloc(1, sizeof(struct entry)); memcpy(new->old_sha1, sha1, 20); memmove(convert + pos + 1, convert + pos, (nr_convert - pos) * sizeof(struct entry *)); convert[pos] = new; @@ -122,7 +124,7 @@ static int write_subdirectory(void *buffer, unsigned long size, const char *base buffer += len; } - write_sha1_file(new, newlen, "tree", result_sha1); + write_sha1_file(new, newlen, tree_type, result_sha1); free(new); return used; } @@ -262,8 +264,8 @@ static void convert_date(void *buffer, unsigned long size, unsigned char *result memcpy(new + newlen, buffer, size); newlen += size; - write_sha1_file(new, newlen, "commit", result_sha1); - free(new); + write_sha1_file(new, newlen, commit_type, result_sha1); + free(new); } static void convert_commit(void *buffer, unsigned long size, unsigned char *result_sha1) @@ -297,12 +299,12 @@ static struct entry * convert_entry(unsigned char *sha1) buffer = xmalloc(size); memcpy(buffer, data, size); - - if (!strcmp(type, "blob")) { - write_sha1_file(buffer, size, "blob", entry->new_sha1); - } else if (!strcmp(type, "tree")) + + if (!strcmp(type, blob_type)) { + write_sha1_file(buffer, size, blob_type, entry->new_sha1); + } else if (!strcmp(type, tree_type)) convert_tree(buffer, size, entry->new_sha1); - else if (!strcmp(type, "commit")) + else if (!strcmp(type, commit_type)) convert_commit(buffer, size, entry->new_sha1); else die("unknown object type '%s' in %s", type, sha1_to_hex(sha1)); diff --git a/count-delta.c b/count-delta.c deleted file mode 100644 index 058a2aa..0000000 --- a/count-delta.c +++ /dev/null @@ -1,72 +0,0 @@ -/* - * Copyright (C) 2005 Junio C Hamano - * The delta-parsing part is almost straight copy of patch-delta.c - * which is (C) 2005 Nicolas Pitre <nico@cam.org>. - */ -#include <stdlib.h> -#include <string.h> -#include <limits.h> -#include "delta.h" -#include "count-delta.h" - -/* - * NOTE. We do not _interpret_ delta fully. As an approximation, we - * just count the number of bytes that are copied from the source, and - * the number of literal data bytes that are inserted. - * - * Number of bytes that are _not_ copied from the source is deletion, - * and number of inserted literal bytes are addition, so sum of them - * is the extent of damage. - */ -int count_delta(void *delta_buf, unsigned long delta_size, - unsigned long *src_copied, unsigned long *literal_added) -{ - unsigned long copied_from_source, added_literal; - const unsigned char *data, *top; - unsigned char cmd; - unsigned long src_size, dst_size, out; - - if (delta_size < DELTA_SIZE_MIN) - return -1; - - data = delta_buf; - top = delta_buf + delta_size; - - src_size = get_delta_hdr_size(&data); - dst_size = get_delta_hdr_size(&data); - - added_literal = copied_from_source = out = 0; - while (data < top) { - cmd = *data++; - if (cmd & 0x80) { - unsigned long cp_off = 0, cp_size = 0; - if (cmd & 0x01) cp_off = *data++; - if (cmd & 0x02) cp_off |= (*data++ << 8); - if (cmd & 0x04) cp_off |= (*data++ << 16); - if (cmd & 0x08) cp_off |= (*data++ << 24); - if (cmd & 0x10) cp_size = *data++; - if (cmd & 0x20) cp_size |= (*data++ << 8); - if (cmd & 0x40) cp_size |= (*data++ << 16); - if (cp_size == 0) cp_size = 0x10000; - - copied_from_source += cp_size; - out += cp_size; - } else { - /* write literal into dst */ - added_literal += cmd; - out += cmd; - data += cmd; - } - } - - /* sanity check */ - if (data != top || out != dst_size) - return -1; - - /* delete size is what was _not_ copied from source. - * edit size is that and literal additions. - */ - *src_copied = copied_from_source; - *literal_added = added_literal; - return 0; -} diff --git a/count-delta.h b/count-delta.h deleted file mode 100644 index 7359629..0000000 --- a/count-delta.h +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Copyright (C) 2005 Junio C Hamano - */ -#ifndef COUNT_DELTA_H -#define COUNT_DELTA_H - -int count_delta(void *, unsigned long, - unsigned long *src_copied, unsigned long *literal_added); - -#endif @@ -123,8 +123,6 @@ static const struct { { "IDLE", +12, 0, }, /* International Date Line East */ }; -#define NR_TZ (sizeof(timezone_names) / sizeof(timezone_names[0])) - static int match_string(const char *date, const char *str) { int i = 0; @@ -173,7 +171,7 @@ static int match_alpha(const char *date, struct tm *tm, int *offset) } } - for (i = 0; i < NR_TZ; i++) { + for (i = 0; i < ARRAY_SIZE(timezone_names); i++) { int match = match_string(date, timezone_names[i].name); if (match >= 3) { int off = timezone_names[i].offset; diff --git a/diff-delta.c b/diff-delta.c index c2f656a..1188b31 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 +30,131 @@ #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; +#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift)) -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; - - 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) +struct index { + const unsigned char *ptr; + unsigned int val; + struct index *next; +}; + +static struct index ** delta_index(const unsigned char *buf, + unsigned long bufsize, + unsigned long trg_bufsize, + unsigned int *hash_shift) { - chanode_t *cur = cha->ancur; - while (cur) { - chanode_t *tmp = cur; - cur = cur->next; - free(tmp); + unsigned int i, hsize, hshift, hlimit, entries, *hash_count; + const unsigned char *data; + struct index *entry, **hash; + void *mem; + + /* determine index hash size */ + entries = bufsize / BLK_SIZE; + hsize = entries / 4; + for (i = 4; (1 << i) < hsize && i < 31; 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)); + + /* allocate an array to count hash entries */ + hash_count = calloc(hsize, sizeof(*hash_count)); + if (!hash_count) { + free(hash); + return NULL; } -} - -typedef struct s_bdrecord { - struct s_bdrecord *next; - unsigned int fp; - const unsigned char *ptr; -} bdrecord_t; -typedef struct s_bdfile { - chastore_t cha; - unsigned int fphbits; - bdrecord_t **fphash; -} bdfile_t; - -static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf) -{ - 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) + /* then populate the index */ + data = buf + entries * BLK_SIZE - BLK_SIZE; + while (data >= buf) { + unsigned int val = adler32(0, data, BLK_SIZE); + i = HASH(val, hshift); + entry->ptr = data; + entry->val = val; + entry->next = hash[i]; + hash[i] = entry++; + hash_count[i]++; 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; + } + + /* + * Determine a limit on the number of entries in the same hash + * bucket. This guard us against patological data sets causing + * really bad hash distribution with most entries in the same hash + * bucket that would bring us to O(m*n) computing costs (m and n + * corresponding to reference and target buffer sizes). + * + * The more the target buffer is large, the more it is important to + * have small entry lists for each hash buckets. With such a limit + * the cost is bounded to something more like O(m+n). + */ + hlimit = (1 << 26) / trg_bufsize; + if (hlimit < 4*BLK_SIZE) + hlimit = 4*BLK_SIZE; + + /* + * Now make sure none of the hash buckets has more entries than + * we're willing to test. Otherwise we cull the entry list + * uniformly to still preserve a good repartition across + * the reference buffer. + */ + for (i = 0; i < hsize; i++) { + if (hash_count[i] < hlimit) + continue; + entry = hash[i]; + do { + struct index *keep = entry; + int skip = hash_count[i] / hlimit / 2; + do { + entry = entry->next; + } while(--skip && entry); + keep->next = entry; + } while(entry); } + free(hash_count); - 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; - - if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf)) + unsigned int i, outpos, outsize, hash_shift; + int inscnt; + const unsigned char *ref_data, *ref_top, *data, *top; + unsigned char *out; + struct index *entry, **hash; + + if (!from_size || !to_size) return NULL; - + hash = delta_index(from_buf, from_size, to_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 +182,30 @@ 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; - } + unsigned int moff = 0, msize = 0; + if (data + BLK_SIZE <= top) { + unsigned int val = adler32(0, data, BLK_SIZE); + 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; + if (ref_size > 0x10000) + ref_size = 0x10000; + if (ref_size <= msize) + break; + while (ref_size-- && *src++ == *ref) + ref++; + if (msize < ref - entry->ptr) { + /* this is our best match so far */ + msize = ref - entry->ptr; + moff = entry->ptr - ref_data; } } } @@ -235,13 +220,29 @@ void *diff_delta(void *from_buf, unsigned long from_size, inscnt = 0; } } else { + unsigned char *op; + if (inscnt) { + while (moff && ref_data[moff-1] == data[-1]) { + if (msize == 0x10000) + break; + /* we can match one byte back */ + msize++; + moff--; + data--; + outpos--; + if (--inscnt) + continue; + outpos--; /* remove count slot */ + inscnt--; /* make it -1 */ + break; + } 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 +257,21 @@ 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 +280,7 @@ 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 0c3f800..3e7f5f1 100644 --- a/diff-files.c +++ b/diff-files.c @@ -149,7 +149,7 @@ int main(int argc, const char **argv) memcpy(combine.p.parent[stage-2].sha1, nce->sha1, 20); combine.p.parent[stage-2].mode = - DIFF_FILE_CANON_MODE(mode); + canon_mode(mode); combine.p.parent[stage-2].status = DIFF_STATUS_MODIFIED; } @@ -193,12 +193,12 @@ 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); - newmode = DIFF_FILE_CANON_MODE(st.st_mode); + newmode = canon_mode(st.st_mode); if (!trust_executable_bit && S_ISREG(newmode) && S_ISREG(oldmode) && ((newmode ^ oldmode) == 0111)) diff --git a/diff-index.c b/diff-index.c index f8a102e..e376d65 100644 --- a/diff-index.c +++ b/diff-index.c @@ -33,12 +33,10 @@ 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 && - S_ISREG(mode) && S_ISREG(ce->ce_mode) && - ((mode ^ ce->ce_mode) == 0111)) + if (!trust_executable_bit && S_ISREG(st.st_mode)) mode = ce->ce_mode; sha1 = no_sha1; } diff --git a/diff-tree.c b/diff-tree.c index f55a35a..d1265d7 100644 --- a/diff-tree.c +++ b/diff-tree.c @@ -52,7 +52,7 @@ static int diff_root_tree(const unsigned char *new, const char *base) void *tree; struct tree_desc empty, real; - tree = read_object_with_reference(new, "tree", &real.size, NULL); + tree = read_object_with_reference(new, tree_type, &real.size, NULL); if (!tree) die("unable to read root tree (%s)", sha1_to_hex(new)); real.buf = tree; @@ -8,8 +8,7 @@ #include "quote.h" #include "diff.h" #include "diffcore.h" - -static const char *diff_opts = "-pu"; +#include "xdiff/xdiff.h" static int use_size_cache; @@ -69,25 +68,10 @@ static const char *external_diff(void) { static const char *external_diff_cmd = NULL; static int done_preparing = 0; - const char *env_diff_opts; if (done_preparing) return external_diff_cmd; - - /* - * Default values above are meant to match the - * Linux kernel development style. Examples of - * alternative styles you can specify via environment - * variables are: - * - * GIT_DIFF_OPTS="-c"; - */ external_diff_cmd = getenv("GIT_EXTERNAL_DIFF"); - - /* In case external diff fails... */ - env_diff_opts = getenv("GIT_DIFF_OPTS"); - if (env_diff_opts) diff_opts = env_diff_opts; - done_preparing = 1; return external_diff_cmd; } @@ -101,13 +85,12 @@ static struct diff_tempfile { char tmp_path[TEMPFILE_PATH_LEN]; } diff_temp[2]; -static int count_lines(const char *filename) +static int count_lines(const char *data, int size) { - FILE *in; int count, ch, completely_empty = 1, nl_just_seen = 0; - in = fopen(filename, "r"); count = 0; - while ((ch = fgetc(in)) != EOF) + while (0 < size--) { + ch = *data++; if (ch == '\n') { count++; nl_just_seen = 1; @@ -117,7 +100,7 @@ static int count_lines(const char *filename) nl_just_seen = 0; completely_empty = 0; } - fclose(in); + } if (completely_empty) return 0; if (!nl_just_seen) @@ -140,12 +123,11 @@ static void print_line_count(int count) } } -static void copy_file(int prefix, const char *filename) +static void copy_file(int prefix, const char *data, int size) { - FILE *in; int ch, nl_just_seen = 1; - in = fopen(filename, "r"); - while ((ch = fgetc(in)) != EOF) { + while (0 < size--) { + ch = *data++; if (nl_just_seen) putchar(prefix); putchar(ch); @@ -154,107 +136,153 @@ static void copy_file(int prefix, const char *filename) else nl_just_seen = 0; } - fclose(in); if (!nl_just_seen) printf("\n\\ No newline at end of file\n"); } static void emit_rewrite_diff(const char *name_a, const char *name_b, - struct diff_tempfile *temp) + struct diff_filespec *one, + struct diff_filespec *two) { /* Use temp[i].name as input, name_a and name_b as labels */ int lc_a, lc_b; - lc_a = count_lines(temp[0].name); - lc_b = count_lines(temp[1].name); + lc_a = count_lines(one->data, one->size); + lc_b = count_lines(two->data, two->size); printf("--- %s\n+++ %s\n@@ -", name_a, name_b); print_line_count(lc_a); printf(" +"); print_line_count(lc_b); printf(" @@\n"); if (lc_a) - copy_file('-', temp[0].name); + copy_file('-', one->data, one->size); if (lc_b) - copy_file('+', temp[1].name); + copy_file('+', two->data, two->size); +} + +static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one) +{ + if (!DIFF_FILE_VALID(one)) { + mf->ptr = ""; /* does not matter */ + mf->size = 0; + return 0; + } + else if (diff_populate_filespec(one, 0)) + return -1; + mf->ptr = one->data; + mf->size = one->size; + return 0; +} + +struct emit_callback { + const char **label_path; +}; + +static int fn_out(void *priv, mmbuffer_t *mb, int nbuf) +{ + int i; + struct emit_callback *ecbdata = priv; + + if (ecbdata->label_path[0]) { + printf("--- %s\n", ecbdata->label_path[0]); + printf("+++ %s\n", ecbdata->label_path[1]); + ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; + } + for (i = 0; i < nbuf; i++) + if (!fwrite(mb[i].ptr, mb[i].size, 1, stdout)) + return -1; + return 0; +} + +#define FIRST_FEW_BYTES 8000 +static int mmfile_is_binary(mmfile_t *mf) +{ + long sz = mf->size; + if (FIRST_FEW_BYTES < sz) + sz = FIRST_FEW_BYTES; + if (memchr(mf->ptr, 0, sz)) + return 1; + return 0; } static void builtin_diff(const char *name_a, const char *name_b, - struct diff_tempfile *temp, + struct diff_filespec *one, + struct diff_filespec *two, const char *xfrm_msg, int complete_rewrite) { - int i, next_at, cmd_size; - const char *const diff_cmd = "diff -L%s -L%s"; - const char *const diff_arg = "-- %s %s||:"; /* "||:" is to return 0 */ - const char *input_name_sq[2]; - const char *label_path[2]; - char *cmd; - - /* diff_cmd and diff_arg have 4 %s in total which makes - * the sum of these strings 8 bytes larger than required. - * we use 2 spaces around diff-opts, and we need to count - * terminating NUL; we used to subtract 5 here, but we do not - * care about small leaks in this subprocess that is about - * to exec "diff" anymore. - */ - cmd_size = (strlen(diff_cmd) + strlen(diff_opts) + strlen(diff_arg) - + 128); - - for (i = 0; i < 2; i++) { - input_name_sq[i] = sq_quote(temp[i].name); - if (!strcmp(temp[i].name, "/dev/null")) - label_path[i] = "/dev/null"; - else if (!i) - label_path[i] = sq_quote(quote_two("a/", name_a)); - else - label_path[i] = sq_quote(quote_two("b/", name_b)); - cmd_size += (strlen(label_path[i]) + strlen(input_name_sq[i])); - } - - cmd = xmalloc(cmd_size); - - next_at = 0; - next_at += snprintf(cmd+next_at, cmd_size-next_at, - diff_cmd, label_path[0], label_path[1]); - next_at += snprintf(cmd+next_at, cmd_size-next_at, - " %s ", diff_opts); - next_at += snprintf(cmd+next_at, cmd_size-next_at, - diff_arg, input_name_sq[0], input_name_sq[1]); - - printf("diff --git %s %s\n", - quote_two("a/", name_a), quote_two("b/", name_b)); - if (label_path[0][0] == '/') { - /* dev/null */ - printf("new file mode %s\n", temp[1].mode); + mmfile_t mf1, mf2; + const char *lbl[2]; + char *a_one, *b_two; + + a_one = quote_two("a/", name_a); + b_two = quote_two("b/", name_b); + lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null"; + lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null"; + printf("diff --git %s %s\n", a_one, b_two); + if (lbl[0][0] == '/') { + /* /dev/null */ + printf("new file mode %06o\n", two->mode); if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); } - else if (label_path[1][0] == '/') { - printf("deleted file mode %s\n", temp[0].mode); + else if (lbl[1][0] == '/') { + printf("deleted file mode %06o\n", one->mode); if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); } else { - if (strcmp(temp[0].mode, temp[1].mode)) { - printf("old mode %s\n", temp[0].mode); - printf("new mode %s\n", temp[1].mode); + if (one->mode != two->mode) { + printf("old mode %06o\n", one->mode); + printf("new mode %06o\n", two->mode); } if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); - if (strncmp(temp[0].mode, temp[1].mode, 3)) - /* we do not run diff between different kind - * of objects. - */ - exit(0); + /* + * we do not run diff between different kind + * of objects. + */ + if ((one->mode ^ two->mode) & S_IFMT) + goto free_ab_and_return; if (complete_rewrite) { - fflush(NULL); - emit_rewrite_diff(name_a, name_b, temp); - exit(0); + emit_rewrite_diff(name_a, name_b, one, two); + goto free_ab_and_return; } } - fflush(NULL); - execlp("/bin/sh","sh", "-c", cmd, NULL); + + if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) + die("unable to read files to diff"); + + if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) + printf("Binary files %s and %s differ\n", lbl[0], lbl[1]); + else { + /* Crazy xdl interfaces.. */ + const char *diffopts = getenv("GIT_DIFF_OPTS"); + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + struct emit_callback ecbdata; + + ecbdata.label_path = lbl; + xpp.flags = XDF_NEED_MINIMAL; + xecfg.ctxlen = 3; + xecfg.flags = XDL_EMIT_FUNCNAMES; + if (!diffopts) + ; + else if (!strncmp(diffopts, "--unified=", 10)) + xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10); + else if (!strncmp(diffopts, "-u", 2)) + xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10); + ecb.outf = fn_out; + ecb.priv = &ecbdata; + xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); + } + + free_ab_and_return: + free(a_one); + free(b_two); + return; } struct diff_filespec *alloc_filespec(const char *path) @@ -272,7 +300,7 @@ void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, unsigned short mode) { if (mode) { - spec->mode = DIFF_FILE_CANON_MODE(mode); + spec->mode = canon_mode(mode); memcpy(spec->sha1, sha1, 20); spec->sha1_valid = !!memcmp(sha1, null_sha1, 20); } @@ -311,7 +339,7 @@ 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, @@ -457,6 +485,8 @@ void diff_free_filespec_data(struct diff_filespec *s) munmap(s->data, s->size); s->should_free = s->should_munmap = 0; s->data = NULL; + free(s->cnt_data); + s->cnt_data = NULL; } static void prep_temp_blob(struct diff_tempfile *temp, @@ -559,6 +589,40 @@ 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 \ @@ -573,11 +637,12 @@ 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; + const char **arg = &spawn_arg[0]; othername = (other? other : name); if (one && two) { @@ -592,59 +657,50 @@ 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); - } - else - execlp(pgm, pgm, name, NULL); + 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; } - /* - * otherwise we use the built-in one. - */ - if (one && two) - builtin_diff(name, othername, temp, xfrm_msg, - complete_rewrite); - else - printf("* Unmerged path %s\n", name); - exit(0); + } else { + *arg++ = pgm; + *arg++ = name; } - 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(); + *arg = NULL; + 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 run_diff_cmd(const char *pgm, + const char *name, + const char *other, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg, + int complete_rewrite) +{ + if (pgm) { + run_external_diff(pgm, name, other, one, two, xfrm_msg, + complete_rewrite); + return; + } + if (one && two) + builtin_diff(name, other ? other : name, + one, two, xfrm_msg, complete_rewrite); + else + printf("* Unmerged path %s\n", name); } static void diff_fill_sha1_info(struct diff_filespec *one) @@ -676,8 +732,7 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) if (DIFF_PAIR_UNMERGED(p)) { /* unmerged */ - run_external_diff(pgm, p->one->path, NULL, NULL, NULL, NULL, - 0); + run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, 0); return; } @@ -749,15 +804,15 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) * needs to be split into deletion and creation. */ struct diff_filespec *null = alloc_filespec(two->path); - run_external_diff(NULL, name, other, one, null, xfrm_msg, 0); + run_diff_cmd(NULL, name, other, one, null, xfrm_msg, 0); free(null); null = alloc_filespec(one->path); - run_external_diff(NULL, name, other, null, two, xfrm_msg, 0); + run_diff_cmd(NULL, name, other, null, two, xfrm_msg, 0); free(null); } else - run_external_diff(pgm, name, other, one, two, xfrm_msg, - complete_rewrite); + run_diff_cmd(pgm, name, other, one, two, xfrm_msg, + complete_rewrite); free(name_munged); free(other_munged); @@ -4,17 +4,7 @@ #ifndef DIFF_H #define DIFF_H -#define DIFF_FILE_CANON_MODE(mode) \ - (S_ISREG(mode) ? (S_IFREG | ce_permissions(mode)) : \ - S_ISLNK(mode) ? S_IFLNK : S_IFDIR) - -struct tree_desc { - void *buf; - unsigned long size; -}; - -extern void update_tree_entry(struct tree_desc *); -extern const unsigned char *tree_entry_extract(struct tree_desc *, const char **, unsigned int *); +#include "tree-walk.h" struct diff_options; diff --git a/diffcore-break.c b/diffcore-break.c index 95b5eb4..ed0e14c 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, @@ -47,9 +45,8 @@ 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; + unsigned long delta_size, base_size, src_copied, literal_added, + src_removed; *merge_score_p = 0; /* assume no deletion --- "do not break" * is the default. @@ -69,47 +66,47 @@ 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 */ + if (diffcore_count_changes(src->data, src->size, + dst->data, dst->size, + NULL, NULL, + 0, + &src_copied, &literal_added)) + return 0; - /* Estimate the edit size by interpreting delta. */ - if (count_delta(delta, delta_size, - &src_copied, &literal_added)) { - free(delta); - return 0; /* we cannot tell */ + /* sanity */ + if (src->size < src_copied) + src_copied = src->size; + if (dst->size < literal_added + src_copied) { + if (src_copied < dst->size) + literal_added = dst->size - src_copied; + else + literal_added = 0; } - free(delta); + src_removed = src->size - src_copied; /* Compute merge-score, which is "how much is removed * from the source material". The clean-up stage will * merge the surviving pair together if the score is * less than the minimum, after rename/copy runs. */ - if (src->size <= src_copied) - ; /* all copied, nothing removed */ - else { - delta_size = src->size - src_copied; - *merge_score_p = delta_size * MAX_SCORE / src->size; - } - + *merge_score_p = src_removed * MAX_SCORE / src->size; + /* Extent of damage, which counts both inserts and * deletes. */ - if (src->size + literal_added <= src_copied) - delta_size = 0; /* avoid wrapping around */ - else - delta_size = (src->size - src_copied) + literal_added; - - /* We break if the edit exceeds the minimum. - * i.e. (break_score / MAX_SCORE < delta_size / base_size) + delta_size = src_removed + literal_added; + if (delta_size * MAX_SCORE / base_size < break_score) + return 0; + + /* If you removed a lot without adding new material, that is + * not really a rewrite. */ - if (break_score * base_size < delta_size * MAX_SCORE) - to_break = 1; + if ((src->size * break_score < src_removed * MAX_SCORE) && + (literal_added * 20 < src_removed) && + (literal_added * 20 < src_copied)) + return 0; - return to_break; + return 1; } void diffcore_break(int break_score) diff --git a/diffcore-delta.c b/diffcore-delta.c new file mode 100644 index 0000000..7338a40 --- /dev/null +++ b/diffcore-delta.c @@ -0,0 +1,213 @@ +#include "cache.h" +#include "diff.h" +#include "diffcore.h" + +/* + * Idea here is very simple. + * + * We have total of (sz-N+1) N-byte overlapping sequences in buf whose + * size is sz. If the same N-byte sequence appears in both source and + * destination, we say the byte that starts that sequence is shared + * between them (i.e. copied from source to destination). + * + * For each possible N-byte sequence, if the source buffer has more + * instances of it than the destination buffer, that means the + * difference are the number of bytes not copied from source to + * destination. If the counts are the same, everything was copied + * from source to destination. If the destination has more, + * everything was copied, and destination added more. + * + * We are doing an approximation so we do not really have to waste + * memory by actually storing the sequence. We just hash them into + * somewhere around 2^16 hashbuckets and count the occurrences. + * + * The length of the sequence is arbitrarily set to 8 for now. + */ + +/* Wild guess at the initial hash size */ +#define INITIAL_HASH_SIZE 9 + +/* We leave more room in smaller hash but do not let it + * grow to have unused hole too much. + */ +#define INITIAL_FREE(sz_log2) ((1<<(sz_log2))*(sz_log2-3)/(sz_log2)) + +/* A prime rather carefully chosen between 2^16..2^17, so that + * HASHBASE < INITIAL_FREE(17). We want to keep the maximum hashtable + * size under the current 2<<17 maximum, which can hold this many + * different values before overflowing to hashtable of size 2<<18. + */ +#define HASHBASE 107927 + +struct spanhash { + unsigned int hashval; + unsigned int cnt; +}; +struct spanhash_top { + int alloc_log2; + int free; + struct spanhash data[FLEX_ARRAY]; +}; + +static struct spanhash *spanhash_find(struct spanhash_top *top, + unsigned int hashval) +{ + int sz = 1 << top->alloc_log2; + int bucket = hashval & (sz - 1); + while (1) { + struct spanhash *h = &(top->data[bucket++]); + if (!h->cnt) + return NULL; + if (h->hashval == hashval) + return h; + if (sz <= bucket) + bucket = 0; + } +} + +static struct spanhash_top *spanhash_rehash(struct spanhash_top *orig) +{ + struct spanhash_top *new; + int i; + int osz = 1 << orig->alloc_log2; + int sz = osz << 1; + + new = xmalloc(sizeof(*orig) + sizeof(struct spanhash) * sz); + new->alloc_log2 = orig->alloc_log2 + 1; + new->free = INITIAL_FREE(new->alloc_log2); + memset(new->data, 0, sizeof(struct spanhash) * sz); + for (i = 0; i < osz; i++) { + struct spanhash *o = &(orig->data[i]); + int bucket; + if (!o->cnt) + continue; + bucket = o->hashval & (sz - 1); + while (1) { + struct spanhash *h = &(new->data[bucket++]); + if (!h->cnt) { + h->hashval = o->hashval; + h->cnt = o->cnt; + new->free--; + break; + } + if (sz <= bucket) + bucket = 0; + } + } + free(orig); + return new; +} + +static struct spanhash_top *add_spanhash(struct spanhash_top *top, + unsigned int hashval, int cnt) +{ + int bucket, lim; + struct spanhash *h; + + lim = (1 << top->alloc_log2); + bucket = hashval & (lim - 1); + while (1) { + h = &(top->data[bucket++]); + if (!h->cnt) { + h->hashval = hashval; + h->cnt = cnt; + top->free--; + if (top->free < 0) + return spanhash_rehash(top); + return top; + } + if (h->hashval == hashval) { + h->cnt += cnt; + return top; + } + if (lim <= bucket) + bucket = 0; + } +} + +static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz) +{ + int i, n; + unsigned int accum1, accum2, hashval; + struct spanhash_top *hash; + + i = INITIAL_HASH_SIZE; + hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i)); + hash->alloc_log2 = i; + hash->free = INITIAL_FREE(i); + memset(hash->data, 0, sizeof(struct spanhash) * (1<<i)); + + n = 0; + accum1 = accum2 = 0; + while (sz) { + unsigned int c = *buf++; + unsigned int old_1 = accum1; + sz--; + accum1 = (accum1 << 7) ^ (accum2 >> 25); + accum2 = (accum2 << 7) ^ (old_1 >> 25); + accum1 += c; + if (++n < 64 && c != '\n') + continue; + hashval = (accum1 + accum2 * 0x61) % HASHBASE; + hash = add_spanhash(hash, hashval, n); + n = 0; + accum1 = accum2 = 0; + } + return hash; +} + +int diffcore_count_changes(void *src, unsigned long src_size, + void *dst, unsigned long dst_size, + void **src_count_p, + void **dst_count_p, + unsigned long delta_limit, + unsigned long *src_copied, + unsigned long *literal_added) +{ + int i, ssz; + struct spanhash_top *src_count, *dst_count; + unsigned long sc, la; + + src_count = dst_count = NULL; + if (src_count_p) + src_count = *src_count_p; + if (!src_count) { + src_count = hash_chars(src, src_size); + if (src_count_p) + *src_count_p = src_count; + } + if (dst_count_p) + dst_count = *dst_count_p; + if (!dst_count) { + dst_count = hash_chars(dst, dst_size); + if (dst_count_p) + *dst_count_p = dst_count; + } + sc = la = 0; + + ssz = 1 << src_count->alloc_log2; + for (i = 0; i < ssz; i++) { + struct spanhash *s = &(src_count->data[i]); + struct spanhash *d; + unsigned dst_cnt, src_cnt; + if (!s->cnt) + continue; + src_cnt = s->cnt; + d = spanhash_find(dst_count, s->hashval); + dst_cnt = d ? d->cnt : 0; + if (src_cnt < dst_cnt) { + la += dst_cnt - src_cnt; + sc += src_cnt; + } + else + sc += dst_cnt; + } + + if (!src_count_p) + free(src_count); + if (!dst_count_p) + free(dst_count); + *src_copied = sc; + *literal_added = la; + return 0; +} diff --git a/diffcore-rename.c b/diffcore-rename.c index ffd126a..e992698 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 */ @@ -135,8 +133,7 @@ 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 max_size, delta_size, base_size, src_copied, literal_added; unsigned long delta_limit; int score; @@ -147,9 +144,9 @@ static int estimate_similarity(struct diff_filespec *src, if (!S_ISREG(src->mode) || !S_ISREG(dst->mode)) return 0; - delta_size = ((src->size < dst->size) ? - (dst->size - src->size) : (src->size - dst->size)); + max_size = ((src->size > dst->size) ? src->size : dst->size); base_size = ((src->size < dst->size) ? src->size : dst->size); + delta_size = max_size - base_size; /* We would not consider edits that change the file size so * drastically. delta_size must be smaller than @@ -165,42 +162,22 @@ 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 */ + if (diffcore_count_changes(src->data, src->size, + dst->data, dst->size, + &src->cnt_data, &dst->cnt_data, + delta_limit, + &src_copied, &literal_added)) return 0; - /* A delta that has a lot of literal additions would have - * big delta_size no matter what else it does. + /* How similar are they? + * what percentage of material in dst are from source? */ - 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); - return 0; - } - free(delta); - - /* Extent of damage */ - if (src->size + literal_added < src_copied) - delta_size = 0; + if (!dst->size) + score = 0; /* should not happen */ else - delta_size = (src->size - src_copied) + literal_added; - - /* - * Now we will give some score to it. 100% edit gets 0 points - * and 0% edit gets MAX_SCORE points. - */ - score = MAX_SCORE - (MAX_SCORE * delta_size / base_size); - if (score < 0) return 0; - if (MAX_SCORE < score) return MAX_SCORE; + score = src_copied * MAX_SCORE / max_size; return score; } @@ -328,6 +305,8 @@ void diffcore_rename(struct diff_options *options) m->score = estimate_similarity(one, two, minimum_score); } + /* We do not need the text anymore */ + diff_free_filespec_data(two); dst_cnt++; } /* cost matrix sorted by most to least similar pair */ @@ -17,8 +17,8 @@ */ #define MAX_SCORE 60000.0 #define DEFAULT_RENAME_SCORE 30000 /* rename/copy similarity minimum (50%) */ -#define DEFAULT_BREAK_SCORE 30000 /* minimum for break to happen (50%)*/ -#define DEFAULT_MERGE_SCORE 48000 /* maximum for break-merge to happen (80%)*/ +#define DEFAULT_BREAK_SCORE 30000 /* minimum for break to happen (50%) */ +#define DEFAULT_MERGE_SCORE 36000 /* maximum for break-merge to happen 60%) */ #define MINIMUM_BREAK_SIZE 400 /* do not break a file smaller than this */ @@ -26,6 +26,7 @@ struct diff_filespec { unsigned char sha1[20]; char *path; void *data; + void *cnt_data; unsigned long size; int xfrm_flags; /* for use by the xfrm */ unsigned short mode; /* file mode */ @@ -101,4 +102,12 @@ 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, + void **src_count_p, + void **dst_count_p, + unsigned long delta_limit, + unsigned long *src_copied, + unsigned long *literal_added); + #endif @@ -1,6 +1,7 @@ #include <sys/types.h> #include <dirent.h> #include "cache.h" +#include "blob.h" static void create_directories(const char *path, struct checkout *state) { @@ -63,7 +64,7 @@ static int create_file(const char *path, unsigned int mode) return open(path, O_WRONLY | O_CREAT | O_EXCL, mode); } -static int write_entry(struct cache_entry *ce, const char *path, struct checkout *state) +static int write_entry(struct cache_entry *ce, char *path, struct checkout *state, int to_tempfile) { int fd; void *new; @@ -72,7 +73,7 @@ static int write_entry(struct cache_entry *ce, const char *path, struct checkout char type[20]; new = read_sha1_file(ce->sha1, type, &size); - if (!new || strcmp(type, "blob")) { + if (!new || strcmp(type, blob_type)) { if (new) free(new); return error("git-checkout-index: unable to read sha1 file of %s (%s)", @@ -80,7 +81,11 @@ static int write_entry(struct cache_entry *ce, const char *path, struct checkout } switch (ntohl(ce->ce_mode) & S_IFMT) { case S_IFREG: - fd = create_file(path, ntohl(ce->ce_mode)); + if (to_tempfile) { + strcpy(path, ".merge_file_XXXXXX"); + fd = mkstemp(path); + } else + fd = create_file(path, ntohl(ce->ce_mode)); if (fd < 0) { free(new); return error("git-checkout-index: unable to create file %s (%s)", @@ -93,12 +98,27 @@ static int write_entry(struct cache_entry *ce, const char *path, struct checkout return error("git-checkout-index: unable to write file %s", path); break; case S_IFLNK: - if (symlink(new, path)) { + if (to_tempfile) { + strcpy(path, ".merge_link_XXXXXX"); + fd = mkstemp(path); + if (fd < 0) { + free(new); + return error("git-checkout-index: unable to create " + "file %s (%s)", path, strerror(errno)); + } + wrote = write(fd, new, size); + close(fd); + free(new); + if (wrote != size) + return error("git-checkout-index: unable to write file %s", + path); + } else { + wrote = symlink(new, path); free(new); - return error("git-checkout-index: unable to create " - "symlink %s (%s)", path, strerror(errno)); + if (wrote) + return error("git-checkout-index: unable to create " + "symlink %s (%s)", path, strerror(errno)); } - free(new); break; default: free(new); @@ -113,17 +133,20 @@ static int write_entry(struct cache_entry *ce, const char *path, struct checkout return 0; } -int checkout_entry(struct cache_entry *ce, struct checkout *state) +int checkout_entry(struct cache_entry *ce, struct checkout *state, char *topath) { - struct stat st; static char path[MAXPATHLEN+1]; + struct stat st; int len = state->base_dir_len; + if (topath) + return write_entry(ce, topath, state, 1); + memcpy(path, state->base_dir, len); 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) { @@ -144,10 +167,10 @@ int checkout_entry(struct cache_entry *ce, struct checkout *state) return error("%s is a directory", path); remove_subtree(path); } - } else if (state->not_new) + } else if (state->not_new) return 0; create_directories(path, state); - return write_entry(ce, path, state); + return write_entry(ce, path, state, 0); } diff --git a/environment.c b/environment.c index 73e4b1c..6df6478 100644 --- a/environment.c +++ b/environment.c @@ -12,7 +12,9 @@ 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 warn_ambiguous_refs = 1; int repository_format_version = 0; char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; int shared_repository = 0; diff --git a/epoch.c b/epoch.c deleted file mode 100644 index 3a76748..0000000 --- a/epoch.c +++ /dev/null @@ -1,639 +0,0 @@ -/* - * Copyright (c) 2005, Jon Seymour - * - * For more information about epoch theory on which this module is based, - * refer to http://blackcubes.dyndns.org/epoch/. That web page defines - * terms such as "epoch" and "minimal, non-linear epoch" and provides rationales - * for some of the algorithms used here. - * - */ -#include <stdlib.h> - -/* Provides arbitrary precision integers required to accurately represent - * fractional mass: */ -#include <openssl/bn.h> - -#include "cache.h" -#include "commit.h" -#include "epoch.h" - -struct fraction { - BIGNUM numerator; - BIGNUM denominator; -}; - -#define HAS_EXACTLY_ONE_PARENT(n) ((n)->parents && !(n)->parents->next) - -static BN_CTX *context = NULL; -static struct fraction *one = NULL; -static struct fraction *zero = NULL; - -static BN_CTX *get_BN_CTX(void) -{ - if (!context) { - context = BN_CTX_new(); - } - return context; -} - -static struct fraction *new_zero(void) -{ - struct fraction *result = xmalloc(sizeof(*result)); - BN_init(&result->numerator); - BN_init(&result->denominator); - BN_zero(&result->numerator); - BN_one(&result->denominator); - return result; -} - -static void clear_fraction(struct fraction *fraction) -{ - BN_clear(&fraction->numerator); - BN_clear(&fraction->denominator); -} - -static struct fraction *divide(struct fraction *result, struct fraction *fraction, int divisor) -{ - BIGNUM bn_divisor; - - BN_init(&bn_divisor); - BN_set_word(&bn_divisor, divisor); - - BN_copy(&result->numerator, &fraction->numerator); - BN_mul(&result->denominator, &fraction->denominator, &bn_divisor, get_BN_CTX()); - - BN_clear(&bn_divisor); - return result; -} - -static struct fraction *init_fraction(struct fraction *fraction) -{ - BN_init(&fraction->numerator); - BN_init(&fraction->denominator); - BN_zero(&fraction->numerator); - BN_one(&fraction->denominator); - return fraction; -} - -static struct fraction *get_one(void) -{ - if (!one) { - one = new_zero(); - BN_one(&one->numerator); - } - return one; -} - -static struct fraction *get_zero(void) -{ - if (!zero) { - zero = new_zero(); - } - return zero; -} - -static struct fraction *copy(struct fraction *to, struct fraction *from) -{ - BN_copy(&to->numerator, &from->numerator); - BN_copy(&to->denominator, &from->denominator); - return to; -} - -static struct fraction *add(struct fraction *result, struct fraction *left, struct fraction *right) -{ - BIGNUM a, b, gcd; - - BN_init(&a); - BN_init(&b); - BN_init(&gcd); - - BN_mul(&a, &left->numerator, &right->denominator, get_BN_CTX()); - BN_mul(&b, &left->denominator, &right->numerator, get_BN_CTX()); - BN_mul(&result->denominator, &left->denominator, &right->denominator, get_BN_CTX()); - BN_add(&result->numerator, &a, &b); - - BN_gcd(&gcd, &result->denominator, &result->numerator, get_BN_CTX()); - BN_div(&result->denominator, NULL, &result->denominator, &gcd, get_BN_CTX()); - BN_div(&result->numerator, NULL, &result->numerator, &gcd, get_BN_CTX()); - - BN_clear(&a); - BN_clear(&b); - BN_clear(&gcd); - - return result; -} - -static int compare(struct fraction *left, struct fraction *right) -{ - BIGNUM a, b; - int result; - - BN_init(&a); - BN_init(&b); - - BN_mul(&a, &left->numerator, &right->denominator, get_BN_CTX()); - BN_mul(&b, &left->denominator, &right->numerator, get_BN_CTX()); - - result = BN_cmp(&a, &b); - - BN_clear(&a); - BN_clear(&b); - - return result; -} - -struct mass_counter { - struct fraction seen; - struct fraction pending; -}; - -static struct mass_counter *new_mass_counter(struct commit *commit, struct fraction *pending) -{ - struct mass_counter *mass_counter = xmalloc(sizeof(*mass_counter)); - memset(mass_counter, 0, sizeof(*mass_counter)); - - init_fraction(&mass_counter->seen); - init_fraction(&mass_counter->pending); - - copy(&mass_counter->pending, pending); - copy(&mass_counter->seen, get_zero()); - - if (commit->object.util) { - die("multiple attempts to initialize mass counter for %s", - sha1_to_hex(commit->object.sha1)); - } - - commit->object.util = mass_counter; - - return mass_counter; -} - -static void free_mass_counter(struct mass_counter *counter) -{ - clear_fraction(&counter->seen); - clear_fraction(&counter->pending); - free(counter); -} - -/* - * Finds the base commit of a list of commits. - * - * One property of the commit being searched for is that every commit reachable - * from the base commit is reachable from the commits in the starting list only - * via paths that include the base commit. - * - * This algorithm uses a conservation of mass approach to find the base commit. - * - * We start by injecting one unit of mass into the graph at each - * of the commits in the starting list. Injecting mass into a commit - * is achieved by adding to its pending mass counter and, if it is not already - * enqueued, enqueuing the commit in a list of pending commits, in latest - * commit date first order. - * - * The algorithm then proceeds to visit each commit in the pending queue. - * Upon each visit, the pending mass is added to the mass already seen for that - * commit and then divided into N equal portions, where N is the number of - * parents of the commit being visited. The divided portions are then injected - * into each of the parents. - * - * The algorithm continues until we discover a commit which has seen all the - * mass originally injected or until we run out of things to do. - * - * If we find a commit that has seen all the original mass, we have found - * the common base of all the commits in the starting list. - * - * The algorithm does _not_ depend on accurate timestamps for correct operation. - * However, reasonably sane (e.g. non-random) timestamps are required in order - * to prevent an exponential performance characteristic. The occasional - * timestamp inaccuracy will not dramatically affect performance but may - * result in more nodes being processed than strictly necessary. - * - * This procedure sets *boundary to the address of the base commit. It returns - * non-zero if, and only if, there was a problem parsing one of the - * commits discovered during the traversal. - */ -static int find_base_for_list(struct commit_list *list, struct commit **boundary) -{ - int ret = 0; - struct commit_list *cleaner = NULL; - struct commit_list *pending = NULL; - struct fraction injected; - init_fraction(&injected); - *boundary = NULL; - - for (; list; list = list->next) { - struct commit *item = list->item; - - if (!item->object.util) { - new_mass_counter(list->item, get_one()); - add(&injected, &injected, get_one()); - - commit_list_insert(list->item, &cleaner); - commit_list_insert(list->item, &pending); - } - } - - while (!*boundary && pending && !ret) { - struct commit *latest = pop_commit(&pending); - struct mass_counter *latest_node = (struct mass_counter *) latest->object.util; - int num_parents; - - if ((ret = parse_commit(latest))) - continue; - add(&latest_node->seen, &latest_node->seen, &latest_node->pending); - - num_parents = count_parents(latest); - if (num_parents) { - struct fraction distribution; - struct commit_list *parents; - - divide(init_fraction(&distribution), &latest_node->pending, num_parents); - - for (parents = latest->parents; parents; parents = parents->next) { - struct commit *parent = parents->item; - struct mass_counter *parent_node = (struct mass_counter *) parent->object.util; - - if (!parent_node) { - parent_node = new_mass_counter(parent, &distribution); - insert_by_date(parent, &pending); - commit_list_insert(parent, &cleaner); - } else { - if (!compare(&parent_node->pending, get_zero())) - insert_by_date(parent, &pending); - add(&parent_node->pending, &parent_node->pending, &distribution); - } - } - - clear_fraction(&distribution); - } - - if (!compare(&latest_node->seen, &injected)) - *boundary = latest; - copy(&latest_node->pending, get_zero()); - } - - while (cleaner) { - struct commit *next = pop_commit(&cleaner); - free_mass_counter((struct mass_counter *) next->object.util); - next->object.util = NULL; - } - - if (pending) - free_commit_list(pending); - - clear_fraction(&injected); - return ret; -} - - -/* - * Finds the base of an minimal, non-linear epoch, headed at head, by - * applying the find_base_for_list to a list consisting of the parents - */ -static int find_base(struct commit *head, struct commit **boundary) -{ - int ret = 0; - struct commit_list *pending = NULL; - struct commit_list *next; - - for (next = head->parents; next; next = next->next) { - commit_list_insert(next->item, &pending); - } - ret = find_base_for_list(pending, boundary); - free_commit_list(pending); - - return ret; -} - -/* - * This procedure traverses to the boundary of the first epoch in the epoch - * sequence of the epoch headed at head_of_epoch. This is either the end of - * the maximal linear epoch or the base of a minimal non-linear epoch. - * - * The queue of pending nodes is sorted in reverse date order and each node - * is currently in the queue at most once. - */ -static int find_next_epoch_boundary(struct commit *head_of_epoch, struct commit **boundary) -{ - int ret; - struct commit *item = head_of_epoch; - - ret = parse_commit(item); - if (ret) - return ret; - - if (HAS_EXACTLY_ONE_PARENT(item)) { - /* - * We are at the start of a maximimal linear epoch. - * Traverse to the end. - */ - while (HAS_EXACTLY_ONE_PARENT(item) && !ret) { - item = item->parents->item; - ret = parse_commit(item); - } - *boundary = item; - - } else { - /* - * Otherwise, we are at the start of a minimal, non-linear - * epoch - find the common base of all parents. - */ - ret = find_base(item, boundary); - } - - return ret; -} - -/* - * Returns non-zero if parent is known to be a parent of child. - */ -static int is_parent_of(struct commit *parent, struct commit *child) -{ - struct commit_list *parents; - for (parents = child->parents; parents; parents = parents->next) { - if (!memcmp(parent->object.sha1, parents->item->object.sha1, - sizeof(parents->item->object.sha1))) - return 1; - } - return 0; -} - -/* - * Pushes an item onto the merge order stack. If the top of the stack is - * marked as being a possible "break", we check to see whether it actually - * is a break. - */ -static void push_onto_merge_order_stack(struct commit_list **stack, struct commit *item) -{ - struct commit_list *top = *stack; - if (top && (top->item->object.flags & DISCONTINUITY)) { - if (is_parent_of(top->item, item)) { - top->item->object.flags &= ~DISCONTINUITY; - } - } - commit_list_insert(item, stack); -} - -/* - * Marks all interesting, visited commits reachable from this commit - * as uninteresting. We stop recursing when we reach the epoch boundary, - * an unvisited node or a node that has already been marking uninteresting. - * - * This doesn't actually mark all ancestors between the start node and the - * epoch boundary uninteresting, but does ensure that they will eventually - * be marked uninteresting when the main sort_first_epoch() traversal - * eventually reaches them. - */ -static void mark_ancestors_uninteresting(struct commit *commit) -{ - unsigned int flags = commit->object.flags; - int visited = flags & VISITED; - int boundary = flags & BOUNDARY; - int uninteresting = flags & UNINTERESTING; - struct commit_list *next; - - commit->object.flags |= UNINTERESTING; - - /* - * We only need to recurse if - * we are not on the boundary and - * we have not already been marked uninteresting and - * we have already been visited. - * - * The main sort_first_epoch traverse will mark unreachable - * all uninteresting, unvisited parents as they are visited - * so there is no need to duplicate that traversal here. - * - * Similarly, if we are already marked uninteresting - * then either all ancestors have already been marked - * uninteresting or will be once the sort_first_epoch - * traverse reaches them. - */ - - if (uninteresting || boundary || !visited) - return; - - for (next = commit->parents; next; next = next->next) - mark_ancestors_uninteresting(next->item); -} - -/* - * Sorts the nodes of the first epoch of the epoch sequence of the epoch headed at head - * into merge order. - */ -static void sort_first_epoch(struct commit *head, struct commit_list **stack) -{ - struct commit_list *parents; - - head->object.flags |= VISITED; - - /* - * TODO: By sorting the parents in a different order, we can alter the - * merge order to show contemporaneous changes in parallel branches - * occurring after "local" changes. This is useful for a developer - * when a developer wants to see all changes that were incorporated - * into the same merge as her own changes occur after her own - * changes. - */ - - for (parents = head->parents; parents; parents = parents->next) { - struct commit *parent = parents->item; - - if (head->object.flags & UNINTERESTING) { - /* - * Propagates the uninteresting bit to all parents. - * if we have already visited this parent, then - * the uninteresting bit will be propagated to each - * reachable commit that is still not marked - * uninteresting and won't otherwise be reached. - */ - mark_ancestors_uninteresting(parent); - } - - if (!(parent->object.flags & VISITED)) { - if (parent->object.flags & BOUNDARY) { - if (*stack) { - die("something else is on the stack - %s", - sha1_to_hex((*stack)->item->object.sha1)); - } - push_onto_merge_order_stack(stack, parent); - parent->object.flags |= VISITED; - - } else { - sort_first_epoch(parent, stack); - if (parents) { - /* - * This indicates a possible - * discontinuity it may not be be - * actual discontinuity if the head - * of parent N happens to be the tail - * of parent N+1. - * - * The next push onto the stack will - * resolve the question. - */ - (*stack)->item->object.flags |= DISCONTINUITY; - } - } - } - } - - push_onto_merge_order_stack(stack, head); -} - -/* - * Emit the contents of the stack. - * - * The stack is freed and replaced by NULL. - * - * Sets the return value to STOP if no further output should be generated. - */ -static int emit_stack(struct commit_list **stack, emitter_func emitter, int include_last) -{ - unsigned int seen = 0; - int action = CONTINUE; - - while (*stack && (action != STOP)) { - struct commit *next = pop_commit(stack); - seen |= next->object.flags; - if (*stack || include_last) { - if (!*stack) - next->object.flags |= BOUNDARY; - action = emitter(next); - } - } - - if (*stack) { - free_commit_list(*stack); - *stack = NULL; - } - - return (action == STOP || (seen & UNINTERESTING)) ? STOP : CONTINUE; -} - -/* - * Sorts an arbitrary epoch into merge order by sorting each epoch - * of its epoch sequence into order. - * - * Note: this algorithm currently leaves traces of its execution in the - * object flags of nodes it discovers. This should probably be fixed. - */ -static int sort_in_merge_order(struct commit *head_of_epoch, emitter_func emitter) -{ - struct commit *next = head_of_epoch; - int ret = 0; - int action = CONTINUE; - - ret = parse_commit(head_of_epoch); - - next->object.flags |= BOUNDARY; - - while (next && next->parents && !ret && (action != STOP)) { - struct commit *base = NULL; - - ret = find_next_epoch_boundary(next, &base); - if (ret) - return ret; - next->object.flags |= BOUNDARY; - if (base) - base->object.flags |= BOUNDARY; - - if (HAS_EXACTLY_ONE_PARENT(next)) { - while (HAS_EXACTLY_ONE_PARENT(next) - && (action != STOP) - && !ret) { - if (next->object.flags & UNINTERESTING) { - action = STOP; - } else { - action = emitter(next); - } - if (action != STOP) { - next = next->parents->item; - ret = parse_commit(next); - } - } - - } else { - struct commit_list *stack = NULL; - sort_first_epoch(next, &stack); - action = emit_stack(&stack, emitter, (base == NULL)); - next = base; - } - } - - if (next && (action != STOP) && !ret) { - emitter(next); - } - - return ret; -} - -/* - * Sorts the nodes reachable from a starting list in merge order, we - * first find the base for the starting list and then sort all nodes - * in this subgraph using the sort_first_epoch algorithm. Once we have - * reached the base we can continue sorting using sort_in_merge_order. - */ -int sort_list_in_merge_order(struct commit_list *list, emitter_func emitter) -{ - struct commit_list *stack = NULL; - struct commit *base; - int ret = 0; - int action = CONTINUE; - struct commit_list *reversed = NULL; - - for (; list; list = list->next) - commit_list_insert(list->item, &reversed); - - if (!reversed) - return ret; - else if (!reversed->next) { - /* - * If there is only one element in the list, we can sort it - * using sort_in_merge_order. - */ - base = reversed->item; - } else { - /* - * Otherwise, we search for the base of the list. - */ - ret = find_base_for_list(reversed, &base); - if (ret) - return ret; - if (base) - base->object.flags |= BOUNDARY; - - while (reversed) { - struct commit * next = pop_commit(&reversed); - - if (!(next->object.flags & VISITED) && next!=base) { - sort_first_epoch(next, &stack); - if (reversed) { - /* - * If we have more commits - * to push, then the first - * push for the next parent may - * (or may * not) represent a - * discontinuity with respect - * to the parent currently on - * the top of the stack. - * - * Mark it for checking here, - * and check it with the next - * push. See sort_first_epoch() - * for more details. - */ - stack->item->object.flags |= DISCONTINUITY; - } - } - } - - action = emit_stack(&stack, emitter, (base==NULL)); - } - - if (base && (action != STOP)) { - ret = sort_in_merge_order(base, emitter); - } - - return ret; -} diff --git a/epoch.h b/epoch.h deleted file mode 100644 index 7493d5a..0000000 --- a/epoch.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef EPOCH_H -#define EPOCH_H - - -// return codes for emitter_func -#define STOP 0 -#define CONTINUE 1 -#define DO 2 -typedef int (*emitter_func) (struct commit *); - -int sort_list_in_merge_order(struct commit_list *list, emitter_func emitter); - -/* Low bits are used by rev-list */ -#define UNINTERESTING (1u<<10) -#define BOUNDARY (1u<<11) -#define VISITED (1u<<12) -#define DISCONTINUITY (1u<<13) -#define LAST_EPOCH_FLAG (1u<<14) - - -#endif /* EPOCH_H */ @@ -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; @@ -29,17 +29,18 @@ const char *git_exec_path() } -int execv_git_cmd(char **argv) +int execv_git_cmd(const char **argv) { char git_command[PATH_MAX + 1]; - char *tmp; int len, err, i; const char *paths[] = { current_exec_path, getenv("GIT_EXEC_PATH"), builtin_exec_path }; - for (i = 0; i < sizeof(paths)/sizeof(paths[0]); ++i) { + for (i = 0; i < ARRAY_SIZE(paths); ++i) { const char *exec_dir = paths[i]; + const char *tmp; + if (!exec_dir) continue; if (*exec_dir != '/') { @@ -82,7 +83,7 @@ int execv_git_cmd(char **argv) argv[0] = git_command; /* execve() can only ever return if it fails */ - execve(git_command, argv, environ); + execve(git_command, (char **)argv, environ); err = errno; @@ -93,11 +94,11 @@ int execv_git_cmd(char **argv) } -int execl_git_cmd(char *cmd,...) +int execl_git_cmd(const char *cmd,...) { int argc; - char *argv[MAX_ARGS + 1]; - char *arg; + const char *argv[MAX_ARGS + 1]; + const char *arg; va_list param; va_start(param, cmd); @@ -3,8 +3,8 @@ extern void git_set_exec_path(const char *exec_path); extern const char* git_exec_path(void); -extern int execv_git_cmd(char **argv); /* NULL terminated */ -extern int execl_git_cmd(char *cmd, ...); +extern int execv_git_cmd(const char **argv); /* NULL terminated */ +extern int execl_git_cmd(const char *cmd, ...); #endif /* __GIT_EXEC_CMD_H_ */ diff --git a/fetch-pack.c b/fetch-pack.c index aa6f42a..a3bcad0 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -7,8 +7,9 @@ static int keep_pack; static int quiet; static int verbose; +static int fetch_all; static const char fetch_pack_usage[] = -"git-fetch-pack [-q] [-v] [-k] [--exec=upload-pack] [host:]directory <refs>..."; +"git-fetch-pack [--all] [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; static const char *exec = "git-upload-pack"; #define COMPLETE (1U << 0) @@ -18,7 +19,7 @@ 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 +83,7 @@ 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 +157,9 @@ 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]); @@ -265,8 +267,9 @@ static void filter_refs(struct ref **refs, int nr_match, char **match) for (prev = NULL, current = *refs; current; current = next) { next = current->next; if ((!memcmp(current->name, "refs/", 5) && - check_ref_format(current->name + 5)) || - !path_match(current->name, nr_match, match)) { + check_ref_format(current->name + 5)) || + (!fetch_all && + !path_match(current->name, nr_match, match))) { if (prev == NULL) *refs = next; else @@ -375,7 +378,11 @@ static int fetch_pack(int fd[2], int nr_match, char **match) goto all_done; } if (find_common(fd, sha1, ref) < 0) - fprintf(stderr, "warning: no common commits\n"); + if (!keep_pack) + /* When cloning, it is not unusual to have + * no common commit. + */ + fprintf(stderr, "warning: no common commits\n"); if (keep_pack) status = receive_keep_pack(fd, "git-fetch-pack", quiet); @@ -421,6 +428,14 @@ int main(int argc, char **argv) keep_pack = 1; continue; } + if (!strcmp("--thin", arg)) { + use_thin_pack = 1; + continue; + } + if (!strcmp("--all", arg)) { + fetch_all = 1; + continue; + } if (!strcmp("-v", arg)) { verbose = 1; continue; @@ -434,6 +449,8 @@ 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 6439d55..59b2590 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -14,13 +14,12 @@ static int show_root = 0; static int show_tags = 0; static int show_unreachable = 0; -static int standalone = 0; static int check_full = 0; static int check_strict = 0; -static int keep_cache_objects = 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 @@ -68,7 +67,7 @@ static void check_connectivity(void) continue; if (!obj->parsed) { - if (!standalone && has_sha1_file(obj->sha1)) + if (has_sha1_file(obj->sha1)) ; /* it is in pack */ else printf("missing %s %s\n", @@ -82,7 +81,7 @@ static void check_connectivity(void) for (j = 0; j < refs->count; j++) { struct object *ref = refs->ref[j]; if (ref->parsed || - (!standalone && has_sha1_file(ref->sha1))) + (has_sha1_file(ref->sha1))) continue; printf("broken link from %7s %s\n", obj->type, sha1_to_hex(obj->sha1)); @@ -390,7 +389,7 @@ static int fsck_handle_ref(const char *refname, const unsigned char *sha1) obj = lookup_object(sha1); if (!obj) { - if (!standalone && has_sha1_file(sha1)) { + if (has_sha1_file(sha1)) { default_refs++; return 0; /* it is in a pack */ } @@ -464,10 +463,6 @@ int main(int argc, char **argv) keep_cache_objects = 1; continue; } - if (!strcmp(arg, "--standalone")) { - standalone = 1; - continue; - } if (!strcmp(arg, "--full")) { check_full = 1; continue; @@ -477,14 +472,9 @@ int main(int argc, char **argv) continue; } if (*arg == '-') - usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--standalone | --full] [--strict] <head-sha1>*]"); + usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--full] [--strict] <head-sha1>*]"); } - if (standalone && check_full) - die("Only one of --standalone or --full can be used."); - if (standalone) - putenv("GIT_ALTERNATE_OBJECT_DIRECTORIES="); - fsck_head_link(); fsck_object_dir(get_object_directory()); if (check_full) { diff --git a/generate-cmdlist.sh b/generate-cmdlist.sh new file mode 100755 index 0000000..6c59dbd --- /dev/null +++ b/generate-cmdlist.sh @@ -0,0 +1,52 @@ +#!/bin/sh + +echo "/* Automatically generated by $0 */ +struct cmdname_help +{ + char name[16]; + char help[64]; +}; + +struct cmdname_help common_cmds[] = {" + +sort <<\EOF | +add +apply +bisect +branch +checkout +cherry-pick +clone +commit +diff +fetch +grep +init-db +log +merge +mv +prune +pull +push +rebase +reset +revert +rm +show +show-branch +status +tag +verify-tag +whatchanged +EOF +while read cmd +do + sed -n ' + /NAME/,/git-'"$cmd"'/H + ${ + x + s/.*git-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/git-$cmd.txt" +done +echo "};" @@ -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 \ @@ -2,7 +2,8 @@ # # Copyright (c) 2005, 2006 Junio C Hamano -USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox> +USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] + [--interactive] [--whitespace=<option>] <mbox>... or, when resuming [--skip | --resolved]' . git-sh-setup diff --git a/git-annotate.perl b/git-annotate.perl new file mode 100755 index 0000000..9df72a1 --- /dev/null +++ b/git-annotate.perl @@ -0,0 +1,508 @@ +#!/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 $0} [-s] [-S revs-file] file [ revision ] + -l, --long + Show long rev (Defaults off) + -t, --time + Show raw timestamp (Defaults off) + -r, --rename + Follow renames (Defaults on). + -S, --rev-file revs-file + Use revs from revs-file instead of calling git-rev-list + -h, --help + This message. +'; + + exit(1); +} + +our ($help, $longrev, $rename, $rawtime, $starting_rev, $rev_file) = (0, 0, 1); + +my $rc = GetOptions( "long|l" => \$longrev, + "time|t" => \$rawtime, + "help|h" => \$help, + "rename|r" => \$rename, + "rev-file|S=s" => \$rev_file); +if (!$rc or $help) { + usage(); +} + +my $filename = shift @ARGV; +if (@ARGV) { + $starting_rev = shift @ARGV; +} + +my @stack = ( + { + 'rev' => defined $starting_rev ? $starting_rev : "HEAD", + 'filename' => $filename, + }, +); + +our @filelines = (); + +if (defined $starting_rev) { + @filelines = git_cat_file($starting_rev, $filename); +} else { + open(F,"<",$filename) + or die "Failed to open filename: $!"; + + while(<F>) { + chomp; + push @filelines, $_; + } + close(F); + +} + +our %revs; +our @revqueue; +our $head; + +my $revsprocessed = 0; +while (my $bound = pop @stack) { + my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'}); + foreach my $revinst (@revisions) { + my ($rev, @parents) = @$revinst; + $head ||= $rev; + + if (!defined($rev)) { + $rev = ""; + } + $revs{$rev}{'filename'} = $bound->{'filename'}; + if (scalar @parents > 0) { + $revs{$rev}{'parents'} = \@parents; + next; + } + + if (!$rename) { + next; + } + + my $newbound = find_parent_renames($rev, $bound->{'filename'}); + if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) { + push @stack, $newbound; + $revs{$rev}{'parents'} = [$newbound->{'rev'}]; + } + } +} +push @revqueue, $head; +init_claim( defined $starting_rev ? $head : 'dirty'); +unless (defined $starting_rev) { + my $diff = open_pipe("git","diff","-R", "HEAD", "--",$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); + die "Failed to find a blob for $filename in rev $rev\n" if !defined $blob; + + my $catfile = open_pipe("git","cat-file", "blob", $blob) + or die "Failed to git-cat-file blob $blob (rev $rev, file $filename): " . $!; + + my @lines; + while(<$catfile>) { + chomp; + push @lines, $_; + } + close($catfile); + + return @lines; +} + +sub git_ls_tree { + my ($rev, $filename) = @_; + + my $lstree = open_pipe("git","ls-tree",$rev,$filename) + or die "Failed to call git ls-tree: $!"; + + my ($mode, $type, $blob, $tfilename); + while(<$lstree>) { + chomp; + ($mode, $type, $blob, $tfilename) = split(/\s+/, $_, 4); + last if ($tfilename eq $filename); + } + close($lstree); + + return $blob if ($tfilename eq $filename); + die "git-ls-tree failed to find blob for $filename"; + +} + + + +sub claim_line { + my ($floffset, $rev, $lines, %revinfo) = @_; + my $oline = get_line($lines, $floffset); + @{$lines->[$floffset]} = ( $oline, $rev, + $revinfo{'author'}, $revinfo{'author_date'} ); + #printf("Claiming line %d with rev %s: '%s'\n", + # $floffset, $rev, $oline) if 1; +} + +sub git_commit_info { + my ($rev) = @_; + my $commit = open_pipe("git-cat-file", "commit", $rev) + or die "Failed to call git-cat-file: $!"; + + my %info; + while(<$commit>) { + chomp; + last if (length $_ == 0); + + if (m/^author (.*) <(.*)> (.*)$/) { + $info{'author'} = $1; + $info{'author_email'} = $2; + $info{'author_date'} = $3; + } elsif (m/^committer (.*) <(.*)> (.*)$/) { + $info{'committer'} = $1; + $info{'committer_email'} = $2; + $info{'committer_date'} = $3; + } + } + close($commit); + + return %info; +} + +sub format_date { + if ($rawtime) { + return $_[0]; + } + my ($timestamp, $timezone) = split(' ', $_[0]); + my $minutes = abs($timezone); + $minutes = int($minutes / 100) * 60 + ($minutes % 100); + if ($timezone < 0) { + $minutes = -$minutes; + } + my $t = $timestamp + $minutes * 60; + return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($t)); +} + +# Copied from git-send-email.perl - We need a Git.pm module.. +sub gitvar { + my ($var) = @_; + my $fh; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-var', $var) or die "$!"; + } + my ($val) = <$fh>; + close $fh or die "$!"; + chomp($val); + return $val; +} + +sub gitvar_name { + my ($name) = @_; + my $val = gitvar($name); + my @field = split(/\s+/, $val); + return join(' ', @field[0...(@field-4)]); +} + +sub open_pipe { + if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { + return open_pipe_activestate(@_); + } else { + return open_pipe_normal(@_); + } +} + +sub open_pipe_activestate { + tie *fh, "Git::ActiveStatePipe", @_; + return *fh; +} + +sub open_pipe_normal { + my (@execlist) = @_; + + my $pid = open my $kid, "-|"; + defined $pid or die "Cannot fork: $!"; + + unless ($pid) { + exec @execlist; + die "Cannot exec @execlist: $!"; + } + + return $kid; +} + +package Git::ActiveStatePipe; +use strict; + +sub TIEHANDLE { + my ($class, @params) = @_; + my $cmdline = join " ", @params; + my @data = qx{$cmdline}; + bless { i => 0, data => \@data }, $class; +} + +sub READLINE { + my $self = shift; + if ($self->{i} >= scalar @{$self->{data}}) { + return undef; + } + return $self->{'data'}->[ $self->{i}++ ]; +} + +sub CLOSE { + my $self = shift; + delete $self->{data}; + delete $self->{i}; +} + +sub EOF { + my $self = shift; + return ($self->{i} >= scalar @{$self->{data}}); +} diff --git a/git-archimport.perl b/git-archimport.perl index 6792624..740bc1f 100755 --- a/git-archimport.perl +++ b/git-archimport.perl @@ -928,7 +928,7 @@ sub find_parents { # now walk up to the mergepoint collecting what patches we have my $branchtip = git_rev_parse($ps->{branch}); - my @ancestors = `git-rev-list --merge-order $branchtip ^$mergebase`; + my @ancestors = `git-rev-list --topo-order $branchtip ^$mergebase`; my %have; # collected merges this branch has foreach my $merge (@{$ps->{merges}}) { $have{$merge} = 1; @@ -951,7 +951,7 @@ sub find_parents { # see what the remote branch has - these are the merges we # will want to have in a consecutive series from the mergebase my $otherbranchtip = git_rev_parse($branch); - my @needraw = `git-rev-list --merge-order $otherbranchtip ^$mergebase`; + my @needraw = `git-rev-list --topo-order $otherbranchtip ^$mergebase`; my @need; foreach my $needps (@needraw) { # get the psets $needps = commitid2pset($needps); diff --git a/git-bisect.sh b/git-bisect.sh index 0750253..03df143 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-branch.sh b/git-branch.sh index 6ac961e..663a3a3 100755 --- a/git-branch.sh +++ b/git-branch.sh @@ -48,6 +48,12 @@ If you are sure you want to delete it, run 'git branch -D $branch_name'." exit 0 } +ls_remote_branches () { + git-rev-parse --symbolic --all | + sed -ne 's|^refs/\(remotes/\)|\1|p' | + sort +} + force= while case "$#,$1" in 0,*) break ;; *,-*) ;; *) break ;; esac do @@ -56,6 +62,10 @@ do delete_branch "$@" exit ;; + -r) + ls_remote_branches + exit + ;; -f) force="$1" ;; diff --git a/git-clone.sh b/git-clone.sh index 89c15d7..823c74b 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -9,7 +9,7 @@ unset CDPATH usage() { - echo >&2 "Usage: $0 [--bare] [-l [-s]] [-q] [-u <upload-pack>] [-o <name>] [-n] <repo> [<dir>]" + echo >&2 "Usage: $0 [--use-separate-remote] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [--origin <name>] [-n] <repo> [<dir>]" exit 1 } @@ -40,22 +40,74 @@ Perhaps git-update-server-info needs to be run there?" do name=`expr "$refname" : 'refs/\(.*\)'` && case "$name" in - *^*) ;; - *) - git-http-fetch -v -a -w "$name" "$name" "$1/" || exit 1 + *^*) continue;; esac + if test -n "$use_separate_remote" && + branch_name=`expr "$name" : 'heads/\(.*\)'` + then + tname="remotes/$origin/$branch_name" + else + tname=$name + fi + git-http-fetch -v -a -w "$tname" "$name" "$1/" || exit 1 done <"$clone_tmp/refs" rm -fr "$clone_tmp" + http_fetch "$1/HEAD" "$GIT_DIR/REMOTE_HEAD" +} + +# Read git-fetch-pack -k output and store the remote branches. +copy_refs=' +use File::Path qw(mkpath); +use File::Basename qw(dirname); +my $git_dir = $ARGV[0]; +my $use_separate_remote = $ARGV[1]; +my $origin = $ARGV[2]; + +my $branch_top = ($use_separate_remote ? "remotes/$origin" : "heads"); +my $tag_top = "tags"; + +sub store { + my ($sha1, $name, $top) = @_; + $name = "$git_dir/refs/$top/$name"; + mkpath(dirname($name)); + open O, ">", "$name"; + print O "$sha1\n"; + close O; } +open FH, "<", "$git_dir/CLONE_HEAD"; +while (<FH>) { + my ($sha1, $name) = /^([0-9a-f]{40})\s(.*)$/; + next if ($name =~ /\^\173/); + if ($name eq "HEAD") { + open O, ">", "$git_dir/REMOTE_HEAD"; + print O "$sha1\n"; + close O; + next; + } + if ($name =~ s/^refs\/heads\///) { + store($sha1, $name, $branch_top); + next; + } + if ($name =~ s/^refs\/tags\///) { + store($sha1, $name, $tag_top); + next; + } +} +close FH; +' + quiet= +local=no use_local=no local_shared=no no_checkout= upload_pack= bare= -origin=origin +reference= +origin= origin_override= +use_separate_remote= while case "$#,$1" in 0,*) break ;; @@ -68,14 +120,27 @@ while *,-s|*,--s|*,--sh|*,--sha|*,--shar|*,--share|*,--shared) local_shared=yes; use_local=yes ;; *,-q|*,--quiet) quiet=-q ;; - 1,-o) usage;; - *,-o) - git-check-ref-format "$2" || { + *,--use-separate-remote) + use_separate_remote=t ;; + 1,--reference) usage ;; + *,--reference) + shift; reference="$1" ;; + *,--reference=*) + reference=`expr "$1" : '--reference=\(.*\)'` ;; + *,-o|*,--or|*,--ori|*,--orig|*,--origi|*,--origin) + case "$2" in + '') + usage ;; + */*) + echo >&2 "'$2' is not suitable for an origin name" + exit 1 + esac + git-check-ref-format "heads/$2" || { echo >&2 "'$2' is not suitable for a branch name" exit 1 } test -z "$origin_override" || { - echo >&2 "Do not give more than one -o options." + echo >&2 "Do not give more than one --origin options." exit 1 } origin_override=yes @@ -92,21 +157,36 @@ do shift done +repo="$1" +if test -z "$repo" +then + echo >&2 'you must specify a repository to clone.' + exit 1 +fi + # --bare implies --no-checkout if test yes = "$bare" then if test yes = "$origin_override" then - echo >&2 '--bare and -o $origin options are incompatible.' + echo >&2 '--bare and --origin $origin options are incompatible.' + exit 1 + fi + if test t = "$use_separate_remote" + then + echo >&2 '--bare and --use-separate-remote options are incompatible.' exit 1 fi no_checkout=yes fi +if test -z "$origin" +then + origin=origin +fi + # Turn the source into an absolute path if # it is local -repo="$1" -local=no if base=$(get_repo_base "$repo"); then repo="$base" local=yes @@ -130,6 +210,28 @@ yes) GIT_DIR="$D/.git" ;; esac +if test -n "$reference" +then + if test -d "$reference" + then + if test -d "$reference/.git/objects" + then + reference="$reference/.git" + fi + reference=$(cd "$reference" && pwd) + echo "$reference/objects" >"$GIT_DIR/objects/info/alternates" + (cd "$reference" && tar cf - refs) | + (cd "$GIT_DIR/refs" && + mkdir reference-tmp && + cd reference-tmp && + tar xf -) + else + echo >&2 "$reference: not a local directory." && usage + fi +fi + +rm -f "$GIT_DIR/CLONE_HEAD" + # We do local magic only when the user tells us to. case "$local,$use_local" in yes,yes) @@ -154,7 +256,7 @@ yes,yes) fi && rm -f "$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" @@ -165,24 +267,14 @@ yes,yes) } >"$GIT_DIR/objects/info/alternates" ;; esac - - # Make a duplicate of refs and HEAD pointer - HEAD= - if test -f "$repo/HEAD" - then - HEAD=HEAD - fi - (cd "$repo" && tar cf - refs $HEAD) | - (cd "$GIT_DIR" && tar xf -) || exit 1 + git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD" ;; *) case "$repo" in rsync://*) rsync $quiet -av --ignore-existing \ - --exclude info "$repo/objects/" "$GIT_DIR/objects/" && - rsync $quiet -av --ignore-existing \ - --exclude info "$repo/refs/" "$GIT_DIR/refs/" || exit - + --exclude info "$repo/objects/" "$GIT_DIR/objects/" || + exit # Look at objects/info/alternates for rsync -- http will # support it natively and git native ones will do it on the # remote end. Not having that file is not a crime. @@ -205,6 +297,7 @@ yes,yes) done rm -f "$GIT_DIR/TMP_ALT" fi + git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD" ;; http://*) if test -z "@@NO_CURL@@" @@ -217,38 +310,89 @@ yes,yes) ;; *) cd "$D" && case "$upload_pack" in - '') git-clone-pack $quiet "$repo" ;; - *) git-clone-pack $quiet "$upload_pack" "$repo" ;; - esac || { - echo >&2 "clone-pack from '$repo' failed." + '') git-fetch-pack --all -k $quiet "$repo" ;; + *) git-fetch-pack --all -k $quiet "$upload_pack" "$repo" ;; + esac >"$GIT_DIR/CLONE_HEAD" || { + echo >&2 "fetch-pack from '$repo' failed." exit 1 } ;; esac ;; esac +test -d "$GIT_DIR/refs/reference-tmp" && rm -fr "$GIT_DIR/refs/reference-tmp" + +if test -f "$GIT_DIR/CLONE_HEAD" +then + # Figure out where the remote HEAD points at. + perl -e "$copy_refs" "$GIT_DIR" "$use_separate_remote" "$origin" +fi cd "$D" || exit -if test -f "$GIT_DIR/HEAD" && test -z "$bare" +if test -z "$bare" && test -f "$GIT_DIR/REMOTE_HEAD" then - head_points_at=`git-symbolic-ref HEAD` + head_sha1=`cat "$GIT_DIR/REMOTE_HEAD"` + # Figure out which remote branch HEAD points at. + case "$use_separate_remote" in + '') remote_top=refs/heads ;; + *) remote_top="refs/remotes/$origin" ;; + esac + + # What to use to track the remote primary branch + if test -n "$use_separate_remote" + then + origin_tracking="remotes/$origin/master" + else + origin_tracking="heads/$origin" + fi + + # The name under $remote_top the remote HEAD seems to point at + head_points_at=$( + ( + echo "master" + cd "$GIT_DIR/$remote_top" && + find . -type f -print | sed -e 's/^\.\///' + ) | ( + done=f + while read name + do + test t = $done && continue + branch_tip=`cat "$GIT_DIR/$remote_top/$name"` + if test "$head_sha1" = "$branch_tip" + then + echo "$name" + done=t + fi + done + ) + ) + + # Write out remotes/$origin file. case "$head_points_at" in - refs/heads/*) - head_points_at=`expr "$head_points_at" : 'refs/heads/\(.*\)'` + ?*) mkdir -p "$GIT_DIR/remotes" && - echo >"$GIT_DIR/remotes/origin" \ + echo >"$GIT_DIR/remotes/$origin" \ "URL: $repo -Pull: $head_points_at:$origin" && - git-update-ref "refs/heads/$origin" $(git-rev-parse HEAD) && - (cd "$GIT_DIR" && find "refs/heads" -type f -print) | - while read ref +Pull: refs/heads/$head_points_at:refs/$origin_tracking" && + case "$use_separate_remote" in + t) git-update-ref HEAD "$head_sha1" ;; + *) git-update-ref "refs/heads/$origin" $(git-rev-parse HEAD) ;; + esac && + (cd "$GIT_DIR/$remote_top" && find . -type f -print) | + while read dotslref do - head=`expr "$ref" : 'refs/heads/\(.*\)'` && - test "$head_points_at" = "$head" || - test "$origin" = "$head" || - echo "Pull: ${head}:${head}" - done >>"$GIT_DIR/remotes/origin" + name=`expr "$dotslref" : './\(.*\)'` && + test "$head_points_at" = "$name" || + test "$origin" = "$name" || + echo "Pull: refs/heads/${name}:$remote_top/${name}" + done >>"$GIT_DIR/remotes/$origin" && + case "$use_separate_remote" in + t) + rm -f "refs/remotes/$origin/HEAD" + git-symbolic-ref "refs/remotes/$origin/HEAD" \ + "refs/remotes/$origin/$head_points_at" + esac esac case "$no_checkout" in @@ -256,6 +400,7 @@ Pull: $head_points_at:$origin" && git-read-tree -m -u -v HEAD HEAD esac fi +rm -f "$GIT_DIR/CLONE_HEAD" "$GIT_DIR/REMOTE_HEAD" trap - exit diff --git a/git-commit.sh b/git-commit.sh index 59551d9..1e7c09e 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>) [--amend] [-e] [--author <author>] [[-i | -o] <path>...]' SUBDIRECTORY_OK=Yes . git-sh-setup @@ -64,6 +64,22 @@ run_status () { # We always show status for the whole tree. cd "$TOP" + IS_INITIAL="$initial_commit" + REFERENCE=HEAD + case "$amend" in + t) + # If we are amending the initial commit, there + # is no HEAD^1. + if git-rev-parse --verify "HEAD^1" >/dev/null 2>&1 + then + REFERENCE="HEAD^1" + IS_INITIAL= + else + IS_INITIAL=t + fi + ;; + esac + # If TMP_INDEX is defined, that means we are doing # "--only" partial commit, and that index file is used # to build the tree for the commit. Otherwise, if @@ -85,10 +101,10 @@ run_status () { *) echo "# On branch $branch" ;; esac - if test -z "$initial_commit" + if test -z "$IS_INITIAL" then git-diff-index -M --cached --name-status \ - --diff-filter=MDTCRA HEAD | + --diff-filter=MDTCRA $REFERENCE | sed -e ' s/\\/\\\\/g s/ /\\ /g @@ -145,9 +161,9 @@ run_status () { } ' - if test -n "$verbose" + if test -n "$verbose" -a -z "$IS_INITIAL" then - git-diff-index --cached -M -p --diff-filter=MDTCRA HEAD + git-diff-index --cached -M -p --diff-filter=MDTCRA $REFERENCE fi case "$committable" in 0) @@ -173,6 +189,7 @@ also= only= logfile= use_commit= +amend= no_edit= log_given= log_message= @@ -180,6 +197,7 @@ verify=t verbose= signoff= force_author= +only_include_assumed= while case "$#" in 0) break;; esac do case "$1" in @@ -253,6 +271,12 @@ do verify= shift ;; + --a|--am|--ame|--amen|--amend) + amend=t + log_given=t$log_given + use_commit=HEAD + shift + ;; -c) case "$#" in 1) usage ;; esac shift @@ -327,6 +351,15 @@ done ################################################################ # Sanity check options +case "$amend,$initial_commit" in +t,t) + die "You do not have anything to amend." ;; +t,) + if [ -f "$GIT_DIR/MERGE_HEAD" ]; then + die "You are in the middle of a merge -- cannot amend." + fi ;; +esac + case "$log_given" in tt*) die "Only one of -c/-C/-F/-m can be used." ;; @@ -340,15 +373,8 @@ case "$#,$also$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 +409,8 @@ t,) ;; ,t) save_index && + git-ls-files --error-unmatch -- "$@" >/dev/null || exit + git-diff-files --name-only -z -- "$@" | ( cd "$TOP" @@ -411,7 +439,7 @@ 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 -- "$@"` || exit # Build the temporary index and update the real index # the same way. @@ -563,17 +591,25 @@ if test -z "$initial_commit" then if [ -f "$GIT_DIR/MERGE_HEAD" ]; then PARENTS="-p HEAD "`sed -e 's/^/-p /' "$GIT_DIR/MERGE_HEAD"` + elif test -n "$amend"; then + PARENTS=$(git-cat-file commit HEAD | + sed -n -e '/^$/q' -e 's/^parent /-p /p') fi + current=$(git-rev-parse --verify HEAD) else if [ -z "$(git-ls-files)" ]; then echo >&2 Nothing to commit exit 1 fi PARENTS="" + current= fi -run_status >>"$GIT_DIR"/COMMIT_EDITMSG -if [ "$?" != "0" -a ! -f "$GIT_DIR/MERGE_HEAD" ] +{ + test -z "$only_include_assumed" || echo "$only_include_assumed" + run_status +} >>"$GIT_DIR"/COMMIT_EDITMSG +if [ "$?" != "0" -a ! -f "$GIT_DIR/MERGE_HEAD" -a -z "$amend" ] then rm -f "$GIT_DIR/COMMIT_EDITMSG" run_status diff --git a/git-compat-util.h b/git-compat-util.h index f982b8e..5d543d2 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -9,6 +9,8 @@ #endif #endif +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + #include <unistd.h> #include <stdio.h> #include <sys/stat.h> diff --git a/git-cvsimport.perl b/git-cvsimport.perl index 24f9834..c0ae00b 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -452,8 +452,8 @@ chdir($git_tree); my $last_branch = ""; my $orig_branch = ""; -my $forward_master = 0; my %branch_date; +my $tip_at_start = undef; my $git_dir = $ENV{"GIT_DIR"} || ".git"; $git_dir = getwd()."/".$git_dir unless $git_dir =~ m#^/#; @@ -488,21 +488,7 @@ unless(-d $git_dir) { $last_branch = "master"; } $orig_branch = $last_branch; - if (-f "$git_dir/CVS2GIT_HEAD") { - die <<EOM; -CVS2GIT_HEAD exists. -Make sure your working directory corresponds to HEAD and remove CVS2GIT_HEAD. -You may need to run - - git read-tree -m -u CVS2GIT_HEAD HEAD -EOM - } - system('cp', "$git_dir/HEAD", "$git_dir/CVS2GIT_HEAD"); - - $forward_master = - $opt_o ne 'master' && -f "$git_dir/refs/heads/master" && - system('cmp', '-s', "$git_dir/refs/heads/master", - "$git_dir/refs/heads/$opt_o") == 0; + $tip_at_start = `git-rev-parse --verify HEAD`; # populate index system('git-read-tree', $last_branch); @@ -691,11 +677,7 @@ my $commit = sub { waitpid($pid,0); die "Error running git-commit-tree: $?\n" if $?; - open(C,">$git_dir/refs/heads/$branch") - or die "Cannot open branch $branch for update: $!\n"; - print C "$cid\n" - or die "Cannot write branch $branch for update: $!\n"; - close(C) + system("git-update-ref refs/heads/$branch $cid") == 0 or die "Cannot write branch $branch for update: $!\n"; if($tag) { @@ -846,8 +828,12 @@ 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; @@ -885,17 +871,26 @@ if (defined $orig_git_index) { # Now switch back to the branch we were in before all of this happened if($orig_branch) { - print "DONE\n" if $opt_v; - system("cp","$git_dir/refs/heads/$opt_o","$git_dir/refs/heads/master") - if $forward_master; - unless ($opt_i) { - system('git-read-tree', '-m', '-u', 'CVS2GIT_HEAD', 'HEAD'); - die "read-tree failed: $?\n" if $?; + print "DONE.\n" if $opt_v; + if ($opt_i) { + exit 0; + } + my $tip_at_end = `git-rev-parse --verify HEAD`; + if ($tip_at_start ne $tip_at_end) { + for ($tip_at_start, $tip_at_end) { chomp; } + print "Fetched into the current branch.\n" if $opt_v; + system(qw(git-read-tree -u -m), + $tip_at_start, $tip_at_end); + die "Fast-forward update failed: $?\n" if $?; + } + else { + system(qw(git-merge cvsimport HEAD), "refs/heads/$opt_o"); + die "Could not merge $opt_o into the current branch.\n" if $?; } } else { $orig_branch = "master"; print "DONE; creating $orig_branch branch\n" if $opt_v; - system("cp","$git_dir/refs/heads/$opt_o","$git_dir/refs/heads/master") + system("git-update-ref", "refs/heads/master", "refs/heads/$opt_o") unless -f "$git_dir/refs/heads/master"; system('git-update-ref', 'HEAD', "$orig_branch"); unless ($opt_i) { @@ -903,4 +898,3 @@ if($orig_branch) { die "checkout failed: $?\n" if $?; } } -unlink("$git_dir/CVS2GIT_HEAD"); diff --git a/git-cvsserver.perl b/git-cvsserver.perl new file mode 100755 index 0000000..7d3f78e --- /dev/null +++ b/git-cvsserver.perl @@ -0,0 +1,2616 @@ +#!/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'"); + +# if we are called with a pserver argument, +# deal with the authentication cat before entereing the +# main loop +if (@ARGV && $ARGV[0] eq 'pserver') { + my $line = <STDIN>; chomp $line; + unless( $line eq 'BEGIN AUTH REQUEST') { + die "E Do not understand $line - expecting BEGIN AUTH REQUEST\n"; + } + $line = <STDIN>; chomp $line; + req_Root('root', $line) # reuse Root + or die "E Invalid root $line \n"; + $line = <STDIN>; chomp $line; + unless ($line eq 'anonymous') { + print "E Only anonymous user allowed via pserver\n"; + print "I HATE YOU\n"; + } + $line = <STDIN>; chomp $line; # validate the password? + $line = <STDIN>; chomp $line; + unless ($line eq 'END AUTH REQUEST') { + die "E Do not understand $line -- expecting END AUTH REQUEST\n"; + } + print "I LOVE YOU\n"; + # and now back to our regular programme... +} + +# Keep going until the client closes the connection +while (<STDIN>) +{ + chomp; + + # Check to see if we've seen this method, and call appropiate function. + if ( /^([\w-]+)(?:\s+(.*))?$/ 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} . "/"; + unless (-d $ENV{GIT_DIR} && -e $ENV{GIT_DIR}.'HEAD') { + print "E $ENV{GIT_DIR} does not seem to be a valid GIT repository\n"; + print "E \n"; + print "error 1 $ENV{GIT_DIR} is not a valid repository\n"; + return 0; + } + + my @gitvars = `git-var -l`; + if ($?) { + print "E problems executing git-var on the server -- this is not a git repository or the PATH is not set correcly.\n"; + print "E \n"; + print "error 1 - problem executing git-var\n"; + return 0; + } + foreach my $line ( @gitvars ) + { + 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"; + return 0; + } + + if ( defined ( $cfg->{gitcvs}{logfile} ) ) + { + $log->setfile($cfg->{gitcvs}{logfile}); + } else { + $log->nofile(); + } + + return 1; +} + +# 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(); + + $checkout_path =~ s|/$||; # get rid of trailing slashes + + # Eclipse seems to need the Clear-sticky command + # to prepare the 'Entries' file for the new directory. + print "Clear-sticky $checkout_path/\n"; + print $state->{CVSROOT} . "/$module/\n"; + print "Clear-static-directory $checkout_path/\n"; + print $state->{CVSROOT} . "/$module/\n"; + print "Clear-sticky $checkout_path/\n"; # yes, twice + print $state->{CVSROOT} . "/$module/\n"; + print "Template $checkout_path/\n"; + print $state->{CVSROOT} . "/$module/\n"; + print "0\n"; + + # instruct the client that we're checking out to $checkout_path + print "E cvs checkout: Updating $checkout_path\n"; + + my %seendirs = (); + my $lastdir =''; + + # recursive + sub prepdir { + my ($dir, $repodir, $remotedir, $seendirs) = @_; + my $parent = dirname($dir); + $dir =~ s|/+$||; + $repodir =~ s|/+$||; + $remotedir =~ s|/+$||; + $parent =~ s|/+$||; + $log->debug("announcedir $dir, $repodir, $remotedir" ); + + if ($parent eq '.' || $parent eq './') { + $parent = ''; + } + # recurse to announce unseen parents first + if (length($parent) && !exists($seendirs->{$parent})) { + prepdir($parent, $repodir, $remotedir, $seendirs); + } + # Announce that we are going to modify at the parent level + if ($parent) { + print "E cvs checkout: Updating $remotedir/$parent\n"; + } else { + print "E cvs checkout: Updating $remotedir\n"; + } + print "Clear-sticky $remotedir/$parent/\n"; + print "$repodir/$parent/\n"; + + print "Clear-static-directory $remotedir/$dir/\n"; + print "$repodir/$dir/\n"; + print "Clear-sticky $remotedir/$parent/\n"; # yes, twice + print "$repodir/$parent/\n"; + print "Template $remotedir/$dir/\n"; + print "$repodir/$dir/\n"; + print "0\n"; + + $seendirs->{$dir} = 1; + } + + 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}); + + if (length($git->{dir}) && $git->{dir} ne './' + && $git->{dir} ne $lastdir ) { + unless (exists($seendirs{$git->{dir}})) { + prepdir($git->{dir}, $state->{CVSROOT} . "/$module/", + $checkout_path, \%seendirs); + $lastdir = $git->{dir}; + $seendirs{$git->{dir}} = 1; + } + print "E cvs checkout: Updating /$checkout_path/$git->{dir}\n"; + } + + # modification time of this file + print "Mod-time $git->{modified}\n"; + + # print some information to the client + if ( defined ( $git->{dir} ) and $git->{dir} ne "./" ) + { + print "M U $checkout_path/$git->{dir}$git->{name}\n"; + } else { + print "M U $checkout_path/$git->{name}\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 the working copy and repo copy have the same revision, + # but the working copy is modified, tell the client it's modified + if ( defined ( $wrev ) + and defined($meta->{revision}) + and $wrev == $meta->{revision} + and not exists ( $state->{opt}{C} ) ) + { + $log->info("Tell the client the file is modified"); + print "MT text U\n"; + print "MT fname $filename\n"; + print "MT newline\n"; + next; + } + + 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 { + $log->info("Updating '$filename'"); + 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 ( @ARGV && $ARGV[0] eq 'pserver') + { + print "error 1 pserver access cannot commit\n"; + exit; + } + + 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 ORDER BY name ASC",{},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-diff.sh b/git-diff.sh index dc4d1b3..dc0dd31 100755 --- a/git-diff.sh +++ b/git-diff.sh @@ -38,9 +38,9 @@ case " $flags " in flags="$flags'$cc_or_p' " ;; esac -# If we do not have -B nor -C, default to -M. +# If we do not have -B, -C, -r, nor -p, default to -M. case " $flags " in -*" '-"[BCM]* | *" '--find-copies-harder' "*) +*" '-"[BCMrp]* | *" '--find-copies-harder' "*) ;; # something like -M50. *) flags="$flags'-M' " ;; diff --git a/git-fetch.sh b/git-fetch.sh index fcc24f8..954901d 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -94,6 +94,9 @@ append_fetch_head () { # remote-nick is the URL given on the command line (or a shorthand) # remote-name is the $GIT_DIR relative refs/ path we computed # for this refspec. + + # the $note_ variable will be fed to git-fmt-merge-msg for further + # processing. case "$remote_name_" in HEAD) note_= ;; @@ -103,6 +106,9 @@ append_fetch_head () { refs/tags/*) note_="$(expr "$remote_name_" : 'refs/tags/\(.*\)')" note_="tag '$note_' of " ;; + refs/remotes/*) + note_="$(expr "$remote_name_" : 'refs/remotes/\(.*\)')" + note_="remote branch '$note_' of " ;; *) note_="$remote_name of " ;; esac @@ -147,10 +153,10 @@ fast_forward_local () { else echo >&2 "* $1: storing $3" fi - git-update-ref "$1" "$2" + git-update-ref "$1" "$2" ;; - refs/heads/*) + refs/heads/* | refs/remotes/*) # $1 is the ref being updated. # $2 is the new value for the ref. local=$(git-rev-parse --verify "$1^0" 2>/dev/null) @@ -164,6 +170,7 @@ fast_forward_local () { ;; *,$local) echo >&2 "* $1: fast forward to $3" + echo >&2 " from $local to $2" git-update-ref "$1" "$2" "$local" ;; *) @@ -178,6 +185,7 @@ fast_forward_local () { ;; *) echo >&2 " not updating." + exit 1 ;; esac } @@ -320,7 +328,7 @@ 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 0467a38..5986e54 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 --no-merges --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; } @@ -82,6 +75,7 @@ while (<>) { $src{$src} = { BRANCH => [], TAG => [], + R_BRANCH => [], GENERIC => [], # &1 == has HEAD. # &2 == has others. @@ -98,6 +92,11 @@ while (<>) { push @{$src{$src}{TAG}}, $1; $src{$src}{HEAD_STATUS} |= 2; } + elsif (/^remote branch (.*)$/) { + $origin = $1; + push @{$src{$src}{R_BRANCH}}, $1; + $src{$src}{HEAD_STATUS} |= 2; + } elsif (/^HEAD$/) { $origin = $src; $src{$src}{HEAD_STATUS} |= 1; @@ -130,6 +129,8 @@ for my $src (@src) { } push @this, andjoin("branch ", "branches ", $src{$src}{BRANCH}); + push @this, andjoin("remote branch ", "remote branches ", + $src{$src}{R_BRANCH}); push @this, andjoin("tag ", "tags ", $src{$src}{TAG}); push @this, andjoin("commit ", "commits ", @@ -140,7 +141,10 @@ 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 +155,7 @@ 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* $name: (" . scalar(@log) . " commits)\n"; } diff --git a/git-format-patch.sh b/git-format-patch.sh index eb75de4..2ebf7e8 100755 --- a/git-format-patch.sh +++ b/git-format-patch.sh @@ -3,7 +3,7 @@ # Copyright (c) 2005 Junio C Hamano # -USAGE='[-n | -k] [-o <dir> | --stdout] [--signoff] [--check] [--diff-options] <his> [<mine>]' +USAGE='[-n | -k] [-o <dir> | --stdout] [--signoff] [--check] [--diff-options] [--attach] <his> [<mine>]' LONG_USAGE='Prepare each commit with its patch since <mine> head forked from <his> head, one file per patch formatted to resemble UNIX mailbox format, for e-mail submission or use with git-am. @@ -18,7 +18,9 @@ is ignored if --stdout is specified. When -n is specified, instead of "[PATCH] Subject", the first line is formatted as "[PATCH N/M] Subject", unless you have only -one patch.' +one patch. + +When --attach is specified, patches are attached, not inlined.' . git-sh-setup @@ -40,6 +42,8 @@ do -d|--d|--da|--dat|--date|\ -m|--m|--mb|--mbo|--mbox) # now noop ;; + --at|--att|--atta|--attac|--attach) + attach=t ;; -k|--k|--ke|--kee|--keep|--keep-|--keep-s|--keep-su|--keep-sub|\ --keep-subj|--keep-subje|--keep-subjec|--keep-subject) keep_subject=t ;; @@ -149,6 +153,12 @@ do done >$series me=`git-var GIT_AUTHOR_IDENT | sed -e 's/>.*/>/'` +headers=`git-repo-config --get format.headers` +case "$attach" in +"") ;; +*) + mimemagic="050802040500080604070107" +esac case "$outdir" in */) ;; @@ -173,8 +183,8 @@ titleScript=' process_one () { perl -w -e ' -my ($keep_subject, $num, $signoff, $commsg) = @ARGV; -my ($signoff_pattern, $done_header, $done_subject, $signoff_seen, +my ($keep_subject, $num, $signoff, $headers, $mimemagic, $commsg) = @ARGV; +my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen, $last_was_signoff); if ($signoff) { @@ -224,10 +234,28 @@ while (<FH>) { s/^\[PATCH[^]]*\]\s*//; s/^/[PATCH$num] /; } + if ($headers) { + print "$headers\n"; + } print "Subject: $_"; + if ($mimemagic) { + print "MIME-Version: 1.0\n"; + print "Content-Type: multipart/mixed;\n"; + print " boundary=\"------------$mimemagic\"\n"; + print "\n"; + print "This is a multi-part message in MIME format.\n"; + print "--------------$mimemagic\n"; + print "Content-Type: text/plain; charset=UTF-8; format=fixed\n"; + print "Content-Transfer-Encoding: 8bit\n"; + } $done_subject = 1; next; } + unless ($done_separator) { + print "\n"; + $done_separator = 1; + next if (/^$/); + } $last_was_signoff = 0; if (/Signed-off-by:/i) { @@ -245,14 +273,33 @@ if (!$signoff_seen && $signoff ne "") { } print "\n---\n\n"; close FH or die "close $commsg pipe"; -' "$keep_subject" "$num" "$signoff" $commsg +' "$keep_subject" "$num" "$signoff" "$headers" "$mimemagic" $commsg git-diff-tree -p $diff_opts "$commit" | git-apply --stat --summary echo + case "$mimemagic" in + '');; + *) + echo "--------------$mimemagic" + echo "Content-Type: text/x-patch;" + echo " name=\"$commit.diff\"" + echo "Content-Transfer-Encoding: 8bit" + echo "Content-Disposition: inline;" + echo " filename=\"$commit.diff\"" + echo + esac git-diff-tree -p $diff_opts "$commit" - echo "-- " - echo "@@GIT_VERSION@@" - + case "$mimemagic" in + '') + echo "-- " + echo "@@GIT_VERSION@@" + ;; + *) + echo + echo "--------------$mimemagic--" + echo + ;; + esac echo } diff --git a/git-ls-remote.sh b/git-ls-remote.sh index 2c9a588..b6882a9 100755 --- a/git-ls-remote.sh +++ b/git-ls-remote.sh @@ -53,7 +53,7 @@ http://* | https://* ) if [ -n "$GIT_SSL_NO_VERIFY" ]; then curl_extra_args="-k" fi - curl -nsf $curl_extra_args "$peek_repo/info/refs" || + curl -nsf $curl_extra_args --header "Pragma: no-cache" "$peek_repo/info/refs" || echo "failed slurping" ;; diff --git a/git-merge.sh b/git-merge.sh index c258ea7..78ab422 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -11,9 +11,17 @@ LF=' ' all_strategies='recursive octopus resolve stupid ours' -default_strategies='recursive' +default_twohead_strategies='recursive' +default_octopus_strategies='octopus' +no_trivial_merge_strategies='ours' use_strategies= +index_merge=t +if test "@@NO_PYTHON@@"; then + all_strategies='resolve octopus stupid ours' + default_twohead_strategies='resolve' +fi + dropsave() { rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" \ "$GIT_DIR/MERGE_SAVE" || exit 1 @@ -86,8 +94,6 @@ do shift done -test "$#" -le 2 && usage ;# we need at least two heads. - merge_msg="$1" shift head_arg="$1" @@ -95,6 +101,8 @@ head=$(git-rev-parse --verify "$1"^0) || usage shift # All the rest are remote heads +test "$#" = 0 && usage ;# we need at least one remote head. + remoteheads= for remote do @@ -104,6 +112,27 @@ do done set x $remoteheads ; shift +case "$use_strategies" in +'') + case "$#" in + 1) + use_strategies="$default_twohead_strategies" ;; + *) + use_strategies="$default_octopus_strategies" ;; + esac + ;; +esac + +for s in $use_strategies +do + case " $s " in + *" $no_trivial_merge_strategies "*) + index_merge=f + break + ;; + esac +done + case "$#" in 1) common=$(git-merge-base --all $head "$@") @@ -114,20 +143,23 @@ case "$#" in esac echo "$head" >"$GIT_DIR/ORIG_HEAD" -case "$#,$common,$no_commit" in -*,'',*) +case "$index_merge,$#,$common,$no_commit" in +f,*) + # We've been told not to try anything clever. Skip to real merge. + ;; +?,*,'',*) # No common ancestors found. We need a real merge. ;; -1,"$1",*) +?,1,"$1",*) # If head can reach all the merge then we are up to date. - # but first the most common case of merging one remote + # but first the most common case of merging one remote. echo "Already up-to-date." dropsave exit 0 ;; -1,"$head",*) +?,1,"$head",*) # Again the most common case of merging one remote. - echo "Updating from $head to $1." + echo "Updating from $head to $1" git-update-index --refresh 2>/dev/null new_head=$(git-rev-parse --verify "$1^0") && git-read-tree -u -v -m $head "$new_head" && @@ -135,11 +167,11 @@ case "$#,$common,$no_commit" in dropsave exit 0 ;; -1,?*"$LF"?*,*) +?,1,?*"$LF"?*,*) # We are not doing octopus and not fast forward. Need a # real merge. ;; -1,*,) +?,1,*,) # We are not doing octopus, not fast forward, and have only # one common. See if it is really trivial. git var GIT_COMMITTER_IDENT >/dev/null || exit @@ -184,17 +216,6 @@ esac # We are going to make a new commit. git var GIT_COMMITTER_IDENT >/dev/null || exit -case "$use_strategies" in -'') - case "$#" in - 1) - use_strategies="$default_strategies" ;; - *) - use_strategies=octopus ;; - esac - ;; -esac - # At this point, we need a real merge. No matter what strategy # we use, it would operate on the index, possibly affecting the # working tree, and when resolved cleanly, have the desired tree @@ -266,11 +287,7 @@ done # auto resolved the merge cleanly. if test '' != "$result_tree" then - parents="-p $head" - for remote - do - parents="$parents -p $remote" - done + parents=$(git-show-branch --independent "$head" "$@" | sed -e 's/^/-p /') result_commit=$(echo "$merge_msg" | git-commit-tree $result_tree $parents) || exit finish "$result_commit" "Merge $result_commit, made by $wt_strategy." dropsave diff --git a/git-mv.perl b/git-mv.perl index f3e859a..75aa8fe 100755 --- a/git-mv.perl +++ b/git-mv.perl @@ -62,9 +62,17 @@ else { $dstDir = ""; } +my $subdir_prefix = `git rev-parse --show-prefix`; +chomp($subdir_prefix); + +# run in git base directory, so that git-ls-files lists all revisioned files +chdir "$GIT_DIR/.."; + # normalize paths, needed to compare against versioned files and update-index # also, this is nicer to end-users by doing ".//a/./b/.//./c" ==> "a/b/c" for (@srcArgs, @dstArgs) { + # prepend git prefix as we run from base directory + $_ = $subdir_prefix.$_; s|^\./||; s|/\./|/| while (m|/\./|); s|//+|/|g; @@ -90,6 +98,15 @@ 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-parse-remote.sh b/git-parse-remote.sh index 5f158c6..63f2281 100755 --- a/git-parse-remote.sh +++ b/git-parse-remote.sh @@ -86,14 +86,14 @@ canon_refs_list_for_fetch () { local=$(expr "$ref" : '[^:]*:\(.*\)') case "$remote" in '') remote=HEAD ;; - refs/heads/* | refs/tags/*) ;; - heads/* | tags/* ) remote="refs/$remote" ;; + refs/heads/* | refs/tags/* | refs/remotes/*) ;; + heads/* | tags/* | remotes/* ) remote="refs/$remote" ;; *) remote="refs/heads/$remote" ;; esac case "$local" in '') local= ;; - refs/heads/* | refs/tags/*) ;; - heads/* | tags/* ) local="refs/$local" ;; + refs/heads/* | refs/tags/* | refs/remotes/*) ;; + heads/* | tags/* | remotes/* ) local="refs/$local" ;; *) local="refs/heads/$local" ;; esac diff --git a/git-pull.sh b/git-pull.sh index 6caf1aa..4611ae6 100755 --- a/git-pull.sh +++ b/git-pull.sh @@ -55,9 +55,17 @@ then # First update the working tree to match $curr_head. echo >&2 "Warning: fetch updated the current branch head." - echo >&2 "Warning: fast forwarding your working tree." + echo >&2 "Warning: fast forwarding your working tree from" + echo >&2 "Warning: $orig_head commit." + git-update-index --refresh 2>/dev/null git-read-tree -u -m "$orig_head" "$curr_head" || - die "You need to first update your working tree." + die 'Cannot fast-forward your working tree. +After making sure that you saved anything precious from +$ git diff '$orig_head' +output, run +$ git reset --hard +to recover.' + fi merge_head=$(sed -e '/ not-for-merge /d' \ @@ -70,20 +78,16 @@ case "$merge_head" in exit 0 ;; ?*' '?*) - var=`git repo-config --get pull.octopus` - if test '' = "$var" + var=`git-repo-config --get pull.octopus` + if test -n "$var" then - strategy_default_args='-s octopus' - else strategy_default_args="-s $var" fi ;; *) - var=`git repo-config --get pull.twohead` - if test '' = "$var" - then - strategy_default_args='-s recursive' - else + var=`git-repo-config --get pull.twohead` + if test -n "$var" + then strategy_default_args="-s $var" fi ;; diff --git a/git-push.sh b/git-push.sh index 706db99..f10cadb 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=--thin remote= do_tags= @@ -22,6 +23,10 @@ do has_force=--force ;; --exec=*) has_exec="$1" ;; + --thin) + ;; # noop + --no-thin) + has_thin= ;; -*) usage ;; *) @@ -72,6 +77,7 @@ set x "$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 16d4359..5956f06 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 "$upstream" ORIG_HEAD | git am --binary -3 -k diff --git a/git-repack.sh b/git-repack.sh index 3d6fec1..a5d349f 100755 --- a/git-repack.sh +++ b/git-repack.sh @@ -29,12 +29,10 @@ PACKDIR="$GIT_OBJECT_DIRECTORY/pack" case ",$all_into_one," in ,,) rev_list='--unpacked' - rev_parse='--all' pack_objects='--incremental' ;; ,t,) rev_list= - rev_parse='--all' pack_objects= # Redundancy check in all-into-one case is trivial. @@ -43,7 +41,7 @@ case ",$all_into_one," in ;; esac pack_objects="$pack_objects $local $quiet $no_reuse_delta" -name=$(git-rev-list --objects $rev_list $(git-rev-parse $rev_parse) 2>&1 | +name=$(git-rev-list --objects --all $rev_list 2>&1 | git-pack-objects --non-empty $pack_objects .tmp-pack) || exit 1 if [ -z "$name" ]; then @@ -75,6 +73,7 @@ then done ) fi + git-prune-packed fi case "$no_update_info" in diff --git a/git-rerere.perl b/git-rerere.perl index df11951..d3664ff 100755 --- a/git-rerere.perl +++ b/git-rerere.perl @@ -131,7 +131,11 @@ sub record_preimage { sub find_conflict { my $in; local $/ = "\0"; - open $in, '-|', qw(git ls-files -z -u) or die "$!: ls-files"; + my $pid = open($in, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec(qw(git ls-files -z -u)) or die "$!: ls-files"; + } my %path = (); my @path = (); while (<$in>) { diff --git a/git-resolve.sh b/git-resolve.sh index b53ede8..1c7aaef 100755 --- a/git-resolve.sh +++ b/git-resolve.sh @@ -41,7 +41,7 @@ case "$common" in exit 0 ;; "$head") - echo "Updating from $head to $merge." + echo "Updating from $head to $merge" git-read-tree -u -m $head $merge || exit 1 git-update-ref HEAD "$merge" "$head" git-diff-tree -p $head $merge | git-apply --stat diff --git a/git-revert.sh b/git-revert.sh index 2c58706..c19d3a6 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 0000000..fda4541 --- /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 $verbose -z --stdin + ;; +esac diff --git a/git-send-email.perl b/git-send-email.perl index 3f1b3ca..ecfa347 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -19,10 +19,16 @@ use strict; use warnings; use Term::ReadLine; -use Mail::Sendmail qw(sendmail %mailcfg); use Getopt::Long; use Data::Dumper; -use Email::Valid; +use Net::SMTP; + +# most mail servers generate the Date: header, but not all... +$ENV{LC_ALL} = 'C'; +use POSIX qw/strftime/; + +my $have_email_valid = eval { require Email::Valid; 1 }; +my $smtp; sub unique_email_list(@); sub cleanup_compose_files(); @@ -31,10 +37,10 @@ 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,$time); # 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 +54,40 @@ 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-by-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 +211,9 @@ 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 +229,19 @@ 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); @@ -227,6 +250,16 @@ EOT # Variables we set as part of the loop over files our ($message_id, $cc, %mail, $subject, $reply_to, $message); +sub extract_valid_address { + my $address = shift; + if ($have_email_valid) { + return Email::Valid->address($address); + } else { + # less robust/correct than the monster regexp in Email::Valid, + # but still does a 99% job, and one less dependency + return ($address =~ /([^\"<>\s]+@[^<>\s]+)/); + } +} # Usually don't need to change anything below here. @@ -236,13 +269,12 @@ our ($message_id, $cc, %mail, $subject, $reply_to, $message); # 1 second since the last time we were called. # We'll setup a template for the message id, using the "from" address: -my $message_id_from = Email::Valid->address($from); +my $message_id_from = extract_valid_address($from); my $message_id_template = "<%s-git-send-email-$message_id_from>"; sub make_message_id { - my $date = `date "+\%s"`; - chomp($date); + my $date = time; my $pseudo_rand = int (rand(4200)); $message_id = sprintf $message_id_template, "$date$pseudo_rand"; #print "new message id = $message_id\n"; # Was useful for debugging @@ -251,38 +283,49 @@ sub make_message_id $cc = ""; +$time = time - scalar $#files; sub send_message { - my $to = join (", ", unique_email_list(@to)); - - %mail = ( To => $to, - From => $from, - CC => $cc, - Subject => $subject, - Message => $message, - 'Reply-to' => $from, - 'In-Reply-To' => $reply_to, - 'Message-ID' => $message_id, - 'X-Mailer' => "git-send-email", - ); - - $mail{smtp} = $smtp_server; - $mailcfg{mime} = 0; - - #print Data::Dumper->Dump([\%mail],[qw(*mail)]); - - sendmail(%mail) or die $Mail::Sendmail::error; + my @recipients = unique_email_list(@to); + my $to = join (",\n\t", @recipients); + @recipients = unique_email_list(@recipients,@cc); + my $date = strftime('%a, %d %b %Y %H:%M:%S %z', localtime($time++)); + + my $header = "From: $from +To: $to +Cc: $cc +Subject: $subject +Reply-To: $from +Date: $date +Message-Id: $message_id +X-Mailer: git-send-email @@GIT_VERSION@@ +"; + $header .= "In-Reply-To: $reply_to\n" if $reply_to; + + $smtp ||= Net::SMTP->new( $smtp_server ); + $smtp->mail( $from ) or die $smtp->message; + $smtp->to( @recipients ) or die $smtp->message; + $smtp->data or die $smtp->message; + $smtp->datasend("$header\n$message") or die $smtp->message; + $smtp->dataend() or die $smtp->message; + $smtp->ok or die "Failed to send $subject\n".$smtp->message; if ($quiet) { printf "Sent %s\n", $subject; } else { - print "OK. Log says:\n", $Mail::Sendmail::log; - print "\n\n" + print "OK. Log says: +Date: $date +Server: $smtp_server Port: 25 +From: $from +Subject: $subject +Cc: $cc +To: $to + +Result: ", $smtp->code, ' ', ($smtp->message =~ /\n([^\n]+\n)$/s), "\n"; } } - $reply_to = $initial_reply_to; make_message_id(); $subject = $initial_subject; @@ -290,7 +333,8 @@ $subject = $initial_subject; foreach my $t (@files) { open(F,"<",$t) or die "can't open file $t"; - @cc = (); + my $author_not_sender = undef; + @cc = @initial_cc; my $found_mbox = 0; my $header_done = 0; $message = ""; @@ -304,6 +348,12 @@ foreach my $t (@files) { $subject = $1; } elsif (/^(Cc|From):\s+(.*)$/) { + if ($2 eq $from) { + next if ($suppress_from); + } + else { + $author_not_sender = $2; + } printf("(mbox) Adding cc: %s from line '%s'\n", $2, $_) unless $quiet; push @cc, $2; @@ -332,7 +382,7 @@ 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; @@ -342,6 +392,9 @@ foreach my $t (@files) { } } close F; + if (defined $author_not_sender) { + $message = "From: $author_not_sender\n\n$message"; + } $cc = join(", ", unique_email_list(@cc)); @@ -363,14 +416,14 @@ sub cleanup_compose_files() { } - +$smtp->quit if $smtp; sub unique_email_list(@) { my %seen; my @emails; foreach my $entry (@_) { - my $clean = Email::Valid->address($entry); + my $clean = extract_valid_address($entry); next if $seen{$clean}++; push @emails, $entry; } diff --git a/git-svnimport.perl b/git-svnimport.perl index f17d5a2..114784f 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"; @@ -746,7 +851,7 @@ sub commit_all { $opt_l = $svn->{'maxrev'} if not defined $opt_l or $opt_l > $svn->{'maxrev'}; -if ($svn->{'maxrev'} < $current_rev) { +if ($opt_l < $current_rev) { print "Up to date: no new revisions to fetch!\n" if $opt_v; unlink("$git_dir/SVN2GIT_HEAD"); exit; @@ -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 726b1e7..36f171b 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' | @@ -11,6 +11,11 @@ #include <sys/ioctl.h> #include "git-compat-util.h" #include "exec_cmd.h" +#include "common-cmds.h" + +#include "cache.h" +#include "commit.h" +#include "revision.h" #ifndef PATH_MAX # define PATH_MAX 4096 @@ -167,11 +172,29 @@ static void list_commands(const char *exec_path, const char *pattern) putchar('\n'); } +static void list_common_cmds_help(void) +{ + int i, longest = 0; + + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + if (longest < strlen(common_cmds[i].name)) + longest = strlen(common_cmds[i].name); + } + + puts("The most commonly used git commands are:"); + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + printf(" %s", common_cmds[i].name); + mput_char(' ', longest - strlen(common_cmds[i].name) + 4); + puts(common_cmds[i].help); + } + puts("(use 'git help -a' to get a list of all installed git commands)"); +} + #ifdef __GNUC__ -static void cmd_usage(const char *exec_path, const char *fmt, ...) - __attribute__((__format__(__printf__, 2, 3), __noreturn__)); +static void cmd_usage(int show_all, const char *exec_path, const char *fmt, ...) + __attribute__((__format__(__printf__, 3, 4), __noreturn__)); #endif -static void cmd_usage(const char *exec_path, const char *fmt, ...) +static void cmd_usage(int show_all, const char *exec_path, const char *fmt, ...) { if (fmt) { va_list ap; @@ -185,10 +208,13 @@ static void cmd_usage(const char *exec_path, const char *fmt, ...) else puts(git_usage); - putchar('\n'); - - if(exec_path) - list_commands(exec_path, "git-*"); + if (exec_path) { + putchar('\n'); + if (show_all) + list_commands(exec_path, "git-*"); + else + list_common_cmds_help(); + } exit(1); } @@ -212,80 +238,231 @@ static void prepend_to_path(const char *dir, int len) setenv("PATH", path, 1); } -static void show_man_page(char *git_cmd) +static void show_man_page(const char *git_cmd) { - char *page; + const char *page; if (!strncmp(git_cmd, "git", 3)) page = git_cmd; else { int page_len = strlen(git_cmd) + 4; - - page = malloc(page_len + 1); - strcpy(page, "git-"); - strcpy(page + 4, git_cmd); - page[page_len] = 0; + char *p = malloc(page_len + 1); + strcpy(p, "git-"); + strcpy(p + 4, git_cmd); + p[page_len] = 0; + page = p; } execlp("man", "man", page, NULL); } -int main(int argc, char **argv, char **envp) +static int cmd_version(int argc, const char **argv, char **envp) { - char git_command[PATH_MAX + 1]; - char wd[PATH_MAX + 1]; - int i, show_help = 0; - const char *exec_path; + printf("git version %s\n", GIT_VERSION); + return 0; +} - getcwd(wd, PATH_MAX); +static int cmd_help(int argc, const char **argv, char **envp) +{ + const char *help_cmd = argv[1]; + if (!help_cmd) + cmd_usage(0, git_exec_path(), NULL); + else if (!strcmp(help_cmd, "--all") || !strcmp(help_cmd, "-a")) + cmd_usage(1, git_exec_path(), NULL); + else + show_man_page(help_cmd); + return 0; +} - for (i = 1; i < argc; i++) { - char *arg = argv[i]; +#define LOGSIZE (65536) - if (!strcmp(arg, "help")) { - show_help = 1; - continue; +static int cmd_log(int argc, const char **argv, char **envp) +{ + struct rev_info rev; + struct commit *commit; + char *buf = xmalloc(LOGSIZE); + static enum cmit_fmt commit_format = CMIT_FMT_DEFAULT; + int abbrev = DEFAULT_ABBREV; + const char *commit_prefix = "commit "; + + argc = setup_revisions(argc, argv, &rev, "HEAD"); + while (1 < argc) { + const char *arg = argv[1]; + if (!strncmp(arg, "--pretty", 8)) { + commit_format = get_commit_format(arg + 8); + if (commit_format == CMIT_FMT_ONELINE) + commit_prefix = ""; } + else if (!strcmp(arg, "--no-abbrev")) { + abbrev = 0; + } + else if (!strncmp(arg, "--abbrev=", 9)) { + abbrev = strtoul(arg + 9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (40 < abbrev) + abbrev = 40; + } + else + die("unrecognized argument: %s", arg); + argc--; argv++; + } - if (strncmp(arg, "--", 2)) - break; - - arg += 2; - - 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); + prepare_revision_walk(&rev); + setup_pager(); + while ((commit = get_revision(&rev)) != NULL) { + printf("%s%s", commit_prefix, + sha1_to_hex(commit->object.sha1)); + if (rev.parents) { + struct commit_list *parents = commit->parents; + while (parents) { + struct object *o = &(parents->item->object); + parents = parents->next; + if (o->flags & TMP_MARK) + continue; + printf(" %s", sha1_to_hex(o->sha1)); + o->flags |= TMP_MARK; } + /* TMP_MARK is a general purpose flag that can + * be used locally, but the user should clean + * things up after it is done with them. + */ + for (parents = commit->parents; + parents; + parents = parents->next) + parents->item->object.flags &= ~TMP_MARK; } - else if (!strcmp(arg, "version")) { - printf("git version %s\n", GIT_VERSION); - exit(0); - } - else if (!strcmp(arg, "help")) - show_help = 1; - else if (!show_help) - cmd_usage(NULL, NULL); + if (commit_format == CMIT_FMT_ONELINE) + putchar(' '); + else + putchar('\n'); + pretty_print_commit(commit_format, commit, ~0, buf, + LOGSIZE, abbrev); + printf("%s\n", buf); + } + free(buf); + return 0; +} + +static void handle_internal_command(int argc, const char **argv, char **envp) +{ + const char *cmd = argv[0]; + static struct cmd_struct { + const char *cmd; + int (*fn)(int, const char **, char **); + } commands[] = { + { "version", cmd_version }, + { "help", cmd_help }, + { "log", cmd_log }, + }; + 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)); } +} - if (i >= argc || show_help) { - if (i >= argc) - cmd_usage(git_exec_path(), NULL); +int main(int argc, const char **argv, char **envp) +{ + const char *cmd = argv[0]; + char *slash = strrchr(cmd, '/'); + char git_command[PATH_MAX + 1]; + 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; + } - show_man_page(argv[i]); + /* + * "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); } + /* Default command: "help" */ + cmd = "help"; + + /* Look for flags.. */ + while (argc > 1) { + cmd = *++argv; + argc--; + + if (strncmp(cmd, "--", 2)) + break; + + 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; + + /* + * 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; + } + puts(git_exec_path()); + exit(0); + } + cmd_usage(0, 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 $0 + * - the regular PATH. + */ + if (exec_path) + prepend_to_path(exec_path, strlen(exec_path)); exec_path = git_exec_path(); prepend_to_path(exec_path, strlen(exec_path)); - execv_git_cmd(argv + i); + /* See if it's an internal command */ + handle_internal_command(argc, argv, envp); + + /* .. then try the external ones */ + execv_git_cmd(argv); if (errno == ENOENT) - cmd_usage(exec_path, "'%s' is not a git-command", argv[i]); + cmd_usage(0, exec_path, "'%s' is not a git-command", cmd); fprintf(stderr, "Failed to run command '%s': %s\n", git_command, strerror(errno)); @@ -34,14 +34,19 @@ proc parse_args {rargs} { proc start_rev_list {rlargs} { global startmsecs nextupdate ncmupdate - global commfd leftover tclencoding + global commfd leftover tclencoding datemode set startmsecs [clock clicks -milliseconds] set nextupdate [expr {$startmsecs + 100}] set ncmupdate 1 + initlayout + set order "--topo-order" + if {$datemode} { + set order "--date-order" + } if {[catch { - set commfd [open [concat | git-rev-list --header --topo-order \ - --parents $rlargs] r] + set commfd [open [concat | git-rev-list --header $order \ + --parents --boundary $rlargs] r] } err]} { puts stderr "Error executing git-rev-list: $err" exit 1 @@ -57,16 +62,8 @@ proc start_rev_list {rlargs} { } proc getcommits {rargs} { - global oldcommits commits phase canv mainfont env + global phase canv mainfont - # check that we can find a .git directory somewhere... - set gitdir [gitdir] - if {![file isdirectory $gitdir]} { - error_popup "Cannot find the git directory \"$gitdir\"." - exit 1 - } - set oldcommits {} - set commits {} set phase getcommits start_rev_list [parse_args $rargs] $canv delete all @@ -75,10 +72,9 @@ proc getcommits {rargs} { } proc getcommitlines {commfd} { - global oldcommits commits parents cdate children nchildren - global commitlisted phase nextupdate - global stopped redisplaying leftover - global canv + global commitlisted nextupdate + global leftover + global displayorder commitidx commitrow commitdata set stuff [read $commfd] if {$stuff == {}} { @@ -101,25 +97,33 @@ proc getcommitlines {commfd} { exit 1 } set start 0 + set gotsome 0 while 1 { set i [string first "\0" $stuff $start] if {$i < 0} { append leftover [string range $stuff $start end] - return + break } - set cmit [string range $stuff $start [expr {$i - 1}]] if {$start == 0} { - set cmit "$leftover$cmit" + set cmit $leftover + append cmit [string range $stuff 0 [expr {$i - 1}]] set leftover {} + } else { + set cmit [string range $stuff $start [expr {$i - 1}]] } set start [expr {$i + 1}] set j [string first "\n" $cmit] set ok 0 + set listed 1 if {$j >= 0} { set ids [string range $cmit 0 [expr {$j - 1}]] + if {[string range $ids 0 0] == "-"} { + set listed 0 + set ids [string range $ids 1 end] + } set ok 1 foreach id $ids { - if {![regexp {^[0-9a-f]{40}$} $id]} { + if {[string length $id] != 40} { set ok 0 break } @@ -134,29 +138,24 @@ proc getcommitlines {commfd} { exit 1 } set id [lindex $ids 0] - set olds [lrange $ids 1 end] - set cmit [string range $cmit [expr {$j + 1}] end] - lappend commits $id - set commitlisted($id) 1 - parsecommit $id $cmit 1 [lrange $ids 1 end] - drawcommit $id 1 - if {[clock clicks -milliseconds] >= $nextupdate} { - doupdate 1 - } - while {$redisplaying} { - set redisplaying 0 - if {$stopped == 1} { - set stopped 0 - set phase "getcommits" - foreach id $commits { - drawcommit $id 1 - if {$stopped} break - if {[clock clicks -milliseconds] >= $nextupdate} { - doupdate 1 - } - } - } + if {$listed} { + set olds [lrange $ids 1 end] + set commitlisted($id) 1 + } else { + set olds {} } + updatechildren $id $olds + set commitdata($id) [string range $cmit [expr {$j + 1}] end] + set commitrow($id) $commitidx + incr commitidx + lappend displayorder $id + set gotsome 1 + } + if {$gotsome} { + layoutmore + } + if {[clock clicks -milliseconds] >= $nextupdate} { + doupdate 1 } } @@ -182,106 +181,31 @@ proc doupdate {reading} { proc readcommit {id} { if {[catch {set contents [exec git-cat-file commit $id]}]} return - parsecommit $id $contents 0 {} + updatechildren $id {} + parsecommit $id $contents 0 } proc updatecommits {rargs} { - global commitlisted commfd phase - global startmsecs nextupdate ncmupdate - global idtags idheads idotherrefs - global leftover - global parsed_args - global canv mainfont - global oldcommits commits - global parents nchildren children ncleft - - set old_args $parsed_args - parse_args $rargs - - if {$phase == "getcommits" || $phase == "incrdraw"} { - # havent read all the old commits, just start again from scratch - stopfindproc - set oldcommits {} - set commits {} - foreach v {children nchildren parents commitlisted commitinfo - selectedline matchinglines treediffs - mergefilelist currentid rowtextx} { - global $v - catch {unset $v} - } - readrefs - if {$phase == "incrdraw"} { - allcanvs delete all - $canv create text 3 3 -anchor nw -text "Reading commits..." \ - -font $mainfont -tags textitems - set phase getcommits - } - start_rev_list $parsed_args - return - } - - foreach id $old_args { - if {![regexp {^[0-9a-f]{40}$} $id]} continue - if {[info exists oldref($id)]} continue - set oldref($id) $id - lappend ignoreold "^$id" - } - foreach id $parsed_args { - if {![regexp {^[0-9a-f]{40}$} $id]} continue - if {[info exists ref($id)]} continue - set ref($id) $id - lappend ignorenew "^$id" - } - - foreach a $old_args { - if {![info exists ref($a)]} { - lappend ignorenew $a - } - } - - set phase updatecommits - set oldcommits $commits - set commits {} - set removed_commits [split [eval exec git-rev-list $ignorenew] "\n" ] - if {[llength $removed_commits] > 0} { - allcanvs delete all - foreach c $removed_commits { - set i [lsearch -exact $oldcommits $c] - if {$i >= 0} { - set oldcommits [lreplace $oldcommits $i $i] - unset commitlisted($c) - foreach p $parents($c) { - if {[info exists nchildren($p)]} { - set j [lsearch -exact $children($p) $c] - if {$j >= 0} { - set children($p) [lreplace $children($p) $j $j] - incr nchildren($p) -1 - } - } - } - } - } - set phase removecommits - } - - set args {} - foreach a $parsed_args { - if {![info exists oldref($a)]} { - lappend args $a - } + stopfindproc + foreach v {children nchildren parents nparents commitlisted + colormap selectedline matchinglines treediffs + mergefilelist currentid rowtextx commitrow + rowidlist rowoffsets idrowranges idrangedrawn iddrawn + linesegends crossings cornercrossings} { + global $v + catch {unset $v} } - + allcanvs delete all readrefs - start_rev_list [concat $ignoreold $args] + getcommits $rargs } proc updatechildren {id olds} { - global children nchildren parents nparents ncleft + global children nchildren parents nparents if {![info exists nchildren($id)]} { set children($id) {} set nchildren($id) 0 - set ncleft($id) 0 } set parents($id) $olds set nparents($id) [llength $olds] @@ -289,16 +213,14 @@ proc updatechildren {id olds} { if {![info exists nchildren($p)]} { set children($p) [list $id] set nchildren($p) 1 - set ncleft($p) 1 } elseif {[lsearch -exact $children($p) $id] < 0} { lappend children($p) $id incr nchildren($p) - incr ncleft($p) } } } -proc parsecommit {id contents listed olds} { +proc parsecommit {id contents listed} { global commitinfo cdate set inhdr 1 @@ -308,7 +230,6 @@ proc parsecommit {id contents listed olds} { set audate {} set comname {} set comdate {} - updatechildren $id $olds set hdrend [string first "\n\n" $contents] if {$hdrend < 0} { # should never happen... @@ -352,6 +273,21 @@ proc parsecommit {id contents listed olds} { $comname $comdate $comment] } +proc getcommit {id} { + global commitdata commitinfo nparents + + if {[info exists commitdata($id)]} { + parsecommit $id $commitdata($id) 1 + } else { + readcommit $id + if {![info exists commitinfo($id)]} { + set commitinfo($id) {"No commit information available"} + set nparents($id) 0 + } + } + return 1 +} + proc readrefs {} { global tagids idtags headids idheads tagcontents global otherrefids idotherrefs @@ -405,6 +341,7 @@ proc error_popup msg { button $w.ok -text OK -command "destroy $w" pack $w.ok -side bottom -fill x bind $w <Visibility> "grab $w; focus $w" + bind $w <Key-Return> "destroy $w" tkwait window $w } @@ -457,7 +394,7 @@ proc makewindow {rargs} { set canv .ctop.top.clist.canv canvas $canv -height $geometry(canvh) -width $geometry(canv1) \ -bg white -bd 0 \ - -yscrollincr $linespc -yscrollcommand "$cscroll set" + -yscrollincr $linespc -yscrollcommand "scrollcanv $cscroll" .ctop.top.clist add $canv set canv2 .ctop.top.clist.canv2 canvas $canv2 -height $geometry(canvh) -width $geometry(canv2) \ @@ -575,8 +512,8 @@ proc makewindow {rargs} { #bindall <B1-Motion> {selcanvline %W %x %y} bindall <ButtonRelease-4> "allcanvs yview scroll -5 units" bindall <ButtonRelease-5> "allcanvs yview scroll 5 units" - bindall <2> "allcanvs scan mark 0 %y" - bindall <B2-Motion> "allcanvs scan dragto 0 %y" + bindall <2> "canvscan mark %W %x %y" + bindall <B2-Motion> "canvscan dragto %W %x %y" bind . <Key-Up> "selnextline -1" bind . <Key-Down> "selnextline 1" bind . <Key-Right> "goforw" @@ -631,6 +568,24 @@ proc makewindow {rargs} { $rowctxmenu add command -label "Write commit to file" -command writecommit } +# mouse-2 makes all windows scan vertically, but only the one +# the cursor is in scans horizontally +proc canvscan {op w x y} { + global canv canv2 canv3 + foreach c [list $canv $canv2 $canv3] { + if {$c == $w} { + $c scan $op $x $y + } else { + $c scan $op 0 $y + } + } +} + +proc scrollcanv {cscroll f0 f1} { + $cscroll set $f0 $f1 + drawfrac $f0 $f1 +} + # when we make a key binding for the toplevel, make sure # it doesn't get triggered when that key is pressed in the # find string entry widget. @@ -763,9 +718,9 @@ proc about {} { toplevel $w wm title $w "About gitk" message $w.m -text { -Gitk version 1.2 +Gitk - a commit viewer for git -Copyright © 2005 Paul Mackerras +Copyright © 2005-2006 Paul Mackerras Use and redistribute under the terms of the GNU General Public License} \ -justify center -aspect 400 @@ -774,14 +729,794 @@ Use and redistribute under the terms of the GNU General Public License} \ pack $w.ok -side bottom } +proc shortids {ids} { + set res {} + foreach id $ids { + if {[llength $id] > 1} { + lappend res [shortids $id] + } elseif {[regexp {^[0-9a-f]{40}$} $id]} { + lappend res [string range $id 0 7] + } else { + lappend res $id + } + } + return $res +} + +proc incrange {l x o} { + set n [llength $l] + while {$x < $n} { + set e [lindex $l $x] + if {$e ne {}} { + lset l $x [expr {$e + $o}] + } + incr x + } + return $l +} + +proc ntimes {n o} { + set ret {} + for {} {$n > 0} {incr n -1} { + lappend ret $o + } + return $ret +} + +proc usedinrange {id l1 l2} { + global children commitrow + + if {[info exists commitrow($id)]} { + set r $commitrow($id) + if {$l1 <= $r && $r <= $l2} { + return [expr {$r - $l1 + 1}] + } + } + foreach c $children($id) { + if {[info exists commitrow($c)]} { + set r $commitrow($c) + if {$l1 <= $r && $r <= $l2} { + return [expr {$r - $l1 + 1}] + } + } + } + return 0 +} + +proc sanity {row {full 0}} { + global rowidlist rowoffsets + + set col -1 + set ids [lindex $rowidlist $row] + foreach id $ids { + incr col + if {$id eq {}} continue + if {$col < [llength $ids] - 1 && + [lsearch -exact -start [expr {$col+1}] $ids $id] >= 0} { + puts "oops: [shortids $id] repeated in row $row col $col: {[shortids [lindex $rowidlist $row]]}" + } + set o [lindex $rowoffsets $row $col] + set y $row + set x $col + while {$o ne {}} { + incr y -1 + incr x $o + if {[lindex $rowidlist $y $x] != $id} { + puts "oops: rowoffsets wrong at row [expr {$y+1}] col [expr {$x-$o}]" + puts " id=[shortids $id] check started at row $row" + for {set i $row} {$i >= $y} {incr i -1} { + puts " row $i ids={[shortids [lindex $rowidlist $i]]} offs={[lindex $rowoffsets $i]}" + } + break + } + if {!$full} break + set o [lindex $rowoffsets $y $x] + } + } +} + +proc makeuparrow {oid x y z} { + global rowidlist rowoffsets uparrowlen idrowranges + + for {set i 1} {$i < $uparrowlen && $y > 1} {incr i} { + incr y -1 + incr x $z + set off0 [lindex $rowoffsets $y] + for {set x0 $x} {1} {incr x0} { + if {$x0 >= [llength $off0]} { + set x0 [llength [lindex $rowoffsets [expr {$y-1}]]] + break + } + set z [lindex $off0 $x0] + if {$z ne {}} { + incr x0 $z + break + } + } + set z [expr {$x0 - $x}] + lset rowidlist $y [linsert [lindex $rowidlist $y] $x $oid] + lset rowoffsets $y [linsert [lindex $rowoffsets $y] $x $z] + } + set tmp [lreplace [lindex $rowoffsets $y] $x $x {}] + lset rowoffsets $y [incrange $tmp [expr {$x+1}] -1] + lappend idrowranges($oid) $y +} + +proc initlayout {} { + global rowidlist rowoffsets displayorder + global rowlaidout rowoptim + global idinlist rowchk + global commitidx numcommits canvxmax canv + global nextcolor + + set commitidx 0 + set numcommits 0 + set displayorder {} + set nextcolor 0 + set rowidlist {{}} + set rowoffsets {{}} + catch {unset idinlist} + catch {unset rowchk} + set rowlaidout 0 + set rowoptim 0 + set canvxmax [$canv cget -width] +} + +proc setcanvscroll {} { + global canv canv2 canv3 numcommits linespc canvxmax canvy0 + + set ymax [expr {$canvy0 + ($numcommits - 0.5) * $linespc + 2}] + $canv conf -scrollregion [list 0 0 $canvxmax $ymax] + $canv2 conf -scrollregion [list 0 0 0 $ymax] + $canv3 conf -scrollregion [list 0 0 0 $ymax] +} + +proc visiblerows {} { + global canv numcommits linespc + + set ymax [lindex [$canv cget -scrollregion] 3] + if {$ymax eq {} || $ymax == 0} return + set f [$canv yview] + set y0 [expr {int([lindex $f 0] * $ymax)}] + set r0 [expr {int(($y0 - 3) / $linespc) - 1}] + if {$r0 < 0} { + set r0 0 + } + set y1 [expr {int([lindex $f 1] * $ymax)}] + set r1 [expr {int(($y1 - 3) / $linespc) + 1}] + if {$r1 >= $numcommits} { + set r1 [expr {$numcommits - 1}] + } + return [list $r0 $r1] +} + +proc layoutmore {} { + global rowlaidout rowoptim commitidx numcommits optim_delay + global uparrowlen + + set row $rowlaidout + set rowlaidout [layoutrows $row $commitidx 0] + set orow [expr {$rowlaidout - $uparrowlen - 1}] + if {$orow > $rowoptim} { + checkcrossings $rowoptim $orow + optimize_rows $rowoptim 0 $orow + set rowoptim $orow + } + set canshow [expr {$rowoptim - $optim_delay}] + if {$canshow > $numcommits} { + showstuff $canshow + } +} + +proc showstuff {canshow} { + global numcommits + global linesegends idrowranges idrangedrawn + + if {$numcommits == 0} { + global phase + set phase "incrdraw" + allcanvs delete all + } + set row $numcommits + set numcommits $canshow + setcanvscroll + set rows [visiblerows] + set r0 [lindex $rows 0] + set r1 [lindex $rows 1] + for {set r $row} {$r < $canshow} {incr r} { + if {[info exists linesegends($r)]} { + foreach id $linesegends($r) { + set i -1 + foreach {s e} $idrowranges($id) { + incr i + if {$e ne {} && $e < $numcommits && $s <= $r1 && $e >= $r0 + && ![info exists idrangedrawn($id,$i)]} { + drawlineseg $id $i + set idrangedrawn($id,$i) 1 + } + } + } + } + } + if {$canshow > $r1} { + set canshow $r1 + } + while {$row < $canshow} { + drawcmitrow $row + incr row + } +} + +proc layoutrows {row endrow last} { + global rowidlist rowoffsets displayorder + global uparrowlen downarrowlen maxwidth mingaplen + global nchildren parents nparents + global idrowranges linesegends + global commitidx + global idinlist rowchk + + set idlist [lindex $rowidlist $row] + set offs [lindex $rowoffsets $row] + while {$row < $endrow} { + set id [lindex $displayorder $row] + set oldolds {} + set newolds {} + foreach p $parents($id) { + if {![info exists idinlist($p)]} { + lappend newolds $p + } elseif {!$idinlist($p)} { + lappend oldolds $p + } + } + set nev [expr {[llength $idlist] + [llength $newolds] + + [llength $oldolds] - $maxwidth + 1}] + if {$nev > 0} { + if {!$last && $row + $uparrowlen + $mingaplen >= $commitidx} break + for {set x [llength $idlist]} {[incr x -1] >= 0} {} { + set i [lindex $idlist $x] + if {![info exists rowchk($i)] || $row >= $rowchk($i)} { + set r [usedinrange $i [expr {$row - $downarrowlen}] \ + [expr {$row + $uparrowlen + $mingaplen}]] + if {$r == 0} { + set idlist [lreplace $idlist $x $x] + set offs [lreplace $offs $x $x] + set offs [incrange $offs $x 1] + set idinlist($i) 0 + set rm1 [expr {$row - 1}] + lappend linesegends($rm1) $i + lappend idrowranges($i) $rm1 + if {[incr nev -1] <= 0} break + continue + } + set rowchk($id) [expr {$row + $r}] + } + } + lset rowidlist $row $idlist + lset rowoffsets $row $offs + } + set col [lsearch -exact $idlist $id] + if {$col < 0} { + set col [llength $idlist] + lappend idlist $id + lset rowidlist $row $idlist + set z {} + if {$nchildren($id) > 0} { + set z [expr {[llength [lindex $rowidlist [expr {$row-1}]]] - $col}] + unset idinlist($id) + } + lappend offs $z + lset rowoffsets $row $offs + if {$z ne {}} { + makeuparrow $id $col $row $z + } + } else { + unset idinlist($id) + } + if {[info exists idrowranges($id)]} { + lappend idrowranges($id) $row + } + incr row + set offs [ntimes [llength $idlist] 0] + set l [llength $newolds] + set idlist [eval lreplace \$idlist $col $col $newolds] + set o 0 + if {$l != 1} { + set offs [lrange $offs 0 [expr {$col - 1}]] + foreach x $newolds { + lappend offs {} + incr o -1 + } + incr o + set tmp [expr {[llength $idlist] - [llength $offs]}] + if {$tmp > 0} { + set offs [concat $offs [ntimes $tmp $o]] + } + } else { + lset offs $col {} + } + foreach i $newolds { + set idinlist($i) 1 + set idrowranges($i) $row + } + incr col $l + foreach oid $oldolds { + set idinlist($oid) 1 + set idlist [linsert $idlist $col $oid] + set offs [linsert $offs $col $o] + makeuparrow $oid $col $row $o + incr col + } + lappend rowidlist $idlist + lappend rowoffsets $offs + } + return $row +} + +proc addextraid {id row} { + global displayorder commitrow commitinfo nparents + global commitidx + + incr commitidx + lappend displayorder $id + set commitrow($id) $row + readcommit $id + if {![info exists commitinfo($id)]} { + set commitinfo($id) {"No commit information available"} + set nparents($id) 0 + } +} + +proc layouttail {} { + global rowidlist rowoffsets idinlist commitidx + global idrowranges + + set row $commitidx + set idlist [lindex $rowidlist $row] + while {$idlist ne {}} { + set col [expr {[llength $idlist] - 1}] + set id [lindex $idlist $col] + addextraid $id $row + unset idinlist($id) + lappend idrowranges($id) $row + incr row + set offs [ntimes $col 0] + set idlist [lreplace $idlist $col $col] + lappend rowidlist $idlist + lappend rowoffsets $offs + } + + foreach id [array names idinlist] { + addextraid $id $row + lset rowidlist $row [list $id] + lset rowoffsets $row 0 + makeuparrow $id 0 $row 0 + lappend idrowranges($id) $row + incr row + lappend rowidlist {} + lappend rowoffsets {} + } +} + +proc insert_pad {row col npad} { + global rowidlist rowoffsets + + set pad [ntimes $npad {}] + lset rowidlist $row [eval linsert [list [lindex $rowidlist $row]] $col $pad] + set tmp [eval linsert [list [lindex $rowoffsets $row]] $col $pad] + lset rowoffsets $row [incrange $tmp [expr {$col + $npad}] [expr {-$npad}]] +} + +proc optimize_rows {row col endrow} { + global rowidlist rowoffsets idrowranges linesegends displayorder + + for {} {$row < $endrow} {incr row} { + set idlist [lindex $rowidlist $row] + set offs [lindex $rowoffsets $row] + set haspad 0 + for {} {$col < [llength $offs]} {incr col} { + if {[lindex $idlist $col] eq {}} { + set haspad 1 + continue + } + set z [lindex $offs $col] + if {$z eq {}} continue + set isarrow 0 + set x0 [expr {$col + $z}] + set y0 [expr {$row - 1}] + set z0 [lindex $rowoffsets $y0 $x0] + if {$z0 eq {}} { + set id [lindex $idlist $col] + if {[info exists idrowranges($id)] && + $y0 > [lindex $idrowranges($id) 0]} { + set isarrow 1 + } + } + if {$z < -1 || ($z < 0 && $isarrow)} { + set npad [expr {-1 - $z + $isarrow}] + set offs [incrange $offs $col $npad] + insert_pad $y0 $x0 $npad + if {$y0 > 0} { + optimize_rows $y0 $x0 $row + } + set z [lindex $offs $col] + set x0 [expr {$col + $z}] + set z0 [lindex $rowoffsets $y0 $x0] + } elseif {$z > 1 || ($z > 0 && $isarrow)} { + set npad [expr {$z - 1 + $isarrow}] + set y1 [expr {$row + 1}] + set offs2 [lindex $rowoffsets $y1] + set x1 -1 + foreach z $offs2 { + incr x1 + if {$z eq {} || $x1 + $z < $col} continue + if {$x1 + $z > $col} { + incr npad + } + lset rowoffsets $y1 [incrange $offs2 $x1 $npad] + break + } + set pad [ntimes $npad {}] + set idlist [eval linsert \$idlist $col $pad] + set tmp [eval linsert \$offs $col $pad] + incr col $npad + set offs [incrange $tmp $col [expr {-$npad}]] + set z [lindex $offs $col] + set haspad 1 + } + if {$z0 eq {} && !$isarrow} { + # this line links to its first child on row $row-2 + set rm2 [expr {$row - 2}] + set id [lindex $displayorder $rm2] + set xc [lsearch -exact [lindex $rowidlist $rm2] $id] + if {$xc >= 0} { + set z0 [expr {$xc - $x0}] + } + } + if {$z0 ne {} && $z < 0 && $z0 > 0} { + insert_pad $y0 $x0 1 + set offs [incrange $offs $col 1] + optimize_rows $y0 [expr {$x0 + 1}] $row + } + } + if {!$haspad} { + set o {} + for {set col [llength $idlist]} {[incr col -1] >= 0} {} { + set o [lindex $offs $col] + if {$o eq {}} { + # check if this is the link to the first child + set id [lindex $idlist $col] + if {[info exists idrowranges($id)] && + $row == [lindex $idrowranges($id) 0]} { + # it is, work out offset to child + set y0 [expr {$row - 1}] + set id [lindex $displayorder $y0] + set x0 [lsearch -exact [lindex $rowidlist $y0] $id] + if {$x0 >= 0} { + set o [expr {$x0 - $col}] + } + } + } + if {$o eq {} || $o <= 0} break + } + if {$o ne {} && [incr col] < [llength $idlist]} { + set y1 [expr {$row + 1}] + set offs2 [lindex $rowoffsets $y1] + set x1 -1 + foreach z $offs2 { + incr x1 + if {$z eq {} || $x1 + $z < $col} continue + lset rowoffsets $y1 [incrange $offs2 $x1 1] + break + } + set idlist [linsert $idlist $col {}] + set tmp [linsert $offs $col {}] + incr col + set offs [incrange $tmp $col -1] + } + } + lset rowidlist $row $idlist + lset rowoffsets $row $offs + set col 0 + } +} + +proc xc {row col} { + global canvx0 linespc + return [expr {$canvx0 + $col * $linespc}] +} + +proc yc {row} { + global canvy0 linespc + return [expr {$canvy0 + $row * $linespc}] +} + +proc linewidth {id} { + global thickerline lthickness + + set wid $lthickness + if {[info exists thickerline] && $id eq $thickerline} { + set wid [expr {2 * $lthickness}] + } + return $wid +} + +proc drawlineseg {id i} { + global rowoffsets rowidlist idrowranges + global displayorder + global canv colormap linespc + + set startrow [lindex $idrowranges($id) [expr {2 * $i}]] + set row [lindex $idrowranges($id) [expr {2 * $i + 1}]] + if {$startrow == $row} return + assigncolor $id + set coords {} + set col [lsearch -exact [lindex $rowidlist $row] $id] + if {$col < 0} { + puts "oops: drawline: id $id not on row $row" + return + } + set lasto {} + set ns 0 + while {1} { + set o [lindex $rowoffsets $row $col] + if {$o eq {}} break + if {$o ne $lasto} { + # changing direction + set x [xc $row $col] + set y [yc $row] + lappend coords $x $y + set lasto $o + } + incr col $o + incr row -1 + } + set x [xc $row $col] + set y [yc $row] + lappend coords $x $y + if {$i == 0} { + # draw the link to the first child as part of this line + incr row -1 + set child [lindex $displayorder $row] + set ccol [lsearch -exact [lindex $rowidlist $row] $child] + if {$ccol >= 0} { + set x [xc $row $ccol] + set y [yc $row] + if {$ccol < $col - 1} { + lappend coords [xc $row [expr {$col - 1}]] [yc $row] + } elseif {$ccol > $col + 1} { + lappend coords [xc $row [expr {$col + 1}]] [yc $row] + } + lappend coords $x $y + } + } + if {[llength $coords] < 4} return + set last [expr {[llength $idrowranges($id)] / 2 - 1}] + if {$i < $last} { + # This line has an arrow at the lower end: check if the arrow is + # on a diagonal segment, and if so, work around the Tk 8.4 + # refusal to draw arrows on diagonal lines. + set x0 [lindex $coords 0] + set x1 [lindex $coords 2] + if {$x0 != $x1} { + set y0 [lindex $coords 1] + set y1 [lindex $coords 3] + if {$y0 - $y1 <= 2 * $linespc && $x1 == [lindex $coords 4]} { + # we have a nearby vertical segment, just trim off the diag bit + set coords [lrange $coords 2 end] + } else { + set slope [expr {($x0 - $x1) / ($y0 - $y1)}] + set xi [expr {$x0 - $slope * $linespc / 2}] + set yi [expr {$y0 - $linespc / 2}] + set coords [lreplace $coords 0 1 $xi $y0 $xi $yi] + } + } + } + set arrow [expr {2 * ($i > 0) + ($i < $last)}] + set arrow [lindex {none first last both} $arrow] + set t [$canv create line $coords -width [linewidth $id] \ + -fill $colormap($id) -tags lines.$id -arrow $arrow] + $canv lower $t + bindline $t $id +} + +proc drawparentlinks {id row col olds} { + global rowidlist canv colormap idrowranges + + set row2 [expr {$row + 1}] + set x [xc $row $col] + set y [yc $row] + set y2 [yc $row2] + set ids [lindex $rowidlist $row2] + # rmx = right-most X coord used + set rmx 0 + foreach p $olds { + set i [lsearch -exact $ids $p] + if {$i < 0} { + puts "oops, parent $p of $id not in list" + continue + } + set x2 [xc $row2 $i] + if {$x2 > $rmx} { + set rmx $x2 + } + if {[info exists idrowranges($p)] && + $row2 == [lindex $idrowranges($p) 0] && + $row2 < [lindex $idrowranges($p) 1]} { + # drawlineseg will do this one for us + continue + } + assigncolor $p + # should handle duplicated parents here... + set coords [list $x $y] + if {$i < $col - 1} { + lappend coords [xc $row [expr {$i + 1}]] $y + } elseif {$i > $col + 1} { + lappend coords [xc $row [expr {$i - 1}]] $y + } + lappend coords $x2 $y2 + set t [$canv create line $coords -width [linewidth $p] \ + -fill $colormap($p) -tags lines.$p] + $canv lower $t + bindline $t $p + } + return $rmx +} + +proc drawlines {id} { + global colormap canv + global idrowranges idrangedrawn + global children iddrawn commitrow rowidlist + + $canv delete lines.$id + set nr [expr {[llength $idrowranges($id)] / 2}] + for {set i 0} {$i < $nr} {incr i} { + if {[info exists idrangedrawn($id,$i)]} { + drawlineseg $id $i + } + } + if {[info exists children($id)]} { + foreach child $children($id) { + if {[info exists iddrawn($child)]} { + set row $commitrow($child) + set col [lsearch -exact [lindex $rowidlist $row] $child] + if {$col >= 0} { + drawparentlinks $child $row $col [list $id] + } + } + } + } +} + +proc drawcmittext {id row col rmx} { + global linespc canv canv2 canv3 canvy0 + global commitlisted commitinfo rowidlist + global rowtextx idpos idtags idheads idotherrefs + global linehtag linentag linedtag + global mainfont namefont canvxmax + + set ofill [expr {[info exists commitlisted($id)]? "blue": "white"}] + set x [xc $row $col] + set y [yc $row] + set orad [expr {$linespc / 3}] + set t [$canv create oval [expr {$x - $orad}] [expr {$y - $orad}] \ + [expr {$x + $orad - 1}] [expr {$y + $orad - 1}] \ + -fill $ofill -outline black -width 1] + $canv raise $t + $canv bind $t <1> {selcanvline {} %x %y} + set xt [xc $row [llength [lindex $rowidlist $row]]] + if {$xt < $rmx} { + set xt $rmx + } + set rowtextx($row) $xt + set idpos($id) [list $x $xt $y] + if {[info exists idtags($id)] || [info exists idheads($id)] + || [info exists idotherrefs($id)]} { + set xt [drawtags $id $x $xt $y] + } + set headline [lindex $commitinfo($id) 0] + set name [lindex $commitinfo($id) 1] + set date [lindex $commitinfo($id) 2] + set date [formatdate $date] + set linehtag($row) [$canv create text $xt $y -anchor w \ + -text $headline -font $mainfont ] + $canv bind $linehtag($row) <Button-3> "rowmenu %X %Y $id" + set linentag($row) [$canv2 create text 3 $y -anchor w \ + -text $name -font $namefont] + set linedtag($row) [$canv3 create text 3 $y -anchor w \ + -text $date -font $mainfont] + set xr [expr {$xt + [font measure $mainfont $headline]}] + if {$xr > $canvxmax} { + set canvxmax $xr + setcanvscroll + } +} + +proc drawcmitrow {row} { + global displayorder rowidlist + global idrowranges idrangedrawn iddrawn + global commitinfo commitlisted parents numcommits + + if {$row >= $numcommits} return + foreach id [lindex $rowidlist $row] { + if {![info exists idrowranges($id)]} continue + set i -1 + foreach {s e} $idrowranges($id) { + incr i + if {$row < $s} continue + if {$e eq {}} break + if {$row <= $e} { + if {$e < $numcommits && ![info exists idrangedrawn($id,$i)]} { + drawlineseg $id $i + set idrangedrawn($id,$i) 1 + } + break + } + } + } + + set id [lindex $displayorder $row] + if {[info exists iddrawn($id)]} return + set col [lsearch -exact [lindex $rowidlist $row] $id] + if {$col < 0} { + puts "oops, row $row id $id not in list" + return + } + if {![info exists commitinfo($id)]} { + getcommit $id + } + assigncolor $id + if {[info exists commitlisted($id)] && [info exists parents($id)] + && $parents($id) ne {}} { + set rmx [drawparentlinks $id $row $col $parents($id)] + } else { + set rmx 0 + } + drawcmittext $id $row $col $rmx + set iddrawn($id) 1 +} + +proc drawfrac {f0 f1} { + global numcommits canv + global linespc + + set ymax [lindex [$canv cget -scrollregion] 3] + if {$ymax eq {} || $ymax == 0} return + set y0 [expr {int($f0 * $ymax)}] + set row [expr {int(($y0 - 3) / $linespc) - 1}] + if {$row < 0} { + set row 0 + } + set y1 [expr {int($f1 * $ymax)}] + set endrow [expr {int(($y1 - 3) / $linespc) + 1}] + if {$endrow >= $numcommits} { + set endrow [expr {$numcommits - 1}] + } + for {} {$row <= $endrow} {incr row} { + drawcmitrow $row + } +} + +proc drawvisible {} { + global canv + eval drawfrac [$canv yview] +} + +proc clear_display {} { + global iddrawn idrangedrawn + + allcanvs delete all + catch {unset iddrawn} + catch {unset idrangedrawn} +} + proc assigncolor {id} { - global colormap commcolors colors nextcolor + global colormap colors nextcolor global parents nparents children nchildren global cornercrossings crossings if {[info exists colormap($id)]} return set ncolors [llength $colors] - if {$nparents($id) <= 1 && $nchildren($id) == 1} { + if {$nchildren($id) == 1} { set child [lindex $children($id) 0] if {[info exists colormap($child)] && $nparents($child) == 1} { @@ -845,28 +1580,6 @@ proc assigncolor {id} { set colormap($id) $c } -proc initgraph {} { - global canvy canvy0 lineno numcommits nextcolor linespc - global nchildren ncleft - global displist nhyperspace - - allcanvs delete all - set nextcolor 0 - set canvy $canvy0 - set lineno -1 - set numcommits 0 - foreach v {mainline mainlinearrow sidelines colormap cornercrossings - crossings idline lineid} { - global $v - catch {unset $v} - } - foreach id [array names nchildren] { - set ncleft($id) $nchildren($id) - } - set displist {} - set nhyperspace 0 -} - proc bindline {t id} { global canv @@ -876,121 +1589,10 @@ proc bindline {t id} { $canv bind $t <Button-1> "lineclick %x %y $id 1" } -proc drawlines {id xtra delold} { - global mainline mainlinearrow sidelines lthickness colormap canv - - if {$delold} { - $canv delete lines.$id - } - if {[info exists mainline($id)]} { - set t [$canv create line $mainline($id) \ - -width [expr {($xtra + 1) * $lthickness}] \ - -fill $colormap($id) -tags lines.$id \ - -arrow $mainlinearrow($id)] - $canv lower $t - bindline $t $id - } - if {[info exists sidelines($id)]} { - foreach ls $sidelines($id) { - set coords [lindex $ls 0] - set thick [lindex $ls 1] - set arrow [lindex $ls 2] - set t [$canv create line $coords -fill $colormap($id) \ - -width [expr {($thick + $xtra) * $lthickness}] \ - -arrow $arrow -tags lines.$id] - $canv lower $t - bindline $t $id - } - } -} - -# level here is an index in displist -proc drawcommitline {level} { - global parents children nparents displist - global canv canv2 canv3 mainfont namefont canvy linespc - global lineid linehtag linentag linedtag commitinfo - global colormap numcommits currentparents dupparents - global idtags idline idheads idotherrefs - global lineno lthickness mainline mainlinearrow sidelines - global commitlisted rowtextx idpos lastuse displist - global oldnlines olddlevel olddisplist - - incr numcommits - incr lineno - set id [lindex $displist $level] - set lastuse($id) $lineno - set lineid($lineno) $id - set idline($id) $lineno - set ofill [expr {[info exists commitlisted($id)]? "blue": "white"}] - if {![info exists commitinfo($id)]} { - readcommit $id - if {![info exists commitinfo($id)]} { - set commitinfo($id) {"No commit information available"} - set nparents($id) 0 - } - } - assigncolor $id - set currentparents {} - set dupparents {} - if {[info exists commitlisted($id)] && [info exists parents($id)]} { - foreach p $parents($id) { - if {[lsearch -exact $currentparents $p] < 0} { - lappend currentparents $p - } else { - # remember that this parent was listed twice - lappend dupparents $p - } - } - } - set x [xcoord $level $level $lineno] - set y1 $canvy - set canvy [expr {$canvy + $linespc}] - allcanvs conf -scrollregion \ - [list 0 0 0 [expr {$y1 + 0.5 * $linespc + 2}]] - if {[info exists mainline($id)]} { - lappend mainline($id) $x $y1 - if {$mainlinearrow($id) ne "none"} { - set mainline($id) [trimdiagstart $mainline($id)] - } - } - drawlines $id 0 0 - set orad [expr {$linespc / 3}] - set t [$canv create oval [expr {$x - $orad}] [expr {$y1 - $orad}] \ - [expr {$x + $orad - 1}] [expr {$y1 + $orad - 1}] \ - -fill $ofill -outline black -width 1] - $canv raise $t - $canv bind $t <1> {selcanvline {} %x %y} - set xt [xcoord [llength $displist] $level $lineno] - if {[llength $currentparents] > 2} { - set xt [expr {$xt + ([llength $currentparents] - 2) * $linespc}] - } - set rowtextx($lineno) $xt - set idpos($id) [list $x $xt $y1] - if {[info exists idtags($id)] || [info exists idheads($id)] - || [info exists idotherrefs($id)]} { - set xt [drawtags $id $x $xt $y1] - } - set headline [lindex $commitinfo($id) 0] - set name [lindex $commitinfo($id) 1] - set date [lindex $commitinfo($id) 2] - set date [formatdate $date] - set linehtag($lineno) [$canv create text $xt $y1 -anchor w \ - -text $headline -font $mainfont ] - $canv bind $linehtag($lineno) <Button-3> "rowmenu %X %Y $id" - set linentag($lineno) [$canv2 create text 3 $y1 -anchor w \ - -text $name -font $namefont] - set linedtag($lineno) [$canv3 create text 3 $y1 -anchor w \ - -text $date -font $mainfont] - - set olddlevel $level - set olddisplist $displist - set oldnlines [llength $displist] -} - proc drawtags {id x xt y1} { global idtags idheads idotherrefs global linespc lthickness - global canv mainfont idline rowtextx + global canv mainfont commitrow rowtextx set marks {} set ntags 0 @@ -1033,7 +1635,7 @@ proc drawtags {id x xt y1} { $xr $yt $xr $yb $xl $yb $x [expr {$yb - $delta}] \ -width 1 -outline black -fill yellow -tags tag.$id] $canv bind $t <1> [list showtag $tag 1] - set rowtextx($idline($id)) [expr {$xr + $linespc}] + set rowtextx($commitrow($id)) [expr {$xr + $linespc}] } else { # draw a head or other ref if {[incr nheads -1] >= 0} { @@ -1054,11 +1656,32 @@ proc drawtags {id x xt y1} { return $xt } -proc notecrossings {id lo hi corner} { - global olddisplist crossings cornercrossings +proc checkcrossings {row endrow} { + global displayorder parents rowidlist + + for {} {$row < $endrow} {incr row} { + set id [lindex $displayorder $row] + set i [lsearch -exact [lindex $rowidlist $row] $id] + if {$i < 0} continue + set idlist [lindex $rowidlist [expr {$row+1}]] + foreach p $parents($id) { + set j [lsearch -exact $idlist $p] + if {$j > 0} { + if {$j < $i - 1} { + notecrossings $row $p $j $i [expr {$j+1}] + } elseif {$j > $i + 1} { + notecrossings $row $p $i $j [expr {$j-1}] + } + } + } + } +} + +proc notecrossings {row id lo hi corner} { + global rowidlist crossings cornercrossings for {set i $lo} {[incr i] < $hi} {} { - set p [lindex $olddisplist $i] + set p [lindex [lindex $rowidlist $row] $i] if {$p == {}} continue if {$i == $corner} { if {![info exists cornercrossings($id)] @@ -1094,512 +1717,23 @@ proc xcoord {i level ln} { return $x } -# it seems Tk can't draw arrows on the end of diagonal line segments... -proc trimdiagend {line} { - while {[llength $line] > 4} { - set x1 [lindex $line end-3] - set y1 [lindex $line end-2] - set x2 [lindex $line end-1] - set y2 [lindex $line end] - if {($x1 == $x2) != ($y1 == $y2)} break - set line [lreplace $line end-1 end] - } - return $line -} - -proc trimdiagstart {line} { - while {[llength $line] > 4} { - set x1 [lindex $line 0] - set y1 [lindex $line 1] - set x2 [lindex $line 2] - set y2 [lindex $line 3] - if {($x1 == $x2) != ($y1 == $y2)} break - set line [lreplace $line 0 1] - } - return $line -} - -proc drawslants {id needonscreen nohs} { - global canv mainline mainlinearrow sidelines - global canvx0 canvy xspc1 xspc2 lthickness - global currentparents dupparents - global lthickness linespc canvy colormap lineno geometry - global maxgraphpct maxwidth - global displist onscreen lastuse - global parents commitlisted - global oldnlines olddlevel olddisplist - global nhyperspace numcommits nnewparents - - if {$lineno < 0} { - lappend displist $id - set onscreen($id) 1 - return 0 - } - - set y1 [expr {$canvy - $linespc}] - set y2 $canvy - - # work out what we need to get back on screen - set reins {} - if {$onscreen($id) < 0} { - # next to do isn't displayed, better get it on screen... - lappend reins [list $id 0] - } - # make sure all the previous commits's parents are on the screen - foreach p $currentparents { - if {$onscreen($p) < 0} { - lappend reins [list $p 0] - } - } - # bring back anything requested by caller - if {$needonscreen ne {}} { - lappend reins $needonscreen - } - - # try the shortcut - if {$currentparents == $id && $onscreen($id) == 0 && $reins eq {}} { - set dlevel $olddlevel - set x [xcoord $dlevel $dlevel $lineno] - set mainline($id) [list $x $y1] - set mainlinearrow($id) none - set lastuse($id) $lineno - set displist [lreplace $displist $dlevel $dlevel $id] - set onscreen($id) 1 - set xspc1([expr {$lineno + 1}]) $xspc1($lineno) - return $dlevel - } - - # update displist - set displist [lreplace $displist $olddlevel $olddlevel] - set j $olddlevel - foreach p $currentparents { - set lastuse($p) $lineno - if {$onscreen($p) == 0} { - set displist [linsert $displist $j $p] - set onscreen($p) 1 - incr j - } - } - if {$onscreen($id) == 0} { - lappend displist $id - set onscreen($id) 1 - } - - # remove the null entry if present - set nullentry [lsearch -exact $displist {}] - if {$nullentry >= 0} { - set displist [lreplace $displist $nullentry $nullentry] - } - - # bring back the ones we need now (if we did it earlier - # it would change displist and invalidate olddlevel) - foreach pi $reins { - # test again in case of duplicates in reins - set p [lindex $pi 0] - if {$onscreen($p) < 0} { - set onscreen($p) 1 - set lastuse($p) $lineno - set displist [linsert $displist [lindex $pi 1] $p] - incr nhyperspace -1 - } - } - - set lastuse($id) $lineno - - # see if we need to make any lines jump off into hyperspace - set displ [llength $displist] - if {$displ > $maxwidth} { - set ages {} - foreach x $displist { - lappend ages [list $lastuse($x) $x] - } - set ages [lsort -integer -index 0 $ages] - set k 0 - while {$displ > $maxwidth} { - set use [lindex $ages $k 0] - set victim [lindex $ages $k 1] - if {$use >= $lineno - 5} break - incr k - if {[lsearch -exact $nohs $victim] >= 0} continue - set i [lsearch -exact $displist $victim] - set displist [lreplace $displist $i $i] - set onscreen($victim) -1 - incr nhyperspace - incr displ -1 - if {$i < $nullentry} { - incr nullentry -1 - } - set x [lindex $mainline($victim) end-1] - lappend mainline($victim) $x $y1 - set line [trimdiagend $mainline($victim)] - set arrow "last" - if {$mainlinearrow($victim) ne "none"} { - set line [trimdiagstart $line] - set arrow "both" - } - lappend sidelines($victim) [list $line 1 $arrow] - unset mainline($victim) - } - } - - set dlevel [lsearch -exact $displist $id] - - # If we are reducing, put in a null entry - if {$displ < $oldnlines} { - # does the next line look like a merge? - # i.e. does it have > 1 new parent? - if {$nnewparents($id) > 1} { - set i [expr {$dlevel + 1}] - } elseif {$nnewparents([lindex $olddisplist $olddlevel]) == 0} { - set i $olddlevel - if {$nullentry >= 0 && $nullentry < $i} { - incr i -1 - } - } elseif {$nullentry >= 0} { - set i $nullentry - while {$i < $displ - && [lindex $olddisplist $i] == [lindex $displist $i]} { - incr i - } - } else { - set i $olddlevel - if {$dlevel >= $i} { - incr i - } - } - if {$i < $displ} { - set displist [linsert $displist $i {}] - incr displ - if {$dlevel >= $i} { - incr dlevel - } - } - } - - # decide on the line spacing for the next line - set lj [expr {$lineno + 1}] - set maxw [expr {$maxgraphpct * $geometry(canv1) / 100}] - if {$displ <= 1 || $canvx0 + $displ * $xspc2 <= $maxw} { - set xspc1($lj) $xspc2 - } else { - set xspc1($lj) [expr {($maxw - $canvx0 - $xspc2) / ($displ - 1)}] - if {$xspc1($lj) < $lthickness} { - set xspc1($lj) $lthickness - } - } - - foreach idi $reins { - set id [lindex $idi 0] - set j [lsearch -exact $displist $id] - set xj [xcoord $j $dlevel $lj] - set mainline($id) [list $xj $y2] - set mainlinearrow($id) first - } - - set i -1 - foreach id $olddisplist { - incr i - if {$id == {}} continue - if {$onscreen($id) <= 0} continue - set xi [xcoord $i $olddlevel $lineno] - if {$i == $olddlevel} { - foreach p $currentparents { - set j [lsearch -exact $displist $p] - set coords [list $xi $y1] - set xj [xcoord $j $dlevel $lj] - if {$xj < $xi - $linespc} { - lappend coords [expr {$xj + $linespc}] $y1 - notecrossings $p $j $i [expr {$j + 1}] - } elseif {$xj > $xi + $linespc} { - lappend coords [expr {$xj - $linespc}] $y1 - notecrossings $p $i $j [expr {$j - 1}] - } - if {[lsearch -exact $dupparents $p] >= 0} { - # draw a double-width line to indicate the doubled parent - lappend coords $xj $y2 - lappend sidelines($p) [list $coords 2 none] - if {![info exists mainline($p)]} { - set mainline($p) [list $xj $y2] - set mainlinearrow($p) none - } - } else { - # normal case, no parent duplicated - set yb $y2 - set dx [expr {abs($xi - $xj)}] - if {0 && $dx < $linespc} { - set yb [expr {$y1 + $dx}] - } - if {![info exists mainline($p)]} { - if {$xi != $xj} { - lappend coords $xj $yb - } - set mainline($p) $coords - set mainlinearrow($p) none - } else { - lappend coords $xj $yb - if {$yb < $y2} { - lappend coords $xj $y2 - } - lappend sidelines($p) [list $coords 1 none] - } - } - } - } else { - set j $i - if {[lindex $displist $i] != $id} { - set j [lsearch -exact $displist $id] - } - if {$j != $i || $xspc1($lineno) != $xspc1($lj) - || ($olddlevel < $i && $i < $dlevel) - || ($dlevel < $i && $i < $olddlevel)} { - set xj [xcoord $j $dlevel $lj] - lappend mainline($id) $xi $y1 $xj $y2 - } - } - } - return $dlevel -} - -# search for x in a list of lists -proc llsearch {llist x} { - set i 0 - foreach l $llist { - if {$l == $x || [lsearch -exact $l $x] >= 0} { - return $i - } - incr i - } - return -1 -} - -proc drawmore {reading} { - global displayorder numcommits ncmupdate nextupdate - global stopped nhyperspace parents commitlisted - global maxwidth onscreen displist currentparents olddlevel - - set n [llength $displayorder] - while {$numcommits < $n} { - set id [lindex $displayorder $numcommits] - set ctxend [expr {$numcommits + 10}] - if {!$reading && $ctxend > $n} { - set ctxend $n - } - set dlist {} - if {$numcommits > 0} { - set dlist [lreplace $displist $olddlevel $olddlevel] - set i $olddlevel - foreach p $currentparents { - if {$onscreen($p) == 0} { - set dlist [linsert $dlist $i $p] - incr i - } - } - } - set nohs {} - set reins {} - set isfat [expr {[llength $dlist] > $maxwidth}] - if {$nhyperspace > 0 || $isfat} { - if {$ctxend > $n} break - # work out what to bring back and - # what we want to don't want to send into hyperspace - set room 1 - for {set k $numcommits} {$k < $ctxend} {incr k} { - set x [lindex $displayorder $k] - set i [llsearch $dlist $x] - if {$i < 0} { - set i [llength $dlist] - lappend dlist $x - } - if {[lsearch -exact $nohs $x] < 0} { - lappend nohs $x - } - if {$reins eq {} && $onscreen($x) < 0 && $room} { - set reins [list $x $i] - } - set newp {} - if {[info exists commitlisted($x)]} { - set right 0 - foreach p $parents($x) { - if {[llsearch $dlist $p] < 0} { - lappend newp $p - if {[lsearch -exact $nohs $p] < 0} { - lappend nohs $p - } - if {$reins eq {} && $onscreen($p) < 0 && $room} { - set reins [list $p [expr {$i + $right}]] - } - } - set right 1 - } - } - set l [lindex $dlist $i] - if {[llength $l] == 1} { - set l $newp - } else { - set j [lsearch -exact $l $x] - set l [concat [lreplace $l $j $j] $newp] - } - set dlist [lreplace $dlist $i $i $l] - if {$room && $isfat && [llength $newp] <= 1} { - set room 0 - } - } - } - - set dlevel [drawslants $id $reins $nohs] - drawcommitline $dlevel - if {[clock clicks -milliseconds] >= $nextupdate - && $numcommits >= $ncmupdate} { - doupdate $reading - if {$stopped} break - } - } -} - -# level here is an index in todo -proc updatetodo {level noshortcut} { - global ncleft todo nnewparents - global commitlisted parents onscreen - - set id [lindex $todo $level] - set olds {} - if {[info exists commitlisted($id)]} { - foreach p $parents($id) { - if {[lsearch -exact $olds $p] < 0} { - lappend olds $p - } - } - } - if {!$noshortcut && [llength $olds] == 1} { - set p [lindex $olds 0] - if {$ncleft($p) == 1 && [lsearch -exact $todo $p] < 0} { - set ncleft($p) 0 - set todo [lreplace $todo $level $level $p] - set onscreen($p) 0 - set nnewparents($id) 1 - return 0 - } - } - - set todo [lreplace $todo $level $level] - set i $level - set n 0 - foreach p $olds { - incr ncleft($p) -1 - set k [lsearch -exact $todo $p] - if {$k < 0} { - set todo [linsert $todo $i $p] - set onscreen($p) 0 - incr i - incr n - } - } - set nnewparents($id) $n - - return 1 -} - -proc decidenext {{noread 0}} { - global ncleft todo - global datemode cdate - global commitinfo - - # choose which one to do next time around - set todol [llength $todo] - set level -1 - set latest {} - for {set k $todol} {[incr k -1] >= 0} {} { - set p [lindex $todo $k] - if {$ncleft($p) == 0} { - if {$datemode} { - if {![info exists commitinfo($p)]} { - if {$noread} { - return {} - } - readcommit $p - } - if {$latest == {} || $cdate($p) > $latest} { - set level $k - set latest $cdate($p) - } - } else { - set level $k - break - } - } - } - - return $level -} - -proc drawcommit {id reading} { - global phase todo nchildren datemode nextupdate revlistorder ncleft - global numcommits ncmupdate displayorder todo onscreen parents - global commitlisted commitordered - - if {$phase != "incrdraw"} { - set phase incrdraw - set displayorder {} - set todo {} - initgraph - catch {unset commitordered} - } - set commitordered($id) 1 - if {$nchildren($id) == 0} { - lappend todo $id - set onscreen($id) 0 - } - if {$revlistorder} { - set level [lsearch -exact $todo $id] - if {$level < 0} { - error_popup "oops, $id isn't in todo" - return - } - lappend displayorder $id - updatetodo $level 0 - } else { - set level [decidenext 1] - if {$level == {} || $level < 0} return - while 1 { - set id [lindex $todo $level] - if {![info exists commitordered($id)]} { - break - } - lappend displayorder [lindex $todo $level] - if {[updatetodo $level $datemode]} { - set level [decidenext 1] - if {$level == {} || $level < 0} break - } - } - } - drawmore $reading -} - proc finishcommits {} { - global phase oldcommits commits + global commitidx phase global canv mainfont ctext maincursor textcursor - global parents displayorder todo + global findinprogress - if {$phase == "incrdraw" || $phase == "removecommits"} { - foreach id $oldcommits { - lappend commits $id - drawcommit $id 0 - } - set oldcommits {} + if {$commitidx > 0} { drawrest - } elseif {$phase == "updatecommits"} { - # there were no new commits, in fact - set commits $oldcommits - set oldcommits {} - set phase {} } else { $canv delete all $canv create text 3 3 -anchor nw -text "No commits selected" \ -font $mainfont -tags textitems - set phase {} } - . config -cursor $maincursor - settextcursor $textcursor + if {![info exists findinprogress]} { + . config -cursor $maincursor + settextcursor $textcursor + } + set phase {} } # Don't change the text pane cursor if it is currently the hand cursor, @@ -1613,61 +1747,20 @@ proc settextcursor {c} { set curtextcursor $c } -proc drawgraph {} { - global nextupdate startmsecs ncmupdate - global displayorder onscreen - - if {$displayorder == {}} return - set startmsecs [clock clicks -milliseconds] - set nextupdate [expr {$startmsecs + 100}] - set ncmupdate 1 - initgraph - foreach id $displayorder { - set onscreen($id) 0 - } - drawmore 0 -} - proc drawrest {} { - global phase stopped redisplaying selectedline - global datemode todo displayorder ncleft - global numcommits ncmupdate - global nextupdate startmsecs revlistorder + global numcommits + global startmsecs + global canvy0 numcommits linespc + global rowlaidout commitidx - set level [decidenext] - if {$level >= 0} { - set phase drawgraph - while 1 { - lappend displayorder [lindex $todo $level] - set hard [updatetodo $level $datemode] - if {$hard} { - set level [decidenext] - if {$level < 0} break - } - } - } - if {$todo != {}} { - puts "ERROR: none of the pending commits can be done yet:" - foreach p $todo { - puts " $p ($ncleft($p))" - } - } + set row $rowlaidout + layoutrows $rowlaidout $commitidx 1 + layouttail + optimize_rows $row 0 $commitidx + showstuff $commitidx - drawmore 0 - set phase {} set drawmsecs [expr {[clock clicks -milliseconds] - $startmsecs}] #puts "overall $drawmsecs ms for $numcommits commits" - if {$redisplaying} { - if {$stopped == 0 && [info exists selectedline]} { - selectline $selectedline 0 - } - if {$stopped == 1} { - set stopped 0 - after idle drawgraph - } else { - set redisplaying 0 - } - } } proc findmatches {f} { @@ -1692,9 +1785,10 @@ proc findmatches {f} { proc dofind {} { global findtype findloc findstring markedmatches commitinfo - global numcommits lineid linehtag linentag linedtag + global numcommits displayorder linehtag linentag linedtag global mainfont namefont canv canv2 canv3 selectedline - global matchinglines foundstring foundstrlen + global matchinglines foundstring foundstrlen matchstring + global commitdata stopfindproc unmarkmatches @@ -1711,6 +1805,8 @@ proc dofind {} { } set foundstrlen [string length $findstring] if {$foundstrlen == 0} return + regsub -all {[*?\[\\]} $foundstring {\\&} matchstring + set matchstring "*$matchstring*" if {$findloc == "Files"} { findfiles return @@ -1722,8 +1818,21 @@ proc dofind {} { } set didsel 0 set fldtypes {Headline Author Date Committer CDate Comment} - for {set l 0} {$l < $numcommits} {incr l} { - set id $lineid($l) + set l -1 + foreach id $displayorder { + set d $commitdata($id) + incr l + if {$findtype == "Regexp"} { + set doesmatch [regexp $foundstring $d] + } elseif {$findtype == "IgnCase"} { + set doesmatch [string match -nocase $matchstring $d] + } else { + set doesmatch [string match $matchstring $d] + } + if {!$doesmatch} continue + if {![info exists commitinfo($id)]} { + getcommit $id + } set info $commitinfo($id) set doesmatch 0 foreach f $info ty $fldtypes { @@ -1734,10 +1843,13 @@ proc dofind {} { if {$matches == {}} continue set doesmatch 1 if {$ty == "Headline"} { + drawcmitrow $l markmatches $canv $l $f $linehtag($l) $matches $mainfont } elseif {$ty == "Author"} { + drawcmitrow $l markmatches $canv2 $l $f $linentag($l) $matches $namefont } elseif {$ty == "Date"} { + drawcmitrow $l markmatches $canv3 $l $f $linedtag($l) $matches $mainfont } } @@ -1845,7 +1957,7 @@ proc stopfindproc {{done 0}} { proc findpatches {} { global findstring selectedline numcommits global findprocpid findprocfile - global finddidsel ctext lineid findinprogress + global finddidsel ctext displayorder findinprogress global findinsertpos if {$numcommits == 0} return @@ -1862,7 +1974,7 @@ proc findpatches {} { if {[incr l] >= $numcommits} { set l 0 } - append inputids $lineid($l) "\n" + append inputids [lindex $displayorder $l] "\n" } if {[catch { @@ -1886,7 +1998,7 @@ proc findpatches {} { proc readfindproc {} { global findprocfile finddidsel - global idline matchinglines findinsertpos + global commitrow matchinglines findinsertpos set n [gets $findprocfile line] if {$n < 0} { @@ -1903,11 +2015,11 @@ proc readfindproc {} { stopfindproc return } - if {![info exists idline($id)]} { + if {![info exists commitrow($id)]} { puts stderr "spurious id: $id" return } - set l $idline($id) + set l $commitrow($id) insertmatch $l $id } @@ -1933,10 +2045,10 @@ proc insertmatch {l id} { } proc findfiles {} { - global selectedline numcommits lineid ctext + global selectedline numcommits displayorder ctext global ffileline finddidsel parents nparents global findinprogress findstartline findinsertpos - global treediffs fdiffids fdiffsneeded fdiffpos + global treediffs fdiffid fdiffsneeded fdiffpos global findmergefiles if {$numcommits == 0} return @@ -1951,13 +2063,11 @@ proc findfiles {} { set diffsneeded {} set fdiffsneeded {} while 1 { - set id $lineid($l) + set id [lindex $displayorder $l] if {$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 +2084,7 @@ 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] @@ -1982,17 +2092,16 @@ proc findfiles {} { set finddidsel 0 set findinsertpos end - set id $lineid($l) - set p [lindex $parents($id) 0] + set id [lindex $displayorder $l] . 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 +2111,19 @@ 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 +2131,50 @@ 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 displayorder 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 +2183,13 @@ 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 [lindex $displayorder $l] } stopfindproc if {!$finddidsel} { @@ -2102,8 +2200,9 @@ proc findcont {ids} { # mark a commit as matching by putting a yellow background # behind the headline proc markheadline {l id} { - global canv mainfont linehtag commitinfo + global canv mainfont linehtag + drawcmitrow $l set bbox [$canv bbox $linehtag($l)] set t [$canv create rect $bbox -outline {} -tags matches -fill yellow] $canv lower $t @@ -2137,7 +2236,7 @@ proc unmarkmatches {} { proc selcanvline {w x y} { global canv canvy0 ctext linespc - global lineid linehtag linentag linedtag rowtextx + global rowtextx set ymax [lindex [$canv cget -scrollregion] 3] if {$ymax == {}} return set yfrac [lindex [$canv yview] 0] @@ -2165,7 +2264,7 @@ proc commit_descriptor {p} { # append some text to the ctext widget, and make any SHA1 ID # that we know about be a clickable link. proc appendwithlinks {text} { - global ctext idline linknum + global ctext commitrow linknum set start [$ctext index "end - 1c"] $ctext insert end $text @@ -2175,11 +2274,11 @@ proc appendwithlinks {text} { set s [lindex $l 0] set e [lindex $l 1] set linkid [string range $text $s $e] - if {![info exists idline($linkid)]} continue + if {![info exists commitrow($linkid)]} continue incr e $ctext tag add link "$start + $s c" "$start + $e c" $ctext tag add link$linknum "$start + $s c" "$start + $e c" - $ctext tag bind link$linknum <1> [list selectline $idline($linkid) 1] + $ctext tag bind link$linknum <1> [list selectline $commitrow($linkid) 1] incr linknum } $ctext tag conf link -foreground blue -underline 1 @@ -2189,27 +2288,15 @@ proc appendwithlinks {text} { proc selectline {l isnew} { global canv canv2 canv3 ctext commitinfo selectedline - global lineid linehtag linentag linedtag + global displayorder linehtag linentag linedtag global canvy0 linespc parents nparents children global cflist currentid sha1entry - global commentend idtags idline linknum - global mergemax + global commentend idtags linknum + global mergemax numcommits $canv delete hover normalline - if {![info exists lineid($l)] || ![info exists linehtag($l)]} return - $canv delete secsel - set t [eval $canv create rect [$canv bbox $linehtag($l)] -outline {{}} \ - -tags secsel -fill [$canv cget -selectbackground]] - $canv lower $t - $canv2 delete secsel - set t [eval $canv2 create rect [$canv2 bbox $linentag($l)] -outline {{}} \ - -tags secsel -fill [$canv2 cget -selectbackground]] - $canv2 lower $t - $canv3 delete secsel - set t [eval $canv3 create rect [$canv3 bbox $linedtag($l)] -outline {{}} \ - -tags secsel -fill [$canv3 cget -selectbackground]] - $canv3 lower $t + if {$l < 0 || $l >= $numcommits} return set y [expr {$canvy0 + $l * $linespc}] set ymax [lindex [$canv cget -scrollregion] 3] set ytop [expr {$y - $linespc - 1}] @@ -2243,15 +2330,30 @@ proc selectline {l isnew} { set newtop 0 } allcanvs yview moveto [expr {$newtop * 1.0 / $ymax}] + drawvisible } + if {![info exists linehtag($l)]} return + $canv delete secsel + set t [eval $canv create rect [$canv bbox $linehtag($l)] -outline {{}} \ + -tags secsel -fill [$canv cget -selectbackground]] + $canv lower $t + $canv2 delete secsel + set t [eval $canv2 create rect [$canv2 bbox $linentag($l)] -outline {{}} \ + -tags secsel -fill [$canv2 cget -selectbackground]] + $canv2 lower $t + $canv3 delete secsel + set t [eval $canv3 create rect [$canv3 bbox $linedtag($l)] -outline {{}} \ + -tags secsel -fill [$canv3 cget -selectbackground]] + $canv3 lower $t + if {$isnew} { addtohistory [list selectline $l 0] } set selectedline $l - set id $lineid($l) + set id [lindex $displayorder $l] set currentid $id $sha1entry delete 0 end $sha1entry insert 0 $id @@ -2315,9 +2417,9 @@ proc selectline {l isnew} { $cflist delete 0 end $cflist insert end "Comments" - if {$nparents($id) == 1} { + if {$nparents($id) <= 1} { startdiff $id - } elseif {$nparents($id) > 1} { + } else { mergediff $id } } @@ -2389,9 +2491,10 @@ proc goforw {} { proc mergediff {id} { global parents diffmergeid diffopts mdifffd - global difffilestart + global difffilestart diffids set diffmergeid $id + set diffids $id catch {unset difffilestart} # this doesn't seem to actually affect anything... set env(GIT_DIFF_OPTS) $diffopts @@ -2408,7 +2511,7 @@ proc mergediff {id} { proc getmergediffline {mdf id} { global diffmergeid ctext cflist nextupdate nparents mergemax - global difffilestart + global difffilestart mdifffd set n [gets $mdf line] if {$n < 0} { @@ -2417,7 +2520,8 @@ proc getmergediffline {mdf id} { } return } - if {![info exists diffmergeid] || $id != $diffmergeid} { + if {![info exists diffmergeid] || $id != $diffmergeid + || $mdf != $mdifffd($id)} { return } $ctext conf -state normal @@ -2527,13 +2631,11 @@ proc gettreediffline {gdtf ids} { set treediffs($ids) $treediff unset treepending if {$ids != $diffids} { - gettreediffs $diffids - } else { - if {[info exists diffmergeid]} { - contmergediff $ids - } else { - addtocflist $ids + if {![info exists diffmergeid]} { + gettreediffs $diffids } + } else { + addtocflist $ids } return } @@ -2609,7 +2711,9 @@ proc getblobdiffline {bdf ids} { set pad [string range "----------------------------------------" 1 $l] $ctext insert end "$pad $header $pad\n" filesep set diffinhdr 1 - } elseif {[regexp {^(---|\+\+\+)} $line]} { + } elseif {$diffinhdr && [string compare -length 3 $line "---"] == 0} { + # do nothing + } elseif {$diffinhdr && [string compare -length 3 $line "+++"] == 0} { set diffinhdr 0 } elseif {[regexp {^@@ -([0-9]+),([0-9]+) \+([0-9]+),([0-9]+) @@(.*)} \ $line match f1l f1c f2l f2c rest]} { @@ -2676,22 +2780,26 @@ proc setcoords {} { set linespc [font metrics $mainfont -linespace] set charspc [font measure $mainfont "m"] - set canvy0 [expr {3 + 0.5 * $linespc}] - set canvx0 [expr {3 + 0.5 * $linespc}] + set canvy0 [expr {int(3 + 0.5 * $linespc)}] + set canvx0 [expr {int(3 + 0.5 * $linespc)}] set lthickness [expr {int($linespc / 9) + 1}] set xspc1(0) $linespc set xspc2 $linespc } proc redisplay {} { - global stopped redisplaying phase - if {$stopped > 1} return - if {$phase == "getcommits"} return - set redisplaying 1 - if {$phase == "drawgraph" || $phase == "incrdraw"} { - set stopped 1 - } else { - drawgraph + global canv + global selectedline + + set ymax [lindex [$canv cget -scrollregion] 3] + if {$ymax eq {} || $ymax == 0} return + set span [$canv yview] + clear_display + setcanvscroll + allcanvs yview moveto [lindex $span 0] + drawvisible + if {[info exists selectedline]} { + selectline $selectedline 0 } } @@ -2738,8 +2846,8 @@ proc sha1change {n1 n2 op} { } proc gotocommit {} { - global sha1string currentid idline tagids - global lineid numcommits + global sha1string currentid commitrow tagids + global displayorder numcommits if {$sha1string == {} || ([info exists currentid] && $sha1string == $currentid)} return @@ -2749,9 +2857,9 @@ proc gotocommit {} { set id [string tolower $sha1string] if {[regexp {^[0-9a-f]{4,39}$} $id]} { set matches {} - for {set l 0} {$l < $numcommits} {incr l} { - if {[string match $id* $lineid($l)]} { - lappend matches $lineid($l) + foreach i $displayorder { + if {[string match $id* $i]} { + lappend matches $i } } if {$matches ne {}} { @@ -2763,8 +2871,8 @@ proc gotocommit {} { } } } - if {[info exists idline($id)]} { - selectline $idline($id) 1 + if {[info exists commitrow($id)]} { + selectline $commitrow($id) 1 return } if {[regexp {^[0-9a-fA-F]{4,}$} $sha1string]} { @@ -2779,7 +2887,7 @@ proc lineenter {x y id} { global hoverx hovery hoverid hovertimer global commitinfo canv - if {![info exists commitinfo($id)]} return + if {![info exists commitinfo($id)] && ![getcommit $id]} return set hoverx $x set hovery $y set hoverid $id @@ -2839,65 +2947,26 @@ proc linehover {} { } proc clickisonarrow {id y} { - global mainline mainlinearrow sidelines lthickness + global lthickness idrowranges set thresh [expr {2 * $lthickness + 6}] - if {[info exists mainline($id)]} { - if {$mainlinearrow($id) ne "none"} { - if {abs([lindex $mainline($id) 1] - $y) < $thresh} { - return "up" - } - } - } - if {[info exists sidelines($id)]} { - foreach ls $sidelines($id) { - set coords [lindex $ls 0] - set arrow [lindex $ls 2] - if {$arrow eq "first" || $arrow eq "both"} { - if {abs([lindex $coords 1] - $y) < $thresh} { - return "up" - } - } - if {$arrow eq "last" || $arrow eq "both"} { - if {abs([lindex $coords end] - $y) < $thresh} { - return "down" - } - } + set n [expr {[llength $idrowranges($id)] - 1}] + for {set i 1} {$i < $n} {incr i} { + set row [lindex $idrowranges($id) $i] + if {abs([yc $row] - $y) < $thresh} { + return $i } } return {} } -proc arrowjump {id dirn y} { - global mainline sidelines canv canv2 canv3 +proc arrowjump {id n y} { + global idrowranges canv - set yt {} - if {$dirn eq "down"} { - if {[info exists mainline($id)]} { - set y1 [lindex $mainline($id) 1] - if {$y1 > $y} { - set yt $y1 - } - } - if {[info exists sidelines($id)]} { - foreach ls $sidelines($id) { - set y1 [lindex $ls 0 1] - if {$y1 > $y && ($yt eq {} || $y1 < $yt)} { - set yt $y1 - } - } - } - } else { - if {[info exists sidelines($id)]} { - foreach ls $sidelines($id) { - set y1 [lindex $ls 0 end] - if {$y1 < $y && ($yt eq {} || $y1 > $yt)} { - set yt $y1 - } - } - } - } - if {$yt eq {}} return + # 1 <-> 2, 3 <-> 4, etc... + set n [expr {(($n - 1) ^ 1) + 1}] + set row [lindex $idrowranges($id) $n] + set yt [yc $row] set ymax [lindex [$canv cget -scrollregion] 3] if {$ymax eq {} || $ymax <= 0} return set view [$canv yview] @@ -2906,21 +2975,20 @@ proc arrowjump {id dirn y} { if {$yfrac < 0} { set yfrac 0 } - $canv yview moveto $yfrac - $canv2 yview moveto $yfrac - $canv3 yview moveto $yfrac + allcanvs yview moveto $yfrac } proc lineclick {x y id isnew} { global ctext commitinfo children cflist canv thickerline + if {![info exists commitinfo($id)] && ![getcommit $id]} return unmarkmatches unselectline normalline $canv delete hover # draw this line thicker than normal - drawlines $id 1 1 set thickerline $id + drawlines $id if {$isnew} { set ymax [lindex [$canv cget -scrollregion] 3] if {$ymax eq {}} return @@ -2955,6 +3023,7 @@ proc lineclick {x y id isnew} { set i 0 foreach child $children($id) { incr i + if {![info exists commitinfo($child)] && ![getcommit $child]} continue set info $commitinfo($child) $ctext insert end "\n\t" $ctext insert end $child [list link link$i] @@ -2973,15 +3042,16 @@ proc lineclick {x y id isnew} { proc normalline {} { global thickerline if {[info exists thickerline]} { - drawlines $thickerline 0 1 + set id $thickerline unset thickerline + drawlines $id } } proc selbyid {id} { - global idline - if {[info exists idline($id)]} { - selectline $idline($id) 1 + global commitrow + if {[info exists commitrow($id)]} { + selectline $commitrow($id) 1 } } @@ -2994,9 +3064,9 @@ proc mstime {} { } proc rowmenu {x y id} { - global rowctxmenu idline selectedline rowmenuid + global rowctxmenu commitrow selectedline rowmenuid - if {![info exists selectedline] || $idline($id) eq $selectedline} { + if {![info exists selectedline] || $commitrow($id) eq $selectedline} { set state disabled } else { set state normal @@ -3009,15 +3079,15 @@ proc rowmenu {x y id} { } proc diffvssel {dirn} { - global rowmenuid selectedline lineid + global rowmenuid selectedline displayorder if {![info exists selectedline]} return if {$dirn} { - set oldid $lineid($selectedline) + set oldid [lindex $displayorder $selectedline] set newid $rowmenuid } else { set oldid $rowmenuid - set newid $lineid($selectedline) + set newid [lindex $displayorder $selectedline] } addtohistory [list doseldiff $oldid $newid] doseldiff $oldid $newid @@ -3199,13 +3269,14 @@ proc domktag {} { } proc redrawtags {id} { - global canv linehtag idline idpos selectedline + global canv linehtag commitrow idpos selectedline - if {![info exists idline($id)]} return + if {![info exists commitrow($id)]} return + drawcmitrow $commitrow($id) $canv delete tag.$id set xt [eval drawtags $id $idpos($id)] - $canv coords $linehtag($idline($id)) $xt [lindex $idpos($id) 2] - if {[info exists selectedline] && $selectedline == $idline($id)} { + $canv coords $linehtag($commitrow($id)) $xt [lindex $idpos($id) 2] + if {[info exists selectedline] && $selectedline == $commitrow($id)} { selectline $selectedline 0 } } @@ -3711,6 +3782,9 @@ set maxgraphpct 50 set maxwidth 16 set revlistorder 0 set fastdate 0 +set uparrowlen 7 +set downarrowlen 7 +set mingaplen 30 set colors {green red blue magenta darkgrey brown orange} @@ -3725,18 +3799,25 @@ foreach arg $argv { switch -regexp -- $arg { "^$" { } "^-d" { set datemode 1 } - "^-r" { set revlistorder 1 } default { lappend revtreeargs $arg } } } +# check that we can find a .git directory somewhere... +set gitdir [gitdir] +if {![file isdirectory $gitdir]} { + error_popup "Cannot find the git directory \"$gitdir\"." + exit 1 +} + set history {} set historyindex 0 +set optim_delay 16 + set stopped 0 -set redisplaying 0 set stuffsaved 0 set patchnum 0 setcoords diff --git a/hash-object.c b/hash-object.c index 6502b5b..43bd93b 100644 --- a/hash-object.c +++ b/hash-object.c @@ -2,9 +2,10 @@ * GIT - The information manager from hell * * Copyright (C) Linus Torvalds, 2005 - * Copyright (C) Junio C Hamano, 2005 + * Copyright (C) Junio C Hamano, 2005 */ #include "cache.h" +#include "blob.h" static void hash_object(const char *path, const char *type, int write_object) { @@ -35,7 +36,7 @@ static const char hash_object_usage[] = int main(int argc, char **argv) { int i; - const char *type = "blob"; + const char *type = blob_type; int write_object = 0; const char *prefix = NULL; int prefix_length = -1; diff --git a/http-fetch.c b/http-fetch.c index 8fd9de0..dc67218 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -8,6 +8,7 @@ #define RANGE_HEADER_SIZE 30 static int got_alternates = -1; +static int corrupt_object_found = 0; static struct curl_slist *no_pragma_header; @@ -468,9 +469,13 @@ static void process_alternates_response(void *callback_data) alt_req->url); active_requests++; slot->in_use = 1; + if (slot->finished != NULL) + (*slot->finished) = 0; if (!start_active_slot(slot)) { got_alternates = -1; slot->in_use = 0; + if (slot->finished != NULL) + (*slot->finished) = 1; } return; } @@ -830,6 +835,7 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) obj_req->errorstr, obj_req->curl_result, obj_req->http_code, hex); } else if (obj_req->zret != Z_STREAM_END) { + corrupt_object_found++; ret = error("File %s (%s) corrupt", hex, obj_req->url); } else if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) { ret = error("File %s has bad hash", hex); @@ -989,5 +995,11 @@ int main(int argc, char **argv) http_cleanup(); + if (corrupt_object_found) { + fprintf(stderr, +"Some loose object were found to be corrupt, but they might be just\n" +"a false '404 Not Found' error message sent with incorrect HTTP\n" +"status code. Suggest running git fsck-objects.\n"); + } return rc; } diff --git a/http-push.c b/http-push.c index fe92560..b60fa8d 100644 --- a/http-push.c +++ b/http-push.c @@ -5,11 +5,14 @@ #include "tag.h" #include "blob.h" #include "http.h" +#include "refs.h" +#include "revision.h" +#include "exec_cmd.h" #include <expat.h> static const char http_push_usage[] = -"git-http-push [--complete] [--force] [--verbose] <url> <ref> [<ref>...]\n"; +"git-http-push [--all] [--force] [--verbose] <remote> [<head>...]\n"; #ifndef XML_STATUS_OK enum XML_Status { @@ -20,6 +23,7 @@ enum XML_Status { #define XML_STATUS_ERROR 0 #endif +#define PREV_BUF_SIZE 4096 #define RANGE_HEADER_SIZE 30 /* DAV methods */ @@ -29,6 +33,7 @@ enum XML_Status { #define DAV_PROPFIND "PROPFIND" #define DAV_PUT "PUT" #define DAV_UNLOCK "UNLOCK" +#define DAV_DELETE "DELETE" /* DAV lock flags */ #define DAV_PROP_LOCKWR (1u << 0) @@ -42,17 +47,31 @@ enum XML_Status { #define DAV_ACTIVELOCK_OWNER ".prop.lockdiscovery.activelock.owner.href" #define DAV_ACTIVELOCK_TIMEOUT ".prop.lockdiscovery.activelock.timeout" #define DAV_ACTIVELOCK_TOKEN ".prop.lockdiscovery.activelock.locktoken.href" +#define DAV_PROPFIND_RESP ".multistatus.response" +#define DAV_PROPFIND_NAME ".multistatus.response.href" +#define DAV_PROPFIND_COLLECTION ".multistatus.response.propstat.prop.resourcetype.collection" /* DAV request body templates */ -#define PROPFIND_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:propfind xmlns:D=\"DAV:\">\n<D:prop xmlns:R=\"%s\">\n<D:supportedlock/>\n</D:prop>\n</D:propfind>" +#define PROPFIND_SUPPORTEDLOCK_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:propfind xmlns:D=\"DAV:\">\n<D:prop xmlns:R=\"%s\">\n<D:supportedlock/>\n</D:prop>\n</D:propfind>" +#define PROPFIND_ALL_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:propfind xmlns:D=\"DAV:\">\n<D:allprop/>\n</D:propfind>" #define LOCK_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:lockinfo xmlns:D=\"DAV:\">\n<D:lockscope><D:exclusive/></D:lockscope>\n<D:locktype><D:write/></D:locktype>\n<D:owner>\n<D:href>mailto:%s</D:href>\n</D:owner>\n</D:lockinfo>" #define LOCK_TIME 600 #define LOCK_REFRESH 30 +/* bits #0-4 in revision.h */ + +#define LOCAL (1u << 5) +#define REMOTE (1u << 6) +#define FETCHING (1u << 7) +#define PUSHING (1u << 8) + +/* We allow "recursive" symbolic refs. Only within reason, though */ +#define MAXDEPTH 5 + static int pushing = 0; static int aborted = 0; -static char remote_dir_exists[256]; +static signed char remote_dir_exists[256]; static struct curl_slist *no_pragma_header; static struct curl_slist *default_headers; @@ -61,17 +80,25 @@ static int push_verbosely = 0; static int push_all = 0; static int force_all = 0; +static struct object_list *objects = NULL; + struct repo { char *url; + int path_len; + int has_info_refs; + int can_update_info_refs; + int has_info_packs; struct packed_git *packs; + struct remote_lock *locks; }; static struct repo *remote = NULL; enum transfer_state { - NEED_CHECK, - RUN_HEAD, + NEED_FETCH, + RUN_FETCH_LOOSE, + RUN_FETCH_PACKED, NEED_PUSH, RUN_MKCOL, RUN_PUT, @@ -82,14 +109,16 @@ enum transfer_state { struct transfer_request { - unsigned char sha1[20]; + struct object *obj; char *url; char *dest; - struct active_lock *lock; + struct remote_lock *lock; struct curl_slist *headers; struct buffer buffer; char filename[PATH_MAX]; char tmpfile[PATH_MAX]; + int local_fileno; + FILE *local_stream; enum transfer_state state; CURLcode curl_result; char errorstr[CURL_ERROR_SIZE]; @@ -99,6 +128,7 @@ struct transfer_request z_stream stream; int zret; int rename; + void *userData; struct active_request_slot *slot; struct transfer_request *next; }; @@ -114,7 +144,7 @@ struct xml_ctx void *userData; }; -struct active_lock +struct remote_lock { char *url; char *owner; @@ -122,9 +152,30 @@ struct active_lock time_t start_time; long timeout; int refreshing; + struct remote_lock *next; +}; + +/* Flags that control remote_ls processing */ +#define PROCESS_FILES (1u << 0) +#define PROCESS_DIRS (1u << 1) +#define RECURSIVE (1u << 2) + +/* Flags that remote_ls passes to callback functions */ +#define IS_DIR (1u << 0) + +struct remote_ls_ctx +{ + char *path; + void (*userFunc)(struct remote_ls_ctx *ls); + void *userData; + int flags; + char *dentry_name; + int dentry_flags; + struct remote_ls_ctx *parent; }; static void finish_request(struct transfer_request *request); +static void release_request(struct transfer_request *request); static void process_response(void *callback_data) { @@ -134,42 +185,261 @@ static void process_response(void *callback_data) finish_request(request); } -static void start_check(struct transfer_request *request) +static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, + void *data) { - char *hex = sha1_to_hex(request->sha1); - struct active_request_slot *slot; + unsigned char expn[4096]; + size_t size = eltsize * nmemb; + int posn = 0; + struct transfer_request *request = (struct transfer_request *)data; + do { + ssize_t retval = write(request->local_fileno, + ptr + posn, size - posn); + if (retval < 0) + return posn; + posn += retval; + } while (posn < size); + + request->stream.avail_in = size; + request->stream.next_in = ptr; + do { + request->stream.next_out = expn; + request->stream.avail_out = sizeof(expn); + request->zret = inflate(&request->stream, Z_SYNC_FLUSH); + SHA1_Update(&request->c, expn, + sizeof(expn) - request->stream.avail_out); + } while (request->stream.avail_in && request->zret == Z_OK); + data_received++; + return size; +} + +static void start_fetch_loose(struct transfer_request *request) +{ + char *hex = sha1_to_hex(request->obj->sha1); + char *filename; + char prevfile[PATH_MAX]; + char *url; char *posn; + int prevlocal; + unsigned char prev_buf[PREV_BUF_SIZE]; + ssize_t prev_read = 0; + long prev_posn = 0; + char range[RANGE_HEADER_SIZE]; + struct curl_slist *range_header = NULL; + struct active_request_slot *slot; - request->url = xmalloc(strlen(remote->url) + 55); - strcpy(request->url, remote->url); - posn = request->url + strlen(remote->url); + filename = sha1_file_name(request->obj->sha1); + snprintf(request->filename, sizeof(request->filename), "%s", filename); + snprintf(request->tmpfile, sizeof(request->tmpfile), + "%s.temp", filename); + + snprintf(prevfile, sizeof(prevfile), "%s.prev", request->filename); + unlink(prevfile); + rename(request->tmpfile, prevfile); + unlink(request->tmpfile); + + if (request->local_fileno != -1) + error("fd leakage in start: %d", request->local_fileno); + request->local_fileno = open(request->tmpfile, + O_WRONLY | O_CREAT | O_EXCL, 0666); + /* This could have failed due to the "lazy directory creation"; + * try to mkdir the last path component. + */ + if (request->local_fileno < 0 && errno == ENOENT) { + char *dir = strrchr(request->tmpfile, '/'); + if (dir) { + *dir = 0; + mkdir(request->tmpfile, 0777); + *dir = '/'; + } + request->local_fileno = open(request->tmpfile, + O_WRONLY | O_CREAT | O_EXCL, 0666); + } + + if (request->local_fileno < 0) { + request->state = ABORTED; + error("Couldn't create temporary file %s for %s: %s", + request->tmpfile, request->filename, strerror(errno)); + return; + } + + memset(&request->stream, 0, sizeof(request->stream)); + + inflateInit(&request->stream); + + SHA1_Init(&request->c); + + url = xmalloc(strlen(remote->url) + 50); + request->url = xmalloc(strlen(remote->url) + 50); + strcpy(url, remote->url); + posn = url + strlen(remote->url); strcpy(posn, "objects/"); posn += 8; memcpy(posn, hex, 2); posn += 2; *(posn++) = '/'; strcpy(posn, hex + 2); + strcpy(request->url, url); + + /* If a previous temp file is present, process what was already + fetched. */ + prevlocal = open(prevfile, O_RDONLY); + if (prevlocal != -1) { + do { + prev_read = read(prevlocal, prev_buf, PREV_BUF_SIZE); + if (prev_read>0) { + if (fwrite_sha1_file(prev_buf, + 1, + prev_read, + request) == prev_read) { + prev_posn += prev_read; + } else { + prev_read = -1; + } + } + } while (prev_read > 0); + close(prevlocal); + } + unlink(prevfile); + + /* Reset inflate/SHA1 if there was an error reading the previous temp + file; also rewind to the beginning of the local file. */ + if (prev_read == -1) { + memset(&request->stream, 0, sizeof(request->stream)); + inflateInit(&request->stream); + SHA1_Init(&request->c); + if (prev_posn>0) { + prev_posn = 0; + lseek(request->local_fileno, SEEK_SET, 0); + ftruncate(request->local_fileno, 0); + } + } slot = get_active_slot(); slot->callback_func = process_response; slot->callback_data = request; + request->slot = slot; + + curl_easy_setopt(slot->curl, CURLOPT_FILE, request); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_sha1_file); curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, request->errorstr); - curl_easy_setopt(slot->curl, CURLOPT_URL, request->url); - curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 1); + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, no_pragma_header); - if (start_active_slot(slot)) { - request->slot = slot; - request->state = RUN_HEAD; - } else { - request->state = ABORTED; - free(request->url); - request->url = NULL; + /* If we have successfully processed data from a previous fetch + attempt, only fetch the data we don't already have. */ + if (prev_posn>0) { + if (push_verbosely) + fprintf(stderr, + "Resuming fetch of object %s at byte %ld\n", + hex, prev_posn); + sprintf(range, "Range: bytes=%ld-", prev_posn); + range_header = curl_slist_append(range_header, range); + curl_easy_setopt(slot->curl, + CURLOPT_HTTPHEADER, range_header); + } + + /* Try to get the request started, abort the request on error */ + request->state = RUN_FETCH_LOOSE; + if (!start_active_slot(slot)) { + fprintf(stderr, "Unable to start GET request\n"); + remote->can_update_info_refs = 0; + release_request(request); + } +} + +static void start_fetch_packed(struct transfer_request *request) +{ + char *url; + struct packed_git *target; + FILE *packfile; + char *filename; + long prev_posn = 0; + char range[RANGE_HEADER_SIZE]; + struct curl_slist *range_header = NULL; + + struct transfer_request *check_request = request_queue_head; + struct active_request_slot *slot; + + target = find_sha1_pack(request->obj->sha1, remote->packs); + if (!target) { + fprintf(stderr, "Unable to fetch %s, will not be able to update server info refs\n", sha1_to_hex(request->obj->sha1)); + remote->can_update_info_refs = 0; + release_request(request); + return; + } + + fprintf(stderr, "Fetching pack %s\n", sha1_to_hex(target->sha1)); + fprintf(stderr, " which contains %s\n", sha1_to_hex(request->obj->sha1)); + + filename = sha1_pack_name(target->sha1); + snprintf(request->filename, sizeof(request->filename), "%s", filename); + snprintf(request->tmpfile, sizeof(request->tmpfile), + "%s.temp", filename); + + url = xmalloc(strlen(remote->url) + 64); + sprintf(url, "%sobjects/pack/pack-%s.pack", + remote->url, sha1_to_hex(target->sha1)); + + /* Make sure there isn't another open request for this pack */ + while (check_request) { + if (check_request->state == RUN_FETCH_PACKED && + !strcmp(check_request->url, url)) { + free(url); + release_request(request); + return; + } + check_request = check_request->next; + } + + packfile = fopen(request->tmpfile, "a"); + if (!packfile) { + fprintf(stderr, "Unable to open local file %s for pack", + filename); + remote->can_update_info_refs = 0; + free(url); + return; + } + + slot = get_active_slot(); + slot->callback_func = process_response; + slot->callback_data = request; + request->slot = slot; + request->local_stream = packfile; + request->userData = target; + + request->url = url; + curl_easy_setopt(slot->curl, CURLOPT_FILE, packfile); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite); + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, no_pragma_header); + slot->local = packfile; + + /* If there is data present from a previous transfer attempt, + resume where it left off */ + prev_posn = ftell(packfile); + if (prev_posn>0) { + if (push_verbosely) + fprintf(stderr, + "Resuming fetch of pack %s at byte %ld\n", + sha1_to_hex(target->sha1), prev_posn); + sprintf(range, "Range: bytes=%ld-", prev_posn); + range_header = curl_slist_append(range_header, range); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, range_header); + } + + /* Try to get the request started, abort the request on error */ + request->state = RUN_FETCH_PACKED; + if (!start_active_slot(slot)) { + fprintf(stderr, "Unable to start GET request\n"); + remote->can_update_info_refs = 0; + release_request(request); } } static void start_mkcol(struct transfer_request *request) { - char *hex = sha1_to_hex(request->sha1); + char *hex = sha1_to_hex(request->obj->sha1); struct active_request_slot *slot; char *posn; @@ -203,7 +473,7 @@ static void start_mkcol(struct transfer_request *request) static void start_put(struct transfer_request *request) { - char *hex = sha1_to_hex(request->sha1); + char *hex = sha1_to_hex(request->obj->sha1); struct active_request_slot *slot; char *posn; char type[20]; @@ -214,7 +484,7 @@ static void start_put(struct transfer_request *request) ssize_t size; z_stream stream; - unpacked = read_sha1_file(request->sha1, type, &len); + unpacked = read_sha1_file(request->obj->sha1, type, &len); hdrlen = sprintf(hdr, "%s %lu", type, len) + 1; /* Set it up */ @@ -309,9 +579,10 @@ static void start_move(struct transfer_request *request) } } -static int refresh_lock(struct active_lock *lock) +static int refresh_lock(struct remote_lock *lock) { struct active_request_slot *slot; + struct slot_results results; char *if_header; char timeout_header[25]; struct curl_slist *dav_headers = NULL; @@ -326,6 +597,7 @@ static int refresh_lock(struct active_lock *lock) dav_headers = curl_slist_append(dav_headers, timeout_header); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_null); curl_easy_setopt(slot->curl, CURLOPT_URL, lock->url); @@ -334,8 +606,9 @@ static int refresh_lock(struct active_lock *lock) if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK) { - fprintf(stderr, "Got HTTP error %ld\n", slot->http_code); + if (results.curl_result != CURLE_OK) { + fprintf(stderr, "LOCK HTTP error %ld\n", + results.http_code); } else { lock->start_time = time(NULL); rc = 1; @@ -349,24 +622,62 @@ static int refresh_lock(struct active_lock *lock) return rc; } -static void finish_request(struct transfer_request *request) +static void check_locks(void) { + struct remote_lock *lock = remote->locks; time_t current_time = time(NULL); int time_remaining; - request->curl_result = request->slot->curl_result; + while (lock) { + time_remaining = lock->start_time + lock->timeout - + current_time; + if (!lock->refreshing && time_remaining < LOCK_REFRESH) { + if (!refresh_lock(lock)) { + fprintf(stderr, + "Unable to refresh lock for %s\n", + lock->url); + aborted = 1; + return; + } + } + lock = lock->next; + } +} + +static void release_request(struct transfer_request *request) +{ + struct transfer_request *entry = request_queue_head; + + if (request == request_queue_head) { + request_queue_head = request->next; + } else { + while (entry->next != NULL && entry->next != request) + entry = entry->next; + if (entry->next == request) + entry->next = entry->next->next; + } + + if (request->local_fileno != -1) + close(request->local_fileno); + if (request->local_stream) + fclose(request->local_stream); + if (request->url != NULL) + free(request->url); + free(request); +} + +static void finish_request(struct transfer_request *request) +{ + struct stat st; + struct packed_git *target; + struct packed_git **lst; + + request->curl_result = request->slot->curl_result; request->http_code = request->slot->http_code; request->slot = NULL; - /* Refresh the lock if it is close to timing out */ - time_remaining = request->lock->start_time + request->lock->timeout - - current_time; - if (time_remaining < LOCK_REFRESH && !request->lock->refreshing) { - if (!refresh_lock(request->lock)) { - fprintf(stderr, "Unable to refresh remote lock\n"); - aborted = 1; - } - } + /* Keep locks active */ + check_locks(); if (request->headers != NULL) curl_slist_free_all(request->headers); @@ -375,29 +686,16 @@ static void finish_request(struct transfer_request *request) if (request->state != RUN_PUT) { free(request->url); request->url = NULL; - } - - if (request->state == RUN_HEAD) { - if (request->http_code == 404) { - request->state = NEED_PUSH; - } else if (request->curl_result == CURLE_OK) { - remote_dir_exists[request->sha1[0]] = 1; - request->state = COMPLETE; - } else { - fprintf(stderr, "HEAD %s failed, aborting (%d/%ld)\n", - sha1_to_hex(request->sha1), - request->curl_result, request->http_code); - request->state = ABORTED; - aborted = 1; - } - } else if (request->state == RUN_MKCOL) { + } + + if (request->state == RUN_MKCOL) { if (request->curl_result == CURLE_OK || request->http_code == 405) { - remote_dir_exists[request->sha1[0]] = 1; + remote_dir_exists[request->obj->sha1[0]] = 1; start_put(request); } else { fprintf(stderr, "MKCOL %s failed, aborting (%d/%ld)\n", - sha1_to_hex(request->sha1), + sha1_to_hex(request->obj->sha1), request->curl_result, request->http_code); request->state = ABORTED; aborted = 1; @@ -407,7 +705,7 @@ static void finish_request(struct transfer_request *request) start_move(request); } else { fprintf(stderr, "PUT %s failed, aborting (%d/%ld)\n", - sha1_to_hex(request->sha1), + sha1_to_hex(request->obj->sha1), request->curl_result, request->http_code); request->state = ABORTED; aborted = 1; @@ -415,41 +713,84 @@ static void finish_request(struct transfer_request *request) } else if (request->state == RUN_MOVE) { if (request->curl_result == CURLE_OK) { if (push_verbosely) - fprintf(stderr, - "sent %s\n", - sha1_to_hex(request->sha1)); - request->state = COMPLETE; + fprintf(stderr, " sent %s\n", + sha1_to_hex(request->obj->sha1)); + request->obj->flags |= REMOTE; + release_request(request); } else { fprintf(stderr, "MOVE %s failed, aborting (%d/%ld)\n", - sha1_to_hex(request->sha1), + sha1_to_hex(request->obj->sha1), request->curl_result, request->http_code); request->state = ABORTED; aborted = 1; } - } -} + } else if (request->state == RUN_FETCH_LOOSE) { + fchmod(request->local_fileno, 0444); + close(request->local_fileno); request->local_fileno = -1; + + if (request->curl_result != CURLE_OK && + request->http_code != 416) { + if (stat(request->tmpfile, &st) == 0) { + if (st.st_size == 0) + unlink(request->tmpfile); + } + } else { + if (request->http_code == 416) + fprintf(stderr, "Warning: requested range invalid; we may already have all the data.\n"); + + inflateEnd(&request->stream); + SHA1_Final(request->real_sha1, &request->c); + if (request->zret != Z_STREAM_END) { + unlink(request->tmpfile); + } else if (memcmp(request->obj->sha1, request->real_sha1, 20)) { + unlink(request->tmpfile); + } else { + request->rename = + move_temp_to_file( + request->tmpfile, + request->filename); + if (request->rename == 0) { + request->obj->flags |= (LOCAL | REMOTE); + } + } + } -static void release_request(struct transfer_request *request) -{ - struct transfer_request *entry = request_queue_head; + /* Try fetching packed if necessary */ + if (request->obj->flags & LOCAL) + release_request(request); + else + start_fetch_packed(request); - if (request == request_queue_head) { - request_queue_head = request->next; - } else { - while (entry->next != NULL && entry->next != request) - entry = entry->next; - if (entry->next == request) - entry->next = entry->next->next; + } else if (request->state == RUN_FETCH_PACKED) { + if (request->curl_result != CURLE_OK) { + fprintf(stderr, "Unable to get pack file %s\n%s", + request->url, curl_errorstr); + remote->can_update_info_refs = 0; + } else { + fclose(request->local_stream); + request->local_stream = NULL; + if (!move_temp_to_file(request->tmpfile, + request->filename)) { + target = (struct packed_git *)request->userData; + lst = &remote->packs; + while (*lst != target) + lst = &((*lst)->next); + *lst = (*lst)->next; + + if (!verify_pack(target, 0)) + install_packed_git(target); + else + remote->can_update_info_refs = 0; + } + } + release_request(request); } - - if (request->url != NULL) - free(request->url); - free(request); } void fill_active_slots(void) { struct transfer_request *request = request_queue_head; + struct transfer_request *next; struct active_request_slot *slot = active_queue_head; int num_transfers; @@ -457,17 +798,18 @@ void fill_active_slots(void) return; while (active_requests < max_requests && request != NULL) { - if (!pushing && request->state == NEED_CHECK) { - start_check(request); - curl_multi_perform(curlm, &num_transfers); + next = request->next; + if (request->state == NEED_FETCH) { + start_fetch_loose(request); } else if (pushing && request->state == NEED_PUSH) { - if (remote_dir_exists[request->sha1[0]]) + if (remote_dir_exists[request->obj->sha1[0]] == 1) { start_put(request); - else + } else { start_mkcol(request); + } curl_multi_perform(curlm, &num_transfers); } - request = request->next; + request = next; } while (slot != NULL) { @@ -476,34 +818,80 @@ void fill_active_slots(void) slot->curl = NULL; } slot = slot->next; - } + } } -static void add_request(unsigned char *sha1, struct active_lock *lock) +static void get_remote_object_list(unsigned char parent); + +static void add_fetch_request(struct object *obj) +{ + struct transfer_request *request; + + check_locks(); + + /* + * Don't fetch the object if it's known to exist locally + * or is already in the request queue + */ + if (remote_dir_exists[obj->sha1[0]] == -1) + get_remote_object_list(obj->sha1[0]); + if (obj->flags & (LOCAL | FETCHING)) + return; + + obj->flags |= FETCHING; + request = xmalloc(sizeof(*request)); + request->obj = obj; + request->url = NULL; + request->lock = NULL; + request->headers = NULL; + request->local_fileno = -1; + request->local_stream = NULL; + request->state = NEED_FETCH; + request->next = request_queue_head; + request_queue_head = request; + + fill_active_slots(); + step_active_slots(); +} + +static int add_send_request(struct object *obj, struct remote_lock *lock) { struct transfer_request *request = request_queue_head; struct packed_git *target; - - while (request != NULL && memcmp(request->sha1, sha1, 20)) - request = request->next; - if (request != NULL) - return; - target = find_sha1_pack(sha1, remote->packs); - if (target) - return; + /* Keep locks active */ + check_locks(); + + /* + * Don't push the object if it's known to exist on the remote + * or is already in the request queue + */ + if (remote_dir_exists[obj->sha1[0]] == -1) + get_remote_object_list(obj->sha1[0]); + if (obj->flags & (REMOTE | PUSHING)) + return 0; + target = find_sha1_pack(obj->sha1, remote->packs); + if (target) { + obj->flags |= REMOTE; + return 0; + } + obj->flags |= PUSHING; request = xmalloc(sizeof(*request)); - memcpy(request->sha1, sha1, 20); + request->obj = obj; request->url = NULL; request->lock = lock; request->headers = NULL; - request->state = NEED_CHECK; + request->local_fileno = -1; + request->local_stream = NULL; + request->state = NEED_PUSH; request->next = request_queue_head; request_queue_head = request; fill_active_slots(); step_active_slots(); + + return 1; } static int fetch_index(unsigned char *sha1) @@ -518,16 +906,18 @@ static int fetch_index(unsigned char *sha1) FILE *indexfile; struct active_request_slot *slot; + struct slot_results results; /* Don't use the index if the pack isn't there */ - url = xmalloc(strlen(remote->url) + 65); - sprintf(url, "%s/objects/pack/pack-%s.pack", remote->url, hex); + url = xmalloc(strlen(remote->url) + 64); + sprintf(url, "%sobjects/pack/pack-%s.pack", remote->url, hex); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_URL, url); curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 1); if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK) { + if (results.curl_result != CURLE_OK) { free(url); return error("Unable to verify pack %s is available", hex); @@ -541,9 +931,9 @@ static int fetch_index(unsigned char *sha1) if (push_verbosely) fprintf(stderr, "Getting index for pack %s\n", hex); - - sprintf(url, "%s/objects/pack/pack-%s.idx", remote->url, hex); - + + sprintf(url, "%sobjects/pack/pack-%s.idx", remote->url, hex); + filename = sha1_pack_index_name(sha1); snprintf(tmpfile, sizeof(tmpfile), "%s.temp", filename); indexfile = fopen(tmpfile, "a"); @@ -552,6 +942,7 @@ static int fetch_index(unsigned char *sha1) filename); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 0); curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); curl_easy_setopt(slot->curl, CURLOPT_FILE, indexfile); @@ -575,7 +966,7 @@ static int fetch_index(unsigned char *sha1) if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK) { + if (results.curl_result != CURLE_OK) { free(url); fclose(indexfile); return error("Unable to get pack index %s\n%s", url, @@ -615,30 +1006,31 @@ static int fetch_indices(void) int i = 0; struct active_request_slot *slot; + struct slot_results results; - data = xmalloc(4096); - memset(data, 0, 4096); + data = xcalloc(1, 4096); buffer.size = 4096; buffer.posn = 0; buffer.buffer = data; if (push_verbosely) fprintf(stderr, "Getting pack list\n"); - - url = xmalloc(strlen(remote->url) + 21); - sprintf(url, "%s/objects/info/packs", remote->url); + + url = xmalloc(strlen(remote->url) + 20); + sprintf(url, "%sobjects/info/packs", remote->url); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_FILE, &buffer); curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); curl_easy_setopt(slot->curl, CURLOPT_URL, url); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, NULL); if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK) { + if (results.curl_result != CURLE_OK) { free(buffer.buffer); free(url); - if (slot->http_code == 404) + if (results.http_code == 404) return 0; else return error("%s", curl_errorstr); @@ -698,14 +1090,13 @@ static char *quote_ref_url(const char *base, const char *ref) int len, baselen, ch; baselen = strlen(base); - len = baselen + 12; /* "refs/heads/" + NUL */ + len = baselen + 1; for (cp = ref; (ch = *cp) != 0; cp++, len++) if (needs_quote(ch)) len += 2; /* extra two hex plus replacement % */ qref = xmalloc(len); memcpy(qref, base, baselen); - memcpy(qref + baselen, "refs/heads/", 11); - for (cp = ref, dp = qref + baselen + 11; (ch = *cp) != 0; cp++) { + for (cp = ref, dp = qref + baselen; (ch = *cp) != 0; cp++) { if (needs_quote(ch)) { *dp++ = '%'; *dp++ = hex((ch >> 4) & 0xF); @@ -726,20 +1117,22 @@ int fetch_ref(char *ref, unsigned char *sha1) struct buffer buffer; char *base = remote->url; struct active_request_slot *slot; + struct slot_results results; buffer.size = 41; buffer.posn = 0; buffer.buffer = hex; hex[41] = '\0'; - + url = quote_ref_url(base, ref); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_FILE, &buffer); curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, NULL); curl_easy_setopt(slot->curl, CURLOPT_URL, url); if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK) + if (results.curl_result != CURLE_OK) return error("Couldn't get %s for %s\n%s", url, ref, curl_errorstr); } else { @@ -751,6 +1144,27 @@ int fetch_ref(char *ref, unsigned char *sha1) return 0; } +static void one_remote_object(const char *hex) +{ + unsigned char sha1[20]; + struct object *obj; + + if (get_sha1_hex(hex, sha1) != 0) + return; + + obj = lookup_object(sha1); + if (!obj) + obj = parse_object(sha1); + + /* Ignore remote objects that don't exist locally */ + if (!obj) + return; + + obj->flags |= REMOTE; + if (!object_list_contains(objects, obj)) + add_object(obj, &objects, NULL, ""); +} + static void handle_lockprop_ctx(struct xml_ctx *ctx, int tag_closed) { int *lock_flags = (int *)ctx->userData; @@ -772,7 +1186,7 @@ static void handle_lockprop_ctx(struct xml_ctx *ctx, int tag_closed) static void handle_new_lock_ctx(struct xml_ctx *ctx, int tag_closed) { - struct active_lock *lock = (struct active_lock *)ctx->userData; + struct remote_lock *lock = (struct remote_lock *)ctx->userData; if (tag_closed && ctx->cdata) { if (!strcmp(ctx->name, DAV_ACTIVELOCK_OWNER)) { @@ -791,6 +1205,8 @@ static void handle_new_lock_ctx(struct xml_ctx *ctx, int tag_closed) } } +static void one_remote_ref(char *refname); + static void xml_start_tag(void *userData, const char *name, const char **atts) { @@ -848,9 +1264,10 @@ xml_cdata(void *userData, const XML_Char *s, int len) strncpy(ctx->cdata, s, len); } -static struct active_lock *lock_remote(char *file, long timeout) +static struct remote_lock *lock_remote(char *path, long timeout) { struct active_request_slot *slot; + struct slot_results results; struct buffer out_buffer; struct buffer in_buffer; char *out_data; @@ -858,28 +1275,29 @@ static struct active_lock *lock_remote(char *file, long timeout) char *url; char *ep; char timeout_header[25]; - struct active_lock *new_lock = NULL; + struct remote_lock *lock = NULL; XML_Parser parser = XML_ParserCreate(NULL); enum XML_Status result; struct curl_slist *dav_headers = NULL; struct xml_ctx ctx; - url = xmalloc(strlen(remote->url) + strlen(file) + 1); - sprintf(url, "%s%s", remote->url, file); + url = xmalloc(strlen(remote->url) + strlen(path) + 1); + sprintf(url, "%s%s", remote->url, path); /* Make sure leading directories exist for the remote ref */ ep = strchr(url + strlen(remote->url) + 11, '/'); while (ep) { *ep = 0; slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); curl_easy_setopt(slot->curl, CURLOPT_URL, url); curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_MKCOL); curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_null); if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result != CURLE_OK && - slot->http_code != 405) { + if (results.curl_result != CURLE_OK && + results.http_code != 405) { fprintf(stderr, "Unable to create branch path %s\n", url); @@ -887,7 +1305,7 @@ static struct active_lock *lock_remote(char *file, long timeout) return NULL; } } else { - fprintf(stderr, "Unable to start request\n"); + fprintf(stderr, "Unable to start MKCOL request\n"); free(url); return NULL; } @@ -911,6 +1329,7 @@ static struct active_lock *lock_remote(char *file, long timeout) dav_headers = curl_slist_append(dav_headers, "Content-Type: text/xml"); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer); curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size); curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); @@ -921,20 +1340,17 @@ static struct active_lock *lock_remote(char *file, long timeout) curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_LOCK); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, dav_headers); - new_lock = xcalloc(1, sizeof(*new_lock)); - new_lock->owner = NULL; - new_lock->token = NULL; - new_lock->timeout = -1; - new_lock->refreshing = 0; + lock = xcalloc(1, sizeof(*lock)); + lock->timeout = -1; if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result == CURLE_OK) { + if (results.curl_result == CURLE_OK) { ctx.name = xcalloc(10, 1); ctx.len = 0; ctx.cdata = NULL; ctx.userFunc = handle_new_lock_ctx; - ctx.userData = new_lock; + ctx.userData = lock; XML_SetUserData(parser, &ctx); XML_SetElementHandler(parser, xml_start_tag, xml_end_tag); @@ -946,36 +1362,40 @@ static struct active_lock *lock_remote(char *file, long timeout) fprintf(stderr, "XML error: %s\n", XML_ErrorString( XML_GetErrorCode(parser))); - new_lock->timeout = -1; + lock->timeout = -1; } } } else { - fprintf(stderr, "Unable to start request\n"); + fprintf(stderr, "Unable to start LOCK request\n"); } curl_slist_free_all(dav_headers); free(out_data); free(in_data); - if (new_lock->token == NULL || new_lock->timeout <= 0) { - if (new_lock->token != NULL) - free(new_lock->token); - if (new_lock->owner != NULL) - free(new_lock->owner); + if (lock->token == NULL || lock->timeout <= 0) { + if (lock->token != NULL) + free(lock->token); + if (lock->owner != NULL) + free(lock->owner); free(url); - free(new_lock); - new_lock = NULL; + free(lock); + lock = NULL; } else { - new_lock->url = url; - new_lock->start_time = time(NULL); + lock->url = url; + lock->start_time = time(NULL); + lock->next = remote->locks; + remote->locks = lock; } - return new_lock; + return lock; } -static int unlock_remote(struct active_lock *lock) +static int unlock_remote(struct remote_lock *lock) { struct active_request_slot *slot; + struct slot_results results; + struct remote_lock *prev = remote->locks; char *lock_token_header; struct curl_slist *dav_headers = NULL; int rc = 0; @@ -986,6 +1406,7 @@ static int unlock_remote(struct active_lock *lock) dav_headers = curl_slist_append(dav_headers, lock_token_header); slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_null); curl_easy_setopt(slot->curl, CURLOPT_URL, lock->url); curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_UNLOCK); @@ -993,18 +1414,27 @@ static int unlock_remote(struct active_lock *lock) if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result == CURLE_OK) + if (results.curl_result == CURLE_OK) rc = 1; else - fprintf(stderr, "Got HTTP error %ld\n", - slot->http_code); + fprintf(stderr, "UNLOCK HTTP error %ld\n", + results.http_code); } else { - fprintf(stderr, "Unable to start request\n"); + fprintf(stderr, "Unable to start UNLOCK request\n"); } curl_slist_free_all(dav_headers); free(lock_token_header); + if (remote->locks == lock) { + remote->locks = lock->next; + } else { + while (prev && prev->next != lock) + prev = prev->next; + if (prev) + prev->next = prev->next->next; + } + if (lock->owner != NULL) free(lock->owner); free(lock->url); @@ -1014,9 +1444,180 @@ static int unlock_remote(struct active_lock *lock) return rc; } +static void remote_ls(const char *path, int flags, + void (*userFunc)(struct remote_ls_ctx *ls), + void *userData); + +static void process_ls_object(struct remote_ls_ctx *ls) +{ + unsigned int *parent = (unsigned int *)ls->userData; + char *path = ls->dentry_name; + char *obj_hex; + + if (!strcmp(ls->path, ls->dentry_name) && (ls->flags & IS_DIR)) { + remote_dir_exists[*parent] = 1; + return; + } + + if (strlen(path) != 49) + return; + path += 8; + obj_hex = xmalloc(strlen(path)); + strncpy(obj_hex, path, 2); + strcpy(obj_hex + 2, path + 3); + one_remote_object(obj_hex); + free(obj_hex); +} + +static void process_ls_ref(struct remote_ls_ctx *ls) +{ + if (!strcmp(ls->path, ls->dentry_name) && (ls->dentry_flags & IS_DIR)) { + fprintf(stderr, " %s\n", ls->dentry_name); + return; + } + + if (!(ls->dentry_flags & IS_DIR)) + one_remote_ref(ls->dentry_name); +} + +static void handle_remote_ls_ctx(struct xml_ctx *ctx, int tag_closed) +{ + struct remote_ls_ctx *ls = (struct remote_ls_ctx *)ctx->userData; + + if (tag_closed) { + if (!strcmp(ctx->name, DAV_PROPFIND_RESP) && ls->dentry_name) { + if (ls->dentry_flags & IS_DIR) { + if (ls->flags & PROCESS_DIRS) { + ls->userFunc(ls); + } + if (strcmp(ls->dentry_name, ls->path) && + ls->flags & RECURSIVE) { + remote_ls(ls->dentry_name, + ls->flags, + ls->userFunc, + ls->userData); + } + } else if (ls->flags & PROCESS_FILES) { + ls->userFunc(ls); + } + } else if (!strcmp(ctx->name, DAV_PROPFIND_NAME) && ctx->cdata) { + ls->dentry_name = xmalloc(strlen(ctx->cdata) - + remote->path_len + 1); + strcpy(ls->dentry_name, ctx->cdata + remote->path_len); + } else if (!strcmp(ctx->name, DAV_PROPFIND_COLLECTION)) { + ls->dentry_flags |= IS_DIR; + } + } else if (!strcmp(ctx->name, DAV_PROPFIND_RESP)) { + if (ls->dentry_name) { + free(ls->dentry_name); + } + ls->dentry_name = NULL; + ls->dentry_flags = 0; + } +} + +static void remote_ls(const char *path, int flags, + void (*userFunc)(struct remote_ls_ctx *ls), + void *userData) +{ + char *url = xmalloc(strlen(remote->url) + strlen(path) + 1); + struct active_request_slot *slot; + struct slot_results results; + struct buffer in_buffer; + struct buffer out_buffer; + char *in_data; + char *out_data; + XML_Parser parser = XML_ParserCreate(NULL); + enum XML_Status result; + struct curl_slist *dav_headers = NULL; + struct xml_ctx ctx; + struct remote_ls_ctx ls; + + ls.flags = flags; + ls.path = strdup(path); + ls.dentry_name = NULL; + ls.dentry_flags = 0; + ls.userData = userData; + ls.userFunc = userFunc; + + sprintf(url, "%s%s", remote->url, path); + + out_buffer.size = strlen(PROPFIND_ALL_REQUEST); + out_data = xmalloc(out_buffer.size + 1); + snprintf(out_data, out_buffer.size + 1, PROPFIND_ALL_REQUEST); + out_buffer.posn = 0; + out_buffer.buffer = out_data; + + in_buffer.size = 4096; + in_data = xmalloc(in_buffer.size); + in_buffer.posn = 0; + in_buffer.buffer = in_data; + + dav_headers = curl_slist_append(dav_headers, "Depth: 1"); + dav_headers = curl_slist_append(dav_headers, "Content-Type: text/xml"); + + slot = get_active_slot(); + slot->results = &results; + curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer); + curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size); + curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); + curl_easy_setopt(slot->curl, CURLOPT_FILE, &in_buffer); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 1); + curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_PROPFIND); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, dav_headers); + + if (start_active_slot(slot)) { + run_active_slot(slot); + if (results.curl_result == CURLE_OK) { + ctx.name = xcalloc(10, 1); + ctx.len = 0; + ctx.cdata = NULL; + ctx.userFunc = handle_remote_ls_ctx; + ctx.userData = &ls; + XML_SetUserData(parser, &ctx); + XML_SetElementHandler(parser, xml_start_tag, + xml_end_tag); + XML_SetCharacterDataHandler(parser, xml_cdata); + result = XML_Parse(parser, in_buffer.buffer, + in_buffer.posn, 1); + free(ctx.name); + + if (result != XML_STATUS_OK) { + fprintf(stderr, "XML error: %s\n", + XML_ErrorString( + XML_GetErrorCode(parser))); + } + } + } else { + fprintf(stderr, "Unable to start PROPFIND request\n"); + } + + free(ls.path); + free(url); + free(out_data); + free(in_buffer.buffer); + curl_slist_free_all(dav_headers); +} + +static void get_remote_object_list(unsigned char parent) +{ + char path[] = "objects/XX/"; + static const char hex[] = "0123456789abcdef"; + unsigned int val = parent; + + path[8] = hex[val >> 4]; + path[9] = hex[val & 0xf]; + remote_dir_exists[val] = 0; + remote_ls(path, (PROCESS_FILES | PROCESS_DIRS), + process_ls_object, &val); +} + static int locking_available(void) { struct active_request_slot *slot; + struct slot_results results; struct buffer in_buffer; struct buffer out_buffer; char *in_data; @@ -1027,9 +1628,12 @@ static int locking_available(void) struct xml_ctx ctx; int lock_flags = 0; - out_buffer.size = strlen(PROPFIND_REQUEST) + strlen(remote->url) - 2; + out_buffer.size = + strlen(PROPFIND_SUPPORTEDLOCK_REQUEST) + + strlen(remote->url) - 2; out_data = xmalloc(out_buffer.size + 1); - snprintf(out_data, out_buffer.size + 1, PROPFIND_REQUEST, remote->url); + snprintf(out_data, out_buffer.size + 1, + PROPFIND_SUPPORTEDLOCK_REQUEST, remote->url); out_buffer.posn = 0; out_buffer.buffer = out_data; @@ -1040,8 +1644,9 @@ static int locking_available(void) dav_headers = curl_slist_append(dav_headers, "Depth: 0"); dav_headers = curl_slist_append(dav_headers, "Content-Type: text/xml"); - + slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer); curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size); curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); @@ -1054,7 +1659,7 @@ static int locking_available(void) if (start_active_slot(slot)) { run_active_slot(slot); - if (slot->curl_result == CURLE_OK) { + if (results.curl_result == CURLE_OK) { ctx.name = xcalloc(10, 1); ctx.len = 0; ctx.cdata = NULL; @@ -1075,7 +1680,7 @@ static int locking_available(void) } } } else { - fprintf(stderr, "Unable to start request\n"); + fprintf(stderr, "Unable to start PROPFIND request\n"); } free(out_data); @@ -1085,87 +1690,105 @@ static int locking_available(void) return lock_flags; } -static int is_ancestor(unsigned char *sha1, struct commit *commit) +static struct object_list **process_blob(struct blob *blob, + struct object_list **p, + struct name_path *path, + const char *name) { - struct commit_list *parents; + struct object *obj = &blob->object; - if (parse_commit(commit)) - return 0; - parents = commit->parents; - for (; parents; parents = parents->next) { - if (!memcmp(sha1, parents->item->object.sha1, 20)) { - return 1; - } else if (parents->item->object.type == commit_type) { - if (is_ancestor( - sha1, - (struct commit *)&parents->item->object - )) - return 1; - } - } - return 0; + obj->flags |= LOCAL; + + if (obj->flags & (UNINTERESTING | SEEN)) + return p; + + obj->flags |= SEEN; + return add_object(obj, p, path, name); } -static void get_delta(unsigned char *sha1, struct object *obj, - struct active_lock *lock) +static struct object_list **process_tree(struct tree *tree, + struct object_list **p, + struct name_path *path, + const char *name) { - struct commit *commit; - struct commit_list *parents; - struct tree *tree; + struct object *obj = &tree->object; struct tree_entry_list *entry; + struct name_path me; + + obj->flags |= LOCAL; + + if (obj->flags & (UNINTERESTING | SEEN)) + return p; + if (parse_tree(tree) < 0) + die("bad tree object %s", sha1_to_hex(obj->sha1)); + + obj->flags |= SEEN; + p = add_object(obj, p, NULL, 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, &me, entry->name); + else + p = process_blob(entry->item.blob, p, &me, entry->name); + free(entry); + entry = next; + } + return p; +} - if (sha1 && !memcmp(sha1, obj->sha1, 20)) - return; +static int get_delta(struct rev_info *revs, struct remote_lock *lock) +{ + struct commit *commit; + struct object_list **p = &objects, *pending; + int count = 0; + + while ((commit = get_revision(revs)) != NULL) { + p = process_tree(commit->tree, p, NULL, ""); + commit->object.flags |= LOCAL; + if (!(commit->object.flags & UNINTERESTING)) + count += add_send_request(&commit->object, lock); + } - if (aborted) - return; + for (pending = revs->pending_objects; pending; pending = pending->next) { + struct object *obj = pending->item; + const char *name = pending->name; - if (obj->type == commit_type) { - if (push_verbosely) - fprintf(stderr, "walk %s\n", sha1_to_hex(obj->sha1)); - add_request(obj->sha1, lock); - commit = (struct commit *)obj; - if (parse_commit(commit)) { - fprintf(stderr, "Error parsing commit %s\n", - sha1_to_hex(obj->sha1)); - aborted = 1; - return; + if (obj->flags & (UNINTERESTING | SEEN)) + continue; + if (obj->type == tag_type) { + obj->flags |= SEEN; + p = add_object(obj, p, NULL, name); + continue; } - parents = commit->parents; - for (; parents; parents = parents->next) - if (sha1 == NULL || - memcmp(sha1, parents->item->object.sha1, 20)) - get_delta(sha1, &parents->item->object, - lock); - get_delta(sha1, &commit->tree->object, lock); - } else if (obj->type == tree_type) { - if (push_verbosely) - fprintf(stderr, "walk %s\n", sha1_to_hex(obj->sha1)); - add_request(obj->sha1, lock); - tree = (struct tree *)obj; - if (parse_tree(tree)) { - fprintf(stderr, "Error parsing tree %s\n", - sha1_to_hex(obj->sha1)); - aborted = 1; - return; + if (obj->type == tree_type) { + p = process_tree((struct tree *)obj, p, NULL, name); + continue; } - entry = tree->entries; - tree->entries = NULL; - while (entry) { - struct tree_entry_list *next = entry->next; - get_delta(sha1, entry->item.any, lock); - free(entry->name); - free(entry); - entry = next; + if (obj->type == blob_type) { + p = process_blob((struct blob *)obj, p, NULL, name); + continue; } - } else if (obj->type == blob_type || obj->type == tag_type) { - add_request(obj->sha1, lock); + die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); } + + while (objects) { + if (!(objects->item->flags & UNINTERESTING)) + count += add_send_request(objects->item, lock); + objects = objects->next; + } + + return count; } -static int update_remote(unsigned char *sha1, struct active_lock *lock) +static int update_remote(unsigned char *sha1, struct remote_lock *lock) { struct active_request_slot *slot; + struct slot_results results; char *out_data; char *if_header; struct buffer out_buffer; @@ -1187,6 +1810,7 @@ static int update_remote(unsigned char *sha1, struct active_lock *lock) out_buffer.buffer = out_data; slot = get_active_slot(); + slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer); curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size); curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); @@ -1201,10 +1825,10 @@ static int update_remote(unsigned char *sha1, struct active_lock *lock) run_active_slot(slot); free(out_data); free(if_header); - if (slot->curl_result != CURLE_OK) { + if (results.curl_result != CURLE_OK) { fprintf(stderr, "PUT error: curl result=%d, HTTP code=%ld\n", - slot->curl_result, slot->http_code); + results.curl_result, results.http_code); /* We should attempt recovery? */ return 0; } @@ -1218,38 +1842,489 @@ static int update_remote(unsigned char *sha1, struct active_lock *lock) return 1; } +static struct ref *local_refs, **local_tail; +static struct ref *remote_refs, **remote_tail; + +static int one_local_ref(const char *refname, const unsigned char *sha1) +{ + struct ref *ref; + int len = strlen(refname) + 1; + ref = xcalloc(1, sizeof(*ref) + len); + memcpy(ref->new_sha1, sha1, 20); + memcpy(ref->name, refname, len); + *local_tail = ref; + local_tail = &ref->next; + return 0; +} + +static void one_remote_ref(char *refname) +{ + struct ref *ref; + unsigned char remote_sha1[20]; + struct object *obj; + int len = strlen(refname) + 1; + + if (fetch_ref(refname, remote_sha1) != 0) { + fprintf(stderr, + "Unable to fetch ref %s from %s\n", + refname, remote->url); + return; + } + + /* + * Fetch a copy of the object if it doesn't exist locally - it + * may be required for updating server info later. + */ + if (remote->can_update_info_refs && !has_sha1_file(remote_sha1)) { + obj = lookup_unknown_object(remote_sha1); + if (obj) { + fprintf(stderr, " fetch %s for %s\n", + sha1_to_hex(remote_sha1), refname); + add_fetch_request(obj); + } + } + + ref = xcalloc(1, sizeof(*ref) + len); + memcpy(ref->old_sha1, remote_sha1, 20); + memcpy(ref->name, refname, len); + *remote_tail = ref; + remote_tail = &ref->next; +} + +static void get_local_heads(void) +{ + local_tail = &local_refs; + for_each_ref(one_local_ref); +} + +static void get_dav_remote_heads(void) +{ + remote_tail = &remote_refs; + remote_ls("refs/", (PROCESS_FILES | PROCESS_DIRS | RECURSIVE), process_ls_ref, NULL); +} + +static int is_zero_sha1(const unsigned char *sha1) +{ + int i; + + for (i = 0; i < 20; i++) { + if (*sha1++) + return 0; + } + return 1; +} + +static void unmark_and_free(struct commit_list *list, unsigned int mark) +{ + while (list) { + struct commit_list *temp = list; + temp->item->object.flags &= ~mark; + list = temp->next; + free(temp); + } +} + +static int ref_newer(const unsigned char *new_sha1, + const unsigned char *old_sha1) +{ + struct object *o; + struct commit *old, *new; + struct commit_list *list, *used; + int found = 0; + + /* Both new and old must be commit-ish and new is descendant of + * old. Otherwise we require --force. + */ + o = deref_tag(parse_object(old_sha1), NULL, 0); + if (!o || o->type != commit_type) + return 0; + old = (struct commit *) o; + + o = deref_tag(parse_object(new_sha1), NULL, 0); + if (!o || o->type != commit_type) + return 0; + new = (struct commit *) o; + + if (parse_commit(new) < 0) + return 0; + + used = list = NULL; + commit_list_insert(new, &list); + while (list) { + new = pop_most_recent_commit(&list, TMP_MARK); + commit_list_insert(new, &used); + if (new == old) { + found = 1; + break; + } + } + unmark_and_free(list, TMP_MARK); + unmark_and_free(used, TMP_MARK); + return found; +} + +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); + } +} + +static void mark_edges_uninteresting(struct commit_list *list) +{ + for ( ; list; list = list->next) { + struct commit *commit = list->item; + + if (commit->object.flags & UNINTERESTING) { + mark_tree_uninteresting(commit->tree); + continue; + } + mark_edge_parents_uninteresting(commit); + } +} + +static void add_remote_info_ref(struct remote_ls_ctx *ls) +{ + struct buffer *buf = (struct buffer *)ls->userData; + unsigned char remote_sha1[20]; + struct object *o; + int len; + char *ref_info; + + if (fetch_ref(ls->dentry_name, remote_sha1) != 0) { + fprintf(stderr, + "Unable to fetch ref %s from %s\n", + ls->dentry_name, remote->url); + aborted = 1; + return; + } + + o = parse_object(remote_sha1); + if (!o) { + fprintf(stderr, + "Unable to parse object %s for remote ref %s\n", + sha1_to_hex(remote_sha1), ls->dentry_name); + aborted = 1; + return; + } + + len = strlen(ls->dentry_name) + 42; + ref_info = xcalloc(len + 1, 1); + sprintf(ref_info, "%s %s\n", + sha1_to_hex(remote_sha1), ls->dentry_name); + fwrite_buffer(ref_info, 1, len, buf); + free(ref_info); + + if (o->type == tag_type) { + o = deref_tag(o, ls->dentry_name, 0); + if (o) { + len = strlen(ls->dentry_name) + 45; + ref_info = xcalloc(len + 1, 1); + sprintf(ref_info, "%s %s^{}\n", + sha1_to_hex(o->sha1), ls->dentry_name); + fwrite_buffer(ref_info, 1, len, buf); + free(ref_info); + } + } +} + +static void update_remote_info_refs(struct remote_lock *lock) +{ + struct buffer buffer; + struct active_request_slot *slot; + struct slot_results results; + char *if_header; + struct curl_slist *dav_headers = NULL; + + buffer.buffer = xcalloc(1, 4096); + buffer.size = 4096; + buffer.posn = 0; + remote_ls("refs/", (PROCESS_FILES | RECURSIVE), + add_remote_info_ref, &buffer); + if (!aborted) { + if_header = xmalloc(strlen(lock->token) + 25); + sprintf(if_header, "If: (<opaquelocktoken:%s>)", lock->token); + dav_headers = curl_slist_append(dav_headers, if_header); + + slot = get_active_slot(); + slot->results = &results; + curl_easy_setopt(slot->curl, CURLOPT_INFILE, &buffer); + curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, buffer.posn); + curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_null); + curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_PUT); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, dav_headers); + curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 1); + curl_easy_setopt(slot->curl, CURLOPT_PUT, 1); + curl_easy_setopt(slot->curl, CURLOPT_URL, lock->url); + + buffer.posn = 0; + + if (start_active_slot(slot)) { + run_active_slot(slot); + if (results.curl_result != CURLE_OK) { + fprintf(stderr, + "PUT error: curl result=%d, HTTP code=%ld\n", + results.curl_result, results.http_code); + } + } + free(if_header); + } + free(buffer.buffer); +} + +static int remote_exists(const char *path) +{ + char *url = xmalloc(strlen(remote->url) + strlen(path) + 1); + struct active_request_slot *slot; + struct slot_results results; + + sprintf(url, "%s%s", remote->url, path); + + slot = get_active_slot(); + slot->results = &results; + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 1); + + if (start_active_slot(slot)) { + run_active_slot(slot); + if (results.http_code == 404) + return 0; + else if (results.curl_result == CURLE_OK) + return 1; + else + fprintf(stderr, "HEAD HTTP error %ld\n", results.http_code); + } else { + fprintf(stderr, "Unable to start HEAD request\n"); + } + + return -1; +} + +static void fetch_symref(char *path, char **symref, unsigned char *sha1) +{ + char *url; + struct buffer buffer; + struct active_request_slot *slot; + struct slot_results results; + + url = xmalloc(strlen(remote->url) + strlen(path) + 1); + sprintf(url, "%s%s", remote->url, path); + + buffer.size = 4096; + buffer.posn = 0; + buffer.buffer = xmalloc(buffer.size); + + slot = get_active_slot(); + slot->results = &results; + curl_easy_setopt(slot->curl, CURLOPT_FILE, &buffer); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, NULL); + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + if (start_active_slot(slot)) { + run_active_slot(slot); + if (results.curl_result != CURLE_OK) { + die("Couldn't get %s for remote symref\n%s", + url, curl_errorstr); + } + } else { + die("Unable to start remote symref request"); + } + free(url); + + if (*symref != NULL) + free(*symref); + *symref = NULL; + memset(sha1, 0, 20); + + if (buffer.posn == 0) + return; + + /* If it's a symref, set the refname; otherwise try for a sha1 */ + if (!strncmp((char *)buffer.buffer, "ref: ", 5)) { + *symref = xcalloc(buffer.posn - 5, 1); + strncpy(*symref, (char *)buffer.buffer + 5, buffer.posn - 6); + } else { + get_sha1_hex(buffer.buffer, sha1); + } + + free(buffer.buffer); +} + +static int verify_merge_base(unsigned char *head_sha1, unsigned char *branch_sha1) +{ + int pipe_fd[2]; + pid_t merge_base_pid; + char line[PATH_MAX + 20]; + unsigned char merge_sha1[20]; + int verified = 0; + + if (pipe(pipe_fd) < 0) + die("Verify merge base: pipe failed"); + + merge_base_pid = fork(); + if (!merge_base_pid) { + static const char *args[] = { + "merge-base", + "-a", + NULL, + NULL, + NULL + }; + args[2] = strdup(sha1_to_hex(head_sha1)); + args[3] = sha1_to_hex(branch_sha1); + + dup2(pipe_fd[1], 1); + close(pipe_fd[0]); + close(pipe_fd[1]); + execv_git_cmd(args); + die("merge-base setup failed"); + } + if (merge_base_pid < 0) + die("merge-base fork failed"); + + dup2(pipe_fd[0], 0); + close(pipe_fd[0]); + close(pipe_fd[1]); + while (fgets(line, sizeof(line), stdin) != NULL) { + if (get_sha1_hex(line, merge_sha1)) + die("expected sha1, got garbage:\n %s", line); + if (!memcmp(branch_sha1, merge_sha1, 20)) { + verified = 1; + break; + } + } + + return verified; +} + +static int delete_remote_branch(char *pattern, int force) +{ + struct ref *refs = remote_refs; + struct ref *remote_ref = NULL; + unsigned char head_sha1[20]; + char *symref = NULL; + int match; + int patlen = strlen(pattern); + int i; + struct active_request_slot *slot; + struct slot_results results; + char *url; + + /* Find the remote branch(es) matching the specified branch name */ + for (match = 0; refs; refs = refs->next) { + char *name = refs->name; + int namelen = strlen(name); + if (namelen < patlen || + memcmp(name + namelen - patlen, pattern, patlen)) + continue; + if (namelen != patlen && name[namelen - patlen - 1] != '/') + continue; + match++; + remote_ref = refs; + } + if (match == 0) + return error("No remote branch matches %s", pattern); + if (match != 1) + return error("More than one remote branch matches %s", + pattern); + + /* + * Remote HEAD must be a symref (not exactly foolproof; a remote + * symlink to a symref will look like a symref) + */ + fetch_symref("HEAD", &symref, head_sha1); + if (!symref) + return error("Remote HEAD is not a symref"); + + /* Remote branch must not be the remote HEAD */ + for (i=0; symref && i<MAXDEPTH; i++) { + if (!strcmp(remote_ref->name, symref)) + return error("Remote branch %s is the current HEAD", + remote_ref->name); + fetch_symref(symref, &symref, head_sha1); + } + + /* Run extra sanity checks if delete is not forced */ + if (!force) { + /* Remote HEAD must resolve to a known object */ + if (symref) + return error("Remote HEAD symrefs too deep"); + if (is_zero_sha1(head_sha1)) + return error("Unable to resolve remote HEAD"); + if (!has_sha1_file(head_sha1)) + return error("Remote HEAD resolves to object %s\nwhich does not exist locally, perhaps you need to fetch?", sha1_to_hex(head_sha1)); + + /* Remote branch must resolve to a known object */ + if (is_zero_sha1(remote_ref->old_sha1)) + return error("Unable to resolve remote branch %s", + remote_ref->name); + if (!has_sha1_file(remote_ref->old_sha1)) + return error("Remote branch %s resolves to object %s\nwhich does not exist locally, perhaps you need to fetch?", remote_ref->name, sha1_to_hex(remote_ref->old_sha1)); + + /* Remote branch must be an ancestor of remote HEAD */ + if (!verify_merge_base(head_sha1, remote_ref->old_sha1)) { + return error("The branch '%s' is not a strict subset of your current HEAD.\nIf you are sure you want to delete it, run:\n\t'git http-push -D %s %s'", remote_ref->name, remote->url, pattern); + } + } + + /* Send delete request */ + fprintf(stderr, "Removing remote branch '%s'\n", remote_ref->name); + url = xmalloc(strlen(remote->url) + strlen(remote_ref->name) + 1); + sprintf(url, "%s%s", remote->url, remote_ref->name); + slot = get_active_slot(); + slot->results = &results; + curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_null); + curl_easy_setopt(slot->curl, CURLOPT_URL, url); + curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_DELETE); + if (start_active_slot(slot)) { + run_active_slot(slot); + free(url); + if (results.curl_result != CURLE_OK) + return error("DELETE request failed (%d/%ld)\n", + results.curl_result, results.http_code); + } else { + free(url); + return error("Unable to start DELETE request"); + } + + return 0; +} + int main(int argc, char **argv) { struct transfer_request *request; struct transfer_request *next_request; int nr_refspec = 0; char **refspec = NULL; - int do_remote_update; - int new_branch; - int force_this; - char *local_ref; - unsigned char local_sha1[20]; - struct object *local_object = NULL; - char *remote_ref = NULL; - unsigned char remote_sha1[20]; - struct active_lock *remote_lock; - char *remote_path = NULL; + struct remote_lock *ref_lock = NULL; + struct remote_lock *info_ref_lock = NULL; + struct rev_info revs; + int delete_branch = 0; + int force_delete = 0; + int objects_to_send; int rc = 0; int i; + int new_refs; + struct ref *ref; setup_git_directory(); setup_ident(); - remote = xmalloc(sizeof(*remote)); - remote->url = NULL; - remote->packs = NULL; + remote = xcalloc(sizeof(*remote), 1); argv++; for (i = 1; i < argc; i++, argv++) { char *arg = *argv; if (*arg == '-') { - if (!strcmp(arg, "--complete")) { + if (!strcmp(arg, "--all")) { push_all = 1; continue; } @@ -1261,10 +2336,24 @@ int main(int argc, char **argv) push_verbosely = 1; continue; } - usage(http_push_usage); + if (!strcmp(arg, "-d")) { + delete_branch = 1; + continue; + } + if (!strcmp(arg, "-D")) { + delete_branch = 1; + force_delete = 1; + continue; + } } if (!remote->url) { + char *path = strstr(arg, "//"); remote->url = arg; + if (path) { + path = index(path+2, '/'); + if (path) + remote->path_len = strlen(path); + } continue; } refspec = argv; @@ -1275,7 +2364,10 @@ int main(int argc, char **argv) if (!remote->url) usage(http_push_usage); - memset(remote_dir_exists, 0, 256); + if (delete_branch && nr_refspec != 1) + die("You must specify only one branch name when deleting a remote branch"); + + memset(remote_dir_exists, -1, 256); http_init(); @@ -1293,121 +2385,165 @@ int main(int argc, char **argv) goto cleanup; } - /* Process each refspec */ - for (i = 0; i < nr_refspec; i++) { - char *ep; - force_this = 0; - do_remote_update = 0; - new_branch = 0; - local_ref = refspec[i]; - if (*local_ref == '+') { - force_this = 1; - local_ref++; + /* Check whether the remote has server info files */ + remote->can_update_info_refs = 0; + remote->has_info_refs = remote_exists("info/refs"); + remote->has_info_packs = remote_exists("objects/info/packs"); + if (remote->has_info_refs) { + info_ref_lock = lock_remote("info/refs", LOCK_TIME); + if (info_ref_lock) + remote->can_update_info_refs = 1; + } + if (remote->has_info_packs) + fetch_indices(); + + /* Get a list of all local and remote heads to validate refspecs */ + get_local_heads(); + fprintf(stderr, "Fetching remote heads...\n"); + get_dav_remote_heads(); + + /* Remove a remote branch if -d or -D was specified */ + if (delete_branch) { + if (delete_remote_branch(refspec[0], force_delete) == -1) + fprintf(stderr, "Unable to delete remote branch %s\n", + refspec[0]); + goto cleanup; + } + + /* match them up */ + if (!remote_tail) + remote_tail = &remote_refs; + if (match_refs(local_refs, remote_refs, &remote_tail, + nr_refspec, refspec, push_all)) + return -1; + if (!remote_refs) { + fprintf(stderr, "No refs in common and none specified; doing nothing.\n"); + return 0; + } + + new_refs = 0; + for (ref = remote_refs; ref; ref = ref->next) { + char old_hex[60], *new_hex; + const char *commit_argv[4]; + int commit_argc; + char *new_sha1_hex, *old_sha1_hex; + + if (!ref->peer_ref) + continue; + if (!memcmp(ref->old_sha1, ref->peer_ref->new_sha1, 20)) { + if (push_verbosely || 1) + fprintf(stderr, "'%s': up-to-date\n", ref->name); + continue; } - ep = strchr(local_ref, ':'); - if (ep) { - remote_ref = ep + 1; - *ep = 0; + + if (!force_all && + !is_zero_sha1(ref->old_sha1) && + !ref->force) { + if (!has_sha1_file(ref->old_sha1) || + !ref_newer(ref->peer_ref->new_sha1, + ref->old_sha1)) { + /* We do not have the remote ref, or + * we know that the remote ref is not + * an ancestor of what we are trying to + * push. Either way this can be losing + * commits at the remote end and likely + * we were not up to date to begin with. + */ + error("remote '%s' is not a strict " + "subset of local ref '%s'. " + "maybe you are not up-to-date and " + "need to pull first?", + ref->name, + ref->peer_ref->name); + rc = -2; + continue; + } } - else - remote_ref = local_ref; + memcpy(ref->new_sha1, ref->peer_ref->new_sha1, 20); + if (is_zero_sha1(ref->new_sha1)) { + error("cannot happen anymore"); + rc = -3; + continue; + } + new_refs++; + strcpy(old_hex, sha1_to_hex(ref->old_sha1)); + new_hex = sha1_to_hex(ref->new_sha1); + + fprintf(stderr, "updating '%s'", ref->name); + if (strcmp(ref->name, ref->peer_ref->name)) + fprintf(stderr, " using '%s'", ref->peer_ref->name); + fprintf(stderr, "\n from %s\n to %s\n", old_hex, new_hex); + /* Lock remote branch ref */ - if (remote_path) - free(remote_path); - remote_path = xmalloc(strlen(remote_ref) + 12); - sprintf(remote_path, "refs/heads/%s", remote_ref); - remote_lock = lock_remote(remote_path, LOCK_TIME); - if (remote_lock == NULL) { + ref_lock = lock_remote(ref->name, LOCK_TIME); + if (ref_lock == NULL) { fprintf(stderr, "Unable to lock remote branch %s\n", - remote_ref); + ref->name); rc = 1; continue; } - /* Resolve local and remote refs */ - if (fetch_ref(remote_ref, remote_sha1) != 0) { - fprintf(stderr, - "Remote branch %s does not exist on %s\n", - remote_ref, remote->url); - new_branch = 1; + /* Set up revision info for this refspec */ + commit_argc = 3; + new_sha1_hex = strdup(sha1_to_hex(ref->new_sha1)); + old_sha1_hex = NULL; + commit_argv[1] = "--objects"; + commit_argv[2] = new_sha1_hex; + if (!push_all && !is_zero_sha1(ref->old_sha1)) { + old_sha1_hex = xmalloc(42); + sprintf(old_sha1_hex, "^%s", + sha1_to_hex(ref->old_sha1)); + commit_argv[3] = old_sha1_hex; + commit_argc++; } - if (get_sha1(local_ref, local_sha1) != 0) { - fprintf(stderr, "Error resolving local branch %s\n", - local_ref); - rc = 1; - goto unlock; - } - - /* Find relationship between local and remote */ - local_object = parse_object(local_sha1); - if (!local_object) { - fprintf(stderr, "Unable to parse local object %s\n", - sha1_to_hex(local_sha1)); - rc = 1; - goto unlock; - } else if (new_branch) { - do_remote_update = 1; - } else { - if (!memcmp(local_sha1, remote_sha1, 20)) { - fprintf(stderr, - "* %s: same as branch '%s' of %s\n", - local_ref, remote_ref, remote->url); - } else if (is_ancestor(remote_sha1, - (struct commit *)local_object)) { - fprintf(stderr, - "Remote %s will fast-forward to local %s\n", - remote_ref, local_ref); - do_remote_update = 1; - } else if (force_all || force_this) { - fprintf(stderr, - "* %s on %s does not fast forward to local branch '%s', overwriting\n", - remote_ref, remote->url, local_ref); - do_remote_update = 1; - } else { - fprintf(stderr, - "* %s on %s does not fast forward to local branch '%s'\n", - remote_ref, remote->url, local_ref); - rc = 1; - goto unlock; - } + setup_revisions(commit_argc, commit_argv, &revs, NULL); + free(new_sha1_hex); + if (old_sha1_hex) { + free(old_sha1_hex); + commit_argv[1] = NULL; } - /* Generate and check list of required objects */ + /* Generate a list of objects that need to be pushed */ pushing = 0; - if (do_remote_update || push_all) - fetch_indices(); - get_delta(push_all ? NULL : remote_sha1, - local_object, remote_lock); + prepare_revision_walk(&revs); + mark_edges_uninteresting(revs.commits); + objects_to_send = get_delta(&revs, ref_lock); finish_all_active_slots(); /* Push missing objects to remote, this would be a convenient time to pack them first if appropriate. */ pushing = 1; + if (objects_to_send) + fprintf(stderr, " sending %d objects\n", + objects_to_send); fill_active_slots(); finish_all_active_slots(); /* Update the remote branch if all went well */ - if (do_remote_update) { - if (!aborted && update_remote(local_sha1, - remote_lock)) { - fprintf(stderr, "%s remote branch %s\n", - new_branch ? "Created" : "Updated", - remote_ref); - } else { - fprintf(stderr, - "Unable to %s remote branch %s\n", - new_branch ? "create" : "update", - remote_ref); - rc = 1; - goto unlock; - } + if (aborted || !update_remote(ref->new_sha1, ref_lock)) { + rc = 1; + goto unlock; } unlock: - unlock_remote(remote_lock); - free(remote_path); + if (!rc) + fprintf(stderr, " done\n"); + unlock_remote(ref_lock); + check_locks(); + } + + /* Update remote server info if appropriate */ + if (remote->has_info_refs && new_refs) { + if (info_ref_lock && remote->can_update_info_refs) { + fprintf(stderr, "Updating remote server info\n"); + update_remote_info_refs(info_ref_lock); + } else { + fprintf(stderr, "Unable to update server info\n"); + } } + if (info_ref_lock) + unlock_remote(info_ref_lock); cleanup: free(remote); @@ -195,6 +195,8 @@ static CURL* get_curl_handle(void) if (getenv("GIT_CURL_VERBOSE")) curl_easy_setopt(result, CURLOPT_VERBOSE, 1); + curl_easy_setopt(result, CURLOPT_USERAGENT, GIT_USER_AGENT); + return result; } @@ -339,6 +341,7 @@ struct active_request_slot *get_active_slot(void) slot->in_use = 1; slot->local = NULL; slot->results = NULL; + slot->finished = NULL; slot->callback_data = NULL; slot->callback_func = NULL; curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, pragma_header); @@ -389,8 +392,10 @@ void run_active_slot(struct active_request_slot *slot) fd_set excfds; int max_fd; struct timeval select_timeout; + int finished = 0; - while (slot->in_use) { + slot->finished = &finished; + while (!finished) { data_received = 0; step_active_slots(); @@ -442,6 +447,9 @@ static void finish_active_slot(struct active_request_slot *slot) closedown_active_slot(slot); curl_easy_getinfo(slot->curl, CURLINFO_HTTP_CODE, &slot->http_code); + if (slot->finished != NULL) + (*slot->finished) = 1; + /* Store slot results so they can be read after the slot is reused */ if (slot->results != NULL) { slot->results->curl_result = slot->curl_result; @@ -35,6 +35,7 @@ struct active_request_slot int in_use; CURLcode curl_result; long http_code; + int *finished; struct slot_results *results; void *callback_data; void (*callback_func)(void *data); diff --git a/imap-send.c b/imap-send.c new file mode 100644 index 0000000..f3cb79b --- /dev/null +++ b/imap-send.c @@ -0,0 +1,1359 @@ +/* + * git-imap-send - drops patches into an imap Drafts folder + * derived from isync/mbsync - mailbox synchronizer + * + * Copyright (C) 2000-2002 Michael R. Elkins <me@mutt.org> + * Copyright (C) 2002-2004 Oswald Buddenhagen <ossi@users.sf.net> + * Copyright (C) 2004 Theodore Y. Ts'o <tytso@mit.edu> + * Copyright (C) 2006 Mike McCormack + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include "cache.h" + +#include <assert.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <arpa/inet.h> +#include <sys/socket.h> +#include <netdb.h> + +typedef struct store_conf { + char *name; + const char *path; /* should this be here? its interpretation is driver-specific */ + char *map_inbox; + char *trash; + unsigned max_size; /* off_t is overkill */ + unsigned trash_remote_new:1, trash_only_new:1; +} store_conf_t; + +typedef struct string_list { + struct string_list *next; + char string[1]; +} string_list_t; + +typedef struct channel_conf { + struct channel_conf *next; + char *name; + store_conf_t *master, *slave; + char *master_name, *slave_name; + char *sync_state; + string_list_t *patterns; + int mops, sops; + unsigned max_messages; /* for slave only */ +} channel_conf_t; + +typedef struct group_conf { + struct group_conf *next; + char *name; + string_list_t *channels; +} group_conf_t; + +/* For message->status */ +#define M_RECENT (1<<0) /* unsyncable flag; maildir_* depend on this being 1<<0 */ +#define M_DEAD (1<<1) /* expunged */ +#define M_FLAGS (1<<2) /* flags fetched */ + +typedef struct message { + struct message *next; + /* string_list_t *keywords; */ + size_t size; /* zero implies "not fetched" */ + int uid; + unsigned char flags, status; +} message_t; + +typedef struct store { + store_conf_t *conf; /* foreign */ + + /* currently open mailbox */ + const char *name; /* foreign! maybe preset? */ + char *path; /* own */ + message_t *msgs; /* own */ + int uidvalidity; + unsigned char opts; /* maybe preset? */ + /* note that the following do _not_ reflect stats from msgs, but mailbox totals */ + int count; /* # of messages */ + int recent; /* # of recent messages - don't trust this beyond the initial read */ +} store_t; + +typedef struct { + char *data; + int len; + unsigned char flags; + unsigned char crlf:1; +} msg_data_t; + +#define DRV_OK 0 +#define DRV_MSG_BAD -1 +#define DRV_BOX_BAD -2 +#define DRV_STORE_BAD -3 + +static int Verbose, Quiet; + +static void info( const char *, ... ); +static void warn( const char *, ... ); + +static char *next_arg( char ** ); + +static void free_generic_messages( message_t * ); + +static int nfvasprintf( char **str, const char *fmt, va_list va ); +static int nfsnprintf( char *buf, int blen, const char *fmt, ... ); + + +static void arc4_init( void ); +static unsigned char arc4_getbyte( void ); + +typedef struct imap_server_conf { + char *name; + char *tunnel; + char *host; + int port; + char *user; + char *pass; +} imap_server_conf_t; + +typedef struct imap_store_conf { + store_conf_t gen; + imap_server_conf_t *server; + unsigned use_namespace:1; +} imap_store_conf_t; + +#define NIL (void*)0x1 +#define LIST (void*)0x2 + +typedef struct _list { + struct _list *next, *child; + char *val; + int len; +} list_t; + +typedef struct { + int fd; +} Socket_t; + +typedef struct { + Socket_t sock; + int bytes; + int offset; + char buf[1024]; +} buffer_t; + +struct imap_cmd; + +typedef struct imap { + int uidnext; /* from SELECT responses */ + list_t *ns_personal, *ns_other, *ns_shared; /* NAMESPACE info */ + unsigned caps, rcaps; /* CAPABILITY results */ + /* command queue */ + int nexttag, num_in_progress, literal_pending; + struct imap_cmd *in_progress, **in_progress_append; + buffer_t buf; /* this is BIG, so put it last */ +} imap_t; + +typedef struct imap_store { + store_t gen; + int uidvalidity; + imap_t *imap; + const char *prefix; + unsigned /*currentnc:1,*/ trashnc:1; +} imap_store_t; + +struct imap_cmd_cb { + int (*cont)( imap_store_t *ctx, struct imap_cmd *cmd, const char *prompt ); + void (*done)( imap_store_t *ctx, struct imap_cmd *cmd, int response); + void *ctx; + char *data; + int dlen; + int uid; + unsigned create:1, trycreate:1; +}; + +struct imap_cmd { + struct imap_cmd *next; + struct imap_cmd_cb cb; + char *cmd; + int tag; +}; + +#define CAP(cap) (imap->caps & (1 << (cap))) + +enum CAPABILITY { + NOLOGIN = 0, + UIDPLUS, + LITERALPLUS, + NAMESPACE, +}; + +static const char *cap_list[] = { + "LOGINDISABLED", + "UIDPLUS", + "LITERAL+", + "NAMESPACE", +}; + +#define RESP_OK 0 +#define RESP_NO 1 +#define RESP_BAD 2 + +static int get_cmd_result( imap_store_t *ctx, struct imap_cmd *tcmd ); + + +static const char *Flags[] = { + "Draft", + "Flagged", + "Answered", + "Seen", + "Deleted", +}; + +static void +socket_perror( const char *func, Socket_t *sock, int ret ) +{ + if (ret < 0) + perror( func ); + else + fprintf( stderr, "%s: unexpected EOF\n", func ); +} + +static int +socket_read( Socket_t *sock, char *buf, int len ) +{ + int n = read( sock->fd, buf, len ); + if (n <= 0) { + socket_perror( "read", sock, n ); + close( sock->fd ); + sock->fd = -1; + } + return n; +} + +static int +socket_write( Socket_t *sock, char *buf, int len ) +{ + int n = write( sock->fd, buf, len ); + if (n != len) { + socket_perror( "write", sock, n ); + close( sock->fd ); + sock->fd = -1; + } + return n; +} + +/* simple line buffering */ +static int +buffer_gets( buffer_t * b, char **s ) +{ + int n; + int start = b->offset; + + *s = b->buf + start; + + for (;;) { + /* make sure we have enough data to read the \r\n sequence */ + if (b->offset + 1 >= b->bytes) { + if (start) { + /* shift down used bytes */ + *s = b->buf; + + assert( start <= b->bytes ); + n = b->bytes - start; + + if (n) + memcpy( b->buf, b->buf + start, n ); + b->offset -= start; + b->bytes = n; + start = 0; + } + + n = socket_read( &b->sock, b->buf + b->bytes, + sizeof(b->buf) - b->bytes ); + + if (n <= 0) + return -1; + + b->bytes += n; + } + + if (b->buf[b->offset] == '\r') { + assert( b->offset + 1 < b->bytes ); + if (b->buf[b->offset + 1] == '\n') { + b->buf[b->offset] = 0; /* terminate the string */ + b->offset += 2; /* next line */ + if (Verbose) + puts( *s ); + return 0; + } + } + + b->offset++; + } + /* not reached */ +} + +static void +info( const char *msg, ... ) +{ + va_list va; + + if (!Quiet) { + va_start( va, msg ); + vprintf( msg, va ); + va_end( va ); + fflush( stdout ); + } +} + +static void +warn( const char *msg, ... ) +{ + va_list va; + + if (Quiet < 2) { + va_start( va, msg ); + vfprintf( stderr, msg, va ); + va_end( va ); + } +} + +static char * +next_arg( char **s ) +{ + char *ret; + + if (!s || !*s) + return NULL; + while (isspace( (unsigned char) **s )) + (*s)++; + if (!**s) { + *s = NULL; + return NULL; + } + if (**s == '"') { + ++*s; + ret = *s; + *s = strchr( *s, '"' ); + } else { + ret = *s; + while (**s && !isspace( (unsigned char) **s )) + (*s)++; + } + if (*s) { + if (**s) + *(*s)++ = 0; + if (!**s) + *s = NULL; + } + return ret; +} + +static void +free_generic_messages( message_t *msgs ) +{ + message_t *tmsg; + + for (; msgs; msgs = tmsg) { + tmsg = msgs->next; + free( msgs ); + } +} + +static int +git_vasprintf( char **strp, const char *fmt, va_list ap ) +{ + int len; + char tmp[1024]; + + if ((len = vsnprintf( tmp, sizeof(tmp), fmt, ap )) < 0 || !(*strp = xmalloc( len + 1 ))) + return -1; + if (len >= (int)sizeof(tmp)) + vsprintf( *strp, fmt, ap ); + else + memcpy( *strp, tmp, len + 1 ); + return len; +} + +static int +nfsnprintf( char *buf, int blen, const char *fmt, ... ) +{ + int ret; + va_list va; + + va_start( va, fmt ); + if (blen <= 0 || (unsigned)(ret = vsnprintf( buf, blen, fmt, va )) >= (unsigned)blen) + die( "Fatal: buffer too small. Please report a bug.\n"); + va_end( va ); + return ret; +} + +static int +nfvasprintf( char **str, const char *fmt, va_list va ) +{ + int ret = git_vasprintf( str, fmt, va ); + if (ret < 0) + die( "Fatal: Out of memory\n"); + return ret; +} + +static struct { + unsigned char i, j, s[256]; +} rs; + +static void +arc4_init( void ) +{ + int i, fd; + unsigned char j, si, dat[128]; + + if ((fd = open( "/dev/urandom", O_RDONLY )) < 0 && (fd = open( "/dev/random", O_RDONLY )) < 0) { + fprintf( stderr, "Fatal: no random number source available.\n" ); + exit( 3 ); + } + if (read( fd, dat, 128 ) != 128) { + fprintf( stderr, "Fatal: cannot read random number source.\n" ); + exit( 3 ); + } + close( fd ); + + for (i = 0; i < 256; i++) + rs.s[i] = i; + for (i = j = 0; i < 256; i++) { + si = rs.s[i]; + j += si + dat[i & 127]; + rs.s[i] = rs.s[j]; + rs.s[j] = si; + } + rs.i = rs.j = 0; + + for (i = 0; i < 256; i++) + arc4_getbyte(); +} + +static unsigned char +arc4_getbyte( void ) +{ + unsigned char si, sj; + + rs.i++; + si = rs.s[rs.i]; + rs.j += si; + sj = rs.s[rs.j]; + rs.s[rs.i] = sj; + rs.s[rs.j] = si; + return rs.s[(si + sj) & 0xff]; +} + +static struct imap_cmd * +v_issue_imap_cmd( imap_store_t *ctx, struct imap_cmd_cb *cb, + const char *fmt, va_list ap ) +{ + imap_t *imap = ctx->imap; + struct imap_cmd *cmd; + int n, bufl; + char buf[1024]; + + cmd = xmalloc( sizeof(struct imap_cmd) ); + nfvasprintf( &cmd->cmd, fmt, ap ); + cmd->tag = ++imap->nexttag; + + if (cb) + cmd->cb = *cb; + else + memset( &cmd->cb, 0, sizeof(cmd->cb) ); + + while (imap->literal_pending) + get_cmd_result( ctx, NULL ); + + bufl = nfsnprintf( buf, sizeof(buf), cmd->cb.data ? CAP(LITERALPLUS) ? + "%d %s{%d+}\r\n" : "%d %s{%d}\r\n" : "%d %s\r\n", + cmd->tag, cmd->cmd, cmd->cb.dlen ); + if (Verbose) { + if (imap->num_in_progress) + printf( "(%d in progress) ", imap->num_in_progress ); + if (memcmp( cmd->cmd, "LOGIN", 5 )) + printf( ">>> %s", buf ); + else + printf( ">>> %d LOGIN <user> <pass>\n", cmd->tag ); + } + if (socket_write( &imap->buf.sock, buf, bufl ) != bufl) { + free( cmd->cmd ); + free( cmd ); + if (cb && cb->data) + free( cb->data ); + return NULL; + } + if (cmd->cb.data) { + if (CAP(LITERALPLUS)) { + n = socket_write( &imap->buf.sock, cmd->cb.data, cmd->cb.dlen ); + free( cmd->cb.data ); + if (n != cmd->cb.dlen || + (n = socket_write( &imap->buf.sock, "\r\n", 2 )) != 2) + { + free( cmd->cmd ); + free( cmd ); + return NULL; + } + cmd->cb.data = NULL; + } else + imap->literal_pending = 1; + } else if (cmd->cb.cont) + imap->literal_pending = 1; + cmd->next = NULL; + *imap->in_progress_append = cmd; + imap->in_progress_append = &cmd->next; + imap->num_in_progress++; + return cmd; +} + +static struct imap_cmd * +issue_imap_cmd( imap_store_t *ctx, struct imap_cmd_cb *cb, const char *fmt, ... ) +{ + struct imap_cmd *ret; + va_list ap; + + va_start( ap, fmt ); + ret = v_issue_imap_cmd( ctx, cb, fmt, ap ); + va_end( ap ); + return ret; +} + +static int +imap_exec( imap_store_t *ctx, struct imap_cmd_cb *cb, const char *fmt, ... ) +{ + va_list ap; + struct imap_cmd *cmdp; + + va_start( ap, fmt ); + cmdp = v_issue_imap_cmd( ctx, cb, fmt, ap ); + va_end( ap ); + if (!cmdp) + return RESP_BAD; + + return get_cmd_result( ctx, cmdp ); +} + +static int +imap_exec_m( imap_store_t *ctx, struct imap_cmd_cb *cb, const char *fmt, ... ) +{ + va_list ap; + struct imap_cmd *cmdp; + + va_start( ap, fmt ); + cmdp = v_issue_imap_cmd( ctx, cb, fmt, ap ); + va_end( ap ); + if (!cmdp) + return DRV_STORE_BAD; + + switch (get_cmd_result( ctx, cmdp )) { + case RESP_BAD: return DRV_STORE_BAD; + case RESP_NO: return DRV_MSG_BAD; + default: return DRV_OK; + } +} + +static int +is_atom( list_t *list ) +{ + return list && list->val && list->val != NIL && list->val != LIST; +} + +static int +is_list( list_t *list ) +{ + return list && list->val == LIST; +} + +static void +free_list( list_t *list ) +{ + list_t *tmp; + + for (; list; list = tmp) { + tmp = list->next; + if (is_list( list )) + free_list( list->child ); + else if (is_atom( list )) + free( list->val ); + free( list ); + } +} + +static int +parse_imap_list_l( imap_t *imap, char **sp, list_t **curp, int level ) +{ + list_t *cur; + char *s = *sp, *p; + int n, bytes; + + for (;;) { + while (isspace( (unsigned char)*s )) + s++; + if (level && *s == ')') { + s++; + break; + } + *curp = cur = xmalloc( sizeof(*cur) ); + curp = &cur->next; + cur->val = NULL; /* for clean bail */ + if (*s == '(') { + /* sublist */ + s++; + cur->val = LIST; + if (parse_imap_list_l( imap, &s, &cur->child, level + 1 )) + goto bail; + } else if (imap && *s == '{') { + /* literal */ + bytes = cur->len = strtol( s + 1, &s, 10 ); + if (*s != '}') + goto bail; + + s = cur->val = xmalloc( cur->len ); + + /* dump whats left over in the input buffer */ + n = imap->buf.bytes - imap->buf.offset; + + if (n > bytes) + /* the entire message fit in the buffer */ + n = bytes; + + memcpy( s, imap->buf.buf + imap->buf.offset, n ); + s += n; + bytes -= n; + + /* mark that we used part of the buffer */ + imap->buf.offset += n; + + /* now read the rest of the message */ + while (bytes > 0) { + if ((n = socket_read (&imap->buf.sock, s, bytes)) <= 0) + goto bail; + s += n; + bytes -= n; + } + + if (buffer_gets( &imap->buf, &s )) + goto bail; + } else if (*s == '"') { + /* quoted string */ + s++; + p = s; + for (; *s != '"'; s++) + if (!*s) + goto bail; + cur->len = s - p; + s++; + cur->val = xmalloc( cur->len + 1 ); + memcpy( cur->val, p, cur->len ); + cur->val[cur->len] = 0; + } else { + /* atom */ + p = s; + for (; *s && !isspace( (unsigned char)*s ); s++) + if (level && *s == ')') + break; + cur->len = s - p; + if (cur->len == 3 && !memcmp ("NIL", p, 3)) + cur->val = NIL; + else { + cur->val = xmalloc( cur->len + 1 ); + memcpy( cur->val, p, cur->len ); + cur->val[cur->len] = 0; + } + } + + if (!level) + break; + if (!*s) + goto bail; + } + *sp = s; + *curp = NULL; + return 0; + + bail: + *curp = NULL; + return -1; +} + +static list_t * +parse_imap_list( imap_t *imap, char **sp ) +{ + list_t *head; + + if (!parse_imap_list_l( imap, sp, &head, 0 )) + return head; + free_list( head ); + return NULL; +} + +static list_t * +parse_list( char **sp ) +{ + return parse_imap_list( NULL, sp ); +} + +static void +parse_capability( imap_t *imap, char *cmd ) +{ + char *arg; + unsigned i; + + imap->caps = 0x80000000; + while ((arg = next_arg( &cmd ))) + for (i = 0; i < ARRAY_SIZE(cap_list); i++) + if (!strcmp( cap_list[i], arg )) + imap->caps |= 1 << i; + imap->rcaps = imap->caps; +} + +static int +parse_response_code( imap_store_t *ctx, struct imap_cmd_cb *cb, char *s ) +{ + imap_t *imap = ctx->imap; + char *arg, *p; + + if (*s != '[') + return RESP_OK; /* no response code */ + s++; + if (!(p = strchr( s, ']' ))) { + fprintf( stderr, "IMAP error: malformed response code\n" ); + return RESP_BAD; + } + *p++ = 0; + arg = next_arg( &s ); + if (!strcmp( "UIDVALIDITY", arg )) { + if (!(arg = next_arg( &s )) || !(ctx->gen.uidvalidity = atoi( arg ))) { + fprintf( stderr, "IMAP error: malformed UIDVALIDITY status\n" ); + return RESP_BAD; + } + } else if (!strcmp( "UIDNEXT", arg )) { + if (!(arg = next_arg( &s )) || !(imap->uidnext = atoi( arg ))) { + fprintf( stderr, "IMAP error: malformed NEXTUID status\n" ); + return RESP_BAD; + } + } else if (!strcmp( "CAPABILITY", arg )) { + parse_capability( imap, s ); + } else if (!strcmp( "ALERT", arg )) { + /* RFC2060 says that these messages MUST be displayed + * to the user + */ + for (; isspace( (unsigned char)*p ); p++); + fprintf( stderr, "*** IMAP ALERT *** %s\n", p ); + } else if (cb && cb->ctx && !strcmp( "APPENDUID", arg )) { + if (!(arg = next_arg( &s )) || !(ctx->gen.uidvalidity = atoi( arg )) || + !(arg = next_arg( &s )) || !(*(int *)cb->ctx = atoi( arg ))) + { + fprintf( stderr, "IMAP error: malformed APPENDUID status\n" ); + return RESP_BAD; + } + } + return RESP_OK; +} + +static int +get_cmd_result( imap_store_t *ctx, struct imap_cmd *tcmd ) +{ + imap_t *imap = ctx->imap; + struct imap_cmd *cmdp, **pcmdp, *ncmdp; + char *cmd, *arg, *arg1, *p; + int n, resp, resp2, tag; + + for (;;) { + if (buffer_gets( &imap->buf, &cmd )) + return RESP_BAD; + + arg = next_arg( &cmd ); + if (*arg == '*') { + arg = next_arg( &cmd ); + if (!arg) { + fprintf( stderr, "IMAP error: unable to parse untagged response\n" ); + return RESP_BAD; + } + + if (!strcmp( "NAMESPACE", arg )) { + imap->ns_personal = parse_list( &cmd ); + imap->ns_other = parse_list( &cmd ); + imap->ns_shared = parse_list( &cmd ); + } else if (!strcmp( "OK", arg ) || !strcmp( "BAD", arg ) || + !strcmp( "NO", arg ) || !strcmp( "BYE", arg )) { + if ((resp = parse_response_code( ctx, NULL, cmd )) != RESP_OK) + return resp; + } else if (!strcmp( "CAPABILITY", arg )) + parse_capability( imap, cmd ); + else if ((arg1 = next_arg( &cmd ))) { + if (!strcmp( "EXISTS", arg1 )) + ctx->gen.count = atoi( arg ); + else if (!strcmp( "RECENT", arg1 )) + ctx->gen.recent = atoi( arg ); + } else { + fprintf( stderr, "IMAP error: unable to parse untagged response\n" ); + return RESP_BAD; + } + } else if (!imap->in_progress) { + fprintf( stderr, "IMAP error: unexpected reply: %s %s\n", arg, cmd ? cmd : "" ); + return RESP_BAD; + } else if (*arg == '+') { + /* This can happen only with the last command underway, as + it enforces a round-trip. */ + cmdp = (struct imap_cmd *)((char *)imap->in_progress_append - + offsetof(struct imap_cmd, next)); + if (cmdp->cb.data) { + n = socket_write( &imap->buf.sock, cmdp->cb.data, cmdp->cb.dlen ); + free( cmdp->cb.data ); + cmdp->cb.data = NULL; + if (n != (int)cmdp->cb.dlen) + return RESP_BAD; + } else if (cmdp->cb.cont) { + if (cmdp->cb.cont( ctx, cmdp, cmd )) + return RESP_BAD; + } else { + fprintf( stderr, "IMAP error: unexpected command continuation request\n" ); + return RESP_BAD; + } + if (socket_write( &imap->buf.sock, "\r\n", 2 ) != 2) + return RESP_BAD; + if (!cmdp->cb.cont) + imap->literal_pending = 0; + if (!tcmd) + return DRV_OK; + } else { + tag = atoi( arg ); + for (pcmdp = &imap->in_progress; (cmdp = *pcmdp); pcmdp = &cmdp->next) + if (cmdp->tag == tag) + goto gottag; + fprintf( stderr, "IMAP error: unexpected tag %s\n", arg ); + return RESP_BAD; + gottag: + if (!(*pcmdp = cmdp->next)) + imap->in_progress_append = pcmdp; + imap->num_in_progress--; + if (cmdp->cb.cont || cmdp->cb.data) + imap->literal_pending = 0; + arg = next_arg( &cmd ); + if (!strcmp( "OK", arg )) + resp = DRV_OK; + else { + if (!strcmp( "NO", arg )) { + if (cmdp->cb.create && cmd && (cmdp->cb.trycreate || !memcmp( cmd, "[TRYCREATE]", 11 ))) { /* SELECT, APPEND or UID COPY */ + p = strchr( cmdp->cmd, '"' ); + if (!issue_imap_cmd( ctx, NULL, "CREATE \"%.*s\"", strchr( p + 1, '"' ) - p + 1, p )) { + resp = RESP_BAD; + goto normal; + } + /* not waiting here violates the spec, but a server that does not + grok this nonetheless violates it too. */ + cmdp->cb.create = 0; + if (!(ncmdp = issue_imap_cmd( ctx, &cmdp->cb, "%s", cmdp->cmd ))) { + resp = RESP_BAD; + goto normal; + } + free( cmdp->cmd ); + free( cmdp ); + if (!tcmd) + return 0; /* ignored */ + if (cmdp == tcmd) + tcmd = ncmdp; + continue; + } + resp = RESP_NO; + } else /*if (!strcmp( "BAD", arg ))*/ + resp = RESP_BAD; + fprintf( stderr, "IMAP command '%s' returned response (%s) - %s\n", + memcmp (cmdp->cmd, "LOGIN", 5) ? + cmdp->cmd : "LOGIN <user> <pass>", + arg, cmd ? cmd : ""); + } + if ((resp2 = parse_response_code( ctx, &cmdp->cb, cmd )) > resp) + resp = resp2; + normal: + if (cmdp->cb.done) + cmdp->cb.done( ctx, cmdp, resp ); + if (cmdp->cb.data) + free( cmdp->cb.data ); + free( cmdp->cmd ); + free( cmdp ); + if (!tcmd || tcmd == cmdp) + return resp; + } + } + /* not reached */ +} + +static void +imap_close_server( imap_store_t *ictx ) +{ + imap_t *imap = ictx->imap; + + if (imap->buf.sock.fd != -1) { + imap_exec( ictx, NULL, "LOGOUT" ); + close( imap->buf.sock.fd ); + } + free_list( imap->ns_personal ); + free_list( imap->ns_other ); + free_list( imap->ns_shared ); + free( imap ); +} + +static void +imap_close_store( store_t *ctx ) +{ + imap_close_server( (imap_store_t *)ctx ); + free_generic_messages( ctx->msgs ); + free( ctx ); +} + +static store_t * +imap_open_store( imap_server_conf_t *srvc ) +{ + imap_store_t *ctx; + imap_t *imap; + char *arg, *rsp; + struct hostent *he; + struct sockaddr_in addr; + int s, a[2], preauth; + + ctx = xcalloc( sizeof(*ctx), 1 ); + + ctx->imap = imap = xcalloc( sizeof(*imap), 1 ); + imap->buf.sock.fd = -1; + imap->in_progress_append = &imap->in_progress; + + /* open connection to IMAP server */ + + if (srvc->tunnel) { + info( "Starting tunnel '%s'... ", srvc->tunnel ); + + if (socketpair( PF_UNIX, SOCK_STREAM, 0, a )) { + perror( "socketpair" ); + exit( 1 ); + } + + if (fork() == 0) { + if (dup2( a[0], 0 ) == -1 || dup2( a[0], 1 ) == -1) + _exit( 127 ); + close( a[0] ); + close( a[1] ); + execl( "/bin/sh", "sh", "-c", srvc->tunnel, NULL ); + _exit( 127 ); + } + + close (a[0]); + + imap->buf.sock.fd = a[1]; + + info( "ok\n" ); + } else { + memset( &addr, 0, sizeof(addr) ); + addr.sin_port = htons( srvc->port ); + addr.sin_family = AF_INET; + + info( "Resolving %s... ", srvc->host ); + he = gethostbyname( srvc->host ); + if (!he) { + perror( "gethostbyname" ); + goto bail; + } + info( "ok\n" ); + + addr.sin_addr.s_addr = *((int *) he->h_addr_list[0]); + + s = socket( PF_INET, SOCK_STREAM, 0 ); + + info( "Connecting to %s:%hu... ", inet_ntoa( addr.sin_addr ), ntohs( addr.sin_port ) ); + if (connect( s, (struct sockaddr *)&addr, sizeof(addr) )) { + close( s ); + perror( "connect" ); + goto bail; + } + info( "ok\n" ); + + imap->buf.sock.fd = s; + + } + + /* read the greeting string */ + if (buffer_gets( &imap->buf, &rsp )) { + fprintf( stderr, "IMAP error: no greeting response\n" ); + goto bail; + } + arg = next_arg( &rsp ); + if (!arg || *arg != '*' || (arg = next_arg( &rsp )) == NULL) { + fprintf( stderr, "IMAP error: invalid greeting response\n" ); + goto bail; + } + preauth = 0; + if (!strcmp( "PREAUTH", arg )) + preauth = 1; + else if (strcmp( "OK", arg ) != 0) { + fprintf( stderr, "IMAP error: unknown greeting response\n" ); + goto bail; + } + parse_response_code( ctx, NULL, rsp ); + if (!imap->caps && imap_exec( ctx, NULL, "CAPABILITY" ) != RESP_OK) + goto bail; + + if (!preauth) { + + info ("Logging in...\n"); + if (!srvc->user) { + fprintf( stderr, "Skipping server %s, no user\n", srvc->host ); + goto bail; + } + if (!srvc->pass) { + char prompt[80]; + sprintf( prompt, "Password (%s@%s): ", srvc->user, srvc->host ); + arg = getpass( prompt ); + if (!arg) { + perror( "getpass" ); + exit( 1 ); + } + if (!*arg) { + fprintf( stderr, "Skipping account %s@%s, no password\n", srvc->user, srvc->host ); + goto bail; + } + /* + * getpass() returns a pointer to a static buffer. make a copy + * for long term storage. + */ + srvc->pass = strdup( arg ); + } + if (CAP(NOLOGIN)) { + fprintf( stderr, "Skipping account %s@%s, server forbids LOGIN\n", srvc->user, srvc->host ); + goto bail; + } + warn( "*** IMAP Warning *** Password is being sent in the clear\n" ); + if (imap_exec( ctx, NULL, "LOGIN \"%s\" \"%s\"", srvc->user, srvc->pass ) != RESP_OK) { + fprintf( stderr, "IMAP error: LOGIN failed\n" ); + goto bail; + } + } /* !preauth */ + + ctx->prefix = ""; + ctx->trashnc = 1; + return (store_t *)ctx; + + bail: + imap_close_store( &ctx->gen ); + return NULL; +} + +static int +imap_make_flags( int flags, char *buf ) +{ + const char *s; + unsigned i, d; + + for (i = d = 0; i < ARRAY_SIZE(Flags); i++) + if (flags & (1 << i)) { + buf[d++] = ' '; + buf[d++] = '\\'; + for (s = Flags[i]; *s; s++) + buf[d++] = *s; + } + buf[0] = '('; + buf[d++] = ')'; + return d; +} + +#define TUIDL 8 + +static int +imap_store_msg( store_t *gctx, msg_data_t *data, int *uid ) +{ + imap_store_t *ctx = (imap_store_t *)gctx; + imap_t *imap = ctx->imap; + struct imap_cmd_cb cb; + char *fmap, *buf; + const char *prefix, *box; + int ret, i, j, d, len, extra, nocr; + int start, sbreak = 0, ebreak = 0; + char flagstr[128], tuid[TUIDL * 2 + 1]; + + memset( &cb, 0, sizeof(cb) ); + + fmap = data->data; + len = data->len; + nocr = !data->crlf; + extra = 0, i = 0; + if (!CAP(UIDPLUS) && uid) { + nloop: + start = i; + while (i < len) + if (fmap[i++] == '\n') { + extra += nocr; + if (i - 2 + nocr == start) { + sbreak = ebreak = i - 2 + nocr; + goto mktid; + } + if (!memcmp( fmap + start, "X-TUID: ", 8 )) { + extra -= (ebreak = i) - (sbreak = start) + nocr; + goto mktid; + } + goto nloop; + } + /* invalid message */ + free( fmap ); + return DRV_MSG_BAD; + mktid: + for (j = 0; j < TUIDL; j++) + sprintf( tuid + j * 2, "%02x", arc4_getbyte() ); + extra += 8 + TUIDL * 2 + 2; + } + if (nocr) + for (; i < len; i++) + if (fmap[i] == '\n') + extra++; + + cb.dlen = len + extra; + buf = cb.data = xmalloc( cb.dlen ); + i = 0; + if (!CAP(UIDPLUS) && uid) { + if (nocr) { + for (; i < sbreak; i++) + if (fmap[i] == '\n') { + *buf++ = '\r'; + *buf++ = '\n'; + } else + *buf++ = fmap[i]; + } else { + memcpy( buf, fmap, sbreak ); + buf += sbreak; + } + memcpy( buf, "X-TUID: ", 8 ); + buf += 8; + memcpy( buf, tuid, TUIDL * 2 ); + buf += TUIDL * 2; + *buf++ = '\r'; + *buf++ = '\n'; + i = ebreak; + } + if (nocr) { + for (; i < len; i++) + if (fmap[i] == '\n') { + *buf++ = '\r'; + *buf++ = '\n'; + } else + *buf++ = fmap[i]; + } else + memcpy( buf, fmap + i, len - i ); + + free( fmap ); + + d = 0; + if (data->flags) { + d = imap_make_flags( data->flags, flagstr ); + flagstr[d++] = ' '; + } + flagstr[d] = 0; + + if (!uid) { + box = gctx->conf->trash; + prefix = ctx->prefix; + cb.create = 1; + if (ctx->trashnc) + imap->caps = imap->rcaps & ~(1 << LITERALPLUS); + } else { + box = gctx->name; + prefix = !strcmp( box, "INBOX" ) ? "" : ctx->prefix; + cb.create = 0; + } + cb.ctx = uid; + ret = imap_exec_m( ctx, &cb, "APPEND \"%s%s\" %s", prefix, box, flagstr ); + imap->caps = imap->rcaps; + if (ret != DRV_OK) + return ret; + if (!uid) + ctx->trashnc = 0; + else + gctx->count++; + + return DRV_OK; +} + +#define CHUNKSIZE 0x1000 + +static int +read_message( FILE *f, msg_data_t *msg ) +{ + int len, r; + + memset( msg, 0, sizeof *msg ); + len = CHUNKSIZE; + msg->data = xmalloc( len+1 ); + msg->data[0] = 0; + + while(!feof( f )) { + if (msg->len >= len) { + void *p; + len += CHUNKSIZE; + p = xrealloc(msg->data, len+1); + if (!p) + break; + } + r = fread( &msg->data[msg->len], 1, len - msg->len, f ); + if (r <= 0) + break; + msg->len += r; + } + msg->data[msg->len] = 0; + return msg->len; +} + +static int +count_messages( msg_data_t *msg ) +{ + int count = 0; + char *p = msg->data; + + while (1) { + if (!strncmp( "From ", p, 5 )) { + count++; + p += 5; + } + p = strstr( p+5, "\nFrom "); + if (!p) + break; + p++; + } + return count; +} + +static int +split_msg( msg_data_t *all_msgs, msg_data_t *msg, int *ofs ) +{ + char *p, *data; + + memset( msg, 0, sizeof *msg ); + if (*ofs >= all_msgs->len) + return 0; + + data = &all_msgs->data[ *ofs ]; + msg->len = all_msgs->len - *ofs; + + if (msg->len < 5 || strncmp( data, "From ", 5 )) + return 0; + + p = strstr( data, "\nFrom " ); + if (p) + msg->len = &p[1] - data; + + msg->data = xmalloc( msg->len + 1 ); + if (!msg->data) + return 0; + + memcpy( msg->data, data, msg->len ); + msg->data[ msg->len ] = 0; + + *ofs += msg->len; + return 1; +} + +static imap_server_conf_t server = +{ + NULL, /* name */ + NULL, /* tunnel */ + NULL, /* host */ + 0, /* port */ + NULL, /* user */ + NULL, /* pass */ +}; + +static char *imap_folder; + +static int +git_imap_config(const char *key, const char *val) +{ + char imap_key[] = "imap."; + + if (strncmp( key, imap_key, sizeof imap_key - 1 )) + return 0; + key += sizeof imap_key - 1; + + if (!strcmp( "folder", key )) { + imap_folder = strdup( val ); + } else if (!strcmp( "host", key )) { + { + if (!strncmp( "imap:", val, 5 )) + val += 5; + if (!server.port) + server.port = 143; + } + if (!strncmp( "//", val, 2 )) + val += 2; + server.host = strdup( val ); + } + else if (!strcmp( "user", key )) + server.user = strdup( val ); + else if (!strcmp( "pass", key )) + server.pass = strdup( val ); + else if (!strcmp( "port", key )) + server.port = git_config_int( key, val ); + else if (!strcmp( "tunnel", key )) + server.tunnel = strdup( val ); + return 0; +} + +int +main(int argc, char **argv) +{ + msg_data_t all_msgs, msg; + store_t *ctx = NULL; + int uid = 0; + int ofs = 0; + int r; + int total, n = 0; + + /* init the random number generator */ + arc4_init(); + + git_config( git_imap_config ); + + if (!imap_folder) { + fprintf( stderr, "no imap store specified\n" ); + return 1; + } + + /* read the messages */ + if (!read_message( stdin, &all_msgs )) { + fprintf(stderr,"nothing to send\n"); + return 1; + } + + /* write it to the imap server */ + ctx = imap_open_store( &server ); + if (!ctx) { + fprintf( stderr,"failed to open store\n"); + return 1; + } + + total = count_messages( &all_msgs ); + fprintf( stderr, "sending %d message%s\n", total, (total!=1)?"s":"" ); + ctx->name = imap_folder; + while (1) { + unsigned percent = n * 100 / total; + fprintf( stderr, "%4u%% (%d/%d) done\r", percent, n, total ); + if (!split_msg( &all_msgs, &msg, &ofs )) + break; + r = imap_store_msg( ctx, &msg, &uid ); + if (r != DRV_OK) break; + n++; + } + fprintf( stderr,"\n" ); + + imap_close_store( ctx ); + + return 0; +} diff --git a/index-pack.c b/index-pack.c index babe34b..b39953d 100644 --- a/index-pack.c +++ b/index-pack.c @@ -2,6 +2,10 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" static const char index_pack_usage[] = "git-index-pack [-o index-file] pack-file"; @@ -224,10 +228,10 @@ static void sha1_object(const void *data, unsigned long size, const char *type_str; switch (type) { - case OBJ_COMMIT: type_str = "commit"; break; - case OBJ_TREE: type_str = "tree"; break; - case OBJ_BLOB: type_str = "blob"; break; - case OBJ_TAG: type_str = "tag"; break; + case OBJ_COMMIT: type_str = commit_type; break; + case OBJ_TREE: type_str = tree_type; break; + case OBJ_BLOB: type_str = blob_type; break; + case OBJ_TAG: type_str = tag_type; break; default: die("bad type %d", type); } @@ -11,6 +11,7 @@ #include "cache.h" #include "quote.h" +static int abbrev = 0; static int show_deleted = 0; static int show_cached = 0; static int show_others = 0; @@ -20,11 +21,15 @@ static int show_unmerged = 0; static int show_modified = 0; static int show_killed = 0; static int show_other_directories = 0; +static int hide_empty_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 = ""; @@ -89,11 +94,12 @@ static int add_excludes_from_file_1(const char *fname, close(fd); return 0; } - buf = xmalloc(size); + buf = xmalloc(size+1); if (read(fd, buf, size) != size) goto err; close(fd); + buf[size++] = '\n'; entry = buf; for (i = 0; i < size; i++) { if (buf[i] == '\n') { @@ -254,11 +260,12 @@ static int dir_exists(const char *dirname, int len) * Also, we ignore the name ".git" (even if it is not a directory). * That likely will not change. */ -static void read_directory(const char *path, const char *base, int baselen) +static int read_directory(const char *path, const char *base, int baselen) { - DIR *dir = opendir(path); + DIR *fdir = opendir(path); + int contents = 0; - if (dir) { + if (fdir) { int exclude_stk; struct dirent *de; char fullname[MAXPATHLEN + 1]; @@ -266,7 +273,7 @@ static void read_directory(const char *path, const char *base, int baselen) exclude_stk = push_exclude_per_directory(base, baselen); - while ((de = readdir(dir)) != NULL) { + while ((de = readdir(fdir)) != NULL) { int len; if ((de->d_name[0] == '.') && @@ -276,11 +283,15 @@ 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; + int subdir, rewind_base; default: continue; case DT_UNKNOWN: @@ -294,22 +305,32 @@ static void read_directory(const char *path, const char *base, int baselen) case DT_DIR: memcpy(fullname + baselen + len, "/", 2); len++; + rewind_base = nr_dir; + subdir = read_directory(fullname, fullname, + baselen + len); if (show_other_directories && - !dir_exists(fullname, baselen + len)) + (subdir || !hide_empty_directories) && + !dir_exists(fullname, baselen + len)) { + // Rewind the read subdirectory + while (nr_dir > rewind_base) + free(dir[--nr_dir]); break; - read_directory(fullname, fullname, - baselen + len); + } + contents += subdir; continue; case DT_REG: case DT_LNK: break; } add_name(fullname, baselen + len); + contents++; } - closedir(dir); + closedir(fdir); pop_exclude_per_directory(exclude_stk); } + + return contents; } static int cmp_name(const void *p1, const void *p2) @@ -325,7 +346,8 @@ 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 +355,24 @@ 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 +385,7 @@ 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 +473,26 @@ 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, @@ -457,7 +503,8 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) printf("%s%06o %s %d\t", tag, ntohl(ce->ce_mode), - sha1_to_hex(ce->sha1), + abbrev ? find_unique_abbrev(ce->sha1,abbrev) + : sha1_to_hex(ce->sha1), ce_stage(ce)); write_name_quoted("", 0, ce->name + offset, line_terminator, stdout); @@ -523,7 +570,7 @@ 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); } } @@ -596,9 +643,10 @@ 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>]*"; + "[ --exclude-per-directory=<filename> ] [--full-name] [--abbrev] " + "[--] [<file>]*"; int main(int argc, const char **argv) { @@ -621,13 +669,15 @@ 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")) { @@ -662,6 +712,10 @@ int main(int argc, const char **argv) show_other_directories = 1; continue; } + if (!strcmp(arg, "--no-empty-directory")) { + hide_empty_directories = 1; + continue; + } if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) { /* There's no point in showing unmerged unless * you also show the stage information. @@ -699,6 +753,22 @@ int main(int argc, const char **argv) prefix_offset = 0; continue; } + if (!strcmp(arg, "--error-unmatch")) { + error_unmatch = 1; + continue; + } + if (!strncmp(arg, "--abbrev=", 9)) { + abbrev = strtoul(arg+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + continue; + } + if (!strcmp(arg, "--abbrev")) { + abbrev = DEFAULT_ABBREV; + continue; + } if (*arg == '-') usage(ls_files_usage); break; @@ -710,6 +780,14 @@ 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 +803,21 @@ 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; } @@ -13,13 +13,14 @@ static int line_termination = '\n'; #define LS_TREE_ONLY 2 #define LS_SHOW_TREES 4 #define LS_NAME_ONLY 8 +static int abbrev = 0; static int ls_options = 0; const char **pathspec; static int chomp_prefix = 0; static const char *prefix; static const char ls_tree_usage[] = - "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] <tree-ish> [path...]"; + "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] [--abbrev[=<n>]] <tree-ish> [path...]"; static int show_recursive(const char *base, int baselen, const char *pathname) { @@ -55,7 +56,7 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage) { int retval = 0; - const char *type = "blob"; + const char *type = blob_type; if (S_ISDIR(mode)) { if (show_recursive(base, baselen, pathname)) { @@ -63,7 +64,7 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen, if (!(ls_options & LS_SHOW_TREES)) return retval; } - type = "tree"; + type = tree_type; } else if (ls_options & LS_TREE_ONLY) return 0; @@ -73,7 +74,9 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen, return 0; if (!(ls_options & LS_NAME_ONLY)) - printf("%06o %s %s\t", mode, type, sha1_to_hex(sha1)); + printf("%06o %s %s\t", mode, type, + abbrev ? find_unique_abbrev(sha1,abbrev) + : sha1_to_hex(sha1)); write_name_quoted(base + chomp_prefix, baselen - chomp_prefix, pathname, line_termination, stdout); @@ -87,6 +90,7 @@ int main(int argc, const char **argv) struct tree *tree; prefix = setup_git_directory(); + git_config(git_default_config); if (prefix && *prefix) chomp_prefix = strlen(prefix); while (1 < argc && argv[1][0] == '-') { @@ -113,6 +117,18 @@ int main(int argc, const char **argv) chomp_prefix = 0; break; } + if (!strncmp(argv[1]+2, "abbrev=",7)) { + abbrev = strtoul(argv[1]+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + break; + } + if (!strcmp(argv[1]+2, "abbrev")) { + abbrev = DEFAULT_ABBREV; + break; + } /* otherwise fallthru */ default: usage(ls_tree_usage); @@ -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-base.c b/merge-base.c index e73fca7..07f5ab4 100644 --- a/merge-base.c +++ b/merge-base.c @@ -237,6 +237,7 @@ int main(int argc, char **argv) unsigned char rev1key[20], rev2key[20]; setup_git_directory(); + git_config(git_default_config); while (1 < argc && argv[1][0] == '-') { char *arg = argv[1]; diff --git a/merge-tree.c b/merge-tree.c new file mode 100644 index 0000000..50528d5 --- /dev/null +++ b/merge-tree.c @@ -0,0 +1,178 @@ +#include "cache.h" +#include "tree-walk.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); + +/* 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); +} + +/* + * 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; +} @@ -1,4 +1,5 @@ #include "cache.h" +#include "tag.h" /* * A signature file has a very simple fixed format: three lines @@ -126,7 +127,7 @@ int main(int argc, char **argv) if (verify_tag(buffer, size) < 0) die("invalid tag signature file"); - if (write_sha1_file(buffer, size, "tag", result_sha1) < 0) + if (write_sha1_file(buffer, size, tag_type, result_sha1) < 0) die("unable to write tag file"); printf("%s\n", sha1_to_hex(result_sha1)); return 0; diff --git a/mktree.c b/mktree.c new file mode 100644 index 0000000..ab63cd9 --- /dev/null +++ b/mktree.c @@ -0,0 +1,138 @@ +/* + * GIT - the stupid content tracker + * + * Copyright (c) Junio C Hamano, 2006 + */ +#include "cache.h" +#include "strbuf.h" +#include "quote.h" +#include "tree.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_type, 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); +} @@ -127,6 +127,7 @@ int main(int argc, char **argv) int as_is = 0, all = 0, transform_stdin = 0; setup_git_directory(); + git_config(git_default_config); if (argc < 2) usage(name_rev_usage); @@ -85,8 +85,7 @@ struct object_refs *alloc_object_refs(unsigned count) struct object_refs *refs; size_t size = sizeof(*refs) + count*sizeof(struct object *); - refs = xmalloc(size); - memset(refs, 0, size); + refs = xcalloc(1, size); refs->count = count; return refs; } @@ -178,8 +177,7 @@ struct object *lookup_unknown_object(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - union any_object *ret = xmalloc(sizeof(*ret)); - memset(ret, 0, sizeof(*ret)); + union any_object *ret = xcalloc(1, sizeof(*ret)); created_object(sha1, &ret->object); ret->object.type = NULL; return &ret->object; @@ -196,15 +194,15 @@ struct object *parse_object(const unsigned char *sha1) struct object *obj; if (check_sha1_signature(sha1, buffer, size, type) < 0) printf("sha1 mismatch %s\n", sha1_to_hex(sha1)); - if (!strcmp(type, "blob")) { + if (!strcmp(type, blob_type)) { struct blob *blob = lookup_blob(sha1); parse_blob_buffer(blob, buffer, size); obj = &blob->object; - } else if (!strcmp(type, "tree")) { + } else if (!strcmp(type, tree_type)) { struct tree *tree = lookup_tree(sha1); parse_tree_buffer(tree, buffer, size); obj = &tree->object; - } else if (!strcmp(type, "commit")) { + } else if (!strcmp(type, commit_type)) { struct commit *commit = lookup_commit(sha1); parse_commit_buffer(commit, buffer, size); if (!commit->buffer) { @@ -212,7 +210,7 @@ struct object *parse_object(const unsigned char *sha1) buffer = NULL; } obj = &commit->object; - } else if (!strcmp(type, "tag")) { + } else if (!strcmp(type, tag_type)) { struct tag *tag = lookup_tag(sha1); parse_tag_buffer(tag, buffer, size); obj = &tag->object; diff --git a/pack-check.c b/pack-check.c index 67a7ecd..84ed90d 100644 --- a/pack-check.c +++ b/pack-check.c @@ -70,13 +70,17 @@ static int verify_packfile(struct packed_git *p) } +#define MAX_CHAIN 40 + static void show_pack_info(struct packed_git *p) { struct pack_header *hdr; int nr_objects, i; + unsigned int chain_histogram[MAX_CHAIN]; hdr = p->pack_base; nr_objects = ntohl(hdr->hdr_entries); + memset(chain_histogram, 0, sizeof(chain_histogram)); for (i = 0; i < nr_objects; i++) { unsigned char sha1[20], base_sha1[20]; @@ -84,7 +88,7 @@ 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"); @@ -97,11 +101,25 @@ static void show_pack_info(struct packed_git *p) printf("%s ", sha1_to_hex(sha1)); 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, + else { + printf("%-6s %lu %u %u %s\n", type, size, e.offset, delta_chain_length, sha1_to_hex(base_sha1)); + if (delta_chain_length < MAX_CHAIN) + chain_histogram[delta_chain_length]++; + else + chain_histogram[0]++; + } } + for (i = 0; i < MAX_CHAIN; i++) { + if (!chain_histogram[i]) + continue; + printf("chain length %s %d: %d object%s\n", + i ? "=" : ">=", + i ? i : MAX_CHAIN, + chain_histogram[i], + 1 < chain_histogram[i] ? "s" : ""); + } } int verify_pack(struct packed_git *p, int verbose) diff --git a/pack-objects.c b/pack-objects.c index 7d62477..9346392 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -1,8 +1,13 @@ #include "cache.h" #include "object.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "tree-walk.h" #include <sys/time.h> #include <signal.h> @@ -27,6 +32,10 @@ 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. + */ }; /* @@ -49,7 +58,7 @@ 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 +100,7 @@ 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 +240,8 @@ 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 +251,9 @@ 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 +348,22 @@ 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 +371,17 @@ 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 +406,7 @@ 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 +416,139 @@ 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 +556,94 @@ 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_type)) { + 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_type, &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 +662,8 @@ 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 @@ -510,38 +688,19 @@ static void check_object(struct object_entry *entry) die("unable to get type of object %s", sha1_to_hex(entry->sha1)); - if (!strcmp(type, "commit")) { + if (!strcmp(type, commit_type)) { entry->type = OBJ_COMMIT; - } else if (!strcmp(type, "tree")) { + } else if (!strcmp(type, tree_type)) { entry->type = OBJ_TREE; - } else if (!strcmp(type, "blob")) { + } else if (!strcmp(type, blob_type)) { entry->type = OBJ_BLOB; - } else if (!strcmp(type, "tag")) { + } else if (!strcmp(type, tag_type)) { entry->type = OBJ_TAG; } else die("unable to pack object %s of type %s", 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 +719,26 @@ 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 +769,24 @@ 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 +797,10 @@ 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) @@ -640,9 +833,15 @@ 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 +850,10 @@ 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; @@ -700,7 +898,7 @@ 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]; @@ -709,12 +907,14 @@ 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; } @@ -744,6 +944,15 @@ static void find_deltas(struct object_entry **list, int window, int depth) if (try_delta(n, m, depth) < 0) break; } +#if 0 + /* if we made n a delta, and if n is already at max + * depth, leaving it in the window is pointless. we + * should evict it first. + * ... in theory only; somehow this makes things worse. + */ + if (entry->delta && depth <= entry->depth) + continue; +#endif idx++; if (idx >= window) idx = 0; @@ -906,8 +1115,6 @@ int main(int argc, char **argv) } for (;;) { - unsigned int hash; - char *p; unsigned char sha1[20]; if (!fgets(line, sizeof(line), stdin)) { @@ -921,40 +1128,38 @@ int main(int argc, char **argv) continue; } - 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,},}; @@ -970,6 +1175,6 @@ 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 1869b38..cd81f5a 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; @@ -0,0 +1,48 @@ +#include "cache.h" + +/* + * This is split up from the rest of git so that we might do + * something different on Windows, for example. + */ + +static void run_pager(void) +{ + const char *prog = getenv("PAGER"); + if (!prog) + prog = "less"; + setenv("LESS", "-S", 0); + execlp(prog, prog, NULL); +} + +void setup_pager(void) +{ + pid_t pid; + int fd[2]; + + if (!isatty(1)) + return; + if (pipe(fd) < 0) + return; + pid = fork(); + if (pid < 0) { + close(fd[0]); + close(fd[1]); + return; + } + + /* return in the child */ + if (!pid) { + dup2(fd[1], 1); + close(fd[0]); + close(fd[1]); + return; + } + + /* The original process turns into the PAGER */ + dup2(fd[0], 0); + close(fd[0]); + close(fd[1]); + + run_pager(); + exit(255); +} diff --git a/read-cache.c b/read-cache.c index c5474d4..f97f92d 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 32fb6fa..26f4f7e 100644 --- a/read-tree.c +++ b/read-tree.c @@ -133,11 +133,9 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len, pathlen = strlen(first); ce_size = cache_entry_size(baselen + pathlen); - src = xmalloc(sizeof(struct cache_entry *) * src_size); - memset(src, 0, sizeof(struct cache_entry *) * src_size); + src = xcalloc(src_size, sizeof(struct cache_entry *)); - subposns = xmalloc(sizeof(struct tree_list_entry *) * len); - memset(subposns, 0, sizeof(struct tree_list_entry *) * len); + subposns = xcalloc(len, sizeof(struct tree_list_entry *)); if (cache_name && !strcmp(cache_name, first)) { any_files = 1; @@ -177,8 +175,7 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len, else ce_stage = 2; - ce = xmalloc(ce_size); - memset(ce, 0, ce_size); + ce = xcalloc(1, ce_size); ce->ce_mode = create_ce_mode(posns[i]->mode); ce->ce_flags = create_ce_flags(baselen + pathlen, ce_stage); @@ -347,7 +344,7 @@ static void check_updates(struct cache_entry **src, int nr) if (ce->ce_flags & mask) { ce->ce_flags &= ~mask; if (update) - checkout_entry(ce, &state); + checkout_entry(ce, &state, NULL); } } if (total) { @@ -414,7 +411,7 @@ 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; @@ -716,7 +713,7 @@ static int read_cache_unmerged(void) return deleted; } -static const char read_tree_usage[] = "git-read-tree (<sha> | -m [-u | -i] <sha1> [<sha2> [<sha3>]])"; +static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])"; static struct cache_file cache_file; @@ -727,6 +724,7 @@ int main(int argc, char **argv) merge_fn_t fn = NULL; setup_git_directory(); + git_config(git_default_config); newfd = hold_index_file_for_update(&cache_file, get_index_file()); if (newfd < 0) diff --git a/receive-pack.c b/receive-pack.c index 2a3db16..93929b5 100644 --- a/receive-pack.c +++ b/receive-pack.c @@ -6,7 +6,7 @@ static const char receive_pack_usage[] = "git-receive-pack <git-dir>"; -static char *unpacker[] = { "unpack-objects", NULL }; +static const char *unpacker[] = { "unpack-objects", NULL }; static int report_status = 0; @@ -177,7 +177,7 @@ static void run_update_post_hook(struct command *cmd) { struct command *cmd_p; int argc; - char **argv; + const char **argv; if (access(update_post_hook, X_OK) < 0) return; @@ -190,10 +190,12 @@ static void run_update_post_hook(struct command *cmd) argv[0] = update_post_hook; for (argc = 1, cmd_p = cmd; cmd_p; cmd_p = cmd_p->next) { + char *p; if (cmd_p->error_string) continue; - argv[argc] = xmalloc(strlen(cmd_p->ref_name) + 1); - strcpy(argv[argc], cmd_p->ref_name); + p = xmalloc(strlen(cmd_p->ref_name) + 1); + strcpy(p, cmd_p->ref_name); + argv[argc] = p; argc++; } argv[argc] = NULL; @@ -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) { + error("%s points nowhere!", path); continue; - if (!has_sha1_file(sha1)) + } + if (!has_sha1_file(sha1)) { + error("%s does not point to a valid " + "commit object!", path); continue; + } retval = fn(path, sha1); if (retval) break; diff --git a/repo-config.c b/repo-config.c index 9cf6519..c5ebb76 100644 --- a/repo-config.c +++ b/repo-config.c @@ -14,6 +14,9 @@ static enum { T_RAW, T_INT, T_BOOL } type = T_RAW; static int show_config(const char* key_, const char* value_) { + if (value_ == NULL) + value_ = ""; + if (!strcmp(key_, key) && (regexp == NULL || (do_not_match ^ @@ -35,7 +38,7 @@ static int show_config(const char* key_, const char* value_) sprintf(value, "%s", git_config_bool(key_, value_) ? "true" : "false"); } else { - value = strdup(value_ ? value_ : ""); + value = strdup(value_); } seen++; } @@ -4,15 +4,12 @@ #include "commit.h" #include "tree.h" #include "blob.h" -#include "epoch.h" -#include "diff.h" +#include "tree-walk.h" +#include "revision.h" -#define SEEN (1u << 0) -#define INTERESTING (1u << 1) -#define COUNTED (1u << 2) -#define SHOWN (1u << 3) -#define TREECHANGE (1u << 4) -#define TMP_MARK (1u << 5) /* for isolated cases; clean after use */ +/* bits #0-5 in revision.h */ + +#define COUNTED (1u<<6) static const char rev_list_usage[] = "git-rev-list [OPTION] <commit-id>... [ -- paths... ]\n" @@ -25,11 +22,11 @@ static const char rev_list_usage[] = " --remove-empty\n" " --all\n" " 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" @@ -37,42 +34,26 @@ static const char rev_list_usage[] = " --bisect" ; -static int dense = 1; -static int unpacked = 0; +struct rev_info revs; + static int bisect_list = 0; -static int tag_objects = 0; -static int tree_objects = 0; -static int blob_objects = 0; static int verbose_header = 0; static int abbrev = DEFAULT_ABBREV; -static int show_parents = 0; +static int show_timestamp = 0; static int hdr_termination = 0; static const char *commit_prefix = ""; -static unsigned long max_age = -1; -static unsigned long min_age = -1; -static int max_count = -1; static enum cmit_fmt commit_format = CMIT_FMT_RAW; -static int merge_order = 0; -static int show_breaks = 0; -static int stop_traversal = 0; -static int topo_order = 0; -static int no_merges = 0; -static const char **paths = NULL; -static int remove_empty_trees = 0; static void show_commit(struct commit *commit) { - commit->object.flags |= SHOWN; - if (show_breaks) { - commit_prefix = "| "; - if (commit->object.flags & DISCONTINUITY) { - commit_prefix = "^ "; - } else if (commit->object.flags & BOUNDARY) { - commit_prefix = "= "; - } - } - printf("%s%s", commit_prefix, sha1_to_hex(commit->object.sha1)); - if (show_parents) { + if (show_timestamp) + printf("%lu ", commit->date); + if (commit_prefix[0]) + fputs(commit_prefix, stdout); + if (commit->object.flags & BOUNDARY) + putchar('-'); + fputs(sha1_to_hex(commit->object.sha1), stdout); + if (revs.parents) { struct commit_list *parents = commit->parents; while (parents) { struct object *o = &(parents->item->object); @@ -104,157 +85,87 @@ static void show_commit(struct commit *commit) fflush(stdout); } -static int rewrite_one(struct commit **pp) -{ - for (;;) { - struct commit *p = *pp; - if (p->object.flags & (TREECHANGE | UNINTERESTING)) - return 0; - if (!p->parents) - return -1; - *pp = p->parents->item; - } -} - -static void rewrite_parents(struct commit *commit) -{ - struct commit_list **pp = &commit->parents; - while (*pp) { - struct commit_list *parent = *pp; - if (rewrite_one(&parent->item) < 0) { - *pp = parent->next; - continue; - } - pp = &parent->next; - } -} - -static int filter_commit(struct commit * commit) -{ - if (stop_traversal && (commit->object.flags & BOUNDARY)) - return STOP; - if (commit->object.flags & (UNINTERESTING|SHOWN)) - return CONTINUE; - if (min_age != -1 && (commit->date > min_age)) - return CONTINUE; - if (max_age != -1 && (commit->date < max_age)) { - stop_traversal=1; - return CONTINUE; - } - if (no_merges && (commit->parents && commit->parents->next)) - return CONTINUE; - if (paths && dense) { - if (!(commit->object.flags & TREECHANGE)) - return CONTINUE; - rewrite_parents(commit); - } - return DO; -} - -static int process_commit(struct commit * commit) -{ - int action=filter_commit(commit); - - if (action == STOP) { - return STOP; - } - - if (action == CONTINUE) { - return CONTINUE; - } - - if (max_count != -1 && !max_count--) - return STOP; - - show_commit(commit); - - return CONTINUE; -} - -static struct object_list **add_object(struct object *obj, struct object_list **p, const char *name) -{ - struct object_list *entry = xmalloc(sizeof(*entry)); - entry->item = obj; - entry->next = *p; - entry->name = 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; - if (!blob_objects) + if (!revs.blob_objects) return p; 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) + if (!revs.tree_objects) return p; if (obj->flags & (UNINTERESTING | SEEN)) return p; 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; } return p; } -static struct object_list *pending_objects = NULL; - -static void show_commit_list(struct commit_list *list) +static void show_commit_list(struct rev_info *revs) { + struct commit *commit; struct object_list *objects = NULL, **p = &objects, *pending; - while (list) { - struct commit *commit = pop_most_recent_commit(&list, SEEN); - p = process_tree(commit->tree, p, ""); - if (process_commit(commit) == STOP) - break; + while ((commit = get_revision(revs)) != NULL) { + p = process_tree(commit->tree, p, NULL, ""); + show_commit(commit); } - for (pending = pending_objects; pending; pending = pending->next) { + for (pending = revs->pending_objects; pending; pending = pending->next) { struct object *obj = pending->item; const char *name = pending->name; if (obj->flags & (UNINTERESTING | SEEN)) 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) { @@ -268,88 +179,6 @@ static void show_commit_list(struct commit_list *list) } } -static void mark_blob_uninteresting(struct blob *blob) -{ - if (!blob_objects) - return; - if (blob->object.flags & UNINTERESTING) - return; - blob->object.flags |= UNINTERESTING; -} - -static void mark_tree_uninteresting(struct tree *tree) -{ - struct object *obj = &tree->object; - struct tree_entry_list *entry; - - if (!tree_objects) - return; - if (obj->flags & UNINTERESTING) - return; - obj->flags |= UNINTERESTING; - if (!has_sha1_file(obj->sha1)) - return; - if (parse_tree(tree) < 0) - die("bad tree %s", sha1_to_hex(obj->sha1)); - entry = tree->entries; - tree->entries = NULL; - while (entry) { - struct tree_entry_list *next = entry->next; - if (entry->directory) - mark_tree_uninteresting(entry->item.tree); - else - mark_blob_uninteresting(entry->item.blob); - free(entry); - entry = next; - } -} - -static void mark_parents_uninteresting(struct commit *commit) -{ - struct commit_list *parents = commit->parents; - - while (parents) { - struct commit *commit = parents->item; - commit->object.flags |= UNINTERESTING; - - /* - * Normally we haven't parsed the parent - * yet, so we won't have a parent of a parent - * here. However, it may turn out that we've - * reached this commit some other way (where it - * wasn't uninteresting), in which case we need - * to mark its parents recursively too.. - */ - if (commit->parents) - mark_parents_uninteresting(commit); - - /* - * A missing commit is ok iff its parent is marked - * uninteresting. - * - * We just mark such a thing parsed, so that when - * it is popped next time around, we won't be trying - * to parse it and get an error. - */ - if (!has_sha1_file(commit->object.sha1)) - commit->object.parsed = 1; - parents = parents->next; - } -} - -static int everybody_uninteresting(struct commit_list *orig) -{ - struct commit_list *list = orig; - while (list) { - struct commit *commit = list->item; - list = list->next; - if (commit->object.flags & UNINTERESTING) - continue; - return 0; - } - return 1; -} - /* * This is a truly stupid algorithm, but it's only * used for bisection, and we just don't care enough. @@ -367,7 +196,7 @@ static int count_distance(struct commit_list *entry) if (commit->object.flags & (UNINTERESTING | COUNTED)) break; - if (!paths || (commit->object.flags & TREECHANGE)) + if (!revs.prune_fn || (commit->object.flags & TREECHANGE)) nr++; commit->object.flags |= COUNTED; p = commit->parents; @@ -401,7 +230,7 @@ static struct commit_list *find_bisection(struct commit_list *list) nr = 0; p = list; while (p) { - if (!paths || (p->item->object.flags & TREECHANGE)) + if (!revs.prune_fn || (p->item->object.flags & TREECHANGE)) nr++; p = p->next; } @@ -411,7 +240,7 @@ static struct commit_list *find_bisection(struct commit_list *list) for (p = list; p; p = p->next) { int distance; - if (paths && !(p->item->object.flags & TREECHANGE)) + if (revs.prune_fn && !(p->item->object.flags & TREECHANGE)) continue; distance = count_distance(p); @@ -428,369 +257,58 @@ static struct commit_list *find_bisection(struct commit_list *list) return best; } -static void mark_edges_uninteresting(struct commit_list *list) +static void mark_edge_parents_uninteresting(struct commit *commit) { - for ( ; list; list = list->next) { - struct commit_list *parents = list->item->parents; - - for ( ; parents; parents = parents->next) { - struct commit *commit = parents->item; - if (commit->object.flags & UNINTERESTING) - mark_tree_uninteresting(commit->tree); - } - } -} - -#define TREE_SAME 0 -#define TREE_NEW 1 -#define TREE_DIFFERENT 2 -static int tree_difference = TREE_SAME; - -static void file_add_remove(struct diff_options *options, - int addremove, unsigned mode, - const unsigned char *sha1, - const char *base, const char *path) -{ - int diff = TREE_DIFFERENT; - - /* - * Is it an add of a new file? It means that - * the old tree didn't have it at all, so we - * will turn "TREE_SAME" -> "TREE_NEW", but - * leave any "TREE_DIFFERENT" alone (and if - * it already was "TREE_NEW", we'll keep it - * "TREE_NEW" of course). - */ - if (addremove == '+') { - diff = tree_difference; - if (diff != TREE_SAME) - return; - diff = TREE_NEW; - } - tree_difference = diff; -} - -static void file_change(struct diff_options *options, - unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - const char *base, const char *path) -{ - tree_difference = TREE_DIFFERENT; -} - -static struct diff_options diff_opt = { - .recursive = 1, - .add_remove = file_add_remove, - .change = file_change, -}; - -static int compare_tree(struct tree *t1, struct tree *t2) -{ - if (!t1) - return TREE_NEW; - if (!t2) - return TREE_DIFFERENT; - tree_difference = TREE_SAME; - if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", &diff_opt) < 0) - return TREE_DIFFERENT; - return tree_difference; -} - -static int same_tree_as_empty(struct tree *t1) -{ - int retval; - void *tree; - struct tree_desc empty, real; - - if (!t1) - return 0; - - tree = read_object_with_reference(t1->object.sha1, "tree", &real.size, NULL); - if (!tree) - return 0; - real.buf = tree; - - empty.buf = ""; - empty.size = 0; - - tree_difference = 0; - retval = diff_tree(&empty, &real, "", &diff_opt); - free(tree); - - return retval >= 0 && !tree_difference; -} - -static void try_to_simplify_commit(struct commit *commit) -{ - struct commit_list **pp, *parent; - - if (!commit->tree) - return; - - if (!commit->parents) { - if (!same_tree_as_empty(commit->tree)) - commit->object.flags |= TREECHANGE; - return; - } - - pp = &commit->parents; - while ((parent = *pp) != NULL) { - struct commit *p = parent->item; + struct commit_list *parents; - if (p->object.flags & UNINTERESTING) { - pp = &parent->next; + for (parents = commit->parents; parents; parents = parents->next) { + struct commit *parent = parents->item; + if (!(parent->object.flags & UNINTERESTING)) continue; + mark_tree_uninteresting(parent->tree); + if (revs.edge_hint && !(parent->object.flags & SHOWN)) { + parent->object.flags |= SHOWN; + printf("-%s\n", sha1_to_hex(parent->object.sha1)); } - - parse_commit(p); - switch (compare_tree(p->tree, commit->tree)) { - case TREE_SAME: - parent->next = NULL; - commit->parents = parent; - return; - - case TREE_NEW: - if (remove_empty_trees && same_tree_as_empty(p->tree)) { - *pp = parent->next; - continue; - } - /* fallthrough */ - case TREE_DIFFERENT: - pp = &parent->next; - continue; - } - die("bad tree compare for commit %s", sha1_to_hex(commit->object.sha1)); } - commit->object.flags |= TREECHANGE; } -static void add_parents_to_list(struct commit *commit, struct commit_list **list) -{ - struct commit_list *parent = commit->parents; - - /* - * If the commit is uninteresting, don't try to - * prune parents - we want the maximal uninteresting - * set. - * - * Normally we haven't parsed the parent - * yet, so we won't have a parent of a parent - * here. However, it may turn out that we've - * reached this commit some other way (where it - * wasn't uninteresting), in which case we need - * to mark its parents recursively too.. - */ - if (commit->object.flags & UNINTERESTING) { - while (parent) { - struct commit *p = parent->item; - parent = parent->next; - parse_commit(p); - p->object.flags |= UNINTERESTING; - if (p->parents) - mark_parents_uninteresting(p); - if (p->object.flags & SEEN) - continue; - p->object.flags |= SEEN; - insert_by_date(p, list); - } - return; - } - - /* - * Ok, the commit wasn't uninteresting. Try to - * simplify the commit history and find the parent - * that has no differences in the path set if one exists. - */ - if (paths) - try_to_simplify_commit(commit); - - parent = commit->parents; - while (parent) { - struct commit *p = parent->item; - - parent = parent->next; - - parse_commit(p); - if (p->object.flags & SEEN) - continue; - p->object.flags |= SEEN; - insert_by_date(p, list); - } -} - -static struct commit_list *limit_list(struct commit_list *list) +static void mark_edges_uninteresting(struct commit_list *list) { - struct commit_list *newlist = NULL; - struct commit_list **p = &newlist; - while (list) { - struct commit_list *entry = list; + for ( ; list; list = list->next) { struct commit *commit = list->item; - struct object *obj = &commit->object; - - list = list->next; - free(entry); - if (max_age != -1 && (commit->date < max_age)) - obj->flags |= UNINTERESTING; - if (unpacked && has_sha1_pack(obj->sha1)) - obj->flags |= UNINTERESTING; - add_parents_to_list(commit, &list); - if (obj->flags & UNINTERESTING) { - mark_parents_uninteresting(commit); - if (everybody_uninteresting(list)) - break; + if (commit->object.flags & UNINTERESTING) { + mark_tree_uninteresting(commit->tree); continue; } - if (min_age != -1 && (commit->date > min_age)) - continue; - p = &commit_list_insert(commit, p)->next; + mark_edge_parents_uninteresting(commit); } - if (tree_objects) - mark_edges_uninteresting(newlist); - if (bisect_list) - newlist = find_bisection(newlist); - return newlist; -} - -static void add_pending_object(struct object *obj, const char *name) -{ - add_object(obj, &pending_objects, name); -} - -static struct commit *get_commit_reference(const char *name, const unsigned char *sha1, unsigned int flags) -{ - struct object *object; - - object = parse_object(sha1); - if (!object) - die("bad object %s", name); - - /* - * Tag object? Look what it points to.. - */ - while (object->type == tag_type) { - struct tag *tag = (struct tag *) object; - object->flags |= flags; - if (tag_objects && !(object->flags & UNINTERESTING)) - add_pending_object(object, tag->tag); - object = parse_object(tag->tagged->sha1); - if (!object) - die("bad object %s", sha1_to_hex(tag->tagged->sha1)); - } - - /* - * Commit object? Just return it, we'll do all the complex - * reachability crud. - */ - if (object->type == commit_type) { - struct commit *commit = (struct commit *)object; - object->flags |= flags; - if (parse_commit(commit) < 0) - die("unable to parse commit %s", name); - if (flags & UNINTERESTING) - mark_parents_uninteresting(commit); - return commit; - } - - /* - * Tree object? Either mark it uniniteresting, or add it - * to the list of objects to look at later.. - */ - if (object->type == tree_type) { - struct tree *tree = (struct tree *)object; - if (!tree_objects) - return NULL; - if (flags & UNINTERESTING) { - mark_tree_uninteresting(tree); - return NULL; - } - add_pending_object(object, ""); - return NULL; - } - - /* - * Blob object? You know the drill by now.. - */ - if (object->type == blob_type) { - struct blob *blob = (struct blob *)object; - if (!blob_objects) - return NULL; - if (flags & UNINTERESTING) { - mark_blob_uninteresting(blob); - return NULL; - } - add_pending_object(object, ""); - return NULL; - } - die("%s is unknown object", name); -} - -static void handle_one_commit(struct commit *com, struct commit_list **lst) -{ - if (!com || com->object.flags & SEEN) - return; - com->object.flags |= SEEN; - commit_list_insert(com, lst); -} - -/* for_each_ref() callback does not allow user data -- Yuck. */ -static struct commit_list **global_lst; - -static int include_one_commit(const char *path, const unsigned char *sha1) -{ - struct commit *com = get_commit_reference(path, sha1, 0); - handle_one_commit(com, global_lst); - return 0; -} - -static void handle_all(struct commit_list **lst) -{ - global_lst = lst; - for_each_ref(include_one_commit); - global_lst = NULL; } int main(int argc, const char **argv) { - const char *prefix = setup_git_directory(); - struct commit_list *list = NULL; - int i, limited = 0; + struct commit_list *list; + int i; + + argc = setup_revisions(argc, argv, &revs, NULL); for (i = 1 ; i < argc; i++) { - int flags; const char *arg = argv[i]; - char *dotdot; - struct commit *commit; - unsigned char sha1[20]; /* accept -<digit>, like traditilnal "head" */ if ((*arg == '-') && isdigit(arg[1])) { - max_count = atoi(arg + 1); + revs.max_count = atoi(arg + 1); continue; } if (!strcmp(arg, "-n")) { if (++i >= argc) die("-n requires an argument"); - max_count = atoi(argv[i]); + revs.max_count = atoi(argv[i]); continue; } if (!strncmp(arg,"-n",2)) { - max_count = atoi(arg + 2); - continue; - } - if (!strncmp(arg, "--max-count=", 12)) { - max_count = atoi(arg + 12); - continue; - } - if (!strncmp(arg, "--max-age=", 10)) { - max_age = atoi(arg + 10); - limited = 1; - continue; - } - if (!strncmp(arg, "--min-age=", 10)) { - min_age = atoi(arg + 10); - limited = 1; + revs.max_count = atoi(arg + 2); continue; } if (!strcmp(arg, "--header")) { @@ -819,138 +337,35 @@ int main(int argc, const char **argv) commit_prefix = "commit "; continue; } - if (!strncmp(arg, "--no-merges", 11)) { - no_merges = 1; - continue; - } - if (!strcmp(arg, "--parents")) { - show_parents = 1; + if (!strcmp(arg, "--timestamp")) { + show_timestamp = 1; continue; } if (!strcmp(arg, "--bisect")) { bisect_list = 1; continue; } - if (!strcmp(arg, "--all")) { - handle_all(&list); - continue; - } - if (!strcmp(arg, "--objects")) { - tag_objects = 1; - tree_objects = 1; - blob_objects = 1; - continue; - } - if (!strcmp(arg, "--unpacked")) { - unpacked = 1; - limited = 1; - continue; - } - if (!strcmp(arg, "--merge-order")) { - merge_order = 1; - continue; - } - if (!strcmp(arg, "--show-breaks")) { - show_breaks = 1; - continue; - } - if (!strcmp(arg, "--topo-order")) { - topo_order = 1; - limited = 1; - continue; - } - if (!strcmp(arg, "--dense")) { - dense = 1; - continue; - } - if (!strcmp(arg, "--sparse")) { - dense = 0; - continue; - } - if (!strcmp(arg, "--remove-empty")) { - remove_empty_trees = 1; - continue; - } - if (!strcmp(arg, "--")) { - i++; - break; - } + usage(rev_list_usage); - if (show_breaks && !merge_order) - usage(rev_list_usage); - - flags = 0; - dotdot = strstr(arg, ".."); - if (dotdot) { - unsigned char from_sha1[20]; - char *next = dotdot + 2; - *dotdot = 0; - if (!*next) - next = "HEAD"; - if (!get_sha1(arg, from_sha1) && !get_sha1(next, sha1)) { - struct commit *exclude; - struct commit *include; - - exclude = get_commit_reference(arg, from_sha1, UNINTERESTING); - include = get_commit_reference(next, sha1, 0); - if (!exclude || !include) - die("Invalid revision range %s..%s", arg, next); - limited = 1; - handle_one_commit(exclude, &list); - handle_one_commit(include, &list); - continue; - } - *dotdot = '.'; - } - if (*arg == '^') { - flags = UNINTERESTING; - arg++; - limited = 1; - } - if (get_sha1(arg, sha1) < 0) { - struct stat st; - if (lstat(arg, &st) < 0) - die("'%s': %s", arg, strerror(errno)); - break; - } - commit = get_commit_reference(arg, sha1, flags); - handle_one_commit(commit, &list); } + list = revs.commits; + if (!list && - (!(tag_objects||tree_objects||blob_objects) && !pending_objects)) + (!(revs.tag_objects||revs.tree_objects||revs.blob_objects) && !revs.pending_objects)) usage(rev_list_usage); - paths = get_pathspec(prefix, argv + i); - if (paths) { - limited = 1; - diff_tree_setup_paths(paths); - } - save_commit_buffer = verbose_header; track_object_refs = 0; - if (!merge_order) { - sort_by_date(&list); - if (list && !limited && max_count == 1 && - !tag_objects && !tree_objects && !blob_objects) { - show_commit(list->item); - return 0; - } - if (limited) - list = limit_list(list); - if (topo_order) - sort_in_topological_order(&list); - show_commit_list(list); - } else { -#ifndef NO_OPENSSL - if (sort_list_in_merge_order(list, &process_commit)) { - die("merge order sort failed\n"); - } -#else - die("merge order sort unsupported, OpenSSL not linked"); -#endif - } + prepare_revision_walk(&revs); + if (revs.tree_objects) + mark_edges_uninteresting(revs.commits); + + if (bisect_list) + revs.commits = find_bisection(revs.commits); + + show_commit_list(&revs); return 0; } diff --git a/rev-parse.c b/rev-parse.c index 70a8271..e956cd5 100644 --- a/rev-parse.c +++ b/rev-parse.c @@ -39,15 +39,15 @@ static int is_rev_argument(const char *arg) "--header", "--max-age=", "--max-count=", - "--merge-order", "--min-age=", "--no-merges", "--objects", + "--objects-edge", "--parents", "--pretty", - "--show-breaks", "--sparse", "--topo-order", + "--date-order", "--unpacked", NULL }; @@ -166,13 +166,17 @@ int main(int argc, char **argv) unsigned char sha1[20]; const char *prefix = setup_git_directory(); + git_config(git_default_config); + for (i = 1; i < argc; i++) { struct stat st; char *arg = argv[i]; char *dotdot; - + if (as_is) { - show_file(arg); + if (show_file(arg) && as_is < 2) + if (lstat(arg, &st) < 0) + die("'%s': %s", arg, strerror(errno)); continue; } if (!strcmp(arg,"-n")) { @@ -192,7 +196,7 @@ int main(int argc, char **argv) if (*arg == '-') { if (!strcmp(arg, "--")) { - as_is = 1; + as_is = 2; /* Pass on the "--" if we show anything but files.. */ if (filter & (DO_FLAGS | DO_REVS)) show_file(arg); @@ -311,16 +315,17 @@ int main(int argc, char **argv) dotdot = strstr(arg, ".."); if (dotdot) { unsigned char end[20]; - char *n = dotdot+2; + char *next = dotdot + 2; + char *this = arg; *dotdot = 0; - if (!get_sha1(arg, sha1)) { - if (!*n) - n = "HEAD"; - if (!get_sha1(n, end)) { - show_rev(NORMAL, end, n); - show_rev(REVERSED, sha1, arg); - continue; - } + if (!*next) + next = "HEAD"; + if (dotdot == arg) + this = "HEAD"; + if (!get_sha1(this, sha1) && !get_sha1(next, end)) { + show_rev(NORMAL, end, next); + show_rev(REVERSED, sha1, this); + continue; } *dotdot = '.'; } diff --git a/revision.c b/revision.c new file mode 100644 index 0000000..ce35b5a --- /dev/null +++ b/revision.c @@ -0,0 +1,811 @@ +#include "cache.h" +#include "tag.h" +#include "blob.h" +#include "tree.h" +#include "commit.h" +#include "diff.h" +#include "refs.h" +#include "revision.h" + +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; +} + +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 = path_name(path, name); + *p = entry; + return &entry->next; +} + +static void mark_blob_uninteresting(struct blob *blob) +{ + if (blob->object.flags & UNINTERESTING) + return; + blob->object.flags |= UNINTERESTING; +} + +void mark_tree_uninteresting(struct tree *tree) +{ + struct object *obj = &tree->object; + struct tree_entry_list *entry; + + if (obj->flags & UNINTERESTING) + return; + obj->flags |= UNINTERESTING; + if (!has_sha1_file(obj->sha1)) + return; + if (parse_tree(tree) < 0) + die("bad tree %s", sha1_to_hex(obj->sha1)); + entry = tree->entries; + tree->entries = NULL; + while (entry) { + struct tree_entry_list *next = entry->next; + if (entry->directory) + mark_tree_uninteresting(entry->item.tree); + else + mark_blob_uninteresting(entry->item.blob); + free(entry); + entry = next; + } +} + +void mark_parents_uninteresting(struct commit *commit) +{ + struct commit_list *parents = commit->parents; + + while (parents) { + struct commit *commit = parents->item; + if (!(commit->object.flags & UNINTERESTING)) { + commit->object.flags |= UNINTERESTING; + + /* + * Normally we haven't parsed the parent + * yet, so we won't have a parent of a parent + * here. However, it may turn out that we've + * reached this commit some other way (where it + * wasn't uninteresting), in which case we need + * to mark its parents recursively too.. + */ + if (commit->parents) + mark_parents_uninteresting(commit); + } + + /* + * A missing commit is ok iff its parent is marked + * uninteresting. + * + * We just mark such a thing parsed, so that when + * it is popped next time around, we won't be trying + * to parse it and get an error. + */ + if (!has_sha1_file(commit->object.sha1)) + commit->object.parsed = 1; + parents = parents->next; + } +} + +static void add_pending_object(struct rev_info *revs, struct object *obj, const char *name) +{ + add_object(obj, &revs->pending_objects, NULL, name); +} + +static struct commit *get_commit_reference(struct rev_info *revs, const char *name, const unsigned char *sha1, unsigned int flags) +{ + struct object *object; + + object = parse_object(sha1); + if (!object) + die("bad object %s", name); + + /* + * Tag object? Look what it points to.. + */ + while (object->type == tag_type) { + struct tag *tag = (struct tag *) object; + object->flags |= flags; + if (revs->tag_objects && !(object->flags & UNINTERESTING)) + add_pending_object(revs, object, tag->tag); + object = parse_object(tag->tagged->sha1); + if (!object) + die("bad object %s", sha1_to_hex(tag->tagged->sha1)); + } + + /* + * Commit object? Just return it, we'll do all the complex + * reachability crud. + */ + if (object->type == commit_type) { + struct commit *commit = (struct commit *)object; + object->flags |= flags; + if (parse_commit(commit) < 0) + die("unable to parse commit %s", name); + if (flags & UNINTERESTING) { + mark_parents_uninteresting(commit); + revs->limited = 1; + } + return commit; + } + + /* + * Tree object? Either mark it uniniteresting, or add it + * to the list of objects to look at later.. + */ + if (object->type == tree_type) { + struct tree *tree = (struct tree *)object; + if (!revs->tree_objects) + return NULL; + if (flags & UNINTERESTING) { + mark_tree_uninteresting(tree); + return NULL; + } + add_pending_object(revs, object, ""); + return NULL; + } + + /* + * Blob object? You know the drill by now.. + */ + if (object->type == blob_type) { + struct blob *blob = (struct blob *)object; + if (!revs->blob_objects) + return NULL; + if (flags & UNINTERESTING) { + mark_blob_uninteresting(blob); + return NULL; + } + add_pending_object(revs, object, ""); + return NULL; + } + die("%s is unknown object", name); +} + +static int everybody_uninteresting(struct commit_list *orig) +{ + struct commit_list *list = orig; + while (list) { + struct commit *commit = list->item; + list = list->next; + if (commit->object.flags & UNINTERESTING) + continue; + return 0; + } + return 1; +} + +static int tree_difference = REV_TREE_SAME; + +static void file_add_remove(struct diff_options *options, + int addremove, unsigned mode, + const unsigned char *sha1, + const char *base, const char *path) +{ + int diff = REV_TREE_DIFFERENT; + + /* + * Is it an add of a new file? It means that the old tree + * didn't have it at all, so we will turn "REV_TREE_SAME" -> + * "REV_TREE_NEW", but leave any "REV_TREE_DIFFERENT" alone + * (and if it already was "REV_TREE_NEW", we'll keep it + * "REV_TREE_NEW" of course). + */ + if (addremove == '+') { + diff = tree_difference; + if (diff != REV_TREE_SAME) + return; + diff = REV_TREE_NEW; + } + tree_difference = diff; +} + +static void file_change(struct diff_options *options, + unsigned old_mode, unsigned new_mode, + const unsigned char *old_sha1, + const unsigned char *new_sha1, + const char *base, const char *path) +{ + tree_difference = REV_TREE_DIFFERENT; +} + +static struct diff_options diff_opt = { + .recursive = 1, + .add_remove = file_add_remove, + .change = file_change, +}; + +int rev_compare_tree(struct tree *t1, struct tree *t2) +{ + if (!t1) + return REV_TREE_NEW; + if (!t2) + return REV_TREE_DIFFERENT; + tree_difference = REV_TREE_SAME; + if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", &diff_opt) < 0) + return REV_TREE_DIFFERENT; + return tree_difference; +} + +int rev_same_tree_as_empty(struct tree *t1) +{ + int retval; + void *tree; + struct tree_desc empty, real; + + if (!t1) + return 0; + + tree = read_object_with_reference(t1->object.sha1, tree_type, &real.size, NULL); + if (!tree) + return 0; + real.buf = tree; + + empty.buf = ""; + empty.size = 0; + + tree_difference = 0; + retval = diff_tree(&empty, &real, "", &diff_opt); + free(tree); + + return retval >= 0 && !tree_difference; +} + +static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) +{ + struct commit_list **pp, *parent; + int tree_changed = 0; + + if (!commit->tree) + return; + + if (!commit->parents) { + if (!rev_same_tree_as_empty(commit->tree)) + commit->object.flags |= TREECHANGE; + return; + } + + pp = &commit->parents; + while ((parent = *pp) != NULL) { + struct commit *p = parent->item; + + parse_commit(p); + switch (rev_compare_tree(p->tree, commit->tree)) { + case REV_TREE_SAME: + if (p->object.flags & UNINTERESTING) { + /* Even if a merge with an uninteresting + * side branch brought the entire change + * we are interested in, we do not want + * to lose the other branches of this + * merge, so we just keep going. + */ + pp = &parent->next; + continue; + } + parent->next = NULL; + commit->parents = parent; + return; + + case REV_TREE_NEW: + if (revs->remove_empty_trees && + rev_same_tree_as_empty(p->tree)) { + /* We are adding all the specified + * paths from this parent, so the + * history beyond this parent is not + * interesting. Remove its parents + * (they are grandparents for us). + * IOW, we pretend this parent is a + * "root" commit. + */ + parse_commit(p); + p->parents = NULL; + } + /* fallthrough */ + case REV_TREE_DIFFERENT: + tree_changed = 1; + pp = &parent->next; + continue; + } + die("bad tree compare for commit %s", sha1_to_hex(commit->object.sha1)); + } + if (tree_changed) + commit->object.flags |= TREECHANGE; +} + +static void add_parents_to_list(struct rev_info *revs, struct commit *commit, struct commit_list **list) +{ + struct commit_list *parent = commit->parents; + + /* + * If the commit is uninteresting, don't try to + * prune parents - we want the maximal uninteresting + * set. + * + * Normally we haven't parsed the parent + * yet, so we won't have a parent of a parent + * here. However, it may turn out that we've + * reached this commit some other way (where it + * wasn't uninteresting), in which case we need + * to mark its parents recursively too.. + */ + if (commit->object.flags & UNINTERESTING) { + while (parent) { + struct commit *p = parent->item; + parent = parent->next; + parse_commit(p); + p->object.flags |= UNINTERESTING; + if (p->parents) + mark_parents_uninteresting(p); + if (p->object.flags & SEEN) + continue; + p->object.flags |= SEEN; + insert_by_date(p, list); + } + return; + } + + /* + * Ok, the commit wasn't uninteresting. Try to + * simplify the commit history and find the parent + * that has no differences in the path set if one exists. + */ + if (revs->prune_fn) + revs->prune_fn(revs, commit); + + parent = commit->parents; + while (parent) { + struct commit *p = parent->item; + + parent = parent->next; + + parse_commit(p); + if (p->object.flags & SEEN) + continue; + p->object.flags |= SEEN; + insert_by_date(p, list); + } +} + +static void limit_list(struct rev_info *revs) +{ + struct commit_list *list = revs->commits; + struct commit_list *newlist = NULL; + struct commit_list **p = &newlist; + + while (list) { + struct commit_list *entry = list; + struct commit *commit = list->item; + struct object *obj = &commit->object; + + list = list->next; + free(entry); + + if (revs->max_age != -1 && (commit->date < revs->max_age)) + obj->flags |= UNINTERESTING; + if (revs->unpacked && has_sha1_pack(obj->sha1)) + obj->flags |= UNINTERESTING; + add_parents_to_list(revs, commit, &list); + if (obj->flags & UNINTERESTING) { + mark_parents_uninteresting(commit); + if (everybody_uninteresting(list)) + break; + continue; + } + if (revs->min_age != -1 && (commit->date > revs->min_age)) + continue; + p = &commit_list_insert(commit, p)->next; + } + if (revs->boundary) { + /* mark the ones that are on the result list first */ + for (list = newlist; list; list = list->next) { + struct commit *commit = list->item; + commit->object.flags |= TMP_MARK; + } + for (list = newlist; list; list = list->next) { + struct commit *commit = list->item; + struct object *obj = &commit->object; + struct commit_list *parent; + if (obj->flags & UNINTERESTING) + continue; + for (parent = commit->parents; + parent; + parent = parent->next) { + struct commit *pcommit = parent->item; + if (!(pcommit->object.flags & UNINTERESTING)) + continue; + pcommit->object.flags |= BOUNDARY; + if (pcommit->object.flags & TMP_MARK) + continue; + pcommit->object.flags |= TMP_MARK; + p = &commit_list_insert(pcommit, p)->next; + } + } + for (list = newlist; list; list = list->next) { + struct commit *commit = list->item; + commit->object.flags &= ~TMP_MARK; + } + } + revs->commits = newlist; +} + +static void add_one_commit(struct commit *commit, struct rev_info *revs) +{ + if (!commit || (commit->object.flags & SEEN)) + return; + commit->object.flags |= SEEN; + commit_list_insert(commit, &revs->commits); +} + +static int all_flags; +static struct rev_info *all_revs; + +static int handle_one_ref(const char *path, const unsigned char *sha1) +{ + struct commit *commit = get_commit_reference(all_revs, path, sha1, all_flags); + add_one_commit(commit, all_revs); + return 0; +} + +static void handle_all(struct rev_info *revs, unsigned flags) +{ + all_revs = revs; + all_flags = flags; + for_each_ref(handle_one_ref); +} + +void init_revisions(struct rev_info *revs) +{ + memset(revs, 0, sizeof(*revs)); + revs->lifo = 1; + revs->dense = 1; + revs->prefix = setup_git_directory(); + revs->max_age = -1; + revs->min_age = -1; + revs->max_count = -1; + + revs->prune_fn = NULL; + revs->prune_data = NULL; + + revs->topo_setter = topo_sort_default_setter; + revs->topo_getter = topo_sort_default_getter; +} + +/* + * Parse revision information, filling in the "rev_info" structure, + * and removing the used arguments from the argument list. + * + * Returns the number of arguments left that weren't recognized + * (which are also moved to the head of the argument list) + */ +int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def) +{ + int i, flags, seen_dashdash; + const char **unrecognized = argv + 1; + int left = 1; + + init_revisions(revs); + + /* First, search for "--" */ + seen_dashdash = 0; + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (strcmp(arg, "--")) + continue; + argv[i] = NULL; + argc = i; + revs->prune_data = get_pathspec(revs->prefix, argv + i + 1); + seen_dashdash = 1; + break; + } + + flags = 0; + for (i = 1; i < argc; i++) { + struct commit *commit; + const char *arg = argv[i]; + unsigned char sha1[20]; + char *dotdot; + int local_flags; + + if (*arg == '-') { + if (!strncmp(arg, "--max-count=", 12)) { + revs->max_count = atoi(arg + 12); + continue; + } + /* accept -<digit>, like traditilnal "head" */ + if ((*arg == '-') && isdigit(arg[1])) { + revs->max_count = atoi(arg + 1); + continue; + } + if (!strcmp(arg, "-n")) { + if (argc <= i + 1) + die("-n requires an argument"); + revs->max_count = atoi(argv[++i]); + continue; + } + if (!strncmp(arg,"-n",2)) { + revs->max_count = atoi(arg + 2); + continue; + } + if (!strncmp(arg, "--max-age=", 10)) { + revs->max_age = atoi(arg + 10); + continue; + } + if (!strncmp(arg, "--since=", 8)) { + revs->max_age = approxidate(arg + 8); + continue; + } + if (!strncmp(arg, "--after=", 8)) { + revs->max_age = approxidate(arg + 8); + continue; + } + if (!strncmp(arg, "--min-age=", 10)) { + revs->min_age = atoi(arg + 10); + continue; + } + if (!strncmp(arg, "--before=", 9)) { + revs->min_age = approxidate(arg + 9); + continue; + } + if (!strncmp(arg, "--until=", 8)) { + revs->min_age = approxidate(arg + 8); + continue; + } + if (!strcmp(arg, "--all")) { + handle_all(revs, flags); + continue; + } + if (!strcmp(arg, "--not")) { + flags ^= UNINTERESTING; + continue; + } + if (!strcmp(arg, "--default")) { + if (++i >= argc) + die("bad --default argument"); + def = argv[i]; + continue; + } + if (!strcmp(arg, "--topo-order")) { + revs->topo_order = 1; + continue; + } + if (!strcmp(arg, "--date-order")) { + revs->lifo = 0; + revs->topo_order = 1; + continue; + } + if (!strcmp(arg, "--parents")) { + revs->parents = 1; + continue; + } + if (!strcmp(arg, "--dense")) { + revs->dense = 1; + continue; + } + if (!strcmp(arg, "--sparse")) { + revs->dense = 0; + continue; + } + if (!strcmp(arg, "--remove-empty")) { + revs->remove_empty_trees = 1; + continue; + } + if (!strcmp(arg, "--no-merges")) { + revs->no_merges = 1; + continue; + } + if (!strcmp(arg, "--boundary")) { + revs->boundary = 1; + continue; + } + if (!strcmp(arg, "--objects")) { + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + continue; + } + if (!strcmp(arg, "--objects-edge")) { + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + revs->edge_hint = 1; + continue; + } + if (!strcmp(arg, "--unpacked")) { + revs->unpacked = 1; + continue; + } + *unrecognized++ = arg; + left++; + continue; + } + dotdot = strstr(arg, ".."); + if (dotdot) { + unsigned char from_sha1[20]; + const char *next = dotdot + 2; + const char *this = arg; + *dotdot = 0; + if (!*next) + next = "HEAD"; + if (dotdot == arg) + this = "HEAD"; + if (!get_sha1(this, from_sha1) && + !get_sha1(next, sha1)) { + struct commit *exclude; + struct commit *include; + + exclude = get_commit_reference(revs, this, from_sha1, flags ^ UNINTERESTING); + include = get_commit_reference(revs, next, sha1, flags); + if (!exclude || !include) + die("Invalid revision range %s..%s", arg, next); + add_one_commit(exclude, revs); + add_one_commit(include, revs); + continue; + } + *dotdot = '.'; + } + local_flags = 0; + if (*arg == '^') { + local_flags = UNINTERESTING; + arg++; + } + if (get_sha1(arg, sha1) < 0) { + struct stat st; + int j; + + if (seen_dashdash || local_flags) + die("bad revision '%s'", arg); + + /* If we didn't have a "--", all filenames must exist */ + for (j = i; j < argc; j++) { + if (lstat(argv[j], &st) < 0) + die("'%s': %s", argv[j], strerror(errno)); + } + revs->prune_data = get_pathspec(revs->prefix, argv + i); + break; + } + commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags); + add_one_commit(commit, revs); + } + if (def && !revs->commits) { + unsigned char sha1[20]; + struct commit *commit; + if (get_sha1(def, sha1) < 0) + die("bad default revision '%s'", def); + commit = get_commit_reference(revs, def, sha1, 0); + add_one_commit(commit, revs); + } + + if (revs->topo_order || revs->unpacked) + revs->limited = 1; + + if (revs->prune_data) { + diff_tree_setup_paths(revs->prune_data); + revs->prune_fn = try_to_simplify_commit; + + /* + * If we fix up parent data, we currently cannot + * do that on-the-fly. + */ + if (revs->parents) + revs->limited = 1; + } + + return left; +} + +void prepare_revision_walk(struct rev_info *revs) +{ + sort_by_date(&revs->commits); + if (revs->limited) + limit_list(revs); + if (revs->topo_order) + sort_in_topological_order_fn(&revs->commits, revs->lifo, + revs->topo_setter, + revs->topo_getter); +} + +static int rewrite_one(struct commit **pp) +{ + for (;;) { + struct commit *p = *pp; + if (p->object.flags & (TREECHANGE | UNINTERESTING)) + return 0; + if (!p->parents) + return -1; + *pp = p->parents->item; + } +} + +static void rewrite_parents(struct commit *commit) +{ + struct commit_list **pp = &commit->parents; + while (*pp) { + struct commit_list *parent = *pp; + if (rewrite_one(&parent->item) < 0) { + *pp = parent->next; + continue; + } + pp = &parent->next; + } +} + +struct commit *get_revision(struct rev_info *revs) +{ + struct commit_list *list = revs->commits; + + if (!list) + return NULL; + + /* Check the max_count ... */ + switch (revs->max_count) { + case -1: + break; + case 0: + return NULL; + default: + revs->max_count--; + } + + do { + struct commit *commit = revs->commits->item; + + revs->commits = revs->commits->next; + + /* + * If we haven't done the list limiting, we need to look at + * the parents here. We also need to do the date-based limiting + * that we'd otherwise have done in limit_list(). + */ + if (!revs->limited) { + if ((revs->unpacked && + has_sha1_pack(commit->object.sha1)) || + (revs->max_age != -1 && + (commit->date < revs->max_age))) + continue; + add_parents_to_list(revs, commit, &revs->commits); + } + if (commit->object.flags & SHOWN) + continue; + if (!(commit->object.flags & BOUNDARY) && + (commit->object.flags & UNINTERESTING)) + continue; + if (revs->min_age != -1 && (commit->date > revs->min_age)) + continue; + if (revs->no_merges && + commit->parents && commit->parents->next) + continue; + if (revs->prune_fn && revs->dense) { + if (!(commit->object.flags & TREECHANGE)) + continue; + if (revs->parents) + rewrite_parents(commit); + } + commit->object.flags |= SHOWN; + return commit; + } while (revs->commits); + return NULL; +} diff --git a/revision.h b/revision.h new file mode 100644 index 0000000..0caeecf --- /dev/null +++ b/revision.h @@ -0,0 +1,76 @@ +#ifndef REVISION_H +#define REVISION_H + +#define SEEN (1u<<0) +#define UNINTERESTING (1u<<1) +#define TREECHANGE (1u<<2) +#define SHOWN (1u<<3) +#define TMP_MARK (1u<<4) /* for isolated cases; clean after use */ +#define BOUNDARY (1u<<5) + +struct rev_info; + +typedef void (prune_fn_t)(struct rev_info *revs, struct commit *commit); + +struct rev_info { + /* Starting list */ + struct commit_list *commits; + struct object_list *pending_objects; + + /* Basic information */ + const char *prefix; + void *prune_data; + prune_fn_t *prune_fn; + + /* Traversal flags */ + unsigned int dense:1, + no_merges:1, + remove_empty_trees:1, + lifo:1, + topo_order:1, + tag_objects:1, + tree_objects:1, + blob_objects:1, + edge_hint:1, + limited:1, + unpacked:1, + boundary:1, + parents:1; + + /* special limits */ + int max_count; + unsigned long max_age; + unsigned long min_age; + + topo_sort_set_fn_t topo_setter; + topo_sort_get_fn_t topo_getter; +}; + +#define REV_TREE_SAME 0 +#define REV_TREE_NEW 1 +#define REV_TREE_DIFFERENT 2 + +/* revision.c */ +extern int rev_same_tree_as_empty(struct tree *t1); +extern int rev_compare_tree(struct tree *t1, struct tree *t2); + +extern void init_revisions(struct rev_info *revs); +extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def); +extern void prepare_revision_walk(struct rev_info *revs); +extern struct commit *get_revision(struct rev_info *revs); + +extern void mark_parents_uninteresting(struct commit *commit); +extern void mark_tree_uninteresting(struct tree *tree); + +struct name_path { + struct name_path *up; + int elem_len; + const char *elem; +}; + +extern struct object_list **add_object(struct object *obj, + struct object_list **p, + struct name_path *path, + const char *name); + +#endif diff --git a/run-command.c b/run-command.c index b3d287e..ca67ee9 100644 --- a/run-command.c +++ b/run-command.c @@ -3,7 +3,7 @@ #include <sys/wait.h> #include "exec_cmd.h" -int run_command_v_opt(int argc, char **argv, int flags) +int run_command_v_opt(int argc, const char **argv, int flags) { pid_t pid = fork(); @@ -47,7 +47,7 @@ int run_command_v_opt(int argc, char **argv, int flags) } } -int run_command_v(int argc, char **argv) +int run_command_v(int argc, const char **argv) { return run_command_v_opt(argc, argv, 0); } @@ -55,7 +55,7 @@ int run_command_v(int argc, char **argv) int run_command(const char *cmd, ...) { int argc; - char *argv[MAX_RUN_COMMAND_ARGS]; + const char *argv[MAX_RUN_COMMAND_ARGS]; const char *arg; va_list param; diff --git a/run-command.h b/run-command.h index ef3ee05..70b477a 100644 --- a/run-command.h +++ b/run-command.h @@ -13,8 +13,8 @@ enum { #define RUN_COMMAND_NO_STDIO 1 #define RUN_GIT_CMD 2 /*If this is to be git sub-command */ -int run_command_v_opt(int argc, char **argv, int opt); -int run_command_v(int argc, char **argv); +int run_command_v_opt(int argc, const char **argv, int opt); +int run_command_v(int argc, const char **argv); int run_command(const char *cmd, ...); #endif diff --git a/send-pack.c b/send-pack.c index 990be3f..409f188 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) { @@ -26,7 +27,7 @@ static int is_zero_sha1(const unsigned char *sha1) static void exec_pack_objects(void) { - static char *args[] = { + static const char *args[] = { "pack-objects", "--stdout", NULL @@ -37,26 +38,47 @@ static void exec_pack_objects(void) static void exec_rev_list(struct ref *refs) { - static char *args[1000]; - int i = 0; + struct ref *ref; + static const char *args[1000]; + 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); @@ -340,6 +362,8 @@ int main(int argc, char **argv) pid_t pid; setup_git_directory(); + git_config(git_default_config); + argv++; for (i = 1; i < argc; i++, argv++) { char *arg = *argv; @@ -361,6 +385,10 @@ 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 aa09b46..ba8c4f7 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -9,6 +9,10 @@ #include "cache.h" #include "delta.h" #include "pack.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@ -864,7 +868,7 @@ 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 +882,7 @@ 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; @@ -894,16 +898,16 @@ void packed_object_info_detail(struct pack_entry *e, } switch (kind) { case OBJ_COMMIT: - strcpy(type, "commit"); + strcpy(type, commit_type); break; case OBJ_TREE: - strcpy(type, "tree"); + strcpy(type, tree_type); break; case OBJ_BLOB: - strcpy(type, "blob"); + strcpy(type, blob_type); break; case OBJ_TAG: - strcpy(type, "tag"); + strcpy(type, tag_type); break; default: die("corrupted pack file %s containing object of kind %d", @@ -934,16 +938,16 @@ static int packed_object_info(struct pack_entry *entry, unuse_packed_git(p); return retval; case OBJ_COMMIT: - strcpy(type, "commit"); + strcpy(type, commit_type); break; case OBJ_TREE: - strcpy(type, "tree"); + strcpy(type, tree_type); break; case OBJ_BLOB: - strcpy(type, "blob"); + strcpy(type, blob_type); break; case OBJ_TAG: - strcpy(type, "tag"); + strcpy(type, tag_type); break; default: die("corrupted pack file %s containing object of kind %d", @@ -973,6 +977,16 @@ static void *unpack_delta_entry(unsigned char *base_sha1, if (left < 20) die("truncated pack file"); + + /* The base entry _must_ be in the same pack */ + if (!find_pack_entry_one(base_sha1, &base_ent, p)) + die("failed to find delta-pack base object %s", + sha1_to_hex(base_sha1)); + base = unpack_entry_gently(&base_ent, type, &base_size); + if (!base) + die("failed to read delta-pack base object %s", + sha1_to_hex(base_sha1)); + data = base_sha1 + 20; data_size = left - 20; delta_data = xmalloc(delta_size); @@ -990,14 +1004,6 @@ static void *unpack_delta_entry(unsigned char *base_sha1, if ((st != Z_STREAM_END) || stream.total_out != delta_size) die("delta data unpack failed"); - /* The base entry _must_ be in the same pack */ - if (!find_pack_entry_one(base_sha1, &base_ent, p)) - die("failed to find delta-pack base object %s", - sha1_to_hex(base_sha1)); - base = unpack_entry_gently(&base_ent, type, &base_size); - if (!base) - die("failed to read delta-pack base object %s", - sha1_to_hex(base_sha1)); result = patch_delta(base, base_size, delta_data, delta_size, &result_size); @@ -1069,16 +1075,16 @@ void *unpack_entry_gently(struct pack_entry *entry, retval = unpack_delta_entry(pack, size, left, type, sizep, p); return retval; case OBJ_COMMIT: - strcpy(type, "commit"); + strcpy(type, commit_type); break; case OBJ_TREE: - strcpy(type, "tree"); + strcpy(type, tree_type); break; case OBJ_BLOB: - strcpy(type, "blob"); + strcpy(type, blob_type); break; case OBJ_TAG: - strcpy(type, "tag"); + strcpy(type, tag_type); break; default: return NULL; @@ -1239,9 +1245,9 @@ void *read_object_with_reference(const unsigned char *sha1, return buffer; } /* Handle references */ - else if (!strcmp(type, "commit")) + else if (!strcmp(type, commit_type)) ref_type = "tree "; - else if (!strcmp(type, "tag")) + else if (!strcmp(type, tag_type)) ref_type = "object "; else { free(buffer); @@ -1623,7 +1629,7 @@ int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) return -1; } if (!type) - type = "blob"; + type = blob_type; if (write_object) ret = write_sha1_file(buf, off, type, sha1); else { @@ -1650,7 +1656,7 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, con return -1; if (!type) - type = "blob"; + type = blob_type; if (write_object) ret = write_sha1_file(buf, size, type, sha1); else { @@ -1688,9 +1694,9 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write if (!write_object) { unsigned char hdr[50]; int hdrlen; - write_sha1_file_prepare(target, st->st_size, "blob", + write_sha1_file_prepare(target, st->st_size, blob_type, sha1, hdr, &hdrlen); - } else if (write_sha1_file(target, st->st_size, "blob", sha1)) + } else if (write_sha1_file(target, st->st_size, blob_type, sha1)) return error("%s: failed to insert into database", path); free(target); diff --git a/sha1_name.c b/sha1_name.c index d67de18..4f92e12 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -235,14 +235,21 @@ static int ambiguous_path(const char *path, int len) static int get_sha1_basic(const char *str, int len, unsigned char *sha1) { - static const char *prefix[] = { - "", - "refs", - "refs/tags", - "refs/heads", + static const char *fmt[] = { + "%.*s", + "refs/%.*s", + "refs/tags/%.*s", + "refs/heads/%.*s", + "refs/remotes/%.*s", + "refs/remotes/%.*s/HEAD", NULL }; const char **p; + const char *warning = "warning: refname '%.*s' is ambiguous.\n"; + char *pathname; + int already_found = 0; + unsigned char *this_result; + unsigned char sha1_from_ref[20]; if (len == 40 && !get_sha1_hex(str, sha1)) return 0; @@ -251,11 +258,21 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) if (ambiguous_path(str, len)) return -1; - for (p = prefix; *p; p++) { - char *pathname = git_path("%s/%.*s", *p, len, str); - if (!read_ref(pathname, sha1)) - return 0; + for (p = fmt; *p; p++) { + this_result = already_found ? sha1_from_ref : sha1; + pathname = git_path(*p, len, str); + if (!read_ref(pathname, this_result)) { + if (warn_ambiguous_refs) { + if (already_found) + fprintf(stderr, warning, len, str); + already_found++; + } + else + return 0; + } } + if (already_found) + return 0; return -1; } @@ -15,7 +15,7 @@ static int do_generic_cmd(const char *me, char *arg) my_argv[1] = arg; my_argv[2] = NULL; - return execv_git_cmd((char**) my_argv); + return execv_git_cmd(my_argv); } static struct commands { diff --git a/show-branch.c b/show-branch.c index 511fd3b..24efb65 100644 --- a/show-branch.c +++ b/show-branch.c @@ -5,7 +5,7 @@ #include "refs.h" static const char show_branch_usage[] = -"git-show-branch [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [<refs>...]"; +"git-show-branch [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...]"; static int default_num = 0; static int default_alloc = 0; @@ -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; @@ -544,9 +545,9 @@ 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; + int topics = 0; setup_git_directory(); git_config(git_show_branch_config); @@ -586,7 +587,11 @@ 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, "--topics")) + topics = 1; + else if (!strcmp(arg, "--date-order")) + lifo = 0; else usage(show_branch_usage); ac--; av++; @@ -710,8 +715,7 @@ 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) @@ -723,11 +727,17 @@ int main(int ac, char **av) while (seen) { struct commit *commit = pop_one_commit(&seen); int this_flag = commit->object.flags; + int is_merge_point = ((this_flag & all_revs) == all_revs); - shown_merge_point |= ((this_flag & all_revs) == all_revs); + shown_merge_point |= is_merge_point; if (1 < num_rev) { int is_merge = !!(commit->parents && commit->parents->next); + if (topics && + !is_merge_point && + (this_flag & (1u << REV_SHIFT))) + continue; + for (i = 0; i < num_rev; i++) { int mark; if (!(this_flag & (1u << (i + REV_SHIFT)))) diff --git a/t/.gitignore b/t/.gitignore new file mode 100644 index 0000000..fad67c0 --- /dev/null +++ b/t/.gitignore @@ -0,0 +1 @@ +trash @@ -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/annotate-tests.sh b/t/annotate-tests.sh new file mode 100644 index 0000000..114938c --- /dev/null +++ b/t/annotate-tests.sh @@ -0,0 +1,121 @@ +# This file isn't used as a test script directly, instead it is +# sourced from t8001-annotate.sh and t8001-blame.sh. + +check_count () { + head= + case "$1" in -h) head="$2"; shift; shift ;; esac + $PROG file $head | perl -e ' + my %expect = (@ARGV); + my %count = (); + while (<STDIN>) { + if (/^[0-9a-f]+\t\(([^\t]+)\t/) { + my $author = $1; + for ($author) { s/^\s*//; s/\s*$//; } + if (exists $expect{$author}) { + $count{$author}++; + } + } + } + my $bad = 0; + while (my ($author, $count) = each %count) { + my $ok; + if ($expect{$author} != $count) { + $bad = 1; + $ok = "bad"; + } + else { + $ok = "good"; + } + print STDERR "Author $author (expected $expect{$author}, attributed $count) $ok\n"; + } + exit($bad); + ' "$@" +} + +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' \ + 'check_count 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, two on B' \ + 'check_count A 2 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, two on B, two on B1' \ + 'check_count A 2 B 2 B1 2' + +test_expect_success \ + 'merge-setup part 2' \ + 'git checkout -b branch2 master && + sed -e "s/2A quick brown/4A quick brown lazy dog/" < file > file.new && + mv file.new file && + GIT_AUTHOR_NAME="B2" git commit -a -m "Branch2-1"' + +test_expect_success \ + 'Two lines blamed on A, one on B, one on B2' \ + 'check_count A 2 B 1 B2 1' + +test_expect_success \ + 'merge-setup part 3' \ + 'git pull . branch1' + +test_expect_success \ + 'Two lines blamed on A, one on B, two on B1, one on B2' \ + 'check_count A 2 B 1 B1 2 B2 1' + +test_expect_success \ + 'Annotating an old revision works' \ + 'check_count -h master A 2 B 2' + +test_expect_success \ + 'Annotating an old revision works' \ + 'check_count -h master^ A 2' + +test_expect_success \ + 'merge-setup part 4' \ + 'echo "evil merge." >>file && + EDITOR=: VISUAL=: git commit -a --amend' + +test_expect_success \ + 'Two lines blamed on A, one on B, two on B1, one on B2, one on A U Thor' \ + 'check_count A 2 B 1 B1 2 B2 1 "A U Thor" 1' + +test_expect_success \ + 'an incomplete line added' \ + 'echo "incomplete" | tr -d "\\012" >>file && + GIT_AUTHOR_NAME="C" git commit -a -m "Incomplete"' + +test_expect_success \ + 'With incomplete lines.' \ + 'check_count A 2 B 1 B1 2 B2 1 "A U Thor" 1 C 1' + +test_expect_success \ + 'some edit' \ + 'mv file file1 && + sed -e 1d -e "5s/3A/99/" file1 >file && + rm -f file1 && + GIT_AUTHOR_NAME="D" git commit -a -m "edit"' + +test_expect_success \ + 'some edit' \ + 'check_count A 1 B 1 B1 1 B2 1 "A U Thor" 1 C 1 D 1' diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index c339a36..6729a18 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/t1200-tutorial.sh b/t/t1200-tutorial.sh index c8a85f9..1002413 100755 --- a/t/t1200-tutorial.sh +++ b/t/t1200-tutorial.sh @@ -128,7 +128,7 @@ test_expect_success 'git show-branch' 'cmp show-branch.expect show-branch.output git checkout mybranch cat > resolve.expect << EOF -Updating from VARIABLE to VARIABLE. +Updating from VARIABLE to VARIABLE example | 1 + hello | 1 + 2 files changed, 2 insertions(+), 0 deletions(-) diff --git a/t/t1300-repo-config.sh b/t/t1300-repo-config.sh index 207dd3d..ab4dd5c 100755 --- a/t/t1300-repo-config.sh +++ b/t/t1300-repo-config.sh @@ -247,5 +247,13 @@ EOF test_expect_success 'hierarchical section value' 'cmp .git/config expect' +cat > .git/config << EOF +[novalue] + variable +EOF + +test_expect_success 'get variable with no value' \ + 'git-repo-config --get novalue.variable ^$' + test_done diff --git a/t/t2004-checkout-cache-temp.sh b/t/t2004-checkout-cache-temp.sh new file mode 100755 index 0000000..c100959 --- /dev/null +++ b/t/t2004-checkout-cache-temp.sh @@ -0,0 +1,212 @@ +#!/bin/sh +# +# Copyright (c) 2006 Shawn Pearce +# + +test_description='git-checkout-index --temp test. + +With --temp flag, git-checkout-index writes to temporary merge files +rather than the tracked path.' + +. ./test-lib.sh + +test_expect_success \ +'preparation' ' +mkdir asubdir && +echo tree1path0 >path0 && +echo tree1path1 >path1 && +echo tree1path3 >path3 && +echo tree1path4 >path4 && +echo tree1asubdir/path5 >asubdir/path5 && +git-update-index --add path0 path1 path3 path4 asubdir/path5 && +t1=$(git-write-tree) && +rm -f path* .merge_* out .git/index && +echo tree2path0 >path0 && +echo tree2path1 >path1 && +echo tree2path2 >path2 && +echo tree2path4 >path4 && +git-update-index --add path0 path1 path2 path4 && +t2=$(git-write-tree) && +rm -f path* .merge_* out .git/index && +echo tree2path0 >path0 && +echo tree3path1 >path1 && +echo tree3path2 >path2 && +echo tree3path3 >path3 && +git-update-index --add path0 path1 path2 path3 && +t3=$(git-write-tree)' + +test_expect_success \ +'checkout one stage 0 to temporary file' ' +rm -f path* .merge_* out .git/index && +git-read-tree $t1 && +git-checkout-index --temp -- path1 >out && +test $(wc -l <out) = 1 && +test $(cut "-d " -f2 out) = path1 && +p=$(cut "-d " -f1 out) && +test -f $p && +test $(cat $p) = tree1path1' + +test_expect_success \ +'checkout all stage 0 to temporary files' ' +rm -f path* .merge_* out .git/index && +git-read-tree $t1 && +git-checkout-index -a --temp >out && +test $(wc -l <out) = 5 && +for f in path0 path1 path3 path4 asubdir/path5 +do + test $(grep $f out | cut "-d " -f2) = $f && + p=$(grep $f out | cut "-d " -f1) && + test -f $p && + test $(cat $p) = tree1$f +done' + +test_expect_success \ +'prepare 3-way merge' ' +rm -f path* .merge_* out .git/index && +git-read-tree -m $t1 $t2 $t3' + +test_expect_success \ +'checkout one stage 2 to temporary file' ' +rm -f path* .merge_* out && +git-checkout-index --stage=2 --temp -- path1 >out && +test $(wc -l <out) = 1 && +test $(cut "-d " -f2 out) = path1 && +p=$(cut "-d " -f1 out) && +test -f $p && +test $(cat $p) = tree2path1' + +test_expect_success \ +'checkout all stage 2 to temporary files' ' +rm -f path* .merge_* out && +git-checkout-index --all --stage=2 --temp >out && +test $(wc -l <out) = 3 && +for f in path1 path2 path4 +do + test $(grep $f out | cut "-d " -f2) = $f && + p=$(grep $f out | cut "-d " -f1) && + test -f $p && + test $(cat $p) = tree2$f +done' + +test_expect_success \ +'checkout all stages/one file to nothing' ' +rm -f path* .merge_* out && +git-checkout-index --stage=all --temp -- path0 >out && +test $(wc -l <out) = 0' + +test_expect_success \ +'checkout all stages/one file to temporary files' ' +rm -f path* .merge_* out && +git-checkout-index --stage=all --temp -- path1 >out && +test $(wc -l <out) = 1 && +test $(cut "-d " -f2 out) = path1 && +cut "-d " -f1 out | (read s1 s2 s3 && +test -f $s1 && +test -f $s2 && +test -f $s3 && +test $(cat $s1) = tree1path1 && +test $(cat $s2) = tree2path1 && +test $(cat $s3) = tree3path1)' + +test_expect_success \ +'checkout some stages/one file to temporary files' ' +rm -f path* .merge_* out && +git-checkout-index --stage=all --temp -- path2 >out && +test $(wc -l <out) = 1 && +test $(cut "-d " -f2 out) = path2 && +cut "-d " -f1 out | (read s1 s2 s3 && +test $s1 = . && +test -f $s2 && +test -f $s3 && +test $(cat $s2) = tree2path2 && +test $(cat $s3) = tree3path2)' + +test_expect_success \ +'checkout all stages/all files to temporary files' ' +rm -f path* .merge_* out && +git-checkout-index -a --stage=all --temp >out && +test $(wc -l <out) = 5' + +test_expect_success \ +'-- path0: no entry' ' +test x$(grep path0 out | cut "-d " -f2) = x' + +test_expect_success \ +'-- path1: all 3 stages' ' +test $(grep path1 out | cut "-d " -f2) = path1 && +grep path1 out | cut "-d " -f1 | (read s1 s2 s3 && +test -f $s1 && +test -f $s2 && +test -f $s3 && +test $(cat $s1) = tree1path1 && +test $(cat $s2) = tree2path1 && +test $(cat $s3) = tree3path1)' + +test_expect_success \ +'-- path2: no stage 1, have stage 2 and 3' ' +test $(grep path2 out | cut "-d " -f2) = path2 && +grep path2 out | cut "-d " -f1 | (read s1 s2 s3 && +test $s1 = . && +test -f $s2 && +test -f $s3 && +test $(cat $s2) = tree2path2 && +test $(cat $s3) = tree3path2)' + +test_expect_success \ +'-- path3: no stage 2, have stage 1 and 3' ' +test $(grep path3 out | cut "-d " -f2) = path3 && +grep path3 out | cut "-d " -f1 | (read s1 s2 s3 && +test -f $s1 && +test $s2 = . && +test -f $s3 && +test $(cat $s1) = tree1path3 && +test $(cat $s3) = tree3path3)' + +test_expect_success \ +'-- path4: no stage 3, have stage 1 and 3' ' +test $(grep path4 out | cut "-d " -f2) = path4 && +grep path4 out | cut "-d " -f1 | (read s1 s2 s3 && +test -f $s1 && +test -f $s2 && +test $s3 = . && +test $(cat $s1) = tree1path4 && +test $(cat $s2) = tree2path4)' + +test_expect_success \ +'-- asubdir/path5: no stage 2 and 3 have stage 1' ' +test $(grep asubdir/path5 out | cut "-d " -f2) = asubdir/path5 && +grep asubdir/path5 out | cut "-d " -f1 | (read s1 s2 s3 && +test -f $s1 && +test $s2 = . && +test $s3 = . && +test $(cat $s1) = tree1asubdir/path5)' + +test_expect_success \ +'checkout --temp within subdir' ' +(cd asubdir && + git-checkout-index -a --stage=all >out && + test $(wc -l <out) = 1 && + test $(grep path5 out | cut "-d " -f2) = path5 && + grep path5 out | cut "-d " -f1 | (read s1 s2 s3 && + test -f ../$s1 && + test $s2 = . && + test $s3 = . && + test $(cat ../$s1) = tree1asubdir/path5) +)' + +test_expect_success \ +'checkout --temp symlink' ' +rm -f path* .merge_* out .git/index && +ln -s b a && +git-update-index --add a && +t4=$(git-write-tree) && +rm -f .git/index && +git-read-tree $t4 && +git-checkout-index --temp -a >out && +test $(wc -l <out) = 1 && +test $(cut "-d " -f2 out) = a && +p=$(cut "-d " -f1 out) && +test -f $p && +test $(cat $p) = b' + +test_done diff --git a/t/t3020-ls-files-error-unmatch.sh b/t/t3020-ls-files-error-unmatch.sh new file mode 100755 index 0000000..d55559e --- /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 0000000..d1947e1 --- /dev/null +++ b/t/t3600-rm.sh @@ -0,0 +1,71 @@ +#!/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' -q +git-add -- foo bar baz 'space embedded' -q +git-commit -m "add normal files" +test_tabs=y +if touch -- 'tab embedded' 'newline +embedded' +then +git-add -- 'tab embedded' 'newline +embedded' +git-commit -m "add files with tabs and newlines" +else + say 'Your filesystem does not allow tabs in filenames.' + test_tabs=n +fi + +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 "$test_tabs" = y && 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'" + +if test "$test_tabs" = y; then +chmod u-w . +test_expect_failure \ + 'Test that "git-rm -f" fails if its rm fails' \ + 'git-rm -f baz' +chmod u+w . +fi + +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/t5000-tar-tree.sh b/t/t5000-tar-tree.sh index adc5e93..278eb66 100755 --- a/t/t5000-tar-tree.sh +++ b/t/t5000-tar-tree.sh @@ -34,6 +34,9 @@ test_expect_success \ mkdir a/bin && cp /bin/sh a/bin && ln -s a a/l1 && + (p=long_path_to_a_file && cd a && + for depth in 1 2 3 4 5; do mkdir $p && cd $p; done && + echo text >file_with_long_path) && (cd a && find .) | sort >a.lst' test_expect_success \ diff --git a/t/t5600-clone-fail-cleanup.sh b/t/t5600-clone-fail-cleanup.sh new file mode 100755 index 0000000..0c6a363 --- /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/t6001-rev-list-merge-order.sh b/t/t6001-rev-list-merge-order.sh deleted file mode 100755 index 7724e8a..0000000 --- a/t/t6001-rev-list-merge-order.sh +++ /dev/null @@ -1,462 +0,0 @@ -#!/bin/sh -# -# Copyright (c) 2005 Jon Seymour -# - -test_description='Tests git-rev-list --merge-order functionality' - -. ./test-lib.sh -. ../t6000lib.sh # t6xxx specific functions - -# test-case specific test function -check_adjacency() -{ - read previous - echo "= $previous" - while read next - do - if ! (git-cat-file commit $previous | grep "^parent $next" >/dev/null) - then - echo "^ $next" - else - echo "| $next" - fi - previous=$next - done -} - -list_duplicates() -{ - "$@" | sort | uniq -d -} - -grep_stderr() -{ - args=$1 - shift 1 - "$@" 2>&1 | grep "$args" -} - -date >path0 -git-update-index --add path0 -save_tag tree git-write-tree -on_committer_date "1971-08-16 00:00:00" hide_error save_tag root unique_commit root tree -on_committer_date "1971-08-16 00:00:01" save_tag l0 unique_commit l0 tree -p root -on_committer_date "1971-08-16 00:00:02" save_tag l1 unique_commit l1 tree -p l0 -on_committer_date "1971-08-16 00:00:03" save_tag l2 unique_commit l2 tree -p l1 -on_committer_date "1971-08-16 00:00:04" save_tag a0 unique_commit a0 tree -p l2 -on_committer_date "1971-08-16 00:00:05" save_tag a1 unique_commit a1 tree -p a0 -on_committer_date "1971-08-16 00:00:06" save_tag b1 unique_commit b1 tree -p a0 -on_committer_date "1971-08-16 00:00:07" save_tag c1 unique_commit c1 tree -p b1 -on_committer_date "1971-08-16 00:00:08" as_author foobar@example.com save_tag b2 unique_commit b2 tree -p b1 -on_committer_date "1971-08-16 00:00:09" save_tag b3 unique_commit b2 tree -p b2 -on_committer_date "1971-08-16 00:00:10" save_tag c2 unique_commit c2 tree -p c1 -p b2 -on_committer_date "1971-08-16 00:00:11" save_tag c3 unique_commit c3 tree -p c2 -on_committer_date "1971-08-16 00:00:12" save_tag a2 unique_commit a2 tree -p a1 -on_committer_date "1971-08-16 00:00:13" save_tag a3 unique_commit a3 tree -p a2 -on_committer_date "1971-08-16 00:00:14" save_tag b4 unique_commit b4 tree -p b3 -p a3 -on_committer_date "1971-08-16 00:00:15" save_tag a4 unique_commit a4 tree -p a3 -p b4 -p c3 -on_committer_date "1971-08-16 00:00:16" save_tag l3 unique_commit l3 tree -p a4 -on_committer_date "1971-08-16 00:00:17" save_tag l4 unique_commit l4 tree -p l3 -on_committer_date "1971-08-16 00:00:18" save_tag l5 unique_commit l5 tree -p l4 -on_committer_date "1971-08-16 00:00:19" save_tag m1 unique_commit m1 tree -p a4 -p c3 -on_committer_date "1971-08-16 00:00:20" save_tag m2 unique_commit m2 tree -p c3 -p a4 -on_committer_date "1971-08-16 00:00:21" hide_error save_tag alt_root unique_commit alt_root tree -on_committer_date "1971-08-16 00:00:22" save_tag r0 unique_commit r0 tree -p alt_root -on_committer_date "1971-08-16 00:00:23" save_tag r1 unique_commit r1 tree -p r0 -on_committer_date "1971-08-16 00:00:24" save_tag l5r1 unique_commit l5r1 tree -p l5 -p r1 -on_committer_date "1971-08-16 00:00:25" save_tag r1l5 unique_commit r1l5 tree -p r1 -p l5 - - -# -# note: as of 20/6, it isn't possible to create duplicate parents, so this -# can't be tested. -# -#on_committer_date "1971-08-16 00:00:20" save_tag m3 unique_commit m3 tree -p c3 -p a4 -p c3 -hide_error save_tag e1 as_author e@example.com unique_commit e1 tree -save_tag e2 as_author e@example.com unique_commit e2 tree -p e1 -save_tag f1 as_author f@example.com unique_commit f1 tree -p e1 -save_tag e3 as_author e@example.com unique_commit e3 tree -p e2 -save_tag f2 as_author f@example.com unique_commit f2 tree -p f1 -save_tag e4 as_author e@example.com unique_commit e4 tree -p e3 -p f2 -save_tag e5 as_author e@example.com unique_commit e5 tree -p e4 -save_tag f3 as_author f@example.com unique_commit f3 tree -p f2 -save_tag f4 as_author f@example.com unique_commit f4 tree -p f3 -save_tag e6 as_author e@example.com unique_commit e6 tree -p e5 -p f4 -save_tag f5 as_author f@example.com unique_commit f5 tree -p f4 -save_tag f6 as_author f@example.com unique_commit f6 tree -p f5 -p e6 -save_tag e7 as_author e@example.com unique_commit e7 tree -p e6 -save_tag e8 as_author e@example.com unique_commit e8 tree -p e7 -save_tag e9 as_author e@example.com unique_commit e9 tree -p e8 -save_tag f7 as_author f@example.com unique_commit f7 tree -p f6 -save_tag f8 as_author f@example.com unique_commit f8 tree -p f7 -save_tag f9 as_author f@example.com unique_commit f9 tree -p f8 -save_tag e10 as_author e@example.com unique_commit e1 tree -p e9 -p f8 - -hide_error save_tag g0 unique_commit g0 tree -save_tag g1 unique_commit g1 tree -p g0 -save_tag h1 unique_commit g2 tree -p g0 -save_tag g2 unique_commit g3 tree -p g1 -p h1 -save_tag h2 unique_commit g4 tree -p g2 -save_tag g3 unique_commit g5 tree -p g2 -save_tag g4 unique_commit g6 tree -p g3 -p h2 - -git-update-ref HEAD $(tag l5) - -test_output_expect_success 'rev-list has correct number of entries' 'git-rev-list HEAD | wc -l | tr -d \" \"' <<EOF -19 -EOF - -if git-rev-list --merge-order HEAD 2>&1 | grep 'OpenSSL not linked' >/dev/null -then - test_expect_success 'skipping merge-order test' : - test_done - exit -fi - -normal_adjacency_count=$(git-rev-list HEAD | check_adjacency | grep -c "\^" | tr -d ' ') -merge_order_adjacency_count=$(git-rev-list --merge-order HEAD | check_adjacency | grep -c "\^" | tr -d ' ') -test_expect_success '--merge-order produces as many or fewer discontinuities' '[ $merge_order_adjacency_count -le $normal_adjacency_count ]' -test_output_expect_success 'simple merge order' 'git-rev-list --merge-order --show-breaks HEAD' <<EOF -= l5 -| l4 -| l3 -= a4 -| c3 -| c2 -| c1 -^ b4 -| b3 -| b2 -| b1 -^ a3 -| a2 -| a1 -= a0 -| l2 -| l1 -| l0 -= root -EOF - -test_output_expect_success 'two diamonds merge order (g6)' 'git-rev-list --merge-order --show-breaks g4' <<EOF -= g4 -| h2 -^ g3 -= g2 -| h1 -^ g1 -= g0 -EOF - -test_output_expect_success 'multiple heads' 'git-rev-list --merge-order a3 b3 c3' <<EOF -c3 -c2 -c1 -b3 -b2 -b1 -a3 -a2 -a1 -a0 -l2 -l1 -l0 -root -EOF - -test_output_expect_success 'multiple heads, prune at a1' 'git-rev-list --merge-order a3 b3 c3 ^a1' <<EOF -c3 -c2 -c1 -b3 -b2 -b1 -a3 -a2 -EOF - -test_output_expect_success 'multiple heads, prune at l1' 'git-rev-list --merge-order a3 b3 c3 ^l1' <<EOF -c3 -c2 -c1 -b3 -b2 -b1 -a3 -a2 -a1 -a0 -l2 -EOF - -test_output_expect_success 'cross-epoch, head at l5, prune at l1' 'git-rev-list --merge-order l5 ^l1' <<EOF -l5 -l4 -l3 -a4 -c3 -c2 -c1 -b4 -b3 -b2 -b1 -a3 -a2 -a1 -a0 -l2 -EOF - -test_output_expect_success 'duplicated head arguments' 'git-rev-list --merge-order l5 l5 ^l1' <<EOF -l5 -l4 -l3 -a4 -c3 -c2 -c1 -b4 -b3 -b2 -b1 -a3 -a2 -a1 -a0 -l2 -EOF - -test_output_expect_success 'prune near merge' 'git-rev-list --merge-order a4 ^c3' <<EOF -a4 -b4 -b3 -a3 -a2 -a1 -EOF - -test_output_expect_success "head has no parent" 'git-rev-list --merge-order --show-breaks root' <<EOF -= root -EOF - -test_output_expect_success "two nodes - one head, one base" 'git-rev-list --merge-order --show-breaks l0' <<EOF -= l0 -= root -EOF - -test_output_expect_success "three nodes one head, one internal, one base" 'git-rev-list --merge-order --show-breaks l1' <<EOF -= l1 -| l0 -= root -EOF - -test_output_expect_success "linear prune l2 ^root" 'git-rev-list --merge-order --show-breaks l2 ^root' <<EOF -^ l2 -| l1 -| l0 -EOF - -test_output_expect_success "linear prune l2 ^l0" 'git-rev-list --merge-order --show-breaks l2 ^l0' <<EOF -^ l2 -| l1 -EOF - -test_output_expect_success "linear prune l2 ^l1" 'git-rev-list --merge-order --show-breaks l2 ^l1' <<EOF -^ l2 -EOF - -test_output_expect_success "linear prune l5 ^a4" 'git-rev-list --merge-order --show-breaks l5 ^a4' <<EOF -^ l5 -| l4 -| l3 -EOF - -test_output_expect_success "linear prune l5 ^l3" 'git-rev-list --merge-order --show-breaks l5 ^l3' <<EOF -^ l5 -| l4 -EOF - -test_output_expect_success "linear prune l5 ^l4" 'git-rev-list --merge-order --show-breaks l5 ^l4' <<EOF -^ l5 -EOF - -test_output_expect_success "max-count 10 - merge order" 'git-rev-list --merge-order --show-breaks --max-count=10 l5' <<EOF -= l5 -| l4 -| l3 -= a4 -| c3 -| c2 -| c1 -^ b4 -| b3 -| b2 -EOF - -test_output_expect_success "max-count 10 - non merge order" 'git-rev-list --max-count=10 l5' <<EOF -l5 -l4 -l3 -a4 -b4 -a3 -a2 -c3 -c2 -b3 -EOF - -test_output_expect_success '--max-age=c3, no --merge-order' "git-rev-list --max-age=$(commit_date c3) l5" <<EOF -l5 -l4 -l3 -a4 -b4 -a3 -a2 -c3 -EOF - -test_output_expect_success '--max-age=c3, --merge-order' "git-rev-list --merge-order --max-age=$(commit_date c3) l5" <<EOF -l5 -l4 -l3 -a4 -c3 -b4 -a3 -a2 -EOF - -test_output_expect_success 'one specified head reachable from another a4, c3, --merge-order' "list_duplicates git-rev-list --merge-order a4 c3" <<EOF -EOF - -test_output_expect_success 'one specified head reachable from another c3, a4, --merge-order' "list_duplicates git-rev-list --merge-order c3 a4" <<EOF -EOF - -test_output_expect_success 'one specified head reachable from another a4, c3, no --merge-order' "list_duplicates git-rev-list a4 c3" <<EOF -EOF - -test_output_expect_success 'one specified head reachable from another c3, a4, no --merge-order' "list_duplicates git-rev-list c3 a4" <<EOF -EOF - -test_output_expect_success 'graph with c3 and a4 parents of head' "list_duplicates git-rev-list m1" <<EOF -EOF - -test_output_expect_success 'graph with a4 and c3 parents of head' "list_duplicates git-rev-list m2" <<EOF -EOF - -test_expect_success "head ^head --merge-order" 'git-rev-list --merge-order --show-breaks a3 ^a3' <<EOF -EOF - -# -# can't test this now - duplicate parents can't be created -# -#test_output_expect_success 'duplicate parents' 'git-rev-list --parents --merge-order --show-breaks m3' <<EOF -#= m3 c3 a4 c3 -#| a4 c3 b4 a3 -#| b4 a3 b3 -#| b3 b2 -#^ a3 a2 -#| a2 a1 -#| a1 a0 -#^ c3 c2 -#| c2 b2 c1 -#| b2 b1 -#^ c1 b1 -#| b1 a0 -#= a0 l2 -#| l2 l1 -#| l1 l0 -#| l0 root -#= root -#EOF - -test_expect_success "head ^head no --merge-order" 'git-rev-list a3 ^a3' <<EOF -EOF - -test_output_expect_success 'simple merge order (l5r1)' 'git-rev-list --merge-order --show-breaks l5r1' <<EOF -= l5r1 -| r1 -| r0 -| alt_root -^ l5 -| l4 -| l3 -| a4 -| c3 -| c2 -| c1 -^ b4 -| b3 -| b2 -| b1 -^ a3 -| a2 -| a1 -| a0 -| l2 -| l1 -| l0 -= root -EOF - -test_output_expect_success 'simple merge order (r1l5)' 'git-rev-list --merge-order --show-breaks r1l5' <<EOF -= r1l5 -| l5 -| l4 -| l3 -| a4 -| c3 -| c2 -| c1 -^ b4 -| b3 -| b2 -| b1 -^ a3 -| a2 -| a1 -| a0 -| l2 -| l1 -| l0 -| root -^ r1 -| r0 -= alt_root -EOF - -test_output_expect_success "don't print things unreachable from one branch" "git-rev-list a3 ^b3 --merge-order" <<EOF -a3 -a2 -a1 -EOF - -test_output_expect_success "--merge-order a4 l3" "git-rev-list --merge-order a4 l3" <<EOF -l3 -a4 -c3 -c2 -c1 -b4 -b3 -b2 -b1 -a3 -a2 -a1 -a0 -l2 -l1 -l0 -root -EOF - -# -# - -test_done diff --git a/t/t6021-merge-criss-cross.sh b/t/t6021-merge-criss-cross.sh index e8606c7..2623813 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 1292caf..a2d24b5 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/t7001-mv.sh b/t/t7001-mv.sh index 43d74c5..811a479 100755 --- a/t/t7001-mv.sh +++ b/t/t7001-mv.sh @@ -11,17 +11,31 @@ test_expect_success \ git-commit -m add -a' test_expect_success \ - 'moving the file' \ + 'moving the file out of subdirectory' \ 'cd path0 && git-mv COPYING ../path1/COPYING' # in path0 currently test_expect_success \ 'commiting the change' \ - 'cd .. && git-commit -m move -a' + 'cd .. && git-commit -m move-out -a' test_expect_success \ 'checking the commit' \ 'git-diff-tree -r -M --name-status HEAD^ HEAD | \ grep -E "^R100.+path0/COPYING.+path1/COPYING"' +test_expect_success \ + 'moving the file back into subdirectory' \ + 'cd path0 && git-mv ../path1/COPYING COPYING' + +# in path0 currently +test_expect_success \ + 'commiting the change' \ + 'cd .. && git-commit -m move-in -a' + +test_expect_success \ + 'checking the commit' \ + 'git-diff-tree -r -M --name-status HEAD^ HEAD | \ + grep -E "^R100.+path1/COPYING.+path0/COPYING"' + test_done diff --git a/t/t8001-annotate.sh b/t/t8001-annotate.sh new file mode 100755 index 0000000..2496397 --- /dev/null +++ b/t/t8001-annotate.sh @@ -0,0 +1,9 @@ +#!/bin/sh + +test_description='git-annotate' +. ./test-lib.sh + +PROG='git annotate' +. ../annotate-tests.sh + +test_done diff --git a/t/t8002-blame.sh b/t/t8002-blame.sh new file mode 100755 index 0000000..9777393 --- /dev/null +++ b/t/t8002-blame.sh @@ -0,0 +1,9 @@ +#!/bin/sh + +test_description='git-blame' +. ./test-lib.sh + +PROG='git blame -c' +. ../annotate-tests.sh + +test_done diff --git a/t/test-lib.sh b/t/test-lib.sh index 66f62b9..05f6e79 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 @@ -19,8 +19,7 @@ struct tag *lookup_tag(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - struct tag *ret = xmalloc(sizeof(struct tag)); - memset(ret, 0, sizeof(struct tag)); + struct tag *ret = xcalloc(1, sizeof(struct tag)); created_object(sha1, &ret->object); ret->object.type = tag_type; return ret; @@ -1,37 +1,23 @@ /* - * Copyright (c) 2005 Rene Scharfe + * Copyright (c) 2005, 2006 Rene Scharfe */ #include <time.h> #include "cache.h" -#include "diff.h" +#include "tree-walk.h" #include "commit.h" +#include "strbuf.h" +#include "tar.h" #define RECORDSIZE (512) #define BLOCKSIZE (RECORDSIZE * 20) -#define TYPEFLAG_AUTO '\0' -#define TYPEFLAG_REG '0' -#define TYPEFLAG_LNK '2' -#define TYPEFLAG_DIR '5' -#define TYPEFLAG_GLOBAL_HEADER 'g' -#define TYPEFLAG_EXT_HEADER 'x' - -#define EXT_HEADER_PATH 1 -#define EXT_HEADER_LINKPATH 2 - static const char tar_tree_usage[] = "git-tar-tree <key> [basedir]"; static char block[BLOCKSIZE]; static unsigned long offset; -static const char *basedir; static time_t archive_time; -struct path_prefix { - struct path_prefix *prev; - const char *name; -}; - /* tries hard to write, either succeeds or dies in the attempt */ static void reliable_write(void *buf, unsigned long size) { @@ -108,7 +94,6 @@ static void write_blocked(void *buf, unsigned long size) } if (size) { memcpy(block + offset, buf, size); - buf += size; offset += size; } tail = offset % RECORDSIZE; @@ -119,230 +104,170 @@ static void write_blocked(void *buf, unsigned long size) write_if_needed(); } -static void append_string(char **p, const char *s) -{ - unsigned int len = strlen(s); - memcpy(*p, s, len); - *p += len; -} - -static void append_char(char **p, char c) -{ - **p = c; - *p += 1; -} - -static void append_path_prefix(char **buffer, struct path_prefix *prefix) +static void strbuf_append_string(struct strbuf *sb, const char *s) { - if (!prefix) - return; - append_path_prefix(buffer, prefix->prev); - append_string(buffer, prefix->name); - append_char(buffer, '/'); -} - -static unsigned int path_prefix_len(struct path_prefix *prefix) -{ - if (!prefix) - return 0; - return path_prefix_len(prefix->prev) + strlen(prefix->name) + 1; -} - -static void append_path(char **p, int is_dir, const char *basepath, - struct path_prefix *prefix, const char *path) -{ - if (basepath) { - append_string(p, basepath); - append_char(p, '/'); + int slen = strlen(s); + int total = sb->len + slen; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; } - append_path_prefix(p, prefix); - append_string(p, path); - if (is_dir) - append_char(p, '/'); + memcpy(sb->buf + sb->len, s, slen); + sb->len = total; } -static unsigned int path_len(int is_dir, const char *basepath, - struct path_prefix *prefix, const char *path) -{ - unsigned int len = 0; - if (basepath) - len += strlen(basepath) + 1; - len += path_prefix_len(prefix) + strlen(path); - if (is_dir) - len++; - return len; -} - -static void append_extended_header_prefix(char **p, unsigned int size, - const char *keyword) +/* + * pax extended header records have the format "%u %s=%s\n". %u contains + * the size of the whole string (including the %u), the first %s is the + * keyword, the second one is the value. This function constructs such a + * string and appends it to a struct strbuf. + */ +static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, + const char *value, unsigned int valuelen) { - int len = sprintf(*p, "%u %s=", size, keyword); - *p += len; -} + char *p; + int len, total, tmp; -static unsigned int extended_header_len(const char *keyword, - unsigned int valuelen) -{ /* "%u %s=%s\n" */ - unsigned int len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; - if (len > 9) - len++; - if (len > 99) + len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; + for (tmp = len; tmp > 9; tmp /= 10) len++; - return len; -} -static void append_extended_header(char **p, const char *keyword, - const char *value, unsigned int len) -{ - unsigned int size = extended_header_len(keyword, len); - append_extended_header_prefix(p, size, keyword); - memcpy(*p, value, len); - *p += len; - append_char(p, '\n'); -} + total = sb->len + len; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } -static void write_header(const unsigned char *, char, const char *, struct path_prefix *, - const char *, unsigned int, void *, unsigned long); + p = sb->buf; + p += sprintf(p, "%u %s=", len, keyword); + memcpy(p, value, valuelen); + p += valuelen; + *p = '\n'; + sb->len = total; +} -/* stores a pax extended header directly in the block buffer */ -static void write_extended_header(const char *headerfilename, int is_dir, - unsigned int flags, const char *basepath, - struct path_prefix *prefix, - const char *path, unsigned int namelen, - void *content, unsigned int contentsize) +static unsigned int ustar_header_chksum(const struct ustar_header *header) { - char *buffer, *p; - unsigned int pathlen, size, linkpathlen = 0; - - size = pathlen = extended_header_len("path", namelen); - if (flags & EXT_HEADER_LINKPATH) { - linkpathlen = extended_header_len("linkpath", contentsize); - size += linkpathlen; - } - write_header(NULL, TYPEFLAG_EXT_HEADER, NULL, NULL, headerfilename, - 0100600, NULL, size); - - buffer = p = malloc(size); - if (!buffer) - die("git-tar-tree: %s", strerror(errno)); - append_extended_header_prefix(&p, pathlen, "path"); - append_path(&p, is_dir, basepath, prefix, path); - append_char(&p, '\n'); - if (flags & EXT_HEADER_LINKPATH) - append_extended_header(&p, "linkpath", content, contentsize); - write_blocked(buffer, size); - free(buffer); + char *p = (char *)header; + unsigned int chksum = 0; + while (p < header->chksum) + chksum += *p++; + chksum += sizeof(header->chksum) * ' '; + p += sizeof(header->chksum); + while (p < (char *)header + sizeof(struct ustar_header)) + chksum += *p++; + return chksum; } -static void write_global_extended_header(const unsigned char *sha1) +static int get_path_prefix(const struct strbuf *path, int maxlen) { - char *p; - unsigned int size; - - size = extended_header_len("comment", 40); - write_header(NULL, TYPEFLAG_GLOBAL_HEADER, NULL, NULL, - "pax_global_header", 0100600, NULL, size); - - p = get_record(); - append_extended_header(&p, "comment", sha1_to_hex(sha1), 40); - write_if_needed(); + int i = path->len; + if (i > maxlen) + i = maxlen; + while (i > 0 && path->buf[i] != '/') + i--; + return i; } -/* stores a ustar header directly in the block buffer */ -static void write_header(const unsigned char *sha1, char typeflag, const char *basepath, - struct path_prefix *prefix, const char *path, - unsigned int mode, void *buffer, unsigned long size) +static void write_entry(const unsigned char *sha1, struct strbuf *path, + unsigned int mode, void *buffer, unsigned long size) { - unsigned int namelen; - char *header = NULL; - unsigned int checksum = 0; - int i; - unsigned int ext_header = 0; - - if (typeflag == TYPEFLAG_AUTO) { - if (S_ISDIR(mode)) - typeflag = TYPEFLAG_DIR; - else if (S_ISLNK(mode)) - typeflag = TYPEFLAG_LNK; - else - typeflag = TYPEFLAG_REG; - } - - namelen = path_len(S_ISDIR(mode), basepath, prefix, path); - if (namelen > 100) - ext_header |= EXT_HEADER_PATH; - if (typeflag == TYPEFLAG_LNK && size > 100) - ext_header |= EXT_HEADER_LINKPATH; - - /* the extended header must be written before the normal one */ - if (ext_header) { - char headerfilename[51]; - sprintf(headerfilename, "%s.paxheader", sha1_to_hex(sha1)); - write_extended_header(headerfilename, S_ISDIR(mode), - ext_header, basepath, prefix, path, - namelen, buffer, size); - } - - header = get_record(); - - if (ext_header) { - sprintf(header, "%s.data", sha1_to_hex(sha1)); + struct ustar_header header; + struct strbuf ext_header; + + memset(&header, 0, sizeof(header)); + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + + if (!sha1) { + *header.typeflag = TYPEFLAG_GLOBAL_HEADER; + mode = 0100666; + strcpy(header.name, "pax_global_header"); + } else if (!path) { + *header.typeflag = TYPEFLAG_EXT_HEADER; + mode = 0100666; + sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); } else { - char *p = header; - append_path(&p, S_ISDIR(mode), basepath, prefix, path); + if (S_ISDIR(mode)) { + *header.typeflag = TYPEFLAG_DIR; + mode |= 0777; + } else if (S_ISLNK(mode)) { + *header.typeflag = TYPEFLAG_LNK; + mode |= 0777; + } else if (S_ISREG(mode)) { + *header.typeflag = TYPEFLAG_REG; + mode |= (mode & 0100) ? 0777 : 0666; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", + mode, sha1_to_hex(sha1)); + return; + } + if (path->len > sizeof(header.name)) { + int plen = get_path_prefix(path, sizeof(header.prefix)); + int rest = path->len - plen - 1; + if (plen > 0 && rest <= sizeof(header.name)) { + memcpy(header.prefix, path->buf, plen); + memcpy(header.name, path->buf + plen + 1, rest); + } else { + sprintf(header.name, "%s.data", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "path", + path->buf, path->len); + } + } else + memcpy(header.name, path->buf, path->len); } - if (typeflag == TYPEFLAG_LNK) { - if (ext_header & EXT_HEADER_LINKPATH) { - sprintf(&header[157], "see %s.paxheader", + if (S_ISLNK(mode) && buffer) { + if (size > sizeof(header.linkname)) { + sprintf(header.linkname, "see %s.paxheader", sha1_to_hex(sha1)); - } else { - if (buffer) - strncpy(&header[157], buffer, size); - } + strbuf_append_ext_header(&ext_header, "linkpath", + buffer, size); + } else + memcpy(header.linkname, buffer, size); } - if (S_ISDIR(mode)) - mode |= 0777; - else if (S_ISREG(mode)) - mode |= (mode & 0100) ? 0777 : 0666; - else if (S_ISLNK(mode)) - mode |= 0777; - sprintf(&header[100], "%07o", mode & 07777); + sprintf(header.mode, "%07o", mode & 07777); + sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); + sprintf(header.mtime, "%011lo", archive_time); /* XXX: should we provide more meaningful info here? */ - sprintf(&header[108], "%07o", 0); /* uid */ - sprintf(&header[116], "%07o", 0); /* gid */ - strncpy(&header[265], "git", 31); /* uname */ - strncpy(&header[297], "git", 31); /* gname */ - - if (S_ISDIR(mode) || S_ISLNK(mode)) - size = 0; - sprintf(&header[124], "%011lo", size); - sprintf(&header[136], "%011lo", archive_time); + sprintf(header.uid, "%07o", 0); + sprintf(header.gid, "%07o", 0); + strncpy(header.uname, "git", 31); + strncpy(header.gname, "git", 31); + sprintf(header.devmajor, "%07o", 0); + sprintf(header.devminor, "%07o", 0); - header[156] = typeflag; + memcpy(header.magic, "ustar", 6); + memcpy(header.version, "00", 2); - memcpy(&header[257], "ustar", 6); - memcpy(&header[263], "00", 2); + sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); - sprintf(&header[329], "%07o", 0); /* devmajor */ - sprintf(&header[337], "%07o", 0); /* devminor */ - - memset(&header[148], ' ', 8); - for (i = 0; i < RECORDSIZE; i++) - checksum += header[i]; - sprintf(&header[148], "%07o", checksum & 0x1fffff); + if (ext_header.len > 0) { + write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); + } + write_blocked(&header, sizeof(header)); + if (S_ISREG(mode) && buffer && size > 0) + write_blocked(buffer, size); +} - write_if_needed(); +static void write_global_extended_header(const unsigned char *sha1) +{ + struct strbuf ext_header; + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); + write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); } -static void traverse_tree(struct tree_desc *tree, - struct path_prefix *prefix) +static void traverse_tree(struct tree_desc *tree, struct strbuf *path) { - struct path_prefix this_prefix; - this_prefix.prev = prefix; + int pathlen = path->len; while (tree->size) { const char *name; @@ -358,16 +283,19 @@ static void traverse_tree(struct tree_desc *tree, eltbuf = read_sha1_file(sha1, elttype, &eltsize); if (!eltbuf) die("cannot read %s", sha1_to_hex(sha1)); - write_header(sha1, TYPEFLAG_AUTO, basedir, - prefix, name, mode, eltbuf, eltsize); + + path->len = pathlen; + strbuf_append_string(path, name); + if (S_ISDIR(mode)) + strbuf_append_string(path, "/"); + + write_entry(sha1, path, mode, eltbuf, eltsize); + if (S_ISDIR(mode)) { struct tree_desc subtree; subtree.buf = eltbuf; subtree.size = eltsize; - this_prefix.name = name; - traverse_tree(&subtree, &this_prefix); - } else if (!S_ISLNK(mode)) { - write_blocked(eltbuf, eltsize); + traverse_tree(&subtree, path); } free(eltbuf); } @@ -375,15 +303,22 @@ static void traverse_tree(struct tree_desc *tree, int main(int argc, char **argv) { - unsigned char sha1[20]; + unsigned char sha1[20], tree_sha1[20]; struct commit *commit; struct tree_desc tree; + struct strbuf current_path; + + current_path.buf = xmalloc(PATH_MAX); + current_path.alloc = PATH_MAX; + current_path.len = current_path.eof = 0; setup_git_directory(); + git_config(git_default_config); switch (argc) { case 3: - basedir = argv[2]; + strbuf_append_string(¤t_path, argv[2]); + strbuf_append_string(¤t_path, "/"); /* FALLTHROUGH */ case 2: if (get_sha1(argv[1], sha1) < 0) @@ -397,17 +332,19 @@ int main(int argc, char **argv) if (commit) { write_global_extended_header(commit->object.sha1); archive_time = commit->date; - } - tree.buf = read_object_with_reference(sha1, "tree", &tree.size, NULL); + } else + archive_time = time(NULL); + + tree.buf = read_object_with_reference(sha1, tree_type, &tree.size, + tree_sha1); if (!tree.buf) die("not a reference to a tag, commit or tree object: %s", sha1_to_hex(sha1)); - if (!archive_time) - archive_time = time(NULL); - if (basedir) - write_header((unsigned char *)"0", TYPEFLAG_DIR, NULL, NULL, - basedir, 040777, NULL, 0); - traverse_tree(&tree, NULL); + + if (current_path.len > 0) + write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); + traverse_tree(&tree, ¤t_path); write_trailer(); + free(current_path.buf); return 0; } @@ -0,0 +1,25 @@ +#define TYPEFLAG_AUTO '\0' +#define TYPEFLAG_REG '0' +#define TYPEFLAG_LNK '2' +#define TYPEFLAG_DIR '5' +#define TYPEFLAG_GLOBAL_HEADER 'g' +#define TYPEFLAG_EXT_HEADER 'x' + +struct ustar_header { + char name[100]; /* 0 */ + char mode[8]; /* 100 */ + char uid[8]; /* 108 */ + char gid[8]; /* 116 */ + char size[12]; /* 124 */ + char mtime[12]; /* 136 */ + char chksum[8]; /* 148 */ + char typeflag[1]; /* 156 */ + char linkname[100]; /* 157 */ + char magic[6]; /* 257 */ + char version[2]; /* 263 */ + char uname[32]; /* 265 */ + char gname[32]; /* 297 */ + char devmajor[8]; /* 329 */ + char devminor[8]; /* 337 */ + char prefix[155]; /* 345 */ +}; diff --git a/templates/hooks--pre-rebase b/templates/hooks--pre-rebase new file mode 100644 index 0000000..981c454 --- /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/tree-diff.c b/tree-diff.c index d978428..701fbba 100644 --- a/tree-diff.c +++ b/tree-diff.c @@ -3,40 +3,13 @@ */ #include "cache.h" #include "diff.h" +#include "tree.h" // What paths are we interested in? static int nr_paths = 0; static const char **paths = NULL; static int *pathlens = NULL; -void update_tree_entry(struct tree_desc *desc) -{ - void *buf = desc->buf; - unsigned long size = desc->size; - int len = strlen(buf) + 1 + 20; - - if (size < len) - die("corrupt tree file"); - desc->buf = buf + len; - desc->size = size - len; -} - -const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep) -{ - void *tree = desc->buf; - unsigned long size = desc->size; - int len = strlen(tree)+1; - const unsigned char *sha1 = tree + len; - const char *path = strchr(tree, ' '); - unsigned int mode; - - if (!path || size < len + 20 || sscanf(tree, "%o", &mode) != 1) - die("corrupt tree file"); - *pathp = path+1; - *modep = DIFF_FILE_CANON_MODE(mode); - return sha1; -} - static char *malloc_base(const char *base, const char *path, int pathlen) { int baselen = strlen(base); @@ -176,7 +149,7 @@ static int show_entry(struct diff_options *opt, const char *prefix, struct tree_ void *tree; tree = read_sha1_file(sha1, type, &inner.size); - if (!tree || strcmp(type, "tree")) + if (!tree || strcmp(type, tree_type)) die("corrupt tree sha %s", sha1_to_hex(sha1)); inner.buf = tree; @@ -234,10 +207,10 @@ int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const cha struct tree_desc t1, t2; int retval; - tree1 = read_object_with_reference(old, "tree", &t1.size, NULL); + tree1 = read_object_with_reference(old, tree_type, &t1.size, NULL); if (!tree1) die("unable to read source tree (%s)", sha1_to_hex(old)); - tree2 = read_object_with_reference(new, "tree", &t2.size, NULL); + tree2 = read_object_with_reference(new, tree_type, &t2.size, NULL); if (!tree2) die("unable to read destination tree (%s)", sha1_to_hex(new)); t1.buf = tree1; diff --git a/tree-walk.c b/tree-walk.c new file mode 100644 index 0000000..bf8bfdf --- /dev/null +++ b/tree-walk.c @@ -0,0 +1,117 @@ +#include "cache.h" +#include "tree-walk.h" +#include "tree.h" + +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_type, &size, NULL); + if (!buf) + die("unable to read tree %s", sha1_to_hex(sha1)); + } + desc->size = size; + desc->buf = buf; + return buf; +} + +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_clear(struct name_entry *a) +{ + memset(a, 0, sizeof(*a)); +} + +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); +} + +void update_tree_entry(struct tree_desc *desc) +{ + void *buf = desc->buf; + unsigned long size = desc->size; + int len = strlen(buf) + 1 + 20; + + if (size < len) + die("corrupt tree file"); + desc->buf = buf + len; + desc->size = size - len; +} + +const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep) +{ + void *tree = desc->buf; + unsigned long size = desc->size; + int len = strlen(tree)+1; + const unsigned char *sha1 = tree + len; + const char *path = strchr(tree, ' '); + unsigned int mode; + + if (!path || size < len + 20 || sscanf(tree, "%o", &mode) != 1) + die("corrupt tree file"); + *pathp = path+1; + *modep = canon_mode(mode); + return sha1; +} + +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); +} + diff --git a/tree-walk.h b/tree-walk.h new file mode 100644 index 0000000..76893e3 --- /dev/null +++ b/tree-walk.h @@ -0,0 +1,25 @@ +#ifndef TREE_WALK_H +#define TREE_WALK_H + +struct tree_desc { + void *buf; + unsigned long size; +}; + +struct name_entry { + const unsigned char *sha1; + const char *path; + unsigned int mode; + int pathlen; +}; + +void update_tree_entry(struct tree_desc *); +const unsigned char *tree_entry_extract(struct tree_desc *, const char **, unsigned int *); + +void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1); + +typedef void (*traverse_callback_t)(int n, unsigned long mask, struct name_entry *entry, const char *base); + +void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback); + +#endif @@ -18,9 +18,7 @@ static int read_one_entry(unsigned char *sha1, const char *base, int baselen, co len = strlen(pathname); size = cache_entry_size(baselen + len); - ce = xmalloc(size); - - memset(ce, 0, size); + ce = xcalloc(1, size); ce->ce_mode = create_ce_mode(mode); ce->ce_flags = create_ce_flags(baselen + len, stage); @@ -130,8 +128,7 @@ struct tree *lookup_tree(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - struct tree *ret = xmalloc(sizeof(struct tree)); - memset(ret, 0, sizeof(struct tree)); + struct tree *ret = xcalloc(1, sizeof(struct tree)); created_object(sha1, &ret->object); ret->object.type = tree_type; return ret; diff --git a/unpack-file.c b/unpack-file.c index 07303f8..23a8562 100644 --- a/unpack-file.c +++ b/unpack-file.c @@ -1,4 +1,5 @@ #include "cache.h" +#include "blob.h" static char *create_temp_file(unsigned char *sha1) { @@ -9,7 +10,7 @@ static char *create_temp_file(unsigned char *sha1) int fd; buf = read_sha1_file(sha1, type, &size); - if (!buf || strcmp(type, "blob")) + if (!buf || strcmp(type, blob_type)) die("unable to read blob object %s", sha1_to_hex(sha1)); strcpy(path, ".merge_file_XXXXXX"); @@ -30,6 +31,7 @@ int main(int argc, char **argv) usage("git-unpack-file <sha1>"); setup_git_directory(); + git_config(git_default_config); puts(create_temp_file(sha1)); return 0; diff --git a/unpack-objects.c b/unpack-objects.c index 815a1b3..3b824b0 100644 --- a/unpack-objects.c +++ b/unpack-objects.c @@ -2,6 +2,10 @@ #include "object.h" #include "delta.h" #include "pack.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" #include <sys/time.h> @@ -148,10 +152,10 @@ static int unpack_non_delta_entry(enum object_type kind, unsigned long size) const char *type; switch (kind) { - case OBJ_COMMIT: type = "commit"; break; - case OBJ_TREE: type = "tree"; break; - case OBJ_BLOB: type = "blob"; break; - case OBJ_TAG: type = "tag"; break; + case OBJ_COMMIT: type = commit_type; break; + case OBJ_TREE: type = tree_type; break; + case OBJ_BLOB: type = blob_type; break; + case OBJ_TAG: type = tag_type; break; default: die("bad type %d", kind); } if (!dry_run) diff --git a/update-index.c b/update-index.c index afec98d..1efac27 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; @@ -91,9 +114,9 @@ static int add_file_to_cache(const char *path) namelen = strlen(path); size = cache_entry_size(namelen); - ce = xmalloc(size); - memset(ce, 0, size); + ce = xcalloc(1, 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 +128,6 @@ 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 +150,7 @@ 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 +159,36 @@ 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 +208,19 @@ 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); @@ -267,13 +311,14 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, len = strlen(path); size = cache_entry_size(len); - ce = xmalloc(size); - memset(ce, 0, size); + ce = xcalloc(1, size); memcpy(ce->sha1, sha1, 20); 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 +362,12 @@ 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 +518,11 @@ 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 +548,14 @@ 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; @@ -512,9 +575,11 @@ int main(int argc, const char **argv) break; } if (!strcmp(path, "--index-info")) { + if (i != argc - 1) + die("--index-info must be at the end"); allow_add = allow_replace = allow_remove = 1; read_index_info(line_termination); - continue; + break; } if (!strcmp(path, "--ignore-missing")) { not_new = 1; diff --git a/update-ref.c b/update-ref.c index e6fbddb..ba4bf51 100644 --- a/update-ref.c +++ b/update-ref.c @@ -25,6 +25,7 @@ int main(int argc, char **argv) int fd, written; setup_git_directory(); + git_config(git_default_config); if (argc < 3 || argc > 4) usage(git_update_ref_usage); diff --git a/upload-pack.c b/upload-pack.c index 3606529..47560c9 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; @@ -45,24 +46,26 @@ static void create_pack_file(void) if (!pid) { int i; int args; - char **argv; + const char **argv; 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 *)); + p = xmalloc(args * sizeof(char *)); + argv = (const char **) p; buf = xmalloc(args * 45); - p = argv; dup2(fd[1], 1); close(0); 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 f866059..dcad6e6 100644 --- a/write-tree.c +++ b/write-tree.c @@ -4,6 +4,7 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "tree.h" static int missing_ok = 0; @@ -78,7 +79,7 @@ static int write_tree(struct cache_entry **cachep, int maxentries, const char *b nr++; } - write_sha1_file(buffer, offset, "tree", returnsha1); + write_sha1_file(buffer, offset, tree_type, returnsha1); free(buffer); return nr; } @@ -111,7 +112,7 @@ 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; diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h new file mode 100644 index 0000000..2540e8a --- /dev/null +++ b/xdiff/xdiff.h @@ -0,0 +1,94 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XDIFF_H) +#define XDIFF_H + +#ifdef __cplusplus +extern "C" { +#endif /* #ifdef __cplusplus */ + + +#define XDF_NEED_MINIMAL (1 << 1) + +#define XDL_PATCH_NORMAL '-' +#define XDL_PATCH_REVERSE '+' +#define XDL_PATCH_MODEMASK ((1 << 8) - 1) +#define XDL_PATCH_IGNOREBSPACE (1 << 8) + +#define XDL_EMIT_FUNCNAMES (1 << 0) + +#define XDL_MMB_READONLY (1 << 0) + +#define XDL_MMF_ATOMIC (1 << 0) + +#define XDL_BDOP_INS 1 +#define XDL_BDOP_CPY 2 +#define XDL_BDOP_INSB 3 + + +typedef struct s_mmfile { + char *ptr; + long size; +} mmfile_t; + +typedef struct s_mmbuffer { + char *ptr; + long size; +} mmbuffer_t; + +typedef struct s_xpparam { + unsigned long flags; +} xpparam_t; + +typedef struct s_xdemitcb { + void *priv; + int (*outf)(void *, mmbuffer_t *, int); +} xdemitcb_t; + +typedef struct s_xdemitconf { + long ctxlen; + unsigned long flags; +} xdemitconf_t; + +typedef struct s_bdiffparam { + long bsize; +} bdiffparam_t; + + +#define xdl_malloc(x) malloc(x) +#define xdl_free(ptr) free(ptr) +#define xdl_realloc(ptr,x) realloc(ptr,x) + +void *xdl_mmfile_first(mmfile_t *mmf, long *size); +void *xdl_mmfile_next(mmfile_t *mmf, long *size); +long xdl_mmfile_size(mmfile_t *mmf); + +int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdemitconf_t const *xecfg, xdemitcb_t *ecb); + +#ifdef __cplusplus +} +#endif /* #ifdef __cplusplus */ + +#endif /* #if !defined(XDIFF_H) */ + diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c new file mode 100644 index 0000000..e81bca6 --- /dev/null +++ b/xdiff/xdiffi.c @@ -0,0 +1,464 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + + +#define XDL_MAX_COST_MIN 256 +#define XDL_HEUR_MIN_COST 256 +#define XDL_LINE_MAX (long)((1UL << (8 * sizeof(long) - 1)) - 1) +#define XDL_SNAKE_CNT 20 +#define XDL_K_HEUR 4 + + + +typedef struct s_xdpsplit { + long i1, i2; + int min_lo, min_hi; +} xdpsplit_t; + + + + +static long xdl_split(unsigned long const *ha1, long off1, long lim1, + unsigned long const *ha2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, + xdalgoenv_t *xenv); +static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2); + + + + +/* + * See "An O(ND) Difference Algorithm and its Variations", by Eugene Myers. + * Basically considers a "box" (off1, off2, lim1, lim2) and scan from both + * the forward diagonal starting from (off1, off2) and the backward diagonal + * starting from (lim1, lim2). If the K values on the same diagonal crosses + * returns the furthest point of reach. We might end up having to expensive + * cases using this algorithm is full, so a little bit of heuristic is needed + * to cut the search and to return a suboptimal point. + */ +static long xdl_split(unsigned long const *ha1, long off1, long lim1, + unsigned long const *ha2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, + xdalgoenv_t *xenv) { + long dmin = off1 - lim2, dmax = lim1 - off2; + long fmid = off1 - off2, bmid = lim1 - lim2; + long odd = (fmid - bmid) & 1; + long fmin = fmid, fmax = fmid; + long bmin = bmid, bmax = bmid; + long ec, d, i1, i2, prev1, best, dd, v, k; + + /* + * Set initial diagonal values for both forward and backward path. + */ + kvdf[fmid] = off1; + kvdb[bmid] = lim1; + + for (ec = 1;; ec++) { + int got_snake = 0; + + /* + * We need to extent the diagonal "domain" by one. If the next + * values exits the box boundaries we need to change it in the + * opposite direction because (max - min) must be a power of two. + * Also we initialize the extenal K value to -1 so that we can + * avoid extra conditions check inside the core loop. + */ + if (fmin > dmin) + kvdf[--fmin - 1] = -1; + else + ++fmin; + if (fmax < dmax) + kvdf[++fmax + 1] = -1; + else + --fmax; + + for (d = fmax; d >= fmin; d -= 2) { + if (kvdf[d - 1] >= kvdf[d + 1]) + i1 = kvdf[d - 1] + 1; + else + i1 = kvdf[d + 1]; + prev1 = i1; + i2 = i1 - d; + for (; i1 < lim1 && i2 < lim2 && ha1[i1] == ha2[i2]; i1++, i2++); + if (i1 - prev1 > xenv->snake_cnt) + got_snake = 1; + kvdf[d] = i1; + if (odd && bmin <= d && d <= bmax && kvdb[d] <= i1) { + spl->i1 = i1; + spl->i2 = i2; + spl->min_lo = spl->min_hi = 1; + return ec; + } + } + + /* + * We need to extent the diagonal "domain" by one. If the next + * values exits the box boundaries we need to change it in the + * opposite direction because (max - min) must be a power of two. + * Also we initialize the extenal K value to -1 so that we can + * avoid extra conditions check inside the core loop. + */ + if (bmin > dmin) + kvdb[--bmin - 1] = XDL_LINE_MAX; + else + ++bmin; + if (bmax < dmax) + kvdb[++bmax + 1] = XDL_LINE_MAX; + else + --bmax; + + for (d = bmax; d >= bmin; d -= 2) { + if (kvdb[d - 1] < kvdb[d + 1]) + i1 = kvdb[d - 1]; + else + i1 = kvdb[d + 1] - 1; + prev1 = i1; + i2 = i1 - d; + for (; i1 > off1 && i2 > off2 && ha1[i1 - 1] == ha2[i2 - 1]; i1--, i2--); + if (prev1 - i1 > xenv->snake_cnt) + got_snake = 1; + kvdb[d] = i1; + if (!odd && fmin <= d && d <= fmax && i1 <= kvdf[d]) { + spl->i1 = i1; + spl->i2 = i2; + spl->min_lo = spl->min_hi = 1; + return ec; + } + } + + if (need_min) + continue; + + /* + * If the edit cost is above the heuristic trigger and if + * we got a good snake, we sample current diagonals to see + * if some of the, have reached an "interesting" path. Our + * measure is a function of the distance from the diagonal + * corner (i1 + i2) penalized with the distance from the + * mid diagonal itself. If this value is above the current + * edit cost times a magic factor (XDL_K_HEUR) we consider + * it interesting. + */ + if (got_snake && ec > xenv->heur_min) { + for (best = 0, d = fmax; d >= fmin; d -= 2) { + dd = d > fmid ? d - fmid: fmid - d; + i1 = kvdf[d]; + i2 = i1 - d; + v = (i1 - off1) + (i2 - off2) - dd; + + if (v > XDL_K_HEUR * ec && v > best && + off1 + xenv->snake_cnt <= i1 && i1 < lim1 && + off2 + xenv->snake_cnt <= i2 && i2 < lim2) { + for (k = 1; ha1[i1 - k] == ha2[i2 - k]; k++) + if (k == xenv->snake_cnt) { + best = v; + spl->i1 = i1; + spl->i2 = i2; + break; + } + } + } + if (best > 0) { + spl->min_lo = 1; + spl->min_hi = 0; + return ec; + } + + for (best = 0, d = bmax; d >= bmin; d -= 2) { + dd = d > bmid ? d - bmid: bmid - d; + i1 = kvdb[d]; + i2 = i1 - d; + v = (lim1 - i1) + (lim2 - i2) - dd; + + if (v > XDL_K_HEUR * ec && v > best && + off1 < i1 && i1 <= lim1 - xenv->snake_cnt && + off2 < i2 && i2 <= lim2 - xenv->snake_cnt) { + for (k = 0; ha1[i1 + k] == ha2[i2 + k]; k++) + if (k == xenv->snake_cnt - 1) { + best = v; + spl->i1 = i1; + spl->i2 = i2; + break; + } + } + } + if (best > 0) { + spl->min_lo = 0; + spl->min_hi = 1; + return ec; + } + } + + /* + * Enough is enough. We spent too much time here and now we collect + * the furthest reaching path using the (i1 + i2) measure. + */ + if (ec >= xenv->mxcost) { + long fbest, fbest1, bbest, bbest1; + + fbest = -1; + for (d = fmax; d >= fmin; d -= 2) { + i1 = XDL_MIN(kvdf[d], lim1); + i2 = i1 - d; + if (lim2 < i2) + i1 = lim2 + d, i2 = lim2; + if (fbest < i1 + i2) { + fbest = i1 + i2; + fbest1 = i1; + } + } + + bbest = XDL_LINE_MAX; + for (d = bmax; d >= bmin; d -= 2) { + i1 = XDL_MAX(off1, kvdb[d]); + i2 = i1 - d; + if (i2 < off2) + i1 = off2 + d, i2 = off2; + if (i1 + i2 < bbest) { + bbest = i1 + i2; + bbest1 = i1; + } + } + + if ((lim1 + lim2) - bbest < fbest - (off1 + off2)) { + spl->i1 = fbest1; + spl->i2 = fbest - fbest1; + spl->min_lo = 1; + spl->min_hi = 0; + } else { + spl->i1 = bbest1; + spl->i2 = bbest - bbest1; + spl->min_lo = 0; + spl->min_hi = 1; + } + return ec; + } + } + + return -1; +} + + +/* + * Rule: "Divide et Impera". Recursively split the box in sub-boxes by calling + * the box splitting function. Note that the real job (marking changed lines) + * is done in the two boundary reaching checks. + */ +int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, + diffdata_t *dd2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) { + unsigned long const *ha1 = dd1->ha, *ha2 = dd2->ha; + + /* + * Shrink the box by walking through each diagonal snake (SW and NE). + */ + for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++); + for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--); + + /* + * If one dimension is empty, then all records on the other one must + * be obviously changed. + */ + if (off1 == lim1) { + char *rchg2 = dd2->rchg; + long *rindex2 = dd2->rindex; + + for (; off2 < lim2; off2++) + rchg2[rindex2[off2]] = 1; + } else if (off2 == lim2) { + char *rchg1 = dd1->rchg; + long *rindex1 = dd1->rindex; + + for (; off1 < lim1; off1++) + rchg1[rindex1[off1]] = 1; + } else { + long ec; + xdpsplit_t spl; + + /* + * Divide ... + */ + if ((ec = xdl_split(ha1, off1, lim1, ha2, off2, lim2, kvdf, kvdb, + need_min, &spl, xenv)) < 0) { + + return -1; + } + + /* + * ... et Impera. + */ + if (xdl_recs_cmp(dd1, off1, spl.i1, dd2, off2, spl.i2, + kvdf, kvdb, spl.min_lo, xenv) < 0 || + xdl_recs_cmp(dd1, spl.i1, lim1, dd2, spl.i2, lim2, + kvdf, kvdb, spl.min_hi, xenv) < 0) { + + return -1; + } + } + + return 0; +} + + +int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe) { + long ndiags; + long *kvd, *kvdf, *kvdb; + xdalgoenv_t xenv; + diffdata_t dd1, dd2; + + if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) { + + return -1; + } + + /* + * Allocate and setup K vectors to be used by the differential algorithm. + * One is to store the forward path and one to store the backward path. + */ + ndiags = xe->xdf1.nreff + xe->xdf2.nreff + 3; + if (!(kvd = (long *) xdl_malloc((2 * ndiags + 2) * sizeof(long)))) { + + xdl_free_env(xe); + return -1; + } + kvdf = kvd; + kvdb = kvdf + ndiags; + kvdf += xe->xdf2.nreff + 1; + kvdb += xe->xdf2.nreff + 1; + + xenv.mxcost = xdl_bogosqrt(ndiags); + if (xenv.mxcost < XDL_MAX_COST_MIN) + xenv.mxcost = XDL_MAX_COST_MIN; + xenv.snake_cnt = XDL_SNAKE_CNT; + xenv.heur_min = XDL_HEUR_MIN_COST; + + dd1.nrec = xe->xdf1.nreff; + dd1.ha = xe->xdf1.ha; + dd1.rchg = xe->xdf1.rchg; + dd1.rindex = xe->xdf1.rindex; + dd2.nrec = xe->xdf2.nreff; + dd2.ha = xe->xdf2.ha; + dd2.rchg = xe->xdf2.rchg; + dd2.rindex = xe->xdf2.rindex; + + if (xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec, + kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, &xenv) < 0) { + + xdl_free(kvd); + xdl_free_env(xe); + return -1; + } + + xdl_free(kvd); + + return 0; +} + + +static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2) { + xdchange_t *xch; + + if (!(xch = (xdchange_t *) xdl_malloc(sizeof(xdchange_t)))) + return NULL; + + xch->next = xscr; + xch->i1 = i1; + xch->i2 = i2; + xch->chg1 = chg1; + xch->chg2 = chg2; + + return xch; +} + + +int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) { + xdchange_t *cscr = NULL, *xch; + char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg; + long i1, i2, l1, l2; + + /* + * Trivial. Collects "groups" of changes and creates an edit script. + */ + for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--) + if (rchg1[i1 - 1] || rchg2[i2 - 1]) { + for (l1 = i1; rchg1[i1 - 1]; i1--); + for (l2 = i2; rchg2[i2 - 1]; i2--); + + if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) { + xdl_free_script(cscr); + return -1; + } + cscr = xch; + } + + *xscr = cscr; + + return 0; +} + + +void xdl_free_script(xdchange_t *xscr) { + xdchange_t *xch; + + while ((xch = xscr) != NULL) { + xscr = xscr->next; + xdl_free(xch); + } +} + + +int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdemitconf_t const *xecfg, xdemitcb_t *ecb) { + xdchange_t *xscr; + xdfenv_t xe; + + if (xdl_do_diff(mf1, mf2, xpp, &xe) < 0) { + + return -1; + } + + if (xdl_build_script(&xe, &xscr) < 0) { + + xdl_free_env(&xe); + return -1; + } + + if (xscr) { + if (xdl_emit_diff(&xe, xscr, ecb, xecfg) < 0) { + + xdl_free_script(xscr); + xdl_free_env(&xe); + return -1; + } + + xdl_free_script(xscr); + } + + xdl_free_env(&xe); + + return 0; +} + diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h new file mode 100644 index 0000000..dd8f3c9 --- /dev/null +++ b/xdiff/xdiffi.h @@ -0,0 +1,60 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XDIFFI_H) +#define XDIFFI_H + + +typedef struct s_diffdata { + long nrec; + unsigned long const *ha; + long *rindex; + char *rchg; +} diffdata_t; + +typedef struct s_xdalgoenv { + long mxcost; + long snake_cnt; + long heur_min; +} xdalgoenv_t; + +typedef struct s_xdchange { + struct s_xdchange *next; + long i1, i2; + long chg1, chg2; +} xdchange_t; + + + +int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, + diffdata_t *dd2, long off2, long lim2, + long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv); +int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe); +int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr); +void xdl_free_script(xdchange_t *xscr); +int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, + xdemitconf_t const *xecfg); + + +#endif /* #if !defined(XDIFFI_H) */ + diff --git a/xdiff/xemit.c b/xdiff/xemit.c new file mode 100644 index 0000000..ad5bfb1 --- /dev/null +++ b/xdiff/xemit.c @@ -0,0 +1,180 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + + + +static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec); +static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb); +static xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg); + + + + +static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) { + + *rec = xdf->recs[ri]->ptr; + + return xdf->recs[ri]->size; +} + + +static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) { + long size, psize = strlen(pre); + char const *rec; + + size = xdl_get_rec(xdf, ri, &rec); + if (xdl_emit_diffrec(rec, size, pre, psize, ecb) < 0) { + + return -1; + } + + return 0; +} + + +/* + * Starting at the passed change atom, find the latest change atom to be included + * inside the differential hunk according to the specified configuration. + */ +static xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg) { + xdchange_t *xch, *xchp; + + for (xchp = xscr, xch = xscr->next; xch; xchp = xch, xch = xch->next) + if (xch->i1 - (xchp->i1 + xchp->chg1) > 2 * xecfg->ctxlen) + break; + + return xchp; +} + + +static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll) { + + /* + * Be quite stupid about this for now. Find a line in the old file + * before the start of the hunk (and context) which starts with a + * plausible character. + */ + + const char *rec; + long len; + + *ll = 0; + while (i-- > 0) { + len = xdl_get_rec(xf, i, &rec); + if (len > 0 && + (isalpha((unsigned char)*rec) || /* identifier? */ + *rec == '_' || /* also identifier? */ + *rec == '(' || /* lisp defun? */ + *rec == '#')) { /* #define? */ + if (len > sz) + len = sz; + if (len && rec[len - 1] == '\n') + len--; + memcpy(buf, rec, len); + *ll = len; + return; + } + } +} + + +int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, + xdemitconf_t const *xecfg) { + long s1, s2, e1, e2, lctx; + xdchange_t *xch, *xche; + char funcbuf[40]; + long funclen = 0; + + for (xch = xche = xscr; xch; xch = xche->next) { + xche = xdl_get_hunk(xch, xecfg); + + s1 = XDL_MAX(xch->i1 - xecfg->ctxlen, 0); + s2 = XDL_MAX(xch->i2 - xecfg->ctxlen, 0); + + lctx = xecfg->ctxlen; + lctx = XDL_MIN(lctx, xe->xdf1.nrec - (xche->i1 + xche->chg1)); + lctx = XDL_MIN(lctx, xe->xdf2.nrec - (xche->i2 + xche->chg2)); + + e1 = xche->i1 + xche->chg1 + lctx; + e2 = xche->i2 + xche->chg2 + lctx; + + /* + * Emit current hunk header. + */ + + if (xecfg->flags & XDL_EMIT_FUNCNAMES) { + xdl_find_func(&xe->xdf1, s1, funcbuf, + sizeof(funcbuf), &funclen); + } + if (xdl_emit_hunk_hdr(s1 + 1, e1 - s1, s2 + 1, e2 - s2, + funcbuf, funclen, ecb) < 0) + return -1; + + /* + * Emit pre-context. + */ + for (; s1 < xch->i1; s1++) + if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + return -1; + + for (s1 = xch->i1, s2 = xch->i2;; xch = xch->next) { + /* + * Merge previous with current change atom. + */ + for (; s1 < xch->i1 && s2 < xch->i2; s1++, s2++) + if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + return -1; + + /* + * Removes lines from the first file. + */ + for (s1 = xch->i1; s1 < xch->i1 + xch->chg1; s1++) + if (xdl_emit_record(&xe->xdf1, s1, "-", ecb) < 0) + return -1; + + /* + * Adds lines from the second file. + */ + for (s2 = xch->i2; s2 < xch->i2 + xch->chg2; s2++) + if (xdl_emit_record(&xe->xdf2, s2, "+", ecb) < 0) + return -1; + + if (xch == xche) + break; + s1 = xch->i1 + xch->chg1; + s2 = xch->i2 + xch->chg2; + } + + /* + * Emit post-context. + */ + for (s1 = xche->i1 + xche->chg1; s1 < e1; s1++) + if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0) + return -1; + } + + return 0; +} + diff --git a/xdiff/xemit.h b/xdiff/xemit.h new file mode 100644 index 0000000..e629417 --- /dev/null +++ b/xdiff/xemit.h @@ -0,0 +1,34 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XEMIT_H) +#define XEMIT_H + + + +int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, + xdemitconf_t const *xecfg); + + + +#endif /* #if !defined(XEMIT_H) */ + diff --git a/xdiff/xinclude.h b/xdiff/xinclude.h new file mode 100644 index 0000000..04a9da8 --- /dev/null +++ b/xdiff/xinclude.h @@ -0,0 +1,43 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XINCLUDE_H) +#define XINCLUDE_H + +#include <ctype.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <limits.h> + +#include "xmacros.h" +#include "xdiff.h" +#include "xtypes.h" +#include "xutils.h" +#include "xprepare.h" +#include "xdiffi.h" +#include "xemit.h" + + +#endif /* #if !defined(XINCLUDE_H) */ + diff --git a/xdiff/xmacros.h b/xdiff/xmacros.h new file mode 100644 index 0000000..4c2fde8 --- /dev/null +++ b/xdiff/xmacros.h @@ -0,0 +1,53 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XMACROS_H) +#define XMACROS_H + + +#define GR_PRIME 0x9e370001UL + + +#define XDL_MIN(a, b) ((a) < (b) ? (a): (b)) +#define XDL_MAX(a, b) ((a) > (b) ? (a): (b)) +#define XDL_ABS(v) ((v) >= 0 ? (v): -(v)) +#define XDL_ISDIGIT(c) ((c) >= '0' && (c) <= '9') +#define XDL_HASHLONG(v, b) (((unsigned long)(v) * GR_PRIME) >> ((CHAR_BIT * sizeof(unsigned long)) - (b))) +#define XDL_PTRFREE(p) do { if (p) { xdl_free(p); (p) = NULL; } } while (0) +#define XDL_LE32_PUT(p, v) \ +do { \ + unsigned char *__p = (unsigned char *) (p); \ + *__p++ = (unsigned char) (v); \ + *__p++ = (unsigned char) ((v) >> 8); \ + *__p++ = (unsigned char) ((v) >> 16); \ + *__p = (unsigned char) ((v) >> 24); \ +} while (0) +#define XDL_LE32_GET(p, v) \ +do { \ + unsigned char const *__p = (unsigned char const *) (p); \ + (v) = (unsigned long) __p[0] | ((unsigned long) __p[1]) << 8 | \ + ((unsigned long) __p[2]) << 16 | ((unsigned long) __p[3]) << 24; \ +} while (0) + + +#endif /* #if !defined(XMACROS_H) */ + diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c new file mode 100644 index 0000000..add5a75 --- /dev/null +++ b/xdiff/xprepare.c @@ -0,0 +1,465 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + + +#define XDL_KPDIS_RUN 4 +#define XDL_MAX_EQLIMIT 1024 + + + +typedef struct s_xdlclass { + struct s_xdlclass *next; + unsigned long ha; + char const *line; + long size; + long idx; +} xdlclass_t; + +typedef struct s_xdlclassifier { + unsigned int hbits; + long hsize; + xdlclass_t **rchash; + chastore_t ncha; + long count; +} xdlclassifier_t; + + + + +static int xdl_init_classifier(xdlclassifier_t *cf, long size); +static void xdl_free_classifier(xdlclassifier_t *cf); +static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, + xrecord_t *rec); +static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, + xdlclassifier_t *cf, xdfile_t *xdf); +static void xdl_free_ctx(xdfile_t *xdf); +static int xdl_clean_mmatch(char const *dis, long i, long s, long e); +static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2); + + + + +static int xdl_init_classifier(xdlclassifier_t *cf, long size) { + long i; + + cf->hbits = xdl_hashbits((unsigned int) size); + cf->hsize = 1 << cf->hbits; + + if (xdl_cha_init(&cf->ncha, sizeof(xdlclass_t), size / 4 + 1) < 0) { + + return -1; + } + if (!(cf->rchash = (xdlclass_t **) xdl_malloc(cf->hsize * sizeof(xdlclass_t *)))) { + + xdl_cha_free(&cf->ncha); + return -1; + } + for (i = 0; i < cf->hsize; i++) + cf->rchash[i] = NULL; + + cf->count = 0; + + return 0; +} + + +static void xdl_free_classifier(xdlclassifier_t *cf) { + + xdl_free(cf->rchash); + xdl_cha_free(&cf->ncha); +} + + +static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, + xrecord_t *rec) { + long hi; + char const *line; + xdlclass_t *rcrec; + + line = rec->ptr; + hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); + for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) + if (rcrec->ha == rec->ha && rcrec->size == rec->size && + !memcmp(line, rcrec->line, rec->size)) + break; + + if (!rcrec) { + if (!(rcrec = xdl_cha_alloc(&cf->ncha))) { + + return -1; + } + rcrec->idx = cf->count++; + rcrec->line = line; + rcrec->size = rec->size; + rcrec->ha = rec->ha; + rcrec->next = cf->rchash[hi]; + cf->rchash[hi] = rcrec; + } + + rec->ha = (unsigned long) rcrec->idx; + + hi = (long) XDL_HASHLONG(rec->ha, hbits); + rec->next = rhash[hi]; + rhash[hi] = rec; + + return 0; +} + + +static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, + xdlclassifier_t *cf, xdfile_t *xdf) { + unsigned int hbits; + long i, nrec, hsize, bsize; + unsigned long hav; + char const *blk, *cur, *top, *prev; + xrecord_t *crec; + xrecord_t **recs, **rrecs; + xrecord_t **rhash; + unsigned long *ha; + char *rchg; + long *rindex; + + if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) { + + return -1; + } + if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *)))) { + + xdl_cha_free(&xdf->rcha); + return -1; + } + + hbits = xdl_hashbits((unsigned int) narec); + hsize = 1 << hbits; + if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *)))) { + + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + for (i = 0; i < hsize; i++) + rhash[i] = NULL; + + nrec = 0; + if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) { + for (top = blk + bsize;;) { + if (cur >= top) { + if (!(cur = blk = xdl_mmfile_next(mf, &bsize))) + break; + top = blk + bsize; + } + prev = cur; + hav = xdl_hash_record(&cur, top); + if (nrec >= narec) { + narec *= 2; + if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *)))) { + + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + recs = rrecs; + } + if (!(crec = xdl_cha_alloc(&xdf->rcha))) { + + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + crec->ptr = prev; + crec->size = (long) (cur - prev); + crec->ha = hav; + recs[nrec++] = crec; + + if (xdl_classify_record(cf, rhash, hbits, crec) < 0) { + + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + } + } + + if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char)))) { + + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + memset(rchg, 0, (nrec + 2) * sizeof(char)); + + if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long)))) { + + xdl_free(rchg); + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long)))) { + + xdl_free(rindex); + xdl_free(rchg); + xdl_free(rhash); + xdl_free(recs); + xdl_cha_free(&xdf->rcha); + return -1; + } + + xdf->nrec = nrec; + xdf->recs = recs; + xdf->hbits = hbits; + xdf->rhash = rhash; + xdf->rchg = rchg + 1; + xdf->rindex = rindex; + xdf->nreff = 0; + xdf->ha = ha; + xdf->dstart = 0; + xdf->dend = nrec - 1; + + return 0; +} + + +static void xdl_free_ctx(xdfile_t *xdf) { + + xdl_free(xdf->rhash); + xdl_free(xdf->rindex); + xdl_free(xdf->rchg - 1); + xdl_free(xdf->ha); + xdl_free(xdf->recs); + xdl_cha_free(&xdf->rcha); +} + + +int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe) { + long enl1, enl2; + xdlclassifier_t cf; + + enl1 = xdl_guess_lines(mf1) + 1; + enl2 = xdl_guess_lines(mf2) + 1; + + if (xdl_init_classifier(&cf, enl1 + enl2 + 1) < 0) { + + return -1; + } + + if (xdl_prepare_ctx(mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { + + xdl_free_classifier(&cf); + return -1; + } + if (xdl_prepare_ctx(mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { + + xdl_free_ctx(&xe->xdf1); + xdl_free_classifier(&cf); + return -1; + } + + xdl_free_classifier(&cf); + + if (xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) { + + xdl_free_ctx(&xe->xdf2); + xdl_free_ctx(&xe->xdf1); + return -1; + } + + return 0; +} + + +void xdl_free_env(xdfenv_t *xe) { + + xdl_free_ctx(&xe->xdf2); + xdl_free_ctx(&xe->xdf1); +} + + +static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { + long r, rdis0, rpdis0, rdis1, rpdis1; + + /* + * Scans the lines before 'i' to find a run of lines that either + * have no match (dis[j] == 0) or have multiple matches (dis[j] > 1). + * Note that we always call this function with dis[i] > 1, so the + * current line (i) is already a multimatch line. + */ + for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) { + if (!dis[i - r]) + rdis0++; + else if (dis[i - r] == 2) + rpdis0++; + else + break; + } + /* + * If the run before the line 'i' found only multimatch lines, we + * return 0 and hence we don't make the current line (i) discarded. + * We want to discard multimatch lines only when they appear in the + * middle of runs with nomatch lines (dis[j] == 0). + */ + if (rdis0 == 0) + return 0; + for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) { + if (!dis[i + r]) + rdis1++; + else if (dis[i + r] == 2) + rpdis1++; + else + break; + } + /* + * If the run after the line 'i' found only multimatch lines, we + * return 0 and hence we don't make the current line (i) discarded. + */ + if (rdis1 == 0) + return 0; + rdis1 += rdis0; + rpdis1 += rpdis0; + + return rpdis1 * XDL_KPDIS_RUN < (rpdis1 + rdis1); +} + + +/* + * Try to reduce the problem complexity, discard records that have no + * matches on the other file. Also, lines that have multiple matches + * might be potentially discarded if they happear in a run of discardable. + */ +static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) { + long i, nm, rhi, nreff, mlim; + unsigned long hav; + xrecord_t **recs; + xrecord_t *rec; + char *dis, *dis1, *dis2; + + if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) { + + return -1; + } + memset(dis, 0, xdf1->nrec + xdf2->nrec + 2); + dis1 = dis; + dis2 = dis1 + xdf1->nrec + 1; + + if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT) + mlim = XDL_MAX_EQLIMIT; + for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { + hav = (*recs)->ha; + rhi = (long) XDL_HASHLONG(hav, xdf2->hbits); + for (nm = 0, rec = xdf2->rhash[rhi]; rec; rec = rec->next) + if (rec->ha == hav && ++nm == mlim) + break; + dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; + } + + if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT) + mlim = XDL_MAX_EQLIMIT; + for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { + hav = (*recs)->ha; + rhi = (long) XDL_HASHLONG(hav, xdf1->hbits); + for (nm = 0, rec = xdf1->rhash[rhi]; rec; rec = rec->next) + if (rec->ha == hav && ++nm == mlim) + break; + dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; + } + + for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; + i <= xdf1->dend; i++, recs++) { + if (dis1[i] == 1 || + (dis1[i] == 2 && !xdl_clean_mmatch(dis1, i, xdf1->dstart, xdf1->dend))) { + xdf1->rindex[nreff] = i; + xdf1->ha[nreff] = (*recs)->ha; + nreff++; + } else + xdf1->rchg[i] = 1; + } + xdf1->nreff = nreff; + + for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; + i <= xdf2->dend; i++, recs++) { + if (dis2[i] == 1 || + (dis2[i] == 2 && !xdl_clean_mmatch(dis2, i, xdf2->dstart, xdf2->dend))) { + xdf2->rindex[nreff] = i; + xdf2->ha[nreff] = (*recs)->ha; + nreff++; + } else + xdf2->rchg[i] = 1; + } + xdf2->nreff = nreff; + + xdl_free(dis); + + return 0; +} + + +/* + * Early trim initial and terminal matching records. + */ +static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { + long i, lim; + xrecord_t **recs1, **recs2; + + recs1 = xdf1->recs; + recs2 = xdf2->recs; + for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim; + i++, recs1++, recs2++) + if ((*recs1)->ha != (*recs2)->ha) + break; + + xdf1->dstart = xdf2->dstart = i; + + recs1 = xdf1->recs + xdf1->nrec - 1; + recs2 = xdf2->recs + xdf2->nrec - 1; + for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--) + if ((*recs1)->ha != (*recs2)->ha) + break; + + xdf1->dend = xdf1->nrec - i - 1; + xdf2->dend = xdf2->nrec - i - 1; + + return 0; +} + + +static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2) { + + if (xdl_trim_ends(xdf1, xdf2) < 0 || + xdl_cleanup_records(xdf1, xdf2) < 0) { + + return -1; + } + + return 0; +} + diff --git a/xdiff/xprepare.h b/xdiff/xprepare.h new file mode 100644 index 0000000..344c569 --- /dev/null +++ b/xdiff/xprepare.h @@ -0,0 +1,35 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XPREPARE_H) +#define XPREPARE_H + + + +int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe); +void xdl_free_env(xdfenv_t *xe); + + + +#endif /* #if !defined(XPREPARE_H) */ + diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h new file mode 100644 index 0000000..3593a66 --- /dev/null +++ b/xdiff/xtypes.h @@ -0,0 +1,68 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XTYPES_H) +#define XTYPES_H + + + +typedef struct s_chanode { + struct s_chanode *next; + long icurr; +} chanode_t; + +typedef struct s_chastore { + chanode_t *head, *tail; + long isize, nsize; + chanode_t *ancur; + chanode_t *sncur; + long scurr; +} chastore_t; + +typedef struct s_xrecord { + struct s_xrecord *next; + char const *ptr; + long size; + unsigned long ha; +} xrecord_t; + +typedef struct s_xdfile { + chastore_t rcha; + long nrec; + unsigned int hbits; + xrecord_t **rhash; + long dstart, dend; + xrecord_t **recs; + char *rchg; + long *rindex; + long nreff; + unsigned long *ha; +} xdfile_t; + +typedef struct s_xdfenv { + xdfile_t xdf1, xdf2; +} xdfenv_t; + + + +#endif /* #if !defined(XTYPES_H) */ + diff --git a/xdiff/xutils.c b/xdiff/xutils.c new file mode 100644 index 0000000..21ab8e7 --- /dev/null +++ b/xdiff/xutils.c @@ -0,0 +1,299 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include "xinclude.h" + + + +#define XDL_GUESS_NLINES 256 + + + + +long xdl_bogosqrt(long n) { + long i; + + /* + * Classical integer square root approximation using shifts. + */ + for (i = 1; n > 0; n >>= 2) + i <<= 1; + + return i; +} + + +int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize, + xdemitcb_t *ecb) { + mmbuffer_t mb[3]; + int i; + + mb[0].ptr = (char *) pre; + mb[0].size = psize; + mb[1].ptr = (char *) rec; + mb[1].size = size; + i = 2; + + if (!size || rec[size-1] != '\n') { + mb[2].ptr = "\n\\ No newline at end of file\n"; + mb[2].size = strlen(mb[2].ptr); + i = 3; + } + + if (ecb->outf(ecb->priv, mb, i) < 0) { + + return -1; + } + + return 0; +} + +void *xdl_mmfile_first(mmfile_t *mmf, long *size) +{ + *size = mmf->size; + return mmf->ptr; +} + + +void *xdl_mmfile_next(mmfile_t *mmf, long *size) +{ + return NULL; +} + + +long xdl_mmfile_size(mmfile_t *mmf) +{ + return mmf->size; +} + + +int xdl_cha_init(chastore_t *cha, long isize, long icount) { + + cha->head = cha->tail = NULL; + cha->isize = isize; + cha->nsize = icount * isize; + cha->ancur = cha->sncur = NULL; + cha->scurr = 0; + + return 0; +} + + +void xdl_cha_free(chastore_t *cha) { + chanode_t *cur, *tmp; + + for (cur = cha->head; (tmp = cur) != NULL;) { + cur = cur->next; + xdl_free(tmp); + } +} + + +void *xdl_cha_alloc(chastore_t *cha) { + chanode_t *ancur; + void *data; + + if (!(ancur = cha->ancur) || ancur->icurr == cha->nsize) { + if (!(ancur = (chanode_t *) xdl_malloc(sizeof(chanode_t) + cha->nsize))) { + + return NULL; + } + ancur->icurr = 0; + ancur->next = NULL; + if (cha->tail) + cha->tail->next = ancur; + if (!cha->head) + cha->head = ancur; + cha->tail = ancur; + cha->ancur = ancur; + } + + data = (char *) ancur + sizeof(chanode_t) + ancur->icurr; + ancur->icurr += cha->isize; + + return data; +} + + +void *xdl_cha_first(chastore_t *cha) { + chanode_t *sncur; + + if (!(cha->sncur = sncur = cha->head)) + return NULL; + + cha->scurr = 0; + + return (char *) sncur + sizeof(chanode_t) + cha->scurr; +} + + +void *xdl_cha_next(chastore_t *cha) { + chanode_t *sncur; + + if (!(sncur = cha->sncur)) + return NULL; + cha->scurr += cha->isize; + if (cha->scurr == sncur->icurr) { + if (!(sncur = cha->sncur = sncur->next)) + return NULL; + cha->scurr = 0; + } + + return (char *) sncur + sizeof(chanode_t) + cha->scurr; +} + + +long xdl_guess_lines(mmfile_t *mf) { + long nl = 0, size, tsize = 0; + char const *data, *cur, *top; + + if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) { + for (top = data + size; nl < XDL_GUESS_NLINES;) { + if (cur >= top) { + tsize += (long) (cur - data); + if (!(cur = data = xdl_mmfile_next(mf, &size))) + break; + top = data + size; + } + nl++; + if (!(cur = memchr(cur, '\n', top - cur))) + cur = top; + else + cur++; + } + tsize += (long) (cur - data); + } + + if (nl && tsize) + nl = xdl_mmfile_size(mf) / (tsize / nl); + + return nl + 1; +} + + +unsigned long xdl_hash_record(char const **data, char const *top) { + unsigned long ha = 5381; + char const *ptr = *data; + + for (; ptr < top && *ptr != '\n'; ptr++) { + ha += (ha << 5); + ha ^= (unsigned long) *ptr; + } + *data = ptr < top ? ptr + 1: ptr; + + return ha; +} + + +unsigned int xdl_hashbits(unsigned int size) { + unsigned int val = 1, bits = 0; + + for (; val < size && bits < CHAR_BIT * sizeof(unsigned int); val <<= 1, bits++); + return bits ? bits: 1; +} + + +int xdl_num_out(char *out, long val) { + char *ptr, *str = out; + char buf[32]; + + ptr = buf + sizeof(buf) - 1; + *ptr = '\0'; + if (val < 0) { + *--ptr = '-'; + val = -val; + } + for (; val && ptr > buf; val /= 10) + *--ptr = "0123456789"[val % 10]; + if (*ptr) + for (; *ptr; ptr++, str++) + *str = *ptr; + else + *str++ = '0'; + *str = '\0'; + + return str - out; +} + + +long xdl_atol(char const *str, char const **next) { + long val, base; + char const *top; + + for (top = str; XDL_ISDIGIT(*top); top++); + if (next) + *next = top; + for (val = 0, base = 1, top--; top >= str; top--, base *= 10) + val += base * (long)(*top - '0'); + return val; +} + + +int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, + const char *func, long funclen, xdemitcb_t *ecb) { + int nb = 0; + mmbuffer_t mb; + char buf[128]; + + memcpy(buf, "@@ -", 4); + nb += 4; + + nb += xdl_num_out(buf + nb, c1 ? s1: s1 - 1); + + if (c1 != 1) { + memcpy(buf + nb, ",", 1); + nb += 1; + + nb += xdl_num_out(buf + nb, c1); + } + + memcpy(buf + nb, " +", 2); + nb += 2; + + nb += xdl_num_out(buf + nb, c2 ? s2: s2 - 1); + + if (c2 != 1) { + memcpy(buf + nb, ",", 1); + nb += 1; + + nb += xdl_num_out(buf + nb, c2); + } + + memcpy(buf + nb, " @@", 3); + nb += 3; + if (func && funclen) { + buf[nb++] = ' '; + if (funclen > sizeof(buf) - nb - 1) + funclen = sizeof(buf) - nb - 1; + memcpy(buf + nb, func, funclen); + nb += funclen; + } + buf[nb++] = '\n'; + + mb.ptr = buf; + mb.size = nb; + if (ecb->outf(ecb->priv, &mb, 1) < 0) + return -1; + + return 0; +} + diff --git a/xdiff/xutils.h b/xdiff/xutils.h new file mode 100644 index 0000000..ea38ee9 --- /dev/null +++ b/xdiff/xutils.h @@ -0,0 +1,46 @@ +/* + * LibXDiff by Davide Libenzi ( File Differential Library ) + * Copyright (C) 2003 Davide Libenzi + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#if !defined(XUTILS_H) +#define XUTILS_H + + +long xdl_bogosqrt(long n); +int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize, + xdemitcb_t *ecb); +int xdl_cha_init(chastore_t *cha, long isize, long icount); +void xdl_cha_free(chastore_t *cha); +void *xdl_cha_alloc(chastore_t *cha); +void *xdl_cha_first(chastore_t *cha); +void *xdl_cha_next(chastore_t *cha); +long xdl_guess_lines(mmfile_t *mf); +unsigned long xdl_hash_record(char const **data, char const *top); +unsigned int xdl_hashbits(unsigned int size); +int xdl_num_out(char *out, long val); +long xdl_atol(char const *str, char const **next); +int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2, + const char *func, long funclen, xdemitcb_t *ecb); + + + +#endif /* #if !defined(XUTILS_H) */ + |