diff options
143 files changed, 5356 insertions, 3199 deletions
diff --git a/.tsan-suppressions b/.tsan-suppressions new file mode 100644 index 000000000..8c85014a0 --- /dev/null +++ b/.tsan-suppressions @@ -0,0 +1,10 @@ +# Suppressions for ThreadSanitizer (tsan). +# +# This file is used by setting the environment variable TSAN_OPTIONS to, e.g., +# "suppressions=$(pwd)/.tsan-suppressions". Observe that relative paths such as +# ".tsan-suppressions" might not work. + +# A static variable is written to racily, but we always write the same value, so +# in practice it (hopefully!) doesn't matter. +race:^want_color$ +race:^transfer_debug$ diff --git a/Documentation/RelNotes/2.15.0.txt b/Documentation/RelNotes/2.15.0.txt index ad429931e..4b3fd229e 100644 --- a/Documentation/RelNotes/2.15.0.txt +++ b/Documentation/RelNotes/2.15.0.txt @@ -18,6 +18,9 @@ Backward compatibility notes and other notable changes. might still be cases that need to be addressed--bug reports are greatly appreciated. + * "branch --set-upstream" that has been deprecated in Git 1.8 has + finally been retired. + Updates since v2.14 ------------------- @@ -48,6 +51,32 @@ UI, Workflows & Features * "git merge" learned a "--signoff" option to add the Signed-off-by: trailer with the committer's name. + * "git diff" learned to optionally paint new lines that are the same + as deleted lines elsewhere differently from genuinely new lines. + + * "git interpret-trailers" learned to take the trailer specifications + from the command line that overrides the configured values. + + * "git interpret-trailers" has been taught a "--parse" and a few + other options to make it easier for scripts to grab existing + trailer lines from a commit log message. + + * "gitweb" shows a link to visit the 'raw' contents of blbos in the + history overview page. + + * "[gc] rerereResolved = 5.days" used to be invalid, as the variable + is defined to take an integer counting the number of days. It now + is allowed. + + * The code to acquire a lock on a reference (e.g. while accepting a + push from a client) used to immediately fail when the reference is + already locked---now it waits for a very short while and retries, + which can make it succeed if the lock holder was holding it during + a read-only operation. + + * "branch --set-upstream" that has been deprecated in Git 1.8 has + finally been retired. + Performance, Internal Implementation, Development Support etc. @@ -97,6 +126,13 @@ Performance, Internal Implementation, Development Support etc. been simplified. (merge 8aade107dd jc/simplify-progress later to maint). + * Code clean-up to avoid mixing values read from the .gitmodules file + and values read from the .git/config file. + + * We used to spend more than necessary cycles allocating and freeing + piece of memory while writing each index entry out. This has been + optimized. + Also contains various documentation updates and code clean-ups. @@ -196,13 +232,32 @@ Fixes since v2.14 the offending subprocess was running. This has been corrected. (merge d3ba566342 cc/subprocess-handshake-missing-capabilities later to maint). + * "git apply" that is used as a better "patch -p1" failed to apply a + taken from a file with CRLF line endings to a file with CRLF line + endings. The root cause was because it misused convert_to_git() + that tried to do "safe-crlf" processing by looking at the index + entry at the same path, which is a nonsense---in that mode, "apply" + is not working on the data in (or derived from) the index at all. + This has been fixed. + (merge c24f3abace tb/apply-with-crlf later to maint). + + * Killing "git merge --edit" before the editor returns control left + the repository in a state with MERGE_MSG but without MERGE_HEAD, + which incorrectly tells the subsequent "git commit" that there was + a squash merge in progress. This has been fixed. + (merge 9d89b35526 mg/killed-merge later to maint). + + * "git archive" did not work well with pathspecs and the + export-ignore attribute. + (merge 5ff247ac0c rs/archive-excluded-directory later to maint). + * Other minor doc, test and build updates and code cleanups. (merge dff2813391 ab/ref-filter-no-contains later to maint). (merge f094b89a4d ma/parse-maybe-bool later to maint). (merge 974ce8078c mf/no-dashed-subcommands later to maint). (merge f81935cc4d jc/perl-git-comment-typofix later to maint). (merge 57ea241ef0 rs/t3700-clean-leftover later to maint). - (merge f1068efefe jk/drop-sha1-entry-pos later to maint). + (merge 39b00fa4d4 jk/drop-sha1-entry-pos later to maint). (merge 0b006014c8 jk/hashcmp-memcmp later to maint). (merge 1e22a9917b rj/add-chmod-error-message later to maint). (merge 881529c846 rs/apply-lose-prefix-length later to maint). @@ -216,3 +271,6 @@ Fixes since v2.14 (merge 794b7e1674 mg/format-ref-doc-fix later to maint). (merge 24da8a26a9 rs/commit-h-single-parent-cleanup later to maint). (merge 4e36907fa3 jk/doc-the-this later to maint). + (merge 15d1d0951e bc/vcs-svn-cleanup later to maint). + (merge b8f43b120b jn/vcs-svn-cleanup later to maint). + (merge 4a4becfb23 jt/doc-pack-objects-fix later to maint). diff --git a/Documentation/config.txt b/Documentation/config.txt index 2271809d9..dc4e3f58a 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -776,6 +776,12 @@ core.commentChar:: If set to "auto", `git-commit` would select a character that is not the beginning character of any line in existing commit messages. +core.filesRefLockTimeout:: + The length of time, in milliseconds, to retry when trying to + lock an individual reference. Value 0 means not to retry at + all; -1 means to try indefinitely. Default is 100 (i.e., + retry for 100ms). + core.packedRefsTimeout:: The length of time, in milliseconds, to retry when trying to lock the `packed-refs` file. Value 0 means not to retry at @@ -1077,14 +1083,25 @@ This does not affect linkgit:git-format-patch[1] or the 'git-diff-{asterisk}' plumbing commands. Can be overridden on the command line with the `--color[=<when>]` option. +diff.colorMoved:: + If set to either a valid `<mode>` or a true value, moved lines + in a diff are colored differently, for details of valid modes + see '--color-moved' in linkgit:git-diff[1]. If simply set to + true the default color mode will be used. When set to false, + moved lines are not colored. + color.diff.<slot>:: Use customized color for diff colorization. `<slot>` specifies which part of the patch to use the specified color, and is one of `context` (context text - `plain` is a historical synonym), `meta` (metainformation), `frag` (hunk header), 'func' (function in hunk header), `old` (removed lines), - `new` (added lines), `commit` (commit headers), or `whitespace` - (highlighting whitespace errors). + `new` (added lines), `commit` (commit headers), `whitespace` + (highlighting whitespace errors), `oldMoved` (deleted lines), + `newMoved` (added lines), `oldMovedDimmed`, `oldMovedAlternative`, + `oldMovedAlternativeDimmed`, `newMovedDimmed`, `newMovedAlternative` + and `newMovedAlternativeDimmed` (See the '<mode>' + setting of '--color-moved' in linkgit:git-diff[1] for details). color.decorate.<slot>:: Use customized color for 'git log --decorate' output. `<slot>` is one @@ -1553,11 +1570,13 @@ gc.<pattern>.reflogExpireUnreachable:: gc.rerereResolved:: Records of conflicted merge you resolved earlier are kept for this many days when 'git rerere gc' is run. + You can also use more human-readable "1.month.ago", etc. The default is 60 days. See linkgit:git-rerere[1]. gc.rerereUnresolved:: Records of conflicted merge you have not resolved are kept for this many days when 'git rerere gc' is run. + You can also use more human-readable "1.month.ago", etc. The default is 15 days. See linkgit:git-rerere[1]. gitcvs.commitMsgAnnotation:: diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt index 56dedafcd..a88c76741 100644 --- a/Documentation/diff-options.txt +++ b/Documentation/diff-options.txt @@ -231,6 +231,40 @@ ifdef::git-diff[] endif::git-diff[] It is the same as `--color=never`. +--color-moved[=<mode>]:: + Moved lines of code are colored differently. +ifdef::git-diff[] + It can be changed by the `diff.colorMoved` configuration setting. +endif::git-diff[] + The <mode> defaults to 'no' if the option is not given + and to 'zebra' if the option with no mode is given. + The mode must be one of: ++ +-- +no:: + Moved lines are not highlighted. +default:: + Is a synonym for `zebra`. This may change to a more sensible mode + in the future. +plain:: + Any line that is added in one location and was removed + in another location will be colored with 'color.diff.newMoved'. + Similarly 'color.diff.oldMoved' will be used for removed lines + that are added somewhere else in the diff. This mode picks up any + moved line, but it is not very useful in a review to determine + if a block of code was moved without permutation. +zebra:: + Blocks of moved text of at least 20 alphanumeric characters + are detected greedily. The detected blocks are + painted using either the 'color.diff.{old,new}Moved' color or + 'color.diff.{old,new}MovedAlternative'. The change between + the two colors indicates that a new block was detected. +dimmed_zebra:: + Similar to 'zebra', but additional dimming of uninteresting parts + of moved code is performed. The bordering lines of two adjacent + blocks are considered interesting, the rest is uninteresting. +-- + --word-diff[=<mode>]:: Show a word diff, using the <mode> to delimit changed words. By default, words are delimited by whitespace; see diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt index 631cbd840..4ebc3d327 100644 --- a/Documentation/git-apply.txt +++ b/Documentation/git-apply.txt @@ -66,7 +66,7 @@ OPTIONS disables it is in effect), make sure the patch is applicable to what the current index file records. If the file to be patched in the working tree is not - up-to-date, it is flagged as an error. This flag also + up to date, it is flagged as an error. This flag also causes the index file to be updated. --cached:: @@ -259,7 +259,7 @@ treats these changes as follows. If `--index` is specified (explicitly or implicitly), then the submodule commits must match the index exactly for the patch to apply. If any of the submodules are checked-out, then these check-outs are completely -ignored, i.e., they are not required to be up-to-date or clean and they +ignored, i.e., they are not required to be up to date or clean and they are not updated. If `--index` is not specified, then the submodule commits in the patch diff --git a/Documentation/git-branch.txt b/Documentation/git-branch.txt index d0b335877..e292737b9 100644 --- a/Documentation/git-branch.txt +++ b/Documentation/git-branch.txt @@ -195,10 +195,8 @@ start-point is either a local or remote-tracking branch. branch.autoSetupMerge configuration variable is true. --set-upstream:: - If specified branch does not exist yet or if `--force` has been - given, acts exactly like `--track`. Otherwise sets up configuration - like `--track` would when creating the branch, except that where - branch points to is not changed. + As this option had confusing syntax, it is no longer supported. + Please use `--track` or `--set-upstream-to` instead. -u <upstream>:: --set-upstream-to=<upstream>:: diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt index a336ae5f6..ba90066f1 100644 --- a/Documentation/git-cvsserver.txt +++ b/Documentation/git-cvsserver.txt @@ -223,7 +223,7 @@ access method and requested operation. That means that even if you offer only read access (e.g. by using the pserver method), 'git-cvsserver' should have write access to the database to work reliably (otherwise you need to make sure -that the database is up-to-date any time 'git-cvsserver' is executed). +that the database is up to date any time 'git-cvsserver' is executed). By default it uses SQLite databases in the Git directory, named `gitcvs.<module_name>.sqlite`. Note that the SQLite backend creates diff --git a/Documentation/git-diff-index.txt b/Documentation/git-diff-index.txt index a17150695..b38067771 100644 --- a/Documentation/git-diff-index.txt +++ b/Documentation/git-diff-index.txt @@ -85,7 +85,7 @@ a 'git write-tree' + 'git diff-tree'. Thus that's the default mode. The non-cached version asks the question: show me the differences between HEAD and the currently checked out - tree - index contents _and_ files that aren't up-to-date + tree - index contents _and_ files that aren't up to date which is obviously a very useful question too, since that tells you what you *could* commit. Again, the output matches the 'git diff-tree -r' @@ -100,8 +100,8 @@ have not actually done a 'git update-index' on it yet - there is no torvalds@ppc970:~/v2.6/linux> git diff-index --abbrev HEAD :100644 100664 7476bb... 000000... kernel/sched.c -i.e., it shows that the tree has changed, and that `kernel/sched.c` has is -not up-to-date and may contain new stuff. The all-zero sha1 means that to +i.e., it shows that the tree has changed, and that `kernel/sched.c` is +not up to date and may contain new stuff. The all-zero sha1 means that to get the real diff, you need to look at the object in the working directory directly rather than do an object-to-object diff. diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt index 31cdeaecd..9dd19a1dd 100644 --- a/Documentation/git-interpret-trailers.txt +++ b/Documentation/git-interpret-trailers.txt @@ -3,24 +3,27 @@ git-interpret-trailers(1) NAME ---- -git-interpret-trailers - help add structured information into commit messages +git-interpret-trailers - add or parse structured information in commit messages SYNOPSIS -------- [verse] -'git interpret-trailers' [--in-place] [--trim-empty] [(--trailer <token>[(=|:)<value>])...] [<file>...] +'git interpret-trailers' [options] [(--trailer <token>[(=|:)<value>])...] [<file>...] +'git interpret-trailers' [options] [--parse] [<file>...] DESCRIPTION ----------- -Help adding 'trailers' lines, that look similar to RFC 822 e-mail +Help parsing or adding 'trailers' lines, that look similar to RFC 822 e-mail headers, at the end of the otherwise free-form part of a commit message. This command reads some patches or commit messages from either the -<file> arguments or the standard input if no <file> is specified. Then -this command applies the arguments passed using the `--trailer` -option, if any, to the commit message part of each input file. The -result is emitted on the standard output. +<file> arguments or the standard input if no <file> is specified. If +`--parse` is specified, the output consists of the parsed trailers. + +Otherwise, this command applies the arguments passed using the +`--trailer` option, if any, to the commit message part of each input +file. The result is emitted on the standard output. Some configuration variables control the way the `--trailer` arguments are applied to each commit message and the way any existing trailer in @@ -80,6 +83,45 @@ OPTIONS trailer to the input messages. See the description of this command. +--where <placement>:: +--no-where:: + Specify where all new trailers will be added. A setting + provided with '--where' overrides all configuration variables + and applies to all '--trailer' options until the next occurrence of + '--where' or '--no-where'. + +--if-exists <action>:: +--no-if-exists:: + Specify what action will be performed when there is already at + least one trailer with the same <token> in the message. A setting + provided with '--if-exists' overrides all configuration variables + and applies to all '--trailer' options until the next occurrence of + '--if-exists' or '--no-if-exists'. + +--if-missing <action>:: +--no-if-missing:: + Specify what action will be performed when there is no other + trailer with the same <token> in the message. A setting + provided with '--if-missing' overrides all configuration variables + and applies to all '--trailer' options until the next occurrence of + '--if-missing' or '--no-if-missing'. + +--only-trailers:: + Output only the trailers, not any other parts of the input. + +--only-input:: + Output only trailers that exist in the input; do not add any + from the command-line or by following configured `trailer.*` + rules. + +--unfold:: + Remove any whitespace-continuation in trailers, so that each + trailer appears on a line by itself with its full content. + +--parse:: + A convenience alias for `--only-trailers --only-input + --unfold`. + CONFIGURATION VARIABLES ----------------------- @@ -170,8 +212,8 @@ trailer.<token>.where:: configuration variable and it overrides what is specified by that option for trailers with the specified <token>. -trailer.<token>.ifexist:: - This option takes the same values as the 'trailer.ifexist' +trailer.<token>.ifexists:: + This option takes the same values as the 'trailer.ifexists' configuration variable and it overrides what is specified by that option for trailers with the specified <token>. diff --git a/Documentation/git-merge.txt b/Documentation/git-merge.txt index 6b308ab6d..4df6431c3 100644 --- a/Documentation/git-merge.txt +++ b/Documentation/git-merge.txt @@ -141,7 +141,7 @@ exception is when the changed index entries are in the state that would result from the merge already.) If all named commits are already ancestors of `HEAD`, 'git merge' -will exit early with the message "Already up-to-date." +will exit early with the message "Already up to date." FAST-FORWARD MERGE ------------------ @@ -288,7 +288,10 @@ After seeing a conflict, you can do two things: * Resolve the conflicts. Git will mark the conflicts in the working tree. Edit the files into shape and - 'git add' them to the index. Use 'git commit' to seal the deal. + 'git add' them to the index. Use 'git commit' or + 'git merge --continue' to seal the deal. The latter command + checks whether there is a (interrupted) merge in progress + before calling 'git commit'. You can work through the conflict with a number of tools: diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 8973510a4..473a16135 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -18,8 +18,9 @@ SYNOPSIS DESCRIPTION ----------- -Reads list of objects from the standard input, and writes a packed -archive with specified base-name, or to the standard output. +Reads list of objects from the standard input, and writes either one or +more packed archives with the specified base-name to disk, or a packed +archive to the standard output. A packed archive is an efficient way to transfer a set of objects between two repositories as well as an access efficient archival @@ -47,9 +48,9 @@ transport by their peers. OPTIONS ------- base-name:: - Write into a pair of files (.pack and .idx), using + Write into pairs of files (.pack and .idx), using <base-name> to determine the name of the created file. - When this option is used, the two files are written in + When this option is used, the two files in a pair are written in <base-name>-<SHA-1>.{pack,idx} files. <SHA-1> is a hash based on the pack content and is written to the standard output of the command. @@ -108,9 +109,13 @@ base-name:: is taken from the `pack.windowMemory` configuration variable. --max-pack-size=<n>:: - Maximum size of each output pack file. The size can be suffixed with + In unusual scenarios, you may not be able to create files + larger than a certain size on your filesystem, and this option + can be used to tell the command to split the output packfile + into multiple independent packfiles, each not larger than the + given size. The size can be suffixed with "k", "m", or "g". The minimum size allowed is limited to 1 MiB. - If specified, multiple packfiles may be created, which also + This option prevents the creation of a bitmap index. The default is unlimited, unless the config variable `pack.packSizeLimit` is set. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 4f6bed61a..6805a74ae 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -334,7 +334,7 @@ which makes little sense. -f:: --force-rebase:: - Force a rebase even if the current branch is up-to-date and + Force a rebase even if the current branch is up to date and the command without `--force` would return without doing anything. + You may find this (or --no-ff with an interactive rebase) helpful after diff --git a/Documentation/git-rerere.txt b/Documentation/git-rerere.txt index 9ee083c41..031f31fa4 100644 --- a/Documentation/git-rerere.txt +++ b/Documentation/git-rerere.txt @@ -205,7 +205,7 @@ development on the topic branch: ------------ you could run `git rebase master topic`, to bring yourself -up-to-date before your topic is ready to be sent upstream. +up to date before your topic is ready to be sent upstream. This would result in falling back to a three-way merge, and it would conflict the same way as the test merge you resolved earlier. 'git rerere' will be run by 'git rebase' to help you resolve this diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt index 683e59133..b5c46223c 100644 --- a/Documentation/git-rm.txt +++ b/Documentation/git-rm.txt @@ -146,7 +146,7 @@ the submodule's history. If it exists the submodule.<name> section in the linkgit:gitmodules[5] file will also be removed and that file will be staged (unless --cached or -n are used). -A submodule is considered up-to-date when the HEAD is the same as +A submodule is considered up to date when the HEAD is the same as recorded in the index, no tracked files are modified and no untracked files that aren't ignored are present in the submodules work tree. Ignored files are deemed expendable and won't stop a submodule's work diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt index aa2aeabb6..636e09048 100644 --- a/Documentation/git-svn.txt +++ b/Documentation/git-svn.txt @@ -424,7 +424,7 @@ Any other arguments are passed directly to 'git log' 'set-tree':: You should consider using 'dcommit' instead of this command. Commit specified commit or tree objects to SVN. This relies on - your imported fetch data being up-to-date. This makes + 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 diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt index 1579abf3c..e19eba62c 100644 --- a/Documentation/git-update-index.txt +++ b/Documentation/git-update-index.txt @@ -214,7 +214,7 @@ will remove the intended effect of the option. Using --refresh --------------- `--refresh` does not calculate a new sha1 file or bring the index -up-to-date for mode/content changes. But what it *does* do is to +up to date for mode/content changes. But what it *does* do is to "re-match" the stat information of a file with the index, so that you can refresh the index for a file that hasn't been changed but where the stat entry is out of date. diff --git a/Documentation/gitcore-tutorial.txt b/Documentation/gitcore-tutorial.txt index 7577f27ec..e29a9effc 100644 --- a/Documentation/gitcore-tutorial.txt +++ b/Documentation/gitcore-tutorial.txt @@ -631,7 +631,7 @@ So after you do a `cp -a` to create a new copy, you'll want to do $ git update-index --refresh ---------------- + -in the new repository to make sure that the index file is up-to-date. +in the new repository to make sure that the index file is up to date. Note that the second point is true even across machines. You can duplicate a remote Git repository with *any* regular copy mechanism, be it @@ -701,7 +701,7 @@ $ git checkout-index -u -a ---------------- where the `-u` flag means that you want the checkout to keep the index -up-to-date (so that you don't have to refresh it afterward), and the +up to date (so that you don't have to refresh it afterward), and the `-a` flag means "check out all files" (if you have a stale copy or an older version of a checked out tree you may also need to add the `-f` flag first, to tell 'git checkout-index' to *force* overwriting of any old @@ -1283,7 +1283,7 @@ run a single command, 'git-receive-pack'. First, you need to create an empty repository on the remote machine that will house your public repository. This empty -repository will be populated and be kept up-to-date by pushing +repository will be populated and be kept up to date by pushing into it later. Obviously, this repository creation needs to be done only once. @@ -1450,7 +1450,7 @@ transport protocols (HTTP), you need to keep this repository would contain a call to 'git update-server-info' but you need to manually enable the hook with `mv post-update.sample post-update`. This makes sure -'git update-server-info' keeps the necessary files up-to-date. +'git update-server-info' keeps the necessary files up to date. 3. Push into the public repository from your primary repository. diff --git a/Documentation/githooks.txt b/Documentation/githooks.txt index 623ed1a13..1bb4f92d4 100644 --- a/Documentation/githooks.txt +++ b/Documentation/githooks.txt @@ -369,7 +369,7 @@ them. When enabled, the default 'post-update' hook runs 'git update-server-info' to keep the information used by dumb -transports (e.g., HTTP) up-to-date. If you are publishing +transports (e.g., HTTP) up to date. If you are publishing a Git repository that is accessible via HTTP, you should probably enable this hook. diff --git a/Documentation/gitrepository-layout.txt b/Documentation/gitrepository-layout.txt index f51ed4e37..adf9554ad 100644 --- a/Documentation/gitrepository-layout.txt +++ b/Documentation/gitrepository-layout.txt @@ -71,7 +71,7 @@ objects/info/packs:: This file is to help dumb transports discover what packs are available in this object store. Whenever a pack is added or removed, `git update-server-info` should be run - to keep this file up-to-date if the repository is + to keep this file up to date if the repository is published for dumb transports. 'git repack' does this by default. diff --git a/Documentation/gittutorial.txt b/Documentation/gittutorial.txt index 794b83393..242de31cb 100644 --- a/Documentation/gittutorial.txt +++ b/Documentation/gittutorial.txt @@ -109,7 +109,7 @@ summary of the situation with 'git status': $ git status On branch master Changes to be committed: -Your branch is up-to-date with 'origin/master'. +Your branch is up to date with 'origin/master'. (use "git reset HEAD <file>..." to unstage) modified: file1 diff --git a/Documentation/merge-options.txt b/Documentation/merge-options.txt index 5b4a62e93..4e3230430 100644 --- a/Documentation/merge-options.txt +++ b/Documentation/merge-options.txt @@ -39,7 +39,7 @@ set to `no` at the beginning of them. --ff-only:: Refuse to merge and exit with a non-zero status unless the - current `HEAD` is already up-to-date or the merge can be + current `HEAD` is already up to date or the merge can be resolved as a fast-forward. --log[=<n>]:: diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt index 973d19606..d433d50f8 100644 --- a/Documentation/pretty-formats.txt +++ b/Documentation/pretty-formats.txt @@ -205,7 +205,10 @@ endif::git-rev-list[] - '%><(<N>)', '%><|(<N>)': similar to '% <(<N>)', '%<|(<N>)' respectively, but padding both sides (i.e. the text is centered) - %(trailers): display the trailers of the body as interpreted by - linkgit:git-interpret-trailers[1] + linkgit:git-interpret-trailers[1]. If the `:only` option is given, + omit non-trailer lines from the trailer block. If the `:unfold` + option is given, behave as if interpret-trailer's `--unfold` option + was given. E.g., `%(trailers:only:unfold)` to do both. NOTE: Some placeholders may depend on other options given to the revision traversal engine. For example, the `%g*` reflog options will diff --git a/Documentation/technical/pack-protocol.txt b/Documentation/technical/pack-protocol.txt index a34917153..ed1eae8b8 100644 --- a/Documentation/technical/pack-protocol.txt +++ b/Documentation/technical/pack-protocol.txt @@ -199,7 +199,7 @@ After reference and capabilities discovery, the client can decide to terminate the connection by sending a flush-pkt, telling the server it can now gracefully terminate, and disconnect, when it does not need any pack data. This can happen with the ls-remote command, and also can happen when -the client already is up-to-date. +the client already is up to date. Otherwise, it enters the negotiation phase, where the client and server determine what the minimal packfile necessary for transport is, diff --git a/Documentation/technical/trivial-merge.txt b/Documentation/technical/trivial-merge.txt index c79d4a7c4..1f1c33d0d 100644 --- a/Documentation/technical/trivial-merge.txt +++ b/Documentation/technical/trivial-merge.txt @@ -32,7 +32,7 @@ or the result. If multiple cases apply, the one used is listed first. A result which changes the index is an error if the index is not empty -and not up-to-date. +and not up to date. Entries marked '+' have stat information. Spaces marked '*' don't affect the result. @@ -65,7 +65,7 @@ empty, no entry is left for that stage). Otherwise, the given entry is left in stage 0, and there are no other entries. A result of "no merge" is an error if the index is not empty and not -up-to-date. +up to date. *empty* means that the tree must not have a directory-file conflict with the entry. diff --git a/Documentation/user-manual.txt b/Documentation/user-manual.txt index bc2929867..b4d88af13 100644 --- a/Documentation/user-manual.txt +++ b/Documentation/user-manual.txt @@ -2044,10 +2044,12 @@ If a push would not result in a <<fast-forwards,fast-forward>> of the remote branch, then it will fail with an error like: ------------------------------------------------- -error: remote 'refs/heads/master' is not an ancestor of - local 'refs/heads/master'. - Maybe you are not up-to-date and need to pull first? -error: failed to push to 'ssh://yourserver.com/~you/proj.git' + ! [rejected] master -> master (non-fast-forward) +error: failed to push some refs to '...' +hint: Updates were rejected because the tip of your current branch is behind +hint: its remote counterpart. Integrate the remote changes (e.g. +hint: 'git pull ...') before pushing again. +hint: See the 'Note about fast-forwards' in 'git push --help' for details. ------------------------------------------------- This can happen, for example, if you: @@ -2193,7 +2195,7 @@ $ cd work Linus's tree will be stored in the remote-tracking branch named origin/master, and can be updated using linkgit:git-fetch[1]; you can track other public trees using linkgit:git-remote[1] to set up a "remote" and -linkgit:git-fetch[1] to keep them up-to-date; see +linkgit:git-fetch[1] to keep them up to date; see <<repositories-and-branches>>. Now create the branches in which you are going to work; these start out @@ -655,6 +655,7 @@ TEST_PROGRAMS_NEED_X += test-parse-options TEST_PROGRAMS_NEED_X += test-path-utils TEST_PROGRAMS_NEED_X += test-prio-queue TEST_PROGRAMS_NEED_X += test-read-cache +TEST_PROGRAMS_NEED_X += test-write-cache TEST_PROGRAMS_NEED_X += test-ref-store TEST_PROGRAMS_NEED_X += test-regex TEST_PROGRAMS_NEED_X += test-revision-walking @@ -816,6 +817,7 @@ LIB_OBJS += notes-merge.o LIB_OBJS += notes-utils.o LIB_OBJS += object.o LIB_OBJS += oidset.o +LIB_OBJS += packfile.o LIB_OBJS += pack-bitmap.o LIB_OBJS += pack-bitmap-write.o LIB_OBJS += pack-check.o @@ -2038,7 +2040,6 @@ XDIFF_OBJS += xdiff/xhistogram.o VCSSVN_OBJS += vcs-svn/line_buffer.o VCSSVN_OBJS += vcs-svn/sliding_window.o -VCSSVN_OBJS += vcs-svn/repo_tree.o VCSSVN_OBJS += vcs-svn/fast_export.o VCSSVN_OBJS += vcs-svn/svndiff.o VCSSVN_OBJS += vcs-svn/svndump.o @@ -219,6 +219,7 @@ struct patch { unsigned int recount:1; unsigned int conflicted_threeway:1; unsigned int direct_to_threeway:1; + unsigned int crlf_in_old:1; struct fragment *fragments; char *result; size_t resultsize; @@ -1662,6 +1663,19 @@ static void check_whitespace(struct apply_state *state, } /* + * Check if the patch has context lines with CRLF or + * the patch wants to remove lines with CRLF. + */ +static void check_old_for_crlf(struct patch *patch, const char *line, int len) +{ + if (len >= 2 && line[len-1] == '\n' && line[len-2] == '\r') { + patch->ws_rule |= WS_CR_AT_EOL; + patch->crlf_in_old = 1; + } +} + + +/* * Parse a unified diff. Note that this really needs to parse each * fragment separately, since the only way to know the difference * between a "---" that is part of a patch, and a "---" that starts @@ -1711,11 +1725,14 @@ static int parse_fragment(struct apply_state *state, if (!deleted && !added) leading++; trailing++; + check_old_for_crlf(patch, line, len); if (!state->apply_in_reverse && state->ws_error_action == correct_ws_error) check_whitespace(state, line, len, patch->ws_rule); break; case '-': + if (!state->apply_in_reverse) + check_old_for_crlf(patch, line, len); if (state->apply_in_reverse && state->ws_error_action != nowarn_ws_error) check_whitespace(state, line, len, patch->ws_rule); @@ -1724,6 +1741,8 @@ static int parse_fragment(struct apply_state *state, trailing = 0; break; case '+': + if (state->apply_in_reverse) + check_old_for_crlf(patch, line, len); if (!state->apply_in_reverse && state->ws_error_action != nowarn_ws_error) check_whitespace(state, line, len, patch->ws_rule); @@ -2266,8 +2285,11 @@ static void show_stats(struct apply_state *state, struct patch *patch) add, pluses, del, minuses); } -static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) +static int read_old_data(struct stat *st, struct patch *patch, + const char *path, struct strbuf *buf) { + enum safe_crlf safe_crlf = patch->crlf_in_old ? + SAFE_CRLF_KEEP_CRLF : SAFE_CRLF_RENORMALIZE; switch (st->st_mode & S_IFMT) { case S_IFLNK: if (strbuf_readlink(buf, path, st->st_size) < 0) @@ -2276,7 +2298,15 @@ static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) case S_IFREG: if (strbuf_read_file(buf, path, st->st_size) != st->st_size) return error(_("unable to open or read %s"), path); - convert_to_git(&the_index, path, buf->buf, buf->len, buf, 0); + /* + * "git apply" without "--index/--cached" should never look + * at the index; the target file may not have been added to + * the index yet, and we may not even be in any Git repository. + * Pass NULL to convert_to_git() to stress this; the function + * should never look at the index when explicit crlf option + * is given. + */ + convert_to_git(NULL, path, buf->buf, buf->len, buf, safe_crlf); return 0; default: return -1; @@ -3379,6 +3409,7 @@ static int load_patch_target(struct apply_state *state, struct strbuf *buf, const struct cache_entry *ce, struct stat *st, + struct patch *patch, const char *name, unsigned expected_mode) { @@ -3394,7 +3425,7 @@ static int load_patch_target(struct apply_state *state, } else if (has_symlink_leading_path(name, strlen(name))) { return error(_("reading from '%s' beyond a symbolic link"), name); } else { - if (read_old_data(st, name, buf)) + if (read_old_data(st, patch, name, buf)) return error(_("failed to read %s"), name); } } @@ -3427,7 +3458,7 @@ static int load_preimage(struct apply_state *state, /* We have a patched copy in memory; use that. */ strbuf_add(&buf, previous->result, previous->resultsize); } else { - status = load_patch_target(state, &buf, ce, st, + status = load_patch_target(state, &buf, ce, st, patch, patch->old_name, patch->old_mode); if (status < 0) return status; @@ -3515,7 +3546,7 @@ static int load_current(struct apply_state *state, if (verify_index_match(ce, &st)) return error(_("%s: does not match index"), name); - status = load_patch_target(state, &buf, ce, &st, name, mode); + status = load_patch_target(state, &buf, ce, &st, patch, name, mode); if (status < 0) return status; else if (status) @@ -103,17 +103,39 @@ struct archiver_context { struct directory *bottom; }; +static const struct attr_check *get_archive_attrs(const char *path) +{ + static struct attr_check *check; + if (!check) + check = attr_check_initl("export-ignore", "export-subst", NULL); + return git_check_attr(path, check) ? NULL : check; +} + +static int check_attr_export_ignore(const struct attr_check *check) +{ + return check && ATTR_TRUE(check->items[0].value); +} + +static int check_attr_export_subst(const struct attr_check *check) +{ + return check && ATTR_TRUE(check->items[1].value); +} + +static int should_queue_directories(const struct archiver_args *args) +{ + return args->pathspec.has_wildcard; +} + static int write_archive_entry(const unsigned char *sha1, const char *base, int baselen, const char *filename, unsigned mode, int stage, void *context) { static struct strbuf path = STRBUF_INIT; - static struct attr_check *check; struct archiver_context *c = context; struct archiver_args *args = c->args; write_archive_entry_fn_t write_entry = c->write_entry; - const char *path_without_prefix; int err; + const char *path_without_prefix; args->convert = 0; strbuf_reset(&path); @@ -125,12 +147,12 @@ static int write_archive_entry(const unsigned char *sha1, const char *base, strbuf_addch(&path, '/'); path_without_prefix = path.buf + args->baselen; - if (!check) - check = attr_check_initl("export-ignore", "export-subst", NULL); - if (!git_check_attr(path_without_prefix, check)) { - if (ATTR_TRUE(check->items[0].value)) + if (!S_ISDIR(mode) || !should_queue_directories(args)) { + const struct attr_check *check; + check = get_archive_attrs(path_without_prefix); + if (check_attr_export_ignore(check)) return 0; - args->convert = ATTR_TRUE(check->items[1].value); + args->convert = check_attr_export_subst(check); } if (S_ISDIR(mode) || S_ISGITLINK(mode)) { @@ -204,6 +226,17 @@ static int queue_or_write_archive_entry(const unsigned char *sha1, } if (S_ISDIR(mode)) { + size_t baselen = base->len; + const struct attr_check *check; + + /* Borrow base, but restore its original value when done. */ + strbuf_addstr(base, filename); + strbuf_addch(base, '/'); + check = get_archive_attrs(base->buf); + strbuf_setlen(base, baselen); + + if (check_attr_export_ignore(check)) + return 0; queue_directory(sha1, base, filename, mode, stage, c); return READ_TREE_RECURSIVE; @@ -257,7 +290,7 @@ int write_archive_entries(struct archiver_args *args, } err = read_tree_recursive(args->tree, "", 0, 0, &args->pathspec, - args->pathspec.has_wildcard ? + should_queue_directories(args) ? queue_or_write_archive_entry : write_archive_entry_buf, &context); @@ -90,24 +90,24 @@ int install_branch_config(int flag, const char *local, const char *origin, const if (shortname) { if (origin) printf_ln(rebasing ? - _("Branch %s set up to track remote branch %s from %s by rebasing.") : - _("Branch %s set up to track remote branch %s from %s."), + _("Branch '%s' set up to track remote branch '%s' from '%s' by rebasing.") : + _("Branch '%s' set up to track remote branch '%s' from '%s'."), local, shortname, origin); else printf_ln(rebasing ? - _("Branch %s set up to track local branch %s by rebasing.") : - _("Branch %s set up to track local branch %s."), + _("Branch '%s' set up to track local branch '%s' by rebasing.") : + _("Branch '%s' set up to track local branch '%s'."), local, shortname); } else { if (origin) printf_ln(rebasing ? - _("Branch %s set up to track remote ref %s by rebasing.") : - _("Branch %s set up to track remote ref %s."), + _("Branch '%s' set up to track remote ref '%s' by rebasing.") : + _("Branch '%s' set up to track remote ref '%s'."), local, remote); else printf_ln(rebasing ? - _("Branch %s set up to track local ref %s by rebasing.") : - _("Branch %s set up to track local ref %s."), + _("Branch '%s' set up to track local ref '%s' by rebasing.") : + _("Branch '%s' set up to track local ref '%s'."), local, remote); } } diff --git a/builtin/add.c b/builtin/add.c index 5d5773d5c..c20548e4f 100644 --- a/builtin/add.c +++ b/builtin/add.c @@ -116,6 +116,7 @@ int add_files_to_cache(const char *prefix, rev.diffopt.output_format = DIFF_FORMAT_CALLBACK; rev.diffopt.format_callback = update_callback; rev.diffopt.format_callback_data = &data; + rev.diffopt.flags |= DIFF_OPT_OVERRIDE_SUBMODULE_CONFIG; rev.max_count = 0; /* do not compare unmerged paths with stage #2 */ run_diff_files(&rev, DIFF_RACY_IS_MODIFIED); return !!data.add_errors; diff --git a/builtin/am.c b/builtin/am.c index 81095dae0..c369dd1dc 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -31,6 +31,7 @@ #include "mailinfo.h" #include "apply.h" #include "string-list.h" +#include "packfile.h" /** * Returns 1 if the file is empty or does not exist, 0 otherwise. diff --git a/builtin/blame.c b/builtin/blame.c index e0daf1754..67adaef4d 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -488,7 +488,7 @@ static int read_ancestry(const char *graft_file) return -1; while (!strbuf_getwholeline(&buf, fp, '\n')) { /* The format is just "Commit Parent1 Parent2 ...\n" */ - struct commit_graft *graft = read_graft_line(buf.buf, buf.len); + struct commit_graft *graft = read_graft_line(&buf); if (graft) register_commit_graft(graft, 0); } diff --git a/builtin/branch.c b/builtin/branch.c index 16d391b40..355f9ef5d 100644 --- a/builtin/branch.c +++ b/builtin/branch.c @@ -561,8 +561,8 @@ int cmd_branch(int argc, const char **argv, const char *prefix) OPT__QUIET(&quiet, N_("suppress informational messages")), OPT_SET_INT('t', "track", &track, N_("set up tracking mode (see git-pull(1))"), BRANCH_TRACK_EXPLICIT), - OPT_SET_INT( 0, "set-upstream", &track, N_("change upstream info"), - BRANCH_TRACK_OVERRIDE), + { OPTION_SET_INT, 0, "set-upstream", &track, NULL, N_("do not use"), + PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, NULL, BRANCH_TRACK_OVERRIDE }, OPT_STRING('u', "set-upstream-to", &new_upstream, N_("upstream"), N_("change the upstream info")), OPT_BOOL(0, "unset-upstream", &unset_upstream, N_("Unset the upstream info")), OPT__COLOR(&branch_use_color, N_("use colored output")), @@ -759,8 +759,6 @@ int cmd_branch(int argc, const char **argv, const char *prefix) strbuf_release(&buf); } else if (argc > 0 && argc <= 2) { struct branch *branch = branch_get(argv[0]); - int branch_existed = 0, remote_tracking = 0; - struct strbuf buf = STRBUF_INIT; if (!strcmp(argv[0], "HEAD")) die(_("it does not make sense to create 'HEAD' manually")); @@ -772,28 +770,11 @@ int cmd_branch(int argc, const char **argv, const char *prefix) die(_("-a and -r options to 'git branch' do not make sense with a branch name")); if (track == BRANCH_TRACK_OVERRIDE) - fprintf(stderr, _("The --set-upstream flag is deprecated and will be removed. Consider using --track or --set-upstream-to\n")); - - strbuf_addf(&buf, "refs/remotes/%s", branch->name); - remote_tracking = ref_exists(buf.buf); - strbuf_release(&buf); + die(_("the '--set-upstream' option is no longer supported. Please use '--track' or '--set-upstream-to' instead.")); - branch_existed = ref_exists(branch->refname); create_branch(argv[0], (argc == 2) ? argv[1] : head, force, reflog, 0, quiet, track); - /* - * We only show the instructions if the user gave us - * one branch which doesn't exist locally, but is the - * name of a remote-tracking branch. - */ - if (argc == 1 && track == BRANCH_TRACK_OVERRIDE && - !branch_existed && remote_tracking) { - fprintf(stderr, _("\nIf you wanted to make '%s' track '%s', do this:\n\n"), head, branch->name); - fprintf(stderr, " git branch -d %s\n", branch->name); - fprintf(stderr, " git branch --set-upstream-to %s\n", branch->name); - } - } else usage_with_options(builtin_branch_usage, options); diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 62c8cf0eb..4ccbfaac3 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -12,6 +12,7 @@ #include "streaming.h" #include "tree-walk.h" #include "sha1-array.h" +#include "packfile.h" struct batch_options { int enabled; diff --git a/builtin/checkout.c b/builtin/checkout.c index 2d75ac66c..5c202b7af 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -861,7 +861,7 @@ static int git_checkout_config(const char *var, const char *value, void *cb) } if (starts_with(var, "submodule.")) - return submodule_config(var, value, NULL); + return git_default_submodule_config(var, value, NULL); return git_xmerge_config(var, value, NULL); } @@ -1182,7 +1182,6 @@ int cmd_checkout(int argc, const char **argv, const char *prefix) opts.prefix = prefix; opts.show_progress = -1; - gitmodules_config(); git_config(git_checkout_config, &opts); opts.track = BRANCH_TRACK_UNSPECIFIED; diff --git a/builtin/clone.c b/builtin/clone.c index f7e17d229..8d11b570a 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -25,6 +25,7 @@ #include "remote.h" #include "run-command.h" #include "connected.h" +#include "packfile.h" /* * Overall FIXMEs: diff --git a/builtin/commit.c b/builtin/commit.c index b79bcfd5b..b3b04f5dd 100644 --- a/builtin/commit.c +++ b/builtin/commit.c @@ -195,7 +195,6 @@ static void determine_whence(struct wt_status *s) static void status_init_config(struct wt_status *s, config_fn_t fn) { wt_status_prepare(s); - gitmodules_config(); git_config(fn, s); determine_whence(s); init_diff_ui_defaults(); diff --git a/builtin/count-objects.c b/builtin/count-objects.c index 1d82e61f2..33343818c 100644 --- a/builtin/count-objects.c +++ b/builtin/count-objects.c @@ -10,6 +10,7 @@ #include "builtin.h" #include "parse-options.h" #include "quote.h" +#include "packfile.h" static unsigned long garbage; static off_t size_garbage; diff --git a/builtin/diff-files.c b/builtin/diff-files.c index 17bf84d18..e88493ffe 100644 --- a/builtin/diff-files.c +++ b/builtin/diff-files.c @@ -26,7 +26,6 @@ int cmd_diff_files(int argc, const char **argv, const char *prefix) git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(&rev, prefix); - gitmodules_config(); rev.abbrev = 0; precompose_argv(argc, argv); diff --git a/builtin/diff-index.c b/builtin/diff-index.c index 185e6f9b5..9d772f8f2 100644 --- a/builtin/diff-index.c +++ b/builtin/diff-index.c @@ -23,7 +23,6 @@ int cmd_diff_index(int argc, const char **argv, const char *prefix) git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(&rev, prefix); - gitmodules_config(); rev.abbrev = 0; precompose_argv(argc, argv); diff --git a/builtin/diff-tree.c b/builtin/diff-tree.c index 31d2cb410..d66499909 100644 --- a/builtin/diff-tree.c +++ b/builtin/diff-tree.c @@ -110,7 +110,6 @@ int cmd_diff_tree(int argc, const char **argv, const char *prefix) git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(opt, prefix); - gitmodules_config(); opt->abbrev = 0; opt->diff = 1; opt->disable_stdin = 1; diff --git a/builtin/diff.c b/builtin/diff.c index 7cde6abbc..7e3ebcea3 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -315,8 +315,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix) no_index = DIFF_NO_INDEX_IMPLICIT; } - if (!no_index) - gitmodules_config(); init_diff_ui_defaults(); git_config(git_diff_ui_config, NULL); precompose_argv(argc, argv); diff --git a/builtin/difftool.c b/builtin/difftool.c index 8864d846f..b2d3ba753 100644 --- a/builtin/difftool.c +++ b/builtin/difftool.c @@ -111,7 +111,7 @@ static int use_wt_file(const char *workdir, const char *name, int fd = open(buf.buf, O_RDONLY); if (fd >= 0 && - !index_fd(wt_oid.hash, fd, &st, OBJ_BLOB, name, 0)) { + !index_fd(&wt_oid, fd, &st, OBJ_BLOB, name, 0)) { if (is_null_oid(oid)) { oidcpy(oid, &wt_oid); use = 1; diff --git a/builtin/fetch.c b/builtin/fetch.c index d84c26391..225c73492 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -17,6 +17,7 @@ #include "connected.h" #include "argv-array.h" #include "utf8.h" +#include "packfile.h" static const char * const builtin_fetch_usage[] = { N_("git fetch [<options>] [<repository> [<refspec>...]]"), @@ -1360,11 +1361,6 @@ int cmd_fetch(int argc, const char **argv, const char *prefix) if (depth || deepen_since || deepen_not.nr) deepen = 1; - if (recurse_submodules != RECURSE_SUBMODULES_OFF) { - gitmodules_config(); - git_config(submodule_config, NULL); - } - if (all) { if (argc == 1) die(_("fetch --all does not take a repository argument")); diff --git a/builtin/fsck.c b/builtin/fsck.c index 0ab13848a..1e4c471b4 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -15,6 +15,7 @@ #include "progress.h" #include "streaming.h" #include "decorate.h" +#include "packfile.h" #define REACHABLE 0x0001 #define SEEN 0x0002 diff --git a/builtin/gc.c b/builtin/gc.c index e6b84475a..3c78fcb9b 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -19,6 +19,7 @@ #include "sigchain.h" #include "argv-array.h" #include "commit.h" +#include "packfile.h" #define FAILED_RUN "failed to run %s" diff --git a/builtin/grep.c b/builtin/grep.c index a70d8e2fb..19e23946a 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -1048,10 +1048,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix) } #endif - if (recurse_submodules) { - gitmodules_config(); - } - if (show_in_pager && (cached || list.nr)) die(_("--open-files-in-pager only works on the worktree")); diff --git a/builtin/hash-object.c b/builtin/hash-object.c index d04baf999..c532ff932 100644 --- a/builtin/hash-object.c +++ b/builtin/hash-object.c @@ -16,7 +16,7 @@ * needs to bypass the data conversion performed by, and the type * limitation imposed by, index_fd() and its callees. */ -static int hash_literally(unsigned char *sha1, int fd, const char *type, unsigned flags) +static int hash_literally(struct object_id *oid, int fd, const char *type, unsigned flags) { struct strbuf buf = STRBUF_INIT; int ret; @@ -24,7 +24,7 @@ static int hash_literally(unsigned char *sha1, int fd, const char *type, unsigne if (strbuf_read(&buf, fd, 4096) < 0) ret = -1; else - ret = hash_sha1_file_literally(buf.buf, buf.len, type, sha1, flags); + ret = hash_sha1_file_literally(buf.buf, buf.len, type, oid, flags); strbuf_release(&buf); return ret; } @@ -33,16 +33,16 @@ static void hash_fd(int fd, const char *type, const char *path, unsigned flags, int literally) { struct stat st; - unsigned char sha1[20]; + struct object_id oid; if (fstat(fd, &st) < 0 || (literally - ? hash_literally(sha1, fd, type, flags) - : index_fd(sha1, fd, &st, type_from_string(type), path, flags))) + ? hash_literally(&oid, fd, type, flags) + : index_fd(&oid, fd, &st, type_from_string(type), path, flags))) die((flags & HASH_WRITE_OBJECT) ? "Unable to add %s to database" : "Unable to hash %s", path); - printf("%s\n", sha1_to_hex(sha1)); + printf("%s\n", oid_to_hex(&oid)); maybe_flush_or_die(stdout, "hash to stdout"); } diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 26828c1d8..f2be145e1 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -12,6 +12,7 @@ #include "exec_cmd.h" #include "streaming.h" #include "thread-utils.h" +#include "packfile.h" static const char index_pack_usage[] = "git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])"; diff --git a/builtin/interpret-trailers.c b/builtin/interpret-trailers.c index 175f14797..b742539d4 100644 --- a/builtin/interpret-trailers.c +++ b/builtin/interpret-trailers.c @@ -16,34 +16,119 @@ static const char * const git_interpret_trailers_usage[] = { NULL }; +static enum trailer_where where; +static enum trailer_if_exists if_exists; +static enum trailer_if_missing if_missing; + +static int option_parse_where(const struct option *opt, + const char *arg, int unset) +{ + return trailer_set_where(&where, arg); +} + +static int option_parse_if_exists(const struct option *opt, + const char *arg, int unset) +{ + return trailer_set_if_exists(&if_exists, arg); +} + +static int option_parse_if_missing(const struct option *opt, + const char *arg, int unset) +{ + return trailer_set_if_missing(&if_missing, arg); +} + +static void new_trailers_clear(struct list_head *trailers) +{ + struct list_head *pos, *tmp; + struct new_trailer_item *item; + + list_for_each_safe(pos, tmp, trailers) { + item = list_entry(pos, struct new_trailer_item, list); + list_del(pos); + free(item); + } +} + +static int option_parse_trailer(const struct option *opt, + const char *arg, int unset) +{ + struct list_head *trailers = opt->value; + struct new_trailer_item *item; + + if (unset) { + new_trailers_clear(trailers); + return 0; + } + + if (!arg) + return -1; + + item = xmalloc(sizeof(*item)); + item->text = arg; + item->where = where; + item->if_exists = if_exists; + item->if_missing = if_missing; + list_add_tail(&item->list, trailers); + return 0; +} + +static int parse_opt_parse(const struct option *opt, const char *arg, + int unset) +{ + struct process_trailer_options *v = opt->value; + v->only_trailers = 1; + v->only_input = 1; + v->unfold = 1; + return 0; +} + int cmd_interpret_trailers(int argc, const char **argv, const char *prefix) { - int in_place = 0; - int trim_empty = 0; - struct string_list trailers = STRING_LIST_INIT_NODUP; + struct process_trailer_options opts = PROCESS_TRAILER_OPTIONS_INIT; + LIST_HEAD(trailers); struct option options[] = { - OPT_BOOL(0, "in-place", &in_place, N_("edit files in place")), - OPT_BOOL(0, "trim-empty", &trim_empty, N_("trim empty trailers")), - OPT_STRING_LIST(0, "trailer", &trailers, N_("trailer"), - N_("trailer(s) to add")), + OPT_BOOL(0, "in-place", &opts.in_place, N_("edit files in place")), + OPT_BOOL(0, "trim-empty", &opts.trim_empty, N_("trim empty trailers")), + + OPT_CALLBACK(0, "where", NULL, N_("action"), + N_("where to place the new trailer"), option_parse_where), + OPT_CALLBACK(0, "if-exists", NULL, N_("action"), + N_("action if trailer already exists"), option_parse_if_exists), + OPT_CALLBACK(0, "if-missing", NULL, N_("action"), + N_("action if trailer is missing"), option_parse_if_missing), + + OPT_BOOL(0, "only-trailers", &opts.only_trailers, N_("output only the trailers")), + OPT_BOOL(0, "only-input", &opts.only_input, N_("do not apply config rules")), + OPT_BOOL(0, "unfold", &opts.unfold, N_("join whitespace-continued values")), + { OPTION_CALLBACK, 0, "parse", &opts, NULL, N_("set parsing options"), + PARSE_OPT_NOARG | PARSE_OPT_NONEG, parse_opt_parse }, + OPT_CALLBACK(0, "trailer", &trailers, N_("trailer"), + N_("trailer(s) to add"), option_parse_trailer), OPT_END() }; argc = parse_options(argc, argv, prefix, options, git_interpret_trailers_usage, 0); + if (opts.only_input && !list_empty(&trailers)) + usage_msg_opt( + _("--trailer with --only-input does not make sense"), + git_interpret_trailers_usage, + options); + if (argc) { int i; for (i = 0; i < argc; i++) - process_trailers(argv[i], in_place, trim_empty, &trailers); + process_trailers(argv[i], &opts, &trailers); } else { - if (in_place) + if (opts.in_place) die(_("no input file given for in-place editing")); - process_trailers(NULL, in_place, trim_empty, &trailers); + process_trailers(NULL, &opts, &trailers); } - string_list_clear(&trailers, 0); + new_trailers_clear(&trailers); return 0; } diff --git a/builtin/ls-files.c b/builtin/ls-files.c index c6126eae5..e1339e6d1 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -19,6 +19,7 @@ #include "pathspec.h" #include "run-command.h" #include "submodule.h" +#include "submodule-config.h" static int abbrev; static int show_deleted; @@ -210,8 +211,6 @@ static void show_submodule(struct repository *superproject, if (repo_read_index(&submodule) < 0) die("index file corrupt"); - repo_read_gitmodules(&submodule); - show_files(&submodule, dir); repo_clear(&submodule); @@ -609,9 +608,6 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix) if (require_work_tree && !is_inside_work_tree()) setup_work_tree(); - if (recurse_submodules) - repo_read_gitmodules(the_repository); - if (recurse_submodules && (show_stage || show_deleted || show_others || show_unmerged || show_killed || show_modified || show_resolve_undo || with_tree)) diff --git a/builtin/merge.c b/builtin/merge.c index cc5705299..3672e3897 100644 --- a/builtin/merge.c +++ b/builtin/merge.c @@ -32,6 +32,7 @@ #include "gpg-interface.h" #include "sequencer.h" #include "string-list.h" +#include "packfile.h" #define DEFAULT_TWOHEAD (1<<0) #define DEFAULT_OCTOPUS (1<<1) @@ -758,15 +759,19 @@ N_("Please enter a commit message to explain why this merge is necessary,\n" "Lines starting with '%c' will be ignored, and an empty message aborts\n" "the commit.\n"); +static void write_merge_heads(struct commit_list *); static void prepare_to_commit(struct commit_list *remoteheads) { struct strbuf msg = STRBUF_INIT; strbuf_addbuf(&msg, &merge_msg); strbuf_addch(&msg, '\n'); + if (squash) + BUG("the control must not reach here under --squash"); if (0 < option_edit) strbuf_commented_addf(&msg, _(merge_editor_comment), comment_line_char); if (signoff) append_signoff(&msg, ignore_non_trailer(msg.buf, msg.len), 0); + write_merge_heads(remoteheads); write_file_buf(git_path_merge_msg(), msg.buf, msg.len); if (run_commit_hook(0 < option_edit, get_index_file(), "prepare-commit-msg", git_path_merge_msg(), "merge", NULL)) @@ -908,7 +913,7 @@ static int setup_with_upstream(const char ***argv) return i; } -static void write_merge_state(struct commit_list *remoteheads) +static void write_merge_heads(struct commit_list *remoteheads) { struct commit_list *j; struct strbuf buf = STRBUF_INIT; @@ -924,8 +929,6 @@ static void write_merge_state(struct commit_list *remoteheads) strbuf_addf(&buf, "%s\n", oid_to_hex(oid)); } write_file_buf(git_path_merge_head(), buf.buf, buf.len); - strbuf_addch(&merge_msg, '\n'); - write_file_buf(git_path_merge_msg(), merge_msg.buf, merge_msg.len); strbuf_reset(&buf); if (fast_forward == FF_NO) @@ -933,6 +936,13 @@ static void write_merge_state(struct commit_list *remoteheads) write_file_buf(git_path_merge_mode(), buf.buf, buf.len); } +static void write_merge_state(struct commit_list *remoteheads) +{ + write_merge_heads(remoteheads); + strbuf_addch(&merge_msg, '\n'); + write_file_buf(git_path_merge_msg(), merge_msg.buf, merge_msg.len); +} + static int default_edit_option(void) { static const char name[] = "GIT_MERGE_AUTOEDIT"; @@ -1349,7 +1359,7 @@ int cmd_merge(int argc, const char **argv, const char *prefix) * If head can reach all the merge then we are up to date. * but first the most common case of merging one remote. */ - finish_up_to_date(_("Already up-to-date.")); + finish_up_to_date(_("Already up to date.")); goto done; } else if (fast_forward != FF_NO && !remoteheads->next && !common->next && @@ -1432,7 +1442,7 @@ int cmd_merge(int argc, const char **argv, const char *prefix) } } if (up_to_date) { - finish_up_to_date(_("Already up-to-date. Yeeah!")); + finish_up_to_date(_("Already up to date. Yeeah!")); goto done; } } diff --git a/builtin/mv.c b/builtin/mv.c index 94fbaaa5d..ffdd5f01a 100644 --- a/builtin/mv.c +++ b/builtin/mv.c @@ -131,7 +131,6 @@ int cmd_mv(int argc, const char **argv, const char *prefix) struct stat st; struct string_list src_for_dst = STRING_LIST_INIT_NODUP; - gitmodules_config(); git_config(git_default_config, NULL); argc = parse_options(argc, argv, prefix, builtin_mv_options, diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index c753e9237..a57b4f058 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -25,6 +25,7 @@ #include "sha1-array.h" #include "argv-array.h" #include "mru.h" +#include "packfile.h" static const char *pack_usage[] = { N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), @@ -2170,7 +2171,10 @@ static void *threaded_find_deltas(void *arg) { struct thread_params *me = arg; + progress_lock(); while (me->remaining) { + progress_unlock(); + find_deltas(me->list, &me->remaining, me->window, me->depth, me->processed); @@ -2192,7 +2196,10 @@ static void *threaded_find_deltas(void *arg) pthread_cond_wait(&me->cond, &me->mutex); me->data_ready = 0; pthread_mutex_unlock(&me->mutex); + + progress_lock(); } + progress_unlock(); /* leave ->working 1 so that this doesn't get more work assigned */ return NULL; } diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index cb1df1c76..aaa813632 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -7,6 +7,7 @@ */ #include "builtin.h" +#include "packfile.h" #define BLKSIZE 512 diff --git a/builtin/prune-packed.c b/builtin/prune-packed.c index 8f41f7c20..419238171 100644 --- a/builtin/prune-packed.c +++ b/builtin/prune-packed.c @@ -2,6 +2,7 @@ #include "cache.h" #include "progress.h" #include "parse-options.h" +#include "packfile.h" static const char * const prune_packed_usage[] = { N_("git prune-packed [-n | --dry-run] [-q | --quiet]"), diff --git a/builtin/read-tree.c b/builtin/read-tree.c index d5f618d08..bf87a2710 100644 --- a/builtin/read-tree.c +++ b/builtin/read-tree.c @@ -164,8 +164,6 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix) argc = parse_options(argc, argv, unused_prefix, read_tree_options, read_tree_usage, 0); - load_submodule_cache(); - hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR); prefix_set = opts.prefix ? 1 : 0; diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 14b6e09b4..52c63ebfd 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -23,6 +23,7 @@ #include "fsck.h" #include "tmp-objdir.h" #include "oidset.h" +#include "packfile.h" static const char * const receive_pack_usage[] = { N_("git receive-pack <git-dir>"), diff --git a/builtin/replace.c b/builtin/replace.c index f4a85a165..3e71a7715 100644 --- a/builtin/replace.c +++ b/builtin/replace.c @@ -269,7 +269,7 @@ static void import_object(struct object_id *oid, enum object_type type, if (fstat(fd, &st) < 0) die_errno("unable to fstat %s", filename); - if (index_fd(oid->hash, fd, &st, type, NULL, flags) < 0) + if (index_fd(oid, fd, &st, type, NULL, flags) < 0) die("unable to write object to database"); /* index_fd close()s fd for us */ } diff --git a/builtin/reset.c b/builtin/reset.c index 4a02d7407..d72c7d1c9 100644 --- a/builtin/reset.c +++ b/builtin/reset.c @@ -156,6 +156,7 @@ static int read_from_tree(const struct pathspec *pathspec, opt.output_format = DIFF_FORMAT_CALLBACK; opt.format_callback = update_index_from_diff; opt.format_callback_data = &intent_to_add; + opt.flags |= DIFF_OPT_OVERRIDE_SUBMODULE_CONFIG; if (do_diff_cache(tree_oid, &opt)) return 1; @@ -308,8 +309,6 @@ int cmd_reset(int argc, const char **argv, const char *prefix) PARSE_OPT_KEEP_DASHDASH); parse_args(&pathspec, argv, prefix, patch_mode, &rev); - load_submodule_cache(); - unborn = !strcmp(rev, "HEAD") && get_oid("HEAD", &oid); if (unborn) { /* reset on unborn branch: treat as reset to empty tree */ diff --git a/builtin/rm.c b/builtin/rm.c index 4057e73fa..d91451fea 100644 --- a/builtin/rm.c +++ b/builtin/rm.c @@ -255,7 +255,6 @@ int cmd_rm(int argc, const char **argv, const char *prefix) struct pathspec pathspec; char *seen; - gitmodules_config(); git_config(git_default_config, NULL); argc = parse_options(argc, argv, prefix, builtin_rm_options, diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c index 0ff9dd0b8..818fe74f0 100644 --- a/builtin/submodule--helper.c +++ b/builtin/submodule--helper.c @@ -275,8 +275,6 @@ static void module_list_active(struct module_list *list) int i; struct module_list active_modules = MODULE_LIST_INIT; - gitmodules_config(); - for (i = 0; i < list->nr; i++) { const struct cache_entry *ce = list->entries[i]; @@ -337,9 +335,6 @@ static void init_submodule(const char *path, const char *prefix, int quiet) struct strbuf sb = STRBUF_INIT; char *upd = NULL, *url = NULL, *displaypath; - /* Only loads from .gitmodules, no overlay with .git/config */ - gitmodules_config(); - if (prefix && get_super_prefix()) die("BUG: cannot have prefix and superprefix"); else if (prefix) @@ -475,7 +470,6 @@ static int module_name(int argc, const char **argv, const char *prefix) if (argc != 2) usage(_("git submodule--helper name <path>")); - gitmodules_config(); sub = submodule_from_path(&null_oid, argv[1]); if (!sub) @@ -780,6 +774,10 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce, struct strbuf *out) { const struct submodule *sub = NULL; + const char *url = NULL; + const char *update_string; + enum submodule_update_type update_type; + char *key; struct strbuf displaypath_sb = STRBUF_INIT; struct strbuf sb = STRBUF_INIT; const char *displaypath = NULL; @@ -808,9 +806,17 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce, goto cleanup; } + key = xstrfmt("submodule.%s.update", sub->name); + if (!repo_config_get_string_const(the_repository, key, &update_string)) { + update_type = parse_submodule_update_type(update_string); + } else { + update_type = sub->update_strategy.type; + } + free(key); + if (suc->update.type == SM_UPDATE_NONE || (suc->update.type == SM_UPDATE_UNSPECIFIED - && sub->update_strategy.type == SM_UPDATE_NONE)) { + && update_type == SM_UPDATE_NONE)) { strbuf_addf(out, _("Skipping submodule '%s'"), displaypath); strbuf_addch(out, '\n'); goto cleanup; @@ -823,6 +829,11 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce, } strbuf_reset(&sb); + strbuf_addf(&sb, "submodule.%s.url", sub->name); + if (repo_config_get_string_const(the_repository, sb.buf, &url)) + url = sub->url; + + strbuf_reset(&sb); strbuf_addf(&sb, "%s/.git", ce->name); needs_cloning = !file_exists(sb.buf); @@ -851,7 +862,7 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce, argv_array_push(&child->args, "--depth=1"); argv_array_pushl(&child->args, "--path", sub->path, NULL); argv_array_pushl(&child->args, "--name", sub->name, NULL); - argv_array_pushl(&child->args, "--url", sub->url, NULL); + argv_array_pushl(&child->args, "--url", url, NULL); if (suc->references.nr) { struct string_list_item *item; for_each_string_list_item(item, &suc->references) @@ -1025,10 +1036,6 @@ static int update_clone(int argc, const char **argv, const char *prefix) if (pathspec.nr) suc.warn_if_uninitialized = 1; - /* Overlay the parsed .gitmodules file with .git/config */ - gitmodules_config(); - git_config(submodule_config, NULL); - run_processes_parallel(max_jobs, update_clone_get_next_task, update_clone_start_failure, @@ -1066,17 +1073,22 @@ static int resolve_relative_path(int argc, const char **argv, const char *prefix static const char *remote_submodule_branch(const char *path) { const struct submodule *sub; - gitmodules_config(); - git_config(submodule_config, NULL); + const char *branch = NULL; + char *key; sub = submodule_from_path(&null_oid, path); if (!sub) return NULL; - if (!sub->branch) + key = xstrfmt("submodule.%s.branch", sub->name); + if (repo_config_get_string_const(the_repository, key, &branch)) + branch = sub->branch; + free(key); + + if (!branch) return "master"; - if (!strcmp(sub->branch, ".")) { + if (!strcmp(branch, ".")) { unsigned char sha1[20]; const char *refname = resolve_ref_unsafe("HEAD", 0, sha1, NULL); @@ -1094,7 +1106,7 @@ static const char *remote_submodule_branch(const char *path) return refname; } - return sub->branch; + return branch; } static int resolve_remote_submodule_branch(int argc, const char **argv, @@ -1213,9 +1225,6 @@ static int absorb_git_dirs(int argc, const char **argv, const char *prefix) argc = parse_options(argc, argv, prefix, embed_gitdir_options, git_submodule_helper_usage, 0); - gitmodules_config(); - git_config(submodule_config, NULL); - if (module_list_compute(argc, argv, prefix, &pathspec, &list) < 0) return 1; @@ -1231,8 +1240,6 @@ static int is_active(int argc, const char **argv, const char *prefix) if (argc != 2) die("submodule--helper is-active takes exactly 1 argument"); - gitmodules_config(); - return !is_submodule_active(the_repository, argv[1]); } diff --git a/builtin/update-index.c b/builtin/update-index.c index 56721cf03..d562f2ec6 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -280,7 +280,7 @@ static int add_one_path(const struct cache_entry *old, const char *path, int len fill_stat_cache_info(ce, st); ce->ce_mode = ce_mode_from_stat(old, st->st_mode); - if (index_path(ce->oid.hash, path, st, + if (index_path(&ce->oid, path, st, info_only ? 0 : HASH_WRITE_OBJECT)) { free(ce); return -1; diff --git a/bulk-checkin.c b/bulk-checkin.c index 5be7ce5c7..9a1f6c49a 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -6,6 +6,7 @@ #include "csum-file.h" #include "pack.h" #include "strbuf.h" +#include "packfile.h" static struct bulk_checkin_state { unsigned plugged:1; @@ -684,8 +684,8 @@ extern int ie_modified(const struct index_state *, const struct cache_entry *, s #define HASH_WRITE_OBJECT 1 #define HASH_FORMAT_CHECK 2 -extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags); -extern int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags); +extern int index_fd(struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags); +extern int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags); /* * Record to sd the data from st that we use to check whether a file @@ -903,20 +903,6 @@ extern void check_repository_format(void); extern const char *sha1_file_name(const unsigned char *sha1); /* - * Return the name of the (local) packfile with the specified sha1 in - * its name. The return value is a pointer to memory that is - * overwritten each time this function is called. - */ -extern char *sha1_pack_name(const unsigned char *sha1); - -/* - * Return the name of the (local) pack index file with the specified - * sha1 in its name. The return value is a pointer to memory that is - * overwritten each time this function is called. - */ -extern char *sha1_pack_index_name(const unsigned char *sha1); - -/* * Return an abbreviated sha1 unique within this repository's object database. * The result will be at least `len` characters long, and will be NUL * terminated. @@ -1192,7 +1178,7 @@ static inline const unsigned char *lookup_replace_object(const unsigned char *sh extern int sha1_object_info(const unsigned char *, unsigned long *); extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1); extern int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *return_sha1); -extern int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, unsigned char *sha1, unsigned flags); +extern int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, struct object_id *oid, unsigned flags); extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *); extern int force_object_loose(const unsigned char *sha1, time_t mtime); extern int git_open_cloexec(const char *name, int flags); @@ -1201,15 +1187,10 @@ extern void *map_sha1_file(const unsigned char *sha1, unsigned long *size); extern int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz); extern int parse_sha1_header(const char *hdr, unsigned long *sizep); -/* global flag to enable extra checks when accessing packed objects */ -extern int do_check_packed_object_crc; - extern int check_sha1_signature(const unsigned char *sha1, void *buf, unsigned long size, const char *type); extern int finalize_object_file(const char *tmpfile, const char *filename); -extern int has_sha1_pack(const unsigned char *sha1); - /* * Open the loose object at path, check its sha1, and return the contents, * type, and size. If the object is a blob, then "contents" may return NULL, @@ -1245,8 +1226,6 @@ extern int has_object_file_with_flags(const struct object_id *oid, int flags); */ extern int has_loose_object_nonlocal(const unsigned char *sha1); -extern int has_pack_index(const unsigned char *sha1); - extern void assert_sha1_type(const unsigned char *sha1, enum object_type expect); /* Helper to check and "touch" a file */ @@ -1619,29 +1598,6 @@ struct pack_entry { struct packed_git *p; }; -extern struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path); - -/* A hook to report invalid files in pack directory */ -#define PACKDIR_FILE_PACK 1 -#define PACKDIR_FILE_IDX 2 -#define PACKDIR_FILE_GARBAGE 4 -extern void (*report_garbage)(unsigned seen_bits, const char *path); - -extern void prepare_packed_git(void); -extern void reprepare_packed_git(void); -extern void install_packed_git(struct packed_git *pack); - -/* - * Give a rough count of objects in the repository. This sacrifices accuracy - * for speed. - */ -unsigned long approximate_object_count(void); - -extern struct packed_git *find_sha1_pack(const unsigned char *sha1, - struct packed_git *packs); - -extern void pack_report(void); - /* * Create a temporary file rooted in the object database directory, or * die on failure. The filename is taken from "pattern", which should have the @@ -1651,15 +1607,6 @@ extern void pack_report(void); extern int odb_mkstemp(struct strbuf *template, const char *pattern); /* - * Generate the filename to be used for a pack file with checksum "sha1" and - * extension "ext". The result is written into the strbuf "buf", overwriting - * any existing contents. A pointer to buf->buf is returned as a convenience. - * - * Example: odb_pack_name(out, sha1, "idx") => ".git/objects/pack/pack-1234..idx" - */ -extern char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); - -/* * Create a pack .keep file named "name" (which should generally be the output * of odb_pack_name). Returns a file descriptor opened for writing, or -1 on * error. @@ -1667,67 +1614,6 @@ extern char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const extern int odb_pack_keep(const char *name); /* - * mmap the index file for the specified packfile (if it is not - * already mmapped). Return 0 on success. - */ -extern int open_pack_index(struct packed_git *); - -/* - * munmap the index file for the specified packfile (if it is - * currently mmapped). - */ -extern void close_pack_index(struct packed_git *); - -extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); -extern void close_pack_windows(struct packed_git *); -extern void close_all_packs(void); -extern void unuse_pack(struct pack_window **); -extern void clear_delta_base_cache(void); -extern struct packed_git *add_packed_git(const char *path, size_t path_len, int local); - -/* - * Make sure that a pointer access into an mmap'd index file is within bounds, - * and can provide at least 8 bytes of data. - * - * Note that this is only necessary for variable-length segments of the file - * (like the 64-bit extended offset table), as we compare the size to the - * fixed-length parts when we open the file. - */ -extern void check_pack_index_ptr(const struct packed_git *p, const void *ptr); - -/* - * Return the SHA-1 of the nth object within the specified packfile. - * Open the index if it is not already open. The return value points - * at the SHA-1 within the mmapped index. Return NULL if there is an - * error. - */ -extern const unsigned char *nth_packed_object_sha1(struct packed_git *, uint32_t n); -/* - * Like nth_packed_object_sha1, but write the data into the object specified by - * the the first argument. Returns the first argument on success, and NULL on - * error. - */ -extern const struct object_id *nth_packed_object_oid(struct object_id *, struct packed_git *, uint32_t n); - -/* - * Return the offset of the nth object within the specified packfile. - * The index must already be opened. - */ -extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t n); - -/* - * If the object named sha1 is present in the specified packfile, - * return its offset within the packfile; otherwise, return 0. - */ -extern off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *); - -extern int is_pack_valid(struct packed_git *); -extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *); -extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); -extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t); -extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *); - -/* * Iterate over the files in the loose-object parts of the object * directory "path", triggering the following callbacks: * @@ -1776,17 +1662,12 @@ int for_each_loose_file_in_objdir_buf(struct strbuf *path, void *data); /* - * Iterate over loose and packed objects in both the local + * Iterate over loose objects in both the local * repository and any alternates repositories (unless the * LOCAL_ONLY flag is set). */ #define FOR_EACH_OBJECT_LOCAL_ONLY 0x1 -typedef int each_packed_object_fn(const struct object_id *oid, - struct packed_git *pack, - uint32_t pos, - void *data); extern int for_each_loose_object(each_loose_object_fn, void *, unsigned flags); -extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags); struct object_info { /* Request */ @@ -1836,7 +1717,6 @@ struct object_info { /* Do not retry packed storage after checking packed and loose storage */ #define OBJECT_INFO_QUICK 8 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags); -extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *); /* Dumb servers support */ extern int update_server_info(int); @@ -1955,6 +1835,8 @@ void shift_tree_by(const struct object_id *, const struct object_id *, struct ob #define WS_TRAILING_SPACE (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF) #define WS_DEFAULT_RULE (WS_TRAILING_SPACE|WS_SPACE_BEFORE_TAB|8) #define WS_TAB_WIDTH_MASK 077 +/* All WS_* -- when extended, adapt diff.c emit_symbol */ +#define WS_RULE_MASK 07777 extern unsigned whitespace_rule_cfg; extern unsigned whitespace_rule(const char *); extern unsigned parse_whitespace_rule(const char *); @@ -338,6 +338,13 @@ static int check_auto_color(void) int want_color(int var) { + /* + * NEEDSWORK: This function is sometimes used from multiple threads, and + * we end up using want_auto racily. That "should not matter" since + * we always write the same value, but it's still wrong. This function + * is listed in .tsan-suppressions for the time being. + */ + static int want_auto = -1; if (var < 0) @@ -42,6 +42,8 @@ struct strbuf; #define GIT_COLOR_BG_BLUE "\033[44m" #define GIT_COLOR_BG_MAGENTA "\033[45m" #define GIT_COLOR_BG_CYAN "\033[46m" +#define GIT_COLOR_FAINT "\033[2m" +#define GIT_COLOR_FAINT_ITALIC "\033[2;3m" /* A special value meaning "no color selected" */ #define GIT_COLOR_NIL "NIL" @@ -134,35 +134,41 @@ int register_commit_graft(struct commit_graft *graft, int ignore_dups) return 0; } -struct commit_graft *read_graft_line(char *buf, int len) +struct commit_graft *read_graft_line(struct strbuf *line) { /* The format is just "Commit Parent1 Parent2 ...\n" */ - int i; + int i, phase; + const char *tail = NULL; struct commit_graft *graft = NULL; - const int entry_size = GIT_SHA1_HEXSZ + 1; + struct object_id dummy_oid, *oid; - while (len && isspace(buf[len-1])) - buf[--len] = '\0'; - if (buf[0] == '#' || buf[0] == '\0') + strbuf_rtrim(line); + if (!line->len || line->buf[0] == '#') return NULL; - if ((len + 1) % entry_size) - goto bad_graft_data; - i = (len + 1) / entry_size - 1; - graft = xmalloc(st_add(sizeof(*graft), st_mult(GIT_SHA1_RAWSZ, i))); - graft->nr_parent = i; - if (get_oid_hex(buf, &graft->oid)) - goto bad_graft_data; - for (i = GIT_SHA1_HEXSZ; i < len; i += entry_size) { - if (buf[i] != ' ') - goto bad_graft_data; - if (get_sha1_hex(buf + i + 1, graft->parent[i/entry_size].hash)) + /* + * phase 0 verifies line, counts hashes in line and allocates graft + * phase 1 fills graft + */ + for (phase = 0; phase < 2; phase++) { + oid = graft ? &graft->oid : &dummy_oid; + if (parse_oid_hex(line->buf, oid, &tail)) goto bad_graft_data; + for (i = 0; *tail != '\0'; i++) { + oid = graft ? &graft->parent[i] : &dummy_oid; + if (!isspace(*tail++) || parse_oid_hex(tail, oid, &tail)) + goto bad_graft_data; + } + if (!graft) { + graft = xmalloc(st_add(sizeof(*graft), + st_mult(sizeof(struct object_id), i))); + graft->nr_parent = i; + } } return graft; bad_graft_data: - error("bad graft data: %s", buf); - free(graft); + error("bad graft data: %s", line->buf); + assert(!graft); return NULL; } @@ -174,7 +180,7 @@ static int read_graft_file(const char *graft_file) return -1; while (!strbuf_getwholeline(&buf, fp, '\n')) { /* The format is just "Commit Parent1 Parent2 ...\n" */ - struct commit_graft *graft = read_graft_line(buf.buf, buf.len); + struct commit_graft *graft = read_graft_line(&buf); if (!graft) continue; if (register_commit_graft(graft, 1)) @@ -247,7 +247,7 @@ struct commit_graft { }; typedef int (*each_commit_graft_fn)(const struct commit_graft *, void *); -struct commit_graft *read_graft_line(char *buf, int len); +struct commit_graft *read_graft_line(struct strbuf *line); int register_commit_graft(struct commit_graft *, int); struct commit_graft *lookup_commit_graft(const struct object_id *oid); @@ -2094,6 +2094,28 @@ int git_config_get_expiry(const char *key, const char **output) return ret; } +int git_config_get_expiry_in_days(const char *key, timestamp_t *expiry, timestamp_t now) +{ + char *expiry_string; + intmax_t days; + timestamp_t when; + + if (git_config_get_string(key, &expiry_string)) + return 1; /* no such thing */ + + if (git_parse_signed(expiry_string, &days, maximum_signed_value_of_type(int))) { + const int scale = 86400; + *expiry = now - days * scale; + return 0; + } + + if (!parse_expiry_date(expiry_string, &when)) { + *expiry = when; + return 0; + } + return -1; /* thing exists but cannot be parsed */ +} + int git_config_get_untracked_cache(void) { int val = -1; @@ -215,6 +215,9 @@ extern int git_config_get_max_percent_split_change(void); /* This dies if the configured or default date is in the future */ extern int git_config_get_expiry(const char *key, const char **output); +/* parse either "this many days" integer, or "5.days.ago" approxidate */ +extern int git_config_get_expiry_in_days(const char *key, timestamp_t *, timestamp_t now); + struct key_value_info { const char *filename; int linenr; diff --git a/connected.c b/connected.c index 136c2ac16..f416b0505 100644 --- a/connected.c +++ b/connected.c @@ -3,6 +3,7 @@ #include "sigchain.h" #include "connected.h" #include "transport.h" +#include "packfile.h" /* * If we feed all the commits we want to verify to this command diff --git a/contrib/examples/git-merge.sh b/contrib/examples/git-merge.sh index ee99f1a4e..932e78dbf 100755 --- a/contrib/examples/git-merge.sh +++ b/contrib/examples/git-merge.sh @@ -399,7 +399,7 @@ case "$allow_fast_forward,$#,$common,$no_commit" in ?,1,"$1",*) # If head can reach all the merge then we are up to date. # but first the most common case of merging one remote. - finish_up_to_date "Already up-to-date." + finish_up_to_date "Already up to date." exit 0 ;; t,1,"$head",*) @@ -459,7 +459,7 @@ t,1,"$head",*) done if test "$up_to_date" = t then - finish_up_to_date "Already up-to-date. Yeeah!" + finish_up_to_date "Already up to date. Yeeah!" exit 0 fi ;; diff --git a/contrib/examples/git-resolve.sh b/contrib/examples/git-resolve.sh index 70fdc27b7..3099dc851 100755 --- a/contrib/examples/git-resolve.sh +++ b/contrib/examples/git-resolve.sh @@ -41,7 +41,7 @@ fi case "$common" in "$merge") - echo "Already up-to-date. Yeeah!" + echo "Already up to date. Yeeah!" dropheads exit 0 ;; diff --git a/contrib/subtree/t/t7900-subtree.sh b/contrib/subtree/t/t7900-subtree.sh index 3c87ebaf5..d05c613c9 100755 --- a/contrib/subtree/t/t7900-subtree.sh +++ b/contrib/subtree/t/t7900-subtree.sh @@ -253,7 +253,7 @@ test_expect_success 'merge the added subproj again, should do nothing' ' # this shouldn not actually do anything, since FETCH_HEAD # is already a parent result=$(git merge -s ours -m "merge -s -ours" FETCH_HEAD) && - check_equal "${result}" "Already up-to-date." + check_equal "${result}" "Already up to date." ) ' @@ -1040,7 +1040,6 @@ static void convert_attrs(struct conv_attrs *ca, const char *path) ca->crlf_action = git_path_check_crlf(ccheck + 4); if (ca->crlf_action == CRLF_UNDEFINED) ca->crlf_action = git_path_check_crlf(ccheck + 0); - ca->attr_action = ca->crlf_action; ca->ident = git_path_check_ident(ccheck + 1); ca->drv = git_path_check_convert(ccheck + 2); if (ca->crlf_action != CRLF_BINARY) { @@ -1054,12 +1053,14 @@ static void convert_attrs(struct conv_attrs *ca, const char *path) else if (eol_attr == EOL_CRLF) ca->crlf_action = CRLF_TEXT_CRLF; } - ca->attr_action = ca->crlf_action; } else { ca->drv = NULL; ca->crlf_action = CRLF_UNDEFINED; ca->ident = 0; } + + /* Save attr and make a decision for action */ + ca->attr_action = ca->crlf_action; if (ca->crlf_action == CRLF_TEXT) ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT; if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE) @@ -1132,10 +1133,12 @@ int convert_to_git(const struct index_state *istate, src = dst->buf; len = dst->len; } - ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, checksafe); - if (ret && dst) { - src = dst->buf; - len = dst->len; + if (checksafe != SAFE_CRLF_KEEP_CRLF) { + ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, checksafe); + if (ret && dst) { + src = dst->buf; + len = dst->len; + } } return ret | ident_to_git(path, src, len, dst, ca.ident); } @@ -12,7 +12,8 @@ enum safe_crlf { SAFE_CRLF_FALSE = 0, SAFE_CRLF_FAIL = 1, SAFE_CRLF_WARN = 2, - SAFE_CRLF_RENORMALIZE = 3 + SAFE_CRLF_RENORMALIZE = 3, + SAFE_CRLF_KEEP_CRLF = 4 }; extern enum safe_crlf safe_crlf; @@ -16,10 +16,12 @@ #include "userdiff.h" #include "submodule-config.h" #include "submodule.h" +#include "hashmap.h" #include "ll-merge.h" #include "string-list.h" #include "argv-array.h" #include "graph.h" +#include "packfile.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 @@ -32,6 +34,7 @@ static int diff_indent_heuristic = 1; static int diff_rename_limit_default = 400; static int diff_suppress_blank_empty; static int diff_use_color_default = -1; +static int diff_color_moved_default; static int diff_context_default = 3; static int diff_interhunk_context_default; static const char *diff_word_regex_cfg; @@ -56,6 +59,14 @@ static char diff_colors[][COLOR_MAXLEN] = { GIT_COLOR_YELLOW, /* COMMIT */ GIT_COLOR_BG_RED, /* WHITESPACE */ GIT_COLOR_NORMAL, /* FUNCINFO */ + GIT_COLOR_BOLD_MAGENTA, /* OLD_MOVED */ + GIT_COLOR_BOLD_BLUE, /* OLD_MOVED ALTERNATIVE */ + GIT_COLOR_FAINT, /* OLD_MOVED_DIM */ + GIT_COLOR_FAINT_ITALIC, /* OLD_MOVED_ALTERNATIVE_DIM */ + GIT_COLOR_BOLD_CYAN, /* NEW_MOVED */ + GIT_COLOR_BOLD_YELLOW, /* NEW_MOVED ALTERNATIVE */ + GIT_COLOR_FAINT, /* NEW_MOVED_DIM */ + GIT_COLOR_FAINT_ITALIC, /* NEW_MOVED_ALTERNATIVE_DIM */ }; static NORETURN void die_want_option(const char *option_name) @@ -81,6 +92,22 @@ static int parse_diff_color_slot(const char *var) return DIFF_WHITESPACE; if (!strcasecmp(var, "func")) return DIFF_FUNCINFO; + if (!strcasecmp(var, "oldmoved")) + return DIFF_FILE_OLD_MOVED; + if (!strcasecmp(var, "oldmovedalternative")) + return DIFF_FILE_OLD_MOVED_ALT; + if (!strcasecmp(var, "oldmoveddimmed")) + return DIFF_FILE_OLD_MOVED_DIM; + if (!strcasecmp(var, "oldmovedalternativedimmed")) + return DIFF_FILE_OLD_MOVED_ALT_DIM; + if (!strcasecmp(var, "newmoved")) + return DIFF_FILE_NEW_MOVED; + if (!strcasecmp(var, "newmovedalternative")) + return DIFF_FILE_NEW_MOVED_ALT; + if (!strcasecmp(var, "newmoveddimmed")) + return DIFF_FILE_NEW_MOVED_DIM; + if (!strcasecmp(var, "newmovedalternativedimmed")) + return DIFF_FILE_NEW_MOVED_ALT_DIM; return -1; } @@ -229,12 +256,44 @@ int git_diff_heuristic_config(const char *var, const char *value, void *cb) return 0; } +static int parse_color_moved(const char *arg) +{ + switch (git_parse_maybe_bool(arg)) { + case 0: + return COLOR_MOVED_NO; + case 1: + return COLOR_MOVED_DEFAULT; + default: + break; + } + + if (!strcmp(arg, "no")) + return COLOR_MOVED_NO; + else if (!strcmp(arg, "plain")) + return COLOR_MOVED_PLAIN; + else if (!strcmp(arg, "zebra")) + return COLOR_MOVED_ZEBRA; + else if (!strcmp(arg, "default")) + return COLOR_MOVED_DEFAULT; + else if (!strcmp(arg, "dimmed_zebra")) + return COLOR_MOVED_ZEBRA_DIM; + else + return error(_("color moved setting must be one of 'no', 'default', 'zebra', 'dimmed_zebra', 'plain'")); +} + int git_diff_ui_config(const char *var, const char *value, void *cb) { if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) { diff_use_color_default = git_config_colorbool(var, value); return 0; } + if (!strcmp(var, "diff.colormoved")) { + int cm = parse_color_moved(value); + if (cm < 0) + return -1; + diff_color_moved_default = cm; + return 0; + } if (!strcmp(var, "diff.context")) { diff_context_default = git_config_int(var, value); if (diff_context_default < 0) @@ -343,9 +402,6 @@ int git_diff_basic_config(const char *var, const char *value, void *cb) return 0; } - if (starts_with(var, "submodule.")) - return parse_submodule_config_option(var, value); - if (git_diff_heuristic_config(var, value, cb) < 0) return -1; @@ -554,68 +610,735 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset emit_line_0(o, set, reset, line[0], line+1, len-1); } -static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len) +enum diff_symbol { + DIFF_SYMBOL_BINARY_DIFF_HEADER, + DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA, + DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL, + DIFF_SYMBOL_BINARY_DIFF_BODY, + DIFF_SYMBOL_BINARY_DIFF_FOOTER, + DIFF_SYMBOL_STATS_SUMMARY_NO_FILES, + DIFF_SYMBOL_STATS_SUMMARY_ABBREV, + DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES, + DIFF_SYMBOL_STATS_LINE, + DIFF_SYMBOL_WORD_DIFF, + DIFF_SYMBOL_STAT_SEP, + DIFF_SYMBOL_SUMMARY, + DIFF_SYMBOL_SUBMODULE_ADD, + DIFF_SYMBOL_SUBMODULE_DEL, + DIFF_SYMBOL_SUBMODULE_UNTRACKED, + DIFF_SYMBOL_SUBMODULE_MODIFIED, + DIFF_SYMBOL_SUBMODULE_HEADER, + DIFF_SYMBOL_SUBMODULE_ERROR, + DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, + DIFF_SYMBOL_REWRITE_DIFF, + DIFF_SYMBOL_BINARY_FILES, + DIFF_SYMBOL_HEADER, + DIFF_SYMBOL_FILEPAIR_PLUS, + DIFF_SYMBOL_FILEPAIR_MINUS, + DIFF_SYMBOL_WORDS_PORCELAIN, + DIFF_SYMBOL_WORDS, + DIFF_SYMBOL_CONTEXT, + DIFF_SYMBOL_CONTEXT_INCOMPLETE, + DIFF_SYMBOL_PLUS, + DIFF_SYMBOL_MINUS, + DIFF_SYMBOL_NO_LF_EOF, + DIFF_SYMBOL_CONTEXT_FRAGINFO, + DIFF_SYMBOL_CONTEXT_MARKER, + DIFF_SYMBOL_SEPARATOR +}; +/* + * Flags for content lines: + * 0..12 are whitespace rules + * 13-15 are WSEH_NEW | WSEH_OLD | WSEH_CONTEXT + * 16 is marking if the line is blank at EOF + */ +#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<16) +#define DIFF_SYMBOL_MOVED_LINE (1<<17) +#define DIFF_SYMBOL_MOVED_LINE_ALT (1<<18) +#define DIFF_SYMBOL_MOVED_LINE_UNINTERESTING (1<<19) +#define DIFF_SYMBOL_CONTENT_WS_MASK (WSEH_NEW | WSEH_OLD | WSEH_CONTEXT | WS_RULE_MASK) + +/* + * This struct is used when we need to buffer the output of the diff output. + * + * NEEDSWORK: Instead of storing a copy of the line, add an offset pointer + * into the pre/post image file. This pointer could be a union with the + * line pointer. By storing an offset into the file instead of the literal line, + * we can decrease the memory footprint for the buffered output. At first we + * may want to only have indirection for the content lines, but we could also + * enhance the state for emitting prefabricated lines, e.g. the similarity + * score line or hunk/file headers would only need to store a number or path + * and then the output can be constructed later on depending on state. + */ +struct emitted_diff_symbol { + const char *line; + int len; + int flags; + enum diff_symbol s; +}; +#define EMITTED_DIFF_SYMBOL_INIT {NULL} + +struct emitted_diff_symbols { + struct emitted_diff_symbol *buf; + int nr, alloc; +}; +#define EMITTED_DIFF_SYMBOLS_INIT {NULL, 0, 0} + +static void append_emitted_diff_symbol(struct diff_options *o, + struct emitted_diff_symbol *e) { - if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) && - ecbdata->blank_at_eof_in_preimage && - ecbdata->blank_at_eof_in_postimage && - ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage && - ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage)) - return 0; - return ws_blank_line(line, len, ecbdata->ws_rule); + struct emitted_diff_symbol *f; + + ALLOC_GROW(o->emitted_symbols->buf, + o->emitted_symbols->nr + 1, + o->emitted_symbols->alloc); + f = &o->emitted_symbols->buf[o->emitted_symbols->nr++]; + + memcpy(f, e, sizeof(struct emitted_diff_symbol)); + f->line = e->line ? xmemdupz(e->line, e->len) : NULL; } -static void emit_line_checked(const char *reset, - struct emit_callback *ecbdata, - const char *line, int len, - enum color_diff color, - unsigned ws_error_highlight, - char sign) +struct moved_entry { + struct hashmap_entry ent; + const struct emitted_diff_symbol *es; + struct moved_entry *next_line; +}; + +static int next_byte(const char **cp, const char **endp, + const struct diff_options *diffopt) +{ + int retval; + + if (*cp > *endp) + return -1; + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE_CHANGE)) { + while (*cp < *endp && isspace(**cp)) + (*cp)++; + /* + * After skipping a couple of whitespaces, we still have to + * account for one space. + */ + return (int)' '; + } + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE)) { + while (*cp < *endp && isspace(**cp)) + (*cp)++; + /* return the first non-ws character via the usual below */ + } + + retval = (unsigned char)(**cp); + (*cp)++; + return retval; +} + +static int moved_entry_cmp(const struct diff_options *diffopt, + const struct moved_entry *a, + const struct moved_entry *b, + const void *keydata) +{ + const char *ap = a->es->line, *ae = a->es->line + a->es->len; + const char *bp = b->es->line, *be = b->es->line + b->es->len; + + if (!(diffopt->xdl_opts & XDF_WHITESPACE_FLAGS)) + return a->es->len != b->es->len || memcmp(ap, bp, a->es->len); + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE_AT_EOL)) { + while (ae > ap && isspace(*ae)) + ae--; + while (be > bp && isspace(*be)) + be--; + } + + while (1) { + int ca, cb; + ca = next_byte(&ap, &ae, diffopt); + cb = next_byte(&bp, &be, diffopt); + if (ca != cb) + return 1; + if (ca < 0) + return 0; + } +} + +static unsigned get_string_hash(struct emitted_diff_symbol *es, struct diff_options *o) +{ + if (o->xdl_opts & XDF_WHITESPACE_FLAGS) { + static struct strbuf sb = STRBUF_INIT; + const char *ap = es->line, *ae = es->line + es->len; + int c; + + strbuf_reset(&sb); + while (ae > ap && isspace(*ae)) + ae--; + while ((c = next_byte(&ap, &ae, o)) > 0) + strbuf_addch(&sb, c); + + return memhash(sb.buf, sb.len); + } else { + return memhash(es->line, es->len); + } +} + +static struct moved_entry *prepare_entry(struct diff_options *o, + int line_no) +{ + struct moved_entry *ret = xmalloc(sizeof(*ret)); + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[line_no]; + + ret->ent.hash = get_string_hash(l, o); + ret->es = l; + ret->next_line = NULL; + + return ret; +} + +static void add_lines_to_move_detection(struct diff_options *o, + struct hashmap *add_lines, + struct hashmap *del_lines) +{ + struct moved_entry *prev_line = NULL; + + int n; + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct hashmap *hm; + struct moved_entry *key; + + switch (o->emitted_symbols->buf[n].s) { + case DIFF_SYMBOL_PLUS: + hm = add_lines; + break; + case DIFF_SYMBOL_MINUS: + hm = del_lines; + break; + default: + prev_line = NULL; + continue; + } + + key = prepare_entry(o, n); + if (prev_line && prev_line->es->s == o->emitted_symbols->buf[n].s) + prev_line->next_line = key; + + hashmap_add(hm, key); + prev_line = key; + } +} + +static int shrink_potential_moved_blocks(struct moved_entry **pmb, + int pmb_nr) +{ + int lp, rp; + + /* Shrink the set of potential block to the remaining running */ + for (lp = 0, rp = pmb_nr - 1; lp <= rp;) { + while (lp < pmb_nr && pmb[lp]) + lp++; + /* lp points at the first NULL now */ + + while (rp > -1 && !pmb[rp]) + rp--; + /* rp points at the last non-NULL */ + + if (lp < pmb_nr && rp > -1 && lp < rp) { + pmb[lp] = pmb[rp]; + pmb[rp] = NULL; + rp--; + lp++; + } + } + + /* Remember the number of running sets */ + return rp + 1; +} + +/* + * If o->color_moved is COLOR_MOVED_PLAIN, this function does nothing. + * + * Otherwise, if the last block has fewer alphanumeric characters than + * COLOR_MOVED_MIN_ALNUM_COUNT, unset DIFF_SYMBOL_MOVED_LINE on all lines in + * that block. + * + * The last block consists of the (n - block_length)'th line up to but not + * including the nth line. + * + * NEEDSWORK: This uses the same heuristic as blame_entry_score() in blame.c. + * Think of a way to unify them. + */ +static void adjust_last_block(struct diff_options *o, int n, int block_length) +{ + int i, alnum_count = 0; + if (o->color_moved == COLOR_MOVED_PLAIN) + return; + for (i = 1; i < block_length + 1; i++) { + const char *c = o->emitted_symbols->buf[n - i].line; + for (; *c; c++) { + if (!isalnum(*c)) + continue; + alnum_count++; + if (alnum_count >= COLOR_MOVED_MIN_ALNUM_COUNT) + return; + } + } + for (i = 1; i < block_length + 1; i++) + o->emitted_symbols->buf[n - i].flags &= ~DIFF_SYMBOL_MOVED_LINE; +} + +/* Find blocks of moved code, delegate actual coloring decision to helper */ +static void mark_color_as_moved(struct diff_options *o, + struct hashmap *add_lines, + struct hashmap *del_lines) +{ + struct moved_entry **pmb = NULL; /* potentially moved blocks */ + int pmb_nr = 0, pmb_alloc = 0; + int n, flipped_block = 1, block_length = 0; + + + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct hashmap *hm = NULL; + struct moved_entry *key; + struct moved_entry *match = NULL; + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; + int i; + + switch (l->s) { + case DIFF_SYMBOL_PLUS: + hm = del_lines; + key = prepare_entry(o, n); + match = hashmap_get(hm, key, o); + free(key); + break; + case DIFF_SYMBOL_MINUS: + hm = add_lines; + key = prepare_entry(o, n); + match = hashmap_get(hm, key, o); + free(key); + break; + default: + flipped_block = 1; + } + + if (!match) { + adjust_last_block(o, n, block_length); + pmb_nr = 0; + block_length = 0; + continue; + } + + l->flags |= DIFF_SYMBOL_MOVED_LINE; + + if (o->color_moved == COLOR_MOVED_PLAIN) + continue; + + /* Check any potential block runs, advance each or nullify */ + for (i = 0; i < pmb_nr; i++) { + struct moved_entry *p = pmb[i]; + struct moved_entry *pnext = (p && p->next_line) ? + p->next_line : NULL; + if (pnext && !hm->cmpfn(o, pnext, match, NULL)) { + pmb[i] = p->next_line; + } else { + pmb[i] = NULL; + } + } + + pmb_nr = shrink_potential_moved_blocks(pmb, pmb_nr); + + if (pmb_nr == 0) { + /* + * The current line is the start of a new block. + * Setup the set of potential blocks. + */ + for (; match; match = hashmap_get_next(hm, match)) { + ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc); + pmb[pmb_nr++] = match; + } + + flipped_block = (flipped_block + 1) % 2; + + adjust_last_block(o, n, block_length); + block_length = 0; + } + + block_length++; + + if (flipped_block) + l->flags |= DIFF_SYMBOL_MOVED_LINE_ALT; + } + adjust_last_block(o, n, block_length); + + free(pmb); +} + +#define DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK \ + (DIFF_SYMBOL_MOVED_LINE | DIFF_SYMBOL_MOVED_LINE_ALT) +static void dim_moved_lines(struct diff_options *o) +{ + int n; + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct emitted_diff_symbol *prev = (n != 0) ? + &o->emitted_symbols->buf[n - 1] : NULL; + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; + struct emitted_diff_symbol *next = + (n < o->emitted_symbols->nr - 1) ? + &o->emitted_symbols->buf[n + 1] : NULL; + + /* Not a plus or minus line? */ + if (l->s != DIFF_SYMBOL_PLUS && l->s != DIFF_SYMBOL_MINUS) + continue; + + /* Not a moved line? */ + if (!(l->flags & DIFF_SYMBOL_MOVED_LINE)) + continue; + + /* + * If prev or next are not a plus or minus line, + * pretend they don't exist + */ + if (prev && prev->s != DIFF_SYMBOL_PLUS && + prev->s != DIFF_SYMBOL_MINUS) + prev = NULL; + if (next && next->s != DIFF_SYMBOL_PLUS && + next->s != DIFF_SYMBOL_MINUS) + next = NULL; + + /* Inside a block? */ + if ((prev && + (prev->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) == + (l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK)) && + (next && + (next->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) == + (l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK))) { + l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING; + continue; + } + + /* Check if we are at an interesting bound: */ + if (prev && (prev->flags & DIFF_SYMBOL_MOVED_LINE) && + (prev->flags & DIFF_SYMBOL_MOVED_LINE_ALT) != + (l->flags & DIFF_SYMBOL_MOVED_LINE_ALT)) + continue; + if (next && (next->flags & DIFF_SYMBOL_MOVED_LINE) && + (next->flags & DIFF_SYMBOL_MOVED_LINE_ALT) != + (l->flags & DIFF_SYMBOL_MOVED_LINE_ALT)) + continue; + + /* + * The boundary to prev and next are not interesting, + * so this line is not interesting as a whole + */ + l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING; + } +} + +static void emit_line_ws_markup(struct diff_options *o, + const char *set, const char *reset, + const char *line, int len, char sign, + unsigned ws_rule, int blank_at_eof) { - const char *set = diff_get_color(ecbdata->color_diff, color); const char *ws = NULL; - if (ecbdata->opt->ws_error_highlight & ws_error_highlight) { - ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE); + if (o->ws_error_highlight & ws_rule) { + ws = diff_get_color_opt(o, DIFF_WHITESPACE); if (!*ws) ws = NULL; } if (!ws) - emit_line_0(ecbdata->opt, set, reset, sign, line, len); - else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len)) + emit_line_0(o, set, reset, sign, line, len); + else if (blank_at_eof) /* Blank line at EOF - paint '+' as well */ - emit_line_0(ecbdata->opt, ws, reset, sign, line, len); + emit_line_0(o, ws, reset, sign, line, len); else { /* Emit just the prefix, then the rest. */ - emit_line_0(ecbdata->opt, set, reset, sign, "", 0); - ws_check_emit(line, len, ecbdata->ws_rule, - ecbdata->opt->file, set, reset, ws); + emit_line_0(o, set, reset, sign, "", 0); + ws_check_emit(line, len, ws_rule, + o->file, set, reset, ws); + } +} + +static void emit_diff_symbol_from_struct(struct diff_options *o, + struct emitted_diff_symbol *eds) +{ + static const char *nneof = " No newline at end of file\n"; + const char *context, *reset, *set, *meta, *fraginfo; + struct strbuf sb = STRBUF_INIT; + + enum diff_symbol s = eds->s; + const char *line = eds->line; + int len = eds->len; + unsigned flags = eds->flags; + + switch (s) { + case DIFF_SYMBOL_NO_LF_EOF: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + putc('\n', o->file); + emit_line_0(o, context, reset, '\\', + nneof, strlen(nneof)); + break; + case DIFF_SYMBOL_SUBMODULE_HEADER: + case DIFF_SYMBOL_SUBMODULE_ERROR: + case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH: + case DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES: + case DIFF_SYMBOL_SUMMARY: + case DIFF_SYMBOL_STATS_LINE: + case DIFF_SYMBOL_BINARY_DIFF_BODY: + case DIFF_SYMBOL_CONTEXT_FRAGINFO: + emit_line(o, "", "", line, len); + break; + case DIFF_SYMBOL_CONTEXT_INCOMPLETE: + case DIFF_SYMBOL_CONTEXT_MARKER: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, context, reset, line, len); + break; + case DIFF_SYMBOL_SEPARATOR: + fprintf(o->file, "%s%c", + diff_line_prefix(o), + o->line_termination); + break; + case DIFF_SYMBOL_CONTEXT: + set = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, ' ', + flags & (DIFF_SYMBOL_CONTENT_WS_MASK), 0); + break; + case DIFF_SYMBOL_PLUS: + switch (flags & (DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) { + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED); + break; + default: + set = diff_get_color_opt(o, DIFF_FILE_NEW); + } + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, '+', + flags & DIFF_SYMBOL_CONTENT_WS_MASK, + flags & DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF); + break; + case DIFF_SYMBOL_MINUS: + switch (flags & (DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) { + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED); + break; + default: + set = diff_get_color_opt(o, DIFF_FILE_OLD); + } + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, '-', + flags & DIFF_SYMBOL_CONTENT_WS_MASK, 0); + break; + case DIFF_SYMBOL_WORDS_PORCELAIN: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, context, reset, line, len); + fputs("~\n", o->file); + break; + case DIFF_SYMBOL_WORDS: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + /* + * Skip the prefix character, if any. With + * diff_suppress_blank_empty, there may be + * none. + */ + if (line[0] != '\n') { + line++; + len--; + } + emit_line(o, context, reset, line, len); + break; + case DIFF_SYMBOL_FILEPAIR_PLUS: + meta = diff_get_color_opt(o, DIFF_METAINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + fprintf(o->file, "%s%s+++ %s%s%s\n", diff_line_prefix(o), meta, + line, reset, + strchr(line, ' ') ? "\t" : ""); + break; + case DIFF_SYMBOL_FILEPAIR_MINUS: + meta = diff_get_color_opt(o, DIFF_METAINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + fprintf(o->file, "%s%s--- %s%s%s\n", diff_line_prefix(o), meta, + line, reset, + strchr(line, ' ') ? "\t" : ""); + break; + case DIFF_SYMBOL_BINARY_FILES: + case DIFF_SYMBOL_HEADER: + fprintf(o->file, "%s", line); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER: + fprintf(o->file, "%sGIT binary patch\n", diff_line_prefix(o)); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA: + fprintf(o->file, "%sdelta %s\n", diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL: + fprintf(o->file, "%sliteral %s\n", diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_BINARY_DIFF_FOOTER: + fputs(diff_line_prefix(o), o->file); + fputc('\n', o->file); + break; + case DIFF_SYMBOL_REWRITE_DIFF: + fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, fraginfo, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_ADD: + set = diff_get_color_opt(o, DIFF_FILE_NEW); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, set, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_DEL: + set = diff_get_color_opt(o, DIFF_FILE_OLD); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, set, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_UNTRACKED: + fprintf(o->file, "%sSubmodule %s contains untracked content\n", + diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_SUBMODULE_MODIFIED: + fprintf(o->file, "%sSubmodule %s contains modified content\n", + diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_STATS_SUMMARY_NO_FILES: + emit_line(o, "", "", " 0 files changed\n", + strlen(" 0 files changed\n")); + break; + case DIFF_SYMBOL_STATS_SUMMARY_ABBREV: + emit_line(o, "", "", " ...\n", strlen(" ...\n")); + break; + case DIFF_SYMBOL_WORD_DIFF: + fprintf(o->file, "%.*s", len, line); + break; + case DIFF_SYMBOL_STAT_SEP: + fputs(o->stat_sep, o->file); + break; + default: + die("BUG: unknown diff symbol"); } + strbuf_release(&sb); +} + +static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s, + const char *line, int len, unsigned flags) +{ + struct emitted_diff_symbol e = {line, len, flags, s}; + + if (o->emitted_symbols) + append_emitted_diff_symbol(o, &e); + else + emit_diff_symbol_from_struct(o, &e); +} + +void diff_emit_submodule_del(struct diff_options *o, const char *line) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_DEL, line, strlen(line), 0); +} + +void diff_emit_submodule_add(struct diff_options *o, const char *line) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ADD, line, strlen(line), 0); +} + +void diff_emit_submodule_untracked(struct diff_options *o, const char *path) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_UNTRACKED, + path, strlen(path), 0); +} + +void diff_emit_submodule_modified(struct diff_options *o, const char *path) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_MODIFIED, + path, strlen(path), 0); +} + +void diff_emit_submodule_header(struct diff_options *o, const char *header) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_HEADER, + header, strlen(header), 0); +} + +void diff_emit_submodule_error(struct diff_options *o, const char *err) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ERROR, err, strlen(err), 0); +} + +void diff_emit_submodule_pipethrough(struct diff_options *o, + const char *line, int len) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, line, len, 0); +} + +static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len) +{ + if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) && + ecbdata->blank_at_eof_in_preimage && + ecbdata->blank_at_eof_in_postimage && + ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage && + ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage)) + return 0; + return ws_blank_line(line, len, ecbdata->ws_rule); } static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_FILE_NEW, WSEH_NEW, '+'); + unsigned flags = WSEH_NEW | ecbdata->ws_rule; + if (new_blank_line_at_eof(ecbdata, line, len)) + flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF; + + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags); } static void emit_del_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_FILE_OLD, WSEH_OLD, '-'); + unsigned flags = WSEH_OLD | ecbdata->ws_rule; + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_MINUS, line, len, flags); } static void emit_context_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_CONTEXT, WSEH_CONTEXT, ' '); + unsigned flags = WSEH_CONTEXT | ecbdata->ws_rule; + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT, line, len, flags); } static void emit_hunk_header(struct emit_callback *ecbdata, @@ -638,7 +1361,8 @@ static void emit_hunk_header(struct emit_callback *ecbdata, if (len < 10 || memcmp(line, atat, 2) || !(ep = memmem(line + 2, len - 2, atat, 2))) { - emit_line(ecbdata->opt, context, reset, line, len); + emit_diff_symbol(ecbdata->opt, + DIFF_SYMBOL_CONTEXT_MARKER, line, len, 0); return; } ep += 2; /* skip over @@ */ @@ -672,7 +1396,9 @@ static void emit_hunk_header(struct emit_callback *ecbdata, } strbuf_add(&msgbuf, line + len, org_len - len); - emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len); + strbuf_complete_line(&msgbuf); + emit_diff_symbol(ecbdata->opt, + DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len, 0); strbuf_release(&msgbuf); } @@ -694,17 +1420,17 @@ static void remove_tempfile(void) } } -static void print_line_count(FILE *file, int count) +static void add_line_count(struct strbuf *out, int count) { switch (count) { case 0: - fprintf(file, "0,0"); + strbuf_addstr(out, "0,0"); break; case 1: - fprintf(file, "1"); + strbuf_addstr(out, "1"); break; default: - fprintf(file, "1,%d", count); + strbuf_addf(out, "1,%d", count); break; } } @@ -713,7 +1439,6 @@ static void emit_rewrite_lines(struct emit_callback *ecb, int prefix, const char *data, int size) { const char *endp = NULL; - static const char *nneof = " No newline at end of file\n"; const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET); while (0 < size) { @@ -731,13 +1456,8 @@ static void emit_rewrite_lines(struct emit_callback *ecb, size -= len; data += len; } - if (!endp) { - const char *context = diff_get_color(ecb->color_diff, - DIFF_CONTEXT); - putc('\n', ecb->opt->file); - emit_line_0(ecb->opt, context, reset, '\\', - nneof, strlen(nneof)); - } + if (!endp) + emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0, 0); } static void emit_rewrite_diff(const char *name_a, @@ -749,16 +1469,12 @@ static void emit_rewrite_diff(const char *name_a, struct diff_options *o) { int lc_a, lc_b; - const char *name_a_tab, *name_b_tab; - const char *metainfo = diff_get_color(o->use_color, DIFF_METAINFO); - const char *fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO); - const char *reset = diff_get_color(o->use_color, DIFF_RESET); static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT; const char *a_prefix, *b_prefix; char *data_one, *data_two; size_t size_one, size_two; struct emit_callback ecbdata; - const char *line_prefix = diff_line_prefix(o); + struct strbuf out = STRBUF_INIT; if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) { a_prefix = o->b_prefix; @@ -770,8 +1486,6 @@ static void emit_rewrite_diff(const char *name_a, name_a += (*name_a == '/'); name_b += (*name_b == '/'); - name_a_tab = strchr(name_a, ' ') ? "\t" : ""; - name_b_tab = strchr(name_b, ' ') ? "\t" : ""; strbuf_reset(&a_name); strbuf_reset(&b_name); @@ -798,18 +1512,23 @@ static void emit_rewrite_diff(const char *name_a, lc_a = count_lines(data_one, size_one); lc_b = count_lines(data_two, size_two); - fprintf(o->file, - "%s%s--- %s%s%s\n%s%s+++ %s%s%s\n%s%s@@ -", - line_prefix, metainfo, a_name.buf, name_a_tab, reset, - line_prefix, metainfo, b_name.buf, name_b_tab, reset, - line_prefix, fraginfo); + + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS, + a_name.buf, a_name.len, 0); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS, + b_name.buf, b_name.len, 0); + + strbuf_addstr(&out, "@@ -"); if (!o->irreversible_delete) - print_line_count(o->file, lc_a); + add_line_count(&out, lc_a); else - fprintf(o->file, "?,?"); - fprintf(o->file, " +"); - print_line_count(o->file, lc_b); - fprintf(o->file, " @@%s\n", reset); + strbuf_addstr(&out, "?,?"); + strbuf_addstr(&out, " +"); + add_line_count(&out, lc_b); + strbuf_addstr(&out, " @@\n"); + emit_diff_symbol(o, DIFF_SYMBOL_REWRITE_DIFF, out.buf, out.len, 0); + strbuf_release(&out); + if (lc_a && !o->irreversible_delete) emit_rewrite_lines(&ecbdata, '-', data_one, size_one); if (lc_b) @@ -869,37 +1588,49 @@ struct diff_words_data { struct diff_words_style *style; }; -static int fn_out_diff_words_write_helper(FILE *fp, +static int fn_out_diff_words_write_helper(struct diff_options *o, struct diff_words_style_elem *st_el, const char *newline, - size_t count, const char *buf, - const char *line_prefix) + size_t count, const char *buf) { int print = 0; + struct strbuf sb = STRBUF_INIT; while (count) { char *p = memchr(buf, '\n', count); if (print) - fputs(line_prefix, fp); + strbuf_addstr(&sb, diff_line_prefix(o)); + if (p != buf) { - if (st_el->color && fputs(st_el->color, fp) < 0) - return -1; - if (fputs(st_el->prefix, fp) < 0 || - fwrite(buf, p ? p - buf : count, 1, fp) != 1 || - fputs(st_el->suffix, fp) < 0) - return -1; - if (st_el->color && *st_el->color - && fputs(GIT_COLOR_RESET, fp) < 0) - return -1; + const char *reset = st_el->color && *st_el->color ? + GIT_COLOR_RESET : NULL; + if (st_el->color && *st_el->color) + strbuf_addstr(&sb, st_el->color); + strbuf_addstr(&sb, st_el->prefix); + strbuf_add(&sb, buf, p ? p - buf : count); + strbuf_addstr(&sb, st_el->suffix); + if (reset) + strbuf_addstr(&sb, reset); } if (!p) - return 0; - if (fputs(newline, fp) < 0) - return -1; + goto out; + + strbuf_addstr(&sb, newline); count -= p + 1 - buf; buf = p + 1; print = 1; + if (count) { + emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF, + sb.buf, sb.len, 0); + strbuf_reset(&sb); + } } + +out: + if (sb.len) + emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF, + sb.buf, sb.len, 0); + strbuf_release(&sb); return 0; } @@ -981,24 +1712,20 @@ static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len) fputs(line_prefix, diff_words->opt->file); } if (diff_words->current_plus != plus_begin) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->ctx, style->newline, plus_begin - diff_words->current_plus, - diff_words->current_plus, line_prefix); - if (*(plus_begin - 1) == '\n') - fputs(line_prefix, diff_words->opt->file); + diff_words->current_plus); } if (minus_begin != minus_end) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->old, style->newline, - minus_end - minus_begin, minus_begin, - line_prefix); + minus_end - minus_begin, minus_begin); } if (plus_begin != plus_end) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->new, style->newline, - plus_end - plus_begin, plus_begin, - line_prefix); + plus_end - plus_begin, plus_begin); } diff_words->current_plus = plus_end; @@ -1092,11 +1819,12 @@ static void diff_words_show(struct diff_words_data *diff_words) /* special case: only removal */ if (!diff_words->plus.text.size) { - fputs(line_prefix, diff_words->opt->file); - fn_out_diff_words_write_helper(diff_words->opt->file, + emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF, + line_prefix, strlen(line_prefix), 0); + fn_out_diff_words_write_helper(diff_words->opt, &style->old, style->newline, diff_words->minus.text.size, - diff_words->minus.text.ptr, line_prefix); + diff_words->minus.text.ptr); diff_words->minus.text.size = 0; return; } @@ -1119,12 +1847,12 @@ static void diff_words_show(struct diff_words_data *diff_words) if (diff_words->current_plus != diff_words->plus.text.ptr + diff_words->plus.text.size) { if (color_words_output_graph_prefix(diff_words)) - fputs(line_prefix, diff_words->opt->file); - fn_out_diff_words_write_helper(diff_words->opt->file, + emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF, + line_prefix, strlen(line_prefix), 0); + fn_out_diff_words_write_helper(diff_words->opt, &style->ctx, style->newline, diff_words->plus.text.ptr + diff_words->plus.text.size - - diff_words->current_plus, diff_words->current_plus, - line_prefix); + - diff_words->current_plus, diff_words->current_plus); } diff_words->minus.text.size = diff_words->plus.text.size = 0; } @@ -1132,9 +1860,29 @@ static void diff_words_show(struct diff_words_data *diff_words) /* In "color-words" mode, show word-diff of words accumulated in the buffer */ static void diff_words_flush(struct emit_callback *ecbdata) { + struct diff_options *wo = ecbdata->diff_words->opt; + if (ecbdata->diff_words->minus.text.size || ecbdata->diff_words->plus.text.size) diff_words_show(ecbdata->diff_words); + + if (wo->emitted_symbols) { + struct diff_options *o = ecbdata->opt; + struct emitted_diff_symbols *wol = wo->emitted_symbols; + int i; + + /* + * NEEDSWORK: + * Instead of appending each, concat all words to a line? + */ + for (i = 0; i < wol->nr; i++) + append_emitted_diff_symbol(o, &wol->buf[i]); + + for (i = 0; i < wol->nr; i++) + free((void *)wol->buf[i].line); + + wol->nr = 0; + } } static void diff_filespec_load_driver(struct diff_filespec *one) @@ -1170,6 +1918,11 @@ static void init_diff_words_data(struct emit_callback *ecbdata, xcalloc(1, sizeof(struct diff_words_data)); ecbdata->diff_words->type = o->word_diff; ecbdata->diff_words->opt = o; + + if (orig_opts->emitted_symbols) + o->emitted_symbols = + xcalloc(1, sizeof(struct emitted_diff_symbols)); + if (!o->word_regex) o->word_regex = userdiff_word_regex(one); if (!o->word_regex) @@ -1204,6 +1957,7 @@ static void free_diff_words_data(struct emit_callback *ecbdata) { if (ecbdata->diff_words) { diff_words_flush(ecbdata); + free (ecbdata->diff_words->opt->emitted_symbols); free (ecbdata->diff_words->opt); free (ecbdata->diff_words->minus.text.ptr); free (ecbdata->diff_words->minus.orig); @@ -1268,30 +2022,25 @@ static void find_lno(const char *line, struct emit_callback *ecbdata) static void fn_out_consume(void *priv, char *line, unsigned long len) { struct emit_callback *ecbdata = priv; - const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO); - const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT); const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET); struct diff_options *o = ecbdata->opt; - const char *line_prefix = diff_line_prefix(o); o->found_changes = 1; if (ecbdata->header) { - fprintf(o->file, "%s", ecbdata->header->buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + ecbdata->header->buf, ecbdata->header->len, 0); strbuf_reset(ecbdata->header); ecbdata->header = NULL; } if (ecbdata->label_path[0]) { - const char *name_a_tab, *name_b_tab; - - name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : ""; - name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : ""; - - fprintf(o->file, "%s%s--- %s%s%s\n", - line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab); - fprintf(o->file, "%s%s+++ %s%s%s\n", - line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS, + ecbdata->label_path[0], + strlen(ecbdata->label_path[0]), 0); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS, + ecbdata->label_path[1], + strlen(ecbdata->label_path[1]), 0); ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; } @@ -1307,12 +2056,13 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) len = sane_truncate_line(ecbdata, line, len); find_lno(line, ecbdata); emit_hunk_header(ecbdata, line, len); - if (line[len-1] != '\n') - putc('\n', o->file); return; } if (ecbdata->diff_words) { + enum diff_symbol s = + ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN ? + DIFF_SYMBOL_WORDS_PORCELAIN : DIFF_SYMBOL_WORDS; if (line[0] == '-') { diff_words_append(line, len, &ecbdata->diff_words->minus); @@ -1332,21 +2082,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) return; } diff_words_flush(ecbdata); - if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) { - emit_line(o, context, reset, line, len); - fputs("~\n", o->file); - } else { - /* - * Skip the prefix character, if any. With - * diff_suppress_blank_empty, there may be - * none. - */ - if (line[0] != '\n') { - line++; - len--; - } - emit_line(o, context, reset, line, len); - } + emit_diff_symbol(o, s, line, len, 0); return; } @@ -1367,8 +2103,8 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) default: /* incomplete line at the end */ ecbdata->lno_in_preimage++; - emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT), - reset, line, len); + emit_diff_symbol(o, DIFF_SYMBOL_CONTEXT_INCOMPLETE, + line, len, 0); break; } } @@ -1513,20 +2249,14 @@ static int scale_linear(int it, int width, int max_change) return 1 + (it * (width - 1) / max_change); } -static void show_name(FILE *file, - const char *prefix, const char *name, int len) -{ - fprintf(file, " %s%-*s |", prefix, len, name); -} - -static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset) +static void show_graph(struct strbuf *out, char ch, int cnt, + const char *set, const char *reset) { if (cnt <= 0) return; - fprintf(file, "%s", set); - while (cnt--) - putc(ch, file); - fprintf(file, "%s", reset); + strbuf_addstr(out, set); + strbuf_addchars(out, ch, cnt); + strbuf_addstr(out, reset); } static void fill_print_name(struct diffstat_file *file) @@ -1550,14 +2280,16 @@ static void fill_print_name(struct diffstat_file *file) file->print_name = pname; } -int print_stat_summary(FILE *fp, int files, int insertions, int deletions) +static void print_stat_summary_inserts_deletes(struct diff_options *options, + int files, int insertions, int deletions) { struct strbuf sb = STRBUF_INIT; - int ret; if (!files) { assert(insertions == 0 && deletions == 0); - return fprintf(fp, "%s\n", " 0 files changed"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_NO_FILES, + NULL, 0, 0); + return; } strbuf_addf(&sb, @@ -1584,9 +2316,19 @@ int print_stat_summary(FILE *fp, int files, int insertions, int deletions) deletions); } strbuf_addch(&sb, '\n'); - ret = fputs(sb.buf, fp); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES, + sb.buf, sb.len, 0); strbuf_release(&sb); - return ret; +} + +void print_stat_summary(FILE *fp, int files, + int insertions, int deletions) +{ + struct diff_options o; + memset(&o, 0, sizeof(o)); + o.file = fp; + + print_stat_summary_inserts_deletes(&o, files, insertions, deletions); } static void show_stats(struct diffstat_t *data, struct diff_options *options) @@ -1596,13 +2338,13 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options) int total_files = data->nr, count; int width, name_width, graph_width, number_width = 0, bin_width = 0; const char *reset, *add_c, *del_c; - const char *line_prefix = ""; int extra_shown = 0; + const char *line_prefix = diff_line_prefix(options); + struct strbuf out = STRBUF_INIT; if (data->nr == 0) return; - line_prefix = diff_line_prefix(options); count = options->stat_count ? options->stat_count : data->nr; reset = diff_get_color_opt(options, DIFF_RESET); @@ -1756,26 +2498,32 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options) } if (file->is_binary) { - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " %*s", number_width, "Bin"); + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addf(&out, " %*s", number_width, "Bin"); if (!added && !deleted) { - putc('\n', options->file); + strbuf_addch(&out, '\n'); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } - fprintf(options->file, " %s%"PRIuMAX"%s", + strbuf_addf(&out, " %s%"PRIuMAX"%s", del_c, deleted, reset); - fprintf(options->file, " -> "); - fprintf(options->file, "%s%"PRIuMAX"%s", + strbuf_addstr(&out, " -> "); + strbuf_addf(&out, "%s%"PRIuMAX"%s", add_c, added, reset); - fprintf(options->file, " bytes"); - fprintf(options->file, "\n"); + strbuf_addstr(&out, " bytes\n"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } else if (file->is_unmerged) { - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " Unmerged\n"); + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addstr(&out, " Unmerged\n"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } @@ -1798,14 +2546,16 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options) add = total - del; } } - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " %*"PRIuMAX"%s", + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addf(&out, " %*"PRIuMAX"%s", number_width, added + deleted, added + deleted ? " " : ""); - show_graph(options->file, '+', add, add_c, reset); - show_graph(options->file, '-', del, del_c, reset); - fprintf(options->file, "\n"); + show_graph(&out, '+', add, add_c, reset); + show_graph(&out, '-', del, del_c, reset); + strbuf_addch(&out, '\n'); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); } for (i = 0; i < data->nr; i++) { @@ -1826,11 +2576,13 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options) if (i < count) continue; if (!extra_shown) - fprintf(options->file, "%s ...\n", line_prefix); + emit_diff_symbol(options, + DIFF_SYMBOL_STATS_SUMMARY_ABBREV, + NULL, 0, 0); extra_shown = 1; } - fprintf(options->file, "%s", line_prefix); - print_stat_summary(options->file, total_files, adds, dels); + + print_stat_summary_inserts_deletes(options, total_files, adds, dels); } static void show_shortstats(struct diffstat_t *data, struct diff_options *options) @@ -1842,7 +2594,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option for (i = 0; i < data->nr; i++) { int added = data->files[i]->added; - int deleted= data->files[i]->deleted; + int deleted = data->files[i]->deleted; if (data->files[i]->is_unmerged || (!data->files[i]->is_interesting && (added + deleted == 0))) { @@ -1852,8 +2604,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option dels += deleted; } } - fprintf(options->file, "%s", diff_line_prefix(options)); - print_stat_summary(options->file, total_files, adds, dels); + print_stat_summary_inserts_deletes(options, total_files, adds, dels); } static void show_numstat(struct diffstat_t *data, struct diff_options *options) @@ -2217,8 +2968,8 @@ static unsigned char *deflate_it(char *data, return deflated; } -static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, - const char *prefix) +static void emit_binary_diff_body(struct diff_options *o, + mmfile_t *one, mmfile_t *two) { void *cp; void *delta; @@ -2247,13 +2998,18 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, } if (delta && delta_size < deflate_size) { - fprintf(file, "%sdelta %lu\n", prefix, orig_size); + char *s = xstrfmt("%lu", orig_size); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA, + s, strlen(s), 0); + free(s); free(deflated); data = delta; data_size = delta_size; - } - else { - fprintf(file, "%sliteral %lu\n", prefix, two->size); + } else { + char *s = xstrfmt("%lu", two->size); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL, + s, strlen(s), 0); + free(s); free(delta); data = deflated; data_size = deflate_size; @@ -2262,8 +3018,9 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, /* emit data encoded in base85 */ cp = data; while (data_size) { + int len; int bytes = (52 < data_size) ? 52 : data_size; - char line[70]; + char line[71]; data_size -= bytes; if (bytes <= 26) line[0] = bytes + 'A' - 1; @@ -2271,20 +3028,24 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, line[0] = bytes - 26 + 'a' - 1; encode_85(line + 1, cp, bytes); cp = (char *) cp + bytes; - fprintf(file, "%s", prefix); - fputs(line, file); - fputc('\n', file); + + len = strlen(line); + line[len++] = '\n'; + line[len] = '\0'; + + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_BODY, + line, len, 0); } - fprintf(file, "%s\n", prefix); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_FOOTER, NULL, 0, 0); free(data); } -static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, - const char *prefix) +static void emit_binary_diff(struct diff_options *o, + mmfile_t *one, mmfile_t *two) { - fprintf(file, "%sGIT binary patch\n", prefix); - emit_binary_diff_body(file, one, two, prefix); - emit_binary_diff_body(file, two, one, prefix); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER, NULL, 0, 0); + emit_binary_diff_body(o, one, two); + emit_binary_diff_body(o, two, one); } int diff_filespec_is_binary(struct diff_filespec *one) @@ -2361,24 +3122,16 @@ static void builtin_diff(const char *name_a, if (o->submodule_format == DIFF_SUBMODULE_LOG && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { - const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); - const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); - show_submodule_summary(o->file, one->path ? one->path : two->path, - line_prefix, + show_submodule_summary(o, one->path ? one->path : two->path, &one->oid, &two->oid, - two->dirty_submodule, - meta, del, add, reset); + two->dirty_submodule); return; } else if (o->submodule_format == DIFF_SUBMODULE_INLINE_DIFF && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { - const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); - const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); - show_submodule_inline_diff(o->file, one->path ? one->path : two->path, - line_prefix, + show_submodule_inline_diff(o, one->path ? one->path : two->path, &one->oid, &two->oid, - two->dirty_submodule, - meta, del, add, reset, o); + two->dirty_submodule); return; } @@ -2427,7 +3180,8 @@ static void builtin_diff(const char *name_a, if (complete_rewrite && (textconv_one || !diff_filespec_is_binary(one)) && (textconv_two || !diff_filespec_is_binary(two))) { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); strbuf_reset(&header); emit_rewrite_diff(name_a, name_b, one, two, textconv_one, textconv_two, o); @@ -2437,23 +3191,31 @@ static void builtin_diff(const char *name_a, } if (o->irreversible_delete && lbl[1][0] == '/') { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf, + header.len, 0); strbuf_reset(&header); goto free_ab_and_return; } else if (!DIFF_OPT_TST(o, TEXT) && ( (!textconv_one && diff_filespec_is_binary(one)) || (!textconv_two && diff_filespec_is_binary(two)) )) { + struct strbuf sb = STRBUF_INIT; if (!one->data && !two->data && S_ISREG(one->mode) && S_ISREG(two->mode) && !DIFF_OPT_TST(o, BINARY)) { if (!oidcmp(&one->oid, &two->oid)) { if (must_show_header) - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, + 0); goto free_ab_and_return; } - fprintf(o->file, "%s", header.buf); - fprintf(o->file, "%sBinary files %s and %s differ\n", - line_prefix, lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); + strbuf_addf(&sb, "%sBinary files %s and %s differ\n", + diff_line_prefix(o), lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_FILES, + sb.buf, sb.len, 0); + strbuf_release(&sb); goto free_ab_and_return; } if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) @@ -2462,16 +3224,21 @@ static void builtin_diff(const char *name_a, if (mf1.size == mf2.size && !memcmp(mf1.ptr, mf2.ptr, mf1.size)) { if (must_show_header) - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); goto free_ab_and_return; } - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf, header.len, 0); strbuf_reset(&header); if (DIFF_OPT_TST(o, BINARY)) - emit_binary_diff(o->file, &mf1, &mf2, line_prefix); - else - fprintf(o->file, "%sBinary files %s and %s differ\n", - line_prefix, lbl[0], lbl[1]); + emit_binary_diff(o, &mf1, &mf2); + else { + strbuf_addf(&sb, "%sBinary files %s and %s differ\n", + diff_line_prefix(o), lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_FILES, + sb.buf, sb.len, 0); + strbuf_release(&sb); + } o->found_changes = 1; } else { /* Crazy xdl interfaces.. */ @@ -2483,7 +3250,8 @@ static void builtin_diff(const char *name_a, const struct userdiff_funcname *pe; if (must_show_header) { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); strbuf_reset(&header); } @@ -3241,7 +4009,7 @@ static void diff_fill_oid_info(struct diff_filespec *one) } if (lstat(one->path, &st) < 0) die_errno("stat '%s'", one->path); - if (index_path(one->oid.hash, one->path, &st, 0)) + if (index_path(&one->oid, one->path, &st, 0)) die("cannot hash %s", one->path); } } @@ -3274,8 +4042,8 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) const char *other; const char *attr_path; - name = p->one->path; - other = (strcmp(name, p->two->path) ? p->two->path : NULL); + name = one->path; + other = (strcmp(name, two->path) ? two->path : NULL); attr_path = name; if (o->prefix_length) strip_prefix(o->prefix_length, &name, &other); @@ -3398,6 +4166,8 @@ void diff_setup(struct diff_options *options) options->a_prefix = "a/"; options->b_prefix = "b/"; } + + options->color_moved = diff_color_moved_default; } void diff_setup_done(struct diff_options *options) @@ -3507,6 +4277,9 @@ void diff_setup_done(struct diff_options *options) if (DIFF_OPT_TST(options, FOLLOW_RENAMES) && options->pathspec.nr != 1) die(_("--follow requires exactly one pathspec")); + + if (!options->use_color || external_diff()) + options->color_moved = 0; } static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val) @@ -3931,7 +4704,19 @@ int diff_opt_parse(struct diff_options *options, } else if (!strcmp(arg, "--no-color")) options->use_color = 0; - else if (!strcmp(arg, "--color-words")) { + else if (!strcmp(arg, "--color-moved")) { + if (diff_color_moved_default) + options->color_moved = diff_color_moved_default; + if (options->color_moved == COLOR_MOVED_NO) + options->color_moved = COLOR_MOVED_DEFAULT; + } else if (!strcmp(arg, "--no-color-moved")) + options->color_moved = COLOR_MOVED_NO; + else if (skip_prefix(arg, "--color-moved=", &arg)) { + int cm = parse_color_moved(arg); + if (cm < 0) + die("bad --color-moved argument: %s", arg); + options->color_moved = cm; + } else if (!strcmp(arg, "--color-words")) { options->use_color = 1; options->word_diff = DIFF_WORDS_COLOR; } @@ -4461,67 +5246,76 @@ static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt) } } -static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs) +static void show_file_mode_name(struct diff_options *opt, const char *newdelete, struct diff_filespec *fs) { + struct strbuf sb = STRBUF_INIT; if (fs->mode) - fprintf(file, " %s mode %06o ", newdelete, fs->mode); + strbuf_addf(&sb, " %s mode %06o ", newdelete, fs->mode); else - fprintf(file, " %s ", newdelete); - write_name_quoted(fs->path, file, '\n'); -} + strbuf_addf(&sb, " %s ", newdelete); + quote_c_style(fs->path, &sb, NULL, 0); + strbuf_addch(&sb, '\n'); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + strbuf_release(&sb); +} -static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name, - const char *line_prefix) +static void show_mode_change(struct diff_options *opt, struct diff_filepair *p, + int show_name) { if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) { - fprintf(file, "%s mode change %06o => %06o%c", line_prefix, p->one->mode, - p->two->mode, show_name ? ' ' : '\n'); + struct strbuf sb = STRBUF_INIT; + strbuf_addf(&sb, " mode change %06o => %06o", + p->one->mode, p->two->mode); if (show_name) { - write_name_quoted(p->two->path, file, '\n'); + strbuf_addch(&sb, ' '); + quote_c_style(p->two->path, &sb, NULL, 0); } + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + strbuf_release(&sb); } } -static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p, - const char *line_prefix) +static void show_rename_copy(struct diff_options *opt, const char *renamecopy, + struct diff_filepair *p) { + struct strbuf sb = STRBUF_INIT; char *names = pprint_rename(p->one->path, p->two->path); - - fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p)); + strbuf_addf(&sb, " %s %s (%d%%)\n", + renamecopy, names, similarity_index(p)); free(names); - show_mode_change(file, p, 0, line_prefix); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + show_mode_change(opt, p, 0); } static void diff_summary(struct diff_options *opt, struct diff_filepair *p) { - FILE *file = opt->file; - const char *line_prefix = diff_line_prefix(opt); - switch(p->status) { case DIFF_STATUS_DELETED: - fputs(line_prefix, file); - show_file_mode_name(file, "delete", p->one); + show_file_mode_name(opt, "delete", p->one); break; case DIFF_STATUS_ADDED: - fputs(line_prefix, file); - show_file_mode_name(file, "create", p->two); + show_file_mode_name(opt, "create", p->two); break; case DIFF_STATUS_COPIED: - fputs(line_prefix, file); - show_rename_copy(file, "copy", p, line_prefix); + show_rename_copy(opt, "copy", p); break; case DIFF_STATUS_RENAMED: - fputs(line_prefix, file); - show_rename_copy(file, "rename", p, line_prefix); + show_rename_copy(opt, "rename", p); break; default: if (p->score) { - fprintf(file, "%s rewrite ", line_prefix); - write_name_quoted(p->two->path, file, ' '); - fprintf(file, "(%d%%)\n", similarity_index(p)); + struct strbuf sb = STRBUF_INIT; + strbuf_addstr(&sb, " rewrite "); + quote_c_style(p->two->path, &sb, NULL, 0); + strbuf_addf(&sb, " (%d%%)\n", similarity_index(p)); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); } - show_mode_change(file, p, !p->score, line_prefix); + show_mode_change(opt, p, !p->score); break; } } @@ -4726,6 +5520,51 @@ void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc) warning(_(rename_limit_advice), varname, needed); } +static void diff_flush_patch_all_file_pairs(struct diff_options *o) +{ + int i; + static struct emitted_diff_symbols esm = EMITTED_DIFF_SYMBOLS_INIT; + struct diff_queue_struct *q = &diff_queued_diff; + + if (WSEH_NEW & WS_RULE_MASK) + die("BUG: WS rules bit mask overlaps with diff symbol flags"); + + if (o->color_moved) + o->emitted_symbols = &esm; + + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (check_pair_status(p)) + diff_flush_patch(p, o); + } + + if (o->emitted_symbols) { + if (o->color_moved) { + struct hashmap add_lines, del_lines; + + hashmap_init(&del_lines, + (hashmap_cmp_fn)moved_entry_cmp, o, 0); + hashmap_init(&add_lines, + (hashmap_cmp_fn)moved_entry_cmp, o, 0); + + add_lines_to_move_detection(o, &add_lines, &del_lines); + mark_color_as_moved(o, &add_lines, &del_lines); + if (o->color_moved == COLOR_MOVED_ZEBRA_DIM) + dim_moved_lines(o); + + hashmap_free(&add_lines, 0); + hashmap_free(&del_lines, 0); + } + + for (i = 0; i < esm.nr; i++) + emit_diff_symbol_from_struct(o, &esm.buf[i]); + + for (i = 0; i < esm.nr; i++) + free((void *)esm.buf[i].line); + } + esm.nr = 0; +} + void diff_flush(struct diff_options *options) { struct diff_queue_struct *q = &diff_queued_diff; @@ -4798,6 +5637,7 @@ void diff_flush(struct diff_options *options) fclose(options->file); options->file = xfopen("/dev/null", "w"); options->close_file = 1; + options->color_moved = 0; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; if (check_pair_status(p)) @@ -4809,20 +5649,14 @@ void diff_flush(struct diff_options *options) if (output_format & DIFF_FORMAT_PATCH) { if (separator) { - fprintf(options->file, "%s%c", - diff_line_prefix(options), - options->line_termination); - if (options->stat_sep) { + emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0, 0); + if (options->stat_sep) /* attach patch instead of inline */ - fputs(options->stat_sep, options->file); - } + emit_diff_symbol(options, DIFF_SYMBOL_STAT_SEP, + NULL, 0, 0); } - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (check_pair_status(p)) - diff_flush_patch(p, options); - } + diff_flush_patch_all_file_pairs(options); } if (output_format & DIFF_FORMAT_CALLBACK) @@ -148,9 +148,9 @@ struct diff_options { int abbrev; int ita_invisible_in_index; /* white-space error highlighting */ -#define WSEH_NEW 1 -#define WSEH_CONTEXT 2 -#define WSEH_OLD 4 +#define WSEH_NEW (1<<12) +#define WSEH_CONTEXT (1<<13) +#define WSEH_OLD (1<<14) unsigned ws_error_highlight; const char *prefix; int prefix_length; @@ -186,8 +186,27 @@ struct diff_options { void *output_prefix_data; int diff_path_counter; + + struct emitted_diff_symbols *emitted_symbols; + enum { + COLOR_MOVED_NO = 0, + COLOR_MOVED_PLAIN = 1, + COLOR_MOVED_ZEBRA = 2, + COLOR_MOVED_ZEBRA_DIM = 3, + } color_moved; + #define COLOR_MOVED_DEFAULT COLOR_MOVED_ZEBRA + #define COLOR_MOVED_MIN_ALNUM_COUNT 20 }; +void diff_emit_submodule_del(struct diff_options *o, const char *line); +void diff_emit_submodule_add(struct diff_options *o, const char *line); +void diff_emit_submodule_untracked(struct diff_options *o, const char *path); +void diff_emit_submodule_modified(struct diff_options *o, const char *path); +void diff_emit_submodule_header(struct diff_options *o, const char *header); +void diff_emit_submodule_error(struct diff_options *o, const char *err); +void diff_emit_submodule_pipethrough(struct diff_options *o, + const char *line, int len); + enum color_diff { DIFF_RESET = 0, DIFF_CONTEXT = 1, @@ -197,7 +216,15 @@ enum color_diff { DIFF_FILE_NEW = 5, DIFF_COMMIT = 6, DIFF_WHITESPACE = 7, - DIFF_FUNCINFO = 8 + DIFF_FUNCINFO = 8, + DIFF_FILE_OLD_MOVED = 9, + DIFF_FILE_OLD_MOVED_ALT = 10, + DIFF_FILE_OLD_MOVED_DIM = 11, + DIFF_FILE_OLD_MOVED_ALT_DIM = 12, + DIFF_FILE_NEW_MOVED = 13, + DIFF_FILE_NEW_MOVED_ALT = 14, + DIFF_FILE_NEW_MOVED_DIM = 15, + DIFF_FILE_NEW_MOVED_ALT_DIM = 16 }; const char *diff_get_color(int diff_use_color, enum color_diff ix); #define diff_get_color_opt(o, ix) \ @@ -396,8 +423,8 @@ extern int parse_rename_score(const char **cp_p); extern long parse_algorithm_value(const char *value); -extern int print_stat_summary(FILE *fp, int files, - int insertions, int deletions); +extern void print_stat_summary(FILE *fp, int files, + int insertions, int deletions); extern void setup_diff_pager(struct diff_options *); #endif /* DIFF_H */ @@ -173,8 +173,7 @@ int finish_delayed_checkout(struct checkout *state) dco->state = CE_RETRY; delayed_object_count = dco->paths.nr; - progress = start_progress_delay( - _("Filtering content"), delayed_object_count, 50, 1); + progress = start_delayed_progress(_("Filtering content"), delayed_object_count); while (dco->filters.nr > 0) { for_each_string_list_item(filter, &dco->filters) { struct string_list available_paths = STRING_LIST_INIT_NODUP; diff --git a/fast-import.c b/fast-import.c index a959161b4..49516d60e 100644 --- a/fast-import.c +++ b/fast-import.c @@ -167,6 +167,7 @@ Format of STDIN stream: #include "quote.h" #include "dir.h" #include "run-command.h" +#include "packfile.h" #define PACK_ID_BITS 16 #define MAX_PACK_ID ((1<<PACK_ID_BITS)-1) diff --git a/fetch-pack.c b/fetch-pack.c index fbbc99c88..105506e9a 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -17,6 +17,7 @@ #include "prio-queue.h" #include "sha1-array.h" #include "oidset.h" +#include "packfile.h" static int transfer_unpack_limit = -1; static int fetch_unpack_limit = -1; diff --git a/git-compat-util.h b/git-compat-util.h index 7d2c0ca75..6678b488c 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -749,8 +749,6 @@ const char *inet_ntop(int af, const void *src, char *dst, size_t size); extern int git_atexit(void (*handler)(void)); #endif -extern void release_pack_memory(size_t); - typedef void (*try_to_free_t)(size_t); extern try_to_free_t set_try_to_free_routine(try_to_free_t); diff --git a/git-gui/po/README b/git-gui/po/README index 0f5837d48..2514bc22a 100644 --- a/git-gui/po/README +++ b/git-gui/po/README @@ -165,7 +165,7 @@ to contribute an update. This may be because you would want to improve the translation of existing messages, or because the git-gui software itself was updated and there are new messages that need translation. -In any case, make sure you are up-to-date before starting your work: +In any case, make sure you are up to date before starting your work: $ git checkout master $ git pull diff --git a/git-merge-octopus.sh b/git-merge-octopus.sh index 6c390d6c2..7d19d3795 100755 --- a/git-merge-octopus.sh +++ b/git-merge-octopus.sh @@ -74,7 +74,7 @@ do case "$LF$common$LF" in *"$LF$SHA1$LF"*) - eval_gettextln "Already up-to-date with \$pretty_name" + eval_gettextln "Already up to date with \$pretty_name" continue ;; esac @@ -3614,7 +3614,7 @@ class P4Rebase(Command): def rebase(self): if os.system("git update-index --refresh") != 0: - die("Some files in your working directory are modified and different than what is in your index. You can use git update-index <filename> to bring the index up-to-date or stash away all your changes with git stash."); + die("Some files in your working directory are modified and different than what is in your index. You can use git update-index <filename> to bring the index up to date or stash away all your changes with git stash."); if len(read_pipe("git diff-index HEAD --")) > 0: die("You have uncommitted changes. Please commit them before rebasing or stash them away with git stash."); diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 9208f42ed..959f04b49 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -5967,6 +5967,9 @@ sub git_history_body { $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff"); if ($ftype eq 'blob') { + print " | " . + $cgi->a({-href => href(action=>"blob_plain", hash_base=>$commit, file_name=>$file_name)}, "raw"); + my $blob_current = $file_hash; my $blob_parent = git_get_hash_by_path($commit, $file_name); if (defined $blob_current && defined $blob_parent && diff --git a/http-backend.c b/http-backend.c index 519025d2c..8076b1d5e 100644 --- a/http-backend.c +++ b/http-backend.c @@ -9,6 +9,7 @@ #include "string-list.h" #include "url.h" #include "argv-array.h" +#include "packfile.h" static const char content_type[] = "Content-Type"; static const char content_length[] = "Content-Length"; diff --git a/http-push.c b/http-push.c index c91f40a61..e4c9b065c 100644 --- a/http-push.c +++ b/http-push.c @@ -11,6 +11,7 @@ #include "list-objects.h" #include "sigchain.h" #include "argv-array.h" +#include "packfile.h" #ifdef EXPAT_NEEDS_XMLPARSE_H #include <xmlparse.h> diff --git a/http-walker.c b/http-walker.c index ee049cb13..1ae8363de 100644 --- a/http-walker.c +++ b/http-walker.c @@ -4,6 +4,7 @@ #include "http.h" #include "list.h" #include "transport.h" +#include "packfile.h" struct alt_base { char *base; @@ -11,6 +11,7 @@ #include "pkt-line.h" #include "gettext.h" #include "transport.h" +#include "packfile.h" static struct trace_key trace_curl = TRACE_KEY_INIT(CURL); #if LIBCURL_VERSION_NUM >= 0x070a08 diff --git a/merge-recursive.c b/merge-recursive.c index 1494ffdb8..182626c02 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -1927,7 +1927,7 @@ int merge_trees(struct merge_options *o, } if (oid_eq(&common->object.oid, &merge->object.oid)) { - output(o, 0, _("Already up-to-date!")); + output(o, 0, _("Already up to date!")); *result = head; return 1; } diff --git a/notes-merge.c b/notes-merge.c index c12b354f1..b04d2f213 100644 --- a/notes-merge.c +++ b/notes-merge.c @@ -624,7 +624,7 @@ int notes_merge(struct notes_merge_options *o, if (!oidcmp(&remote->object.oid, base_oid)) { /* Already merged; result == local commit */ if (o->verbosity >= 2) - printf("Already up-to-date!\n"); + printf("Already up to date!\n"); oidcpy(result_oid, &local->object.oid); goto found_result; } @@ -709,7 +709,7 @@ int notes_merge_commit(struct notes_merge_options *o, /* write file as blob, and add to partial_tree */ if (stat(path.buf, &st)) die_errno("Failed to stat '%s'", path.buf); - if (index_path(blob_oid.hash, path.buf, &st, HASH_WRITE_OBJECT)) + if (index_path(&blob_oid, path.buf, &st, HASH_WRITE_OBJECT)) die("Failed to write blob object from '%s'", path.buf); if (add_note(partial_tree, &obj_oid, &blob_oid, NULL)) die("Failed to add resolved note '%s' to notes tree", diff --git a/outgoing/packfile.h b/outgoing/packfile.h new file mode 100644 index 000000000..e69de29bb --- /dev/null +++ b/outgoing/packfile.h diff --git a/pack-bitmap.c b/pack-bitmap.c index 327634cd7..cb3d14ba4 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -9,6 +9,7 @@ #include "pack-bitmap.h" #include "pack-revindex.h" #include "pack-objects.h" +#include "packfile.h" /* * An entry on the bitmap index, representing the bitmap for a given diff --git a/pack-check.c b/pack-check.c index e1fcb228f..073c1fbd4 100644 --- a/pack-check.c +++ b/pack-check.c @@ -2,6 +2,7 @@ #include "pack.h" #include "pack-revindex.h" #include "progress.h" +#include "packfile.h" struct idx_entry { off_t offset; diff --git a/packfile.c b/packfile.c new file mode 100644 index 000000000..f86fa051c --- /dev/null +++ b/packfile.c @@ -0,0 +1,1896 @@ +#include "cache.h" +#include "mru.h" +#include "pack.h" +#include "dir.h" +#include "mergesort.h" +#include "packfile.h" +#include "delta.h" +#include "list.h" +#include "streaming.h" +#include "sha1-lookup.h" + +char *odb_pack_name(struct strbuf *buf, + const unsigned char *sha1, + const char *ext) +{ + strbuf_reset(buf); + strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), + sha1_to_hex(sha1), ext); + return buf->buf; +} + +char *sha1_pack_name(const unsigned char *sha1) +{ + static struct strbuf buf = STRBUF_INIT; + return odb_pack_name(&buf, sha1, "pack"); +} + +char *sha1_pack_index_name(const unsigned char *sha1) +{ + static struct strbuf buf = STRBUF_INIT; + return odb_pack_name(&buf, sha1, "idx"); +} + +static unsigned int pack_used_ctr; +static unsigned int pack_mmap_calls; +static unsigned int peak_pack_open_windows; +static unsigned int pack_open_windows; +static unsigned int pack_open_fds; +static unsigned int pack_max_fds; +static size_t peak_pack_mapped; +static size_t pack_mapped; +struct packed_git *packed_git; + +static struct mru packed_git_mru_storage; +struct mru *packed_git_mru = &packed_git_mru_storage; + +#define SZ_FMT PRIuMAX +static inline uintmax_t sz_fmt(size_t s) { return s; } + +void pack_report(void) +{ + fprintf(stderr, + "pack_report: getpagesize() = %10" SZ_FMT "\n" + "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" + "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", + sz_fmt(getpagesize()), + sz_fmt(packed_git_window_size), + sz_fmt(packed_git_limit)); + fprintf(stderr, + "pack_report: pack_used_ctr = %10u\n" + "pack_report: pack_mmap_calls = %10u\n" + "pack_report: pack_open_windows = %10u / %10u\n" + "pack_report: pack_mapped = " + "%10" SZ_FMT " / %10" SZ_FMT "\n", + pack_used_ctr, + pack_mmap_calls, + pack_open_windows, peak_pack_open_windows, + sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped)); +} + +/* + * Open and mmap the index file at path, perform a couple of + * consistency checks, then record its information to p. Return 0 on + * success. + */ +static int check_packed_git_idx(const char *path, struct packed_git *p) +{ + void *idx_map; + struct pack_idx_header *hdr; + size_t idx_size; + uint32_t version, nr, i, *index; + int fd = git_open(path); + struct stat st; + + if (fd < 0) + return -1; + if (fstat(fd, &st)) { + close(fd); + return -1; + } + idx_size = xsize_t(st.st_size); + if (idx_size < 4 * 256 + 20 + 20) { + close(fd); + return error("index file %s is too small", path); + } + idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + + hdr = idx_map; + if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { + version = ntohl(hdr->idx_version); + if (version < 2 || version > 2) { + munmap(idx_map, idx_size); + return error("index file %s is version %"PRIu32 + " and is not supported by this binary" + " (try upgrading GIT to a newer version)", + path, version); + } + } else + version = 1; + + nr = 0; + index = idx_map; + if (version > 1) + index += 2; /* skip index header */ + for (i = 0; i < 256; i++) { + uint32_t n = ntohl(index[i]); + if (n < nr) { + munmap(idx_map, idx_size); + return error("non-monotonic index %s", path); + } + nr = n; + } + + if (version == 1) { + /* + * Total size: + * - 256 index entries 4 bytes each + * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + */ + if (idx_size != 4*256 + nr * 24 + 20 + 20) { + munmap(idx_map, idx_size); + return error("wrong index v1 file size in %s", path); + } + } else if (version == 2) { + /* + * Minimum size: + * - 8 bytes of header + * - 256 index entries 4 bytes each + * - 20-byte sha1 entry * nr + * - 4-byte crc entry * nr + * - 4-byte offset entry * nr + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + * And after the 4-byte offset table might be a + * variable sized table containing 8-byte entries + * for offsets larger than 2^31. + */ + unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; + unsigned long max_size = min_size; + if (nr) + max_size += (nr - 1)*8; + if (idx_size < min_size || idx_size > max_size) { + munmap(idx_map, idx_size); + return error("wrong index v2 file size in %s", path); + } + if (idx_size != min_size && + /* + * make sure we can deal with large pack offsets. + * 31-bit signed offset won't be enough, neither + * 32-bit unsigned one will be. + */ + (sizeof(off_t) <= 4)) { + munmap(idx_map, idx_size); + return error("pack too large for current definition of off_t in %s", path); + } + } + + p->index_version = version; + p->index_data = idx_map; + p->index_size = idx_size; + p->num_objects = nr; + return 0; +} + +int open_pack_index(struct packed_git *p) +{ + char *idx_name; + size_t len; + int ret; + + if (p->index_data) + return 0; + + if (!strip_suffix(p->pack_name, ".pack", &len)) + die("BUG: pack_name does not end in .pack"); + idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name); + ret = check_packed_git_idx(idx_name, p); + free(idx_name); + return ret; +} + +static struct packed_git *alloc_packed_git(int extra) +{ + struct packed_git *p = xmalloc(st_add(sizeof(*p), extra)); + memset(p, 0, sizeof(*p)); + p->pack_fd = -1; + return p; +} + +struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) +{ + const char *path = sha1_pack_name(sha1); + size_t alloc = st_add(strlen(path), 1); + struct packed_git *p = alloc_packed_git(alloc); + + memcpy(p->pack_name, path, alloc); /* includes NUL */ + hashcpy(p->sha1, sha1); + if (check_packed_git_idx(idx_path, p)) { + free(p); + return NULL; + } + + return p; +} + +static void scan_windows(struct packed_git *p, + struct packed_git **lru_p, + struct pack_window **lru_w, + struct pack_window **lru_l) +{ + struct pack_window *w, *w_l; + + for (w_l = NULL, w = p->windows; w; w = w->next) { + if (!w->inuse_cnt) { + if (!*lru_w || w->last_used < (*lru_w)->last_used) { + *lru_p = p; + *lru_w = w; + *lru_l = w_l; + } + } + w_l = w; + } +} + +static int unuse_one_window(struct packed_git *current) +{ + struct packed_git *p, *lru_p = NULL; + struct pack_window *lru_w = NULL, *lru_l = NULL; + + if (current) + scan_windows(current, &lru_p, &lru_w, &lru_l); + for (p = packed_git; p; p = p->next) + scan_windows(p, &lru_p, &lru_w, &lru_l); + if (lru_p) { + munmap(lru_w->base, lru_w->len); + pack_mapped -= lru_w->len; + if (lru_l) + lru_l->next = lru_w->next; + else + lru_p->windows = lru_w->next; + free(lru_w); + pack_open_windows--; + return 1; + } + return 0; +} + +void release_pack_memory(size_t need) +{ + size_t cur = pack_mapped; + while (need >= (cur - pack_mapped) && unuse_one_window(NULL)) + ; /* nothing */ +} + +void close_pack_windows(struct packed_git *p) +{ + while (p->windows) { + struct pack_window *w = p->windows; + + if (w->inuse_cnt) + die("pack '%s' still has open windows to it", + p->pack_name); + munmap(w->base, w->len); + pack_mapped -= w->len; + pack_open_windows--; + p->windows = w->next; + free(w); + } +} + +static int close_pack_fd(struct packed_git *p) +{ + if (p->pack_fd < 0) + return 0; + + close(p->pack_fd); + pack_open_fds--; + p->pack_fd = -1; + + return 1; +} + +void close_pack_index(struct packed_git *p) +{ + if (p->index_data) { + munmap((void *)p->index_data, p->index_size); + p->index_data = NULL; + } +} + +static void close_pack(struct packed_git *p) +{ + close_pack_windows(p); + close_pack_fd(p); + close_pack_index(p); +} + +void close_all_packs(void) +{ + struct packed_git *p; + + for (p = packed_git; p; p = p->next) + if (p->do_not_close) + die("BUG: want to close pack marked 'do-not-close'"); + else + close_pack(p); +} + +/* + * The LRU pack is the one with the oldest MRU window, preferring packs + * with no used windows, or the oldest mtime if it has no windows allocated. + */ +static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse) +{ + struct pack_window *w, *this_mru_w; + int has_windows_inuse = 0; + + /* + * Reject this pack if it has windows and the previously selected + * one does not. If this pack does not have windows, reject + * it if the pack file is newer than the previously selected one. + */ + if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime)) + return; + + for (w = this_mru_w = p->windows; w; w = w->next) { + /* + * Reject this pack if any of its windows are in use, + * but the previously selected pack did not have any + * inuse windows. Otherwise, record that this pack + * has windows in use. + */ + if (w->inuse_cnt) { + if (*accept_windows_inuse) + has_windows_inuse = 1; + else + return; + } + + if (w->last_used > this_mru_w->last_used) + this_mru_w = w; + + /* + * Reject this pack if it has windows that have been + * used more recently than the previously selected pack. + * If the previously selected pack had windows inuse and + * we have not encountered a window in this pack that is + * inuse, skip this check since we prefer a pack with no + * inuse windows to one that has inuse windows. + */ + if (*mru_w && *accept_windows_inuse == has_windows_inuse && + this_mru_w->last_used > (*mru_w)->last_used) + return; + } + + /* + * Select this pack. + */ + *mru_w = this_mru_w; + *lru_p = p; + *accept_windows_inuse = has_windows_inuse; +} + +static int close_one_pack(void) +{ + struct packed_git *p, *lru_p = NULL; + struct pack_window *mru_w = NULL; + int accept_windows_inuse = 1; + + for (p = packed_git; p; p = p->next) { + if (p->pack_fd == -1) + continue; + find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); + } + + if (lru_p) + return close_pack_fd(lru_p); + + return 0; +} + +static unsigned int get_max_fd_limit(void) +{ +#ifdef RLIMIT_NOFILE + { + struct rlimit lim; + + if (!getrlimit(RLIMIT_NOFILE, &lim)) + return lim.rlim_cur; + } +#endif + +#ifdef _SC_OPEN_MAX + { + long open_max = sysconf(_SC_OPEN_MAX); + if (0 < open_max) + return open_max; + /* + * Otherwise, we got -1 for one of the two + * reasons: + * + * (1) sysconf() did not understand _SC_OPEN_MAX + * and signaled an error with -1; or + * (2) sysconf() said there is no limit. + * + * We _could_ clear errno before calling sysconf() to + * tell these two cases apart and return a huge number + * in the latter case to let the caller cap it to a + * value that is not so selfish, but letting the + * fallback OPEN_MAX codepath take care of these cases + * is a lot simpler. + */ + } +#endif + +#ifdef OPEN_MAX + return OPEN_MAX; +#else + return 1; /* see the caller ;-) */ +#endif +} + +/* + * Do not call this directly as this leaks p->pack_fd on error return; + * call open_packed_git() instead. + */ +static int open_packed_git_1(struct packed_git *p) +{ + struct stat st; + struct pack_header hdr; + unsigned char sha1[20]; + unsigned char *idx_sha1; + long fd_flag; + + if (!p->index_data && open_pack_index(p)) + return error("packfile %s index unavailable", p->pack_name); + + if (!pack_max_fds) { + unsigned int max_fds = get_max_fd_limit(); + + /* Save 3 for stdin/stdout/stderr, 22 for work */ + if (25 < max_fds) + pack_max_fds = max_fds - 25; + else + pack_max_fds = 1; + } + + while (pack_max_fds <= pack_open_fds && close_one_pack()) + ; /* nothing */ + + p->pack_fd = git_open(p->pack_name); + if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) + return -1; + pack_open_fds++; + + /* If we created the struct before we had the pack we lack size. */ + if (!p->pack_size) { + if (!S_ISREG(st.st_mode)) + return error("packfile %s not a regular file", p->pack_name); + p->pack_size = st.st_size; + } else if (p->pack_size != st.st_size) + return error("packfile %s size changed", p->pack_name); + + /* We leave these file descriptors open with sliding mmap; + * there is no point keeping them open across exec(), though. + */ + fd_flag = fcntl(p->pack_fd, F_GETFD, 0); + if (fd_flag < 0) + return error("cannot determine file descriptor flags"); + fd_flag |= FD_CLOEXEC; + if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) + return error("cannot set FD_CLOEXEC"); + + /* Verify we recognize this pack file format. */ + if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) + return error("file %s is far too short to be a packfile", p->pack_name); + if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) + return error("file %s is not a GIT packfile", p->pack_name); + if (!pack_version_ok(hdr.hdr_version)) + return error("packfile %s is version %"PRIu32" and not" + " supported (try upgrading GIT to a newer version)", + p->pack_name, ntohl(hdr.hdr_version)); + + /* Verify the pack matches its index. */ + if (p->num_objects != ntohl(hdr.hdr_entries)) + return error("packfile %s claims to have %"PRIu32" objects" + " while index indicates %"PRIu32" objects", + p->pack_name, ntohl(hdr.hdr_entries), + p->num_objects); + if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) + return error("end of packfile %s is unavailable", p->pack_name); + if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) + return error("packfile %s signature is unavailable", p->pack_name); + idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40; + if (hashcmp(sha1, idx_sha1)) + return error("packfile %s does not match index", p->pack_name); + return 0; +} + +static int open_packed_git(struct packed_git *p) +{ + if (!open_packed_git_1(p)) + return 0; + close_pack_fd(p); + return -1; +} + +static int in_window(struct pack_window *win, off_t offset) +{ + /* We must promise at least 20 bytes (one hash) after the + * offset is available from this window, otherwise the offset + * is not actually in this window and a different window (which + * has that one hash excess) must be used. This is to support + * the object header and delta base parsing routines below. + */ + off_t win_off = win->offset; + return win_off <= offset + && (offset + 20) <= (win_off + win->len); +} + +unsigned char *use_pack(struct packed_git *p, + struct pack_window **w_cursor, + off_t offset, + unsigned long *left) +{ + struct pack_window *win = *w_cursor; + + /* Since packfiles end in a hash of their content and it's + * pointless to ask for an offset into the middle of that + * hash, and the in_window function above wouldn't match + * don't allow an offset too close to the end of the file. + */ + if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) + die("packfile %s cannot be accessed", p->pack_name); + if (offset > (p->pack_size - 20)) + die("offset beyond end of packfile (truncated pack?)"); + if (offset < 0) + die(_("offset before end of packfile (broken .idx?)")); + + if (!win || !in_window(win, offset)) { + if (win) + win->inuse_cnt--; + for (win = p->windows; win; win = win->next) { + if (in_window(win, offset)) + break; + } + if (!win) { + size_t window_align = packed_git_window_size / 2; + off_t len; + + if (p->pack_fd == -1 && open_packed_git(p)) + die("packfile %s cannot be accessed", p->pack_name); + + win = xcalloc(1, sizeof(*win)); + win->offset = (offset / window_align) * window_align; + len = p->pack_size - win->offset; + if (len > packed_git_window_size) + len = packed_git_window_size; + win->len = (size_t)len; + pack_mapped += win->len; + while (packed_git_limit < pack_mapped + && unuse_one_window(p)) + ; /* nothing */ + win->base = xmmap(NULL, win->len, + PROT_READ, MAP_PRIVATE, + p->pack_fd, win->offset); + if (win->base == MAP_FAILED) + die_errno("packfile %s cannot be mapped", + p->pack_name); + if (!win->offset && win->len == p->pack_size + && !p->do_not_close) + close_pack_fd(p); + pack_mmap_calls++; + pack_open_windows++; + if (pack_mapped > peak_pack_mapped) + peak_pack_mapped = pack_mapped; + if (pack_open_windows > peak_pack_open_windows) + peak_pack_open_windows = pack_open_windows; + win->next = p->windows; + p->windows = win; + } + } + if (win != *w_cursor) { + win->last_used = pack_used_ctr++; + win->inuse_cnt++; + *w_cursor = win; + } + offset -= win->offset; + if (left) + *left = win->len - xsize_t(offset); + return win->base + offset; +} + +void unuse_pack(struct pack_window **w_cursor) +{ + struct pack_window *w = *w_cursor; + if (w) { + w->inuse_cnt--; + *w_cursor = NULL; + } +} + +static void try_to_free_pack_memory(size_t size) +{ + release_pack_memory(size); +} + +struct packed_git *add_packed_git(const char *path, size_t path_len, int local) +{ + static int have_set_try_to_free_routine; + struct stat st; + size_t alloc; + struct packed_git *p; + + if (!have_set_try_to_free_routine) { + have_set_try_to_free_routine = 1; + set_try_to_free_routine(try_to_free_pack_memory); + } + + /* + * Make sure a corresponding .pack file exists and that + * the index looks sane. + */ + if (!strip_suffix_mem(path, &path_len, ".idx")) + return NULL; + + /* + * ".pack" is long enough to hold any suffix we're adding (and + * the use xsnprintf double-checks that) + */ + alloc = st_add3(path_len, strlen(".pack"), 1); + p = alloc_packed_git(alloc); + memcpy(p->pack_name, path, path_len); + + xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); + if (!access(p->pack_name, F_OK)) + p->pack_keep = 1; + + xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); + if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { + free(p); + return NULL; + } + + /* ok, it looks sane as far as we can check without + * actually mapping the pack file. + */ + p->pack_size = st.st_size; + p->pack_local = local; + p->mtime = st.st_mtime; + if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) + hashclr(p->sha1); + return p; +} + +void install_packed_git(struct packed_git *pack) +{ + if (pack->pack_fd != -1) + pack_open_fds++; + + pack->next = packed_git; + packed_git = pack; +} + +void (*report_garbage)(unsigned seen_bits, const char *path); + +static void report_helper(const struct string_list *list, + int seen_bits, int first, int last) +{ + if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX)) + return; + + for (; first < last; first++) + report_garbage(seen_bits, list->items[first].string); +} + +static void report_pack_garbage(struct string_list *list) +{ + int i, baselen = -1, first = 0, seen_bits = 0; + + if (!report_garbage) + return; + + string_list_sort(list); + + for (i = 0; i < list->nr; i++) { + const char *path = list->items[i].string; + if (baselen != -1 && + strncmp(path, list->items[first].string, baselen)) { + report_helper(list, seen_bits, first, i); + baselen = -1; + seen_bits = 0; + } + if (baselen == -1) { + const char *dot = strrchr(path, '.'); + if (!dot) { + report_garbage(PACKDIR_FILE_GARBAGE, path); + continue; + } + baselen = dot - path + 1; + first = i; + } + if (!strcmp(path + baselen, "pack")) + seen_bits |= 1; + else if (!strcmp(path + baselen, "idx")) + seen_bits |= 2; + } + report_helper(list, seen_bits, first, list->nr); +} + +static void prepare_packed_git_one(char *objdir, int local) +{ + struct strbuf path = STRBUF_INIT; + size_t dirnamelen; + DIR *dir; + struct dirent *de; + struct string_list garbage = STRING_LIST_INIT_DUP; + + strbuf_addstr(&path, objdir); + strbuf_addstr(&path, "/pack"); + dir = opendir(path.buf); + if (!dir) { + if (errno != ENOENT) + error_errno("unable to open object pack directory: %s", + path.buf); + strbuf_release(&path); + return; + } + strbuf_addch(&path, '/'); + dirnamelen = path.len; + while ((de = readdir(dir)) != NULL) { + struct packed_git *p; + size_t base_len; + + if (is_dot_or_dotdot(de->d_name)) + continue; + + strbuf_setlen(&path, dirnamelen); + strbuf_addstr(&path, de->d_name); + + base_len = path.len; + if (strip_suffix_mem(path.buf, &base_len, ".idx")) { + /* Don't reopen a pack we already have. */ + for (p = packed_git; p; p = p->next) { + size_t len; + if (strip_suffix(p->pack_name, ".pack", &len) && + len == base_len && + !memcmp(p->pack_name, path.buf, len)) + break; + } + if (p == NULL && + /* + * See if it really is a valid .idx file with + * corresponding .pack file that we can map. + */ + (p = add_packed_git(path.buf, path.len, local)) != NULL) + install_packed_git(p); + } + + if (!report_garbage) + continue; + + if (ends_with(de->d_name, ".idx") || + ends_with(de->d_name, ".pack") || + ends_with(de->d_name, ".bitmap") || + ends_with(de->d_name, ".keep")) + string_list_append(&garbage, path.buf); + else + report_garbage(PACKDIR_FILE_GARBAGE, path.buf); + } + closedir(dir); + report_pack_garbage(&garbage); + string_list_clear(&garbage, 0); + strbuf_release(&path); +} + +static int approximate_object_count_valid; + +/* + * Give a fast, rough count of the number of objects in the repository. This + * ignores loose objects completely. If you have a lot of them, then either + * you should repack because your performance will be awful, or they are + * all unreachable objects about to be pruned, in which case they're not really + * interesting as a measure of repo size in the first place. + */ +unsigned long approximate_object_count(void) +{ + static unsigned long count; + if (!approximate_object_count_valid) { + struct packed_git *p; + + prepare_packed_git(); + count = 0; + for (p = packed_git; p; p = p->next) { + if (open_pack_index(p)) + continue; + count += p->num_objects; + } + } + return count; +} + +static void *get_next_packed_git(const void *p) +{ + return ((const struct packed_git *)p)->next; +} + +static void set_next_packed_git(void *p, void *next) +{ + ((struct packed_git *)p)->next = next; +} + +static int sort_pack(const void *a_, const void *b_) +{ + const struct packed_git *a = a_; + const struct packed_git *b = b_; + int st; + + /* + * Local packs tend to contain objects specific to our + * variant of the project than remote ones. In addition, + * remote ones could be on a network mounted filesystem. + * Favor local ones for these reasons. + */ + st = a->pack_local - b->pack_local; + if (st) + return -st; + + /* + * Younger packs tend to contain more recent objects, + * and more recent objects tend to get accessed more + * often. + */ + if (a->mtime < b->mtime) + return 1; + else if (a->mtime == b->mtime) + return 0; + return -1; +} + +static void rearrange_packed_git(void) +{ + packed_git = llist_mergesort(packed_git, get_next_packed_git, + set_next_packed_git, sort_pack); +} + +static void prepare_packed_git_mru(void) +{ + struct packed_git *p; + + mru_clear(packed_git_mru); + for (p = packed_git; p; p = p->next) + mru_append(packed_git_mru, p); +} + +static int prepare_packed_git_run_once = 0; +void prepare_packed_git(void) +{ + struct alternate_object_database *alt; + + if (prepare_packed_git_run_once) + return; + prepare_packed_git_one(get_object_directory(), 1); + prepare_alt_odb(); + for (alt = alt_odb_list; alt; alt = alt->next) + prepare_packed_git_one(alt->path, 0); + rearrange_packed_git(); + prepare_packed_git_mru(); + prepare_packed_git_run_once = 1; +} + +void reprepare_packed_git(void) +{ + approximate_object_count_valid = 0; + prepare_packed_git_run_once = 0; + prepare_packed_git(); +} + +unsigned long unpack_object_header_buffer(const unsigned char *buf, + unsigned long len, enum object_type *type, unsigned long *sizep) +{ + unsigned shift; + unsigned long size, c; + unsigned long used = 0; + + c = buf[used++]; + *type = (c >> 4) & 7; + size = c & 15; + shift = 4; + while (c & 0x80) { + if (len <= used || bitsizeof(long) <= shift) { + error("bad object header"); + size = used = 0; + break; + } + c = buf[used++]; + size += (c & 0x7f) << shift; + shift += 7; + } + *sizep = size; + return used; +} + +unsigned long get_size_from_delta(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos) +{ + const unsigned char *data; + unsigned char delta_head[20], *in; + git_zstream stream; + int st; + + memset(&stream, 0, sizeof(stream)); + stream.next_out = delta_head; + stream.avail_out = sizeof(delta_head); + + git_inflate_init(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = git_inflate(&stream, Z_FINISH); + curpos += stream.next_in - in; + } while ((st == Z_OK || st == Z_BUF_ERROR) && + stream.total_out < sizeof(delta_head)); + git_inflate_end(&stream); + if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) { + error("delta data unpack-initial failed"); + return 0; + } + + /* Examine the initial part of the delta to figure out + * the result size. + */ + data = delta_head; + + /* ignore base size */ + get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); + + /* Read the result size */ + return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); +} + +int unpack_object_header(struct packed_git *p, + struct pack_window **w_curs, + off_t *curpos, + unsigned long *sizep) +{ + unsigned char *base; + unsigned long left; + unsigned long used; + enum object_type type; + + /* use_pack() assures us we have [base, base + 20) available + * as a range that we can look at. (Its actually the hash + * size that is assured.) With our object header encoding + * the maximum deflated object size is 2^137, which is just + * insane, so we know won't exceed what we have been given. + */ + base = use_pack(p, w_curs, *curpos, &left); + used = unpack_object_header_buffer(base, left, &type, sizep); + if (!used) { + type = OBJ_BAD; + } else + *curpos += used; + + return type; +} + +void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1) +{ + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i)) + return; + p->bad_object_sha1 = xrealloc(p->bad_object_sha1, + st_mult(GIT_MAX_RAWSZ, + st_add(p->num_bad_objects, 1))); + hashcpy(p->bad_object_sha1 + GIT_SHA1_RAWSZ * p->num_bad_objects, sha1); + p->num_bad_objects++; +} + +const struct packed_git *has_packed_and_bad(const unsigned char *sha1) +{ + struct packed_git *p; + unsigned i; + + for (p = packed_git; p; p = p->next) + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return p; + return NULL; +} + +static off_t get_delta_base(struct packed_git *p, + struct pack_window **w_curs, + off_t *curpos, + enum object_type type, + off_t delta_obj_offset) +{ + unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL); + off_t base_offset; + + /* use_pack() assured us we have [base_info, base_info + 20) + * as a range that we can look at without walking off the + * end of the mapped window. Its actually the hash size + * that is assured. An OFS_DELTA longer than the hash size + * is stupid, as then a REF_DELTA would be smaller to store. + */ + if (type == OBJ_OFS_DELTA) { + unsigned used = 0; + unsigned char c = base_info[used++]; + base_offset = c & 127; + while (c & 128) { + base_offset += 1; + if (!base_offset || MSB(base_offset, 7)) + return 0; /* overflow */ + c = base_info[used++]; + base_offset = (base_offset << 7) + (c & 127); + } + base_offset = delta_obj_offset - base_offset; + if (base_offset <= 0 || base_offset >= delta_obj_offset) + return 0; /* out of bound */ + *curpos += used; + } else if (type == OBJ_REF_DELTA) { + /* The base entry _must_ be in the same pack */ + base_offset = find_pack_entry_one(base_info, p); + *curpos += 20; + } else + die("I am totally screwed"); + return base_offset; +} + +/* + * Like get_delta_base above, but we return the sha1 instead of the pack + * offset. This means it is cheaper for REF deltas (we do not have to do + * the final object lookup), but more expensive for OFS deltas (we + * have to load the revidx to convert the offset back into a sha1). + */ +static const unsigned char *get_delta_base_sha1(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + enum object_type type, + off_t delta_obj_offset) +{ + if (type == OBJ_REF_DELTA) { + unsigned char *base = use_pack(p, w_curs, curpos, NULL); + return base; + } else if (type == OBJ_OFS_DELTA) { + struct revindex_entry *revidx; + off_t base_offset = get_delta_base(p, w_curs, &curpos, + type, delta_obj_offset); + + if (!base_offset) + return NULL; + + revidx = find_pack_revindex(p, base_offset); + if (!revidx) + return NULL; + + return nth_packed_object_sha1(p, revidx->nr); + } else + return NULL; +} + +static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) +{ + int type; + struct revindex_entry *revidx; + const unsigned char *sha1; + revidx = find_pack_revindex(p, obj_offset); + if (!revidx) + return OBJ_BAD; + sha1 = nth_packed_object_sha1(p, revidx->nr); + mark_bad_packed_object(p, sha1); + type = sha1_object_info(sha1, NULL); + if (type <= OBJ_NONE) + return OBJ_BAD; + return type; +} + +#define POI_STACK_PREALLOC 64 + +static enum object_type packed_to_object_type(struct packed_git *p, + off_t obj_offset, + enum object_type type, + struct pack_window **w_curs, + off_t curpos) +{ + off_t small_poi_stack[POI_STACK_PREALLOC]; + off_t *poi_stack = small_poi_stack; + int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC; + + while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + off_t base_offset; + unsigned long size; + /* Push the object we're going to leave behind */ + if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) { + poi_stack_alloc = alloc_nr(poi_stack_nr); + ALLOC_ARRAY(poi_stack, poi_stack_alloc); + memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr); + } else { + ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc); + } + poi_stack[poi_stack_nr++] = obj_offset; + /* If parsing the base offset fails, just unwind */ + base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); + if (!base_offset) + goto unwind; + curpos = obj_offset = base_offset; + type = unpack_object_header(p, w_curs, &curpos, &size); + if (type <= OBJ_NONE) { + /* If getting the base itself fails, we first + * retry the base, otherwise unwind */ + type = retry_bad_packed_offset(p, base_offset); + if (type > OBJ_NONE) + goto out; + goto unwind; + } + } + + switch (type) { + case OBJ_BAD: + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + break; + default: + error("unknown object type %i at offset %"PRIuMAX" in %s", + type, (uintmax_t)obj_offset, p->pack_name); + type = OBJ_BAD; + } + +out: + if (poi_stack != small_poi_stack) + free(poi_stack); + return type; + +unwind: + while (poi_stack_nr) { + obj_offset = poi_stack[--poi_stack_nr]; + type = retry_bad_packed_offset(p, obj_offset); + if (type > OBJ_NONE) + goto out; + } + type = OBJ_BAD; + goto out; +} + +static struct hashmap delta_base_cache; +static size_t delta_base_cached; + +static LIST_HEAD(delta_base_cache_lru); + +struct delta_base_cache_key { + struct packed_git *p; + off_t base_offset; +}; + +struct delta_base_cache_entry { + struct hashmap hash; + struct delta_base_cache_key key; + struct list_head lru; + void *data; + unsigned long size; + enum object_type type; +}; + +static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset) +{ + unsigned int hash; + + hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset; + hash += (hash >> 8) + (hash >> 16); + return hash; +} + +static struct delta_base_cache_entry * +get_delta_base_cache_entry(struct packed_git *p, off_t base_offset) +{ + struct hashmap_entry entry; + struct delta_base_cache_key key; + + if (!delta_base_cache.cmpfn) + return NULL; + + hashmap_entry_init(&entry, pack_entry_hash(p, base_offset)); + key.p = p; + key.base_offset = base_offset; + return hashmap_get(&delta_base_cache, &entry, &key); +} + +static int delta_base_cache_key_eq(const struct delta_base_cache_key *a, + const struct delta_base_cache_key *b) +{ + return a->p == b->p && a->base_offset == b->base_offset; +} + +static int delta_base_cache_hash_cmp(const void *unused_cmp_data, + const void *va, const void *vb, + const void *vkey) +{ + const struct delta_base_cache_entry *a = va, *b = vb; + const struct delta_base_cache_key *key = vkey; + if (key) + return !delta_base_cache_key_eq(&a->key, key); + else + return !delta_base_cache_key_eq(&a->key, &b->key); +} + +static int in_delta_base_cache(struct packed_git *p, off_t base_offset) +{ + return !!get_delta_base_cache_entry(p, base_offset); +} + +/* + * Remove the entry from the cache, but do _not_ free the associated + * entry data. The caller takes ownership of the "data" buffer, and + * should copy out any fields it wants before detaching. + */ +static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent) +{ + hashmap_remove(&delta_base_cache, ent, &ent->key); + list_del(&ent->lru); + delta_base_cached -= ent->size; + free(ent); +} + +static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, + unsigned long *base_size, enum object_type *type) +{ + struct delta_base_cache_entry *ent; + + ent = get_delta_base_cache_entry(p, base_offset); + if (!ent) + return unpack_entry(p, base_offset, type, base_size); + + if (type) + *type = ent->type; + if (base_size) + *base_size = ent->size; + return xmemdupz(ent->data, ent->size); +} + +static inline void release_delta_base_cache(struct delta_base_cache_entry *ent) +{ + free(ent->data); + detach_delta_base_cache_entry(ent); +} + +void clear_delta_base_cache(void) +{ + struct list_head *lru, *tmp; + list_for_each_safe(lru, tmp, &delta_base_cache_lru) { + struct delta_base_cache_entry *entry = + list_entry(lru, struct delta_base_cache_entry, lru); + release_delta_base_cache(entry); + } +} + +static void add_delta_base_cache(struct packed_git *p, off_t base_offset, + void *base, unsigned long base_size, enum object_type type) +{ + struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent)); + struct list_head *lru, *tmp; + + delta_base_cached += base_size; + + list_for_each_safe(lru, tmp, &delta_base_cache_lru) { + struct delta_base_cache_entry *f = + list_entry(lru, struct delta_base_cache_entry, lru); + if (delta_base_cached <= delta_base_cache_limit) + break; + release_delta_base_cache(f); + } + + ent->key.p = p; + ent->key.base_offset = base_offset; + ent->type = type; + ent->data = base; + ent->size = base_size; + list_add_tail(&ent->lru, &delta_base_cache_lru); + + if (!delta_base_cache.cmpfn) + hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0); + hashmap_entry_init(ent, pack_entry_hash(p, base_offset)); + hashmap_add(&delta_base_cache, ent); +} + +int packed_object_info(struct packed_git *p, off_t obj_offset, + struct object_info *oi) +{ + struct pack_window *w_curs = NULL; + unsigned long size; + off_t curpos = obj_offset; + enum object_type type; + + /* + * We always get the representation type, but only convert it to + * a "real" type later if the caller is interested. + */ + if (oi->contentp) { + *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep, + &type); + if (!*oi->contentp) + type = OBJ_BAD; + } else { + type = unpack_object_header(p, &w_curs, &curpos, &size); + } + + if (!oi->contentp && oi->sizep) { + if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + off_t tmp_pos = curpos; + off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos, + type, obj_offset); + if (!base_offset) { + type = OBJ_BAD; + goto out; + } + *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos); + if (*oi->sizep == 0) { + type = OBJ_BAD; + goto out; + } + } else { + *oi->sizep = size; + } + } + + if (oi->disk_sizep) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + *oi->disk_sizep = revidx[1].offset - obj_offset; + } + + if (oi->typep || oi->typename) { + enum object_type ptot; + ptot = packed_to_object_type(p, obj_offset, type, &w_curs, + curpos); + if (oi->typep) + *oi->typep = ptot; + if (oi->typename) { + const char *tn = typename(ptot); + if (tn) + strbuf_addstr(oi->typename, tn); + } + if (ptot < 0) { + type = OBJ_BAD; + goto out; + } + } + + if (oi->delta_base_sha1) { + if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + const unsigned char *base; + + base = get_delta_base_sha1(p, &w_curs, curpos, + type, obj_offset); + if (!base) { + type = OBJ_BAD; + goto out; + } + + hashcpy(oi->delta_base_sha1, base); + } else + hashclr(oi->delta_base_sha1); + } + + oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED : + OI_PACKED; + +out: + unuse_pack(&w_curs); + return type; +} + +static void *unpack_compressed_entry(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + unsigned long size) +{ + int st; + git_zstream stream; + unsigned char *buffer, *in; + + buffer = xmallocz_gently(size); + if (!buffer) + return NULL; + memset(&stream, 0, sizeof(stream)); + stream.next_out = buffer; + stream.avail_out = size + 1; + + git_inflate_init(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = git_inflate(&stream, Z_FINISH); + if (!stream.avail_out) + break; /* the payload is larger than it should be */ + curpos += stream.next_in - in; + } while (st == Z_OK || st == Z_BUF_ERROR); + git_inflate_end(&stream); + if ((st != Z_STREAM_END) || stream.total_out != size) { + free(buffer); + return NULL; + } + + return buffer; +} + +static void write_pack_access_log(struct packed_git *p, off_t obj_offset) +{ + static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS); + trace_printf_key(&pack_access, "%s %"PRIuMAX"\n", + p->pack_name, (uintmax_t)obj_offset); +} + +int do_check_packed_object_crc; + +#define UNPACK_ENTRY_STACK_PREALLOC 64 +struct unpack_entry_stack_ent { + off_t obj_offset; + off_t curpos; + unsigned long size; +}; + +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) +{ + struct object_info oi = OBJECT_INFO_INIT; + void *content; + oi.typep = type; + oi.sizep = size; + oi.contentp = &content; + + if (sha1_object_info_extended(sha1, &oi, 0) < 0) + return NULL; + return content; +} + +void *unpack_entry(struct packed_git *p, off_t obj_offset, + enum object_type *final_type, unsigned long *final_size) +{ + struct pack_window *w_curs = NULL; + off_t curpos = obj_offset; + void *data = NULL; + unsigned long size; + enum object_type type; + struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC]; + struct unpack_entry_stack_ent *delta_stack = small_delta_stack; + int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC; + int base_from_cache = 0; + + write_pack_access_log(p, obj_offset); + + /* PHASE 1: drill down to the innermost base object */ + for (;;) { + off_t base_offset; + int i; + struct delta_base_cache_entry *ent; + + ent = get_delta_base_cache_entry(p, curpos); + if (ent) { + type = ent->type; + data = ent->data; + size = ent->size; + detach_delta_base_cache_entry(ent); + base_from_cache = 1; + break; + } + + if (do_check_packed_object_crc && p->index_version > 1) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + off_t len = revidx[1].offset - obj_offset; + if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) { + const unsigned char *sha1 = + nth_packed_object_sha1(p, revidx->nr); + error("bad packed object CRC for %s", + sha1_to_hex(sha1)); + mark_bad_packed_object(p, sha1); + data = NULL; + goto out; + } + } + + type = unpack_object_header(p, &w_curs, &curpos, &size); + if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA) + break; + + base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); + if (!base_offset) { + error("failed to validate delta base reference " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + /* bail to phase 2, in hopes of recovery */ + data = NULL; + break; + } + + /* push object, proceed to base */ + if (delta_stack_nr >= delta_stack_alloc + && delta_stack == small_delta_stack) { + delta_stack_alloc = alloc_nr(delta_stack_nr); + ALLOC_ARRAY(delta_stack, delta_stack_alloc); + memcpy(delta_stack, small_delta_stack, + sizeof(*delta_stack)*delta_stack_nr); + } else { + ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc); + } + i = delta_stack_nr++; + delta_stack[i].obj_offset = obj_offset; + delta_stack[i].curpos = curpos; + delta_stack[i].size = size; + + curpos = obj_offset = base_offset; + } + + /* PHASE 2: handle the base */ + switch (type) { + case OBJ_OFS_DELTA: + case OBJ_REF_DELTA: + if (data) + die("BUG: unpack_entry: left loop at a valid delta"); + break; + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + if (!base_from_cache) + data = unpack_compressed_entry(p, &w_curs, curpos, size); + break; + default: + data = NULL; + error("unknown object type %i at offset %"PRIuMAX" in %s", + type, (uintmax_t)obj_offset, p->pack_name); + } + + /* PHASE 3: apply deltas in order */ + + /* invariants: + * 'data' holds the base data, or NULL if there was corruption + */ + while (delta_stack_nr) { + void *delta_data; + void *base = data; + void *external_base = NULL; + unsigned long delta_size, base_size = size; + int i; + + data = NULL; + + if (base) + add_delta_base_cache(p, obj_offset, base, base_size, type); + + if (!base) { + /* + * We're probably in deep shit, but let's try to fetch + * the required base anyway from another pack or loose. + * This is costly but should happen only in the presence + * of a corrupted pack, and is better than failing outright. + */ + struct revindex_entry *revidx; + const unsigned char *base_sha1; + revidx = find_pack_revindex(p, obj_offset); + if (revidx) { + base_sha1 = nth_packed_object_sha1(p, revidx->nr); + error("failed to read delta base object %s" + " at offset %"PRIuMAX" from %s", + sha1_to_hex(base_sha1), (uintmax_t)obj_offset, + p->pack_name); + mark_bad_packed_object(p, base_sha1); + base = read_object(base_sha1, &type, &base_size); + external_base = base; + } + } + + i = --delta_stack_nr; + obj_offset = delta_stack[i].obj_offset; + curpos = delta_stack[i].curpos; + delta_size = delta_stack[i].size; + + if (!base) + continue; + + delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size); + + if (!delta_data) { + error("failed to unpack compressed delta " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + data = NULL; + free(external_base); + continue; + } + + data = patch_delta(base, base_size, + delta_data, delta_size, + &size); + + /* + * We could not apply the delta; warn the user, but keep going. + * Our failure will be noticed either in the next iteration of + * the loop, or if this is the final delta, in the caller when + * we return NULL. Those code paths will take care of making + * a more explicit warning and retrying with another copy of + * the object. + */ + if (!data) + error("failed to apply delta"); + + free(delta_data); + free(external_base); + } + + if (final_type) + *final_type = type; + if (final_size) + *final_size = size; + +out: + unuse_pack(&w_curs); + + if (delta_stack != small_delta_stack) + free(delta_stack); + + return data; +} + +const unsigned char *nth_packed_object_sha1(struct packed_git *p, + uint32_t n) +{ + const unsigned char *index = p->index_data; + if (!index) { + if (open_pack_index(p)) + return NULL; + index = p->index_data; + } + if (n >= p->num_objects) + return NULL; + index += 4 * 256; + if (p->index_version == 1) { + return index + 24 * n + 4; + } else { + index += 8; + return index + 20 * n; + } +} + +const struct object_id *nth_packed_object_oid(struct object_id *oid, + struct packed_git *p, + uint32_t n) +{ + const unsigned char *hash = nth_packed_object_sha1(p, n); + if (!hash) + return NULL; + hashcpy(oid->hash, hash); + return oid; +} + +void check_pack_index_ptr(const struct packed_git *p, const void *vptr) +{ + const unsigned char *ptr = vptr; + const unsigned char *start = p->index_data; + const unsigned char *end = start + p->index_size; + if (ptr < start) + die(_("offset before start of pack index for %s (corrupt index?)"), + p->pack_name); + /* No need to check for underflow; .idx files must be at least 8 bytes */ + if (ptr >= end - 8) + die(_("offset beyond end of pack index for %s (truncated index?)"), + p->pack_name); +} + +off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) +{ + const unsigned char *index = p->index_data; + index += 4 * 256; + if (p->index_version == 1) { + return ntohl(*((uint32_t *)(index + 24 * n))); + } else { + uint32_t off; + index += 8 + p->num_objects * (20 + 4); + off = ntohl(*((uint32_t *)(index + 4 * n))); + if (!(off & 0x80000000)) + return off; + index += p->num_objects * 4 + (off & 0x7fffffff) * 8; + check_pack_index_ptr(p, index); + return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) | + ntohl(*((uint32_t *)(index + 4))); + } +} + +off_t find_pack_entry_one(const unsigned char *sha1, + struct packed_git *p) +{ + const uint32_t *level1_ofs = p->index_data; + const unsigned char *index = p->index_data; + unsigned hi, lo, stride; + static int debug_lookup = -1; + + if (debug_lookup < 0) + debug_lookup = !!getenv("GIT_DEBUG_LOOKUP"); + + if (!index) { + if (open_pack_index(p)) + return 0; + level1_ofs = p->index_data; + index = p->index_data; + } + if (p->index_version > 1) { + level1_ofs += 2; + index += 8; + } + index += 4 * 256; + hi = ntohl(level1_ofs[*sha1]); + lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); + if (p->index_version > 1) { + stride = 20; + } else { + stride = 24; + index += 4; + } + + if (debug_lookup) + printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n", + sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects); + + while (lo < hi) { + unsigned mi = (lo + hi) / 2; + int cmp = hashcmp(index + mi * stride, sha1); + + if (debug_lookup) + printf("lo %u hi %u rg %u mi %u\n", + lo, hi, hi - lo, mi); + if (!cmp) + return nth_packed_object_offset(p, mi); + if (cmp > 0) + hi = mi; + else + lo = mi+1; + } + return 0; +} + +int is_pack_valid(struct packed_git *p) +{ + /* An already open pack is known to be valid. */ + if (p->pack_fd != -1) + return 1; + + /* If the pack has one window completely covering the + * file size, the pack is known to be valid even if + * the descriptor is not currently open. + */ + if (p->windows) { + struct pack_window *w = p->windows; + + if (!w->offset && w->len == p->pack_size) + return 1; + } + + /* Force the pack to open to prove its valid. */ + return !open_packed_git(p); +} + +struct packed_git *find_sha1_pack(const unsigned char *sha1, + struct packed_git *packs) +{ + struct packed_git *p; + + for (p = packs; p; p = p->next) { + if (find_pack_entry_one(sha1, p)) + return p; + } + return NULL; + +} + +static int fill_pack_entry(const unsigned char *sha1, + struct pack_entry *e, + struct packed_git *p) +{ + off_t offset; + + if (p->num_bad_objects) { + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return 0; + } + + offset = find_pack_entry_one(sha1, p); + if (!offset) + return 0; + + /* + * We are about to tell the caller where they can locate the + * requested object. We better make sure the packfile is + * still here and can be accessed before supplying that + * answer, as it may have been deleted since the index was + * loaded! + */ + if (!is_pack_valid(p)) + return 0; + e->offset = offset; + e->p = p; + hashcpy(e->sha1, sha1); + return 1; +} + +/* + * Iff a pack file contains the object named by sha1, return true and + * store its location to e. + */ +int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) +{ + struct mru_entry *p; + + prepare_packed_git(); + if (!packed_git) + return 0; + + for (p = packed_git_mru->head; p; p = p->next) { + if (fill_pack_entry(sha1, e, p->item)) { + mru_mark(packed_git_mru, p); + return 1; + } + } + return 0; +} + +int has_sha1_pack(const unsigned char *sha1) +{ + struct pack_entry e; + return find_pack_entry(sha1, &e); +} + +int has_pack_index(const unsigned char *sha1) +{ + struct stat st; + if (stat(sha1_pack_index_name(sha1), &st)) + return 0; + return 1; +} + +static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) +{ + uint32_t i; + int r = 0; + + for (i = 0; i < p->num_objects; i++) { + struct object_id oid; + + if (!nth_packed_object_oid(&oid, p, i)) + return error("unable to get sha1 of object %u in %s", + i, p->pack_name); + + r = cb(&oid, p, i, data); + if (r) + break; + } + return r; +} + +int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags) +{ + struct packed_git *p; + int r = 0; + int pack_errors = 0; + + prepare_packed_git(); + for (p = packed_git; p; p = p->next) { + if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) + continue; + if (open_pack_index(p)) { + pack_errors = 1; + continue; + } + r = for_each_object_in_pack(p, cb, data); + if (r) + break; + } + return r ? r : pack_errors; +} diff --git a/packfile.h b/packfile.h new file mode 100644 index 000000000..0cdeb54dc --- /dev/null +++ b/packfile.h @@ -0,0 +1,138 @@ +#ifndef PACKFILE_H +#define PACKFILE_H + +/* + * Generate the filename to be used for a pack file with checksum "sha1" and + * extension "ext". The result is written into the strbuf "buf", overwriting + * any existing contents. A pointer to buf->buf is returned as a convenience. + * + * Example: odb_pack_name(out, sha1, "idx") => ".git/objects/pack/pack-1234..idx" + */ +extern char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); + +/* + * Return the name of the (local) packfile with the specified sha1 in + * its name. The return value is a pointer to memory that is + * overwritten each time this function is called. + */ +extern char *sha1_pack_name(const unsigned char *sha1); + +/* + * Return the name of the (local) pack index file with the specified + * sha1 in its name. The return value is a pointer to memory that is + * overwritten each time this function is called. + */ +extern char *sha1_pack_index_name(const unsigned char *sha1); + +extern struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path); + +/* A hook to report invalid files in pack directory */ +#define PACKDIR_FILE_PACK 1 +#define PACKDIR_FILE_IDX 2 +#define PACKDIR_FILE_GARBAGE 4 +extern void (*report_garbage)(unsigned seen_bits, const char *path); + +extern void prepare_packed_git(void); +extern void reprepare_packed_git(void); +extern void install_packed_git(struct packed_git *pack); + +/* + * Give a rough count of objects in the repository. This sacrifices accuracy + * for speed. + */ +unsigned long approximate_object_count(void); + +extern struct packed_git *find_sha1_pack(const unsigned char *sha1, + struct packed_git *packs); + +extern void pack_report(void); + +/* + * mmap the index file for the specified packfile (if it is not + * already mmapped). Return 0 on success. + */ +extern int open_pack_index(struct packed_git *); + +/* + * munmap the index file for the specified packfile (if it is + * currently mmapped). + */ +extern void close_pack_index(struct packed_git *); + +extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); +extern void close_pack_windows(struct packed_git *); +extern void close_all_packs(void); +extern void unuse_pack(struct pack_window **); +extern void clear_delta_base_cache(void); +extern struct packed_git *add_packed_git(const char *path, size_t path_len, int local); + +/* + * Make sure that a pointer access into an mmap'd index file is within bounds, + * and can provide at least 8 bytes of data. + * + * Note that this is only necessary for variable-length segments of the file + * (like the 64-bit extended offset table), as we compare the size to the + * fixed-length parts when we open the file. + */ +extern void check_pack_index_ptr(const struct packed_git *p, const void *ptr); + +/* + * Return the SHA-1 of the nth object within the specified packfile. + * Open the index if it is not already open. The return value points + * at the SHA-1 within the mmapped index. Return NULL if there is an + * error. + */ +extern const unsigned char *nth_packed_object_sha1(struct packed_git *, uint32_t n); +/* + * Like nth_packed_object_sha1, but write the data into the object specified by + * the the first argument. Returns the first argument on success, and NULL on + * error. + */ +extern const struct object_id *nth_packed_object_oid(struct object_id *, struct packed_git *, uint32_t n); + +/* + * Return the offset of the nth object within the specified packfile. + * The index must already be opened. + */ +extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t n); + +/* + * If the object named sha1 is present in the specified packfile, + * return its offset within the packfile; otherwise, return 0. + */ +extern off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *); + +extern int is_pack_valid(struct packed_git *); +extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *); +extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); +extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t); +extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *); + +extern void release_pack_memory(size_t); + +/* global flag to enable extra checks when accessing packed objects */ +extern int do_check_packed_object_crc; + +extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *); + +extern void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1); +extern const struct packed_git *has_packed_and_bad(const unsigned char *sha1); + +extern int find_pack_entry(const unsigned char *sha1, struct pack_entry *e); + +extern int has_sha1_pack(const unsigned char *sha1); + +extern int has_pack_index(const unsigned char *sha1); + +/* + * Iterate over packed objects in both the local + * repository and any alternates repositories (unless the + * FOR_EACH_OBJECT_LOCAL_ONLY flag, defined in cache.h, is set). + */ +typedef int each_packed_object_fn(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data); +extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags); + +#endif @@ -9,6 +9,7 @@ #include "worktree.h" #include "submodule-config.h" #include "path.h" +#include "packfile.h" static int get_st_mode_bits(const char *path, int *mode) { @@ -871,16 +871,6 @@ const char *format_subject(struct strbuf *sb, const char *msg, return msg; } -static void format_trailers(struct strbuf *sb, const char *msg) -{ - struct trailer_info info; - - trailer_info_get(&info, msg); - strbuf_add(sb, info.trailer_start, - info.trailer_end - info.trailer_start); - trailer_info_release(&info); -} - static void parse_commit_message(struct format_commit_context *c) { const char *msg = c->message + c->message_off; @@ -1074,6 +1064,7 @@ static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */ const struct commit *commit = c->commit; const char *msg = c->message; struct commit_list *p; + const char *arg; int ch; /* these are independent of the commit */ @@ -1292,9 +1283,18 @@ static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */ return 1; } - if (starts_with(placeholder, "(trailers)")) { - format_trailers(sb, msg + c->subject_off); - return strlen("(trailers)"); + if (skip_prefix(placeholder, "(trailers", &arg)) { + struct process_trailer_options opts = PROCESS_TRAILER_OPTIONS_INIT; + while (*arg == ':') { + if (skip_prefix(arg, ":only", &arg)) + opts.only_trailers = 1; + else if (skip_prefix(arg, ":unfold", &arg)) + opts.unfold = 1; + } + if (*arg == ')') { + format_trailers_from_commit(sb, msg + c->subject_off, &opts); + return arg - placeholder + 1; + } } return 0; /* unknown placeholder */ diff --git a/reachable.c b/reachable.c index c62efbfd4..d1ac5d97e 100644 --- a/reachable.c +++ b/reachable.c @@ -9,6 +9,7 @@ #include "cache-tree.h" #include "progress.h" #include "list-objects.h" +#include "packfile.h" struct connectivity_progress { struct progress *progress; diff --git a/read-cache.c b/read-cache.c index acfb028f4..40da87ea7 100644 --- a/read-cache.c +++ b/read-cache.c @@ -160,9 +160,9 @@ static int ce_compare_data(const struct cache_entry *ce, struct stat *st) int fd = git_open_cloexec(ce->name, O_RDONLY); if (fd >= 0) { - unsigned char sha1[20]; - if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0)) - match = hashcmp(sha1, ce->oid.hash); + struct object_id oid; + if (!index_fd(&oid, fd, st, OBJ_BLOB, ce->name, 0)) + match = oidcmp(&oid, &ce->oid); /* index_fd() closed the file descriptor already */ } return match; @@ -689,7 +689,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, return 0; } if (!intent_only) { - if (index_path(ce->oid.hash, path, st, HASH_WRITE_OBJECT)) { + if (index_path(&ce->oid, path, st, HASH_WRITE_OBJECT)) { free(ce); return error("unable to index file %s", path); } @@ -1499,6 +1499,7 @@ struct ondisk_cache_entry_extended { }; /* These are only used for v3 or lower */ +#define align_padding_size(size, len) ((size + (len) + 8) & ~7) - (size + len) #define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7) #define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len) #define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len) @@ -2032,7 +2033,7 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce) } /* Copy miscellaneous fields but not the name */ -static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, +static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce) { short flags; @@ -2056,32 +2057,35 @@ static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, struct ondisk_cache_entry_extended *ondisk2; ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16); - return ondisk2->name; - } - else { - return ondisk->name; } } static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, - struct strbuf *previous_name) + struct strbuf *previous_name, struct ondisk_cache_entry *ondisk) { int size; - struct ondisk_cache_entry *ondisk; int saved_namelen = saved_namelen; /* compiler workaround */ - char *name; int result; + static unsigned char padding[8] = { 0x00 }; if (ce->ce_flags & CE_STRIP_NAME) { saved_namelen = ce_namelen(ce); ce->ce_namelen = 0; } + if (ce->ce_flags & CE_EXTENDED) + size = offsetof(struct ondisk_cache_entry_extended, name); + else + size = offsetof(struct ondisk_cache_entry, name); + if (!previous_name) { - size = ondisk_ce_size(ce); - ondisk = xcalloc(1, size); - name = copy_cache_entry_to_ondisk(ondisk, ce); - memcpy(name, ce->name, ce_namelen(ce)); + int len = ce_namelen(ce); + copy_cache_entry_to_ondisk(ondisk, ce); + result = ce_write(c, fd, ondisk, size); + if (!result) + result = ce_write(c, fd, ce->name, len); + if (!result) + result = ce_write(c, fd, padding, align_padding_size(size, len)); } else { int common, to_remove, prefix_size; unsigned char to_remove_vi[16]; @@ -2094,16 +2098,12 @@ static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, to_remove = previous_name->len - common; prefix_size = encode_varint(to_remove, to_remove_vi); - if (ce->ce_flags & CE_EXTENDED) - size = offsetof(struct ondisk_cache_entry_extended, name); - else - size = offsetof(struct ondisk_cache_entry, name); - size += prefix_size + (ce_namelen(ce) - common + 1); - - ondisk = xcalloc(1, size); - name = copy_cache_entry_to_ondisk(ondisk, ce); - memcpy(name, to_remove_vi, prefix_size); - memcpy(name + prefix_size, ce->name + common, ce_namelen(ce) - common); + copy_cache_entry_to_ondisk(ondisk, ce); + result = ce_write(c, fd, ondisk, size); + if (!result) + result = ce_write(c, fd, to_remove_vi, prefix_size); + if (!result) + result = ce_write(c, fd, ce->name + common, ce_namelen(ce) - common + 1); strbuf_splice(previous_name, common, to_remove, ce->name + common, ce_namelen(ce) - common); @@ -2113,8 +2113,6 @@ static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, ce->ce_flags &= ~CE_STRIP_NAME; } - result = ce_write(c, fd, ondisk, size); - free(ondisk); return result; } @@ -2192,10 +2190,11 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, int newfd = tempfile->fd; git_SHA_CTX c; struct cache_header hdr; - int i, err, removed, extended, hdr_version; + int i, err = 0, removed, extended, hdr_version; struct cache_entry **cache = istate->cache; int entries = istate->cache_nr; struct stat st; + struct ondisk_cache_entry_extended ondisk; struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; int drop_cache_tree = 0; @@ -2232,6 +2231,7 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, return -1; previous_name = (hdr_version == 4) ? &previous_name_buf : NULL; + for (i = 0; i < entries; i++) { struct cache_entry *ce = cache[i]; if (ce->ce_flags & CE_REMOVE) @@ -2247,15 +2247,21 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, if (allow) warning(msg, ce->name); else - return error(msg, ce->name); + err = error(msg, ce->name); drop_cache_tree = 1; } - if (ce_write_entry(&c, newfd, ce, previous_name) < 0) - return -1; + if (ce_write_entry(&c, newfd, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0) + err = -1; + + if (err) + break; } strbuf_release(&previous_name_buf); + if (err) + return err; + /* Write extension data here */ if (!strip_extensions && istate->split_index) { struct strbuf sb = STRBUF_INIT; @@ -579,6 +579,21 @@ enum ref_type ref_type(const char *refname) return REF_TYPE_NORMAL; } +long get_files_ref_lock_timeout_ms(void) +{ + static int configured = 0; + + /* The default timeout is 100 ms: */ + static int timeout_ms = 100; + + if (!configured) { + git_config_get_int("core.filesreflocktimeout", &timeout_ms); + configured = 1; + } + + return timeout_ms; +} + static int write_pseudoref(const char *pseudoref, const unsigned char *sha1, const unsigned char *old_sha1, struct strbuf *err) { @@ -591,7 +606,9 @@ static int write_pseudoref(const char *pseudoref, const unsigned char *sha1, strbuf_addf(&buf, "%s\n", sha1_to_hex(sha1)); filename = git_path("%s", pseudoref); - fd = hold_lock_file_for_update(&lock, filename, LOCK_DIE_ON_ERROR); + fd = hold_lock_file_for_update_timeout(&lock, filename, + LOCK_DIE_ON_ERROR, + get_files_ref_lock_timeout_ms()); if (fd < 0) { strbuf_addf(err, "could not open '%s' for writing: %s", filename, strerror(errno)); @@ -634,8 +651,9 @@ static int delete_pseudoref(const char *pseudoref, const unsigned char *old_sha1 int fd; unsigned char actual_old_sha1[20]; - fd = hold_lock_file_for_update(&lock, filename, - LOCK_DIE_ON_ERROR); + fd = hold_lock_file_for_update_timeout( + &lock, filename, LOCK_DIE_ON_ERROR, + get_files_ref_lock_timeout_ms()); if (fd < 0) die_errno(_("Could not open '%s' for writing"), filename); if (read_ref(pseudoref, actual_old_sha1)) diff --git a/refs/files-backend.c b/refs/files-backend.c index 5cca55510..fccbc24ac 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -537,7 +537,9 @@ retry: if (!lock->lk) lock->lk = xcalloc(1, sizeof(struct lock_file)); - if (hold_lock_file_for_update(lock->lk, ref_file.buf, LOCK_NO_DEREF) < 0) { + if (hold_lock_file_for_update_timeout( + lock->lk, ref_file.buf, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0) { if (errno == ENOENT && --attempts_remaining > 0) { /* * Maybe somebody just deleted one of the @@ -865,7 +867,9 @@ static int create_reflock(const char *path, void *cb) { struct lock_file *lk = cb; - return hold_lock_file_for_update(lk, path, LOCK_NO_DEREF) < 0 ? -1 : 0; + return hold_lock_file_for_update_timeout( + lk, path, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0 ? -1 : 0; } /* diff --git a/refs/refs-internal.h b/refs/refs-internal.h index 4789106fc..b02dc5a7e 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -62,6 +62,12 @@ #define REF_DELETED_LOOSE 0x200 /* + * Return the length of time to retry acquiring a loose reference lock + * before giving up, in milliseconds: + */ +long get_files_ref_lock_timeout_ms(void); + +/* * Return true iff refname is minimally safe. "Safe" here means that * deleting a loose reference by this name will not do any damage, for * example by causing a file that is not a reference to be deleted. @@ -2084,7 +2084,7 @@ int format_tracking_info(struct branch *branch, struct strbuf *sb) _(" (use \"git branch --unset-upstream\" to fixup)\n")); } else if (!ours && !theirs) { strbuf_addf(sb, - _("Your branch is up-to-date with '%s'.\n"), + _("Your branch is up to date with '%s'.\n"), base); } else if (!theirs) { strbuf_addf(sb, @@ -1133,14 +1133,14 @@ int rerere_forget(struct pathspec *pathspec) * Garbage collection support */ -static time_t rerere_created_at(struct rerere_id *id) +static timestamp_t rerere_created_at(struct rerere_id *id) { struct stat st; return stat(rerere_path(id, "preimage"), &st) ? (time_t) 0 : st.st_mtime; } -static time_t rerere_last_used_at(struct rerere_id *id) +static timestamp_t rerere_last_used_at(struct rerere_id *id) { struct stat st; @@ -1157,11 +1157,11 @@ static void unlink_rr_item(struct rerere_id *id) id->collection->status[id->variant] = 0; } -static void prune_one(struct rerere_id *id, time_t now, - int cutoff_resolve, int cutoff_noresolve) +static void prune_one(struct rerere_id *id, + timestamp_t cutoff_resolve, timestamp_t cutoff_noresolve) { - time_t then; - int cutoff; + timestamp_t then; + timestamp_t cutoff; then = rerere_last_used_at(id); if (then) @@ -1172,7 +1172,7 @@ static void prune_one(struct rerere_id *id, time_t now, return; cutoff = cutoff_noresolve; } - if (then < now - cutoff * 86400) + if (then < cutoff) unlink_rr_item(id); } @@ -1182,15 +1182,15 @@ void rerere_gc(struct string_list *rr) DIR *dir; struct dirent *e; int i; - time_t now = time(NULL); - int cutoff_noresolve = 15; - int cutoff_resolve = 60; + timestamp_t now = time(NULL); + timestamp_t cutoff_noresolve = now - 15 * 86400; + timestamp_t cutoff_resolve = now - 60 * 86400; if (setup_rerere(rr, 0) < 0) return; - git_config_get_int("gc.rerereresolved", &cutoff_resolve); - git_config_get_int("gc.rerereunresolved", &cutoff_noresolve); + git_config_get_expiry_in_days("gc.rerereresolved", &cutoff_resolve, now); + git_config_get_expiry_in_days("gc.rerereunresolved", &cutoff_noresolve, now); git_config(git_default_config, NULL); dir = opendir(git_path("rr-cache")); if (!dir) @@ -1211,7 +1211,7 @@ void rerere_gc(struct string_list *rr) for (id.variant = 0, id.collection = rr_dir; id.variant < id.collection->status_nr; id.variant++) { - prune_one(&id, now, cutoff_resolve, cutoff_noresolve); + prune_one(&id, cutoff_resolve, cutoff_noresolve); if (id.collection->status[id.variant]) now_empty = 0; } diff --git a/revision.c b/revision.c index aa3b946a8..94a5e9852 100644 --- a/revision.c +++ b/revision.c @@ -19,6 +19,7 @@ #include "dir.h" #include "cache-tree.h" #include "bisect.h" +#include "packfile.h" volatile show_early_output_fn_t show_early_output; diff --git a/server-info.c b/server-info.c index 5ec5b1d82..26a6c20b7 100644 --- a/server-info.c +++ b/server-info.c @@ -3,6 +3,7 @@ #include "object.h" #include "commit.h" #include "tag.h" +#include "packfile.h" /* * Create the file "path" by writing to a temporary file and renaming diff --git a/sha1_file.c b/sha1_file.c index 189a1c3cd..5f71bbac3 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -28,11 +28,9 @@ #include "list.h" #include "mergesort.h" #include "quote.h" +#include "packfile.h" -#define SZ_FMT PRIuMAX -static inline uintmax_t sz_fmt(size_t s) { return s; } - -const unsigned char null_sha1[20]; +const unsigned char null_sha1[GIT_MAX_RAWSZ]; const struct object_id null_oid; const struct object_id empty_tree_oid = { EMPTY_TREE_SHA1_BIN_LITERAL @@ -278,28 +276,6 @@ static const char *alt_sha1_path(struct alternate_object_database *alt, return buf->buf; } - char *odb_pack_name(struct strbuf *buf, - const unsigned char *sha1, - const char *ext) -{ - strbuf_reset(buf); - strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), - sha1_to_hex(sha1), ext); - return buf->buf; -} - -char *sha1_pack_name(const unsigned char *sha1) -{ - static struct strbuf buf = STRBUF_INIT; - return odb_pack_name(&buf, sha1, "pack"); -} - -char *sha1_pack_index_name(const unsigned char *sha1) -{ - static struct strbuf buf = STRBUF_INIT; - return odb_pack_name(&buf, sha1, "idx"); -} - struct alternate_object_database *alt_odb_list; static struct alternate_object_database **alt_odb_tail; @@ -705,213 +681,6 @@ static int has_loose_object(const unsigned char *sha1) return check_and_freshen(sha1, 0); } -static unsigned int pack_used_ctr; -static unsigned int pack_mmap_calls; -static unsigned int peak_pack_open_windows; -static unsigned int pack_open_windows; -static unsigned int pack_open_fds; -static unsigned int pack_max_fds; -static size_t peak_pack_mapped; -static size_t pack_mapped; -struct packed_git *packed_git; - -static struct mru packed_git_mru_storage; -struct mru *packed_git_mru = &packed_git_mru_storage; - -void pack_report(void) -{ - fprintf(stderr, - "pack_report: getpagesize() = %10" SZ_FMT "\n" - "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" - "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", - sz_fmt(getpagesize()), - sz_fmt(packed_git_window_size), - sz_fmt(packed_git_limit)); - fprintf(stderr, - "pack_report: pack_used_ctr = %10u\n" - "pack_report: pack_mmap_calls = %10u\n" - "pack_report: pack_open_windows = %10u / %10u\n" - "pack_report: pack_mapped = " - "%10" SZ_FMT " / %10" SZ_FMT "\n", - pack_used_ctr, - pack_mmap_calls, - pack_open_windows, peak_pack_open_windows, - sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped)); -} - -/* - * Open and mmap the index file at path, perform a couple of - * consistency checks, then record its information to p. Return 0 on - * success. - */ -static int check_packed_git_idx(const char *path, struct packed_git *p) -{ - void *idx_map; - struct pack_idx_header *hdr; - size_t idx_size; - uint32_t version, nr, i, *index; - int fd = git_open(path); - struct stat st; - - if (fd < 0) - return -1; - if (fstat(fd, &st)) { - close(fd); - return -1; - } - idx_size = xsize_t(st.st_size); - if (idx_size < 4 * 256 + 20 + 20) { - close(fd); - return error("index file %s is too small", path); - } - idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); - close(fd); - - hdr = idx_map; - if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { - version = ntohl(hdr->idx_version); - if (version < 2 || version > 2) { - munmap(idx_map, idx_size); - return error("index file %s is version %"PRIu32 - " and is not supported by this binary" - " (try upgrading GIT to a newer version)", - path, version); - } - } else - version = 1; - - nr = 0; - index = idx_map; - if (version > 1) - index += 2; /* skip index header */ - for (i = 0; i < 256; i++) { - uint32_t n = ntohl(index[i]); - if (n < nr) { - munmap(idx_map, idx_size); - return error("non-monotonic index %s", path); - } - nr = n; - } - - if (version == 1) { - /* - * Total size: - * - 256 index entries 4 bytes each - * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) - * - 20-byte SHA1 of the packfile - * - 20-byte SHA1 file checksum - */ - if (idx_size != 4*256 + nr * 24 + 20 + 20) { - munmap(idx_map, idx_size); - return error("wrong index v1 file size in %s", path); - } - } else if (version == 2) { - /* - * Minimum size: - * - 8 bytes of header - * - 256 index entries 4 bytes each - * - 20-byte sha1 entry * nr - * - 4-byte crc entry * nr - * - 4-byte offset entry * nr - * - 20-byte SHA1 of the packfile - * - 20-byte SHA1 file checksum - * And after the 4-byte offset table might be a - * variable sized table containing 8-byte entries - * for offsets larger than 2^31. - */ - unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; - unsigned long max_size = min_size; - if (nr) - max_size += (nr - 1)*8; - if (idx_size < min_size || idx_size > max_size) { - munmap(idx_map, idx_size); - return error("wrong index v2 file size in %s", path); - } - if (idx_size != min_size && - /* - * make sure we can deal with large pack offsets. - * 31-bit signed offset won't be enough, neither - * 32-bit unsigned one will be. - */ - (sizeof(off_t) <= 4)) { - munmap(idx_map, idx_size); - return error("pack too large for current definition of off_t in %s", path); - } - } - - p->index_version = version; - p->index_data = idx_map; - p->index_size = idx_size; - p->num_objects = nr; - return 0; -} - -int open_pack_index(struct packed_git *p) -{ - char *idx_name; - size_t len; - int ret; - - if (p->index_data) - return 0; - - if (!strip_suffix(p->pack_name, ".pack", &len)) - die("BUG: pack_name does not end in .pack"); - idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name); - ret = check_packed_git_idx(idx_name, p); - free(idx_name); - return ret; -} - -static void scan_windows(struct packed_git *p, - struct packed_git **lru_p, - struct pack_window **lru_w, - struct pack_window **lru_l) -{ - struct pack_window *w, *w_l; - - for (w_l = NULL, w = p->windows; w; w = w->next) { - if (!w->inuse_cnt) { - if (!*lru_w || w->last_used < (*lru_w)->last_used) { - *lru_p = p; - *lru_w = w; - *lru_l = w_l; - } - } - w_l = w; - } -} - -static int unuse_one_window(struct packed_git *current) -{ - struct packed_git *p, *lru_p = NULL; - struct pack_window *lru_w = NULL, *lru_l = NULL; - - if (current) - scan_windows(current, &lru_p, &lru_w, &lru_l); - for (p = packed_git; p; p = p->next) - scan_windows(p, &lru_p, &lru_w, &lru_l); - if (lru_p) { - munmap(lru_w->base, lru_w->len); - pack_mapped -= lru_w->len; - if (lru_l) - lru_l->next = lru_w->next; - else - lru_p->windows = lru_w->next; - free(lru_w); - pack_open_windows--; - return 1; - } - return 0; -} - -void release_pack_memory(size_t need) -{ - size_t cur = pack_mapped; - while (need >= (cur - pack_mapped) && unuse_one_window(NULL)) - ; /* nothing */ -} - static void mmap_limit_check(size_t length) { static size_t limit = 0; @@ -950,681 +719,6 @@ void *xmmap(void *start, size_t length, return ret; } -void close_pack_windows(struct packed_git *p) -{ - while (p->windows) { - struct pack_window *w = p->windows; - - if (w->inuse_cnt) - die("pack '%s' still has open windows to it", - p->pack_name); - munmap(w->base, w->len); - pack_mapped -= w->len; - pack_open_windows--; - p->windows = w->next; - free(w); - } -} - -static int close_pack_fd(struct packed_git *p) -{ - if (p->pack_fd < 0) - return 0; - - close(p->pack_fd); - pack_open_fds--; - p->pack_fd = -1; - - return 1; -} - -static void close_pack(struct packed_git *p) -{ - close_pack_windows(p); - close_pack_fd(p); - close_pack_index(p); -} - -void close_all_packs(void) -{ - struct packed_git *p; - - for (p = packed_git; p; p = p->next) - if (p->do_not_close) - die("BUG: want to close pack marked 'do-not-close'"); - else - close_pack(p); -} - - -/* - * The LRU pack is the one with the oldest MRU window, preferring packs - * with no used windows, or the oldest mtime if it has no windows allocated. - */ -static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse) -{ - struct pack_window *w, *this_mru_w; - int has_windows_inuse = 0; - - /* - * Reject this pack if it has windows and the previously selected - * one does not. If this pack does not have windows, reject - * it if the pack file is newer than the previously selected one. - */ - if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime)) - return; - - for (w = this_mru_w = p->windows; w; w = w->next) { - /* - * Reject this pack if any of its windows are in use, - * but the previously selected pack did not have any - * inuse windows. Otherwise, record that this pack - * has windows in use. - */ - if (w->inuse_cnt) { - if (*accept_windows_inuse) - has_windows_inuse = 1; - else - return; - } - - if (w->last_used > this_mru_w->last_used) - this_mru_w = w; - - /* - * Reject this pack if it has windows that have been - * used more recently than the previously selected pack. - * If the previously selected pack had windows inuse and - * we have not encountered a window in this pack that is - * inuse, skip this check since we prefer a pack with no - * inuse windows to one that has inuse windows. - */ - if (*mru_w && *accept_windows_inuse == has_windows_inuse && - this_mru_w->last_used > (*mru_w)->last_used) - return; - } - - /* - * Select this pack. - */ - *mru_w = this_mru_w; - *lru_p = p; - *accept_windows_inuse = has_windows_inuse; -} - -static int close_one_pack(void) -{ - struct packed_git *p, *lru_p = NULL; - struct pack_window *mru_w = NULL; - int accept_windows_inuse = 1; - - for (p = packed_git; p; p = p->next) { - if (p->pack_fd == -1) - continue; - find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); - } - - if (lru_p) - return close_pack_fd(lru_p); - - return 0; -} - -void unuse_pack(struct pack_window **w_cursor) -{ - struct pack_window *w = *w_cursor; - if (w) { - w->inuse_cnt--; - *w_cursor = NULL; - } -} - -void close_pack_index(struct packed_git *p) -{ - if (p->index_data) { - munmap((void *)p->index_data, p->index_size); - p->index_data = NULL; - } -} - -static unsigned int get_max_fd_limit(void) -{ -#ifdef RLIMIT_NOFILE - { - struct rlimit lim; - - if (!getrlimit(RLIMIT_NOFILE, &lim)) - return lim.rlim_cur; - } -#endif - -#ifdef _SC_OPEN_MAX - { - long open_max = sysconf(_SC_OPEN_MAX); - if (0 < open_max) - return open_max; - /* - * Otherwise, we got -1 for one of the two - * reasons: - * - * (1) sysconf() did not understand _SC_OPEN_MAX - * and signaled an error with -1; or - * (2) sysconf() said there is no limit. - * - * We _could_ clear errno before calling sysconf() to - * tell these two cases apart and return a huge number - * in the latter case to let the caller cap it to a - * value that is not so selfish, but letting the - * fallback OPEN_MAX codepath take care of these cases - * is a lot simpler. - */ - } -#endif - -#ifdef OPEN_MAX - return OPEN_MAX; -#else - return 1; /* see the caller ;-) */ -#endif -} - -/* - * Do not call this directly as this leaks p->pack_fd on error return; - * call open_packed_git() instead. - */ -static int open_packed_git_1(struct packed_git *p) -{ - struct stat st; - struct pack_header hdr; - unsigned char sha1[20]; - unsigned char *idx_sha1; - long fd_flag; - - if (!p->index_data && open_pack_index(p)) - return error("packfile %s index unavailable", p->pack_name); - - if (!pack_max_fds) { - unsigned int max_fds = get_max_fd_limit(); - - /* Save 3 for stdin/stdout/stderr, 22 for work */ - if (25 < max_fds) - pack_max_fds = max_fds - 25; - else - pack_max_fds = 1; - } - - while (pack_max_fds <= pack_open_fds && close_one_pack()) - ; /* nothing */ - - p->pack_fd = git_open(p->pack_name); - if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) - return -1; - pack_open_fds++; - - /* If we created the struct before we had the pack we lack size. */ - if (!p->pack_size) { - if (!S_ISREG(st.st_mode)) - return error("packfile %s not a regular file", p->pack_name); - p->pack_size = st.st_size; - } else if (p->pack_size != st.st_size) - return error("packfile %s size changed", p->pack_name); - - /* We leave these file descriptors open with sliding mmap; - * there is no point keeping them open across exec(), though. - */ - fd_flag = fcntl(p->pack_fd, F_GETFD, 0); - if (fd_flag < 0) - return error("cannot determine file descriptor flags"); - fd_flag |= FD_CLOEXEC; - if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) - return error("cannot set FD_CLOEXEC"); - - /* Verify we recognize this pack file format. */ - if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - return error("file %s is far too short to be a packfile", p->pack_name); - if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) - return error("file %s is not a GIT packfile", p->pack_name); - if (!pack_version_ok(hdr.hdr_version)) - return error("packfile %s is version %"PRIu32" and not" - " supported (try upgrading GIT to a newer version)", - p->pack_name, ntohl(hdr.hdr_version)); - - /* Verify the pack matches its index. */ - if (p->num_objects != ntohl(hdr.hdr_entries)) - return error("packfile %s claims to have %"PRIu32" objects" - " while index indicates %"PRIu32" objects", - p->pack_name, ntohl(hdr.hdr_entries), - p->num_objects); - if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) - return error("end of packfile %s is unavailable", p->pack_name); - if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) - return error("packfile %s signature is unavailable", p->pack_name); - idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40; - if (hashcmp(sha1, idx_sha1)) - return error("packfile %s does not match index", p->pack_name); - return 0; -} - -static int open_packed_git(struct packed_git *p) -{ - if (!open_packed_git_1(p)) - return 0; - close_pack_fd(p); - return -1; -} - -static int in_window(struct pack_window *win, off_t offset) -{ - /* We must promise at least 20 bytes (one hash) after the - * offset is available from this window, otherwise the offset - * is not actually in this window and a different window (which - * has that one hash excess) must be used. This is to support - * the object header and delta base parsing routines below. - */ - off_t win_off = win->offset; - return win_off <= offset - && (offset + 20) <= (win_off + win->len); -} - -unsigned char *use_pack(struct packed_git *p, - struct pack_window **w_cursor, - off_t offset, - unsigned long *left) -{ - struct pack_window *win = *w_cursor; - - /* Since packfiles end in a hash of their content and it's - * pointless to ask for an offset into the middle of that - * hash, and the in_window function above wouldn't match - * don't allow an offset too close to the end of the file. - */ - if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) - die("packfile %s cannot be accessed", p->pack_name); - if (offset > (p->pack_size - 20)) - die("offset beyond end of packfile (truncated pack?)"); - if (offset < 0) - die(_("offset before end of packfile (broken .idx?)")); - - if (!win || !in_window(win, offset)) { - if (win) - win->inuse_cnt--; - for (win = p->windows; win; win = win->next) { - if (in_window(win, offset)) - break; - } - if (!win) { - size_t window_align = packed_git_window_size / 2; - off_t len; - - if (p->pack_fd == -1 && open_packed_git(p)) - die("packfile %s cannot be accessed", p->pack_name); - - win = xcalloc(1, sizeof(*win)); - win->offset = (offset / window_align) * window_align; - len = p->pack_size - win->offset; - if (len > packed_git_window_size) - len = packed_git_window_size; - win->len = (size_t)len; - pack_mapped += win->len; - while (packed_git_limit < pack_mapped - && unuse_one_window(p)) - ; /* nothing */ - win->base = xmmap(NULL, win->len, - PROT_READ, MAP_PRIVATE, - p->pack_fd, win->offset); - if (win->base == MAP_FAILED) - die_errno("packfile %s cannot be mapped", - p->pack_name); - if (!win->offset && win->len == p->pack_size - && !p->do_not_close) - close_pack_fd(p); - pack_mmap_calls++; - pack_open_windows++; - if (pack_mapped > peak_pack_mapped) - peak_pack_mapped = pack_mapped; - if (pack_open_windows > peak_pack_open_windows) - peak_pack_open_windows = pack_open_windows; - win->next = p->windows; - p->windows = win; - } - } - if (win != *w_cursor) { - win->last_used = pack_used_ctr++; - win->inuse_cnt++; - *w_cursor = win; - } - offset -= win->offset; - if (left) - *left = win->len - xsize_t(offset); - return win->base + offset; -} - -static struct packed_git *alloc_packed_git(int extra) -{ - struct packed_git *p = xmalloc(st_add(sizeof(*p), extra)); - memset(p, 0, sizeof(*p)); - p->pack_fd = -1; - return p; -} - -static void try_to_free_pack_memory(size_t size) -{ - release_pack_memory(size); -} - -struct packed_git *add_packed_git(const char *path, size_t path_len, int local) -{ - static int have_set_try_to_free_routine; - struct stat st; - size_t alloc; - struct packed_git *p; - - if (!have_set_try_to_free_routine) { - have_set_try_to_free_routine = 1; - set_try_to_free_routine(try_to_free_pack_memory); - } - - /* - * Make sure a corresponding .pack file exists and that - * the index looks sane. - */ - if (!strip_suffix_mem(path, &path_len, ".idx")) - return NULL; - - /* - * ".pack" is long enough to hold any suffix we're adding (and - * the use xsnprintf double-checks that) - */ - alloc = st_add3(path_len, strlen(".pack"), 1); - p = alloc_packed_git(alloc); - memcpy(p->pack_name, path, path_len); - - xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); - if (!access(p->pack_name, F_OK)) - p->pack_keep = 1; - - xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); - if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { - free(p); - return NULL; - } - - /* ok, it looks sane as far as we can check without - * actually mapping the pack file. - */ - p->pack_size = st.st_size; - p->pack_local = local; - p->mtime = st.st_mtime; - if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) - hashclr(p->sha1); - return p; -} - -struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) -{ - const char *path = sha1_pack_name(sha1); - size_t alloc = st_add(strlen(path), 1); - struct packed_git *p = alloc_packed_git(alloc); - - memcpy(p->pack_name, path, alloc); /* includes NUL */ - hashcpy(p->sha1, sha1); - if (check_packed_git_idx(idx_path, p)) { - free(p); - return NULL; - } - - return p; -} - -void install_packed_git(struct packed_git *pack) -{ - if (pack->pack_fd != -1) - pack_open_fds++; - - pack->next = packed_git; - packed_git = pack; -} - -void (*report_garbage)(unsigned seen_bits, const char *path); - -static void report_helper(const struct string_list *list, - int seen_bits, int first, int last) -{ - if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX)) - return; - - for (; first < last; first++) - report_garbage(seen_bits, list->items[first].string); -} - -static void report_pack_garbage(struct string_list *list) -{ - int i, baselen = -1, first = 0, seen_bits = 0; - - if (!report_garbage) - return; - - string_list_sort(list); - - for (i = 0; i < list->nr; i++) { - const char *path = list->items[i].string; - if (baselen != -1 && - strncmp(path, list->items[first].string, baselen)) { - report_helper(list, seen_bits, first, i); - baselen = -1; - seen_bits = 0; - } - if (baselen == -1) { - const char *dot = strrchr(path, '.'); - if (!dot) { - report_garbage(PACKDIR_FILE_GARBAGE, path); - continue; - } - baselen = dot - path + 1; - first = i; - } - if (!strcmp(path + baselen, "pack")) - seen_bits |= 1; - else if (!strcmp(path + baselen, "idx")) - seen_bits |= 2; - } - report_helper(list, seen_bits, first, list->nr); -} - -static void prepare_packed_git_one(char *objdir, int local) -{ - struct strbuf path = STRBUF_INIT; - size_t dirnamelen; - DIR *dir; - struct dirent *de; - struct string_list garbage = STRING_LIST_INIT_DUP; - - strbuf_addstr(&path, objdir); - strbuf_addstr(&path, "/pack"); - dir = opendir(path.buf); - if (!dir) { - if (errno != ENOENT) - error_errno("unable to open object pack directory: %s", - path.buf); - strbuf_release(&path); - return; - } - strbuf_addch(&path, '/'); - dirnamelen = path.len; - while ((de = readdir(dir)) != NULL) { - struct packed_git *p; - size_t base_len; - - if (is_dot_or_dotdot(de->d_name)) - continue; - - strbuf_setlen(&path, dirnamelen); - strbuf_addstr(&path, de->d_name); - - base_len = path.len; - if (strip_suffix_mem(path.buf, &base_len, ".idx")) { - /* Don't reopen a pack we already have. */ - for (p = packed_git; p; p = p->next) { - size_t len; - if (strip_suffix(p->pack_name, ".pack", &len) && - len == base_len && - !memcmp(p->pack_name, path.buf, len)) - break; - } - if (p == NULL && - /* - * See if it really is a valid .idx file with - * corresponding .pack file that we can map. - */ - (p = add_packed_git(path.buf, path.len, local)) != NULL) - install_packed_git(p); - } - - if (!report_garbage) - continue; - - if (ends_with(de->d_name, ".idx") || - ends_with(de->d_name, ".pack") || - ends_with(de->d_name, ".bitmap") || - ends_with(de->d_name, ".keep")) - string_list_append(&garbage, path.buf); - else - report_garbage(PACKDIR_FILE_GARBAGE, path.buf); - } - closedir(dir); - report_pack_garbage(&garbage); - string_list_clear(&garbage, 0); - strbuf_release(&path); -} - -static int approximate_object_count_valid; - -/* - * Give a fast, rough count of the number of objects in the repository. This - * ignores loose objects completely. If you have a lot of them, then either - * you should repack because your performance will be awful, or they are - * all unreachable objects about to be pruned, in which case they're not really - * interesting as a measure of repo size in the first place. - */ -unsigned long approximate_object_count(void) -{ - static unsigned long count; - if (!approximate_object_count_valid) { - struct packed_git *p; - - prepare_packed_git(); - count = 0; - for (p = packed_git; p; p = p->next) { - if (open_pack_index(p)) - continue; - count += p->num_objects; - } - } - return count; -} - -static void *get_next_packed_git(const void *p) -{ - return ((const struct packed_git *)p)->next; -} - -static void set_next_packed_git(void *p, void *next) -{ - ((struct packed_git *)p)->next = next; -} - -static int sort_pack(const void *a_, const void *b_) -{ - const struct packed_git *a = a_; - const struct packed_git *b = b_; - int st; - - /* - * Local packs tend to contain objects specific to our - * variant of the project than remote ones. In addition, - * remote ones could be on a network mounted filesystem. - * Favor local ones for these reasons. - */ - st = a->pack_local - b->pack_local; - if (st) - return -st; - - /* - * Younger packs tend to contain more recent objects, - * and more recent objects tend to get accessed more - * often. - */ - if (a->mtime < b->mtime) - return 1; - else if (a->mtime == b->mtime) - return 0; - return -1; -} - -static void rearrange_packed_git(void) -{ - packed_git = llist_mergesort(packed_git, get_next_packed_git, - set_next_packed_git, sort_pack); -} - -static void prepare_packed_git_mru(void) -{ - struct packed_git *p; - - mru_clear(packed_git_mru); - for (p = packed_git; p; p = p->next) - mru_append(packed_git_mru, p); -} - -static int prepare_packed_git_run_once = 0; -void prepare_packed_git(void) -{ - struct alternate_object_database *alt; - - if (prepare_packed_git_run_once) - return; - prepare_packed_git_one(get_object_directory(), 1); - prepare_alt_odb(); - for (alt = alt_odb_list; alt; alt = alt->next) - prepare_packed_git_one(alt->path, 0); - rearrange_packed_git(); - prepare_packed_git_mru(); - prepare_packed_git_run_once = 1; -} - -void reprepare_packed_git(void) -{ - approximate_object_count_valid = 0; - prepare_packed_git_run_once = 0; - prepare_packed_git(); -} - -static void mark_bad_packed_object(struct packed_git *p, - const unsigned char *sha1) -{ - unsigned i; - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i)) - return; - p->bad_object_sha1 = xrealloc(p->bad_object_sha1, - st_mult(GIT_MAX_RAWSZ, - st_add(p->num_bad_objects, 1))); - hashcpy(p->bad_object_sha1 + GIT_SHA1_RAWSZ * p->num_bad_objects, sha1); - p->num_bad_objects++; -} - -static const struct packed_git *has_packed_and_bad(const unsigned char *sha1) -{ - struct packed_git *p; - unsigned i; - - for (p = packed_git; p; p = p->next) - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - return p; - return NULL; -} - /* * With an in-core object data in "map", rehash it to make sure the * object name actually matches "sha1" to detect object corruption. @@ -1795,31 +889,6 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) return map_sha1_file_1(NULL, sha1, size); } -unsigned long unpack_object_header_buffer(const unsigned char *buf, - unsigned long len, enum object_type *type, unsigned long *sizep) -{ - unsigned shift; - unsigned long size, c; - unsigned long used = 0; - - c = buf[used++]; - *type = (c >> 4) & 7; - size = c & 15; - shift = 4; - while (c & 0x80) { - if (len <= used || bitsizeof(long) <= shift) { - error("bad object header"); - size = used = 0; - break; - } - c = buf[used++]; - size += (c & 0x7f) << shift; - shift += 7; - } - *sizep = size; - return used; -} - static int unpack_sha1_short_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) @@ -2006,897 +1075,6 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep) return parse_sha1_header_extended(hdr, &oi, 0); } -unsigned long get_size_from_delta(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos) -{ - const unsigned char *data; - unsigned char delta_head[20], *in; - git_zstream stream; - int st; - - memset(&stream, 0, sizeof(stream)); - stream.next_out = delta_head; - stream.avail_out = sizeof(delta_head); - - git_inflate_init(&stream); - do { - in = use_pack(p, w_curs, curpos, &stream.avail_in); - stream.next_in = in; - st = git_inflate(&stream, Z_FINISH); - curpos += stream.next_in - in; - } while ((st == Z_OK || st == Z_BUF_ERROR) && - stream.total_out < sizeof(delta_head)); - git_inflate_end(&stream); - if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) { - error("delta data unpack-initial failed"); - return 0; - } - - /* Examine the initial part of the delta to figure out - * the result size. - */ - data = delta_head; - - /* ignore base size */ - get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); - - /* Read the result size */ - return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); -} - -static off_t get_delta_base(struct packed_git *p, - struct pack_window **w_curs, - off_t *curpos, - enum object_type type, - off_t delta_obj_offset) -{ - unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL); - off_t base_offset; - - /* use_pack() assured us we have [base_info, base_info + 20) - * as a range that we can look at without walking off the - * end of the mapped window. Its actually the hash size - * that is assured. An OFS_DELTA longer than the hash size - * is stupid, as then a REF_DELTA would be smaller to store. - */ - if (type == OBJ_OFS_DELTA) { - unsigned used = 0; - unsigned char c = base_info[used++]; - base_offset = c & 127; - while (c & 128) { - base_offset += 1; - if (!base_offset || MSB(base_offset, 7)) - return 0; /* overflow */ - c = base_info[used++]; - base_offset = (base_offset << 7) + (c & 127); - } - base_offset = delta_obj_offset - base_offset; - if (base_offset <= 0 || base_offset >= delta_obj_offset) - return 0; /* out of bound */ - *curpos += used; - } else if (type == OBJ_REF_DELTA) { - /* The base entry _must_ be in the same pack */ - base_offset = find_pack_entry_one(base_info, p); - *curpos += 20; - } else - die("I am totally screwed"); - return base_offset; -} - -/* - * Like get_delta_base above, but we return the sha1 instead of the pack - * offset. This means it is cheaper for REF deltas (we do not have to do - * the final object lookup), but more expensive for OFS deltas (we - * have to load the revidx to convert the offset back into a sha1). - */ -static const unsigned char *get_delta_base_sha1(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - enum object_type type, - off_t delta_obj_offset) -{ - if (type == OBJ_REF_DELTA) { - unsigned char *base = use_pack(p, w_curs, curpos, NULL); - return base; - } else if (type == OBJ_OFS_DELTA) { - struct revindex_entry *revidx; - off_t base_offset = get_delta_base(p, w_curs, &curpos, - type, delta_obj_offset); - - if (!base_offset) - return NULL; - - revidx = find_pack_revindex(p, base_offset); - if (!revidx) - return NULL; - - return nth_packed_object_sha1(p, revidx->nr); - } else - return NULL; -} - -int unpack_object_header(struct packed_git *p, - struct pack_window **w_curs, - off_t *curpos, - unsigned long *sizep) -{ - unsigned char *base; - unsigned long left; - unsigned long used; - enum object_type type; - - /* use_pack() assures us we have [base, base + 20) available - * as a range that we can look at. (Its actually the hash - * size that is assured.) With our object header encoding - * the maximum deflated object size is 2^137, which is just - * insane, so we know won't exceed what we have been given. - */ - base = use_pack(p, w_curs, *curpos, &left); - used = unpack_object_header_buffer(base, left, &type, sizep); - if (!used) { - type = OBJ_BAD; - } else - *curpos += used; - - return type; -} - -static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) -{ - int type; - struct revindex_entry *revidx; - const unsigned char *sha1; - revidx = find_pack_revindex(p, obj_offset); - if (!revidx) - return OBJ_BAD; - sha1 = nth_packed_object_sha1(p, revidx->nr); - mark_bad_packed_object(p, sha1); - type = sha1_object_info(sha1, NULL); - if (type <= OBJ_NONE) - return OBJ_BAD; - return type; -} - -#define POI_STACK_PREALLOC 64 - -static enum object_type packed_to_object_type(struct packed_git *p, - off_t obj_offset, - enum object_type type, - struct pack_window **w_curs, - off_t curpos) -{ - off_t small_poi_stack[POI_STACK_PREALLOC]; - off_t *poi_stack = small_poi_stack; - int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC; - - while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - off_t base_offset; - unsigned long size; - /* Push the object we're going to leave behind */ - if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) { - poi_stack_alloc = alloc_nr(poi_stack_nr); - ALLOC_ARRAY(poi_stack, poi_stack_alloc); - memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr); - } else { - ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc); - } - poi_stack[poi_stack_nr++] = obj_offset; - /* If parsing the base offset fails, just unwind */ - base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); - if (!base_offset) - goto unwind; - curpos = obj_offset = base_offset; - type = unpack_object_header(p, w_curs, &curpos, &size); - if (type <= OBJ_NONE) { - /* If getting the base itself fails, we first - * retry the base, otherwise unwind */ - type = retry_bad_packed_offset(p, base_offset); - if (type > OBJ_NONE) - goto out; - goto unwind; - } - } - - switch (type) { - case OBJ_BAD: - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - break; - default: - error("unknown object type %i at offset %"PRIuMAX" in %s", - type, (uintmax_t)obj_offset, p->pack_name); - type = OBJ_BAD; - } - -out: - if (poi_stack != small_poi_stack) - free(poi_stack); - return type; - -unwind: - while (poi_stack_nr) { - obj_offset = poi_stack[--poi_stack_nr]; - type = retry_bad_packed_offset(p, obj_offset); - if (type > OBJ_NONE) - goto out; - } - type = OBJ_BAD; - goto out; -} - -static struct hashmap delta_base_cache; -static size_t delta_base_cached; - -static LIST_HEAD(delta_base_cache_lru); - -struct delta_base_cache_key { - struct packed_git *p; - off_t base_offset; -}; - -struct delta_base_cache_entry { - struct hashmap hash; - struct delta_base_cache_key key; - struct list_head lru; - void *data; - unsigned long size; - enum object_type type; -}; - -static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset) -{ - unsigned int hash; - - hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset; - hash += (hash >> 8) + (hash >> 16); - return hash; -} - -static struct delta_base_cache_entry * -get_delta_base_cache_entry(struct packed_git *p, off_t base_offset) -{ - struct hashmap_entry entry; - struct delta_base_cache_key key; - - if (!delta_base_cache.cmpfn) - return NULL; - - hashmap_entry_init(&entry, pack_entry_hash(p, base_offset)); - key.p = p; - key.base_offset = base_offset; - return hashmap_get(&delta_base_cache, &entry, &key); -} - -static int delta_base_cache_key_eq(const struct delta_base_cache_key *a, - const struct delta_base_cache_key *b) -{ - return a->p == b->p && a->base_offset == b->base_offset; -} - -static int delta_base_cache_hash_cmp(const void *unused_cmp_data, - const void *va, const void *vb, - const void *vkey) -{ - const struct delta_base_cache_entry *a = va, *b = vb; - const struct delta_base_cache_key *key = vkey; - if (key) - return !delta_base_cache_key_eq(&a->key, key); - else - return !delta_base_cache_key_eq(&a->key, &b->key); -} - -static int in_delta_base_cache(struct packed_git *p, off_t base_offset) -{ - return !!get_delta_base_cache_entry(p, base_offset); -} - -/* - * Remove the entry from the cache, but do _not_ free the associated - * entry data. The caller takes ownership of the "data" buffer, and - * should copy out any fields it wants before detaching. - */ -static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent) -{ - hashmap_remove(&delta_base_cache, ent, &ent->key); - list_del(&ent->lru); - delta_base_cached -= ent->size; - free(ent); -} - -static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, - unsigned long *base_size, enum object_type *type) -{ - struct delta_base_cache_entry *ent; - - ent = get_delta_base_cache_entry(p, base_offset); - if (!ent) - return unpack_entry(p, base_offset, type, base_size); - - if (type) - *type = ent->type; - if (base_size) - *base_size = ent->size; - return xmemdupz(ent->data, ent->size); -} - -static inline void release_delta_base_cache(struct delta_base_cache_entry *ent) -{ - free(ent->data); - detach_delta_base_cache_entry(ent); -} - -void clear_delta_base_cache(void) -{ - struct list_head *lru, *tmp; - list_for_each_safe(lru, tmp, &delta_base_cache_lru) { - struct delta_base_cache_entry *entry = - list_entry(lru, struct delta_base_cache_entry, lru); - release_delta_base_cache(entry); - } -} - -static void add_delta_base_cache(struct packed_git *p, off_t base_offset, - void *base, unsigned long base_size, enum object_type type) -{ - struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent)); - struct list_head *lru, *tmp; - - delta_base_cached += base_size; - - list_for_each_safe(lru, tmp, &delta_base_cache_lru) { - struct delta_base_cache_entry *f = - list_entry(lru, struct delta_base_cache_entry, lru); - if (delta_base_cached <= delta_base_cache_limit) - break; - release_delta_base_cache(f); - } - - ent->key.p = p; - ent->key.base_offset = base_offset; - ent->type = type; - ent->data = base; - ent->size = base_size; - list_add_tail(&ent->lru, &delta_base_cache_lru); - - if (!delta_base_cache.cmpfn) - hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0); - hashmap_entry_init(ent, pack_entry_hash(p, base_offset)); - hashmap_add(&delta_base_cache, ent); -} - -int packed_object_info(struct packed_git *p, off_t obj_offset, - struct object_info *oi) -{ - struct pack_window *w_curs = NULL; - unsigned long size; - off_t curpos = obj_offset; - enum object_type type; - - /* - * We always get the representation type, but only convert it to - * a "real" type later if the caller is interested. - */ - if (oi->contentp) { - *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep, - &type); - if (!*oi->contentp) - type = OBJ_BAD; - } else { - type = unpack_object_header(p, &w_curs, &curpos, &size); - } - - if (!oi->contentp && oi->sizep) { - if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - off_t tmp_pos = curpos; - off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos, - type, obj_offset); - if (!base_offset) { - type = OBJ_BAD; - goto out; - } - *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos); - if (*oi->sizep == 0) { - type = OBJ_BAD; - goto out; - } - } else { - *oi->sizep = size; - } - } - - if (oi->disk_sizep) { - struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); - *oi->disk_sizep = revidx[1].offset - obj_offset; - } - - if (oi->typep || oi->typename) { - enum object_type ptot; - ptot = packed_to_object_type(p, obj_offset, type, &w_curs, - curpos); - if (oi->typep) - *oi->typep = ptot; - if (oi->typename) { - const char *tn = typename(ptot); - if (tn) - strbuf_addstr(oi->typename, tn); - } - if (ptot < 0) { - type = OBJ_BAD; - goto out; - } - } - - if (oi->delta_base_sha1) { - if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - const unsigned char *base; - - base = get_delta_base_sha1(p, &w_curs, curpos, - type, obj_offset); - if (!base) { - type = OBJ_BAD; - goto out; - } - - hashcpy(oi->delta_base_sha1, base); - } else - hashclr(oi->delta_base_sha1); - } - - oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED : - OI_PACKED; - -out: - unuse_pack(&w_curs); - return type; -} - -static void *unpack_compressed_entry(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - unsigned long size) -{ - int st; - git_zstream stream; - unsigned char *buffer, *in; - - buffer = xmallocz_gently(size); - if (!buffer) - return NULL; - memset(&stream, 0, sizeof(stream)); - stream.next_out = buffer; - stream.avail_out = size + 1; - - git_inflate_init(&stream); - do { - in = use_pack(p, w_curs, curpos, &stream.avail_in); - stream.next_in = in; - st = git_inflate(&stream, Z_FINISH); - if (!stream.avail_out) - break; /* the payload is larger than it should be */ - curpos += stream.next_in - in; - } while (st == Z_OK || st == Z_BUF_ERROR); - git_inflate_end(&stream); - if ((st != Z_STREAM_END) || stream.total_out != size) { - free(buffer); - return NULL; - } - - return buffer; -} - -static void *read_object(const unsigned char *sha1, enum object_type *type, - unsigned long *size); - -static void write_pack_access_log(struct packed_git *p, off_t obj_offset) -{ - static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS); - trace_printf_key(&pack_access, "%s %"PRIuMAX"\n", - p->pack_name, (uintmax_t)obj_offset); -} - -int do_check_packed_object_crc; - -#define UNPACK_ENTRY_STACK_PREALLOC 64 -struct unpack_entry_stack_ent { - off_t obj_offset; - off_t curpos; - unsigned long size; -}; - -void *unpack_entry(struct packed_git *p, off_t obj_offset, - enum object_type *final_type, unsigned long *final_size) -{ - struct pack_window *w_curs = NULL; - off_t curpos = obj_offset; - void *data = NULL; - unsigned long size; - enum object_type type; - struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC]; - struct unpack_entry_stack_ent *delta_stack = small_delta_stack; - int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC; - int base_from_cache = 0; - - write_pack_access_log(p, obj_offset); - - /* PHASE 1: drill down to the innermost base object */ - for (;;) { - off_t base_offset; - int i; - struct delta_base_cache_entry *ent; - - ent = get_delta_base_cache_entry(p, curpos); - if (ent) { - type = ent->type; - data = ent->data; - size = ent->size; - detach_delta_base_cache_entry(ent); - base_from_cache = 1; - break; - } - - if (do_check_packed_object_crc && p->index_version > 1) { - struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); - off_t len = revidx[1].offset - obj_offset; - if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) { - const unsigned char *sha1 = - nth_packed_object_sha1(p, revidx->nr); - error("bad packed object CRC for %s", - sha1_to_hex(sha1)); - mark_bad_packed_object(p, sha1); - data = NULL; - goto out; - } - } - - type = unpack_object_header(p, &w_curs, &curpos, &size); - if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA) - break; - - base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); - if (!base_offset) { - error("failed to validate delta base reference " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - /* bail to phase 2, in hopes of recovery */ - data = NULL; - break; - } - - /* push object, proceed to base */ - if (delta_stack_nr >= delta_stack_alloc - && delta_stack == small_delta_stack) { - delta_stack_alloc = alloc_nr(delta_stack_nr); - ALLOC_ARRAY(delta_stack, delta_stack_alloc); - memcpy(delta_stack, small_delta_stack, - sizeof(*delta_stack)*delta_stack_nr); - } else { - ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc); - } - i = delta_stack_nr++; - delta_stack[i].obj_offset = obj_offset; - delta_stack[i].curpos = curpos; - delta_stack[i].size = size; - - curpos = obj_offset = base_offset; - } - - /* PHASE 2: handle the base */ - switch (type) { - case OBJ_OFS_DELTA: - case OBJ_REF_DELTA: - if (data) - die("BUG: unpack_entry: left loop at a valid delta"); - break; - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - if (!base_from_cache) - data = unpack_compressed_entry(p, &w_curs, curpos, size); - break; - default: - data = NULL; - error("unknown object type %i at offset %"PRIuMAX" in %s", - type, (uintmax_t)obj_offset, p->pack_name); - } - - /* PHASE 3: apply deltas in order */ - - /* invariants: - * 'data' holds the base data, or NULL if there was corruption - */ - while (delta_stack_nr) { - void *delta_data; - void *base = data; - void *external_base = NULL; - unsigned long delta_size, base_size = size; - int i; - - data = NULL; - - if (base) - add_delta_base_cache(p, obj_offset, base, base_size, type); - - if (!base) { - /* - * We're probably in deep shit, but let's try to fetch - * the required base anyway from another pack or loose. - * This is costly but should happen only in the presence - * of a corrupted pack, and is better than failing outright. - */ - struct revindex_entry *revidx; - const unsigned char *base_sha1; - revidx = find_pack_revindex(p, obj_offset); - if (revidx) { - base_sha1 = nth_packed_object_sha1(p, revidx->nr); - error("failed to read delta base object %s" - " at offset %"PRIuMAX" from %s", - sha1_to_hex(base_sha1), (uintmax_t)obj_offset, - p->pack_name); - mark_bad_packed_object(p, base_sha1); - base = read_object(base_sha1, &type, &base_size); - external_base = base; - } - } - - i = --delta_stack_nr; - obj_offset = delta_stack[i].obj_offset; - curpos = delta_stack[i].curpos; - delta_size = delta_stack[i].size; - - if (!base) - continue; - - delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size); - - if (!delta_data) { - error("failed to unpack compressed delta " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - data = NULL; - free(external_base); - continue; - } - - data = patch_delta(base, base_size, - delta_data, delta_size, - &size); - - /* - * We could not apply the delta; warn the user, but keep going. - * Our failure will be noticed either in the next iteration of - * the loop, or if this is the final delta, in the caller when - * we return NULL. Those code paths will take care of making - * a more explicit warning and retrying with another copy of - * the object. - */ - if (!data) - error("failed to apply delta"); - - free(delta_data); - free(external_base); - } - - if (final_type) - *final_type = type; - if (final_size) - *final_size = size; - -out: - unuse_pack(&w_curs); - - if (delta_stack != small_delta_stack) - free(delta_stack); - - return data; -} - -const unsigned char *nth_packed_object_sha1(struct packed_git *p, - uint32_t n) -{ - const unsigned char *index = p->index_data; - if (!index) { - if (open_pack_index(p)) - return NULL; - index = p->index_data; - } - if (n >= p->num_objects) - return NULL; - index += 4 * 256; - if (p->index_version == 1) { - return index + 24 * n + 4; - } else { - index += 8; - return index + 20 * n; - } -} - -const struct object_id *nth_packed_object_oid(struct object_id *oid, - struct packed_git *p, - uint32_t n) -{ - const unsigned char *hash = nth_packed_object_sha1(p, n); - if (!hash) - return NULL; - hashcpy(oid->hash, hash); - return oid; -} - -void check_pack_index_ptr(const struct packed_git *p, const void *vptr) -{ - const unsigned char *ptr = vptr; - const unsigned char *start = p->index_data; - const unsigned char *end = start + p->index_size; - if (ptr < start) - die(_("offset before start of pack index for %s (corrupt index?)"), - p->pack_name); - /* No need to check for underflow; .idx files must be at least 8 bytes */ - if (ptr >= end - 8) - die(_("offset beyond end of pack index for %s (truncated index?)"), - p->pack_name); -} - -off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) -{ - const unsigned char *index = p->index_data; - index += 4 * 256; - if (p->index_version == 1) { - return ntohl(*((uint32_t *)(index + 24 * n))); - } else { - uint32_t off; - index += 8 + p->num_objects * (20 + 4); - off = ntohl(*((uint32_t *)(index + 4 * n))); - if (!(off & 0x80000000)) - return off; - index += p->num_objects * 4 + (off & 0x7fffffff) * 8; - check_pack_index_ptr(p, index); - return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) | - ntohl(*((uint32_t *)(index + 4))); - } -} - -off_t find_pack_entry_one(const unsigned char *sha1, - struct packed_git *p) -{ - const uint32_t *level1_ofs = p->index_data; - const unsigned char *index = p->index_data; - unsigned hi, lo, stride; - static int debug_lookup = -1; - - if (debug_lookup < 0) - debug_lookup = !!getenv("GIT_DEBUG_LOOKUP"); - - if (!index) { - if (open_pack_index(p)) - return 0; - level1_ofs = p->index_data; - index = p->index_data; - } - if (p->index_version > 1) { - level1_ofs += 2; - index += 8; - } - index += 4 * 256; - hi = ntohl(level1_ofs[*sha1]); - lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); - if (p->index_version > 1) { - stride = 20; - } else { - stride = 24; - index += 4; - } - - if (debug_lookup) - printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n", - sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects); - - while (lo < hi) { - unsigned mi = (lo + hi) / 2; - int cmp = hashcmp(index + mi * stride, sha1); - - if (debug_lookup) - printf("lo %u hi %u rg %u mi %u\n", - lo, hi, hi - lo, mi); - if (!cmp) - return nth_packed_object_offset(p, mi); - if (cmp > 0) - hi = mi; - else - lo = mi+1; - } - return 0; -} - -int is_pack_valid(struct packed_git *p) -{ - /* An already open pack is known to be valid. */ - if (p->pack_fd != -1) - return 1; - - /* If the pack has one window completely covering the - * file size, the pack is known to be valid even if - * the descriptor is not currently open. - */ - if (p->windows) { - struct pack_window *w = p->windows; - - if (!w->offset && w->len == p->pack_size) - return 1; - } - - /* Force the pack to open to prove its valid. */ - return !open_packed_git(p); -} - -static int fill_pack_entry(const unsigned char *sha1, - struct pack_entry *e, - struct packed_git *p) -{ - off_t offset; - - if (p->num_bad_objects) { - unsigned i; - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - return 0; - } - - offset = find_pack_entry_one(sha1, p); - if (!offset) - return 0; - - /* - * We are about to tell the caller where they can locate the - * requested object. We better make sure the packfile is - * still here and can be accessed before supplying that - * answer, as it may have been deleted since the index was - * loaded! - */ - if (!is_pack_valid(p)) - return 0; - e->offset = offset; - e->p = p; - hashcpy(e->sha1, sha1); - return 1; -} - -/* - * Iff a pack file contains the object named by sha1, return true and - * store its location to e. - */ -static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) -{ - struct mru_entry *p; - - prepare_packed_git(); - if (!packed_git) - return 0; - - for (p = packed_git_mru->head; p; p = p->next) { - if (fill_pack_entry(sha1, e, p->item)) { - mru_mark(packed_git_mru, p); - return 1; - } - } - return 0; -} - -struct packed_git *find_sha1_pack(const unsigned char *sha1, - struct packed_git *packs) -{ - struct packed_git *p; - - for (p = packs; p; p = p->next) { - if (find_pack_entry_one(sha1, p)) - return p; - } - return NULL; - -} - static int sha1_loose_object_info(const unsigned char *sha1, struct object_info *oi, int flags) @@ -3053,6 +1231,20 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) return type; } +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) +{ + struct object_info oi = OBJECT_INFO_INIT; + void *content; + oi.typep = type; + oi.sizep = size; + oi.contentp = &content; + + if (sha1_object_info_extended(sha1, &oi, 0) < 0) + return NULL; + return content; +} + int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, unsigned char *sha1) { @@ -3071,20 +1263,6 @@ int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, return 0; } -static void *read_object(const unsigned char *sha1, enum object_type *type, - unsigned long *size) -{ - struct object_info oi = OBJECT_INFO_INIT; - void *content; - oi.typep = type; - oi.sizep = size; - oi.contentp = &content; - - if (sha1_object_info_extended(sha1, &oi, 0) < 0) - return NULL; - return content; -} - /* * This function dies on corrupt objects; the callers who want to * deal with them should arrange to call read_object() and give error @@ -3403,7 +1581,7 @@ int write_sha1_file(const void *buf, unsigned long len, const char *type, unsign } int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, - unsigned char *sha1, unsigned flags) + struct object_id *oid, unsigned flags) { char *header; int hdrlen, status = 0; @@ -3411,13 +1589,13 @@ int hash_sha1_file_literally(const void *buf, unsigned long len, const char *typ /* type string, SP, %lu of the length plus NUL must fit this */ hdrlen = strlen(type) + 32; header = xmalloc(hdrlen); - write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen); + write_sha1_file_prepare(buf, len, type, oid->hash, header, &hdrlen); if (!(flags & HASH_WRITE_OBJECT)) goto cleanup; - if (freshen_packed_object(sha1) || freshen_loose_object(sha1)) + if (freshen_packed_object(oid->hash) || freshen_loose_object(oid->hash)) goto cleanup; - status = write_loose_object(sha1, header, hdrlen, buf, len, 0); + status = write_loose_object(oid->hash, header, hdrlen, buf, len, 0); cleanup: free(header); @@ -3445,20 +1623,6 @@ int force_object_loose(const unsigned char *sha1, time_t mtime) return ret; } -int has_pack_index(const unsigned char *sha1) -{ - struct stat st; - if (stat(sha1_pack_index_name(sha1), &st)) - return 0; - return 1; -} - -int has_sha1_pack(const unsigned char *sha1) -{ - struct pack_entry e; - return find_pack_entry(sha1, &e); -} - int has_sha1_file_with_flags(const unsigned char *sha1, int flags) { if (!startup_info->have_repository) @@ -3621,14 +1785,14 @@ static int index_core(unsigned char *sha1, int fd, size_t size, * binary blobs, they generally do not want to get any conversion, and * callers should avoid this code path when filters are requested. */ -static int index_stream(unsigned char *sha1, int fd, size_t size, +static int index_stream(struct object_id *oid, int fd, size_t size, enum object_type type, const char *path, unsigned flags) { - return index_bulk_checkin(sha1, fd, size, type, path, flags); + return index_bulk_checkin(oid->hash, fd, size, type, path, flags); } -int index_fd(unsigned char *sha1, int fd, struct stat *st, +int index_fd(struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags) { int ret; @@ -3638,21 +1802,21 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, * die() for large files. */ if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path)) - ret = index_stream_convert_blob(sha1, fd, path, flags); + ret = index_stream_convert_blob(oid->hash, fd, path, flags); else if (!S_ISREG(st->st_mode)) - ret = index_pipe(sha1, fd, type, path, flags); + ret = index_pipe(oid->hash, fd, type, path, flags); else if (st->st_size <= big_file_threshold || type != OBJ_BLOB || (path && would_convert_to_git(&the_index, path))) - ret = index_core(sha1, fd, xsize_t(st->st_size), type, path, + ret = index_core(oid->hash, fd, xsize_t(st->st_size), type, path, flags); else - ret = index_stream(sha1, fd, xsize_t(st->st_size), type, path, + ret = index_stream(oid, fd, xsize_t(st->st_size), type, path, flags); close(fd); return ret; } -int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags) +int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags) { int fd; struct strbuf sb = STRBUF_INIT; @@ -3662,7 +1826,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned fd = open(path, O_RDONLY); if (fd < 0) return error_errno("open(\"%s\")", path); - if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0) + if (index_fd(oid, fd, st, OBJ_BLOB, path, flags) < 0) return error("%s: failed to insert into database", path); break; @@ -3670,14 +1834,14 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned if (strbuf_readlink(&sb, path, st->st_size)) return error_errno("readlink(\"%s\")", path); if (!(flags & HASH_WRITE_OBJECT)) - hash_sha1_file(sb.buf, sb.len, blob_type, sha1); - else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1)) + hash_sha1_file(sb.buf, sb.len, blob_type, oid->hash); + else if (write_sha1_file(sb.buf, sb.len, blob_type, oid->hash)) return error("%s: failed to insert into database", path); strbuf_release(&sb); break; case S_IFDIR: - return resolve_gitlink_ref(path, "HEAD", sha1); + return resolve_gitlink_ref(path, "HEAD", oid->hash); default: return error("%s: unsupported file type", path); } @@ -3851,46 +2015,6 @@ int for_each_loose_object(each_loose_object_fn cb, void *data, unsigned flags) return foreach_alt_odb(loose_from_alt_odb, &alt); } -static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) -{ - uint32_t i; - int r = 0; - - for (i = 0; i < p->num_objects; i++) { - struct object_id oid; - - if (!nth_packed_object_oid(&oid, p, i)) - return error("unable to get sha1 of object %u in %s", - i, p->pack_name); - - r = cb(&oid, p, i, data); - if (r) - break; - } - return r; -} - -int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags) -{ - struct packed_git *p; - int r = 0; - int pack_errors = 0; - - prepare_packed_git(); - for (p = packed_git; p; p = p->next) { - if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) - continue; - if (open_pack_index(p)) { - pack_errors = 1; - continue; - } - r = for_each_object_in_pack(p, cb, data); - if (r) - break; - } - return r ? r : pack_errors; -} - static int check_stream_sha1(git_zstream *stream, const char *hdr, unsigned long size, diff --git a/sha1_name.c b/sha1_name.c index 862b6f130..134ac9742 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -9,6 +9,7 @@ #include "remote.h" #include "dir.h" #include "sha1-array.h" +#include "packfile.h" static int get_oid_oneline(const char *, struct object_id *, struct commit_list *); @@ -147,7 +147,10 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) if (len > (sb->alloc ? sb->alloc - 1 : 0)) die("BUG: strbuf_setlen() beyond buffer"); sb->len = len; - sb->buf[len] = '\0'; + if (sb->buf != strbuf_slopbuf) + sb->buf[len] = '\0'; + else + assert(!strbuf_slopbuf[0]); } /** diff --git a/streaming.c b/streaming.c index 9afa66b8b..6f1c60f12 100644 --- a/streaming.c +++ b/streaming.c @@ -3,6 +3,7 @@ */ #include "cache.h" #include "streaming.h" +#include "packfile.h" enum input_source { stream_error = -1, diff --git a/submodule-config.c b/submodule-config.c index 0c839019e..2aa8a1747 100644 --- a/submodule-config.c +++ b/submodule-config.c @@ -18,6 +18,7 @@ struct submodule_cache { struct hashmap for_path; struct hashmap for_name; unsigned initialized:1; + unsigned gitmodules_read:1; }; /* @@ -99,6 +100,7 @@ static void submodule_cache_clear(struct submodule_cache *cache) hashmap_free(&cache->for_path, 1); hashmap_free(&cache->for_name, 1); cache->initialized = 0; + cache->gitmodules_read = 0; } void submodule_cache_free(struct submodule_cache *cache) @@ -455,9 +457,9 @@ static int parse_config(const char *var, const char *value, void *data) return ret; } -int gitmodule_oid_from_commit(const struct object_id *treeish_name, - struct object_id *gitmodules_oid, - struct strbuf *rev) +static int gitmodule_oid_from_commit(const struct object_id *treeish_name, + struct object_id *gitmodules_oid, + struct strbuf *rev) { int ret = 0; @@ -558,13 +560,11 @@ static void submodule_cache_check_init(struct repository *repo) submodule_cache_init(repo->submodule_cache); } -int submodule_config_option(struct repository *repo, - const char *var, const char *value) +static int gitmodules_cb(const char *var, const char *value, void *data) { + struct repository *repo = data; struct parse_config_parameter parameter; - submodule_cache_check_init(repo); - parameter.cache = repo->submodule_cache; parameter.treeish_name = NULL; parameter.gitmodules_sha1 = null_sha1; @@ -573,22 +573,63 @@ int submodule_config_option(struct repository *repo, return parse_config(var, value, ¶meter); } -int parse_submodule_config_option(const char *var, const char *value) +void repo_read_gitmodules(struct repository *repo) { - return submodule_config_option(the_repository, var, value); + submodule_cache_check_init(repo); + + if (repo->worktree) { + char *gitmodules; + + if (repo_read_index(repo) < 0) + return; + + gitmodules = repo_worktree_path(repo, GITMODULES_FILE); + + if (!is_gitmodules_unmerged(repo->index)) + git_config_from_file(gitmodules_cb, gitmodules, repo); + + free(gitmodules); + } + + repo->submodule_cache->gitmodules_read = 1; +} + +void gitmodules_config_oid(const struct object_id *commit_oid) +{ + struct strbuf rev = STRBUF_INIT; + struct object_id oid; + + submodule_cache_check_init(the_repository); + + if (gitmodule_oid_from_commit(commit_oid, &oid, &rev)) { + git_config_from_blob_oid(gitmodules_cb, rev.buf, + &oid, the_repository); + } + strbuf_release(&rev); + + the_repository->submodule_cache->gitmodules_read = 1; +} + +static void gitmodules_read_check(struct repository *repo) +{ + submodule_cache_check_init(repo); + + /* read the repo's .gitmodules file if it hasn't been already */ + if (!repo->submodule_cache->gitmodules_read) + repo_read_gitmodules(repo); } const struct submodule *submodule_from_name(const struct object_id *treeish_name, const char *name) { - submodule_cache_check_init(the_repository); + gitmodules_read_check(the_repository); return config_from(the_repository->submodule_cache, treeish_name, name, lookup_name); } const struct submodule *submodule_from_path(const struct object_id *treeish_name, const char *path) { - submodule_cache_check_init(the_repository); + gitmodules_read_check(the_repository); return config_from(the_repository->submodule_cache, treeish_name, path, lookup_path); } @@ -596,7 +637,7 @@ const struct submodule *submodule_from_cache(struct repository *repo, const struct object_id *treeish_name, const char *key) { - submodule_cache_check_init(repo); + gitmodules_read_check(repo); return config_from(repo->submodule_cache, treeish_name, key, lookup_path); } diff --git a/submodule-config.h b/submodule-config.h index cccd34b92..e3845831f 100644 --- a/submodule-config.h +++ b/submodule-config.h @@ -34,9 +34,8 @@ extern int option_fetch_parse_recurse_submodules(const struct option *opt, const char *arg, int unset); extern int parse_update_recurse_submodules_arg(const char *opt, const char *arg); extern int parse_push_recurse_submodules_arg(const char *opt, const char *arg); -extern int parse_submodule_config_option(const char *var, const char *value); -extern int submodule_config_option(struct repository *repo, - const char *var, const char *value); +extern void repo_read_gitmodules(struct repository *repo); +extern void gitmodules_config_oid(const struct object_id *commit_oid); extern const struct submodule *submodule_from_name( const struct object_id *commit_or_tree, const char *name); extern const struct submodule *submodule_from_path( @@ -44,9 +43,6 @@ extern const struct submodule *submodule_from_path( extern const struct submodule *submodule_from_cache(struct repository *repo, const struct object_id *treeish_name, const char *key); -extern int gitmodule_oid_from_commit(const struct object_id *commit_oid, - struct object_id *gitmodules_oid, - struct strbuf *rev); extern void submodule_free(void); #endif /* SUBMODULE_CONFIG_H */ diff --git a/submodule.c b/submodule.c index e072036e7..3cea8221e 100644 --- a/submodule.c +++ b/submodule.c @@ -165,31 +165,18 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt, { const struct submodule *submodule = submodule_from_path(&null_oid, path); if (submodule) { - if (submodule->ignore) - handle_ignore_submodules_arg(diffopt, submodule->ignore); - else if (is_gitmodules_unmerged(&the_index)) - DIFF_OPT_SET(diffopt, IGNORE_SUBMODULES); - } -} + const char *ignore; + char *key; -/* For loading from the .gitmodules file. */ -static int git_modules_config(const char *var, const char *value, void *cb) -{ - if (starts_with(var, "submodule.")) - return parse_submodule_config_option(var, value); - return 0; -} + key = xstrfmt("submodule.%s.ignore", submodule->name); + if (repo_config_get_string_const(the_repository, key, &ignore)) + ignore = submodule->ignore; + free(key); -/* Loads all submodule settings from the config. */ -int submodule_config(const char *var, const char *value, void *cb) -{ - if (!strcmp(var, "submodule.recurse")) { - int v = git_config_bool(var, value) ? - RECURSE_SUBMODULES_ON : RECURSE_SUBMODULES_OFF; - config_update_recurse_submodules = v; - return 0; - } else { - return git_modules_config(var, value, cb); + if (ignore) + handle_ignore_submodules_arg(diffopt, ignore); + else if (is_gitmodules_unmerged(&the_index)) + DIFF_OPT_SET(diffopt, IGNORE_SUBMODULES); } } @@ -221,55 +208,6 @@ int option_parse_recurse_submodules_worktree_updater(const struct option *opt, return 0; } -void load_submodule_cache(void) -{ - if (config_update_recurse_submodules == RECURSE_SUBMODULES_OFF) - return; - - gitmodules_config(); - git_config(submodule_config, NULL); -} - -static int gitmodules_cb(const char *var, const char *value, void *data) -{ - struct repository *repo = data; - return submodule_config_option(repo, var, value); -} - -void repo_read_gitmodules(struct repository *repo) -{ - if (repo->worktree) { - char *gitmodules; - - if (repo_read_index(repo) < 0) - return; - - gitmodules = repo_worktree_path(repo, GITMODULES_FILE); - - if (!is_gitmodules_unmerged(repo->index)) - git_config_from_file(gitmodules_cb, gitmodules, repo); - - free(gitmodules); - } -} - -void gitmodules_config(void) -{ - repo_read_gitmodules(the_repository); -} - -void gitmodules_config_oid(const struct object_id *commit_oid) -{ - struct strbuf rev = STRBUF_INIT; - struct object_id oid; - - if (gitmodule_oid_from_commit(commit_oid, &oid, &rev)) { - git_config_from_blob_oid(submodule_config, rev.buf, - &oid, NULL); - } - strbuf_release(&rev); -} - /* * Determine if a submodule has been initialized at a given 'path' */ @@ -398,24 +336,38 @@ void die_path_inside_submodule(const struct index_state *istate, } } -int parse_submodule_update_strategy(const char *value, - struct submodule_update_strategy *dst) +enum submodule_update_type parse_submodule_update_type(const char *value) { - free((void*)dst->command); - dst->command = NULL; if (!strcmp(value, "none")) - dst->type = SM_UPDATE_NONE; + return SM_UPDATE_NONE; else if (!strcmp(value, "checkout")) - dst->type = SM_UPDATE_CHECKOUT; + return SM_UPDATE_CHECKOUT; else if (!strcmp(value, "rebase")) - dst->type = SM_UPDATE_REBASE; + return SM_UPDATE_REBASE; else if (!strcmp(value, "merge")) - dst->type = SM_UPDATE_MERGE; - else if (skip_prefix(value, "!", &value)) { - dst->type = SM_UPDATE_COMMAND; - dst->command = xstrdup(value); - } else + return SM_UPDATE_MERGE; + else if (*value == '!') + return SM_UPDATE_COMMAND; + else + return SM_UPDATE_UNSPECIFIED; +} + +int parse_submodule_update_strategy(const char *value, + struct submodule_update_strategy *dst) +{ + enum submodule_update_type type; + + free((void*)dst->command); + dst->command = NULL; + + type = parse_submodule_update_type(value); + if (type == SM_UPDATE_UNSPECIFIED) return -1; + + dst->type = type; + if (type == SM_UPDATE_COMMAND) + dst->command = xstrdup(value + 1); + return 0; } @@ -478,9 +430,7 @@ static int prepare_submodule_summary(struct rev_info *rev, const char *path, return prepare_revision_walk(rev); } -static void print_submodule_summary(struct rev_info *rev, FILE *f, - const char *line_prefix, - const char *del, const char *add, const char *reset) +static void print_submodule_summary(struct rev_info *rev, struct diff_options *o) { static const char format[] = " %m %s"; struct strbuf sb = STRBUF_INIT; @@ -491,18 +441,12 @@ static void print_submodule_summary(struct rev_info *rev, FILE *f, ctx.date_mode = rev->date_mode; ctx.output_encoding = get_log_output_encoding(); strbuf_setlen(&sb, 0); - strbuf_addstr(&sb, line_prefix); - if (commit->object.flags & SYMMETRIC_LEFT) { - if (del) - strbuf_addstr(&sb, del); - } - else if (add) - strbuf_addstr(&sb, add); format_commit_message(commit, format, &sb, &ctx); - if (reset) - strbuf_addstr(&sb, reset); strbuf_addch(&sb, '\n'); - fprintf(f, "%s", sb.buf); + if (commit->object.flags & SYMMETRIC_LEFT) + diff_emit_submodule_del(o, sb.buf); + else + diff_emit_submodule_add(o, sb.buf); } strbuf_release(&sb); } @@ -529,11 +473,9 @@ void prepare_submodule_repo_env(struct argv_array *out) * attempt to lookup both the left and right commits and put them into the * left and right pointers. */ -static void show_submodule_header(FILE *f, const char *path, - const char *line_prefix, +static void show_submodule_header(struct diff_options *o, const char *path, struct object_id *one, struct object_id *two, - unsigned dirty_submodule, const char *meta, - const char *reset, + unsigned dirty_submodule, struct commit **left, struct commit **right, struct commit_list **merge_bases) { @@ -542,11 +484,10 @@ static void show_submodule_header(FILE *f, const char *path, int fast_forward = 0, fast_backward = 0; if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED) - fprintf(f, "%sSubmodule %s contains untracked content\n", - line_prefix, path); + diff_emit_submodule_untracked(o, path); + if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED) - fprintf(f, "%sSubmodule %s contains modified content\n", - line_prefix, path); + diff_emit_submodule_modified(o, path); if (is_null_oid(one)) message = "(new submodule)"; @@ -588,31 +529,29 @@ static void show_submodule_header(FILE *f, const char *path, } output_header: - strbuf_addf(&sb, "%s%sSubmodule %s ", line_prefix, meta, path); + strbuf_addf(&sb, "Submodule %s ", path); strbuf_add_unique_abbrev(&sb, one->hash, DEFAULT_ABBREV); strbuf_addstr(&sb, (fast_backward || fast_forward) ? ".." : "..."); strbuf_add_unique_abbrev(&sb, two->hash, DEFAULT_ABBREV); if (message) - strbuf_addf(&sb, " %s%s\n", message, reset); + strbuf_addf(&sb, " %s\n", message); else - strbuf_addf(&sb, "%s:%s\n", fast_backward ? " (rewind)" : "", reset); - fwrite(sb.buf, sb.len, 1, f); + strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : ""); + diff_emit_submodule_header(o, sb.buf); strbuf_release(&sb); } -void show_submodule_summary(FILE *f, const char *path, - const char *line_prefix, +void show_submodule_summary(struct diff_options *o, const char *path, struct object_id *one, struct object_id *two, - unsigned dirty_submodule, const char *meta, - const char *del, const char *add, const char *reset) + unsigned dirty_submodule) { struct rev_info rev; struct commit *left = NULL, *right = NULL; struct commit_list *merge_bases = NULL; - show_submodule_header(f, path, line_prefix, one, two, dirty_submodule, - meta, reset, &left, &right, &merge_bases); + show_submodule_header(o, path, one, two, dirty_submodule, + &left, &right, &merge_bases); /* * If we don't have both a left and a right pointer, there is no @@ -624,11 +563,11 @@ void show_submodule_summary(FILE *f, const char *path, /* Treat revision walker failure the same as missing commits */ if (prepare_submodule_summary(&rev, path, left, right, merge_bases)) { - fprintf(f, "%s(revision walker failed)\n", line_prefix); + diff_emit_submodule_error(o, "(revision walker failed)\n"); goto out; } - print_submodule_summary(&rev, f, line_prefix, del, add, reset); + print_submodule_summary(&rev, o); out: if (merge_bases) @@ -637,21 +576,18 @@ out: clear_commit_marks(right, ~0); } -void show_submodule_inline_diff(FILE *f, const char *path, - const char *line_prefix, +void show_submodule_inline_diff(struct diff_options *o, const char *path, struct object_id *one, struct object_id *two, - unsigned dirty_submodule, const char *meta, - const char *del, const char *add, const char *reset, - const struct diff_options *o) + unsigned dirty_submodule) { const struct object_id *old = &empty_tree_oid, *new = &empty_tree_oid; struct commit *left = NULL, *right = NULL; struct commit_list *merge_bases = NULL; - struct strbuf submodule_dir = STRBUF_INIT; struct child_process cp = CHILD_PROCESS_INIT; + struct strbuf sb = STRBUF_INIT; - show_submodule_header(f, path, line_prefix, one, two, dirty_submodule, - meta, reset, &left, &right, &merge_bases); + show_submodule_header(o, path, one, two, dirty_submodule, + &left, &right, &merge_bases); /* We need a valid left and right commit to display a difference */ if (!(left || is_null_oid(one)) || @@ -663,16 +599,16 @@ void show_submodule_inline_diff(FILE *f, const char *path, if (right) new = two; - fflush(f); cp.git_cmd = 1; cp.dir = path; - cp.out = dup(fileno(f)); + cp.out = -1; cp.no_stdin = 1; /* TODO: other options may need to be passed here. */ argv_array_pushl(&cp.args, "diff", "--submodule=diff", NULL); + argv_array_pushf(&cp.args, "--color=%s", want_color(o->use_color) ? + "always" : "never"); - argv_array_pushf(&cp.args, "--line-prefix=%s", line_prefix); if (DIFF_OPT_TST(o, REVERSE_DIFF)) { argv_array_pushf(&cp.args, "--src-prefix=%s%s/", o->b_prefix, path); @@ -695,11 +631,17 @@ void show_submodule_inline_diff(FILE *f, const char *path, argv_array_push(&cp.args, oid_to_hex(new)); prepare_submodule_repo_env(&cp.env_array); - if (run_command(&cp)) - fprintf(f, "(diff failed)\n"); + if (start_command(&cp)) + diff_emit_submodule_error(o, "(diff failed)\n"); + + while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF) + diff_emit_submodule_pipethrough(o, sb.buf, sb.len); + + if (finish_command(&cp)) + diff_emit_submodule_error(o, "(diff failed)\n"); done: - strbuf_release(&submodule_dir); + strbuf_release(&sb); if (merge_bases) free_commit_list(merge_bases); if (left) @@ -1140,7 +1082,6 @@ int submodule_touches_in_range(struct object_id *excl_oid, struct argv_array args = ARGV_ARRAY_INIT; int ret; - gitmodules_config(); /* No need to check if there are no submodules configured */ if (!submodule_from_path(NULL, NULL)) return 0; @@ -1189,19 +1130,27 @@ static int get_next_submodule(struct child_process *cp, continue; submodule = submodule_from_path(&null_oid, ce->name); - if (!submodule) - submodule = submodule_from_name(&null_oid, ce->name); default_argv = "yes"; if (spf->command_line_option == RECURSE_SUBMODULES_DEFAULT) { - if (submodule && - submodule->fetch_recurse != - RECURSE_SUBMODULES_NONE) { - if (submodule->fetch_recurse == - RECURSE_SUBMODULES_OFF) + int fetch_recurse = RECURSE_SUBMODULES_NONE; + + if (submodule) { + char *key; + const char *value; + + fetch_recurse = submodule->fetch_recurse; + key = xstrfmt("submodule.%s.fetchRecurseSubmodules", submodule->name); + if (!repo_config_get_string_const(the_repository, key, &value)) { + fetch_recurse = parse_fetch_recurse_submodules_arg(key, value); + } + free(key); + } + + if (fetch_recurse != RECURSE_SUBMODULES_NONE) { + if (fetch_recurse == RECURSE_SUBMODULES_OFF) continue; - if (submodule->fetch_recurse == - RECURSE_SUBMODULES_ON_DEMAND) { + if (fetch_recurse == RECURSE_SUBMODULES_ON_DEMAND) { if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name)) continue; default_argv = "on-demand"; @@ -2039,7 +1988,6 @@ int submodule_to_gitdir(struct strbuf *buf, const char *submodule) strbuf_addstr(buf, git_dir); } if (!is_git_directory(buf->buf)) { - gitmodules_config(); sub = submodule_from_path(&null_oid, submodule); if (!sub) { ret = -1; diff --git a/submodule.h b/submodule.h index e402b004f..6b52133c8 100644 --- a/submodule.h +++ b/submodule.h @@ -40,16 +40,11 @@ extern int remove_path_from_gitmodules(const char *path); extern void stage_updated_gitmodules(void); extern void set_diffopt_flags_from_submodule_config(struct diff_options *, const char *path); -extern int submodule_config(const char *var, const char *value, void *cb); extern int git_default_submodule_config(const char *var, const char *value, void *cb); struct option; int option_parse_recurse_submodules_worktree_updater(const struct option *opt, const char *arg, int unset); -void load_submodule_cache(void); -extern void gitmodules_config(void); -extern void repo_read_gitmodules(struct repository *repo); -extern void gitmodules_config_oid(const struct object_id *commit_oid); extern int is_submodule_active(struct repository *repo, const char *path); /* * Determine if a submodule has been populated at a given 'path' by checking if @@ -62,21 +57,17 @@ extern void die_in_unpopulated_submodule(const struct index_state *istate, const char *prefix); extern void die_path_inside_submodule(const struct index_state *istate, const struct pathspec *ps); +extern enum submodule_update_type parse_submodule_update_type(const char *value); extern int parse_submodule_update_strategy(const char *value, struct submodule_update_strategy *dst); extern const char *submodule_strategy_to_string(const struct submodule_update_strategy *s); extern void handle_ignore_submodules_arg(struct diff_options *, const char *); -extern void show_submodule_summary(FILE *f, const char *path, - const char *line_prefix, +extern void show_submodule_summary(struct diff_options *o, const char *path, struct object_id *one, struct object_id *two, - unsigned dirty_submodule, const char *meta, - const char *del, const char *add, const char *reset); -extern void show_submodule_inline_diff(FILE *f, const char *path, - const char *line_prefix, + unsigned dirty_submodule); +extern void show_submodule_inline_diff(struct diff_options *o, const char *path, struct object_id *one, struct object_id *two, - unsigned dirty_submodule, const char *meta, - const char *del, const char *add, const char *reset, - const struct diff_options *opt); + unsigned dirty_submodule); /* Check if we want to update any submodule.*/ extern int should_update_submodules(void); /* diff --git a/t/helper/test-submodule-config.c b/t/helper/test-submodule-config.c index e13fbcc1b..f23db3b19 100644 --- a/t/helper/test-submodule-config.c +++ b/t/helper/test-submodule-config.c @@ -10,11 +10,6 @@ static void die_usage(int argc, const char **argv, const char *msg) exit(1); } -static int git_test_config(const char *var, const char *value, void *cb) -{ - return parse_submodule_config_option(var, value); -} - int cmd_main(int argc, const char **argv) { const char **arg = argv; @@ -37,8 +32,6 @@ int cmd_main(int argc, const char **argv) die_usage(argc, argv, "Wrong number of arguments."); setup_git_directory(); - gitmodules_config(); - git_config(git_test_config, NULL); while (*arg) { struct object_id commit_oid; diff --git a/t/helper/test-write-cache.c b/t/helper/test-write-cache.c new file mode 100644 index 000000000..b7ee03966 --- /dev/null +++ b/t/helper/test-write-cache.c @@ -0,0 +1,23 @@ +#include "cache.h" +#include "lockfile.h" + +static struct lock_file index_lock; + +int cmd_main(int argc, const char **argv) +{ + int i, cnt = 1, lockfd; + if (argc == 2) + cnt = strtol(argv[1], NULL, 0); + setup_git_directory(); + read_cache(); + for (i = 0; i < cnt; i++) { + lockfd = hold_locked_index(&index_lock, LOCK_DIE_ON_ERROR); + if (0 <= lockfd) { + write_locked_index(&the_index, &index_lock, COMMIT_LOCK); + } else { + rollback_lock_file(&index_lock); + } + } + + return 0; +} diff --git a/t/perf/p0007-write-cache.sh b/t/perf/p0007-write-cache.sh new file mode 100755 index 000000000..261fe92fd --- /dev/null +++ b/t/perf/p0007-write-cache.sh @@ -0,0 +1,29 @@ +#!/bin/sh + +test_description="Tests performance of writing the index" + +. ./perf-lib.sh + +test_perf_default_repo + +test_expect_success "setup repo" ' + if git rev-parse --verify refs/heads/p0006-ballast^{commit} + then + echo Assuming synthetic repo from many-files.sh + git config --local core.sparsecheckout 1 + cat >.git/info/sparse-checkout <<-EOF + /* + !ballast/* + EOF + else + echo Assuming non-synthetic repo... + fi && + nr_files=$(git ls-files | wc -l) +' + +count=3 +test_perf "write_locked_index $count times ($nr_files files)" " + test-write-cache $count +" + +test_done diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh index 9d707d2a4..51738fb96 100755 --- a/t/t3200-branch.sh +++ b/t/t3200-branch.sh @@ -559,6 +559,7 @@ test_expect_success 'use --set-upstream-to modify HEAD' ' test_expect_success 'use --set-upstream-to modify a particular branch' ' git branch my13 && git branch --set-upstream-to master my13 && + test_when_finished "git branch --unset-upstream my13" && test "$(git config branch.my13.remote)" = "." && test "$(git config branch.my13.merge)" = "refs/heads/master" ' @@ -604,38 +605,8 @@ test_expect_success 'test --unset-upstream on a particular branch' ' test_must_fail git config branch.my14.merge ' -test_expect_success '--set-upstream shows message when creating a new branch that exists as remote-tracking' ' - git update-ref refs/remotes/origin/master HEAD && - git branch --set-upstream origin/master 2>actual && - test_when_finished git update-ref -d refs/remotes/origin/master && - test_when_finished git branch -d origin/master && - cat >expected <<EOF && -The --set-upstream flag is deprecated and will be removed. Consider using --track or --set-upstream-to - -If you wanted to make '"'master'"' track '"'origin/master'"', do this: - - git branch -d origin/master - git branch --set-upstream-to origin/master -EOF - test_i18ncmp expected actual -' - -test_expect_success '--set-upstream with two args only shows the deprecation message' ' - git branch --set-upstream master my13 2>actual && - test_when_finished git branch --unset-upstream master && - cat >expected <<EOF && -The --set-upstream flag is deprecated and will be removed. Consider using --track or --set-upstream-to -EOF - test_i18ncmp expected actual -' - -test_expect_success '--set-upstream with one arg only shows the deprecation message if the branch existed' ' - git branch --set-upstream my13 2>actual && - test_when_finished git branch --unset-upstream my13 && - cat >expected <<EOF && -The --set-upstream flag is deprecated and will be removed. Consider using --track or --set-upstream-to -EOF - test_i18ncmp expected actual +test_expect_success '--set-upstream fails' ' + test_must_fail git branch --set-upstream origin/master ' test_expect_success '--set-upstream-to notices an error to set branch as own upstream' ' @@ -960,19 +931,6 @@ test_expect_success 'attempt to delete a branch merged to its base' ' test_must_fail git branch -d my10 ' -test_expect_success 'use set-upstream on the current branch' ' - git checkout master && - git --bare init myupstream.git && - git push myupstream.git master:refs/heads/frotz && - git remote add origin myupstream.git && - git fetch && - git branch --set-upstream master origin/frotz && - - test "z$(git config branch.master.remote)" = "zorigin" && - test "z$(git config branch.master.merge)" = "zrefs/heads/frotz" - -' - test_expect_success 'use --edit-description' ' write_script editor <<-\EOF && echo "New contents" >"$1" diff --git a/t/t3903-stash.sh b/t/t3903-stash.sh index 4046817d7..3b1ac1971 100755 --- a/t/t3903-stash.sh +++ b/t/t3903-stash.sh @@ -444,6 +444,14 @@ test_expect_failure 'stash file to directory' ' test foo = "$(cat file/file)" ' +test_expect_success 'stash create - no changes' ' + git stash clear && + test_when_finished "git reset --hard HEAD" && + git reset --hard && + git stash create >actual && + test_must_be_empty actual +' + test_expect_success 'stash branch - no stashes on stack, stash-like argument' ' git stash clear && test_when_finished "git reset --hard HEAD" && @@ -648,6 +656,20 @@ test_expect_success 'stash branch should not drop the stash if the branch exists git rev-parse stash@{0} -- ' +test_expect_success 'stash branch should not drop the stash if the apply fails' ' + git stash clear && + git reset HEAD~1 --hard && + echo foo >file && + git add file && + git commit -m initial && + echo bar >file && + git stash && + echo baz >file && + test_when_finished "git checkout master" && + test_must_fail git stash branch new_branch stash@{0} && + git rev-parse stash@{0} -- +' + test_expect_success 'stash apply shows status same as git status (relative to current directory)' ' git stash clear && echo 1 >subdir/subfile1 && @@ -800,6 +822,18 @@ test_expect_success 'create with multiple arguments for the message' ' test_cmp expect actual ' +test_expect_success 'create in a detached state' ' + test_when_finished "git checkout master" && + git checkout HEAD~1 && + >foo && + git add foo && + STASH_ID=$(git stash create) && + HEAD_ID=$(git rev-parse --short HEAD) && + echo "WIP on (no branch): ${HEAD_ID} initial" >expect && + git show --pretty=%s -s ${STASH_ID} >actual && + test_cmp expect actual +' + test_expect_success 'stash -- <pathspec> stashes and restores the file' ' >foo && >bar && diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh index 289806d0c..12d182dc1 100755 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@ -972,4 +972,563 @@ test_expect_success 'option overrides diff.wsErrorHighlight' ' ' +test_expect_success 'detect moved code, complete file' ' + git reset --hard && + cat <<-\EOF >test.c && + #include<stdio.h> + main() + { + printf("Hello World"); + } + EOF + git add test.c && + git commit -m "add main function" && + git mv test.c main.c && + test_config color.diff.oldMoved "normal red" && + test_config color.diff.newMoved "normal green" && + git diff HEAD --color-moved=zebra --no-renames | test_decode_color >actual && + cat >expected <<-\EOF && + <BOLD>diff --git a/main.c b/main.c<RESET> + <BOLD>new file mode 100644<RESET> + <BOLD>index 0000000..a986c57<RESET> + <BOLD>--- /dev/null<RESET> + <BOLD>+++ b/main.c<RESET> + <CYAN>@@ -0,0 +1,5 @@<RESET> + <BGREEN>+<RESET><BGREEN>#include<stdio.h><RESET> + <BGREEN>+<RESET><BGREEN>main()<RESET> + <BGREEN>+<RESET><BGREEN>{<RESET> + <BGREEN>+<RESET><BGREEN>printf("Hello World");<RESET> + <BGREEN>+<RESET><BGREEN>}<RESET> + <BOLD>diff --git a/test.c b/test.c<RESET> + <BOLD>deleted file mode 100644<RESET> + <BOLD>index a986c57..0000000<RESET> + <BOLD>--- a/test.c<RESET> + <BOLD>+++ /dev/null<RESET> + <CYAN>@@ -1,5 +0,0 @@<RESET> + <BRED>-#include<stdio.h><RESET> + <BRED>-main()<RESET> + <BRED>-{<RESET> + <BRED>-printf("Hello World");<RESET> + <BRED>-}<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success 'detect malicious moved code, inside file' ' + test_config color.diff.oldMoved "normal red" && + test_config color.diff.newMoved "normal green" && + test_config color.diff.oldMovedAlternative "blue" && + test_config color.diff.newMovedAlternative "yellow" && + git reset --hard && + cat <<-\EOF >main.c && + #include<stdio.h> + int stuff() + { + printf("Hello "); + printf("World\n"); + } + + int secure_foo(struct user *u) + { + if (!u->is_allowed_foo) + return; + foo(u); + } + + int main() + { + foo(); + } + EOF + cat <<-\EOF >test.c && + #include<stdio.h> + int bar() + { + printf("Hello World, but different\n"); + } + + int another_function() + { + bar(); + } + EOF + git add main.c test.c && + git commit -m "add main and test file" && + cat <<-\EOF >main.c && + #include<stdio.h> + int stuff() + { + printf("Hello "); + printf("World\n"); + } + + int main() + { + foo(); + } + EOF + cat <<-\EOF >test.c && + #include<stdio.h> + int bar() + { + printf("Hello World, but different\n"); + } + + int secure_foo(struct user *u) + { + foo(u); + if (!u->is_allowed_foo) + return; + } + + int another_function() + { + bar(); + } + EOF + git diff HEAD --no-renames --color-moved=zebra| test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/main.c b/main.c<RESET> + <BOLD>index 27a619c..7cf9336 100644<RESET> + <BOLD>--- a/main.c<RESET> + <BOLD>+++ b/main.c<RESET> + <CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET> + printf("World\n");<RESET> + }<RESET> + <RESET> + <BRED>-int secure_foo(struct user *u)<RESET> + <BRED>-{<RESET> + <BLUE>-if (!u->is_allowed_foo)<RESET> + <BLUE>-return;<RESET> + <RED>-foo(u);<RESET> + <RED>-}<RESET> + <RED>-<RESET> + int main()<RESET> + {<RESET> + foo();<RESET> + <BOLD>diff --git a/test.c b/test.c<RESET> + <BOLD>index 1dc1d85..2bedec9 100644<RESET> + <BOLD>--- a/test.c<RESET> + <BOLD>+++ b/test.c<RESET> + <CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET> + printf("Hello World, but different\n");<RESET> + }<RESET> + <RESET> + <BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET> + <BGREEN>+<RESET><BGREEN>{<RESET> + <GREEN>+<RESET><GREEN>foo(u);<RESET> + <BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET> + <BGREEN>+<RESET><BGREEN>return;<RESET> + <GREEN>+<RESET><GREEN>}<RESET> + <GREEN>+<RESET> + int another_function()<RESET> + {<RESET> + bar();<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success 'plain moved code, inside file' ' + test_config color.diff.oldMoved "normal red" && + test_config color.diff.newMoved "normal green" && + test_config color.diff.oldMovedAlternative "blue" && + test_config color.diff.newMovedAlternative "yellow" && + # needs previous test as setup + git diff HEAD --no-renames --color-moved=plain| test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/main.c b/main.c<RESET> + <BOLD>index 27a619c..7cf9336 100644<RESET> + <BOLD>--- a/main.c<RESET> + <BOLD>+++ b/main.c<RESET> + <CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET> + printf("World\n");<RESET> + }<RESET> + <RESET> + <BRED>-int secure_foo(struct user *u)<RESET> + <BRED>-{<RESET> + <BRED>-if (!u->is_allowed_foo)<RESET> + <BRED>-return;<RESET> + <BRED>-foo(u);<RESET> + <BRED>-}<RESET> + <BRED>-<RESET> + int main()<RESET> + {<RESET> + foo();<RESET> + <BOLD>diff --git a/test.c b/test.c<RESET> + <BOLD>index 1dc1d85..2bedec9 100644<RESET> + <BOLD>--- a/test.c<RESET> + <BOLD>+++ b/test.c<RESET> + <CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET> + printf("Hello World, but different\n");<RESET> + }<RESET> + <RESET> + <BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET> + <BGREEN>+<RESET><BGREEN>{<RESET> + <BGREEN>+<RESET><BGREEN>foo(u);<RESET> + <BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET> + <BGREEN>+<RESET><BGREEN>return;<RESET> + <BGREEN>+<RESET><BGREEN>}<RESET> + <BGREEN>+<RESET> + int another_function()<RESET> + {<RESET> + bar();<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success 'detect permutations inside moved code -- dimmed_zebra' ' + git reset --hard && + cat <<-\EOF >lines.txt && + long line 1 + long line 2 + long line 3 + line 4 + line 5 + line 6 + line 7 + line 8 + line 9 + line 10 + line 11 + line 12 + line 13 + long line 14 + long line 15 + long line 16 + EOF + git add lines.txt && + git commit -m "add poetry" && + cat <<-\EOF >lines.txt && + line 4 + line 5 + line 6 + line 7 + line 8 + line 9 + long line 1 + long line 2 + long line 3 + long line 14 + long line 15 + long line 16 + line 10 + line 11 + line 12 + line 13 + EOF + test_config color.diff.oldMoved "magenta" && + test_config color.diff.newMoved "cyan" && + test_config color.diff.oldMovedAlternative "blue" && + test_config color.diff.newMovedAlternative "yellow" && + test_config color.diff.oldMovedDimmed "normal magenta" && + test_config color.diff.newMovedDimmed "normal cyan" && + test_config color.diff.oldMovedAlternativeDimmed "normal blue" && + test_config color.diff.newMovedAlternativeDimmed "normal yellow" && + git diff HEAD --no-renames --color-moved=dimmed_zebra | + grep -v "index" | + test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/lines.txt b/lines.txt<RESET> + <BOLD>--- a/lines.txt<RESET> + <BOLD>+++ b/lines.txt<RESET> + <CYAN>@@ -1,16 +1,16 @@<RESET> + <BMAGENTA>-long line 1<RESET> + <BMAGENTA>-long line 2<RESET> + <BMAGENTA>-long line 3<RESET> + line 4<RESET> + line 5<RESET> + line 6<RESET> + line 7<RESET> + line 8<RESET> + line 9<RESET> + <BCYAN>+<RESET><BCYAN>long line 1<RESET> + <BCYAN>+<RESET><BCYAN>long line 2<RESET> + <CYAN>+<RESET><CYAN>long line 3<RESET> + <YELLOW>+<RESET><YELLOW>long line 14<RESET> + <BYELLOW>+<RESET><BYELLOW>long line 15<RESET> + <BYELLOW>+<RESET><BYELLOW>long line 16<RESET> + line 10<RESET> + line 11<RESET> + line 12<RESET> + line 13<RESET> + <BMAGENTA>-long line 14<RESET> + <BMAGENTA>-long line 15<RESET> + <BMAGENTA>-long line 16<RESET> + EOF + test_cmp expected actual +' + +test_expect_success 'cmd option assumes configured colored-moved' ' + test_config color.diff.oldMoved "magenta" && + test_config color.diff.newMoved "cyan" && + test_config color.diff.oldMovedAlternative "blue" && + test_config color.diff.newMovedAlternative "yellow" && + test_config color.diff.oldMovedDimmed "normal magenta" && + test_config color.diff.newMovedDimmed "normal cyan" && + test_config color.diff.oldMovedAlternativeDimmed "normal blue" && + test_config color.diff.newMovedAlternativeDimmed "normal yellow" && + test_config diff.colorMoved zebra && + git diff HEAD --no-renames --color-moved | + grep -v "index" | + test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/lines.txt b/lines.txt<RESET> + <BOLD>--- a/lines.txt<RESET> + <BOLD>+++ b/lines.txt<RESET> + <CYAN>@@ -1,16 +1,16 @@<RESET> + <MAGENTA>-long line 1<RESET> + <MAGENTA>-long line 2<RESET> + <MAGENTA>-long line 3<RESET> + line 4<RESET> + line 5<RESET> + line 6<RESET> + line 7<RESET> + line 8<RESET> + line 9<RESET> + <CYAN>+<RESET><CYAN>long line 1<RESET> + <CYAN>+<RESET><CYAN>long line 2<RESET> + <CYAN>+<RESET><CYAN>long line 3<RESET> + <YELLOW>+<RESET><YELLOW>long line 14<RESET> + <YELLOW>+<RESET><YELLOW>long line 15<RESET> + <YELLOW>+<RESET><YELLOW>long line 16<RESET> + line 10<RESET> + line 11<RESET> + line 12<RESET> + line 13<RESET> + <MAGENTA>-long line 14<RESET> + <MAGENTA>-long line 15<RESET> + <MAGENTA>-long line 16<RESET> + EOF + test_cmp expected actual +' + +test_expect_success 'no effect from --color-moved with --word-diff' ' + cat <<-\EOF >text.txt && + Lorem Ipsum is simply dummy text of the printing and typesetting industry. + EOF + git add text.txt && + git commit -a -m "clean state" && + cat <<-\EOF >text.txt && + simply Lorem Ipsum dummy is text of the typesetting and printing industry. + EOF + git diff --color-moved --word-diff >actual && + git diff --word-diff >expect && + test_cmp expect actual +' + +test_expect_success 'move detection ignoring whitespace ' ' + git reset --hard && + cat <<\EOF >lines.txt && +line 1 +line 2 +line 3 +line 4 +long line 5 +long line 6 +long line 7 +EOF + git add lines.txt && + git commit -m "add poetry" && + cat <<\EOF >lines.txt && + long line 5 + long line 6 + long line 7 +line 1 +line 2 +line 3 +line 4 +EOF + test_config color.diff.oldMoved "magenta" && + test_config color.diff.newMoved "cyan" && + git diff HEAD --no-renames --color-moved | + grep -v "index" | + test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/lines.txt b/lines.txt<RESET> + <BOLD>--- a/lines.txt<RESET> + <BOLD>+++ b/lines.txt<RESET> + <CYAN>@@ -1,7 +1,7 @@<RESET> + <GREEN>+<RESET> <GREEN>long line 5<RESET> + <GREEN>+<RESET> <GREEN>long line 6<RESET> + <GREEN>+<RESET> <GREEN>long line 7<RESET> + line 1<RESET> + line 2<RESET> + line 3<RESET> + line 4<RESET> + <RED>-long line 5<RESET> + <RED>-long line 6<RESET> + <RED>-long line 7<RESET> + EOF + test_cmp expected actual && + + git diff HEAD --no-renames -w --color-moved | + grep -v "index" | + test_decode_color >actual && + cat <<-\EOF >expected && + <BOLD>diff --git a/lines.txt b/lines.txt<RESET> + <BOLD>--- a/lines.txt<RESET> + <BOLD>+++ b/lines.txt<RESET> + <CYAN>@@ -1,7 +1,7 @@<RESET> + <CYAN>+<RESET> <CYAN>long line 5<RESET> + <CYAN>+<RESET> <CYAN>long line 6<RESET> + <CYAN>+<RESET> <CYAN>long line 7<RESET> + line 1<RESET> + line 2<RESET> + line 3<RESET> + line 4<RESET> + <MAGENTA>-long line 5<RESET> + <MAGENTA>-long line 6<RESET> + <MAGENTA>-long line 7<RESET> + EOF + test_cmp expected actual +' + +test_expect_success '--color-moved block at end of diff output respects MIN_ALNUM_COUNT' ' + git reset --hard && + >bar && + cat <<-\EOF >foo && + irrelevant_line + line1 + EOF + git add foo bar && + git commit -m x && + + cat <<-\EOF >bar && + line1 + EOF + cat <<-\EOF >foo && + irrelevant_line + EOF + + git diff HEAD --color-moved=zebra --no-renames | + grep -v "index" | + test_decode_color >actual && + cat >expected <<-\EOF && + <BOLD>diff --git a/bar b/bar<RESET> + <BOLD>--- a/bar<RESET> + <BOLD>+++ b/bar<RESET> + <CYAN>@@ -0,0 +1 @@<RESET> + <GREEN>+<RESET><GREEN>line1<RESET> + <BOLD>diff --git a/foo b/foo<RESET> + <BOLD>--- a/foo<RESET> + <BOLD>+++ b/foo<RESET> + <CYAN>@@ -1,2 +1 @@<RESET> + irrelevant_line<RESET> + <RED>-line1<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success '--color-moved respects MIN_ALNUM_COUNT' ' + git reset --hard && + cat <<-\EOF >foo && + nineteen chars 456789 + irrelevant_line + twenty chars 234567890 + EOF + >bar && + git add foo bar && + git commit -m x && + + cat <<-\EOF >foo && + irrelevant_line + EOF + cat <<-\EOF >bar && + twenty chars 234567890 + nineteen chars 456789 + EOF + + git diff HEAD --color-moved=zebra --no-renames | + grep -v "index" | + test_decode_color >actual && + cat >expected <<-\EOF && + <BOLD>diff --git a/bar b/bar<RESET> + <BOLD>--- a/bar<RESET> + <BOLD>+++ b/bar<RESET> + <CYAN>@@ -0,0 +1,2 @@<RESET> + <BOLD;CYAN>+<RESET><BOLD;CYAN>twenty chars 234567890<RESET> + <GREEN>+<RESET><GREEN>nineteen chars 456789<RESET> + <BOLD>diff --git a/foo b/foo<RESET> + <BOLD>--- a/foo<RESET> + <BOLD>+++ b/foo<RESET> + <CYAN>@@ -1,3 +1 @@<RESET> + <RED>-nineteen chars 456789<RESET> + irrelevant_line<RESET> + <BOLD;MAGENTA>-twenty chars 234567890<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success '--color-moved treats adjacent blocks as separate for MIN_ALNUM_COUNT' ' + git reset --hard && + cat <<-\EOF >foo && + 7charsA + irrelevant_line + 7charsB + 7charsC + EOF + >bar && + git add foo bar && + git commit -m x && + + cat <<-\EOF >foo && + irrelevant_line + EOF + cat <<-\EOF >bar && + 7charsB + 7charsC + 7charsA + EOF + + git diff HEAD --color-moved=zebra --no-renames | grep -v "index" | test_decode_color >actual && + cat >expected <<-\EOF && + <BOLD>diff --git a/bar b/bar<RESET> + <BOLD>--- a/bar<RESET> + <BOLD>+++ b/bar<RESET> + <CYAN>@@ -0,0 +1,3 @@<RESET> + <GREEN>+<RESET><GREEN>7charsB<RESET> + <GREEN>+<RESET><GREEN>7charsC<RESET> + <GREEN>+<RESET><GREEN>7charsA<RESET> + <BOLD>diff --git a/foo b/foo<RESET> + <BOLD>--- a/foo<RESET> + <BOLD>+++ b/foo<RESET> + <CYAN>@@ -1,4 +1 @@<RESET> + <RED>-7charsA<RESET> + irrelevant_line<RESET> + <RED>-7charsB<RESET> + <RED>-7charsC<RESET> + EOF + + test_cmp expected actual +' + +test_expect_success 'move detection with submodules' ' + test_create_repo bananas && + echo ripe >bananas/recipe && + git -C bananas add recipe && + test_commit fruit && + test_commit -C bananas recipe && + git submodule add ./bananas && + git add bananas && + git commit -a -m "bananas are like a heavy library?" && + echo foul >bananas/recipe && + echo ripe >fruit.t && + + git diff --submodule=diff --color-moved >actual && + + # no move detection as the moved line is across repository boundaries. + test_decode_color <actual >decoded_actual && + ! grep BGREEN decoded_actual && + ! grep BRED decoded_actual && + + # nor did we mess with it another way + git diff --submodule=diff | test_decode_color >expect && + test_cmp expect decoded_actual +' + test_done diff --git a/t/t4027-diff-submodule.sh b/t/t4027-diff-submodule.sh index 518bf9524..2ffd11a14 100755 --- a/t/t4027-diff-submodule.sh +++ b/t/t4027-diff-submodule.sh @@ -113,35 +113,6 @@ test_expect_success 'git diff HEAD with dirty submodule (work tree, refs match)' ! test -s actual4 ' -test_expect_success 'git diff HEAD with dirty submodule (work tree, refs match) [.git/config]' ' - git config diff.ignoreSubmodules all && - git diff HEAD >actual && - ! test -s actual && - git config submodule.subname.ignore none && - git config submodule.subname.path sub && - git diff HEAD >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subprev $subprev-dirty && - test_cmp expect.body actual.body && - git config submodule.subname.ignore all && - git diff HEAD >actual2 && - ! test -s actual2 && - git config submodule.subname.ignore untracked && - git diff HEAD >actual3 && - sed -e "1,/^@@/d" actual3 >actual3.body && - expect_from_to >expect.body $subprev $subprev-dirty && - test_cmp expect.body actual3.body && - git config submodule.subname.ignore dirty && - git diff HEAD >actual4 && - ! test -s actual4 && - git diff HEAD --ignore-submodules=none >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subprev $subprev-dirty && - test_cmp expect.body actual.body && - git config --remove-section submodule.subname && - git config --unset diff.ignoreSubmodules -' - test_expect_success 'git diff HEAD with dirty submodule (work tree, refs match) [.gitmodules]' ' git config diff.ignoreSubmodules dirty && git diff HEAD >actual && @@ -208,24 +179,6 @@ test_expect_success 'git diff HEAD with dirty submodule (untracked, refs match)' ! test -s actual4 ' -test_expect_success 'git diff HEAD with dirty submodule (untracked, refs match) [.git/config]' ' - git config submodule.subname.ignore all && - git config submodule.subname.path sub && - git diff HEAD >actual2 && - ! test -s actual2 && - git config submodule.subname.ignore untracked && - git diff HEAD >actual3 && - ! test -s actual3 && - git config submodule.subname.ignore dirty && - git diff HEAD >actual4 && - ! test -s actual4 && - git diff --ignore-submodules=none HEAD >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subprev $subprev-dirty && - test_cmp expect.body actual.body && - git config --remove-section submodule.subname -' - test_expect_success 'git diff HEAD with dirty submodule (untracked, refs match) [.gitmodules]' ' git config --add -f .gitmodules submodule.subname.ignore all && git config --add -f .gitmodules submodule.subname.path sub && @@ -261,26 +214,6 @@ test_expect_success 'git diff between submodule commits' ' ! test -s actual ' -test_expect_success 'git diff between submodule commits [.git/config]' ' - git diff HEAD^..HEAD >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subtip $subprev && - test_cmp expect.body actual.body && - git config submodule.subname.ignore dirty && - git config submodule.subname.path sub && - git diff HEAD^..HEAD >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subtip $subprev && - test_cmp expect.body actual.body && - git config submodule.subname.ignore all && - git diff HEAD^..HEAD >actual && - ! test -s actual && - git diff --ignore-submodules=dirty HEAD^..HEAD >actual && - sed -e "1,/^@@/d" actual >actual.body && - expect_from_to >expect.body $subtip $subprev && - git config --remove-section submodule.subname -' - test_expect_success 'git diff between submodule commits [.gitmodules]' ' git diff HEAD^..HEAD >actual && sed -e "1,/^@@/d" actual >actual.body && diff --git a/t/t4124-apply-ws-rule.sh b/t/t4124-apply-ws-rule.sh index d350065f2..4fc27c51f 100755 --- a/t/t4124-apply-ws-rule.sh +++ b/t/t4124-apply-ws-rule.sh @@ -467,21 +467,42 @@ test_expect_success 'same, but with CR-LF line endings && cr-at-eol set' ' test_cmp one expect ' -test_expect_success 'same, but with CR-LF line endings && cr-at-eol unset' ' +test_expect_success 'CR-LF line endings && add line && text=auto' ' git config --unset core.whitespace && printf "a\r\n" >one && + cp one save-one && + git add one && printf "b\r\n" >>one && - printf "c\r\n" >>one && + cp one expect && + git diff -- one >patch && + mv save-one one && + echo "one text=auto" >.gitattributes && + git apply patch && + test_cmp one expect +' + +test_expect_success 'CR-LF line endings && change line && text=auto' ' + printf "a\r\n" >one && cp one save-one && - printf " \r\n" >>one && git add one && + printf "b\r\n" >one && cp one expect && - printf "d\r\n" >>one && git diff -- one >patch && mv save-one one && - echo d >>expect && + echo "one text=auto" >.gitattributes && + git apply patch && + test_cmp one expect +' - git apply --ignore-space-change --whitespace=fix patch && +test_expect_success 'LF in repo, CRLF in worktree && change line && text=auto' ' + printf "a\n" >one && + git add one && + printf "b\r\n" >one && + git diff -- one >patch && + printf "a\r\n" >one && + echo "one text=auto" >.gitattributes && + git -c core.eol=CRLF apply patch && + printf "b\r\n" >expect && test_cmp one expect ' diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh index 1a080e782..d97d2bebc 100755 --- a/t/t4200-rerere.sh +++ b/t/t4200-rerere.sh @@ -239,6 +239,43 @@ test_expect_success 'old records rest in peace' ' ! test -f $rr2/preimage ' +rerere_gc_custom_expiry_test () { + five_days="$1" right_now="$2" + test_expect_success "rerere gc with custom expiry ($five_days, $right_now)" ' + rm -fr .git/rr-cache && + rr=.git/rr-cache/$_z40 && + mkdir -p "$rr" && + >"$rr/preimage" && + >"$rr/postimage" && + + two_days_ago=$((-2*86400)) && + test-chmtime =$two_days_ago "$rr/preimage" && + test-chmtime =$two_days_ago "$rr/postimage" && + + find .git/rr-cache -type f | sort >original && + + git -c "gc.rerereresolved=$five_days" \ + -c "gc.rerereunresolved=$five_days" rerere gc && + find .git/rr-cache -type f | sort >actual && + test_cmp original actual && + + git -c "gc.rerereresolved=$five_days" \ + -c "gc.rerereunresolved=$right_now" rerere gc && + find .git/rr-cache -type f | sort >actual && + test_cmp original actual && + + git -c "gc.rerereresolved=$right_now" \ + -c "gc.rerereunresolved=$right_now" rerere gc && + find .git/rr-cache -type f | sort >actual && + >expect && + test_cmp expect actual + ' +} + +rerere_gc_custom_expiry_test 5 0 + +rerere_gc_custom_expiry_test 5.days.ago now + test_expect_success 'setup: file2 added differently in two branches' ' git reset --hard && @@ -419,24 +456,6 @@ count_pre_post () { test_line_count = "$2" actual } -test_expect_success 'rerere gc' ' - find .git/rr-cache -type f >original && - xargs test-chmtime -172800 <original && - - git -c gc.rerereresolved=5 -c gc.rerereunresolved=5 rerere gc && - find .git/rr-cache -type f >actual && - test_cmp original actual && - - git -c gc.rerereresolved=5 -c gc.rerereunresolved=0 rerere gc && - find .git/rr-cache -type f >actual && - test_cmp original actual && - - git -c gc.rerereresolved=0 -c gc.rerereunresolved=0 rerere gc && - find .git/rr-cache -type f >actual && - >expect && - test_cmp expect actual -' - merge_conflict_resolve () { git reset --hard && test_must_fail git merge six.1 && @@ -446,6 +465,8 @@ merge_conflict_resolve () { } test_expect_success 'multiple identical conflicts' ' + rm -fr .git/rr-cache && + mkdir .git/rr-cache && git reset --hard && test_seq 1 6 >early && diff --git a/t/t4205-log-pretty-formats.sh b/t/t4205-log-pretty-formats.sh index 18aa1b588..ec5f53010 100755 --- a/t/t4205-log-pretty-formats.sh +++ b/t/t4205-log-pretty-formats.sh @@ -539,25 +539,62 @@ cat >trailers <<EOF Signed-off-by: A U Thor <author@example.com> Acked-by: A U Thor <author@example.com> [ v2 updated patch description ] -Signed-off-by: A U Thor <author@example.com> +Signed-off-by: A U Thor + <author@example.com> EOF -test_expect_success 'pretty format %(trailers) shows trailers' ' +unfold () { + perl -0pe 's/\n\s+/ /' +} + +test_expect_success 'set up trailer tests' ' echo "Some contents" >trailerfile && git add trailerfile && - git commit -F - <<-EOF && + git commit -F - <<-EOF trailers: this commit message has trailers This commit is a test commit with trailers at the end. We parse this - message and display the trailers using %bT + message and display the trailers using %(trailers). $(cat trailers) EOF +' + +test_expect_success 'pretty format %(trailers) shows trailers' ' git log --no-walk --pretty="%(trailers)" >actual && - cat >expect <<-EOF && - $(cat trailers) + { + cat trailers && + echo + } >expect && + test_cmp expect actual +' - EOF +test_expect_success '%(trailers:only) shows only "key: value" trailers' ' + git log --no-walk --pretty="%(trailers:only)" >actual && + { + grep -v patch.description <trailers && + echo + } >expect && + test_cmp expect actual +' + +test_expect_success '%(trailers:unfold) unfolds trailers' ' + git log --no-walk --pretty="%(trailers:unfold)" >actual && + { + unfold <trailers && + echo + } >expect && + test_cmp expect actual +' + +test_expect_success ':only and :unfold work together' ' + git log --no-walk --pretty="%(trailers:only:unfold)" >actual && + git log --no-walk --pretty="%(trailers:unfold:only)" >reverse && + test_cmp actual reverse && + { + grep -v patch.description <trailers | unfold && + echo + } >expect && test_cmp expect actual ' diff --git a/t/t5001-archive-attr.sh b/t/t5001-archive-attr.sh index b04d955bf..897f6f06d 100755 --- a/t/t5001-archive-attr.sh +++ b/t/t5001-archive-attr.sh @@ -7,11 +7,15 @@ test_description='git archive attribute tests' SUBSTFORMAT='%H (%h)%n' test_expect_exists() { - test_expect_success " $1 exists" "test -e $1" + test_expect_${2:-success} " $1 exists" "test -e $1" } test_expect_missing() { - test_expect_success " $1 does not exist" "test ! -e $1" + test_expect_${2:-success} " $1 does not exist" "test ! -e $1" +} + +extract_tar_to_dir () { + (mkdir "$1" && cd "$1" && "$TAR" xf -) <"$1.tar" } test_expect_success 'setup' ' @@ -21,12 +25,19 @@ test_expect_success 'setup' ' echo ignored by tree >ignored-by-tree && echo ignored-by-tree export-ignore >.gitattributes && - git add ignored-by-tree .gitattributes && + mkdir ignored-by-tree.d && + >ignored-by-tree.d/file && + echo ignored-by-tree.d export-ignore >>.gitattributes && + git add ignored-by-tree ignored-by-tree.d .gitattributes && echo ignored by worktree >ignored-by-worktree && echo ignored-by-worktree export-ignore >.gitattributes && git add ignored-by-worktree && + mkdir excluded-by-pathspec.d && + >excluded-by-pathspec.d/file && + git add excluded-by-pathspec.d && + printf "A\$Format:%s\$O" "$SUBSTFORMAT" >nosubstfile && printf "A\$Format:%s\$O" "$SUBSTFORMAT" >substfile1 && printf "A not substituted O" >substfile2 && @@ -46,7 +57,37 @@ test_expect_success 'git archive' ' test_expect_missing archive/ignored test_expect_missing archive/ignored-by-tree +test_expect_missing archive/ignored-by-tree.d +test_expect_missing archive/ignored-by-tree.d/file test_expect_exists archive/ignored-by-worktree +test_expect_exists archive/excluded-by-pathspec.d +test_expect_exists archive/excluded-by-pathspec.d/file + +test_expect_success 'git archive with pathspec' ' + git archive HEAD ":!excluded-by-pathspec.d" >archive-pathspec.tar && + extract_tar_to_dir archive-pathspec +' + +test_expect_missing archive-pathspec/ignored +test_expect_missing archive-pathspec/ignored-by-tree +test_expect_missing archive-pathspec/ignored-by-tree.d +test_expect_missing archive-pathspec/ignored-by-tree.d/file +test_expect_exists archive-pathspec/ignored-by-worktree +test_expect_missing archive-pathspec/excluded-by-pathspec.d failure +test_expect_missing archive-pathspec/excluded-by-pathspec.d/file + +test_expect_success 'git archive with wildcard pathspec' ' + git archive HEAD ":!excluded-by-p*" >archive-pathspec-wildcard.tar && + extract_tar_to_dir archive-pathspec-wildcard +' + +test_expect_missing archive-pathspec-wildcard/ignored +test_expect_missing archive-pathspec-wildcard/ignored-by-tree +test_expect_missing archive-pathspec-wildcard/ignored-by-tree.d +test_expect_missing archive-pathspec-wildcard/ignored-by-tree.d/file +test_expect_exists archive-pathspec-wildcard/ignored-by-worktree +test_expect_missing archive-pathspec-wildcard/excluded-by-pathspec.d +test_expect_missing archive-pathspec-wildcard/excluded-by-pathspec.d/file test_expect_success 'git archive with worktree attributes' ' git archive --worktree-attributes HEAD >worktree.tar && diff --git a/t/t6040-tracking-info.sh b/t/t6040-tracking-info.sh index 97a07655a..8f17fd9da 100755 --- a/t/t6040-tracking-info.sh +++ b/t/t6040-tracking-info.sh @@ -100,7 +100,7 @@ test_expect_success 'checkout (up-to-date with upstream)' ' ( cd test && git checkout b6 ) >actual && - test_i18ngrep "Your branch is up-to-date with .origin/master" actual + test_i18ngrep "Your branch is up to date with .origin/master" actual ' test_expect_success 'status (diverged from upstream)' ' @@ -130,7 +130,7 @@ test_expect_success 'status (up-to-date with upstream)' ' # reports nothing to commit test_must_fail git commit --dry-run ) >actual && - test_i18ngrep "Your branch is up-to-date with .origin/master" actual + test_i18ngrep "Your branch is up to date with .origin/master" actual ' cat >expect <<\EOF @@ -188,35 +188,29 @@ test_expect_success 'fail to track annotated tags' ' test_must_fail git checkout heavytrack ' -test_expect_success 'setup tracking with branch --set-upstream on existing branch' ' +test_expect_success '--set-upstream-to does not change branch' ' git branch from-master master && - test_must_fail git config branch.from-master.merge > actual && - git branch --set-upstream from-master master && - git config branch.from-master.merge > actual && - grep -q "^refs/heads/master$" actual -' - -test_expect_success '--set-upstream does not change branch' ' + git branch --set-upstream-to master from-master && git branch from-master2 master && test_must_fail git config branch.from-master2.merge > actual && git rev-list from-master2 && git update-ref refs/heads/from-master2 from-master2^ && git rev-parse from-master2 >expect2 && - git branch --set-upstream from-master2 master && + git branch --set-upstream-to master from-master2 && git config branch.from-master.merge > actual && git rev-parse from-master2 >actual2 && grep -q "^refs/heads/master$" actual && cmp expect2 actual2 ' -test_expect_success '--set-upstream @{-1}' ' - git checkout from-master && +test_expect_success '--set-upstream-to @{-1}' ' + git checkout follower && git checkout from-master2 && git config branch.from-master2.merge > expect2 && - git branch --set-upstream @{-1} follower && + git branch --set-upstream-to @{-1} from-master && git config branch.from-master.merge > actual && git config branch.from-master2.merge > actual2 && - git branch --set-upstream from-master follower && + git branch --set-upstream-to follower from-master && git config branch.from-master.merge > expect && test_cmp expect2 actual2 && test_cmp expect actual diff --git a/t/t7400-submodule-basic.sh b/t/t7400-submodule-basic.sh index e9c3335b7..6f8337ffb 100755 --- a/t/t7400-submodule-basic.sh +++ b/t/t7400-submodule-basic.sh @@ -46,16 +46,6 @@ test_expect_success 'submodule update aborts on missing gitmodules url' ' test_must_fail git submodule init ' -test_expect_success 'configuration parsing' ' - test_when_finished "rm -f .gitmodules" && - cat >.gitmodules <<-\EOF && - [submodule "s"] - path - ignore - EOF - test_must_fail git status -' - test_expect_success 'setup - repository in init subdirectory' ' mkdir init && ( diff --git a/t/t7411-submodule-config.sh b/t/t7411-submodule-config.sh index eea36f1db..46c09c776 100755 --- a/t/t7411-submodule-config.sh +++ b/t/t7411-submodule-config.sh @@ -31,6 +31,21 @@ test_expect_success 'submodule config cache setup' ' ) ' +test_expect_success 'configuration parsing with error' ' + test_when_finished "rm -rf repo" && + test_create_repo repo && + cat >repo/.gitmodules <<-\EOF && + [submodule "s"] + path + ignore + EOF + ( + cd repo && + test_must_fail test-submodule-config "" s 2>actual && + test_i18ngrep "bad config" actual + ) +' + cat >super/expect <<EOF Submodule name: 'a' for path 'a' Submodule name: 'a' for path 'b' @@ -107,78 +122,6 @@ test_expect_success 'using different treeishs works' ' ) ' -cat >super/expect_url <<EOF -Submodule url: 'git@somewhere.else.net:a.git' for path 'b' -Submodule url: 'git@somewhere.else.net:submodule.git' for path 'submodule' -EOF - -cat >super/expect_local_path <<EOF -Submodule name: 'a' for path 'c' -Submodule name: 'submodule' for path 'submodule' -EOF - -test_expect_success 'reading of local configuration' ' - (cd super && - old_a=$(git config submodule.a.url) && - old_submodule=$(git config submodule.submodule.url) && - git config submodule.a.url git@somewhere.else.net:a.git && - git config submodule.submodule.url git@somewhere.else.net:submodule.git && - test-submodule-config --url \ - "" b \ - "" submodule \ - >actual && - test_cmp expect_url actual && - git config submodule.a.path c && - test-submodule-config \ - "" c \ - "" submodule \ - >actual && - test_cmp expect_local_path actual && - git config submodule.a.url "$old_a" && - git config submodule.submodule.url "$old_submodule" && - git config --unset submodule.a.path c - ) -' - -cat >super/expect_url <<EOF -Submodule url: '../submodule' for path 'b' -Submodule url: 'git@somewhere.else.net:submodule.git' for path 'submodule' -EOF - -test_expect_success 'reading of local configuration for uninitialized submodules' ' - ( - cd super && - git submodule deinit -f b && - old_submodule=$(git config submodule.submodule.url) && - git config submodule.submodule.url git@somewhere.else.net:submodule.git && - test-submodule-config --url \ - "" b \ - "" submodule \ - >actual && - test_cmp expect_url actual && - git config submodule.submodule.url "$old_submodule" && - git submodule init b - ) -' - -cat >super/expect_fetchrecurse_die.err <<EOF -fatal: bad submodule.submodule.fetchrecursesubmodules argument: blabla -EOF - -test_expect_success 'local error in fetchrecursesubmodule dies early' ' - (cd super && - git config submodule.submodule.fetchrecursesubmodules blabla && - test_must_fail test-submodule-config \ - "" b \ - "" submodule \ - >actual.out 2>actual.err && - touch expect_fetchrecurse_die.out && - test_cmp expect_fetchrecurse_die.out actual.out && - test_cmp expect_fetchrecurse_die.err actual.err && - git config --unset submodule.submodule.fetchrecursesubmodules - ) -' - test_expect_success 'error in history in fetchrecursesubmodule lets continue' ' (cd super && git config -f .gitmodules \ diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh index 0c6f91c43..164719d1c 100755 --- a/t/t7513-interpret-trailers.sh +++ b/t/t7513-interpret-trailers.sh @@ -681,6 +681,36 @@ test_expect_success 'using "where = before"' ' test_cmp expected actual ' +test_expect_success 'overriding configuration with "--where after"' ' + git config trailer.ack.where "before" && + cat complex_message_body >expected && + sed -e "s/ Z\$/ /" >>expected <<-\EOF && + Fixes: Z + Acked-by= Z + Acked-by= Peff + Reviewed-by: Z + Signed-off-by: Z + EOF + git interpret-trailers --where after --trailer "ack: Peff" \ + complex_message >actual && + test_cmp expected actual +' + +test_expect_success 'using "where = before" with "--no-where"' ' + cat complex_message_body >expected && + sed -e "s/ Z\$/ /" >>expected <<-\EOF && + Bug #42 + Fixes: Z + Acked-by= Peff + Acked-by= Z + Reviewed-by: Z + Signed-off-by: Z + EOF + git interpret-trailers --where after --no-where --trailer "ack: Peff" \ + --trailer "bug: 42" complex_message >actual && + test_cmp expected actual +' + test_expect_success 'using "where = after"' ' git config trailer.ack.where "after" && cat complex_message_body >expected && @@ -947,6 +977,23 @@ test_expect_success 'using "ifExists = add" with "where = after"' ' test_cmp expected actual ' +test_expect_success 'overriding configuration with "--if-exists replace"' ' + git config trailer.fix.key "Fixes: " && + git config trailer.fix.ifExists "add" && + cat complex_message_body >expected && + sed -e "s/ Z\$/ /" >>expected <<-\EOF && + Bug #42 + Acked-by= Z + Reviewed-by: + Signed-off-by: Z + Fixes: 22 + EOF + git interpret-trailers --if-exists replace --trailer "review:" \ + --trailer "fix=53" --trailer "fix=22" --trailer "bug: 42" \ + <complex_message >actual && + test_cmp expected actual +' + test_expect_success 'using "ifExists = replace"' ' git config trailer.fix.key "Fixes: " && git config trailer.fix.ifExists "replace" && @@ -1026,6 +1073,25 @@ test_expect_success 'the default is "ifMissing = add"' ' test_cmp expected actual ' +test_expect_success 'overriding configuration with "--if-missing doNothing"' ' + git config trailer.ifmissing "add" && + cat complex_message_body >expected && + sed -e "s/ Z\$/ /" >>expected <<-\EOF && + Fixes: Z + Acked-by= Z + Acked-by= Junio + Acked-by= Peff + Reviewed-by: + Signed-off-by: Z + EOF + git interpret-trailers --if-missing doNothing \ + --trailer "review:" --trailer "fix=53" \ + --trailer "cc=Linus" --trailer "ack: Junio" \ + --trailer "fix=22" --trailer "bug: 42" --trailer "ack: Peff" \ + <complex_message >actual && + test_cmp expected actual +' + test_expect_success 'when default "ifMissing" is "doNothing"' ' git config trailer.ifmissing "doNothing" && cat complex_message_body >expected && @@ -1275,4 +1341,80 @@ test_expect_success 'with cut line' ' test_cmp expected actual ' +test_expect_success 'only trailers' ' + git config trailer.sign.command "echo config-value" && + cat >expected <<-\EOF && + existing: existing-value + sign: config-value + added: added-value + EOF + git interpret-trailers \ + --trailer added:added-value \ + --only-trailers >actual <<-\EOF && + my subject + + my body + + existing: existing-value + EOF + test_cmp expected actual +' + +test_expect_success 'only-trailers omits non-trailer in middle of block' ' + git config trailer.sign.command "echo config-value" && + cat >expected <<-\EOF && + Signed-off-by: nobody <nobody@nowhere> + Signed-off-by: somebody <somebody@somewhere> + sign: config-value + EOF + git interpret-trailers --only-trailers >actual <<-\EOF && + subject + + it is important that the trailers below are signed-off-by + so that they meet the "25% trailers Git knows about" heuristic + + Signed-off-by: nobody <nobody@nowhere> + this is not a trailer + Signed-off-by: somebody <somebody@somewhere> + EOF + test_cmp expected actual +' + +test_expect_success 'only input' ' + git config trailer.sign.command "echo config-value" && + cat >expected <<-\EOF && + existing: existing-value + EOF + git interpret-trailers \ + --only-trailers --only-input >actual <<-\EOF && + my subject + + my body + + existing: existing-value + EOF + test_cmp expected actual +' + +test_expect_success 'unfold' ' + cat >expected <<-\EOF && + foo: continued across several lines + EOF + # pass through tr to make leading and trailing whitespace more obvious + tr _ " " <<-\EOF | + my subject + + my body + + foo:_ + __continued + ___across + ____several + _____lines + ___ + EOF + git interpret-trailers --only-trailers --only-input --unfold >actual && + test_cmp expected actual +' + test_done diff --git a/t/t7600-merge.sh b/t/t7600-merge.sh index 2ebda509a..80194b79f 100755 --- a/t/t7600-merge.sh +++ b/t/t7600-merge.sh @@ -774,4 +774,19 @@ test_expect_success 'merge can be completed with --continue' ' verify_parents $c0 $c1 ' +write_script .git/FAKE_EDITOR <<EOF +# kill -TERM command added below. +EOF + +test_expect_success EXECKEEPSPID 'killed merge can be completed with --continue' ' + git reset --hard c0 && + ! "$SHELL_PATH" -c '\'' + echo kill -TERM $$ >> .git/FAKE_EDITOR + GIT_EDITOR=.git/FAKE_EDITOR + export GIT_EDITOR + exec git merge --no-ff --edit c1'\'' && + git merge --continue && + verify_parents $c0 $c1 +' + test_done diff --git a/templates/hooks--pre-rebase.sample b/templates/hooks--pre-rebase.sample index b7f81c198..db5feab8a 100755 --- a/templates/hooks--pre-rebase.sample +++ b/templates/hooks--pre-rebase.sample @@ -58,7 +58,7 @@ then not_in_topic=`git rev-list "^$topic" master` if test -z "$not_in_topic" then - echo >&2 "$topic is already up-to-date with master" + echo >&2 "$topic is already up to date with master" exit 1 ;# we could allow it, but there is no point. else exit 0 @@ -10,18 +10,13 @@ * Copyright (c) 2013, 2014 Christian Couder <chriscool@tuxfamily.org> */ -enum action_where { WHERE_END, WHERE_AFTER, WHERE_BEFORE, WHERE_START }; -enum action_if_exists { EXISTS_ADD_IF_DIFFERENT_NEIGHBOR, EXISTS_ADD_IF_DIFFERENT, - EXISTS_ADD, EXISTS_REPLACE, EXISTS_DO_NOTHING }; -enum action_if_missing { MISSING_ADD, MISSING_DO_NOTHING }; - struct conf_info { char *name; char *key; char *command; - enum action_where where; - enum action_if_exists if_exists; - enum action_if_missing if_missing; + enum trailer_where where; + enum trailer_if_exists if_exists; + enum trailer_if_missing if_missing; }; static struct conf_info default_conf_info; @@ -63,7 +58,7 @@ static const char *git_generated_prefixes[] = { pos != (head); \ pos = is_reverse ? pos->prev : pos->next) -static int after_or_end(enum action_where where) +static int after_or_end(enum trailer_where where) { return (where == WHERE_AFTER) || (where == WHERE_END); } @@ -164,13 +159,15 @@ static void print_tok_val(FILE *outfile, const char *tok, const char *val) fprintf(outfile, "%s%c %s\n", tok, separators[0], val); } -static void print_all(FILE *outfile, struct list_head *head, int trim_empty) +static void print_all(FILE *outfile, struct list_head *head, + const struct process_trailer_options *opts) { struct list_head *pos; struct trailer_item *item; list_for_each(pos, head) { item = list_entry(pos, struct trailer_item, list); - if (!trim_empty || strlen(item->value) > 0) + if ((!opts->trim_empty || strlen(item->value) > 0) && + (!opts->only_trailers || item->token)) print_tok_val(outfile, item->token, item->value); } } @@ -201,7 +198,7 @@ static int check_if_different(struct trailer_item *in_tok, int check_all, struct list_head *head) { - enum action_where where = arg_tok->conf.where; + enum trailer_where where = arg_tok->conf.where; struct list_head *next_head; do { if (same_trailer(in_tok, arg_tok)) @@ -300,13 +297,16 @@ static void apply_arg_if_exists(struct trailer_item *in_tok, else free_arg_item(arg_tok); break; + default: + die("BUG: trailer.c: unhandled value %d", + arg_tok->conf.if_exists); } } static void apply_arg_if_missing(struct list_head *head, struct arg_item *arg_tok) { - enum action_where where; + enum trailer_where where; struct trailer_item *to_add; switch (arg_tok->conf.if_missing) { @@ -321,6 +321,10 @@ static void apply_arg_if_missing(struct list_head *head, list_add_tail(&to_add->list, head); else list_add(&to_add->list, head); + break; + default: + die("BUG: trailer.c: unhandled value %d", + arg_tok->conf.if_missing); } } @@ -331,7 +335,7 @@ static int find_same_and_apply_arg(struct list_head *head, struct trailer_item *in_tok; struct trailer_item *on_tok; - enum action_where where = arg_tok->conf.where; + enum trailer_where where = arg_tok->conf.where; int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE); int backwards = after_or_end(where); struct trailer_item *start_tok; @@ -373,44 +377,50 @@ static void process_trailers_lists(struct list_head *head, } } -static int set_where(struct conf_info *item, const char *value) +int trailer_set_where(enum trailer_where *item, const char *value) { - if (!strcasecmp("after", value)) - item->where = WHERE_AFTER; + if (!value) + *item = WHERE_DEFAULT; + else if (!strcasecmp("after", value)) + *item = WHERE_AFTER; else if (!strcasecmp("before", value)) - item->where = WHERE_BEFORE; + *item = WHERE_BEFORE; else if (!strcasecmp("end", value)) - item->where = WHERE_END; + *item = WHERE_END; else if (!strcasecmp("start", value)) - item->where = WHERE_START; + *item = WHERE_START; else return -1; return 0; } -static int set_if_exists(struct conf_info *item, const char *value) +int trailer_set_if_exists(enum trailer_if_exists *item, const char *value) { - if (!strcasecmp("addIfDifferent", value)) - item->if_exists = EXISTS_ADD_IF_DIFFERENT; + if (!value) + *item = EXISTS_DEFAULT; + else if (!strcasecmp("addIfDifferent", value)) + *item = EXISTS_ADD_IF_DIFFERENT; else if (!strcasecmp("addIfDifferentNeighbor", value)) - item->if_exists = EXISTS_ADD_IF_DIFFERENT_NEIGHBOR; + *item = EXISTS_ADD_IF_DIFFERENT_NEIGHBOR; else if (!strcasecmp("add", value)) - item->if_exists = EXISTS_ADD; + *item = EXISTS_ADD; else if (!strcasecmp("replace", value)) - item->if_exists = EXISTS_REPLACE; + *item = EXISTS_REPLACE; else if (!strcasecmp("doNothing", value)) - item->if_exists = EXISTS_DO_NOTHING; + *item = EXISTS_DO_NOTHING; else return -1; return 0; } -static int set_if_missing(struct conf_info *item, const char *value) +int trailer_set_if_missing(enum trailer_if_missing *item, const char *value) { - if (!strcasecmp("doNothing", value)) - item->if_missing = MISSING_DO_NOTHING; + if (!value) + *item = MISSING_DEFAULT; + else if (!strcasecmp("doNothing", value)) + *item = MISSING_DO_NOTHING; else if (!strcasecmp("add", value)) - item->if_missing = MISSING_ADD; + *item = MISSING_ADD; else return -1; return 0; @@ -470,15 +480,18 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v variable_name = strrchr(trailer_item, '.'); if (!variable_name) { if (!strcmp(trailer_item, "where")) { - if (set_where(&default_conf_info, value) < 0) + if (trailer_set_where(&default_conf_info.where, + value) < 0) warning(_("unknown value '%s' for key '%s'"), value, conf_key); } else if (!strcmp(trailer_item, "ifexists")) { - if (set_if_exists(&default_conf_info, value) < 0) + if (trailer_set_if_exists(&default_conf_info.if_exists, + value) < 0) warning(_("unknown value '%s' for key '%s'"), value, conf_key); } else if (!strcmp(trailer_item, "ifmissing")) { - if (set_if_missing(&default_conf_info, value) < 0) + if (trailer_set_if_missing(&default_conf_info.if_missing, + value) < 0) warning(_("unknown value '%s' for key '%s'"), value, conf_key); } else if (!strcmp(trailer_item, "separators")) { @@ -532,15 +545,15 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb) conf->command = xstrdup(value); break; case TRAILER_WHERE: - if (set_where(conf, value)) + if (trailer_set_where(&conf->where, value)) warning(_("unknown value '%s' for key '%s'"), value, conf_key); break; case TRAILER_IF_EXISTS: - if (set_if_exists(conf, value)) + if (trailer_set_if_exists(&conf->if_exists, value)) warning(_("unknown value '%s' for key '%s'"), value, conf_key); break; case TRAILER_IF_MISSING: - if (set_if_missing(conf, value)) + if (trailer_set_if_missing(&conf->if_missing, value)) warning(_("unknown value '%s' for key '%s'"), value, conf_key); break; default: @@ -555,6 +568,9 @@ static void ensure_configured(void) return; /* Default config must be setup first */ + default_conf_info.where = WHERE_END; + default_conf_info.if_exists = EXISTS_ADD_IF_DIFFERENT_NEIGHBOR; + default_conf_info.if_missing = MISSING_ADD; git_config(git_trailer_default_config, NULL); git_config(git_trailer_config, NULL); configured = 1; @@ -658,19 +674,27 @@ static struct trailer_item *add_trailer_item(struct list_head *head, char *tok, } static void add_arg_item(struct list_head *arg_head, char *tok, char *val, - const struct conf_info *conf) + const struct conf_info *conf, + const struct new_trailer_item *new_trailer_item) { struct arg_item *new = xcalloc(sizeof(*new), 1); new->token = tok; new->value = val; duplicate_conf(&new->conf, conf); + if (new_trailer_item) { + if (new_trailer_item->where != WHERE_DEFAULT) + new->conf.where = new_trailer_item->where; + if (new_trailer_item->if_exists != EXISTS_DEFAULT) + new->conf.if_exists = new_trailer_item->if_exists; + if (new_trailer_item->if_missing != MISSING_DEFAULT) + new->conf.if_missing = new_trailer_item->if_missing; + } list_add_tail(&new->list, arg_head); } static void process_command_line_args(struct list_head *arg_head, - struct string_list *trailers) + struct list_head *new_trailer_head) { - struct string_list_item *tr; struct arg_item *item; struct strbuf tok = STRBUF_INIT; struct strbuf val = STRBUF_INIT; @@ -690,26 +714,29 @@ static void process_command_line_args(struct list_head *arg_head, add_arg_item(arg_head, xstrdup(token_from_item(item, NULL)), xstrdup(""), - &item->conf); + &item->conf, NULL); } /* Add an arg item for each trailer on the command line */ - for_each_string_list_item(tr, trailers) { - int separator_pos = find_separator(tr->string, cl_separators); + list_for_each(pos, new_trailer_head) { + struct new_trailer_item *tr = + list_entry(pos, struct new_trailer_item, list); + int separator_pos = find_separator(tr->text, cl_separators); + if (separator_pos == 0) { struct strbuf sb = STRBUF_INIT; - strbuf_addstr(&sb, tr->string); + strbuf_addstr(&sb, tr->text); strbuf_trim(&sb); error(_("empty trailer token in trailer '%.*s'"), (int) sb.len, sb.buf); strbuf_release(&sb); } else { - parse_trailer(&tok, &val, &conf, tr->string, + parse_trailer(&tok, &val, &conf, tr->text, separator_pos); add_arg_item(arg_head, strbuf_detach(&tok, NULL), strbuf_detach(&val, NULL), - conf); + conf, tr); } } @@ -885,9 +912,37 @@ static int ends_with_blank_line(const char *buf, size_t len) return is_blank_line(buf + ll); } +static void unfold_value(struct strbuf *val) +{ + struct strbuf out = STRBUF_INIT; + size_t i; + + strbuf_grow(&out, val->len); + i = 0; + while (i < val->len) { + char c = val->buf[i++]; + if (c == '\n') { + /* Collapse continuation down to a single space. */ + while (i < val->len && isspace(val->buf[i])) + i++; + strbuf_addch(&out, ' '); + } else { + strbuf_addch(&out, c); + } + } + + /* Empty lines may have left us with whitespace cruft at the edges */ + strbuf_trim(&out); + + /* output goes back to val as if we modified it in-place */ + strbuf_swap(&out, val); + strbuf_release(&out); +} + static int process_input_file(FILE *outfile, const char *str, - struct list_head *head) + struct list_head *head, + const struct process_trailer_options *opts) { struct trailer_info info; struct strbuf tok = STRBUF_INIT; @@ -897,9 +952,10 @@ static int process_input_file(FILE *outfile, trailer_info_get(&info, str); /* Print lines before the trailers as is */ - fwrite(str, 1, info.trailer_start - str, outfile); + if (!opts->only_trailers) + fwrite(str, 1, info.trailer_start - str, outfile); - if (!info.blank_line_before_trailer) + if (!opts->only_trailers && !info.blank_line_before_trailer) fprintf(outfile, "\n"); for (i = 0; i < info.trailer_nr; i++) { @@ -911,10 +967,12 @@ static int process_input_file(FILE *outfile, if (separator_pos >= 1) { parse_trailer(&tok, &val, NULL, trailer, separator_pos); + if (opts->unfold) + unfold_value(&val); add_trailer_item(head, strbuf_detach(&tok, NULL), strbuf_detach(&val, NULL)); - } else { + } else if (!opts->only_trailers) { strbuf_addstr(&val, trailer); strbuf_strip_suffix(&val, "\n"); add_trailer_item(head, @@ -968,10 +1026,11 @@ static FILE *create_in_place_tempfile(const char *file) return outfile; } -void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers) +void process_trailers(const char *file, + const struct process_trailer_options *opts, + struct list_head *new_trailer_head) { LIST_HEAD(head); - LIST_HEAD(arg_head); struct strbuf sb = STRBUF_INIT; int trailer_end; FILE *outfile = stdout; @@ -980,24 +1039,27 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str read_input_file(&sb, file); - if (in_place) + if (opts->in_place) outfile = create_in_place_tempfile(file); /* Print the lines before the trailers */ - trailer_end = process_input_file(outfile, sb.buf, &head); - - process_command_line_args(&arg_head, trailers); + trailer_end = process_input_file(outfile, sb.buf, &head, opts); - process_trailers_lists(&head, &arg_head); + if (!opts->only_input) { + LIST_HEAD(arg_head); + process_command_line_args(&arg_head, new_trailer_head); + process_trailers_lists(&head, &arg_head); + } - print_all(outfile, &head, trim_empty); + print_all(outfile, &head, opts); free_all(&head); /* Print the lines after the trailers as is */ - fwrite(sb.buf + trailer_end, 1, sb.len - trailer_end, outfile); + if (!opts->only_trailers) + fwrite(sb.buf + trailer_end, 1, sb.len - trailer_end, outfile); - if (in_place) + if (opts->in_place) if (rename_tempfile(&trailers_tempfile, file)) die_errno(_("could not rename temporary file to %s"), file); @@ -1054,3 +1116,49 @@ void trailer_info_release(struct trailer_info *info) free(info->trailers[i]); free(info->trailers); } + +static void format_trailer_info(struct strbuf *out, + const struct trailer_info *info, + const struct process_trailer_options *opts) +{ + int i; + + /* If we want the whole block untouched, we can take the fast path. */ + if (!opts->only_trailers && !opts->unfold) { + strbuf_add(out, info->trailer_start, + info->trailer_end - info->trailer_start); + return; + } + + for (i = 0; i < info->trailer_nr; i++) { + char *trailer = info->trailers[i]; + int separator_pos = find_separator(trailer, separators); + + if (separator_pos >= 1) { + struct strbuf tok = STRBUF_INIT; + struct strbuf val = STRBUF_INIT; + + parse_trailer(&tok, &val, NULL, trailer, separator_pos); + if (opts->unfold) + unfold_value(&val); + + strbuf_addf(out, "%s: %s\n", tok.buf, val.buf); + strbuf_release(&tok); + strbuf_release(&val); + + } else if (!opts->only_trailers) { + strbuf_addstr(out, trailer); + } + } + +} + +void format_trailers_from_commit(struct strbuf *out, const char *msg, + const struct process_trailer_options *opts) +{ + struct trailer_info info; + + trailer_info_get(&info, msg); + format_trailer_info(out, &info, opts); + trailer_info_release(&info); +} @@ -1,6 +1,33 @@ #ifndef TRAILER_H #define TRAILER_H +#include "list.h" + +enum trailer_where { + WHERE_DEFAULT, + WHERE_END, + WHERE_AFTER, + WHERE_BEFORE, + WHERE_START +}; +enum trailer_if_exists { + EXISTS_DEFAULT, + EXISTS_ADD_IF_DIFFERENT_NEIGHBOR, + EXISTS_ADD_IF_DIFFERENT, + EXISTS_ADD, + EXISTS_REPLACE, + EXISTS_DO_NOTHING +}; +enum trailer_if_missing { + MISSING_DEFAULT, + MISSING_ADD, + MISSING_DO_NOTHING +}; + +int trailer_set_where(enum trailer_where *item, const char *value); +int trailer_set_if_exists(enum trailer_if_exists *item, const char *value); +int trailer_set_if_missing(enum trailer_if_missing *item, const char *value); + struct trailer_info { /* * True if there is a blank line before the location pointed to by @@ -22,11 +49,50 @@ struct trailer_info { size_t trailer_nr; }; -void process_trailers(const char *file, int in_place, int trim_empty, - struct string_list *trailers); +/* + * A list that represents newly-added trailers, such as those provided + * with the --trailer command line option of git-interpret-trailers. + */ +struct new_trailer_item { + struct list_head list; + + const char *text; + + enum trailer_where where; + enum trailer_if_exists if_exists; + enum trailer_if_missing if_missing; +}; + +struct process_trailer_options { + int in_place; + int trim_empty; + int only_trailers; + int only_input; + int unfold; +}; + +#define PROCESS_TRAILER_OPTIONS_INIT {0} + +void process_trailers(const char *file, + const struct process_trailer_options *opts, + struct list_head *new_trailer_head); void trailer_info_get(struct trailer_info *info, const char *str); void trailer_info_release(struct trailer_info *info); +/* + * Format the trailers from the commit msg "msg" into the strbuf "out". + * Note two caveats about "opts": + * + * - this is primarily a helper for pretty.c, and not + * all of the flags are supported. + * + * - this differs from process_trailers slightly in that we always format + * only the trailer block itself, even if the "only_trailers" option is not + * set. + */ +void format_trailers_from_commit(struct strbuf *out, const char *msg, + const struct process_trailer_options *opts); + #endif /* TRAILER_H */ diff --git a/transport-helper.c b/transport-helper.c index 8f68d69a8..f50b34df2 100644 --- a/transport-helper.c +++ b/transport-helper.c @@ -1117,6 +1117,13 @@ int transport_helper_init(struct transport *transport, const char *name) __attribute__((format (printf, 1, 2))) static void transfer_debug(const char *fmt, ...) { + /* + * NEEDSWORK: This function is sometimes used from multiple threads, and + * we end up using debug_enabled racily. That "should not matter" since + * we always write the same value, but it's still wrong. This function + * is listed in .tsan-suppressions for the time being. + */ + va_list args; char msgbuf[PBUFFERSIZE]; static int debug_enabled = -1; diff --git a/unpack-trees.c b/unpack-trees.c index 0013a1194..71b70ccb1 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1,5 +1,6 @@ #define NO_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" +#include "repository.h" #include "config.h" #include "dir.h" #include "tree.h" @@ -162,7 +163,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, msgs[ERROR_BIND_OVERLAP] = _("Entry '%s' overlaps with '%s'. Cannot bind."); msgs[ERROR_SPARSE_NOT_UPTODATE_FILE] = - _("Cannot update sparse checkout: the following entries are not up-to-date:\n%s"); + _("Cannot update sparse checkout: the following entries are not up to date:\n%s"); msgs[ERROR_WOULD_LOSE_ORPHANED_OVERWRITTEN] = _("The following working tree files would be overwritten by sparse checkout update:\n%s"); msgs[ERROR_WOULD_LOSE_ORPHANED_REMOVED] = @@ -255,47 +256,41 @@ static int check_submodule_move_head(const struct cache_entry *ce, { unsigned flags = SUBMODULE_MOVE_HEAD_DRY_RUN; const struct submodule *sub = submodule_from_ce(ce); + if (!sub) return 0; if (o->reset) flags |= SUBMODULE_MOVE_HEAD_FORCE; - switch (sub->update_strategy.type) { - case SM_UPDATE_UNSPECIFIED: - case SM_UPDATE_CHECKOUT: - if (submodule_move_head(ce->name, old_id, new_id, flags)) - return o->gently ? -1 : - add_rejected_path(o, ERROR_WOULD_LOSE_SUBMODULE, ce->name); - return 0; - case SM_UPDATE_NONE: - return 0; - case SM_UPDATE_REBASE: - case SM_UPDATE_MERGE: - case SM_UPDATE_COMMAND: - default: - warning(_("submodule update strategy not supported for submodule '%s'"), ce->name); - return -1; - } + if (submodule_move_head(ce->name, old_id, new_id, flags)) + return o->gently ? -1 : + add_rejected_path(o, ERROR_WOULD_LOSE_SUBMODULE, ce->name); + return 0; } -static void reload_gitmodules_file(struct index_state *index, - struct checkout *state) +/* + * Preform the loading of the repository's gitmodules file. This function is + * used by 'check_update()' to perform loading of the gitmodules file in two + * differnt situations: + * (1) before removing entries from the working tree if the gitmodules file has + * been marked for removal. This situation is specified by 'state' == NULL. + * (2) before checking out entries to the working tree if the gitmodules file + * has been marked for update. This situation is specified by 'state' != NULL. + */ +static void load_gitmodules_file(struct index_state *index, + struct checkout *state) { - int i; - for (i = 0; i < index->cache_nr; i++) { - struct cache_entry *ce = index->cache[i]; - if (ce->ce_flags & CE_UPDATE) { - int r = strcmp(ce->name, GITMODULES_FILE); - if (r < 0) - continue; - else if (r == 0) { - submodule_free(); - checkout_entry(ce, state, NULL); - gitmodules_config(); - git_config(submodule_config, NULL); - } else - break; + int pos = index_name_pos(index, GITMODULES_FILE, strlen(GITMODULES_FILE)); + + if (pos >= 0) { + struct cache_entry *ce = index->cache[pos]; + if (!state && ce->ce_flags & CE_WT_REMOVE) { + repo_read_gitmodules(the_repository); + } else if (state && (ce->ce_flags & CE_UPDATE)) { + submodule_free(); + checkout_entry(ce, state, NULL); + repo_read_gitmodules(the_repository); } } } @@ -308,19 +303,9 @@ static void unlink_entry(const struct cache_entry *ce) { const struct submodule *sub = submodule_from_ce(ce); if (sub) { - switch (sub->update_strategy.type) { - case SM_UPDATE_UNSPECIFIED: - case SM_UPDATE_CHECKOUT: - case SM_UPDATE_REBASE: - case SM_UPDATE_MERGE: - /* state.force is set at the caller. */ - submodule_move_head(ce->name, "HEAD", NULL, - SUBMODULE_MOVE_HEAD_FORCE); - break; - case SM_UPDATE_NONE: - case SM_UPDATE_COMMAND: - return; /* Do not touch the submodule. */ - } + /* state.force is set at the caller. */ + submodule_move_head(ce->name, "HEAD", NULL, + SUBMODULE_MOVE_HEAD_FORCE); } if (!check_leading_path(ce->name, ce_namelen(ce))) return; @@ -364,6 +349,10 @@ static int check_updates(struct unpack_trees_options *o) if (o->update) git_attr_set_direction(GIT_ATTR_CHECKOUT, index); + + if (should_update_submodules() && o->update && !o->dry_run) + load_gitmodules_file(index, NULL); + for (i = 0; i < index->cache_nr; i++) { const struct cache_entry *ce = index->cache[i]; @@ -377,7 +366,7 @@ static int check_updates(struct unpack_trees_options *o) remove_scheduled_dirs(); if (should_update_submodules() && o->update && !o->dry_run) - reload_gitmodules_file(index, &state); + load_gitmodules_file(index, &state); enable_delayed_checkout(&state); for (i = 0; i < index->cache_nr; i++) { diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c index 5a89db30e..3fd047a8b 100644 --- a/vcs-svn/fast_export.c +++ b/vcs-svn/fast_export.c @@ -6,7 +6,6 @@ #include "cache.h" #include "quote.h" #include "fast_export.h" -#include "repo_tree.h" #include "strbuf.h" #include "svndiff.h" #include "sliding_window.h" @@ -210,7 +209,7 @@ static long apply_delta(off_t len, struct line_buffer *input, die("invalid cat-blob response: %s", response); check_preimage_overflow(preimage.max_off, 1); } - if (old_mode == REPO_MODE_LNK) { + if (old_mode == S_IFLNK) { strbuf_addstr(&preimage.buf, "link "); check_preimage_overflow(preimage.max_off, strlen("link ")); preimage.max_off += strlen("link "); @@ -244,7 +243,7 @@ void fast_export_buf_to_data(const struct strbuf *data) void fast_export_data(uint32_t mode, off_t len, struct line_buffer *input) { assert(len >= 0); - if (mode == REPO_MODE_LNK) { + if (mode == S_IFLNK) { /* svn symlink blobs start with "link " */ if (len < 5) die("invalid dump: symlink too short for \"link\" prefix"); @@ -312,6 +311,40 @@ int fast_export_ls(const char *path, uint32_t *mode, struct strbuf *dataref) return parse_ls_response(get_response_line(), mode, dataref); } +const char *fast_export_read_path(const char *path, uint32_t *mode_out) +{ + int err; + static struct strbuf buf = STRBUF_INIT; + + strbuf_reset(&buf); + err = fast_export_ls(path, mode_out, &buf); + if (err) { + if (errno != ENOENT) + die_errno("BUG: unexpected fast_export_ls error"); + /* Treat missing paths as directories. */ + *mode_out = S_IFDIR; + return NULL; + } + return buf.buf; +} + +void fast_export_copy(uint32_t revision, const char *src, const char *dst) +{ + int err; + uint32_t mode; + static struct strbuf data = STRBUF_INIT; + + strbuf_reset(&data); + err = fast_export_ls_rev(revision, src, &mode, &data); + if (err) { + if (errno != ENOENT) + die_errno("BUG: unexpected fast_export_ls_rev error"); + fast_export_delete(dst); + return; + } + fast_export_modify(dst, mode, data.buf); +} + void fast_export_blob_delta(uint32_t mode, uint32_t old_mode, const char *old_data, off_t len, struct line_buffer *input) @@ -320,7 +353,7 @@ void fast_export_blob_delta(uint32_t mode, assert(len >= 0); postimage_len = apply_delta(len, input, old_data, old_mode); - if (mode == REPO_MODE_LNK) { + if (mode == S_IFLNK) { buffer_skip_bytes(&postimage, strlen("link ")); postimage_len -= strlen("link "); } diff --git a/vcs-svn/fast_export.h b/vcs-svn/fast_export.h index b9a3b71c9..60b79c35b 100644 --- a/vcs-svn/fast_export.h +++ b/vcs-svn/fast_export.h @@ -28,4 +28,7 @@ int fast_export_ls_rev(uint32_t rev, const char *path, int fast_export_ls(const char *path, uint32_t *mode_out, struct strbuf *dataref_out); +void fast_export_copy(uint32_t revision, const char *src, const char *dst); +const char *fast_export_read_path(const char *path, uint32_t *mode_out); + #endif diff --git a/vcs-svn/repo_tree.c b/vcs-svn/repo_tree.c deleted file mode 100644 index 67d27f0b6..000000000 --- a/vcs-svn/repo_tree.c +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Licensed under a two-clause BSD-style license. - * See LICENSE for details. - */ - -#include "git-compat-util.h" -#include "strbuf.h" -#include "repo_tree.h" -#include "fast_export.h" - -const char *repo_read_path(const char *path, uint32_t *mode_out) -{ - int err; - static struct strbuf buf = STRBUF_INIT; - - strbuf_reset(&buf); - err = fast_export_ls(path, mode_out, &buf); - if (err) { - if (errno != ENOENT) - die_errno("BUG: unexpected fast_export_ls error"); - /* Treat missing paths as directories. */ - *mode_out = REPO_MODE_DIR; - return NULL; - } - return buf.buf; -} - -void repo_copy(uint32_t revision, const char *src, const char *dst) -{ - int err; - uint32_t mode; - static struct strbuf data = STRBUF_INIT; - - strbuf_reset(&data); - err = fast_export_ls_rev(revision, src, &mode, &data); - if (err) { - if (errno != ENOENT) - die_errno("BUG: unexpected fast_export_ls_rev error"); - fast_export_delete(dst); - return; - } - fast_export_modify(dst, mode, data.buf); -} - -void repo_delete(const char *path) -{ - fast_export_delete(path); -} diff --git a/vcs-svn/repo_tree.h b/vcs-svn/repo_tree.h deleted file mode 100644 index 889c6a3c9..000000000 --- a/vcs-svn/repo_tree.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef REPO_TREE_H_ -#define REPO_TREE_H_ - -struct strbuf; - -#define REPO_MODE_DIR 0040000 -#define REPO_MODE_BLB 0100644 -#define REPO_MODE_EXE 0100755 -#define REPO_MODE_LNK 0120000 - -uint32_t next_blob_mark(void); -void repo_copy(uint32_t revision, const char *src, const char *dst); -void repo_add(const char *path, uint32_t mode, uint32_t blob_mark); -const char *repo_read_path(const char *path, uint32_t *mode_out); -void repo_delete(const char *path); -void repo_commit(uint32_t revision, const char *author, - const struct strbuf *log, const char *uuid, const char *url, - long unsigned timestamp); -void repo_diff(uint32_t r1, uint32_t r2); -void repo_init(void); -void repo_reset(void); - -#endif diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c index 1846685a2..ec6b35061 100644 --- a/vcs-svn/svndump.c +++ b/vcs-svn/svndump.c @@ -8,7 +8,6 @@ */ #include "cache.h" -#include "repo_tree.h" #include "fast_export.h" #include "line_buffer.h" #include "strbuf.h" @@ -134,13 +133,13 @@ static void handle_property(const struct strbuf *key_buf, die("invalid dump: sets type twice"); } if (!val) { - node_ctx.type = REPO_MODE_BLB; + node_ctx.type = S_IFREG | 0644; return; } *type_set = 1; node_ctx.type = keylen == strlen("svn:executable") ? - REPO_MODE_EXE : - REPO_MODE_LNK; + (S_IFREG | 0755) : + S_IFLNK; } } @@ -219,45 +218,45 @@ static void handle_node(void) */ static const char *const empty_blob = "::empty::"; const char *old_data = NULL; - uint32_t old_mode = REPO_MODE_BLB; + uint32_t old_mode = S_IFREG | 0644; if (node_ctx.action == NODEACT_DELETE) { if (have_text || have_props || node_ctx.srcRev) die("invalid dump: deletion node has " "copyfrom info, text, or properties"); - repo_delete(node_ctx.dst.buf); + fast_export_delete(node_ctx.dst.buf); return; } if (node_ctx.action == NODEACT_REPLACE) { - repo_delete(node_ctx.dst.buf); + fast_export_delete(node_ctx.dst.buf); node_ctx.action = NODEACT_ADD; } if (node_ctx.srcRev) { - repo_copy(node_ctx.srcRev, node_ctx.src.buf, node_ctx.dst.buf); + fast_export_copy(node_ctx.srcRev, node_ctx.src.buf, node_ctx.dst.buf); if (node_ctx.action == NODEACT_ADD) node_ctx.action = NODEACT_CHANGE; } - if (have_text && type == REPO_MODE_DIR) + if (have_text && type == S_IFDIR) die("invalid dump: directories cannot have text attached"); /* * Find old content (old_data) and decide on the new mode. */ if (node_ctx.action == NODEACT_CHANGE && !*node_ctx.dst.buf) { - if (type != REPO_MODE_DIR) + if (type != S_IFDIR) die("invalid dump: root of tree is not a regular file"); old_data = NULL; } else if (node_ctx.action == NODEACT_CHANGE) { uint32_t mode; - old_data = repo_read_path(node_ctx.dst.buf, &mode); - if (mode == REPO_MODE_DIR && type != REPO_MODE_DIR) + old_data = fast_export_read_path(node_ctx.dst.buf, &mode); + if (mode == S_IFDIR && type != S_IFDIR) die("invalid dump: cannot modify a directory into a file"); - if (mode != REPO_MODE_DIR && type == REPO_MODE_DIR) + if (mode != S_IFDIR && type == S_IFDIR) die("invalid dump: cannot modify a file into a directory"); node_ctx.type = mode; old_mode = mode; } else if (node_ctx.action == NODEACT_ADD) { - if (type == REPO_MODE_DIR) + if (type == S_IFDIR) old_data = NULL; else if (have_text) old_data = empty_blob; @@ -280,7 +279,7 @@ static void handle_node(void) /* * Save the result. */ - if (type == REPO_MODE_DIR) /* directories are not tracked. */ + if (type == S_IFDIR) /* directories are not tracked. */ return; assert(old_data); if (old_data == empty_blob) @@ -385,9 +384,9 @@ void svndump_read(const char *url, const char *local_ref, const char *notes_ref) continue; strbuf_addf(&rev_ctx.note, "%s\n", t); if (!strcmp(val, "dir")) - node_ctx.type = REPO_MODE_DIR; + node_ctx.type = S_IFDIR; else if (!strcmp(val, "file")) - node_ctx.type = REPO_MODE_BLB; + node_ctx.type = S_IFREG | 0644; else fprintf(stderr, "Unknown node-kind: %s\n", val); break; |