diff options
146 files changed, 5636 insertions, 3710 deletions
diff --git a/Documentation/CodingGuidelines b/Documentation/CodingGuidelines index 2248cf7324..c4cb5ff0d4 100644 --- a/Documentation/CodingGuidelines +++ b/Documentation/CodingGuidelines @@ -256,12 +256,12 @@ For C programs: Note however that a comment that explains a translatable string to translators uses a convention of starting with a magic token - "TRANSLATORS: " immediately after the opening delimiter, even when - it spans multiple lines. We do not add an asterisk at the beginning - of each line, either. E.g. + "TRANSLATORS: ", e.g. - /* TRANSLATORS: here is a comment that explains the string - to be translated, that follows immediately after it */ + /* + * TRANSLATORS: here is a comment that explains the string to + * be translated, that follows immediately after it. + */ _("Here is a translatable string explained by the above."); - Double negation is often harder to understand than no negation diff --git a/Documentation/RelNotes/2.13.1.txt b/Documentation/RelNotes/2.13.1.txt new file mode 100644 index 0000000000..ed7cd976d9 --- /dev/null +++ b/Documentation/RelNotes/2.13.1.txt @@ -0,0 +1,114 @@ +Git v2.13.1 Release Notes +========================= + +Fixes since v2.13 +----------------- + + * The Web interface to gmane news archive is long gone, even though + the articles are still accessible via NTTP. Replace the links with + ones to public-inbox.org. Because their message identification is + based on the actual message-id, it is likely that it will be easier + to migrate away from it if/when necessary. + + * Update tests to pass under GETTEXT_POISON (a mechanism to ensure + that output strings that should not be translated are not + translated by mistake), and tell TravisCI to run them. + + * Setting "log.decorate=false" in the configuration file did not take + effect in v2.13, which has been corrected. + + * An earlier update to test 7400 needed to be skipped on CYGWIN. + + * Git sometimes gives an advice in a rhetorical question that does + not require an answer, which can confuse new users and non native + speakers. Attempt to rephrase them. + + * "git read-tree -m" (no tree-ish) gave a nonsense suggestion "use + --empty if you want to clear the index". With "-m", such a request + will still fail anyway, as you'd need to name at least one tree-ish + to be merged. + + * The codepath in "git am" that is used when running "git rebase" + leaked memory held for the log message of the commits being rebased. + + * "pack-objects" can stream a slice of an existing packfile out when + the pack bitmap can tell that the reachable objects are all needed + in the output, without inspecting individual objects. This + strategy however would not work well when "--local" and other + options are in use, and need to be disabled. + + * Clarify documentation for include.path and includeIf.<condition>.path + configuration variables. + + * Tag objects, which are not reachable from any ref, that point at + missing objects were mishandled by "git gc" and friends (they + should silently be ignored instead) + + * A few http:// links that are redirected to https:// in the + documentation have been updated to https:// links. + + * Make sure our tests would pass when the sources are checked out + with "platform native" line ending convention by default on + Windows. Some "text" files out tests use and the test scripts + themselves that are meant to be run with /bin/sh, ought to be + checked out with eol=LF even on Windows. + + * Fix memory leaks pointed out by Coverity (and people). + + * The receive-pack program now makes sure that the push certificate + records the same set of push options used for pushing. + + * "git cherry-pick" and other uses of the sequencer machinery + mishandled a trailer block whose last line is an incomplete line. + This has been fixed so that an additional sign-off etc. are added + after completing the existing incomplete line. + + * The shell completion script (in contrib/) learned "git stash" has + a new "push" subcommand. + + * Travis CI gained a task to format the documentation with both + AsciiDoc and AsciiDoctor. + + * Update the C style recommendation for notes for translators, as + recent versions of gettext tools can work with our style of + multi-line comments. + + * "git clone --config var=val" is a way to populate the + per-repository configuration file of the new repository, but it did + not work well when val is an empty string. This has been fixed. + + * A few codepaths in "checkout" and "am" working on an unborn branch + tried to access an uninitialized piece of memory. + + * "git for-each-ref --format=..." with %(HEAD) in the format used to + resolve the HEAD symref as many times as it had processed refs, + which was wasteful, and "git branch" shared the same problem. + + * "git interpret-trailers", when used as GIT_EDITOR for "git commit + -v", looked for and appended to a trailer block at the very end, + i.e. at the end of the "diff" output. The command has been + corrected to pay attention to the cut-mark line "commit -v" adds to + the buffer---the real trailer block should appear just before it. + + * A test allowed both "git push" and "git receive-pack" on the other + end write their traces into the same file. This is OK on platforms + that allows atomically appending to a file opened with O_APPEND, + but on other platforms led to a mangled output, causing + intermittent test failures. This has been fixed by disabling + traces from "receive-pack" in the test. + + * "foo\bar\baz" in "git fetch foo\bar\baz", even though there is no + slashes in it, cannot be a nickname for a remote on Windows, as + that is likely to be a pathname on a local filesystem. + + * The "collision detecting" SHA-1 implementation shipped with 2.13 + was quite broken on some big-endian platforms and/or platforms that + do not like unaligned fetches. Update to the upstream code which + has already fixed these issues. + + * "git am -h" triggered a BUG(). + + * The interaction of "url.*.insteadOf" and custom URL scheme's + whitelisting is now documented better. + +Also contains various documentation updates and code clean-ups. diff --git a/Documentation/RelNotes/2.13.2.txt b/Documentation/RelNotes/2.13.2.txt new file mode 100644 index 0000000000..c8ba0fa16f --- /dev/null +++ b/Documentation/RelNotes/2.13.2.txt @@ -0,0 +1,37 @@ +Git v2.13.2 Release Notes +========================= + +Fixes since v2.13.1 +------------------- + + * The "collision detecting" SHA-1 implementation shipped with 2.13.1 + was still broken on some platforms. Update to the upstream code + again to take their fix. + + * "git checkout --recurse-submodules" did not quite work with a + submodule that itself has submodules. + + * Introduce the BUG() macro to improve die("BUG: ..."). + + * The "run-command" API implementation has been made more robust + against dead-locking in a threaded environment. + + * A recent update to t5545-push-options.sh started skipping all the + tests in the script when a web server testing is disabled or + unavailable, not just the ones that require a web server. Non HTTP + tests have been salvaged to always run in this script. + + * "git clean -d" used to clean directories that has ignored files, + even though the command should not lose ignored ones without "-x". + "git status --ignored" did not list ignored and untracked files + without "-uall". These have been corrected. + + * The timestamp of the index file is now taken after the file is + closed, to help Windows, on which a stale timestamp is reported by + fstat() on a file that is opened for writing and data was written + but not yet closed. + + * "git pull --rebase --autostash" didn't auto-stash when the local history + fast-forwards to the upstream. + +Also contains various documentation updates and code clean-ups. diff --git a/Documentation/RelNotes/2.14.0.txt b/Documentation/RelNotes/2.14.0.txt index d0f7ef5590..257f1e7d29 100644 --- a/Documentation/RelNotes/2.14.0.txt +++ b/Documentation/RelNotes/2.14.0.txt @@ -18,6 +18,10 @@ Backward compatibility notes. might still be cases that need to be addressed--bug reports are greatly appreciated. + * The experiment to improve the hunk-boundary selection of textual + diff output has finished, and the "indent heuristics" has now + become the default. + Updates since v2.13 ------------------- @@ -46,7 +50,7 @@ UI, Workflows & Features * "git send-email" learned to run sendemail-validate hook to inspect and reject a message before sending it out. - (merge 6489660b4b jt/send-email-validate-hook later to maint). + (merge 177409e589 jt/send-email-validate-hook later to maint). * There is no good reason why "git fetch $there $sha1" should fail when the $sha1 names an object at the tip of an advertised ref, @@ -60,6 +64,12 @@ UI, Workflows & Features current repository to determine if the contents from the named path should be included. + * Make the "indent" heuristics the default in "diff" and diff.indentHeuristics + configuration variable an escape hatch for those who do no want it. + + * Many commands learned to pay attention to submodule.recurse + configuration. + Performance, Internal Implementation, Development Support etc. @@ -76,7 +86,6 @@ Performance, Internal Implementation, Development Support etc. * Travis CI gained a task to format the documentation with both AsciiDoc and AsciiDoctor. - (merge 505ad91304 ls/travis-doc-asciidoctor later to maint). * Some platforms have ulong that is smaller than time_t, and our historical use of ulong for timestamp would mean they cannot @@ -110,6 +119,33 @@ Performance, Internal Implementation, Development Support etc. operations now, which would speed up "git status" (as long as the cache is properly invalidated). + * The internal implementation of "git grep" has seen some clean-up. + (merge 8df4c2953f ab/grep-preparatory-cleanup later to maint). + + * Update the C style recommendation for notes for translators, as + recent versions of gettext tools can work with our style of + multi-line comments. + + * The implementation of "ref" API around the "packed refs" have been + cleaned up, in preparation for further changes. + + * The internal logic used in "git blame" has been libified to make it + easier to use by cgit. + + * Our code often opens a path to an optional file, to work on its + contents when we can successfully open it. We can ignore a failure + to open if such an optional file does not exist, but we do want to + report a failure in opening for other reasons (e.g. we got an I/O + error, or the file is there, but we lack the permission to open). + + The exact errors we need to ignore are ENOENT (obviously) and + ENOTDIR (less obvious). Instead of repeating comparison of errno + with these two constants, introduce a helper function to do so. + + * We often try to open a file for reading whose existence is + optional, and silently ignore errors from open/fopen; report such + errors if they are not due to missing files. + Also contains various documentation updates and code clean-ups. @@ -128,44 +164,35 @@ notes for details). mishandled a trailer block whose last line is an incomplete line. This has been fixed so that an additional sign-off etc. are added after completing the existing incomplete line. - (merge 44dc738a39 jt/use-trailer-api-in-commands later to maint). * The codepath in "git am" that is used when running "git rebase" leaked memory held for the log message of the commits being rebased. - (merge 721f5f1e35 jk/am-leakfix later to maint). * "git clone --config var=val" is a way to populate the per-repository configuration file of the new repository, but it did not work well when val is an empty string. This has been fixed. - (merge db4eca1fea jn/clone-add-empty-config-from-command-line later to maint). * Setting "log.decorate=false" in the configuration file did not take effect in v2.13, which has been corrected. - (merge c74271aae7 ah/log-decorate-default-to-auto later to maint). * A few codepaths in "checkout" and "am" working on an unborn branch tried to access an uninitialized piece of memory. - (merge 57e0ef0e0e rs/checkout-am-fix-unborn later to maint). * The Web interface to gmane news archive is long gone, even though the articles are still accessible via NTTP. Replace the links with ones to public-inbox.org. Because their message identification is based on the actual message-id, it is likely that it will be easier to migrate away from it if/when necessary. - (merge 5840eb9d14 ab/doc-replace-gmane-links later to maint). * The receive-pack program now makes sure that the push certificate records the same set of push options used for pushing. - (merge cbaf82cc6b jt/push-options-doc later to maint). * Tests have been updated to pass under GETTEXT_POISON (a mechanism to ensure that output strings that should not be translated are not translated by mistake), and TravisCI is told to run them. - (merge b8e188f6f5 ab/fix-poison-tests later to maint). * "git checkout --recurse-submodules" did not quite work with a submodule that itself has submodules. - (merge 218c883783 sb/checkout-recurse-submodules later to maint). * Plug some leaks and updates internal API used to implement the split index feature to make it easier to avoid such a leak in the @@ -177,58 +204,46 @@ notes for details). in the output, without inspecting individual objects. This strategy however would not work well when "--local" and other options are in use, and need to be disabled. - (merge da5a1f8100 jk/disable-pack-reuse-when-broken later to maint). * Fix memory leaks pointed out by Coverity (and people). - (merge 443a12f37b js/plug-leaks later to maint). * "git read-tree -m" (no tree-ish) gave a nonsense suggestion "use --empty if you want to clear the index". With "-m", such a request will still fail anyway, as you'd need to name at least one tree-ish to be merged. - (merge b9b10d3681 jc/read-tree-empty-with-m later to maint). * Make sure our tests would pass when the sources are checked out with "platform native" line ending convention by default on Windows. Some "text" files out tests use and the test scripts themselves that are meant to be run with /bin/sh, ought to be checked out with eol=LF even on Windows. - (merge 2779f66505 js/eol-on-ourselves later to maint). * Introduce the BUG() macro to improve die("BUG: ..."). - (merge 3d7dd2d3b6 jk/bug-to-abort later to maint). * Clarify documentation for include.path and includeIf.<condition>.path configuration variables. - (merge ce933ebd5a jk/doc-config-include later to maint). * Git sometimes gives an advice in a rhetorical question that does not require an answer, which can confuse new users and non native speakers. Attempt to rephrase them. - (merge 6963893943 ja/do-not-ask-needless-questions later to maint). * A few http:// links that are redirected to https:// in the documentation have been updated to https:// links. - (merge 5e68729fd9 jk/update-links-in-docs later to maint). * "git for-each-ref --format=..." with %(HEAD) in the format used to resolve the HEAD symref as many times as it had processed refs, which was wasteful, and "git branch" shared the same problem. - (merge 613a0e52ea kn/ref-filter-branch-list later to maint). * Regression fix to topic recently merged to 'master'. - (merge d096d7f1ef pw/rebase-i-regression-fix later to maint). * The shell completion script (in contrib/) learned "git stash" has a new "push" subcommand. - (merge 3851e4483f tg/stash-push-fixup later to maint). * "git interpret-trailers", when used as GIT_EDITOR for "git commit -v", looked for and appended to a trailer block at the very end, i.e. at the end of the "diff" output. The command has been corrected to pay attention to the cut-mark line "commit -v" adds to the buffer---the real trailer block should appear just before it. - (merge d76650b8d1 bm/interpret-trailers-cut-line-is-eom later to maint). * A test allowed both "git push" and "git receive-pack" on the other end write their traces into the same file. This is OK on platforms @@ -236,12 +251,10 @@ notes for details). but on other platforms led to a mangled output, causing intermittent test failures. This has been fixed by disabling traces from "receive-pack" in the test. - (merge 71406ed4d6 jk/alternate-ref-optim later to maint). * Tag objects, which are not reachable from any ref, that point at missing objects were mishandled by "git gc" and friends (they should silently be ignored instead) - (merge a3ba6bf10a jk/ignore-broken-tags-when-ignoring-missing-links later to maint). * "git describe --contains" penalized light-weight tags so much that they were almost never considered. Instead, give them about the @@ -251,24 +264,50 @@ notes for details). * The "run-command" API implementation has been made more robust against dead-locking in a threaded environment. - (merge e3f43ce765 bw/forking-and-threading later to maint). * A recent update to t5545-push-options.sh started skipping all the tests in the script when a web server testing is disabled or unavailable, not just the ones that require a web server. Non HTTP tests have been salvaged to always run in this script. - (merge 2e397e4ddf jc/skip-test-in-the-middle later to maint). * "git send-email" now uses Net::SMTP::SSL, which is obsolete, only when needed. Recent versions of Net::SMTP can do TLS natively. - (merge 0ead000c3a dk/send-email-avoid-net-smtp-ssl-when-able later to maint). + + * "foo\bar\baz" in "git fetch foo\bar\baz", even though there is no + slashes in it, cannot be a nickname for a remote on Windows, as + that is likely to be a pathname on a local filesystem. + + * "git clean -d" used to clean directories that has ignored files, + even though the command should not lose ignored ones without "-x". + "git status --ignored" did not list ignored and untracked files + without "-uall". These have been corrected. + + * The result from "git diff" that compares two blobs, e.g. "git diff + $commit1:$path $commit2:$path", used to be shown with the full + object name as given on the command line, but it is more natural to + use the $path in the output and use it to look up .gitattributes. + (merge 30d005c020 jk/diff-blob later to maint). + + * The "collision detecting" SHA-1 implementation shipped with 2.13 + was quite broken on some big-endian platforms and/or platforms that + do not like unaligned fetches. Update to the upstream code which + has already fixed these issues. + + * "git am -h" triggered a BUG(). + + * The interaction of "url.*.insteadOf" and custom URL scheme's + whitelisting is now documented better. + + * The timestamp of the index file is now taken after the file is + closed, to help Windows, on which a stale timestamp is reported by + fstat() on a file that is opened for writing and data was written + but not yet closed. + + * "git pull --rebase --autostash" didn't auto-stash when the local history + fast-forwards to the upstream. + + * A flaky test has been corrected. + (merge 7c2115aa07 jk/pack-idx-corruption-safety later to maint). * Other minor doc, test and build updates and code cleanups. - (merge 515360f9e9 jn/credential-doc-on-clear later to maint). - (merge 0e6d899fee ab/aix-needs-compat-regex later to maint). - (merge e294e8959f jc/apply-fix-mismerge later to maint). - (merge 7f1b225153 bw/submodule-with-bs-path later to maint). - (merge c8f7c8b704 tb/dedup-crlf-tests later to maint). - (merge 449456ad47 sg/core-filemode-doc-typofix later to maint). - (merge ba4dce784e km/log-showsignature-doc later to maint). - (merge c5a9157393 jh/memihash-opt later to maint). + (merge 8ba74bfd7c jc/diff-tree-stale-comment later to maint). diff --git a/Documentation/config.txt b/Documentation/config.txt index 43d830ee3b..f6278a5ae6 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -883,6 +883,7 @@ core.abbrev:: computed based on the approximate number of packed objects in your repository, which hopefully is enough for abbreviated object names to stay unique for some time. + The minimum length is 4. add.ignoreErrors:: add.ignore-errors (deprecated):: @@ -3090,6 +3091,11 @@ submodule.active:: submodule's path to determine if the submodule is of interest to git commands. +submodule.recurse:: + Specifies if commands recurse into submodules by default. This + applies to all commands that have a `--recurse-submodules` option. + Defaults to false. + submodule.fetchJobs:: Specifies how many submodules are fetched/cloned at the same time. A positive integer allows up to that number of submodules fetched @@ -3235,6 +3241,13 @@ url.<base>.insteadOf:: the best alternative for the particular user, even for a never-before-seen repository on the site. When more than one insteadOf strings match a given URL, the longest match is used. ++ +Note that any protocol restrictions will be applied to the rewritten +URL. If the rewrite changes the URL to use a custom protocol or remote +helper, you may need to adjust the `protocol.*.allow` config to permit +the request. In particular, protocols you expect to use for submodules +must be set to `always` rather than the default of `user`. See the +description of `protocol.allow` above. url.<base>.pushInsteadOf:: Any URL that starts with this value will not be pushed to; diff --git a/Documentation/git-filter-branch.txt b/Documentation/git-filter-branch.txt index 6e4bb02204..7b695dbb72 100644 --- a/Documentation/git-filter-branch.txt +++ b/Documentation/git-filter-branch.txt @@ -86,8 +86,7 @@ OPTIONS This filter may be used if you only need to modify the environment in which the commit will be performed. Specifically, you might want to rewrite the author/committer name/email/time environment - variables (see linkgit:git-commit-tree[1] for details). Do not forget - to re-export the variables. + variables (see linkgit:git-commit-tree[1] for details). --tree-filter <command>:: This is the filter for rewriting the tree and its contents. @@ -340,12 +339,10 @@ git filter-branch --env-filter ' if test "$GIT_AUTHOR_EMAIL" = "root@localhost" then GIT_AUTHOR_EMAIL=john@example.com - export GIT_AUTHOR_EMAIL fi if test "$GIT_COMMITTER_EMAIL" = "root@localhost" then GIT_COMMITTER_EMAIL=john@example.com - export GIT_COMMITTER_EMAIL fi ' -- --all -------------------------------------------------------- diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt index 71f32f3508..5033483db4 100644 --- a/Documentation/git-grep.txt +++ b/Documentation/git-grep.txt @@ -161,8 +161,11 @@ OPTIONS -P:: --perl-regexp:: - Use Perl-compatible regexp for patterns. Requires libpcre to be - compiled in. + Use Perl-compatible regular expressions for patterns. ++ +Support for these types of regular expressions is an optional +compile-time dependency. If Git wasn't compiled with support for them +providing this option will cause it to die. -F:: --fixed-strings:: diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt index 09074c75a4..31cdeaecdf 100644 --- a/Documentation/git-interpret-trailers.txt +++ b/Documentation/git-interpret-trailers.txt @@ -123,7 +123,7 @@ trailer.ifexists:: same <token> in the message. + The valid values for this option are: `addIfDifferentNeighbor` (this -is the default), `addIfDifferent`, `add`, `overwrite` or `doNothing`. +is the default), `addIfDifferent`, `add`, `replace` or `doNothing`. + With `addIfDifferentNeighbor`, a new trailer will be added only if no trailer with the same (<token>, <value>) pair is above or below the line diff --git a/Documentation/git-pull.txt b/Documentation/git-pull.txt index 942af8e0f7..e414185f5a 100644 --- a/Documentation/git-pull.txt +++ b/Documentation/git-pull.txt @@ -159,15 +159,15 @@ present while on branch `<name>`, that value is used instead of In order to determine what URL to use to fetch from, the value of the configuration `remote.<origin>.url` is consulted -and if there is not any such variable, the value on `URL: ` line -in `$GIT_DIR/remotes/<origin>` file is used. +and if there is not any such variable, the value on the `URL:` line +in `$GIT_DIR/remotes/<origin>` is used. In order to determine what remote branches to fetch (and optionally store in the remote-tracking branches) when the command is run without any refspec parameters on the command line, values of the configuration variable `remote.<origin>.fetch` are consulted, and if there aren't any, `$GIT_DIR/remotes/<origin>` -file is consulted and its `Pull: ` lines are used. +is consulted and its `Pull:` lines are used. In addition to the refspec formats described in the OPTIONS section, you can have a globbing refspec that looks like this: diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index c40c470448..b1293f24bb 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -126,6 +126,12 @@ can be used. 'git diff-{asterisk}'). In contrast to the `--sq-quote` option, the command input is still interpreted as usual. +--short[=length]:: + Same as `--verify` but shortens the object name to a unique + prefix with at least `length` characters. The minimum length + is 4, the default is the effective value of the `core.abbrev` + configuration variable (see linkgit:git-config[1]). + --not:: When showing object names, prefix them with '{caret}' and strip '{caret}' prefix from the object names that already have @@ -136,12 +142,6 @@ can be used. The option core.warnAmbiguousRefs is used to select the strict abbreviation mode. ---short:: ---short=number:: - Instead of outputting the full SHA-1 values of object names try to - abbreviate them to a shorter unique name. When no length is specified - 7 is used. The minimum length is 4. - --symbolic:: Usually the object names are output in SHA-1 form (with possible '{caret}' prefix); this option makes them output in a diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt index f1efc116eb..8c87e8cdd7 100644 --- a/Documentation/git-rm.txt +++ b/Documentation/git-rm.txt @@ -140,10 +140,11 @@ Only submodules using a gitfile (which means they were cloned with a Git version 1.7.8 or newer) will be removed from the work tree, as their repository lives inside the .git directory of the superproject. If a submodule (or one of those nested inside it) -still uses a .git directory, `git rm` will fail - no matter if forced -or not - to protect 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). +still uses a .git directory, `git rm` will move the submodules +git directory into the superprojects git directory to protect +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 recorded in the index, no tracked files are modified and no untracked diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt index 9bee9b0c4c..aa2aeabb60 100644 --- a/Documentation/git-svn.txt +++ b/Documentation/git-svn.txt @@ -95,6 +95,10 @@ If you still want the old default, you can get it by passing `--prefix ""` on the command line (`--prefix=""` may not work if your Perl's Getopt::Long is < v2.37). +--ignore-refs=<regex>;; + When passed to 'init' or 'clone' this regular expression will + be preserved as a config key. See 'fetch' for a description + of `--ignore-refs`. --ignore-paths=<regex>;; When passed to 'init' or 'clone' this regular expression will be preserved as a config key. See 'fetch' for a description @@ -138,6 +142,18 @@ the same local time zone. --parent;; Fetch only from the SVN parent of the current HEAD. +--ignore-refs=<regex>;; + Ignore refs for branches or tags matching the Perl regular + expression. A "negative look-ahead assertion" like + `^refs/remotes/origin/(?!tags/wanted-tag|wanted-branch).*$` + can be used to allow only certain refs. ++ +[verse] +config key: svn-remote.<name>.ignore-refs ++ +If the ignore-refs configuration key is set, and the command-line +option is also given, both regular expressions will be used. + --ignore-paths=<regex>;; This allows one to specify a Perl regular expression that will cause skipping of all matching paths from checkout from SVN. @@ -443,6 +459,21 @@ Any other arguments are passed directly to 'git log' (URL) may be omitted if you are working from a 'git svn'-aware repository (that has been `init`-ed with 'git svn'). The -r<revision> option is required for this. ++ +The commit message is supplied either directly with the `-m` or `-F` +option, or indirectly from the tag or commit when the second tree-ish +denotes such an object, or it is requested by invoking an editor (see +`--edit` option below). + +-m <msg>;; +--message=<msg>;; + Use the given `msg` as the commit message. This option + disables the `--edit` option. + +-F <filename>;; +--file=<filename>;; + Take the commit message from the given file. This option + disables the `--edit` option. 'info':: Shows information about a file or directory similar to what diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt index f8a0b787f4..1eb15afa1c 100644 --- a/Documentation/git-tag.txt +++ b/Documentation/git-tag.txt @@ -12,7 +12,7 @@ SYNOPSIS 'git tag' [-a | -s | -u <keyid>] [-f] [-m <msg> | -F <file>] <tagname> [<commit> | <object>] 'git tag' -d <tagname>... -'git tag' [-n[<num>]] -l [--contains <commit>] [--contains <commit>] +'git tag' [-n[<num>]] -l [--contains <commit>] [--no-contains <commit>] [--points-at <object>] [--column[=<options>] | --no-column] [--create-reflog] [--sort=<key>] [--format=<format>] [--[no-]merged [<commit>]] [<pattern>...] diff --git a/Documentation/git.txt b/Documentation/git.txt index fb10314c1d..7dd5e03280 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -35,516 +35,6 @@ manual page gives you an overview of the command-line command syntax. A formatted and hyperlinked copy of the latest Git documentation can be viewed at `https://git.github.io/htmldocs/git.html`. -ifdef::stalenotes[] -[NOTE] -============ - -You are reading the documentation for the latest (possibly -unreleased) version of Git, that is available from the 'master' -branch of the `git.git` repository. -Documentation for older releases are available here: - -* link:v2.13.0/git.html[documentation for release 2.13] - -* release notes for - link:RelNotes/2.13.0.txt[2.13]. - - -* link:v2.12.3/git.html[documentation for release 2.12.3] - -* release notes for - link:RelNotes/2.12.3.txt[2.12.3], - link:RelNotes/2.12.2.txt[2.12.2], - link:RelNotes/2.12.1.txt[2.12.1], - link:RelNotes/2.12.0.txt[2.12]. - -* link:v2.11.1/git.html[documentation for release 2.11.1] - -* release notes for - link:RelNotes/2.11.2.txt[2.11.2], - link:RelNotes/2.11.1.txt[2.11.1], - link:RelNotes/2.11.0.txt[2.11]. - -* link:v2.10.3/git.html[documentation for release 2.10.3] - -* release notes for - link:RelNotes/2.10.3.txt[2.10.3], - link:RelNotes/2.10.2.txt[2.10.2], - link:RelNotes/2.10.1.txt[2.10.1], - link:RelNotes/2.10.0.txt[2.10]. - -* link:v2.9.4/git.html[documentation for release 2.9.4] - -* release notes for - link:RelNotes/2.9.4.txt[2.9.4], - link:RelNotes/2.9.3.txt[2.9.3], - link:RelNotes/2.9.2.txt[2.9.2], - link:RelNotes/2.9.1.txt[2.9.1], - link:RelNotes/2.9.0.txt[2.9]. - -* link:v2.8.5/git.html[documentation for release 2.8.5] - -* release notes for - link:RelNotes/2.8.5.txt[2.8.5], - link:RelNotes/2.8.4.txt[2.8.4], - link:RelNotes/2.8.3.txt[2.8.3], - link:RelNotes/2.8.2.txt[2.8.2], - link:RelNotes/2.8.1.txt[2.8.1], - link:RelNotes/2.8.0.txt[2.8]. - -* link:v2.7.5/git.html[documentation for release 2.7.5] - -* release notes for - link:RelNotes/2.7.5.txt[2.7.5], - link:RelNotes/2.7.4.txt[2.7.4], - link:RelNotes/2.7.3.txt[2.7.3], - link:RelNotes/2.7.2.txt[2.7.2], - link:RelNotes/2.7.1.txt[2.7.1], - link:RelNotes/2.7.0.txt[2.7]. - -* link:v2.6.7/git.html[documentation for release 2.6.7] - -* release notes for - link:RelNotes/2.6.7.txt[2.6.7], - link:RelNotes/2.6.6.txt[2.6.6], - link:RelNotes/2.6.5.txt[2.6.5], - link:RelNotes/2.6.4.txt[2.6.4], - link:RelNotes/2.6.3.txt[2.6.3], - link:RelNotes/2.6.2.txt[2.6.2], - link:RelNotes/2.6.1.txt[2.6.1], - link:RelNotes/2.6.0.txt[2.6]. - -* link:v2.5.6/git.html[documentation for release 2.5.6] - -* release notes for - link:RelNotes/2.5.6.txt[2.5.6], - link:RelNotes/2.5.5.txt[2.5.5], - link:RelNotes/2.5.4.txt[2.5.4], - link:RelNotes/2.5.3.txt[2.5.3], - link:RelNotes/2.5.2.txt[2.5.2], - link:RelNotes/2.5.1.txt[2.5.1], - link:RelNotes/2.5.0.txt[2.5]. - -* link:v2.4.12/git.html[documentation for release 2.4.12] - -* release notes for - link:RelNotes/2.4.12.txt[2.4.12], - link:RelNotes/2.4.11.txt[2.4.11], - link:RelNotes/2.4.10.txt[2.4.10], - link:RelNotes/2.4.9.txt[2.4.9], - link:RelNotes/2.4.8.txt[2.4.8], - link:RelNotes/2.4.7.txt[2.4.7], - link:RelNotes/2.4.6.txt[2.4.6], - link:RelNotes/2.4.5.txt[2.4.5], - link:RelNotes/2.4.4.txt[2.4.4], - link:RelNotes/2.4.3.txt[2.4.3], - link:RelNotes/2.4.2.txt[2.4.2], - link:RelNotes/2.4.1.txt[2.4.1], - link:RelNotes/2.4.0.txt[2.4]. - -* link:v2.3.10/git.html[documentation for release 2.3.10] - -* release notes for - link:RelNotes/2.3.10.txt[2.3.10], - link:RelNotes/2.3.9.txt[2.3.9], - link:RelNotes/2.3.8.txt[2.3.8], - link:RelNotes/2.3.7.txt[2.3.7], - link:RelNotes/2.3.6.txt[2.3.6], - link:RelNotes/2.3.5.txt[2.3.5], - link:RelNotes/2.3.4.txt[2.3.4], - link:RelNotes/2.3.3.txt[2.3.3], - link:RelNotes/2.3.2.txt[2.3.2], - link:RelNotes/2.3.1.txt[2.3.1], - link:RelNotes/2.3.0.txt[2.3]. - -* link:v2.2.3/git.html[documentation for release 2.2.3] - -* release notes for - link:RelNotes/2.2.3.txt[2.2.3], - link:RelNotes/2.2.2.txt[2.2.2], - link:RelNotes/2.2.1.txt[2.2.1], - link:RelNotes/2.2.0.txt[2.2]. - -* link:v2.1.4/git.html[documentation for release 2.1.4] - -* release notes for - link:RelNotes/2.1.4.txt[2.1.4], - link:RelNotes/2.1.3.txt[2.1.3], - link:RelNotes/2.1.2.txt[2.1.2], - link:RelNotes/2.1.1.txt[2.1.1], - link:RelNotes/2.1.0.txt[2.1]. - -* link:v2.0.5/git.html[documentation for release 2.0.5] - -* release notes for - link:RelNotes/2.0.5.txt[2.0.5], - link:RelNotes/2.0.4.txt[2.0.4], - link:RelNotes/2.0.3.txt[2.0.3], - link:RelNotes/2.0.2.txt[2.0.2], - link:RelNotes/2.0.1.txt[2.0.1], - link:RelNotes/2.0.0.txt[2.0.0]. - -* link:v1.9.5/git.html[documentation for release 1.9.5] - -* release notes for - link:RelNotes/1.9.5.txt[1.9.5], - link:RelNotes/1.9.4.txt[1.9.4], - link:RelNotes/1.9.3.txt[1.9.3], - link:RelNotes/1.9.2.txt[1.9.2], - link:RelNotes/1.9.1.txt[1.9.1], - link:RelNotes/1.9.0.txt[1.9.0]. - -* link:v1.8.5.6/git.html[documentation for release 1.8.5.6] - -* release notes for - link:RelNotes/1.8.5.6.txt[1.8.5.6], - link:RelNotes/1.8.5.5.txt[1.8.5.5], - link:RelNotes/1.8.5.4.txt[1.8.5.4], - link:RelNotes/1.8.5.3.txt[1.8.5.3], - link:RelNotes/1.8.5.2.txt[1.8.5.2], - link:RelNotes/1.8.5.1.txt[1.8.5.1], - link:RelNotes/1.8.5.txt[1.8.5]. - -* link:v1.8.4.5/git.html[documentation for release 1.8.4.5] - -* release notes for - link:RelNotes/1.8.4.5.txt[1.8.4.5], - link:RelNotes/1.8.4.4.txt[1.8.4.4], - link:RelNotes/1.8.4.3.txt[1.8.4.3], - link:RelNotes/1.8.4.2.txt[1.8.4.2], - link:RelNotes/1.8.4.1.txt[1.8.4.1], - link:RelNotes/1.8.4.txt[1.8.4]. - -* link:v1.8.3.4/git.html[documentation for release 1.8.3.4] - -* release notes for - link:RelNotes/1.8.3.4.txt[1.8.3.4], - link:RelNotes/1.8.3.3.txt[1.8.3.3], - link:RelNotes/1.8.3.2.txt[1.8.3.2], - link:RelNotes/1.8.3.1.txt[1.8.3.1], - link:RelNotes/1.8.3.txt[1.8.3]. - -* link:v1.8.2.3/git.html[documentation for release 1.8.2.3] - -* release notes for - link:RelNotes/1.8.2.3.txt[1.8.2.3], - link:RelNotes/1.8.2.2.txt[1.8.2.2], - link:RelNotes/1.8.2.1.txt[1.8.2.1], - link:RelNotes/1.8.2.txt[1.8.2]. - -* link:v1.8.1.6/git.html[documentation for release 1.8.1.6] - -* release notes for - link:RelNotes/1.8.1.6.txt[1.8.1.6], - link:RelNotes/1.8.1.5.txt[1.8.1.5], - link:RelNotes/1.8.1.4.txt[1.8.1.4], - link:RelNotes/1.8.1.3.txt[1.8.1.3], - link:RelNotes/1.8.1.2.txt[1.8.1.2], - link:RelNotes/1.8.1.1.txt[1.8.1.1], - link:RelNotes/1.8.1.txt[1.8.1]. - -* link:v1.8.0.3/git.html[documentation for release 1.8.0.3] - -* release notes for - link:RelNotes/1.8.0.3.txt[1.8.0.3], - link:RelNotes/1.8.0.2.txt[1.8.0.2], - link:RelNotes/1.8.0.1.txt[1.8.0.1], - link:RelNotes/1.8.0.txt[1.8.0]. - -* link:v1.7.12.4/git.html[documentation for release 1.7.12.4] - -* release notes for - link:RelNotes/1.7.12.4.txt[1.7.12.4], - link:RelNotes/1.7.12.3.txt[1.7.12.3], - link:RelNotes/1.7.12.2.txt[1.7.12.2], - link:RelNotes/1.7.12.1.txt[1.7.12.1], - link:RelNotes/1.7.12.txt[1.7.12]. - -* link:v1.7.11.7/git.html[documentation for release 1.7.11.7] - -* release notes for - link:RelNotes/1.7.11.7.txt[1.7.11.7], - link:RelNotes/1.7.11.6.txt[1.7.11.6], - link:RelNotes/1.7.11.5.txt[1.7.11.5], - link:RelNotes/1.7.11.4.txt[1.7.11.4], - link:RelNotes/1.7.11.3.txt[1.7.11.3], - link:RelNotes/1.7.11.2.txt[1.7.11.2], - link:RelNotes/1.7.11.1.txt[1.7.11.1], - link:RelNotes/1.7.11.txt[1.7.11]. - -* link:v1.7.10.5/git.html[documentation for release 1.7.10.5] - -* release notes for - link:RelNotes/1.7.10.5.txt[1.7.10.5], - link:RelNotes/1.7.10.4.txt[1.7.10.4], - link:RelNotes/1.7.10.3.txt[1.7.10.3], - link:RelNotes/1.7.10.2.txt[1.7.10.2], - link:RelNotes/1.7.10.1.txt[1.7.10.1], - link:RelNotes/1.7.10.txt[1.7.10]. - -* link:v1.7.9.7/git.html[documentation for release 1.7.9.7] - -* release notes for - link:RelNotes/1.7.9.7.txt[1.7.9.7], - link:RelNotes/1.7.9.6.txt[1.7.9.6], - link:RelNotes/1.7.9.5.txt[1.7.9.5], - link:RelNotes/1.7.9.4.txt[1.7.9.4], - link:RelNotes/1.7.9.3.txt[1.7.9.3], - link:RelNotes/1.7.9.2.txt[1.7.9.2], - link:RelNotes/1.7.9.1.txt[1.7.9.1], - link:RelNotes/1.7.9.txt[1.7.9]. - -* link:v1.7.8.6/git.html[documentation for release 1.7.8.6] - -* release notes for - link:RelNotes/1.7.8.6.txt[1.7.8.6], - link:RelNotes/1.7.8.5.txt[1.7.8.5], - link:RelNotes/1.7.8.4.txt[1.7.8.4], - link:RelNotes/1.7.8.3.txt[1.7.8.3], - link:RelNotes/1.7.8.2.txt[1.7.8.2], - link:RelNotes/1.7.8.1.txt[1.7.8.1], - link:RelNotes/1.7.8.txt[1.7.8]. - -* link:v1.7.7.7/git.html[documentation for release 1.7.7.7] - -* release notes for - link:RelNotes/1.7.7.7.txt[1.7.7.7], - link:RelNotes/1.7.7.6.txt[1.7.7.6], - link:RelNotes/1.7.7.5.txt[1.7.7.5], - link:RelNotes/1.7.7.4.txt[1.7.7.4], - link:RelNotes/1.7.7.3.txt[1.7.7.3], - link:RelNotes/1.7.7.2.txt[1.7.7.2], - link:RelNotes/1.7.7.1.txt[1.7.7.1], - link:RelNotes/1.7.7.txt[1.7.7]. - -* link:v1.7.6.6/git.html[documentation for release 1.7.6.6] - -* release notes for - link:RelNotes/1.7.6.6.txt[1.7.6.6], - link:RelNotes/1.7.6.5.txt[1.7.6.5], - link:RelNotes/1.7.6.4.txt[1.7.6.4], - link:RelNotes/1.7.6.3.txt[1.7.6.3], - link:RelNotes/1.7.6.2.txt[1.7.6.2], - link:RelNotes/1.7.6.1.txt[1.7.6.1], - link:RelNotes/1.7.6.txt[1.7.6]. - -* link:v1.7.5.4/git.html[documentation for release 1.7.5.4] - -* release notes for - link:RelNotes/1.7.5.4.txt[1.7.5.4], - link:RelNotes/1.7.5.3.txt[1.7.5.3], - link:RelNotes/1.7.5.2.txt[1.7.5.2], - link:RelNotes/1.7.5.1.txt[1.7.5.1], - link:RelNotes/1.7.5.txt[1.7.5]. - -* link:v1.7.4.5/git.html[documentation for release 1.7.4.5] - -* release notes for - link:RelNotes/1.7.4.5.txt[1.7.4.5], - link:RelNotes/1.7.4.4.txt[1.7.4.4], - link:RelNotes/1.7.4.3.txt[1.7.4.3], - link:RelNotes/1.7.4.2.txt[1.7.4.2], - link:RelNotes/1.7.4.1.txt[1.7.4.1], - link:RelNotes/1.7.4.txt[1.7.4]. - -* link:v1.7.3.5/git.html[documentation for release 1.7.3.5] - -* release notes for - link:RelNotes/1.7.3.5.txt[1.7.3.5], - link:RelNotes/1.7.3.4.txt[1.7.3.4], - link:RelNotes/1.7.3.3.txt[1.7.3.3], - link:RelNotes/1.7.3.2.txt[1.7.3.2], - link:RelNotes/1.7.3.1.txt[1.7.3.1], - link:RelNotes/1.7.3.txt[1.7.3]. - -* link:v1.7.2.5/git.html[documentation for release 1.7.2.5] - -* release notes for - link:RelNotes/1.7.2.5.txt[1.7.2.5], - link:RelNotes/1.7.2.4.txt[1.7.2.4], - link:RelNotes/1.7.2.3.txt[1.7.2.3], - link:RelNotes/1.7.2.2.txt[1.7.2.2], - link:RelNotes/1.7.2.1.txt[1.7.2.1], - link:RelNotes/1.7.2.txt[1.7.2]. - -* link:v1.7.1.4/git.html[documentation for release 1.7.1.4] - -* release notes for - link:RelNotes/1.7.1.4.txt[1.7.1.4], - link:RelNotes/1.7.1.3.txt[1.7.1.3], - link:RelNotes/1.7.1.2.txt[1.7.1.2], - link:RelNotes/1.7.1.1.txt[1.7.1.1], - link:RelNotes/1.7.1.txt[1.7.1]. - -* link:v1.7.0.9/git.html[documentation for release 1.7.0.9] - -* release notes for - link:RelNotes/1.7.0.9.txt[1.7.0.9], - link:RelNotes/1.7.0.8.txt[1.7.0.8], - link:RelNotes/1.7.0.7.txt[1.7.0.7], - link:RelNotes/1.7.0.6.txt[1.7.0.6], - link:RelNotes/1.7.0.5.txt[1.7.0.5], - link:RelNotes/1.7.0.4.txt[1.7.0.4], - link:RelNotes/1.7.0.3.txt[1.7.0.3], - link:RelNotes/1.7.0.2.txt[1.7.0.2], - link:RelNotes/1.7.0.1.txt[1.7.0.1], - link:RelNotes/1.7.0.txt[1.7.0]. - -* link:v1.6.6.3/git.html[documentation for release 1.6.6.3] - -* release notes for - link:RelNotes/1.6.6.3.txt[1.6.6.3], - link:RelNotes/1.6.6.2.txt[1.6.6.2], - link:RelNotes/1.6.6.1.txt[1.6.6.1], - link:RelNotes/1.6.6.txt[1.6.6]. - -* link:v1.6.5.9/git.html[documentation for release 1.6.5.9] - -* release notes for - link:RelNotes/1.6.5.9.txt[1.6.5.9], - link:RelNotes/1.6.5.8.txt[1.6.5.8], - link:RelNotes/1.6.5.7.txt[1.6.5.7], - link:RelNotes/1.6.5.6.txt[1.6.5.6], - link:RelNotes/1.6.5.5.txt[1.6.5.5], - link:RelNotes/1.6.5.4.txt[1.6.5.4], - link:RelNotes/1.6.5.3.txt[1.6.5.3], - link:RelNotes/1.6.5.2.txt[1.6.5.2], - link:RelNotes/1.6.5.1.txt[1.6.5.1], - link:RelNotes/1.6.5.txt[1.6.5]. - -* link:v1.6.4.5/git.html[documentation for release 1.6.4.5] - -* release notes for - link:RelNotes/1.6.4.5.txt[1.6.4.5], - link:RelNotes/1.6.4.4.txt[1.6.4.4], - link:RelNotes/1.6.4.3.txt[1.6.4.3], - link:RelNotes/1.6.4.2.txt[1.6.4.2], - link:RelNotes/1.6.4.1.txt[1.6.4.1], - link:RelNotes/1.6.4.txt[1.6.4]. - -* link:v1.6.3.4/git.html[documentation for release 1.6.3.4] - -* release notes for - link:RelNotes/1.6.3.4.txt[1.6.3.4], - link:RelNotes/1.6.3.3.txt[1.6.3.3], - link:RelNotes/1.6.3.2.txt[1.6.3.2], - link:RelNotes/1.6.3.1.txt[1.6.3.1], - link:RelNotes/1.6.3.txt[1.6.3]. - -* release notes for - link:RelNotes/1.6.2.5.txt[1.6.2.5], - link:RelNotes/1.6.2.4.txt[1.6.2.4], - link:RelNotes/1.6.2.3.txt[1.6.2.3], - link:RelNotes/1.6.2.2.txt[1.6.2.2], - link:RelNotes/1.6.2.1.txt[1.6.2.1], - link:RelNotes/1.6.2.txt[1.6.2]. - -* link:v1.6.1.3/git.html[documentation for release 1.6.1.3] - -* release notes for - link:RelNotes/1.6.1.3.txt[1.6.1.3], - link:RelNotes/1.6.1.2.txt[1.6.1.2], - link:RelNotes/1.6.1.1.txt[1.6.1.1], - link:RelNotes/1.6.1.txt[1.6.1]. - -* link:v1.6.0.6/git.html[documentation for release 1.6.0.6] - -* release notes for - link:RelNotes/1.6.0.6.txt[1.6.0.6], - link:RelNotes/1.6.0.5.txt[1.6.0.5], - link:RelNotes/1.6.0.4.txt[1.6.0.4], - link:RelNotes/1.6.0.3.txt[1.6.0.3], - link:RelNotes/1.6.0.2.txt[1.6.0.2], - link:RelNotes/1.6.0.1.txt[1.6.0.1], - link:RelNotes/1.6.0.txt[1.6.0]. - -* link:v1.5.6.6/git.html[documentation for release 1.5.6.6] - -* release notes for - link:RelNotes/1.5.6.6.txt[1.5.6.6], - link:RelNotes/1.5.6.5.txt[1.5.6.5], - link:RelNotes/1.5.6.4.txt[1.5.6.4], - link:RelNotes/1.5.6.3.txt[1.5.6.3], - link:RelNotes/1.5.6.2.txt[1.5.6.2], - link:RelNotes/1.5.6.1.txt[1.5.6.1], - link:RelNotes/1.5.6.txt[1.5.6]. - -* link:v1.5.5.6/git.html[documentation for release 1.5.5.6] - -* release notes for - link:RelNotes/1.5.5.6.txt[1.5.5.6], - link:RelNotes/1.5.5.5.txt[1.5.5.5], - link:RelNotes/1.5.5.4.txt[1.5.5.4], - link:RelNotes/1.5.5.3.txt[1.5.5.3], - link:RelNotes/1.5.5.2.txt[1.5.5.2], - link:RelNotes/1.5.5.1.txt[1.5.5.1], - link:RelNotes/1.5.5.txt[1.5.5]. - -* link:v1.5.4.7/git.html[documentation for release 1.5.4.7] - -* release notes for - link:RelNotes/1.5.4.7.txt[1.5.4.7], - link:RelNotes/1.5.4.6.txt[1.5.4.6], - link:RelNotes/1.5.4.5.txt[1.5.4.5], - link:RelNotes/1.5.4.4.txt[1.5.4.4], - link:RelNotes/1.5.4.3.txt[1.5.4.3], - link:RelNotes/1.5.4.2.txt[1.5.4.2], - link:RelNotes/1.5.4.1.txt[1.5.4.1], - link:RelNotes/1.5.4.txt[1.5.4]. - -* link:v1.5.3.8/git.html[documentation for release 1.5.3.8] - -* release notes for - link:RelNotes/1.5.3.8.txt[1.5.3.8], - link:RelNotes/1.5.3.7.txt[1.5.3.7], - link:RelNotes/1.5.3.6.txt[1.5.3.6], - link:RelNotes/1.5.3.5.txt[1.5.3.5], - link:RelNotes/1.5.3.4.txt[1.5.3.4], - link:RelNotes/1.5.3.3.txt[1.5.3.3], - link:RelNotes/1.5.3.2.txt[1.5.3.2], - link:RelNotes/1.5.3.1.txt[1.5.3.1], - link:RelNotes/1.5.3.txt[1.5.3]. - -* link:v1.5.2.5/git.html[documentation for release 1.5.2.5] - -* release notes for - link:RelNotes/1.5.2.5.txt[1.5.2.5], - link:RelNotes/1.5.2.4.txt[1.5.2.4], - link:RelNotes/1.5.2.3.txt[1.5.2.3], - link:RelNotes/1.5.2.2.txt[1.5.2.2], - link:RelNotes/1.5.2.1.txt[1.5.2.1], - link:RelNotes/1.5.2.txt[1.5.2]. - -* link:v1.5.1.6/git.html[documentation for release 1.5.1.6] - -* release notes for - link:RelNotes/1.5.1.6.txt[1.5.1.6], - link:RelNotes/1.5.1.5.txt[1.5.1.5], - link:RelNotes/1.5.1.4.txt[1.5.1.4], - link:RelNotes/1.5.1.3.txt[1.5.1.3], - link:RelNotes/1.5.1.2.txt[1.5.1.2], - link:RelNotes/1.5.1.1.txt[1.5.1.1], - link:RelNotes/1.5.1.txt[1.5.1]. - -* link:v1.5.0.7/git.html[documentation for release 1.5.0.7] - -* release notes for - link:RelNotes/1.5.0.7.txt[1.5.0.7], - link:RelNotes/1.5.0.6.txt[1.5.0.6], - link:RelNotes/1.5.0.5.txt[1.5.0.5], - link:RelNotes/1.5.0.3.txt[1.5.0.3], - link:RelNotes/1.5.0.2.txt[1.5.0.2], - link:RelNotes/1.5.0.1.txt[1.5.0.1], - link:RelNotes/1.5.0.txt[1.5.0]. - -* documentation for release link:v1.4.4.4/git.html[1.4.4.4], - link:v1.3.3/git.html[1.3.3], - link:v1.2.6/git.html[1.2.6], - link:v1.0.13/git.html[1.0.13]. - -============ - -endif::stalenotes[] OPTIONS ------- diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt index 47b286b33e..38040e95b5 100644 --- a/Documentation/pretty-formats.txt +++ b/Documentation/pretty-formats.txt @@ -199,7 +199,7 @@ endif::git-rev-list[] than given and there are spaces on its left, use those spaces - '%><(<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 +- %(trailers): display the trailers of the body as interpreted by linkgit:git-interpret-trailers[1] NOTE: Some placeholders may depend on other options given to the diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt index a02f7324c0..9c44eae55d 100644 --- a/Documentation/rev-list-options.txt +++ b/Documentation/rev-list-options.txt @@ -91,9 +91,14 @@ endif::git-rev-list[] Consider the limiting patterns to be fixed strings (don't interpret pattern as a regular expression). +-P:: --perl-regexp:: - Consider the limiting patterns to be Perl-compatible regular expressions. - Requires libpcre to be compiled in. + Consider the limiting patterns to be Perl-compatible regular + expressions. ++ +Support for these types of regular expressions is an optional +compile-time dependency. If Git wasn't compiled with support for them +providing this option will cause it to die. --remove-empty:: Stop when a given path disappears from the tree. diff --git a/Documentation/technical/api-directory-listing.txt b/Documentation/technical/api-directory-listing.txt index 7f8e78d916..6c77b4920c 100644 --- a/Documentation/technical/api-directory-listing.txt +++ b/Documentation/technical/api-directory-listing.txt @@ -33,6 +33,12 @@ The notable options are: Similar to `DIR_SHOW_IGNORED`, but return ignored files in `ignored[]` in addition to untracked files in `entries[]`. +`DIR_KEEP_UNTRACKED_CONTENTS`::: + + Only has meaning if `DIR_SHOW_IGNORED_TOO` is also set; if this is set, the + untracked contents of untracked directories are also returned in + `entries[]`. + `DIR_COLLECT_IGNORED`::: Special mode for git-add. Return ignored files in `ignored[]` and @@ -24,11 +24,28 @@ all:: # Define NO_OPENSSL environment variable if you do not have OpenSSL. # This also implies BLK_SHA1. # -# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be -# able to use Perl-compatible regular expressions. -# -# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in -# /foo/bar/include and /foo/bar/lib directories. +# Define USE_LIBPCRE if you have and want to use libpcre. Various +# commands such as log and grep offer runtime options to use +# Perl-compatible regular expressions instead of standard or extended +# POSIX regular expressions. +# +# Currently USE_LIBPCRE is a synonym for USE_LIBPCRE1, define +# USE_LIBPCRE2 instead if you'd like to use version 2 of the PCRE +# library. The USE_LIBPCRE flag will likely be changed to mean v2 by +# default in future releases. +# +# When using USE_LIBPCRE1, define NO_LIBPCRE1_JIT if the PCRE v1 +# library is compiled without --enable-jit. We will auto-detect +# whether the version of the PCRE v1 library in use has JIT support at +# all, but we unfortunately can't auto-detect whether JIT support +# hasn't been compiled in in an otherwise JIT-supporting version. If +# you have link-time errors about a missing `pcre_jit_exec` define +# this, or recompile PCRE v1 with --enable-jit. +# +# Define LIBPCREDIR=/foo/bar if your PCRE header and library files are +# in /foo/bar/include and /foo/bar/lib directories. Which version of +# PCRE this points to determined by the USE_LIBPCRE1 and USE_LIBPCRE2 +# variables. # # Define HAVE_ALLOCA_H if you have working alloca(3) defined in that header. # @@ -718,6 +735,7 @@ LIB_OBJS += argv-array.o LIB_OBJS += attr.o LIB_OBJS += base85.o LIB_OBJS += bisect.o +LIB_OBJS += blame.o LIB_OBJS += blob.o LIB_OBJS += branch.o LIB_OBJS += bulk-checkin.o @@ -1086,13 +1104,29 @@ ifdef NO_LIBGEN_H COMPAT_OBJS += compat/basename.o endif -ifdef USE_LIBPCRE - BASIC_CFLAGS += -DUSE_LIBPCRE - ifdef LIBPCREDIR - BASIC_CFLAGS += -I$(LIBPCREDIR)/include - EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib) +USE_LIBPCRE1 ?= $(USE_LIBPCRE) + +ifneq (,$(USE_LIBPCRE1)) + ifdef USE_LIBPCRE2 +$(error Only set USE_LIBPCRE1 (or its alias USE_LIBPCRE) or USE_LIBPCRE2, not both!) endif + + BASIC_CFLAGS += -DUSE_LIBPCRE1 EXTLIBS += -lpcre + +ifdef NO_LIBPCRE1_JIT + BASIC_CFLAGS += -DNO_LIBPCRE1_JIT +endif +endif + +ifdef USE_LIBPCRE2 + BASIC_CFLAGS += -DUSE_LIBPCRE2 + EXTLIBS += -lpcre2-8 +endif + +ifdef LIBPCREDIR + BASIC_CFLAGS += -I$(LIBPCREDIR)/include + EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib) endif ifdef HAVE_ALLOCA_H @@ -1415,7 +1449,14 @@ else DC_SHA1 := YesPlease LIB_OBJS += sha1dc/sha1.o LIB_OBJS += sha1dc/ubc_check.o - BASIC_CFLAGS += -DSHA1_DC + BASIC_CFLAGS += \ + -DSHA1_DC \ + -DSHA1DC_NO_STANDARD_INCLUDES \ + -DSHA1DC_INIT_SAFE_HASH_DEFAULT=0 \ + -DSHA1DC_CUSTOM_INCLUDE_SHA1_C="\"cache.h\"" \ + -DSHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C="\"sha1dc_git.c\"" \ + -DSHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H="\"sha1dc_git.h\"" \ + -DSHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C="\"git-compat-util.h\"" endif endif endif @@ -2239,8 +2280,11 @@ GIT-BUILD-OPTIONS: FORCE @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@+ @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@+ @echo NO_EXPAT=\''$(subst ','\'',$(subst ','\'',$(NO_EXPAT)))'\' >>$@+ - @echo USE_LIBPCRE=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE)))'\' >>$@+ + @echo USE_LIBPCRE1=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE1)))'\' >>$@+ + @echo USE_LIBPCRE2=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE2)))'\' >>$@+ + @echo NO_LIBPCRE1_JIT=\''$(subst ','\'',$(subst ','\'',$(NO_LIBPCRE1_JIT)))'\' >>$@+ @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@+ + @echo NO_PTHREADS=\''$(subst ','\'',$(subst ','\'',$(NO_PTHREADS)))'\' >>$@+ @echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@+ @echo NO_UNIX_SOCKETS=\''$(subst ','\'',$(subst ','\'',$(NO_UNIX_SOCKETS)))'\' >>$@+ @echo PAGER_ENV=\''$(subst ','\'',$(subst ','\'',$(PAGER_ENV)))'\' >>$@+ @@ -2271,6 +2315,9 @@ endif ifdef GIT_PERF_MAKE_OPTS @echo GIT_PERF_MAKE_OPTS=\''$(subst ','\'',$(subst ','\'',$(GIT_PERF_MAKE_OPTS)))'\' >>$@+ endif +ifdef GIT_PERF_MAKE_COMMAND + @echo GIT_PERF_MAKE_COMMAND=\''$(subst ','\'',$(subst ','\'',$(GIT_PERF_MAKE_COMMAND)))'\' >>$@+ +endif ifdef GIT_INTEROP_MAKE_OPTS @echo GIT_INTEROP_MAKE_OPTS=\''$(subst ','\'',$(subst ','\'',$(GIT_INTEROP_MAKE_OPTS)))'\' >>$@+ endif @@ -3741,7 +3741,7 @@ static int check_to_create(struct apply_state *state, return 0; return EXISTS_IN_WORKTREE; - } else if ((errno != ENOENT) && (errno != ENOTDIR)) { + } else if (!is_missing_file_error(errno)) { return error_errno("%s", new_name); } return 0; @@ -720,16 +720,13 @@ void git_attr_set_direction(enum git_attr_direction new_direction, static struct attr_stack *read_attr_from_file(const char *path, int macro_ok) { - FILE *fp = fopen(path, "r"); + FILE *fp = fopen_or_warn(path, "r"); struct attr_stack *res; char buf[2048]; int lineno = 0; - if (!fp) { - if (errno != ENOENT && errno != ENOTDIR) - warn_on_inaccessible(path); + if (!fp) return NULL; - } res = xcalloc(1, sizeof(*res)); while (fgets(buf, sizeof(buf), fp)) { char *bufp = buf; @@ -438,10 +438,7 @@ static void read_bisect_paths(struct argv_array *array) { struct strbuf str = STRBUF_INIT; const char *filename = git_path_bisect_names(); - FILE *fp = fopen(filename, "r"); - - if (!fp) - die_errno(_("Could not open file '%s'"), filename); + FILE *fp = xfopen(filename, "r"); while (strbuf_getline_lf(&str, fp) != EOF) { strbuf_trim(&str); @@ -669,7 +666,7 @@ static int is_expected_rev(const struct object_id *oid) if (stat(filename, &st) || !S_ISREG(st.st_mode)) return 0; - fp = fopen(filename, "r"); + fp = fopen_or_warn(filename, "r"); if (!fp) return 0; @@ -995,8 +992,10 @@ int bisect_next_all(const char *prefix, int no_checkout) steps_msg = xstrfmt(Q_("(roughly %d step)", "(roughly %d steps)", steps), steps); - /* TRANSLATORS: the last %s will be replaced with - "(roughly %d steps)" translation */ + /* + * TRANSLATORS: the last %s will be replaced with "(roughly %d + * steps)" translation. + */ printf(Q_("Bisecting: %d revision left to test after this %s\n", "Bisecting: %d revisions left to test after this %s\n", nr), nr, steps_msg); diff --git a/blame.c b/blame.c new file mode 100644 index 0000000000..194b58e960 --- /dev/null +++ b/blame.c @@ -0,0 +1,1863 @@ +#include "cache.h" +#include "refs.h" +#include "cache-tree.h" +#include "mergesort.h" +#include "diff.h" +#include "diffcore.h" +#include "tag.h" +#include "blame.h" + +void blame_origin_decref(struct blame_origin *o) +{ + if (o && --o->refcnt <= 0) { + struct blame_origin *p, *l = NULL; + if (o->previous) + blame_origin_decref(o->previous); + free(o->file.ptr); + /* Should be present exactly once in commit chain */ + for (p = o->commit->util; p; l = p, p = p->next) { + if (p == o) { + if (l) + l->next = p->next; + else + o->commit->util = p->next; + free(o); + return; + } + } + die("internal error in blame_origin_decref"); + } +} + +/* + * Given a commit and a path in it, create a new origin structure. + * The callers that add blame to the scoreboard should use + * get_origin() to obtain shared, refcounted copy instead of calling + * this function directly. + */ +static struct blame_origin *make_origin(struct commit *commit, const char *path) +{ + struct blame_origin *o; + FLEX_ALLOC_STR(o, path, path); + o->commit = commit; + o->refcnt = 1; + o->next = commit->util; + commit->util = o; + return o; +} + +/* + * Locate an existing origin or create a new one. + * This moves the origin to front position in the commit util list. + */ +static struct blame_origin *get_origin(struct commit *commit, const char *path) +{ + struct blame_origin *o, *l; + + for (o = commit->util, l = NULL; o; l = o, o = o->next) { + if (!strcmp(o->path, path)) { + /* bump to front */ + if (l) { + l->next = o->next; + o->next = commit->util; + commit->util = o; + } + return blame_origin_incref(o); + } + } + return make_origin(commit, path); +} + + + +static void verify_working_tree_path(struct commit *work_tree, const char *path) +{ + struct commit_list *parents; + int pos; + + for (parents = work_tree->parents; parents; parents = parents->next) { + const struct object_id *commit_oid = &parents->item->object.oid; + struct object_id blob_oid; + unsigned mode; + + if (!get_tree_entry(commit_oid->hash, path, blob_oid.hash, &mode) && + sha1_object_info(blob_oid.hash, NULL) == OBJ_BLOB) + return; + } + + pos = cache_name_pos(path, strlen(path)); + if (pos >= 0) + ; /* path is in the index */ + else if (-1 - pos < active_nr && + !strcmp(active_cache[-1 - pos]->name, path)) + ; /* path is in the index, unmerged */ + else + die("no such path '%s' in HEAD", path); +} + +static struct commit_list **append_parent(struct commit_list **tail, const struct object_id *oid) +{ + struct commit *parent; + + parent = lookup_commit_reference(oid); + if (!parent) + die("no such commit %s", oid_to_hex(oid)); + return &commit_list_insert(parent, tail)->next; +} + +static void append_merge_parents(struct commit_list **tail) +{ + int merge_head; + struct strbuf line = STRBUF_INIT; + + merge_head = open(git_path_merge_head(), O_RDONLY); + if (merge_head < 0) { + if (errno == ENOENT) + return; + die("cannot open '%s' for reading", git_path_merge_head()); + } + + while (!strbuf_getwholeline_fd(&line, merge_head, '\n')) { + struct object_id oid; + if (line.len < GIT_SHA1_HEXSZ || get_oid_hex(line.buf, &oid)) + die("unknown line in '%s': %s", git_path_merge_head(), line.buf); + tail = append_parent(tail, &oid); + } + close(merge_head); + strbuf_release(&line); +} + +/* + * This isn't as simple as passing sb->buf and sb->len, because we + * want to transfer ownership of the buffer to the commit (so we + * must use detach). + */ +static void set_commit_buffer_from_strbuf(struct commit *c, struct strbuf *sb) +{ + size_t len; + void *buf = strbuf_detach(sb, &len); + set_commit_buffer(c, buf, len); +} + +/* + * Prepare a dummy commit that represents the work tree (or staged) item. + * Note that annotating work tree item never works in the reverse. + */ +static struct commit *fake_working_tree_commit(struct diff_options *opt, + const char *path, + const char *contents_from) +{ + struct commit *commit; + struct blame_origin *origin; + struct commit_list **parent_tail, *parent; + struct object_id head_oid; + struct strbuf buf = STRBUF_INIT; + const char *ident; + time_t now; + int size, len; + struct cache_entry *ce; + unsigned mode; + struct strbuf msg = STRBUF_INIT; + + read_cache(); + time(&now); + commit = alloc_commit_node(); + commit->object.parsed = 1; + commit->date = now; + parent_tail = &commit->parents; + + if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) + die("no such ref: HEAD"); + + parent_tail = append_parent(parent_tail, &head_oid); + append_merge_parents(parent_tail); + verify_working_tree_path(commit, path); + + origin = make_origin(commit, path); + + ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0); + strbuf_addstr(&msg, "tree 0000000000000000000000000000000000000000\n"); + for (parent = commit->parents; parent; parent = parent->next) + strbuf_addf(&msg, "parent %s\n", + oid_to_hex(&parent->item->object.oid)); + strbuf_addf(&msg, + "author %s\n" + "committer %s\n\n" + "Version of %s from %s\n", + ident, ident, path, + (!contents_from ? path : + (!strcmp(contents_from, "-") ? "standard input" : contents_from))); + set_commit_buffer_from_strbuf(commit, &msg); + + if (!contents_from || strcmp("-", contents_from)) { + struct stat st; + const char *read_from; + char *buf_ptr; + unsigned long buf_len; + + if (contents_from) { + if (stat(contents_from, &st) < 0) + die_errno("Cannot stat '%s'", contents_from); + read_from = contents_from; + } + else { + if (lstat(path, &st) < 0) + die_errno("Cannot lstat '%s'", path); + read_from = path; + } + mode = canon_mode(st.st_mode); + + switch (st.st_mode & S_IFMT) { + case S_IFREG: + if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && + textconv_object(read_from, mode, &null_oid, 0, &buf_ptr, &buf_len)) + strbuf_attach(&buf, buf_ptr, buf_len, buf_len + 1); + else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size) + die_errno("cannot open or read '%s'", read_from); + break; + case S_IFLNK: + if (strbuf_readlink(&buf, read_from, st.st_size) < 0) + die_errno("cannot readlink '%s'", read_from); + break; + default: + die("unsupported file type %s", read_from); + } + } + else { + /* Reading from stdin */ + mode = 0; + if (strbuf_read(&buf, 0, 0) < 0) + die_errno("failed to read from stdin"); + } + convert_to_git(path, buf.buf, buf.len, &buf, 0); + origin->file.ptr = buf.buf; + origin->file.size = buf.len; + pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_oid.hash); + + /* + * Read the current index, replace the path entry with + * origin->blob_sha1 without mucking with its mode or type + * bits; we are not going to write this index out -- we just + * want to run "diff-index --cached". + */ + discard_cache(); + read_cache(); + + len = strlen(path); + if (!mode) { + int pos = cache_name_pos(path, len); + if (0 <= pos) + mode = active_cache[pos]->ce_mode; + else + /* Let's not bother reading from HEAD tree */ + mode = S_IFREG | 0644; + } + size = cache_entry_size(len); + ce = xcalloc(1, size); + oidcpy(&ce->oid, &origin->blob_oid); + memcpy(ce->name, path, len); + ce->ce_flags = create_ce_flags(0); + ce->ce_namelen = len; + ce->ce_mode = create_ce_mode(mode); + add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); + + cache_tree_invalidate_path(&the_index, path); + + return commit; +} + + + +static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b, + xdl_emit_hunk_consume_func_t hunk_func, void *cb_data, int xdl_opts) +{ + xpparam_t xpp = {0}; + xdemitconf_t xecfg = {0}; + xdemitcb_t ecb = {NULL}; + + xpp.flags = xdl_opts; + xecfg.hunk_func = hunk_func; + ecb.priv = cb_data; + return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb); +} + +/* + * Given an origin, prepare mmfile_t structure to be used by the + * diff machinery + */ +static void fill_origin_blob(struct diff_options *opt, + struct blame_origin *o, mmfile_t *file, int *num_read_blob) +{ + if (!o->file.ptr) { + enum object_type type; + unsigned long file_size; + + (*num_read_blob)++; + if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && + textconv_object(o->path, o->mode, &o->blob_oid, 1, &file->ptr, &file_size)) + ; + else + file->ptr = read_sha1_file(o->blob_oid.hash, &type, + &file_size); + file->size = file_size; + + if (!file->ptr) + die("Cannot read blob %s for path %s", + oid_to_hex(&o->blob_oid), + o->path); + o->file = *file; + } + else + *file = o->file; +} + +static void drop_origin_blob(struct blame_origin *o) +{ + if (o->file.ptr) { + free(o->file.ptr); + o->file.ptr = NULL; + } +} + +/* + * Any merge of blames happens on lists of blames that arrived via + * different parents in a single suspect. In this case, we want to + * sort according to the suspect line numbers as opposed to the final + * image line numbers. The function body is somewhat longish because + * it avoids unnecessary writes. + */ + +static struct blame_entry *blame_merge(struct blame_entry *list1, + struct blame_entry *list2) +{ + struct blame_entry *p1 = list1, *p2 = list2, + **tail = &list1; + + if (!p1) + return p2; + if (!p2) + return p1; + + if (p1->s_lno <= p2->s_lno) { + do { + tail = &p1->next; + if ((p1 = *tail) == NULL) { + *tail = p2; + return list1; + } + } while (p1->s_lno <= p2->s_lno); + } + for (;;) { + *tail = p2; + do { + tail = &p2->next; + if ((p2 = *tail) == NULL) { + *tail = p1; + return list1; + } + } while (p1->s_lno > p2->s_lno); + *tail = p1; + do { + tail = &p1->next; + if ((p1 = *tail) == NULL) { + *tail = p2; + return list1; + } + } while (p1->s_lno <= p2->s_lno); + } +} + +static void *get_next_blame(const void *p) +{ + return ((struct blame_entry *)p)->next; +} + +static void set_next_blame(void *p1, void *p2) +{ + ((struct blame_entry *)p1)->next = p2; +} + +/* + * Final image line numbers are all different, so we don't need a + * three-way comparison here. + */ + +static int compare_blame_final(const void *p1, const void *p2) +{ + return ((struct blame_entry *)p1)->lno > ((struct blame_entry *)p2)->lno + ? 1 : -1; +} + +static int compare_blame_suspect(const void *p1, const void *p2) +{ + const struct blame_entry *s1 = p1, *s2 = p2; + /* + * to allow for collating suspects, we sort according to the + * respective pointer value as the primary sorting criterion. + * The actual relation is pretty unimportant as long as it + * establishes a total order. Comparing as integers gives us + * that. + */ + if (s1->suspect != s2->suspect) + return (intptr_t)s1->suspect > (intptr_t)s2->suspect ? 1 : -1; + if (s1->s_lno == s2->s_lno) + return 0; + return s1->s_lno > s2->s_lno ? 1 : -1; +} + +void blame_sort_final(struct blame_scoreboard *sb) +{ + sb->ent = llist_mergesort(sb->ent, get_next_blame, set_next_blame, + compare_blame_final); +} + +static int compare_commits_by_reverse_commit_date(const void *a, + const void *b, + void *c) +{ + return -compare_commits_by_commit_date(a, b, c); +} + +/* + * For debugging -- origin is refcounted, and this asserts that + * we do not underflow. + */ +static void sanity_check_refcnt(struct blame_scoreboard *sb) +{ + int baa = 0; + struct blame_entry *ent; + + for (ent = sb->ent; ent; ent = ent->next) { + /* Nobody should have zero or negative refcnt */ + if (ent->suspect->refcnt <= 0) { + fprintf(stderr, "%s in %s has negative refcnt %d\n", + ent->suspect->path, + oid_to_hex(&ent->suspect->commit->object.oid), + ent->suspect->refcnt); + baa = 1; + } + } + if (baa) + sb->on_sanity_fail(sb, baa); +} + +/* + * If two blame entries that are next to each other came from + * contiguous lines in the same origin (i.e. <commit, path> pair), + * merge them together. + */ +void blame_coalesce(struct blame_scoreboard *sb) +{ + struct blame_entry *ent, *next; + + for (ent = sb->ent; ent && (next = ent->next); ent = next) { + if (ent->suspect == next->suspect && + ent->s_lno + ent->num_lines == next->s_lno) { + ent->num_lines += next->num_lines; + ent->next = next->next; + blame_origin_decref(next->suspect); + free(next); + ent->score = 0; + next = ent; /* again */ + } + } + + if (sb->debug) /* sanity */ + sanity_check_refcnt(sb); +} + +/* + * Merge the given sorted list of blames into a preexisting origin. + * If there were no previous blames to that commit, it is entered into + * the commit priority queue of the score board. + */ + +static void queue_blames(struct blame_scoreboard *sb, struct blame_origin *porigin, + struct blame_entry *sorted) +{ + if (porigin->suspects) + porigin->suspects = blame_merge(porigin->suspects, sorted); + else { + struct blame_origin *o; + for (o = porigin->commit->util; o; o = o->next) { + if (o->suspects) { + porigin->suspects = sorted; + return; + } + } + porigin->suspects = sorted; + prio_queue_put(&sb->commits, porigin->commit); + } +} + +/* + * Fill the blob_sha1 field of an origin if it hasn't, so that later + * call to fill_origin_blob() can use it to locate the data. blob_sha1 + * for an origin is also used to pass the blame for the entire file to + * the parent to detect the case where a child's blob is identical to + * that of its parent's. + * + * This also fills origin->mode for corresponding tree path. + */ +static int fill_blob_sha1_and_mode(struct blame_origin *origin) +{ + if (!is_null_oid(&origin->blob_oid)) + return 0; + if (get_tree_entry(origin->commit->object.oid.hash, + origin->path, + origin->blob_oid.hash, &origin->mode)) + goto error_out; + if (sha1_object_info(origin->blob_oid.hash, NULL) != OBJ_BLOB) + goto error_out; + return 0; + error_out: + oidclr(&origin->blob_oid); + origin->mode = S_IFINVALID; + return -1; +} + +/* + * We have an origin -- check if the same path exists in the + * parent and return an origin structure to represent it. + */ +static struct blame_origin *find_origin(struct commit *parent, + struct blame_origin *origin) +{ + struct blame_origin *porigin; + struct diff_options diff_opts; + const char *paths[2]; + + /* First check any existing origins */ + for (porigin = parent->util; porigin; porigin = porigin->next) + if (!strcmp(porigin->path, origin->path)) { + /* + * The same path between origin and its parent + * without renaming -- the most common case. + */ + return blame_origin_incref (porigin); + } + + /* See if the origin->path is different between parent + * and origin first. Most of the time they are the + * same and diff-tree is fairly efficient about this. + */ + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.detect_rename = 0; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + paths[0] = origin->path; + paths[1] = NULL; + + parse_pathspec(&diff_opts.pathspec, + PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL, + PATHSPEC_LITERAL_PATH, "", paths); + diff_setup_done(&diff_opts); + + if (is_null_oid(&origin->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else + diff_tree_oid(&parent->tree->object.oid, + &origin->commit->tree->object.oid, + "", &diff_opts); + diffcore_std(&diff_opts); + + if (!diff_queued_diff.nr) { + /* The path is the same as parent */ + porigin = get_origin(parent, origin->path); + oidcpy(&porigin->blob_oid, &origin->blob_oid); + porigin->mode = origin->mode; + } else { + /* + * Since origin->path is a pathspec, if the parent + * commit had it as a directory, we will see a whole + * bunch of deletion of files in the directory that we + * do not care about. + */ + int i; + struct diff_filepair *p = NULL; + for (i = 0; i < diff_queued_diff.nr; i++) { + const char *name; + p = diff_queued_diff.queue[i]; + name = p->one->path ? p->one->path : p->two->path; + if (!strcmp(name, origin->path)) + break; + } + if (!p) + die("internal error in blame::find_origin"); + switch (p->status) { + default: + die("internal error in blame::find_origin (%c)", + p->status); + case 'M': + porigin = get_origin(parent, origin->path); + oidcpy(&porigin->blob_oid, &p->one->oid); + porigin->mode = p->one->mode; + break; + case 'A': + case 'T': + /* Did not exist in parent, or type changed */ + break; + } + } + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); + return porigin; +} + +/* + * We have an origin -- find the path that corresponds to it in its + * parent and return an origin structure to represent it. + */ +static struct blame_origin *find_rename(struct commit *parent, + struct blame_origin *origin) +{ + struct blame_origin *porigin = NULL; + struct diff_options diff_opts; + int i; + + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.detect_rename = DIFF_DETECT_RENAME; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_opts.single_follow = origin->path; + diff_setup_done(&diff_opts); + + if (is_null_oid(&origin->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else + diff_tree_oid(&parent->tree->object.oid, + &origin->commit->tree->object.oid, + "", &diff_opts); + diffcore_std(&diff_opts); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + if ((p->status == 'R' || p->status == 'C') && + !strcmp(p->two->path, origin->path)) { + porigin = get_origin(parent, p->one->path); + oidcpy(&porigin->blob_oid, &p->one->oid); + porigin->mode = p->one->mode; + break; + } + } + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); + return porigin; +} + +/* + * Append a new blame entry to a given output queue. + */ +static void add_blame_entry(struct blame_entry ***queue, + const struct blame_entry *src) +{ + struct blame_entry *e = xmalloc(sizeof(*e)); + memcpy(e, src, sizeof(*e)); + blame_origin_incref(e->suspect); + + e->next = **queue; + **queue = e; + *queue = &e->next; +} + +/* + * src typically is on-stack; we want to copy the information in it to + * a malloced blame_entry that gets added to the given queue. The + * origin of dst loses a refcnt. + */ +static void dup_entry(struct blame_entry ***queue, + struct blame_entry *dst, struct blame_entry *src) +{ + blame_origin_incref(src->suspect); + blame_origin_decref(dst->suspect); + memcpy(dst, src, sizeof(*src)); + dst->next = **queue; + **queue = dst; + *queue = &dst->next; +} + +const char *blame_nth_line(struct blame_scoreboard *sb, long lno) +{ + return sb->final_buf + sb->lineno[lno]; +} + +/* + * It is known that lines between tlno to same came from parent, and e + * has an overlap with that range. it also is known that parent's + * line plno corresponds to e's line tlno. + * + * <---- e -----> + * <------> + * <------------> + * <------------> + * <------------------> + * + * Split e into potentially three parts; before this chunk, the chunk + * to be blamed for the parent, and after that portion. + */ +static void split_overlap(struct blame_entry *split, + struct blame_entry *e, + int tlno, int plno, int same, + struct blame_origin *parent) +{ + int chunk_end_lno; + memset(split, 0, sizeof(struct blame_entry [3])); + + if (e->s_lno < tlno) { + /* there is a pre-chunk part not blamed on parent */ + split[0].suspect = blame_origin_incref(e->suspect); + split[0].lno = e->lno; + split[0].s_lno = e->s_lno; + split[0].num_lines = tlno - e->s_lno; + split[1].lno = e->lno + tlno - e->s_lno; + split[1].s_lno = plno; + } + else { + split[1].lno = e->lno; + split[1].s_lno = plno + (e->s_lno - tlno); + } + + if (same < e->s_lno + e->num_lines) { + /* there is a post-chunk part not blamed on parent */ + split[2].suspect = blame_origin_incref(e->suspect); + split[2].lno = e->lno + (same - e->s_lno); + split[2].s_lno = e->s_lno + (same - e->s_lno); + split[2].num_lines = e->s_lno + e->num_lines - same; + chunk_end_lno = split[2].lno; + } + else + chunk_end_lno = e->lno + e->num_lines; + split[1].num_lines = chunk_end_lno - split[1].lno; + + /* + * if it turns out there is nothing to blame the parent for, + * forget about the splitting. !split[1].suspect signals this. + */ + if (split[1].num_lines < 1) + return; + split[1].suspect = blame_origin_incref(parent); +} + +/* + * split_overlap() divided an existing blame e into up to three parts + * in split. Any assigned blame is moved to queue to + * reflect the split. + */ +static void split_blame(struct blame_entry ***blamed, + struct blame_entry ***unblamed, + struct blame_entry *split, + struct blame_entry *e) +{ + if (split[0].suspect && split[2].suspect) { + /* The first part (reuse storage for the existing entry e) */ + dup_entry(unblamed, e, &split[0]); + + /* The last part -- me */ + add_blame_entry(unblamed, &split[2]); + + /* ... and the middle part -- parent */ + add_blame_entry(blamed, &split[1]); + } + else if (!split[0].suspect && !split[2].suspect) + /* + * The parent covers the entire area; reuse storage for + * e and replace it with the parent. + */ + dup_entry(blamed, e, &split[1]); + else if (split[0].suspect) { + /* me and then parent */ + dup_entry(unblamed, e, &split[0]); + add_blame_entry(blamed, &split[1]); + } + else { + /* parent and then me */ + dup_entry(blamed, e, &split[1]); + add_blame_entry(unblamed, &split[2]); + } +} + +/* + * After splitting the blame, the origins used by the + * on-stack blame_entry should lose one refcnt each. + */ +static void decref_split(struct blame_entry *split) +{ + int i; + + for (i = 0; i < 3; i++) + blame_origin_decref(split[i].suspect); +} + +/* + * reverse_blame reverses the list given in head, appending tail. + * That allows us to build lists in reverse order, then reverse them + * afterwards. This can be faster than building the list in proper + * order right away. The reason is that building in proper order + * requires writing a link in the _previous_ element, while building + * in reverse order just requires placing the list head into the + * _current_ element. + */ + +static struct blame_entry *reverse_blame(struct blame_entry *head, + struct blame_entry *tail) +{ + while (head) { + struct blame_entry *next = head->next; + head->next = tail; + tail = head; + head = next; + } + return tail; +} + +/* + * Process one hunk from the patch between the current suspect for + * blame_entry e and its parent. This first blames any unfinished + * entries before the chunk (which is where target and parent start + * differing) on the parent, and then splits blame entries at the + * start and at the end of the difference region. Since use of -M and + * -C options may lead to overlapping/duplicate source line number + * ranges, all we can rely on from sorting/merging is the order of the + * first suspect line number. + */ +static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq, + int tlno, int offset, int same, + struct blame_origin *parent) +{ + struct blame_entry *e = **srcq; + struct blame_entry *samep = NULL, *diffp = NULL; + + while (e && e->s_lno < tlno) { + struct blame_entry *next = e->next; + /* + * current record starts before differing portion. If + * it reaches into it, we need to split it up and + * examine the second part separately. + */ + if (e->s_lno + e->num_lines > tlno) { + /* Move second half to a new record */ + int len = tlno - e->s_lno; + struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); + n->suspect = e->suspect; + n->lno = e->lno + len; + n->s_lno = e->s_lno + len; + n->num_lines = e->num_lines - len; + e->num_lines = len; + e->score = 0; + /* Push new record to diffp */ + n->next = diffp; + diffp = n; + } else + blame_origin_decref(e->suspect); + /* Pass blame for everything before the differing + * chunk to the parent */ + e->suspect = blame_origin_incref(parent); + e->s_lno += offset; + e->next = samep; + samep = e; + e = next; + } + /* + * As we don't know how much of a common stretch after this + * diff will occur, the currently blamed parts are all that we + * can assign to the parent for now. + */ + + if (samep) { + **dstq = reverse_blame(samep, **dstq); + *dstq = &samep->next; + } + /* + * Prepend the split off portions: everything after e starts + * after the blameable portion. + */ + e = reverse_blame(diffp, e); + + /* + * Now retain records on the target while parts are different + * from the parent. + */ + samep = NULL; + diffp = NULL; + while (e && e->s_lno < same) { + struct blame_entry *next = e->next; + + /* + * If current record extends into sameness, need to split. + */ + if (e->s_lno + e->num_lines > same) { + /* + * Move second half to a new record to be + * processed by later chunks + */ + int len = same - e->s_lno; + struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); + n->suspect = blame_origin_incref(e->suspect); + n->lno = e->lno + len; + n->s_lno = e->s_lno + len; + n->num_lines = e->num_lines - len; + e->num_lines = len; + e->score = 0; + /* Push new record to samep */ + n->next = samep; + samep = n; + } + e->next = diffp; + diffp = e; + e = next; + } + **srcq = reverse_blame(diffp, reverse_blame(samep, e)); + /* Move across elements that are in the unblamable portion */ + if (diffp) + *srcq = &diffp->next; +} + +struct blame_chunk_cb_data { + struct blame_origin *parent; + long offset; + struct blame_entry **dstq; + struct blame_entry **srcq; +}; + +/* diff chunks are from parent to target */ +static int blame_chunk_cb(long start_a, long count_a, + long start_b, long count_b, void *data) +{ + struct blame_chunk_cb_data *d = data; + if (start_a - start_b != d->offset) + die("internal error in blame::blame_chunk_cb"); + blame_chunk(&d->dstq, &d->srcq, start_b, start_a - start_b, + start_b + count_b, d->parent); + d->offset = start_a + count_a - (start_b + count_b); + return 0; +} + +/* + * We are looking at the origin 'target' and aiming to pass blame + * for the lines it is suspected to its parent. Run diff to find + * which lines came from parent and pass blame for them. + */ +static void pass_blame_to_parent(struct blame_scoreboard *sb, + struct blame_origin *target, + struct blame_origin *parent) +{ + mmfile_t file_p, file_o; + struct blame_chunk_cb_data d; + struct blame_entry *newdest = NULL; + + if (!target->suspects) + return; /* nothing remains for this target */ + + d.parent = parent; + d.offset = 0; + d.dstq = &newdest; d.srcq = &target->suspects; + + fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob); + fill_origin_blob(&sb->revs->diffopt, target, &file_o, &sb->num_read_blob); + sb->num_get_patch++; + + if (diff_hunks(&file_p, &file_o, blame_chunk_cb, &d, sb->xdl_opts)) + die("unable to generate diff (%s -> %s)", + oid_to_hex(&parent->commit->object.oid), + oid_to_hex(&target->commit->object.oid)); + /* The rest are the same as the parent */ + blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent); + *d.dstq = NULL; + queue_blames(sb, parent, newdest); + + return; +} + +/* + * The lines in blame_entry after splitting blames many times can become + * very small and trivial, and at some point it becomes pointless to + * blame the parents. E.g. "\t\t}\n\t}\n\n" appears everywhere in any + * ordinary C program, and it is not worth to say it was copied from + * totally unrelated file in the parent. + * + * Compute how trivial the lines in the blame_entry are. + */ +unsigned blame_entry_score(struct blame_scoreboard *sb, struct blame_entry *e) +{ + unsigned score; + const char *cp, *ep; + + if (e->score) + return e->score; + + score = 1; + cp = blame_nth_line(sb, e->lno); + ep = blame_nth_line(sb, e->lno + e->num_lines); + while (cp < ep) { + unsigned ch = *((unsigned char *)cp); + if (isalnum(ch)) + score++; + cp++; + } + e->score = score; + return score; +} + +/* + * best_so_far[] and this[] are both a split of an existing blame_entry + * that passes blame to the parent. Maintain best_so_far the best split + * so far, by comparing this and best_so_far and copying this into + * bst_so_far as needed. + */ +static void copy_split_if_better(struct blame_scoreboard *sb, + struct blame_entry *best_so_far, + struct blame_entry *this) +{ + int i; + + if (!this[1].suspect) + return; + if (best_so_far[1].suspect) { + if (blame_entry_score(sb, &this[1]) < blame_entry_score(sb, &best_so_far[1])) + return; + } + + for (i = 0; i < 3; i++) + blame_origin_incref(this[i].suspect); + decref_split(best_so_far); + memcpy(best_so_far, this, sizeof(struct blame_entry [3])); +} + +/* + * We are looking at a part of the final image represented by + * ent (tlno and same are offset by ent->s_lno). + * tlno is where we are looking at in the final image. + * up to (but not including) same match preimage. + * plno is where we are looking at in the preimage. + * + * <-------------- final image ----------------------> + * <------ent------> + * ^tlno ^same + * <---------preimage-----> + * ^plno + * + * All line numbers are 0-based. + */ +static void handle_split(struct blame_scoreboard *sb, + struct blame_entry *ent, + int tlno, int plno, int same, + struct blame_origin *parent, + struct blame_entry *split) +{ + if (ent->num_lines <= tlno) + return; + if (tlno < same) { + struct blame_entry this[3]; + tlno += ent->s_lno; + same += ent->s_lno; + split_overlap(this, ent, tlno, plno, same, parent); + copy_split_if_better(sb, split, this); + decref_split(this); + } +} + +struct handle_split_cb_data { + struct blame_scoreboard *sb; + struct blame_entry *ent; + struct blame_origin *parent; + struct blame_entry *split; + long plno; + long tlno; +}; + +static int handle_split_cb(long start_a, long count_a, + long start_b, long count_b, void *data) +{ + struct handle_split_cb_data *d = data; + handle_split(d->sb, d->ent, d->tlno, d->plno, start_b, d->parent, + d->split); + d->plno = start_a + count_a; + d->tlno = start_b + count_b; + return 0; +} + +/* + * Find the lines from parent that are the same as ent so that + * we can pass blames to it. file_p has the blob contents for + * the parent. + */ +static void find_copy_in_blob(struct blame_scoreboard *sb, + struct blame_entry *ent, + struct blame_origin *parent, + struct blame_entry *split, + mmfile_t *file_p) +{ + const char *cp; + mmfile_t file_o; + struct handle_split_cb_data d; + + memset(&d, 0, sizeof(d)); + d.sb = sb; d.ent = ent; d.parent = parent; d.split = split; + /* + * Prepare mmfile that contains only the lines in ent. + */ + cp = blame_nth_line(sb, ent->lno); + file_o.ptr = (char *) cp; + file_o.size = blame_nth_line(sb, ent->lno + ent->num_lines) - cp; + + /* + * file_o is a part of final image we are annotating. + * file_p partially may match that image. + */ + memset(split, 0, sizeof(struct blame_entry [3])); + if (diff_hunks(file_p, &file_o, handle_split_cb, &d, sb->xdl_opts)) + die("unable to generate diff (%s)", + oid_to_hex(&parent->commit->object.oid)); + /* remainder, if any, all match the preimage */ + handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split); +} + +/* Move all blame entries from list *source that have a score smaller + * than score_min to the front of list *small. + * Returns a pointer to the link pointing to the old head of the small list. + */ + +static struct blame_entry **filter_small(struct blame_scoreboard *sb, + struct blame_entry **small, + struct blame_entry **source, + unsigned score_min) +{ + struct blame_entry *p = *source; + struct blame_entry *oldsmall = *small; + while (p) { + if (blame_entry_score(sb, p) <= score_min) { + *small = p; + small = &p->next; + p = *small; + } else { + *source = p; + source = &p->next; + p = *source; + } + } + *small = oldsmall; + *source = NULL; + return small; +} + +/* + * See if lines currently target is suspected for can be attributed to + * parent. + */ +static void find_move_in_parent(struct blame_scoreboard *sb, + struct blame_entry ***blamed, + struct blame_entry **toosmall, + struct blame_origin *target, + struct blame_origin *parent) +{ + struct blame_entry *e, split[3]; + struct blame_entry *unblamed = target->suspects; + struct blame_entry *leftover = NULL; + mmfile_t file_p; + + if (!unblamed) + return; /* nothing remains for this target */ + + fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob); + if (!file_p.ptr) + return; + + /* At each iteration, unblamed has a NULL-terminated list of + * entries that have not yet been tested for blame. leftover + * contains the reversed list of entries that have been tested + * without being assignable to the parent. + */ + do { + struct blame_entry **unblamedtail = &unblamed; + struct blame_entry *next; + for (e = unblamed; e; e = next) { + next = e->next; + find_copy_in_blob(sb, e, parent, split, &file_p); + if (split[1].suspect && + sb->move_score < blame_entry_score(sb, &split[1])) { + split_blame(blamed, &unblamedtail, split, e); + } else { + e->next = leftover; + leftover = e; + } + decref_split(split); + } + *unblamedtail = NULL; + toosmall = filter_small(sb, toosmall, &unblamed, sb->move_score); + } while (unblamed); + target->suspects = reverse_blame(leftover, NULL); +} + +struct blame_list { + struct blame_entry *ent; + struct blame_entry split[3]; +}; + +/* + * Count the number of entries the target is suspected for, + * and prepare a list of entry and the best split. + */ +static struct blame_list *setup_blame_list(struct blame_entry *unblamed, + int *num_ents_p) +{ + struct blame_entry *e; + int num_ents, i; + struct blame_list *blame_list = NULL; + + for (e = unblamed, num_ents = 0; e; e = e->next) + num_ents++; + if (num_ents) { + blame_list = xcalloc(num_ents, sizeof(struct blame_list)); + for (e = unblamed, i = 0; e; e = e->next) + blame_list[i++].ent = e; + } + *num_ents_p = num_ents; + return blame_list; +} + +/* + * For lines target is suspected for, see if we can find code movement + * across file boundary from the parent commit. porigin is the path + * in the parent we already tried. + */ +static void find_copy_in_parent(struct blame_scoreboard *sb, + struct blame_entry ***blamed, + struct blame_entry **toosmall, + struct blame_origin *target, + struct commit *parent, + struct blame_origin *porigin, + int opt) +{ + struct diff_options diff_opts; + int i, j; + struct blame_list *blame_list; + int num_ents; + struct blame_entry *unblamed = target->suspects; + struct blame_entry *leftover = NULL; + + if (!unblamed) + return; /* nothing remains for this target */ + + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + + diff_setup_done(&diff_opts); + + /* Try "find copies harder" on new path if requested; + * we do not want to use diffcore_rename() actually to + * match things up; find_copies_harder is set only to + * force diff_tree_oid() to feed all filepairs to diff_queue, + * and this code needs to be after diff_setup_done(), which + * usually makes find-copies-harder imply copy detection. + */ + if ((opt & PICKAXE_BLAME_COPY_HARDEST) + || ((opt & PICKAXE_BLAME_COPY_HARDER) + && (!porigin || strcmp(target->path, porigin->path)))) + DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER); + + if (is_null_oid(&target->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else + diff_tree_oid(&parent->tree->object.oid, + &target->commit->tree->object.oid, + "", &diff_opts); + + if (!DIFF_OPT_TST(&diff_opts, FIND_COPIES_HARDER)) + diffcore_std(&diff_opts); + + do { + struct blame_entry **unblamedtail = &unblamed; + blame_list = setup_blame_list(unblamed, &num_ents); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + struct blame_origin *norigin; + mmfile_t file_p; + struct blame_entry this[3]; + + if (!DIFF_FILE_VALID(p->one)) + continue; /* does not exist in parent */ + if (S_ISGITLINK(p->one->mode)) + continue; /* ignore git links */ + if (porigin && !strcmp(p->one->path, porigin->path)) + /* find_move already dealt with this path */ + continue; + + norigin = get_origin(parent, p->one->path); + oidcpy(&norigin->blob_oid, &p->one->oid); + norigin->mode = p->one->mode; + fill_origin_blob(&sb->revs->diffopt, norigin, &file_p, &sb->num_read_blob); + if (!file_p.ptr) + continue; + + for (j = 0; j < num_ents; j++) { + find_copy_in_blob(sb, blame_list[j].ent, + norigin, this, &file_p); + copy_split_if_better(sb, blame_list[j].split, + this); + decref_split(this); + } + blame_origin_decref(norigin); + } + + for (j = 0; j < num_ents; j++) { + struct blame_entry *split = blame_list[j].split; + if (split[1].suspect && + sb->copy_score < blame_entry_score(sb, &split[1])) { + split_blame(blamed, &unblamedtail, split, + blame_list[j].ent); + } else { + blame_list[j].ent->next = leftover; + leftover = blame_list[j].ent; + } + decref_split(split); + } + free(blame_list); + *unblamedtail = NULL; + toosmall = filter_small(sb, toosmall, &unblamed, sb->copy_score); + } while (unblamed); + target->suspects = reverse_blame(leftover, NULL); + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); +} + +/* + * The blobs of origin and porigin exactly match, so everything + * origin is suspected for can be blamed on the parent. + */ +static void pass_whole_blame(struct blame_scoreboard *sb, + struct blame_origin *origin, struct blame_origin *porigin) +{ + struct blame_entry *e, *suspects; + + if (!porigin->file.ptr && origin->file.ptr) { + /* Steal its file */ + porigin->file = origin->file; + origin->file.ptr = NULL; + } + suspects = origin->suspects; + origin->suspects = NULL; + for (e = suspects; e; e = e->next) { + blame_origin_incref(porigin); + blame_origin_decref(e->suspect); + e->suspect = porigin; + } + queue_blames(sb, porigin, suspects); +} + +/* + * We pass blame from the current commit to its parents. We keep saying + * "parent" (and "porigin"), but what we mean is to find scapegoat to + * exonerate ourselves. + */ +static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit, + int reverse) +{ + if (!reverse) { + if (revs->first_parent_only && + commit->parents && + commit->parents->next) { + free_commit_list(commit->parents->next); + commit->parents->next = NULL; + } + return commit->parents; + } + return lookup_decoration(&revs->children, &commit->object); +} + +static int num_scapegoats(struct rev_info *revs, struct commit *commit, int reverse) +{ + struct commit_list *l = first_scapegoat(revs, commit, reverse); + return commit_list_count(l); +} + +/* Distribute collected unsorted blames to the respected sorted lists + * in the various origins. + */ +static void distribute_blame(struct blame_scoreboard *sb, struct blame_entry *blamed) +{ + blamed = llist_mergesort(blamed, get_next_blame, set_next_blame, + compare_blame_suspect); + while (blamed) + { + struct blame_origin *porigin = blamed->suspect; + struct blame_entry *suspects = NULL; + do { + struct blame_entry *next = blamed->next; + blamed->next = suspects; + suspects = blamed; + blamed = next; + } while (blamed && blamed->suspect == porigin); + suspects = reverse_blame(suspects, NULL); + queue_blames(sb, porigin, suspects); + } +} + +#define MAXSG 16 + +static void pass_blame(struct blame_scoreboard *sb, struct blame_origin *origin, int opt) +{ + struct rev_info *revs = sb->revs; + int i, pass, num_sg; + struct commit *commit = origin->commit; + struct commit_list *sg; + struct blame_origin *sg_buf[MAXSG]; + struct blame_origin *porigin, **sg_origin = sg_buf; + struct blame_entry *toosmall = NULL; + struct blame_entry *blames, **blametail = &blames; + + num_sg = num_scapegoats(revs, commit, sb->reverse); + if (!num_sg) + goto finish; + else if (num_sg < ARRAY_SIZE(sg_buf)) + memset(sg_buf, 0, sizeof(sg_buf)); + else + sg_origin = xcalloc(num_sg, sizeof(*sg_origin)); + + /* + * The first pass looks for unrenamed path to optimize for + * common cases, then we look for renames in the second pass. + */ + for (pass = 0; pass < 2 - sb->no_whole_file_rename; pass++) { + struct blame_origin *(*find)(struct commit *, struct blame_origin *); + find = pass ? find_rename : find_origin; + + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct commit *p = sg->item; + int j, same; + + if (sg_origin[i]) + continue; + if (parse_commit(p)) + continue; + porigin = find(p, origin); + if (!porigin) + continue; + if (!oidcmp(&porigin->blob_oid, &origin->blob_oid)) { + pass_whole_blame(sb, origin, porigin); + blame_origin_decref(porigin); + goto finish; + } + for (j = same = 0; j < i; j++) + if (sg_origin[j] && + !oidcmp(&sg_origin[j]->blob_oid, &porigin->blob_oid)) { + same = 1; + break; + } + if (!same) + sg_origin[i] = porigin; + else + blame_origin_decref(porigin); + } + } + + sb->num_commits++; + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + if (!porigin) + continue; + if (!origin->previous) { + blame_origin_incref(porigin); + origin->previous = porigin; + } + pass_blame_to_parent(sb, origin, porigin); + if (!origin->suspects) + goto finish; + } + + /* + * Optionally find moves in parents' files. + */ + if (opt & PICKAXE_BLAME_MOVE) { + filter_small(sb, &toosmall, &origin->suspects, sb->move_score); + if (origin->suspects) { + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + if (!porigin) + continue; + find_move_in_parent(sb, &blametail, &toosmall, origin, porigin); + if (!origin->suspects) + break; + } + } + } + + /* + * Optionally find copies from parents' files. + */ + if (opt & PICKAXE_BLAME_COPY) { + if (sb->copy_score > sb->move_score) + filter_small(sb, &toosmall, &origin->suspects, sb->copy_score); + else if (sb->copy_score < sb->move_score) { + origin->suspects = blame_merge(origin->suspects, toosmall); + toosmall = NULL; + filter_small(sb, &toosmall, &origin->suspects, sb->copy_score); + } + if (!origin->suspects) + goto finish; + + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + find_copy_in_parent(sb, &blametail, &toosmall, + origin, sg->item, porigin, opt); + if (!origin->suspects) + goto finish; + } + } + +finish: + *blametail = NULL; + distribute_blame(sb, blames); + /* + * prepend toosmall to origin->suspects + * + * There is no point in sorting: this ends up on a big + * unsorted list in the caller anyway. + */ + if (toosmall) { + struct blame_entry **tail = &toosmall; + while (*tail) + tail = &(*tail)->next; + *tail = origin->suspects; + origin->suspects = toosmall; + } + for (i = 0; i < num_sg; i++) { + if (sg_origin[i]) { + drop_origin_blob(sg_origin[i]); + blame_origin_decref(sg_origin[i]); + } + } + drop_origin_blob(origin); + if (sg_buf != sg_origin) + free(sg_origin); +} + +/* + * The main loop -- while we have blobs with lines whose true origin + * is still unknown, pick one blob, and allow its lines to pass blames + * to its parents. */ +void assign_blame(struct blame_scoreboard *sb, int opt) +{ + struct rev_info *revs = sb->revs; + struct commit *commit = prio_queue_get(&sb->commits); + + while (commit) { + struct blame_entry *ent; + struct blame_origin *suspect = commit->util; + + /* find one suspect to break down */ + while (suspect && !suspect->suspects) + suspect = suspect->next; + + if (!suspect) { + commit = prio_queue_get(&sb->commits); + continue; + } + + assert(commit == suspect->commit); + + /* + * We will use this suspect later in the loop, + * so hold onto it in the meantime. + */ + blame_origin_incref(suspect); + parse_commit(commit); + if (sb->reverse || + (!(commit->object.flags & UNINTERESTING) && + !(revs->max_age != -1 && commit->date < revs->max_age))) + pass_blame(sb, suspect, opt); + else { + commit->object.flags |= UNINTERESTING; + if (commit->object.parsed) + mark_parents_uninteresting(commit); + } + /* treat root commit as boundary */ + if (!commit->parents && !sb->show_root) + commit->object.flags |= UNINTERESTING; + + /* Take responsibility for the remaining entries */ + ent = suspect->suspects; + if (ent) { + suspect->guilty = 1; + for (;;) { + struct blame_entry *next = ent->next; + if (sb->found_guilty_entry) + sb->found_guilty_entry(ent, sb->found_guilty_entry_data); + if (next) { + ent = next; + continue; + } + ent->next = sb->ent; + sb->ent = suspect->suspects; + suspect->suspects = NULL; + break; + } + } + blame_origin_decref(suspect); + + if (sb->debug) /* sanity */ + sanity_check_refcnt(sb); + } +} + +static const char *get_next_line(const char *start, const char *end) +{ + const char *nl = memchr(start, '\n', end - start); + return nl ? nl + 1 : end; +} + +/* + * To allow quick access to the contents of nth line in the + * final image, prepare an index in the scoreboard. + */ +static int prepare_lines(struct blame_scoreboard *sb) +{ + const char *buf = sb->final_buf; + unsigned long len = sb->final_buf_size; + const char *end = buf + len; + const char *p; + int *lineno; + int num = 0; + + for (p = buf; p < end; p = get_next_line(p, end)) + num++; + + ALLOC_ARRAY(sb->lineno, num + 1); + lineno = sb->lineno; + + for (p = buf; p < end; p = get_next_line(p, end)) + *lineno++ = p - buf; + + *lineno = len; + + sb->num_lines = num; + return sb->num_lines; +} + +static struct commit *find_single_final(struct rev_info *revs, + const char **name_p) +{ + int i; + struct commit *found = NULL; + const char *name = NULL; + + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (obj->flags & UNINTERESTING) + continue; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (found) + die("More than one commit to dig from %s and %s?", + revs->pending.objects[i].name, name); + found = (struct commit *)obj; + name = revs->pending.objects[i].name; + } + if (name_p) + *name_p = name; + return found; +} + +static struct commit *dwim_reverse_initial(struct rev_info *revs, + const char **name_p) +{ + /* + * DWIM "git blame --reverse ONE -- PATH" as + * "git blame --reverse ONE..HEAD -- PATH" but only do so + * when it makes sense. + */ + struct object *obj; + struct commit *head_commit; + struct object_id head_oid; + + if (revs->pending.nr != 1) + return NULL; + + /* Is that sole rev a committish? */ + obj = revs->pending.objects[0].item; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + return NULL; + + /* Do we have HEAD? */ + if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) + return NULL; + head_commit = lookup_commit_reference_gently(&head_oid, 1); + if (!head_commit) + return NULL; + + /* Turn "ONE" into "ONE..HEAD" then */ + obj->flags |= UNINTERESTING; + add_pending_object(revs, &head_commit->object, "HEAD"); + + if (name_p) + *name_p = revs->pending.objects[0].name; + return (struct commit *)obj; +} + +static struct commit *find_single_initial(struct rev_info *revs, + const char **name_p) +{ + int i; + struct commit *found = NULL; + const char *name = NULL; + + /* + * There must be one and only one negative commit, and it must be + * the boundary. + */ + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (!(obj->flags & UNINTERESTING)) + continue; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (found) + die("More than one commit to dig up from, %s and %s?", + revs->pending.objects[i].name, name); + found = (struct commit *) obj; + name = revs->pending.objects[i].name; + } + + if (!name) + found = dwim_reverse_initial(revs, &name); + if (!name) + die("No commit to dig up from?"); + + if (name_p) + *name_p = name; + return found; +} + +void init_scoreboard(struct blame_scoreboard *sb) +{ + memset(sb, 0, sizeof(struct blame_scoreboard)); + sb->move_score = BLAME_DEFAULT_MOVE_SCORE; + sb->copy_score = BLAME_DEFAULT_COPY_SCORE; +} + +void setup_scoreboard(struct blame_scoreboard *sb, const char *path, struct blame_origin **orig) +{ + const char *final_commit_name = NULL; + struct blame_origin *o; + struct commit *final_commit = NULL; + enum object_type type; + + if (sb->reverse && sb->contents_from) + die(_("--contents and --reverse do not blend well.")); + + if (!sb->reverse) { + sb->final = find_single_final(sb->revs, &final_commit_name); + sb->commits.compare = compare_commits_by_commit_date; + } else { + sb->final = find_single_initial(sb->revs, &final_commit_name); + sb->commits.compare = compare_commits_by_reverse_commit_date; + } + + if (sb->final && sb->contents_from) + die(_("cannot use --contents with final commit object name")); + + if (sb->reverse && sb->revs->first_parent_only) + sb->revs->children.name = NULL; + + if (!sb->final) { + /* + * "--not A B -- path" without anything positive; + * do not default to HEAD, but use the working tree + * or "--contents". + */ + setup_work_tree(); + sb->final = fake_working_tree_commit(&sb->revs->diffopt, + path, sb->contents_from); + add_pending_object(sb->revs, &(sb->final->object), ":"); + } + + if (sb->reverse && sb->revs->first_parent_only) { + final_commit = find_single_final(sb->revs, NULL); + if (!final_commit) + die(_("--reverse and --first-parent together require specified latest commit")); + } + + /* + * If we have bottom, this will mark the ancestors of the + * bottom commits we would reach while traversing as + * uninteresting. + */ + if (prepare_revision_walk(sb->revs)) + die(_("revision walk setup failed")); + + if (sb->reverse && sb->revs->first_parent_only) { + struct commit *c = final_commit; + + sb->revs->children.name = "children"; + while (c->parents && + oidcmp(&c->object.oid, &sb->final->object.oid)) { + struct commit_list *l = xcalloc(1, sizeof(*l)); + + l->item = c; + if (add_decoration(&sb->revs->children, + &c->parents->item->object, l)) + die("BUG: not unique item in first-parent chain"); + c = c->parents->item; + } + + if (oidcmp(&c->object.oid, &sb->final->object.oid)) + die(_("--reverse --first-parent together require range along first-parent chain")); + } + + if (is_null_oid(&sb->final->object.oid)) { + o = sb->final->util; + sb->final_buf = xmemdupz(o->file.ptr, o->file.size); + sb->final_buf_size = o->file.size; + } + else { + o = get_origin(sb->final, path); + if (fill_blob_sha1_and_mode(o)) + die(_("no such path %s in %s"), path, final_commit_name); + + if (DIFF_OPT_TST(&sb->revs->diffopt, ALLOW_TEXTCONV) && + textconv_object(path, o->mode, &o->blob_oid, 1, (char **) &sb->final_buf, + &sb->final_buf_size)) + ; + else + sb->final_buf = read_sha1_file(o->blob_oid.hash, &type, + &sb->final_buf_size); + + if (!sb->final_buf) + die(_("cannot read blob %s for path %s"), + oid_to_hex(&o->blob_oid), + path); + } + sb->num_read_blob++; + prepare_lines(sb); + + if (orig) + *orig = o; +} + + + +struct blame_entry *blame_entry_prepend(struct blame_entry *head, + long start, long end, + struct blame_origin *o) +{ + struct blame_entry *new_head = xcalloc(1, sizeof(struct blame_entry)); + new_head->lno = start; + new_head->num_lines = end - start; + new_head->suspect = o; + new_head->s_lno = start; + new_head->next = head; + blame_origin_incref(o); + return new_head; +} diff --git a/blame.h b/blame.h new file mode 100644 index 0000000000..a6c915c277 --- /dev/null +++ b/blame.h @@ -0,0 +1,175 @@ +#ifndef BLAME_H +#define BLAME_H + +#include "cache.h" +#include "commit.h" +#include "xdiff-interface.h" +#include "revision.h" +#include "prio-queue.h" +#include "diff.h" + +#define PICKAXE_BLAME_MOVE 01 +#define PICKAXE_BLAME_COPY 02 +#define PICKAXE_BLAME_COPY_HARDER 04 +#define PICKAXE_BLAME_COPY_HARDEST 010 + +#define BLAME_DEFAULT_MOVE_SCORE 20 +#define BLAME_DEFAULT_COPY_SCORE 40 + +/* + * One blob in a commit that is being suspected + */ +struct blame_origin { + int refcnt; + /* Record preceding blame record for this blob */ + struct blame_origin *previous; + /* origins are put in a list linked via `next' hanging off the + * corresponding commit's util field in order to make finding + * them fast. The presence in this chain does not count + * towards the origin's reference count. It is tempting to + * let it count as long as the commit is pending examination, + * but even under circumstances where the commit will be + * present multiple times in the priority queue of unexamined + * commits, processing the first instance will not leave any + * work requiring the origin data for the second instance. An + * interspersed commit changing that would have to be + * preexisting with a different ancestry and with the same + * commit date in order to wedge itself between two instances + * of the same commit in the priority queue _and_ produce + * blame entries relevant for it. While we don't want to let + * us get tripped up by this case, it certainly does not seem + * worth optimizing for. + */ + struct blame_origin *next; + struct commit *commit; + /* `suspects' contains blame entries that may be attributed to + * this origin's commit or to parent commits. When a commit + * is being processed, all suspects will be moved, either by + * assigning them to an origin in a different commit, or by + * shipping them to the scoreboard's ent list because they + * cannot be attributed to a different commit. + */ + struct blame_entry *suspects; + mmfile_t file; + struct object_id blob_oid; + unsigned mode; + /* guilty gets set when shipping any suspects to the final + * blame list instead of other commits + */ + char guilty; + char path[FLEX_ARRAY]; +}; + +/* + * Each group of lines is described by a blame_entry; it can be split + * as we pass blame to the parents. They are arranged in linked lists + * kept as `suspects' of some unprocessed origin, or entered (when the + * blame origin has been finalized) into the scoreboard structure. + * While the scoreboard structure is only sorted at the end of + * processing (according to final image line number), the lists + * attached to an origin are sorted by the target line number. + */ +struct blame_entry { + struct blame_entry *next; + + /* the first line of this group in the final image; + * internally all line numbers are 0 based. + */ + int lno; + + /* how many lines this group has */ + int num_lines; + + /* the commit that introduced this group into the final image */ + struct blame_origin *suspect; + + /* the line number of the first line of this group in the + * suspect's file; internally all line numbers are 0 based. + */ + int s_lno; + + /* how significant this entry is -- cached to avoid + * scanning the lines over and over. + */ + unsigned score; +}; + +/* + * The current state of the blame assignment. + */ +struct blame_scoreboard { + /* the final commit (i.e. where we started digging from) */ + struct commit *final; + /* Priority queue for commits with unassigned blame records */ + struct prio_queue commits; + struct rev_info *revs; + const char *path; + + /* + * The contents in the final image. + * Used by many functions to obtain contents of the nth line, + * indexed with scoreboard.lineno[blame_entry.lno]. + */ + const char *final_buf; + unsigned long final_buf_size; + + /* linked list of blames */ + struct blame_entry *ent; + + /* look-up a line in the final buffer */ + int num_lines; + int *lineno; + + /* stats */ + int num_read_blob; + int num_get_patch; + int num_commits; + + /* + * blame for a blame_entry with score lower than these thresholds + * is not passed to the parent using move/copy logic. + */ + unsigned move_score; + unsigned copy_score; + + /* use this file's contents as the final image */ + const char *contents_from; + + /* flags */ + int reverse; + int show_root; + int xdl_opts; + int no_whole_file_rename; + int debug; + + /* callbacks */ + void(*on_sanity_fail)(struct blame_scoreboard *, int); + void(*found_guilty_entry)(struct blame_entry *, void *); + + void *found_guilty_entry_data; +}; + +/* + * Origin is refcounted and usually we keep the blob contents to be + * reused. + */ +static inline struct blame_origin *blame_origin_incref(struct blame_origin *o) +{ + if (o) + o->refcnt++; + return o; +} +extern void blame_origin_decref(struct blame_origin *o); + +extern void blame_coalesce(struct blame_scoreboard *sb); +extern void blame_sort_final(struct blame_scoreboard *sb); +extern unsigned blame_entry_score(struct blame_scoreboard *sb, struct blame_entry *e); +extern void assign_blame(struct blame_scoreboard *sb, int opt); +extern const char *blame_nth_line(struct blame_scoreboard *sb, long lno); + +extern void init_scoreboard(struct blame_scoreboard *sb); +extern void setup_scoreboard(struct blame_scoreboard *sb, const char *path, struct blame_origin **orig); + +extern struct blame_entry *blame_entry_prepend(struct blame_entry *head, long start, long end, struct blame_origin *o); + +#endif /* BLAME_H */ @@ -25,8 +25,6 @@ struct fmt_merge_msg_opts { extern int fmt_merge_msg(struct strbuf *in, struct strbuf *out, struct fmt_merge_msg_opts *); -extern int textconv_object(const char *path, unsigned mode, const struct object_id *oid, int oid_valid, char **buf, unsigned long *buf_size); - extern int is_builtin(const char *s); extern int cmd_add(int argc, const char **argv, const char *prefix); diff --git a/builtin/am.c b/builtin/am.c index d9fdddac4a..3985f9a89f 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -1275,12 +1275,8 @@ static int parse_mail(struct am_state *state, const char *mail) die("BUG: invalid value for state->scissors"); } - mi.input = fopen(mail, "r"); - if (!mi.input) - die("could not open input"); - mi.output = fopen(am_path(state, "info"), "w"); - if (!mi.output) - die("could not open output 'info'"); + mi.input = xfopen(mail, "r"); + mi.output = xfopen(am_path(state, "info"), "w"); if (mailinfo(&mi, am_path(state, "msg"), am_path(state, "patch"))) die("could not parse patch"); @@ -2311,6 +2307,9 @@ int cmd_am(int argc, const char **argv, const char *prefix) OPT_END() }; + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(usage, options); + git_config(git_am_config, NULL); am_state_init(&state); diff --git a/builtin/blame.c b/builtin/blame.c index 7645aa991d..749ad7f05b 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -6,21 +6,13 @@ */ #include "cache.h" -#include "refs.h" #include "builtin.h" -#include "blob.h" #include "commit.h" -#include "tag.h" -#include "tree-walk.h" #include "diff.h" -#include "diffcore.h" #include "revision.h" #include "quote.h" -#include "xdiff-interface.h" -#include "cache-tree.h" #include "string-list.h" #include "mailmap.h" -#include "mergesort.h" #include "parse-options.h" #include "prio-queue.h" #include "utf8.h" @@ -29,6 +21,7 @@ #include "line-log.h" #include "dir.h" #include "progress.h" +#include "blame.h" static char blame_usage[] = N_("git blame [<options>] [<rev-opts>] [<rev>] [--] <file>"); @@ -62,1497 +55,21 @@ static struct string_list mailmap = STRING_LIST_INIT_NODUP; #define DEBUG 0 #endif -/* stats */ -static int num_read_blob; -static int num_get_patch; -static int num_commits; - -#define PICKAXE_BLAME_MOVE 01 -#define PICKAXE_BLAME_COPY 02 -#define PICKAXE_BLAME_COPY_HARDER 04 -#define PICKAXE_BLAME_COPY_HARDEST 010 - -/* - * blame for a blame_entry with score lower than these thresholds - * is not passed to the parent using move/copy logic. - */ static unsigned blame_move_score; static unsigned blame_copy_score; -#define BLAME_DEFAULT_MOVE_SCORE 20 -#define BLAME_DEFAULT_COPY_SCORE 40 /* Remember to update object flag allocation in object.h */ #define METAINFO_SHOWN (1u<<12) #define MORE_THAN_ONE_PATH (1u<<13) -/* - * One blob in a commit that is being suspected - */ -struct origin { - int refcnt; - /* Record preceding blame record for this blob */ - struct origin *previous; - /* origins are put in a list linked via `next' hanging off the - * corresponding commit's util field in order to make finding - * them fast. The presence in this chain does not count - * towards the origin's reference count. It is tempting to - * let it count as long as the commit is pending examination, - * but even under circumstances where the commit will be - * present multiple times in the priority queue of unexamined - * commits, processing the first instance will not leave any - * work requiring the origin data for the second instance. An - * interspersed commit changing that would have to be - * preexisting with a different ancestry and with the same - * commit date in order to wedge itself between two instances - * of the same commit in the priority queue _and_ produce - * blame entries relevant for it. While we don't want to let - * us get tripped up by this case, it certainly does not seem - * worth optimizing for. - */ - struct origin *next; - struct commit *commit; - /* `suspects' contains blame entries that may be attributed to - * this origin's commit or to parent commits. When a commit - * is being processed, all suspects will be moved, either by - * assigning them to an origin in a different commit, or by - * shipping them to the scoreboard's ent list because they - * cannot be attributed to a different commit. - */ - struct blame_entry *suspects; - mmfile_t file; - struct object_id blob_oid; - unsigned mode; - /* guilty gets set when shipping any suspects to the final - * blame list instead of other commits - */ - char guilty; - char path[FLEX_ARRAY]; -}; - struct progress_info { struct progress *progress; int blamed_lines; }; -static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b, - xdl_emit_hunk_consume_func_t hunk_func, void *cb_data) -{ - xpparam_t xpp = {0}; - xdemitconf_t xecfg = {0}; - xdemitcb_t ecb = {NULL}; - - xpp.flags = xdl_opts; - xecfg.hunk_func = hunk_func; - ecb.priv = cb_data; - return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb); -} - -/* - * Prepare diff_filespec and convert it using diff textconv API - * if the textconv driver exists. - * Return 1 if the conversion succeeds, 0 otherwise. - */ -int textconv_object(const char *path, - unsigned mode, - const struct object_id *oid, - int oid_valid, - char **buf, - unsigned long *buf_size) -{ - struct diff_filespec *df; - struct userdiff_driver *textconv; - - df = alloc_filespec(path); - fill_filespec(df, oid, oid_valid, mode); - textconv = get_textconv(df); - if (!textconv) { - free_filespec(df); - return 0; - } - - *buf_size = fill_textconv(textconv, df, buf); - free_filespec(df); - return 1; -} - -/* - * Given an origin, prepare mmfile_t structure to be used by the - * diff machinery - */ -static void fill_origin_blob(struct diff_options *opt, - struct origin *o, mmfile_t *file) -{ - if (!o->file.ptr) { - enum object_type type; - unsigned long file_size; - - num_read_blob++; - if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && - textconv_object(o->path, o->mode, &o->blob_oid, 1, &file->ptr, &file_size)) - ; - else - file->ptr = read_sha1_file(o->blob_oid.hash, &type, - &file_size); - file->size = file_size; - - if (!file->ptr) - die("Cannot read blob %s for path %s", - oid_to_hex(&o->blob_oid), - o->path); - o->file = *file; - } - else - *file = o->file; -} - -/* - * Origin is refcounted and usually we keep the blob contents to be - * reused. - */ -static inline struct origin *origin_incref(struct origin *o) -{ - if (o) - o->refcnt++; - return o; -} - -static void origin_decref(struct origin *o) -{ - if (o && --o->refcnt <= 0) { - struct origin *p, *l = NULL; - if (o->previous) - origin_decref(o->previous); - free(o->file.ptr); - /* Should be present exactly once in commit chain */ - for (p = o->commit->util; p; l = p, p = p->next) { - if (p == o) { - if (l) - l->next = p->next; - else - o->commit->util = p->next; - free(o); - return; - } - } - die("internal error in blame::origin_decref"); - } -} - -static void drop_origin_blob(struct origin *o) -{ - if (o->file.ptr) { - free(o->file.ptr); - o->file.ptr = NULL; - } -} - -/* - * Each group of lines is described by a blame_entry; it can be split - * as we pass blame to the parents. They are arranged in linked lists - * kept as `suspects' of some unprocessed origin, or entered (when the - * blame origin has been finalized) into the scoreboard structure. - * While the scoreboard structure is only sorted at the end of - * processing (according to final image line number), the lists - * attached to an origin are sorted by the target line number. - */ -struct blame_entry { - struct blame_entry *next; - - /* the first line of this group in the final image; - * internally all line numbers are 0 based. - */ - int lno; - - /* how many lines this group has */ - int num_lines; - - /* the commit that introduced this group into the final image */ - struct origin *suspect; - - /* the line number of the first line of this group in the - * suspect's file; internally all line numbers are 0 based. - */ - int s_lno; - - /* how significant this entry is -- cached to avoid - * scanning the lines over and over. - */ - unsigned score; -}; - -/* - * Any merge of blames happens on lists of blames that arrived via - * different parents in a single suspect. In this case, we want to - * sort according to the suspect line numbers as opposed to the final - * image line numbers. The function body is somewhat longish because - * it avoids unnecessary writes. - */ - -static struct blame_entry *blame_merge(struct blame_entry *list1, - struct blame_entry *list2) -{ - struct blame_entry *p1 = list1, *p2 = list2, - **tail = &list1; - - if (!p1) - return p2; - if (!p2) - return p1; - - if (p1->s_lno <= p2->s_lno) { - do { - tail = &p1->next; - if ((p1 = *tail) == NULL) { - *tail = p2; - return list1; - } - } while (p1->s_lno <= p2->s_lno); - } - for (;;) { - *tail = p2; - do { - tail = &p2->next; - if ((p2 = *tail) == NULL) { - *tail = p1; - return list1; - } - } while (p1->s_lno > p2->s_lno); - *tail = p1; - do { - tail = &p1->next; - if ((p1 = *tail) == NULL) { - *tail = p2; - return list1; - } - } while (p1->s_lno <= p2->s_lno); - } -} - -static void *get_next_blame(const void *p) -{ - return ((struct blame_entry *)p)->next; -} - -static void set_next_blame(void *p1, void *p2) -{ - ((struct blame_entry *)p1)->next = p2; -} - -/* - * Final image line numbers are all different, so we don't need a - * three-way comparison here. - */ - -static int compare_blame_final(const void *p1, const void *p2) -{ - return ((struct blame_entry *)p1)->lno > ((struct blame_entry *)p2)->lno - ? 1 : -1; -} - -static int compare_blame_suspect(const void *p1, const void *p2) -{ - const struct blame_entry *s1 = p1, *s2 = p2; - /* - * to allow for collating suspects, we sort according to the - * respective pointer value as the primary sorting criterion. - * The actual relation is pretty unimportant as long as it - * establishes a total order. Comparing as integers gives us - * that. - */ - if (s1->suspect != s2->suspect) - return (intptr_t)s1->suspect > (intptr_t)s2->suspect ? 1 : -1; - if (s1->s_lno == s2->s_lno) - return 0; - return s1->s_lno > s2->s_lno ? 1 : -1; -} - -static struct blame_entry *blame_sort(struct blame_entry *head, - int (*compare_fn)(const void *, const void *)) -{ - return llist_mergesort (head, get_next_blame, set_next_blame, compare_fn); -} - -static int compare_commits_by_reverse_commit_date(const void *a, - const void *b, - void *c) -{ - return -compare_commits_by_commit_date(a, b, c); -} - -/* - * The current state of the blame assignment. - */ -struct scoreboard { - /* the final commit (i.e. where we started digging from) */ - struct commit *final; - /* Priority queue for commits with unassigned blame records */ - struct prio_queue commits; - struct rev_info *revs; - const char *path; - - /* - * The contents in the final image. - * Used by many functions to obtain contents of the nth line, - * indexed with scoreboard.lineno[blame_entry.lno]. - */ - const char *final_buf; - unsigned long final_buf_size; - - /* linked list of blames */ - struct blame_entry *ent; - - /* look-up a line in the final buffer */ - int num_lines; - int *lineno; -}; - -static void sanity_check_refcnt(struct scoreboard *); - -/* - * If two blame entries that are next to each other came from - * contiguous lines in the same origin (i.e. <commit, path> pair), - * merge them together. - */ -static void coalesce(struct scoreboard *sb) -{ - struct blame_entry *ent, *next; - - for (ent = sb->ent; ent && (next = ent->next); ent = next) { - if (ent->suspect == next->suspect && - ent->s_lno + ent->num_lines == next->s_lno) { - ent->num_lines += next->num_lines; - ent->next = next->next; - origin_decref(next->suspect); - free(next); - ent->score = 0; - next = ent; /* again */ - } - } - - if (DEBUG) /* sanity */ - sanity_check_refcnt(sb); -} - -/* - * Merge the given sorted list of blames into a preexisting origin. - * If there were no previous blames to that commit, it is entered into - * the commit priority queue of the score board. - */ - -static void queue_blames(struct scoreboard *sb, struct origin *porigin, - struct blame_entry *sorted) -{ - if (porigin->suspects) - porigin->suspects = blame_merge(porigin->suspects, sorted); - else { - struct origin *o; - for (o = porigin->commit->util; o; o = o->next) { - if (o->suspects) { - porigin->suspects = sorted; - return; - } - } - porigin->suspects = sorted; - prio_queue_put(&sb->commits, porigin->commit); - } -} - -/* - * Given a commit and a path in it, create a new origin structure. - * The callers that add blame to the scoreboard should use - * get_origin() to obtain shared, refcounted copy instead of calling - * this function directly. - */ -static struct origin *make_origin(struct commit *commit, const char *path) -{ - struct origin *o; - FLEX_ALLOC_STR(o, path, path); - o->commit = commit; - o->refcnt = 1; - o->next = commit->util; - commit->util = o; - return o; -} - -/* - * Locate an existing origin or create a new one. - * This moves the origin to front position in the commit util list. - */ -static struct origin *get_origin(struct scoreboard *sb, - struct commit *commit, - const char *path) -{ - struct origin *o, *l; - - for (o = commit->util, l = NULL; o; l = o, o = o->next) { - if (!strcmp(o->path, path)) { - /* bump to front */ - if (l) { - l->next = o->next; - o->next = commit->util; - commit->util = o; - } - return origin_incref(o); - } - } - return make_origin(commit, path); -} - -/* - * Fill the blob_sha1 field of an origin if it hasn't, so that later - * call to fill_origin_blob() can use it to locate the data. blob_sha1 - * for an origin is also used to pass the blame for the entire file to - * the parent to detect the case where a child's blob is identical to - * that of its parent's. - * - * This also fills origin->mode for corresponding tree path. - */ -static int fill_blob_sha1_and_mode(struct origin *origin) -{ - if (!is_null_oid(&origin->blob_oid)) - return 0; - if (get_tree_entry(origin->commit->object.oid.hash, - origin->path, - origin->blob_oid.hash, &origin->mode)) - goto error_out; - if (sha1_object_info(origin->blob_oid.hash, NULL) != OBJ_BLOB) - goto error_out; - return 0; - error_out: - oidclr(&origin->blob_oid); - origin->mode = S_IFINVALID; - return -1; -} - -/* - * We have an origin -- check if the same path exists in the - * parent and return an origin structure to represent it. - */ -static struct origin *find_origin(struct scoreboard *sb, - struct commit *parent, - struct origin *origin) -{ - struct origin *porigin; - struct diff_options diff_opts; - const char *paths[2]; - - /* First check any existing origins */ - for (porigin = parent->util; porigin; porigin = porigin->next) - if (!strcmp(porigin->path, origin->path)) { - /* - * The same path between origin and its parent - * without renaming -- the most common case. - */ - return origin_incref (porigin); - } - - /* See if the origin->path is different between parent - * and origin first. Most of the time they are the - * same and diff-tree is fairly efficient about this. - */ - diff_setup(&diff_opts); - DIFF_OPT_SET(&diff_opts, RECURSIVE); - diff_opts.detect_rename = 0; - diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; - paths[0] = origin->path; - paths[1] = NULL; - - parse_pathspec(&diff_opts.pathspec, - PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL, - PATHSPEC_LITERAL_PATH, "", paths); - diff_setup_done(&diff_opts); - - if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); - else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, - "", &diff_opts); - diffcore_std(&diff_opts); - - if (!diff_queued_diff.nr) { - /* The path is the same as parent */ - porigin = get_origin(sb, parent, origin->path); - oidcpy(&porigin->blob_oid, &origin->blob_oid); - porigin->mode = origin->mode; - } else { - /* - * Since origin->path is a pathspec, if the parent - * commit had it as a directory, we will see a whole - * bunch of deletion of files in the directory that we - * do not care about. - */ - int i; - struct diff_filepair *p = NULL; - for (i = 0; i < diff_queued_diff.nr; i++) { - const char *name; - p = diff_queued_diff.queue[i]; - name = p->one->path ? p->one->path : p->two->path; - if (!strcmp(name, origin->path)) - break; - } - if (!p) - die("internal error in blame::find_origin"); - switch (p->status) { - default: - die("internal error in blame::find_origin (%c)", - p->status); - case 'M': - porigin = get_origin(sb, parent, origin->path); - oidcpy(&porigin->blob_oid, &p->one->oid); - porigin->mode = p->one->mode; - break; - case 'A': - case 'T': - /* Did not exist in parent, or type changed */ - break; - } - } - diff_flush(&diff_opts); - clear_pathspec(&diff_opts.pathspec); - return porigin; -} - -/* - * We have an origin -- find the path that corresponds to it in its - * parent and return an origin structure to represent it. - */ -static struct origin *find_rename(struct scoreboard *sb, - struct commit *parent, - struct origin *origin) -{ - struct origin *porigin = NULL; - struct diff_options diff_opts; - int i; - - diff_setup(&diff_opts); - DIFF_OPT_SET(&diff_opts, RECURSIVE); - diff_opts.detect_rename = DIFF_DETECT_RENAME; - diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_opts.single_follow = origin->path; - diff_setup_done(&diff_opts); - - if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); - else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, - "", &diff_opts); - diffcore_std(&diff_opts); - - for (i = 0; i < diff_queued_diff.nr; i++) { - struct diff_filepair *p = diff_queued_diff.queue[i]; - if ((p->status == 'R' || p->status == 'C') && - !strcmp(p->two->path, origin->path)) { - porigin = get_origin(sb, parent, p->one->path); - oidcpy(&porigin->blob_oid, &p->one->oid); - porigin->mode = p->one->mode; - break; - } - } - diff_flush(&diff_opts); - clear_pathspec(&diff_opts.pathspec); - return porigin; -} - -/* - * Append a new blame entry to a given output queue. - */ -static void add_blame_entry(struct blame_entry ***queue, - const struct blame_entry *src) -{ - struct blame_entry *e = xmalloc(sizeof(*e)); - memcpy(e, src, sizeof(*e)); - origin_incref(e->suspect); - - e->next = **queue; - **queue = e; - *queue = &e->next; -} - -/* - * src typically is on-stack; we want to copy the information in it to - * a malloced blame_entry that gets added to the given queue. The - * origin of dst loses a refcnt. - */ -static void dup_entry(struct blame_entry ***queue, - struct blame_entry *dst, struct blame_entry *src) -{ - origin_incref(src->suspect); - origin_decref(dst->suspect); - memcpy(dst, src, sizeof(*src)); - dst->next = **queue; - **queue = dst; - *queue = &dst->next; -} - -static const char *nth_line(struct scoreboard *sb, long lno) -{ - return sb->final_buf + sb->lineno[lno]; -} - static const char *nth_line_cb(void *data, long lno) { - return nth_line((struct scoreboard *)data, lno); -} - -/* - * It is known that lines between tlno to same came from parent, and e - * has an overlap with that range. it also is known that parent's - * line plno corresponds to e's line tlno. - * - * <---- e -----> - * <------> - * <------------> - * <------------> - * <------------------> - * - * Split e into potentially three parts; before this chunk, the chunk - * to be blamed for the parent, and after that portion. - */ -static void split_overlap(struct blame_entry *split, - struct blame_entry *e, - int tlno, int plno, int same, - struct origin *parent) -{ - int chunk_end_lno; - memset(split, 0, sizeof(struct blame_entry [3])); - - if (e->s_lno < tlno) { - /* there is a pre-chunk part not blamed on parent */ - split[0].suspect = origin_incref(e->suspect); - split[0].lno = e->lno; - split[0].s_lno = e->s_lno; - split[0].num_lines = tlno - e->s_lno; - split[1].lno = e->lno + tlno - e->s_lno; - split[1].s_lno = plno; - } - else { - split[1].lno = e->lno; - split[1].s_lno = plno + (e->s_lno - tlno); - } - - if (same < e->s_lno + e->num_lines) { - /* there is a post-chunk part not blamed on parent */ - split[2].suspect = origin_incref(e->suspect); - split[2].lno = e->lno + (same - e->s_lno); - split[2].s_lno = e->s_lno + (same - e->s_lno); - split[2].num_lines = e->s_lno + e->num_lines - same; - chunk_end_lno = split[2].lno; - } - else - chunk_end_lno = e->lno + e->num_lines; - split[1].num_lines = chunk_end_lno - split[1].lno; - - /* - * if it turns out there is nothing to blame the parent for, - * forget about the splitting. !split[1].suspect signals this. - */ - if (split[1].num_lines < 1) - return; - split[1].suspect = origin_incref(parent); -} - -/* - * split_overlap() divided an existing blame e into up to three parts - * in split. Any assigned blame is moved to queue to - * reflect the split. - */ -static void split_blame(struct blame_entry ***blamed, - struct blame_entry ***unblamed, - struct blame_entry *split, - struct blame_entry *e) -{ - if (split[0].suspect && split[2].suspect) { - /* The first part (reuse storage for the existing entry e) */ - dup_entry(unblamed, e, &split[0]); - - /* The last part -- me */ - add_blame_entry(unblamed, &split[2]); - - /* ... and the middle part -- parent */ - add_blame_entry(blamed, &split[1]); - } - else if (!split[0].suspect && !split[2].suspect) - /* - * The parent covers the entire area; reuse storage for - * e and replace it with the parent. - */ - dup_entry(blamed, e, &split[1]); - else if (split[0].suspect) { - /* me and then parent */ - dup_entry(unblamed, e, &split[0]); - add_blame_entry(blamed, &split[1]); - } - else { - /* parent and then me */ - dup_entry(blamed, e, &split[1]); - add_blame_entry(unblamed, &split[2]); - } -} - -/* - * After splitting the blame, the origins used by the - * on-stack blame_entry should lose one refcnt each. - */ -static void decref_split(struct blame_entry *split) -{ - int i; - - for (i = 0; i < 3; i++) - origin_decref(split[i].suspect); -} - -/* - * reverse_blame reverses the list given in head, appending tail. - * That allows us to build lists in reverse order, then reverse them - * afterwards. This can be faster than building the list in proper - * order right away. The reason is that building in proper order - * requires writing a link in the _previous_ element, while building - * in reverse order just requires placing the list head into the - * _current_ element. - */ - -static struct blame_entry *reverse_blame(struct blame_entry *head, - struct blame_entry *tail) -{ - while (head) { - struct blame_entry *next = head->next; - head->next = tail; - tail = head; - head = next; - } - return tail; -} - -/* - * Process one hunk from the patch between the current suspect for - * blame_entry e and its parent. This first blames any unfinished - * entries before the chunk (which is where target and parent start - * differing) on the parent, and then splits blame entries at the - * start and at the end of the difference region. Since use of -M and - * -C options may lead to overlapping/duplicate source line number - * ranges, all we can rely on from sorting/merging is the order of the - * first suspect line number. - */ -static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq, - int tlno, int offset, int same, - struct origin *parent) -{ - struct blame_entry *e = **srcq; - struct blame_entry *samep = NULL, *diffp = NULL; - - while (e && e->s_lno < tlno) { - struct blame_entry *next = e->next; - /* - * current record starts before differing portion. If - * it reaches into it, we need to split it up and - * examine the second part separately. - */ - if (e->s_lno + e->num_lines > tlno) { - /* Move second half to a new record */ - int len = tlno - e->s_lno; - struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); - n->suspect = e->suspect; - n->lno = e->lno + len; - n->s_lno = e->s_lno + len; - n->num_lines = e->num_lines - len; - e->num_lines = len; - e->score = 0; - /* Push new record to diffp */ - n->next = diffp; - diffp = n; - } else - origin_decref(e->suspect); - /* Pass blame for everything before the differing - * chunk to the parent */ - e->suspect = origin_incref(parent); - e->s_lno += offset; - e->next = samep; - samep = e; - e = next; - } - /* - * As we don't know how much of a common stretch after this - * diff will occur, the currently blamed parts are all that we - * can assign to the parent for now. - */ - - if (samep) { - **dstq = reverse_blame(samep, **dstq); - *dstq = &samep->next; - } - /* - * Prepend the split off portions: everything after e starts - * after the blameable portion. - */ - e = reverse_blame(diffp, e); - - /* - * Now retain records on the target while parts are different - * from the parent. - */ - samep = NULL; - diffp = NULL; - while (e && e->s_lno < same) { - struct blame_entry *next = e->next; - - /* - * If current record extends into sameness, need to split. - */ - if (e->s_lno + e->num_lines > same) { - /* - * Move second half to a new record to be - * processed by later chunks - */ - int len = same - e->s_lno; - struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); - n->suspect = origin_incref(e->suspect); - n->lno = e->lno + len; - n->s_lno = e->s_lno + len; - n->num_lines = e->num_lines - len; - e->num_lines = len; - e->score = 0; - /* Push new record to samep */ - n->next = samep; - samep = n; - } - e->next = diffp; - diffp = e; - e = next; - } - **srcq = reverse_blame(diffp, reverse_blame(samep, e)); - /* Move across elements that are in the unblamable portion */ - if (diffp) - *srcq = &diffp->next; -} - -struct blame_chunk_cb_data { - struct origin *parent; - long offset; - struct blame_entry **dstq; - struct blame_entry **srcq; -}; - -/* diff chunks are from parent to target */ -static int blame_chunk_cb(long start_a, long count_a, - long start_b, long count_b, void *data) -{ - struct blame_chunk_cb_data *d = data; - if (start_a - start_b != d->offset) - die("internal error in blame::blame_chunk_cb"); - blame_chunk(&d->dstq, &d->srcq, start_b, start_a - start_b, - start_b + count_b, d->parent); - d->offset = start_a + count_a - (start_b + count_b); - return 0; -} - -/* - * We are looking at the origin 'target' and aiming to pass blame - * for the lines it is suspected to its parent. Run diff to find - * which lines came from parent and pass blame for them. - */ -static void pass_blame_to_parent(struct scoreboard *sb, - struct origin *target, - struct origin *parent) -{ - mmfile_t file_p, file_o; - struct blame_chunk_cb_data d; - struct blame_entry *newdest = NULL; - - if (!target->suspects) - return; /* nothing remains for this target */ - - d.parent = parent; - d.offset = 0; - d.dstq = &newdest; d.srcq = &target->suspects; - - fill_origin_blob(&sb->revs->diffopt, parent, &file_p); - fill_origin_blob(&sb->revs->diffopt, target, &file_o); - num_get_patch++; - - if (diff_hunks(&file_p, &file_o, blame_chunk_cb, &d)) - die("unable to generate diff (%s -> %s)", - oid_to_hex(&parent->commit->object.oid), - oid_to_hex(&target->commit->object.oid)); - /* The rest are the same as the parent */ - blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent); - *d.dstq = NULL; - queue_blames(sb, parent, newdest); - - return; -} - -/* - * The lines in blame_entry after splitting blames many times can become - * very small and trivial, and at some point it becomes pointless to - * blame the parents. E.g. "\t\t}\n\t}\n\n" appears everywhere in any - * ordinary C program, and it is not worth to say it was copied from - * totally unrelated file in the parent. - * - * Compute how trivial the lines in the blame_entry are. - */ -static unsigned ent_score(struct scoreboard *sb, struct blame_entry *e) -{ - unsigned score; - const char *cp, *ep; - - if (e->score) - return e->score; - - score = 1; - cp = nth_line(sb, e->lno); - ep = nth_line(sb, e->lno + e->num_lines); - while (cp < ep) { - unsigned ch = *((unsigned char *)cp); - if (isalnum(ch)) - score++; - cp++; - } - e->score = score; - return score; -} - -/* - * best_so_far[] and this[] are both a split of an existing blame_entry - * that passes blame to the parent. Maintain best_so_far the best split - * so far, by comparing this and best_so_far and copying this into - * bst_so_far as needed. - */ -static void copy_split_if_better(struct scoreboard *sb, - struct blame_entry *best_so_far, - struct blame_entry *this) -{ - int i; - - if (!this[1].suspect) - return; - if (best_so_far[1].suspect) { - if (ent_score(sb, &this[1]) < ent_score(sb, &best_so_far[1])) - return; - } - - for (i = 0; i < 3; i++) - origin_incref(this[i].suspect); - decref_split(best_so_far); - memcpy(best_so_far, this, sizeof(struct blame_entry [3])); -} - -/* - * We are looking at a part of the final image represented by - * ent (tlno and same are offset by ent->s_lno). - * tlno is where we are looking at in the final image. - * up to (but not including) same match preimage. - * plno is where we are looking at in the preimage. - * - * <-------------- final image ----------------------> - * <------ent------> - * ^tlno ^same - * <---------preimage-----> - * ^plno - * - * All line numbers are 0-based. - */ -static void handle_split(struct scoreboard *sb, - struct blame_entry *ent, - int tlno, int plno, int same, - struct origin *parent, - struct blame_entry *split) -{ - if (ent->num_lines <= tlno) - return; - if (tlno < same) { - struct blame_entry this[3]; - tlno += ent->s_lno; - same += ent->s_lno; - split_overlap(this, ent, tlno, plno, same, parent); - copy_split_if_better(sb, split, this); - decref_split(this); - } -} - -struct handle_split_cb_data { - struct scoreboard *sb; - struct blame_entry *ent; - struct origin *parent; - struct blame_entry *split; - long plno; - long tlno; -}; - -static int handle_split_cb(long start_a, long count_a, - long start_b, long count_b, void *data) -{ - struct handle_split_cb_data *d = data; - handle_split(d->sb, d->ent, d->tlno, d->plno, start_b, d->parent, - d->split); - d->plno = start_a + count_a; - d->tlno = start_b + count_b; - return 0; -} - -/* - * Find the lines from parent that are the same as ent so that - * we can pass blames to it. file_p has the blob contents for - * the parent. - */ -static void find_copy_in_blob(struct scoreboard *sb, - struct blame_entry *ent, - struct origin *parent, - struct blame_entry *split, - mmfile_t *file_p) -{ - const char *cp; - mmfile_t file_o; - struct handle_split_cb_data d; - - memset(&d, 0, sizeof(d)); - d.sb = sb; d.ent = ent; d.parent = parent; d.split = split; - /* - * Prepare mmfile that contains only the lines in ent. - */ - cp = nth_line(sb, ent->lno); - file_o.ptr = (char *) cp; - file_o.size = nth_line(sb, ent->lno + ent->num_lines) - cp; - - /* - * file_o is a part of final image we are annotating. - * file_p partially may match that image. - */ - memset(split, 0, sizeof(struct blame_entry [3])); - if (diff_hunks(file_p, &file_o, handle_split_cb, &d)) - die("unable to generate diff (%s)", - oid_to_hex(&parent->commit->object.oid)); - /* remainder, if any, all match the preimage */ - handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split); -} - -/* Move all blame entries from list *source that have a score smaller - * than score_min to the front of list *small. - * Returns a pointer to the link pointing to the old head of the small list. - */ - -static struct blame_entry **filter_small(struct scoreboard *sb, - struct blame_entry **small, - struct blame_entry **source, - unsigned score_min) -{ - struct blame_entry *p = *source; - struct blame_entry *oldsmall = *small; - while (p) { - if (ent_score(sb, p) <= score_min) { - *small = p; - small = &p->next; - p = *small; - } else { - *source = p; - source = &p->next; - p = *source; - } - } - *small = oldsmall; - *source = NULL; - return small; -} - -/* - * See if lines currently target is suspected for can be attributed to - * parent. - */ -static void find_move_in_parent(struct scoreboard *sb, - struct blame_entry ***blamed, - struct blame_entry **toosmall, - struct origin *target, - struct origin *parent) -{ - struct blame_entry *e, split[3]; - struct blame_entry *unblamed = target->suspects; - struct blame_entry *leftover = NULL; - mmfile_t file_p; - - if (!unblamed) - return; /* nothing remains for this target */ - - fill_origin_blob(&sb->revs->diffopt, parent, &file_p); - if (!file_p.ptr) - return; - - /* At each iteration, unblamed has a NULL-terminated list of - * entries that have not yet been tested for blame. leftover - * contains the reversed list of entries that have been tested - * without being assignable to the parent. - */ - do { - struct blame_entry **unblamedtail = &unblamed; - struct blame_entry *next; - for (e = unblamed; e; e = next) { - next = e->next; - find_copy_in_blob(sb, e, parent, split, &file_p); - if (split[1].suspect && - blame_move_score < ent_score(sb, &split[1])) { - split_blame(blamed, &unblamedtail, split, e); - } else { - e->next = leftover; - leftover = e; - } - decref_split(split); - } - *unblamedtail = NULL; - toosmall = filter_small(sb, toosmall, &unblamed, blame_move_score); - } while (unblamed); - target->suspects = reverse_blame(leftover, NULL); -} - -struct blame_list { - struct blame_entry *ent; - struct blame_entry split[3]; -}; - -/* - * Count the number of entries the target is suspected for, - * and prepare a list of entry and the best split. - */ -static struct blame_list *setup_blame_list(struct blame_entry *unblamed, - int *num_ents_p) -{ - struct blame_entry *e; - int num_ents, i; - struct blame_list *blame_list = NULL; - - for (e = unblamed, num_ents = 0; e; e = e->next) - num_ents++; - if (num_ents) { - blame_list = xcalloc(num_ents, sizeof(struct blame_list)); - for (e = unblamed, i = 0; e; e = e->next) - blame_list[i++].ent = e; - } - *num_ents_p = num_ents; - return blame_list; -} - -/* - * For lines target is suspected for, see if we can find code movement - * across file boundary from the parent commit. porigin is the path - * in the parent we already tried. - */ -static void find_copy_in_parent(struct scoreboard *sb, - struct blame_entry ***blamed, - struct blame_entry **toosmall, - struct origin *target, - struct commit *parent, - struct origin *porigin, - int opt) -{ - struct diff_options diff_opts; - int i, j; - struct blame_list *blame_list; - int num_ents; - struct blame_entry *unblamed = target->suspects; - struct blame_entry *leftover = NULL; - - if (!unblamed) - return; /* nothing remains for this target */ - - diff_setup(&diff_opts); - DIFF_OPT_SET(&diff_opts, RECURSIVE); - diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; - - diff_setup_done(&diff_opts); - - /* Try "find copies harder" on new path if requested; - * we do not want to use diffcore_rename() actually to - * match things up; find_copies_harder is set only to - * force diff_tree_oid() to feed all filepairs to diff_queue, - * and this code needs to be after diff_setup_done(), which - * usually makes find-copies-harder imply copy detection. - */ - if ((opt & PICKAXE_BLAME_COPY_HARDEST) - || ((opt & PICKAXE_BLAME_COPY_HARDER) - && (!porigin || strcmp(target->path, porigin->path)))) - DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER); - - if (is_null_oid(&target->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); - else - diff_tree_oid(&parent->tree->object.oid, - &target->commit->tree->object.oid, - "", &diff_opts); - - if (!DIFF_OPT_TST(&diff_opts, FIND_COPIES_HARDER)) - diffcore_std(&diff_opts); - - do { - struct blame_entry **unblamedtail = &unblamed; - blame_list = setup_blame_list(unblamed, &num_ents); - - for (i = 0; i < diff_queued_diff.nr; i++) { - struct diff_filepair *p = diff_queued_diff.queue[i]; - struct origin *norigin; - mmfile_t file_p; - struct blame_entry this[3]; - - if (!DIFF_FILE_VALID(p->one)) - continue; /* does not exist in parent */ - if (S_ISGITLINK(p->one->mode)) - continue; /* ignore git links */ - if (porigin && !strcmp(p->one->path, porigin->path)) - /* find_move already dealt with this path */ - continue; - - norigin = get_origin(sb, parent, p->one->path); - oidcpy(&norigin->blob_oid, &p->one->oid); - norigin->mode = p->one->mode; - fill_origin_blob(&sb->revs->diffopt, norigin, &file_p); - if (!file_p.ptr) - continue; - - for (j = 0; j < num_ents; j++) { - find_copy_in_blob(sb, blame_list[j].ent, - norigin, this, &file_p); - copy_split_if_better(sb, blame_list[j].split, - this); - decref_split(this); - } - origin_decref(norigin); - } - - for (j = 0; j < num_ents; j++) { - struct blame_entry *split = blame_list[j].split; - if (split[1].suspect && - blame_copy_score < ent_score(sb, &split[1])) { - split_blame(blamed, &unblamedtail, split, - blame_list[j].ent); - } else { - blame_list[j].ent->next = leftover; - leftover = blame_list[j].ent; - } - decref_split(split); - } - free(blame_list); - *unblamedtail = NULL; - toosmall = filter_small(sb, toosmall, &unblamed, blame_copy_score); - } while (unblamed); - target->suspects = reverse_blame(leftover, NULL); - diff_flush(&diff_opts); - clear_pathspec(&diff_opts.pathspec); -} - -/* - * The blobs of origin and porigin exactly match, so everything - * origin is suspected for can be blamed on the parent. - */ -static void pass_whole_blame(struct scoreboard *sb, - struct origin *origin, struct origin *porigin) -{ - struct blame_entry *e, *suspects; - - if (!porigin->file.ptr && origin->file.ptr) { - /* Steal its file */ - porigin->file = origin->file; - origin->file.ptr = NULL; - } - suspects = origin->suspects; - origin->suspects = NULL; - for (e = suspects; e; e = e->next) { - origin_incref(porigin); - origin_decref(e->suspect); - e->suspect = porigin; - } - queue_blames(sb, porigin, suspects); -} - -/* - * We pass blame from the current commit to its parents. We keep saying - * "parent" (and "porigin"), but what we mean is to find scapegoat to - * exonerate ourselves. - */ -static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit) -{ - if (!reverse) { - if (revs->first_parent_only && - commit->parents && - commit->parents->next) { - free_commit_list(commit->parents->next); - commit->parents->next = NULL; - } - return commit->parents; - } - return lookup_decoration(&revs->children, &commit->object); -} - -static int num_scapegoats(struct rev_info *revs, struct commit *commit) -{ - struct commit_list *l = first_scapegoat(revs, commit); - return commit_list_count(l); -} - -/* Distribute collected unsorted blames to the respected sorted lists - * in the various origins. - */ -static void distribute_blame(struct scoreboard *sb, struct blame_entry *blamed) -{ - blamed = blame_sort(blamed, compare_blame_suspect); - while (blamed) - { - struct origin *porigin = blamed->suspect; - struct blame_entry *suspects = NULL; - do { - struct blame_entry *next = blamed->next; - blamed->next = suspects; - suspects = blamed; - blamed = next; - } while (blamed && blamed->suspect == porigin); - suspects = reverse_blame(suspects, NULL); - queue_blames(sb, porigin, suspects); - } -} - -#define MAXSG 16 - -static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) -{ - struct rev_info *revs = sb->revs; - int i, pass, num_sg; - struct commit *commit = origin->commit; - struct commit_list *sg; - struct origin *sg_buf[MAXSG]; - struct origin *porigin, **sg_origin = sg_buf; - struct blame_entry *toosmall = NULL; - struct blame_entry *blames, **blametail = &blames; - - num_sg = num_scapegoats(revs, commit); - if (!num_sg) - goto finish; - else if (num_sg < ARRAY_SIZE(sg_buf)) - memset(sg_buf, 0, sizeof(sg_buf)); - else - sg_origin = xcalloc(num_sg, sizeof(*sg_origin)); - - /* - * The first pass looks for unrenamed path to optimize for - * common cases, then we look for renames in the second pass. - */ - for (pass = 0; pass < 2 - no_whole_file_rename; pass++) { - struct origin *(*find)(struct scoreboard *, - struct commit *, struct origin *); - find = pass ? find_rename : find_origin; - - for (i = 0, sg = first_scapegoat(revs, commit); - i < num_sg && sg; - sg = sg->next, i++) { - struct commit *p = sg->item; - int j, same; - - if (sg_origin[i]) - continue; - if (parse_commit(p)) - continue; - porigin = find(sb, p, origin); - if (!porigin) - continue; - if (!oidcmp(&porigin->blob_oid, &origin->blob_oid)) { - pass_whole_blame(sb, origin, porigin); - origin_decref(porigin); - goto finish; - } - for (j = same = 0; j < i; j++) - if (sg_origin[j] && - !oidcmp(&sg_origin[j]->blob_oid, &porigin->blob_oid)) { - same = 1; - break; - } - if (!same) - sg_origin[i] = porigin; - else - origin_decref(porigin); - } - } - - num_commits++; - for (i = 0, sg = first_scapegoat(revs, commit); - i < num_sg && sg; - sg = sg->next, i++) { - struct origin *porigin = sg_origin[i]; - if (!porigin) - continue; - if (!origin->previous) { - origin_incref(porigin); - origin->previous = porigin; - } - pass_blame_to_parent(sb, origin, porigin); - if (!origin->suspects) - goto finish; - } - - /* - * Optionally find moves in parents' files. - */ - if (opt & PICKAXE_BLAME_MOVE) { - filter_small(sb, &toosmall, &origin->suspects, blame_move_score); - if (origin->suspects) { - for (i = 0, sg = first_scapegoat(revs, commit); - i < num_sg && sg; - sg = sg->next, i++) { - struct origin *porigin = sg_origin[i]; - if (!porigin) - continue; - find_move_in_parent(sb, &blametail, &toosmall, origin, porigin); - if (!origin->suspects) - break; - } - } - } - - /* - * Optionally find copies from parents' files. - */ - if (opt & PICKAXE_BLAME_COPY) { - if (blame_copy_score > blame_move_score) - filter_small(sb, &toosmall, &origin->suspects, blame_copy_score); - else if (blame_copy_score < blame_move_score) { - origin->suspects = blame_merge(origin->suspects, toosmall); - toosmall = NULL; - filter_small(sb, &toosmall, &origin->suspects, blame_copy_score); - } - if (!origin->suspects) - goto finish; - - for (i = 0, sg = first_scapegoat(revs, commit); - i < num_sg && sg; - sg = sg->next, i++) { - struct origin *porigin = sg_origin[i]; - find_copy_in_parent(sb, &blametail, &toosmall, - origin, sg->item, porigin, opt); - if (!origin->suspects) - goto finish; - } - } - -finish: - *blametail = NULL; - distribute_blame(sb, blames); - /* - * prepend toosmall to origin->suspects - * - * There is no point in sorting: this ends up on a big - * unsorted list in the caller anyway. - */ - if (toosmall) { - struct blame_entry **tail = &toosmall; - while (*tail) - tail = &(*tail)->next; - *tail = origin->suspects; - origin->suspects = toosmall; - } - for (i = 0; i < num_sg; i++) { - if (sg_origin[i]) { - drop_origin_blob(sg_origin[i]); - origin_decref(sg_origin[i]); - } - } - drop_origin_blob(origin); - if (sg_buf != sg_origin) - free(sg_origin); + return blame_nth_line((struct blame_scoreboard *)data, lno); } /* @@ -1699,10 +216,10 @@ static void get_commit_info(struct commit *commit, * To allow LF and other nonportable characters in pathnames, * they are c-style quoted as needed. */ -static void write_filename_info(struct origin *suspect) +static void write_filename_info(struct blame_origin *suspect) { if (suspect->previous) { - struct origin *prev = suspect->previous; + struct blame_origin *prev = suspect->previous; printf("previous %s ", oid_to_hex(&prev->commit->object.oid)); write_name_quoted(prev->path, stdout, '\n'); } @@ -1716,7 +233,7 @@ static void write_filename_info(struct origin *suspect) * the first time each commit appears in the output (unless the * user has specifically asked for us to repeat). */ -static int emit_one_suspect_detail(struct origin *suspect, int repeat) +static int emit_one_suspect_detail(struct blame_origin *suspect, int repeat) { struct commit_info ci; @@ -1746,11 +263,12 @@ static int emit_one_suspect_detail(struct origin *suspect, int repeat) * The blame_entry is found to be guilty for the range. * Show it in incremental output. */ -static void found_guilty_entry(struct blame_entry *ent, - struct progress_info *pi) +static void found_guilty_entry(struct blame_entry *ent, void *data) { + struct progress_info *pi = (struct progress_info *)data; + if (incremental) { - struct origin *suspect = ent->suspect; + struct blame_origin *suspect = ent->suspect; printf("%s %d %d %d\n", oid_to_hex(&suspect->commit->object.oid), @@ -1763,80 +281,6 @@ static void found_guilty_entry(struct blame_entry *ent, display_progress(pi->progress, pi->blamed_lines); } -/* - * The main loop -- while we have blobs with lines whose true origin - * is still unknown, pick one blob, and allow its lines to pass blames - * to its parents. */ -static void assign_blame(struct scoreboard *sb, int opt) -{ - struct rev_info *revs = sb->revs; - struct commit *commit = prio_queue_get(&sb->commits); - struct progress_info pi = { NULL, 0 }; - - if (show_progress) - pi.progress = start_progress_delay(_("Blaming lines"), - sb->num_lines, 50, 1); - - while (commit) { - struct blame_entry *ent; - struct origin *suspect = commit->util; - - /* find one suspect to break down */ - while (suspect && !suspect->suspects) - suspect = suspect->next; - - if (!suspect) { - commit = prio_queue_get(&sb->commits); - continue; - } - - assert(commit == suspect->commit); - - /* - * We will use this suspect later in the loop, - * so hold onto it in the meantime. - */ - origin_incref(suspect); - parse_commit(commit); - if (reverse || - (!(commit->object.flags & UNINTERESTING) && - !(revs->max_age != -1 && commit->date < revs->max_age))) - pass_blame(sb, suspect, opt); - else { - commit->object.flags |= UNINTERESTING; - if (commit->object.parsed) - mark_parents_uninteresting(commit); - } - /* treat root commit as boundary */ - if (!commit->parents && !show_root) - commit->object.flags |= UNINTERESTING; - - /* Take responsibility for the remaining entries */ - ent = suspect->suspects; - if (ent) { - suspect->guilty = 1; - for (;;) { - struct blame_entry *next = ent->next; - found_guilty_entry(ent, &pi); - if (next) { - ent = next; - continue; - } - ent->next = sb->ent; - sb->ent = suspect->suspects; - suspect->suspects = NULL; - break; - } - } - origin_decref(suspect); - - if (DEBUG) /* sanity */ - sanity_check_refcnt(sb); - } - - stop_progress(&pi.progress); -} - static const char *format_time(timestamp_t time, const char *tz_str, int show_raw_time) { @@ -1876,20 +320,20 @@ static const char *format_time(timestamp_t time, const char *tz_str, #define OUTPUT_SHOW_EMAIL 0400 #define OUTPUT_LINE_PORCELAIN 01000 -static void emit_porcelain_details(struct origin *suspect, int repeat) +static void emit_porcelain_details(struct blame_origin *suspect, int repeat) { if (emit_one_suspect_detail(suspect, repeat) || (suspect->commit->object.flags & MORE_THAN_ONE_PATH)) write_filename_info(suspect); } -static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent, +static void emit_porcelain(struct blame_scoreboard *sb, struct blame_entry *ent, int opt) { int repeat = opt & OUTPUT_LINE_PORCELAIN; int cnt; const char *cp; - struct origin *suspect = ent->suspect; + struct blame_origin *suspect = ent->suspect; char hex[GIT_MAX_HEXSZ + 1]; oid_to_hex_r(hex, &suspect->commit->object.oid); @@ -1900,7 +344,7 @@ static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent, ent->num_lines); emit_porcelain_details(suspect, repeat); - cp = nth_line(sb, ent->lno); + cp = blame_nth_line(sb, ent->lno); for (cnt = 0; cnt < ent->num_lines; cnt++) { char ch; if (cnt) { @@ -1922,11 +366,11 @@ static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent, putchar('\n'); } -static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt) +static void emit_other(struct blame_scoreboard *sb, struct blame_entry *ent, int opt) { int cnt; const char *cp; - struct origin *suspect = ent->suspect; + struct blame_origin *suspect = ent->suspect; struct commit_info ci; char hex[GIT_MAX_HEXSZ + 1]; int show_raw_time = !!(opt & OUTPUT_RAW_TIMESTAMP); @@ -1934,7 +378,7 @@ static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt) get_commit_info(suspect->commit, &ci, 1); oid_to_hex_r(hex, &suspect->commit->object.oid); - cp = nth_line(sb, ent->lno); + cp = blame_nth_line(sb, ent->lno); for (cnt = 0; cnt < ent->num_lines; cnt++) { char ch; int length = (opt & OUTPUT_LONG_OBJECT_NAME) ? GIT_SHA1_HEXSZ : abbrev; @@ -2001,14 +445,14 @@ static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt) commit_info_destroy(&ci); } -static void output(struct scoreboard *sb, int option) +static void output(struct blame_scoreboard *sb, int option) { struct blame_entry *ent; if (option & OUTPUT_PORCELAIN) { for (ent = sb->ent; ent; ent = ent->next) { int count = 0; - struct origin *suspect; + struct blame_origin *suspect; struct commit *commit = ent->suspect->commit; if (commit->object.flags & MORE_THAN_ONE_PATH) continue; @@ -2030,40 +474,6 @@ static void output(struct scoreboard *sb, int option) } } -static const char *get_next_line(const char *start, const char *end) -{ - const char *nl = memchr(start, '\n', end - start); - return nl ? nl + 1 : end; -} - -/* - * To allow quick access to the contents of nth line in the - * final image, prepare an index in the scoreboard. - */ -static int prepare_lines(struct scoreboard *sb) -{ - const char *buf = sb->final_buf; - unsigned long len = sb->final_buf_size; - const char *end = buf + len; - const char *p; - int *lineno; - int num = 0; - - for (p = buf; p < end; p = get_next_line(p, end)) - num++; - - ALLOC_ARRAY(sb->lineno, num + 1); - lineno = sb->lineno; - - for (p = buf; p < end; p = get_next_line(p, end)) - *lineno++ = p - buf; - - *lineno = len; - - sb->num_lines = num; - return sb->num_lines; -} - /* * Add phony grafts for use with -S; this is primarily to * support git's cvsserver that wants to give a linear history @@ -2071,7 +481,7 @@ static int prepare_lines(struct scoreboard *sb) */ static int read_ancestry(const char *graft_file) { - FILE *fp = fopen(graft_file, "r"); + FILE *fp = fopen_or_warn(graft_file, "r"); struct strbuf buf = STRBUF_INIT; if (!fp) return -1; @@ -2086,7 +496,7 @@ static int read_ancestry(const char *graft_file) return 0; } -static int update_auto_abbrev(int auto_abbrev, struct origin *suspect) +static int update_auto_abbrev(int auto_abbrev, struct blame_origin *suspect) { const char *uniq = find_unique_abbrev(suspect->commit->object.oid.hash, auto_abbrev); @@ -2100,7 +510,7 @@ static int update_auto_abbrev(int auto_abbrev, struct origin *suspect) * How many columns do we need to show line numbers, authors, * and filenames? */ -static void find_alignment(struct scoreboard *sb, int *option) +static void find_alignment(struct blame_scoreboard *sb, int *option) { int longest_src_lines = 0; int longest_dst_lines = 0; @@ -2110,7 +520,7 @@ static void find_alignment(struct scoreboard *sb, int *option) int auto_abbrev = DEFAULT_ABBREV; for (e = sb->ent; e; e = e->next) { - struct origin *suspect = e->suspect; + struct blame_origin *suspect = e->suspect; int num; if (compute_auto_abbrev) @@ -2138,8 +548,8 @@ static void find_alignment(struct scoreboard *sb, int *option) num = e->lno + e->num_lines; if (longest_dst_lines < num) longest_dst_lines = num; - if (largest_score < ent_score(sb, e)) - largest_score = ent_score(sb, e); + if (largest_score < blame_entry_score(sb, e)) + largest_score = blame_entry_score(sb, e); } max_orig_digits = decimal_width(longest_src_lines); max_digits = decimal_width(longest_dst_lines); @@ -2150,31 +560,12 @@ static void find_alignment(struct scoreboard *sb, int *option) abbrev = auto_abbrev + 1; } -/* - * For debugging -- origin is refcounted, and this asserts that - * we do not underflow. - */ -static void sanity_check_refcnt(struct scoreboard *sb) +static void sanity_check_on_fail(struct blame_scoreboard *sb, int baa) { - int baa = 0; - struct blame_entry *ent; - - for (ent = sb->ent; ent; ent = ent->next) { - /* Nobody should have zero or negative refcnt */ - if (ent->suspect->refcnt <= 0) { - fprintf(stderr, "%s in %s has negative refcnt %d\n", - ent->suspect->path, - oid_to_hex(&ent->suspect->commit->object.oid), - ent->suspect->refcnt); - baa = 1; - } - } - if (baa) { - int opt = 0160; - find_alignment(sb, &opt); - output(sb, opt); - die("Baa %d!", baa); - } + int opt = OUTPUT_SHOW_SCORE | OUTPUT_SHOW_NUMBER | OUTPUT_SHOW_NAME; + find_alignment(sb, &opt); + output(sb, opt); + die("Baa %d!", baa); } static unsigned parse_score(const char *arg) @@ -2224,301 +615,6 @@ static int git_blame_config(const char *var, const char *value, void *cb) return git_default_config(var, value, cb); } -static void verify_working_tree_path(struct commit *work_tree, const char *path) -{ - struct commit_list *parents; - int pos; - - for (parents = work_tree->parents; parents; parents = parents->next) { - const struct object_id *commit_oid = &parents->item->object.oid; - struct object_id blob_oid; - unsigned mode; - - if (!get_tree_entry(commit_oid->hash, path, blob_oid.hash, &mode) && - sha1_object_info(blob_oid.hash, NULL) == OBJ_BLOB) - return; - } - - pos = cache_name_pos(path, strlen(path)); - if (pos >= 0) - ; /* path is in the index */ - else if (-1 - pos < active_nr && - !strcmp(active_cache[-1 - pos]->name, path)) - ; /* path is in the index, unmerged */ - else - die("no such path '%s' in HEAD", path); -} - -static struct commit_list **append_parent(struct commit_list **tail, const struct object_id *oid) -{ - struct commit *parent; - - parent = lookup_commit_reference(oid); - if (!parent) - die("no such commit %s", oid_to_hex(oid)); - return &commit_list_insert(parent, tail)->next; -} - -static void append_merge_parents(struct commit_list **tail) -{ - int merge_head; - struct strbuf line = STRBUF_INIT; - - merge_head = open(git_path_merge_head(), O_RDONLY); - if (merge_head < 0) { - if (errno == ENOENT) - return; - die("cannot open '%s' for reading", git_path_merge_head()); - } - - while (!strbuf_getwholeline_fd(&line, merge_head, '\n')) { - struct object_id oid; - if (line.len < GIT_SHA1_HEXSZ || get_oid_hex(line.buf, &oid)) - die("unknown line in '%s': %s", git_path_merge_head(), line.buf); - tail = append_parent(tail, &oid); - } - close(merge_head); - strbuf_release(&line); -} - -/* - * This isn't as simple as passing sb->buf and sb->len, because we - * want to transfer ownership of the buffer to the commit (so we - * must use detach). - */ -static void set_commit_buffer_from_strbuf(struct commit *c, struct strbuf *sb) -{ - size_t len; - void *buf = strbuf_detach(sb, &len); - set_commit_buffer(c, buf, len); -} - -/* - * Prepare a dummy commit that represents the work tree (or staged) item. - * Note that annotating work tree item never works in the reverse. - */ -static struct commit *fake_working_tree_commit(struct diff_options *opt, - const char *path, - const char *contents_from) -{ - struct commit *commit; - struct origin *origin; - struct commit_list **parent_tail, *parent; - struct object_id head_oid; - struct strbuf buf = STRBUF_INIT; - const char *ident; - time_t now; - int size, len; - struct cache_entry *ce; - unsigned mode; - struct strbuf msg = STRBUF_INIT; - - read_cache(); - time(&now); - commit = alloc_commit_node(); - commit->object.parsed = 1; - commit->date = now; - parent_tail = &commit->parents; - - if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) - die("no such ref: HEAD"); - - parent_tail = append_parent(parent_tail, &head_oid); - append_merge_parents(parent_tail); - verify_working_tree_path(commit, path); - - origin = make_origin(commit, path); - - ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0); - strbuf_addstr(&msg, "tree 0000000000000000000000000000000000000000\n"); - for (parent = commit->parents; parent; parent = parent->next) - strbuf_addf(&msg, "parent %s\n", - oid_to_hex(&parent->item->object.oid)); - strbuf_addf(&msg, - "author %s\n" - "committer %s\n\n" - "Version of %s from %s\n", - ident, ident, path, - (!contents_from ? path : - (!strcmp(contents_from, "-") ? "standard input" : contents_from))); - set_commit_buffer_from_strbuf(commit, &msg); - - if (!contents_from || strcmp("-", contents_from)) { - struct stat st; - const char *read_from; - char *buf_ptr; - unsigned long buf_len; - - if (contents_from) { - if (stat(contents_from, &st) < 0) - die_errno("Cannot stat '%s'", contents_from); - read_from = contents_from; - } - else { - if (lstat(path, &st) < 0) - die_errno("Cannot lstat '%s'", path); - read_from = path; - } - mode = canon_mode(st.st_mode); - - switch (st.st_mode & S_IFMT) { - case S_IFREG: - if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && - textconv_object(read_from, mode, &null_oid, 0, &buf_ptr, &buf_len)) - strbuf_attach(&buf, buf_ptr, buf_len, buf_len + 1); - else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size) - die_errno("cannot open or read '%s'", read_from); - break; - case S_IFLNK: - if (strbuf_readlink(&buf, read_from, st.st_size) < 0) - die_errno("cannot readlink '%s'", read_from); - break; - default: - die("unsupported file type %s", read_from); - } - } - else { - /* Reading from stdin */ - mode = 0; - if (strbuf_read(&buf, 0, 0) < 0) - die_errno("failed to read from stdin"); - } - convert_to_git(path, buf.buf, buf.len, &buf, 0); - origin->file.ptr = buf.buf; - origin->file.size = buf.len; - pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_oid.hash); - - /* - * Read the current index, replace the path entry with - * origin->blob_sha1 without mucking with its mode or type - * bits; we are not going to write this index out -- we just - * want to run "diff-index --cached". - */ - discard_cache(); - read_cache(); - - len = strlen(path); - if (!mode) { - int pos = cache_name_pos(path, len); - if (0 <= pos) - mode = active_cache[pos]->ce_mode; - else - /* Let's not bother reading from HEAD tree */ - mode = S_IFREG | 0644; - } - size = cache_entry_size(len); - ce = xcalloc(1, size); - oidcpy(&ce->oid, &origin->blob_oid); - memcpy(ce->name, path, len); - ce->ce_flags = create_ce_flags(0); - ce->ce_namelen = len; - ce->ce_mode = create_ce_mode(mode); - add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); - - cache_tree_invalidate_path(&the_index, path); - - return commit; -} - -static struct commit *find_single_final(struct rev_info *revs, - const char **name_p) -{ - int i; - struct commit *found = NULL; - const char *name = NULL; - - for (i = 0; i < revs->pending.nr; i++) { - struct object *obj = revs->pending.objects[i].item; - if (obj->flags & UNINTERESTING) - continue; - obj = deref_tag(obj, NULL, 0); - if (obj->type != OBJ_COMMIT) - die("Non commit %s?", revs->pending.objects[i].name); - if (found) - die("More than one commit to dig from %s and %s?", - revs->pending.objects[i].name, name); - found = (struct commit *)obj; - name = revs->pending.objects[i].name; - } - if (name_p) - *name_p = name; - return found; -} - -static char *prepare_final(struct scoreboard *sb) -{ - const char *name; - sb->final = find_single_final(sb->revs, &name); - return xstrdup_or_null(name); -} - -static const char *dwim_reverse_initial(struct scoreboard *sb) -{ - /* - * DWIM "git blame --reverse ONE -- PATH" as - * "git blame --reverse ONE..HEAD -- PATH" but only do so - * when it makes sense. - */ - struct object *obj; - struct commit *head_commit; - struct object_id head_oid; - - if (sb->revs->pending.nr != 1) - return NULL; - - /* Is that sole rev a committish? */ - obj = sb->revs->pending.objects[0].item; - obj = deref_tag(obj, NULL, 0); - if (obj->type != OBJ_COMMIT) - return NULL; - - /* Do we have HEAD? */ - if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) - return NULL; - head_commit = lookup_commit_reference_gently(&head_oid, 1); - if (!head_commit) - return NULL; - - /* Turn "ONE" into "ONE..HEAD" then */ - obj->flags |= UNINTERESTING; - add_pending_object(sb->revs, &head_commit->object, "HEAD"); - - sb->final = (struct commit *)obj; - return sb->revs->pending.objects[0].name; -} - -static char *prepare_initial(struct scoreboard *sb) -{ - int i; - const char *final_commit_name = NULL; - struct rev_info *revs = sb->revs; - - /* - * There must be one and only one negative commit, and it must be - * the boundary. - */ - for (i = 0; i < revs->pending.nr; i++) { - struct object *obj = revs->pending.objects[i].item; - if (!(obj->flags & UNINTERESTING)) - continue; - obj = deref_tag(obj, NULL, 0); - if (obj->type != OBJ_COMMIT) - die("Non commit %s?", revs->pending.objects[i].name); - if (sb->final) - die("More than one commit to dig up from, %s and %s?", - revs->pending.objects[i].name, - final_commit_name); - sb->final = (struct commit *) obj; - final_commit_name = revs->pending.objects[i].name; - } - - if (!final_commit_name) - final_commit_name = dwim_reverse_initial(sb); - if (!final_commit_name) - die("No commit to dig up from?"); - return xstrdup(final_commit_name); -} - static int blame_copy_callback(const struct option *option, const char *arg, int unset) { int *opt = option->value; @@ -2556,13 +652,11 @@ int cmd_blame(int argc, const char **argv, const char *prefix) { struct rev_info revs; const char *path; - struct scoreboard sb; - struct origin *o; + struct blame_scoreboard sb; + struct blame_origin *o; struct blame_entry *ent = NULL; long dashdash_pos, lno; - char *final_commit_name = NULL; - enum object_type type; - struct commit *final_commit = NULL; + struct progress_info pi = { NULL, 0 }; struct string_list range_list = STRING_LIST_INIT_NODUP; int output_option = 0, opt = 0; @@ -2688,12 +782,15 @@ parse_done: blame_date_width = sizeof("2006-10-19"); break; case DATE_RELATIVE: - /* TRANSLATORS: This string is used to tell us the maximum - display width for a relative timestamp in "git blame" - output. For C locale, "4 years, 11 months ago", which - takes 22 places, is the longest among various forms of - relative timestamps, but your language may need more or - fewer display columns. */ + /* + * TRANSLATORS: This string is used to tell us the + * maximum display width for a relative timestamp in + * "git blame" output. For C locale, "4 years, 11 + * months ago", which takes 22 places, is the longest + * among various forms of relative timestamps, but + * your language may need more or fewer display + * columns. + */ blame_date_width = utf8_strwidth(_("4 years, 11 months ago")) + 1; /* add the null */ break; case DATE_NORMAL: @@ -2709,11 +806,6 @@ parse_done: opt |= (PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE | PICKAXE_BLAME_COPY_HARDER); - if (!blame_move_score) - blame_move_score = BLAME_DEFAULT_MOVE_SCORE; - if (!blame_copy_score) - blame_copy_score = BLAME_DEFAULT_COPY_SCORE; - /* * We have collected options unknown to us in argv[1..unk] * which are to be passed to revision machinery if we are @@ -2766,94 +858,13 @@ parse_done: revs.disable_stdin = 1; setup_revisions(argc, argv, &revs, NULL); - memset(&sb, 0, sizeof(sb)); + init_scoreboard(&sb); sb.revs = &revs; - if (!reverse) { - final_commit_name = prepare_final(&sb); - sb.commits.compare = compare_commits_by_commit_date; - } - else if (contents_from) - die(_("--contents and --reverse do not blend well.")); - else { - final_commit_name = prepare_initial(&sb); - sb.commits.compare = compare_commits_by_reverse_commit_date; - if (revs.first_parent_only) - revs.children.name = NULL; - } - - if (!sb.final) { - /* - * "--not A B -- path" without anything positive; - * do not default to HEAD, but use the working tree - * or "--contents". - */ - setup_work_tree(); - sb.final = fake_working_tree_commit(&sb.revs->diffopt, - path, contents_from); - add_pending_object(&revs, &(sb.final->object), ":"); - } - else if (contents_from) - die(_("cannot use --contents with final commit object name")); - - if (reverse && revs.first_parent_only) { - final_commit = find_single_final(sb.revs, NULL); - if (!final_commit) - die(_("--reverse and --first-parent together require specified latest commit")); - } - - /* - * If we have bottom, this will mark the ancestors of the - * bottom commits we would reach while traversing as - * uninteresting. - */ - if (prepare_revision_walk(&revs)) - die(_("revision walk setup failed")); - - if (reverse && revs.first_parent_only) { - struct commit *c = final_commit; - - sb.revs->children.name = "children"; - while (c->parents && - oidcmp(&c->object.oid, &sb.final->object.oid)) { - struct commit_list *l = xcalloc(1, sizeof(*l)); - - l->item = c; - if (add_decoration(&sb.revs->children, - &c->parents->item->object, l)) - die("BUG: not unique item in first-parent chain"); - c = c->parents->item; - } - - if (oidcmp(&c->object.oid, &sb.final->object.oid)) - die(_("--reverse --first-parent together require range along first-parent chain")); - } - - if (is_null_oid(&sb.final->object.oid)) { - o = sb.final->util; - sb.final_buf = xmemdupz(o->file.ptr, o->file.size); - sb.final_buf_size = o->file.size; - } - else { - o = get_origin(&sb, sb.final, path); - if (fill_blob_sha1_and_mode(o)) - die(_("no such path %s in %s"), path, final_commit_name); - - if (DIFF_OPT_TST(&sb.revs->diffopt, ALLOW_TEXTCONV) && - textconv_object(path, o->mode, &o->blob_oid, 1, (char **) &sb.final_buf, - &sb.final_buf_size)) - ; - else - sb.final_buf = read_sha1_file(o->blob_oid.hash, &type, - &sb.final_buf_size); - - if (!sb.final_buf) - die(_("cannot read blob %s for path %s"), - oid_to_hex(&o->blob_oid), - path); - } - num_read_blob++; - lno = prepare_lines(&sb); + sb.contents_from = contents_from; + sb.reverse = reverse; + setup_scoreboard(&sb, path, &o); + lno = sb.num_lines; if (lno && !range_list.nr) string_list_append(&range_list, "1"); @@ -2882,22 +893,13 @@ parse_done: for (range_i = ranges.nr; range_i > 0; --range_i) { const struct range *r = &ranges.ranges[range_i - 1]; - long bottom = r->start; - long top = r->end; - struct blame_entry *next = ent; - ent = xcalloc(1, sizeof(*ent)); - ent->lno = bottom; - ent->num_lines = top - bottom; - ent->suspect = o; - ent->s_lno = bottom; - ent->next = next; - origin_incref(o); + ent = blame_entry_prepend(ent, r->start, r->end, o); } o->suspects = ent; prio_queue_put(&sb.commits, o->commit); - origin_decref(o); + blame_origin_decref(o); range_set_release(&ranges); string_list_clear(&range_list, 0); @@ -2905,21 +907,38 @@ parse_done: sb.ent = NULL; sb.path = path; + if (blame_move_score) + sb.move_score = blame_move_score; + if (blame_copy_score) + sb.copy_score = blame_copy_score; + + sb.debug = DEBUG; + sb.on_sanity_fail = &sanity_check_on_fail; + + sb.show_root = show_root; + sb.xdl_opts = xdl_opts; + sb.no_whole_file_rename = no_whole_file_rename; + read_mailmap(&mailmap, NULL); + sb.found_guilty_entry = &found_guilty_entry; + sb.found_guilty_entry_data = π + if (show_progress) + pi.progress = start_progress_delay(_("Blaming lines"), + sb.num_lines, 50, 1); + assign_blame(&sb, opt); + stop_progress(&pi.progress); + if (!incremental) setup_pager(); - - free(final_commit_name); - - if (incremental) + else return 0; - sb.ent = blame_sort(sb.ent, compare_blame_final); + blame_sort_final(&sb); - coalesce(&sb); + blame_coalesce(&sb); if (!(output_option & OUTPUT_PORCELAIN)) find_alignment(&sb, &output_option); @@ -2933,9 +952,9 @@ parse_done: } if (show_stats) { - printf("num read blob: %d\n", num_read_blob); - printf("num get patch: %d\n", num_get_patch); - printf("num commits: %d\n", num_commits); + printf("num read blob: %d\n", sb.num_read_blob); + printf("num get patch: %d\n", sb.num_get_patch); + printf("num commits: %d\n", sb.num_commits); } return 0; } diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 9af863e791..4bffd7a2d8 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -5,6 +5,7 @@ */ #include "cache.h" #include "builtin.h" +#include "diff.h" #include "parse-options.h" #include "userdiff.h" #include "streaming.h" @@ -61,7 +62,8 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, if (unknown_type) flags |= LOOKUP_UNKNOWN_OBJECT; - if (get_sha1_with_context(obj_name, 0, oid.hash, &obj_context)) + if (get_sha1_with_context(obj_name, GET_SHA1_RECORD_PATH, + oid.hash, &obj_context)) die("Not a valid object name %s", obj_name); if (!path) @@ -166,6 +168,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, write_or_die(1, buf, size); free(buf); + free(obj_context.path); return 0; } diff --git a/builtin/checkout.c b/builtin/checkout.c index a6b2af39d3..1624eed7e7 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -21,31 +21,12 @@ #include "submodule-config.h" #include "submodule.h" -static int recurse_submodules = RECURSE_SUBMODULES_DEFAULT; - static const char * const checkout_usage[] = { N_("git checkout [<options>] <branch>"), N_("git checkout [<options>] [<branch>] -- <file>..."), NULL, }; -static int option_parse_recurse_submodules(const struct option *opt, - const char *arg, int unset) -{ - if (unset) { - recurse_submodules = RECURSE_SUBMODULES_OFF; - return 0; - } - if (arg) - recurse_submodules = - parse_update_recurse_submodules_arg(opt->long_name, - arg); - else - recurse_submodules = RECURSE_SUBMODULES_ON; - - return 0; -} - struct checkout_opts { int patch_mode; int quiet; @@ -876,7 +857,7 @@ static int git_checkout_config(const char *var, const char *value, void *cb) } if (starts_with(var, "submodule.")) - return parse_submodule_config_option(var, value); + return submodule_config(var, value, NULL); return git_xmerge_config(var, value, NULL); } @@ -1184,9 +1165,9 @@ int cmd_checkout(int argc, const char **argv, const char *prefix) N_("second guess 'git checkout <no-such-branch>'")), OPT_BOOL(0, "ignore-other-worktrees", &opts.ignore_other_worktrees, N_("do not check if another worktree is holding the given ref")), - { OPTION_CALLBACK, 0, "recurse-submodules", &recurse_submodules, + { OPTION_CALLBACK, 0, "recurse-submodules", NULL, "checkout", "control recursive updating of submodules", - PARSE_OPT_OPTARG, option_parse_recurse_submodules }, + PARSE_OPT_OPTARG, option_parse_recurse_submodules_worktree_updater }, OPT_BOOL(0, "progress", &opts.show_progress, N_("force progress reporting")), OPT_END(), }; @@ -1217,12 +1198,6 @@ int cmd_checkout(int argc, const char **argv, const char *prefix) git_xmerge_config("merge.conflictstyle", conflict_style, NULL); } - if (recurse_submodules != RECURSE_SUBMODULES_OFF) { - git_config(submodule_config, NULL); - if (recurse_submodules != RECURSE_SUBMODULES_DEFAULT) - set_config_update_recurse_submodules(recurse_submodules); - } - if ((!!opts.new_branch + !!opts.new_branch_force + !!opts.new_orphan_branch) > 1) die(_("-b, -B and --orphan are mutually exclusive")); diff --git a/builtin/clean.c b/builtin/clean.c index 329b68c40b..142bf668cf 100644 --- a/builtin/clean.c +++ b/builtin/clean.c @@ -857,6 +857,38 @@ static void interactive_main_loop(void) } } +static void correct_untracked_entries(struct dir_struct *dir) +{ + int src, dst, ign; + + for (src = dst = ign = 0; src < dir->nr; src++) { + /* skip paths in ignored[] that cannot be inside entries[src] */ + while (ign < dir->ignored_nr && + 0 <= cmp_dir_entry(&dir->entries[src], &dir->ignored[ign])) + ign++; + + if (ign < dir->ignored_nr && + check_dir_entry_contains(dir->entries[src], dir->ignored[ign])) { + /* entries[src] contains an ignored path, so we drop it */ + free(dir->entries[src]); + } else { + struct dir_entry *ent = dir->entries[src++]; + + /* entries[src] does not contain an ignored path, so we keep it */ + dir->entries[dst++] = ent; + + /* then discard paths in entries[] contained inside entries[src] */ + while (src < dir->nr && + check_dir_entry_contains(ent, dir->entries[src])) + free(dir->entries[src++]); + + /* compensate for the outer loop's loop control */ + src--; + } + } + dir->nr = dst; +} + int cmd_clean(int argc, const char **argv, const char *prefix) { int i, res; @@ -916,6 +948,9 @@ int cmd_clean(int argc, const char **argv, const char *prefix) dir.flags |= DIR_SHOW_OTHER_DIRECTORIES; + if (remove_directories) + dir.flags |= DIR_SHOW_IGNORED_TOO | DIR_KEEP_UNTRACKED_CONTENTS; + if (read_cache() < 0) die(_("index file corrupt")); @@ -931,6 +966,7 @@ int cmd_clean(int argc, const char **argv, const char *prefix) prefix, argv); fill_directory(&dir, &the_index, &pathspec); + correct_untracked_entries(&dir); for (i = 0; i < dir.nr; i++) { struct dir_entry *ent = dir.entries[i]; @@ -958,6 +994,12 @@ int cmd_clean(int argc, const char **argv, const char *prefix) string_list_append(&del_list, rel); } + for (i = 0; i < dir.nr; i++) + free(dir.entries[i]); + + for (i = 0; i < dir.ignored_nr; i++) + free(dir.ignored[i]); + if (interactive && del_list.nr > 0) interactive_main_loop(); diff --git a/builtin/clone.c b/builtin/clone.c index 743f16ae2a..a2ea019c59 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -360,7 +360,7 @@ static void copy_alternates(struct strbuf *src, struct strbuf *dst, * to turn entries with paths relative to the original * absolute, so that they can be used in the new repository. */ - FILE *in = fopen(src->buf, "r"); + FILE *in = xfopen(src->buf, "r"); struct strbuf line = STRBUF_INIT; while (strbuf_getline(&line, in) != EOF) { diff --git a/builtin/commit.c b/builtin/commit.c index 7587810045..e3c9e190b0 100644 --- a/builtin/commit.c +++ b/builtin/commit.c @@ -1699,10 +1699,7 @@ int cmd_commit(int argc, const char **argv, const char *prefix) if (!reflog_msg) reflog_msg = "commit (merge)"; pptr = commit_list_append(current_head, pptr); - fp = fopen(git_path_merge_head(), "r"); - if (fp == NULL) - die_errno(_("could not open '%s' for reading"), - git_path_merge_head()); + fp = xfopen(git_path_merge_head(), "r"); while (strbuf_getline_lf(&m, fp) != EOF) { struct commit *parent; diff --git a/builtin/diff-files.c b/builtin/diff-files.c index 15c61fd8d1..a572da9d51 100644 --- a/builtin/diff-files.c +++ b/builtin/diff-files.c @@ -20,9 +20,9 @@ int cmd_diff_files(int argc, const char **argv, const char *prefix) int result; unsigned options = 0; + git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(&rev, prefix); gitmodules_config(); - git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ rev.abbrev = 0; precompose_argv(argc, argv); diff --git a/builtin/diff-index.c b/builtin/diff-index.c index 1af373d002..f084826a29 100644 --- a/builtin/diff-index.c +++ b/builtin/diff-index.c @@ -17,9 +17,9 @@ int cmd_diff_index(int argc, const char **argv, const char *prefix) int i; int result; + git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(&rev, prefix); gitmodules_config(); - git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ rev.abbrev = 0; precompose_argv(argc, argv); diff --git a/builtin/diff-tree.c b/builtin/diff-tree.c index 8b26a66a95..1fd06eac4b 100644 --- a/builtin/diff-tree.c +++ b/builtin/diff-tree.c @@ -104,9 +104,9 @@ int cmd_diff_tree(int argc, const char **argv, const char *prefix) struct setup_revision_opt s_r_opt; int read_stdin = 0; + git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(opt, prefix); gitmodules_config(); - git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ opt->abbrev = 0; opt->diff = 1; opt->disable_stdin = 1; @@ -127,9 +127,11 @@ int cmd_diff_tree(int argc, const char **argv, const char *prefix) } /* - * NOTE! We expect "a ^b" to be equal to "a..b", so we - * reverse the order of the objects if the second one - * is marked UNINTERESTING. + * NOTE! We expect "a..b" to expand to "^a b" but it is + * perfectly valid for revision range parser to yield "b ^a", + * which means the same thing. If we get the latter, i.e. the + * second one is marked UNINTERESTING, we recover the original + * order the user gave, i.e. "a..b", by swapping the trees. */ switch (opt->pending.nr) { case 0: diff --git a/builtin/diff.c b/builtin/diff.c index 4c6a1a962f..d9152c21bf 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -20,23 +20,22 @@ #define DIFF_NO_INDEX_EXPLICIT 1 #define DIFF_NO_INDEX_IMPLICIT 2 -struct blobinfo { - struct object_id oid; - const char *name; - unsigned mode; -}; - static const char builtin_diff_usage[] = "git diff [<options>] [<commit> [<commit>]] [--] [<path>...]"; +static const char *blob_path(struct object_array_entry *entry) +{ + return entry->path ? entry->path : entry->name; +} + static void stuff_change(struct diff_options *opt, unsigned old_mode, unsigned new_mode, const struct object_id *old_oid, const struct object_id *new_oid, int old_oid_valid, int new_oid_valid, - const char *old_name, - const char *new_name) + const char *old_path, + const char *new_path) { struct diff_filespec *one, *two; @@ -47,16 +46,16 @@ static void stuff_change(struct diff_options *opt, if (DIFF_OPT_TST(opt, REVERSE_DIFF)) { SWAP(old_mode, new_mode); SWAP(old_oid, new_oid); - SWAP(old_name, new_name); + SWAP(old_path, new_path); } if (opt->prefix && - (strncmp(old_name, opt->prefix, opt->prefix_length) || - strncmp(new_name, opt->prefix, opt->prefix_length))) + (strncmp(old_path, opt->prefix, opt->prefix_length) || + strncmp(new_path, opt->prefix, opt->prefix_length))) return; - one = alloc_filespec(old_name); - two = alloc_filespec(new_name); + one = alloc_filespec(old_path); + two = alloc_filespec(new_path); fill_filespec(one, old_oid, old_oid_valid, old_mode); fill_filespec(two, new_oid, new_oid_valid, new_mode); @@ -65,7 +64,7 @@ static void stuff_change(struct diff_options *opt, static int builtin_diff_b_f(struct rev_info *revs, int argc, const char **argv, - struct blobinfo *blob) + struct object_array_entry **blob) { /* Blob vs file in the working tree*/ struct stat st; @@ -84,14 +83,15 @@ static int builtin_diff_b_f(struct rev_info *revs, diff_set_mnemonic_prefix(&revs->diffopt, "o/", "w/"); - if (blob[0].mode == S_IFINVALID) - blob[0].mode = canon_mode(st.st_mode); + if (blob[0]->mode == S_IFINVALID) + blob[0]->mode = canon_mode(st.st_mode); stuff_change(&revs->diffopt, - blob[0].mode, canon_mode(st.st_mode), - &blob[0].oid, &null_oid, + blob[0]->mode, canon_mode(st.st_mode), + &blob[0]->item->oid, &null_oid, 1, 0, - path, path); + blob[0]->path ? blob[0]->path : path, + path); diffcore_std(&revs->diffopt); diff_flush(&revs->diffopt); return 0; @@ -99,24 +99,24 @@ static int builtin_diff_b_f(struct rev_info *revs, static int builtin_diff_blobs(struct rev_info *revs, int argc, const char **argv, - struct blobinfo *blob) + struct object_array_entry **blob) { unsigned mode = canon_mode(S_IFREG | 0644); if (argc > 1) usage(builtin_diff_usage); - if (blob[0].mode == S_IFINVALID) - blob[0].mode = mode; + if (blob[0]->mode == S_IFINVALID) + blob[0]->mode = mode; - if (blob[1].mode == S_IFINVALID) - blob[1].mode = mode; + if (blob[1]->mode == S_IFINVALID) + blob[1]->mode = mode; stuff_change(&revs->diffopt, - blob[0].mode, blob[1].mode, - &blob[0].oid, &blob[1].oid, + blob[0]->mode, blob[1]->mode, + &blob[0]->item->oid, &blob[1]->item->oid, 1, 1, - blob[0].name, blob[1].name); + blob_path(blob[0]), blob_path(blob[1])); diffcore_std(&revs->diffopt); diff_flush(&revs->diffopt); return 0; @@ -259,7 +259,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix) struct rev_info rev; struct object_array ent = OBJECT_ARRAY_INIT; int blobs = 0, paths = 0; - struct blobinfo blob[2]; + struct object_array_entry *blob[2]; int nongit = 0, no_index = 0; int result = 0; @@ -408,9 +408,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix) } else if (obj->type == OBJ_BLOB) { if (2 <= blobs) die(_("more than two blobs given: '%s'"), name); - oidcpy(&blob[blobs].oid, &obj->oid); - blob[blobs].name = name; - blob[blobs].mode = entry->mode; + blob[blobs] = entry; blobs++; } else { diff --git a/builtin/fast-export.c b/builtin/fast-export.c index d57f36c438..a932be04f4 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -907,9 +907,7 @@ static void export_marks(char *file) static void import_marks(char *input_file) { char line[512]; - FILE *f = fopen(input_file, "r"); - if (!f) - die_errno("cannot read '%s'", input_file); + FILE *f = xfopen(input_file, "r"); while (fgets(line, sizeof(line), f)) { uint32_t mark; diff --git a/builtin/fetch.c b/builtin/fetch.c index d4d573b985..100248c5af 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -73,6 +73,13 @@ static int git_fetch_config(const char *k, const char *v, void *cb) fetch_prune_config = git_config_bool(k, v); return 0; } + + if (!strcmp(k, "submodule.recurse")) { + int r = git_config_bool(k, v) ? + RECURSE_SUBMODULES_ON : RECURSE_SUBMODULES_OFF; + recurse_submodules = r; + } + return git_default_config(k, v, cb); } @@ -941,7 +948,7 @@ static int prune_refs(struct refspec *refs, int ref_count, struct ref *ref_map, for (ref = stale_refs; ref; ref = ref->next) string_list_append(&refnames, ref->name); - result = delete_refs(&refnames, 0); + result = delete_refs("fetch: prune", &refnames, 0); string_list_clear(&refnames, 0); } diff --git a/builtin/fsck.c b/builtin/fsck.c index cb2ba6cd1b..3a2c27f241 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -280,8 +280,7 @@ static void check_unreachable_object(struct object *obj) free(filename); return; } - if (!(f = fopen(filename, "w"))) - die_errno("Could not open '%s'", filename); + f = xfopen(filename, "w"); if (obj->type == OBJ_BLOB) { if (stream_blob_to_fd(fileno(f), &obj->oid, NULL, 1)) die_errno("Could not write '%s'", filename); diff --git a/builtin/grep.c b/builtin/grep.c index 623c13a939..3e4b9600e8 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -73,14 +73,14 @@ static pthread_mutex_t grep_mutex; static inline void grep_lock(void) { - if (num_threads) - pthread_mutex_lock(&grep_mutex); + assert(num_threads); + pthread_mutex_lock(&grep_mutex); } static inline void grep_unlock(void) { - if (num_threads) - pthread_mutex_unlock(&grep_mutex); + assert(num_threads); + pthread_mutex_unlock(&grep_mutex); } /* Signalled when a new work_item is added to todo. */ @@ -224,7 +224,8 @@ static void start_threads(struct grep_opt *opt) int err; struct grep_opt *o = grep_opt_dup(opt); o->output = strbuf_out; - o->debug = 0; + if (i) + o->debug = 0; compile_grep_patterns(o); err = pthread_create(&threads[i], NULL, run, o); @@ -289,8 +290,22 @@ static int grep_cmd_config(const char *var, const char *value, void *cb) if (num_threads < 0) die(_("invalid number of threads specified (%d) for %s"), num_threads, var); +#ifdef NO_PTHREADS + else if (num_threads && num_threads != 1) { + /* + * TRANSLATORS: %s is the configuration + * variable for tweaking threads, currently + * grep.threads + */ + warning(_("no threads support, ignoring %s"), var); + num_threads = 0; + } +#endif } + if (!strcmp(var, "submodule.recurse")) + recurse_submodules = git_config_bool(var, value); + return st; } @@ -495,6 +510,8 @@ static void compile_submodule_options(const struct grep_opt *opt, break; case GREP_PATTERN_TYPE_UNSPECIFIED: break; + default: + die("BUG: Added a new grep pattern type without updating switch statement"); } for (pattern = opt->pattern_list; pattern != NULL; @@ -1154,8 +1171,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix) if (!opt.fixed && opt.ignore_case) opt.regflags |= REG_ICASE; - compile_grep_patterns(&opt); - /* * We have to find "--" in a separate pass, because its presence * influences how we will parse arguments that come before it. @@ -1190,7 +1205,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix) break; } - if (get_sha1_with_context(arg, 0, oid.hash, &oc)) { + if (get_sha1_with_context(arg, GET_SHA1_RECORD_PATH, + oid.hash, &oc)) { if (seen_dashdash) die(_("unable to resolve revision: %s"), arg); break; @@ -1200,6 +1216,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) if (!seen_dashdash) verify_non_filename(prefix, arg); add_object_array_with_path(object, arg, &list, oc.mode, oc.path); + free(oc.path); } /* @@ -1226,10 +1243,23 @@ int cmd_grep(int argc, const char **argv, const char *prefix) num_threads = GREP_NUM_THREADS_DEFAULT; else if (num_threads < 0) die(_("invalid number of threads specified (%d)"), num_threads); + if (num_threads == 1) + num_threads = 0; #else + if (num_threads) + warning(_("no threads support, ignoring --threads")); num_threads = 0; #endif + if (!num_threads) + /* + * The compiled patterns on the main path are only + * used when not using threading. Otherwise + * start_threads() below calls compile_grep_patterns() + * for each thread. + */ + compile_grep_patterns(&opt); + #ifndef NO_PTHREADS if (num_threads) { if (!(opt.name_only || opt.unmatch_name_only || opt.count) diff --git a/builtin/log.c b/builtin/log.c index 4ef522ee50..998437b23d 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -483,16 +483,20 @@ static int show_blob_object(const struct object_id *oid, struct rev_info *rev, c !DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV)) return stream_blob_to_fd(1, oid, NULL, 0); - if (get_sha1_with_context(obj_name, 0, oidc.hash, &obj_context)) + if (get_sha1_with_context(obj_name, GET_SHA1_RECORD_PATH, + oidc.hash, &obj_context)) die(_("Not a valid object name %s"), obj_name); - if (!obj_context.path[0] || - !textconv_object(obj_context.path, obj_context.mode, &oidc, 1, &buf, &size)) + if (!obj_context.path || + !textconv_object(obj_context.path, obj_context.mode, &oidc, 1, &buf, &size)) { + free(obj_context.path); return stream_blob_to_fd(1, oid, NULL, 0); + } if (!buf) die(_("git show %s: bad file"), obj_name); write_or_die(1, buf, size); + free(obj_context.path); return 0; } @@ -842,8 +846,10 @@ static int open_next_file(struct commit *commit, const char *subject, if (output_directory) { strbuf_addstr(&filename, output_directory); if (filename.len >= - PATH_MAX - FORMAT_PATCH_NAME_MAX - suffix_len) + PATH_MAX - FORMAT_PATCH_NAME_MAX - suffix_len) { + strbuf_release(&filename); return error(_("name of output directory is too long")); + } strbuf_complete(&filename, '/'); } @@ -857,8 +863,11 @@ static int open_next_file(struct commit *commit, const char *subject, if (!quiet) printf("%s\n", filename.buf + outdir_offset); - if ((rev->diffopt.file = fopen(filename.buf, "w")) == NULL) - return error(_("Cannot open patch file %s"), filename.buf); + if ((rev->diffopt.file = fopen(filename.buf, "w")) == NULL) { + error_errno(_("Cannot open patch file %s"), filename.buf); + strbuf_release(&filename); + return -1; + } strbuf_release(&filename); return 0; diff --git a/builtin/merge.c b/builtin/merge.c index afaed6a2c2..84970cd85e 100644 --- a/builtin/merge.c +++ b/builtin/merge.c @@ -839,9 +839,7 @@ static int suggest_conflicts(void) struct strbuf msgbuf = STRBUF_INIT; filename = git_path_merge_msg(); - fp = fopen(filename, "a"); - if (!fp) - die_errno(_("Could not open '%s' for writing"), filename); + fp = xfopen(filename, "a"); append_conflicts_hint(&msgbuf); fputs(msgbuf.buf, fp); diff --git a/builtin/notes.c b/builtin/notes.c index 2ebc2b7c43..c939a84b76 100644 --- a/builtin/notes.c +++ b/builtin/notes.c @@ -340,8 +340,10 @@ static struct notes_tree *init_notes_check(const char *subcommand, ref = (flags & NOTES_INIT_WRITABLE) ? t->update_ref : t->ref; if (!starts_with(ref, "refs/notes/")) - /* TRANSLATORS: the first %s will be replaced by a - git notes command: 'add', 'merge', 'remove', etc.*/ + /* + * TRANSLATORS: the first %s will be replaced by a git + * notes command: 'add', 'merge', 'remove', etc. + */ die(_("refusing to %s notes in %s (outside of refs/notes/)"), subcommand, ref); return t; diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 80439047aa..f672225def 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -2483,8 +2483,10 @@ static int git_pack_config(const char *k, const char *v, void *cb) die("invalid number of threads specified (%d)", delta_search_threads); #ifdef NO_PTHREADS - if (delta_search_threads != 1) + if (delta_search_threads != 1) { warning("no threads support, ignoring %s", k); + delta_search_threads = 0; + } #endif return 0; } diff --git a/builtin/pull.c b/builtin/pull.c index 318c273eb3..69417e4f36 100644 --- a/builtin/pull.c +++ b/builtin/pull.c @@ -337,8 +337,7 @@ static void get_merge_heads(struct oid_array *merge_heads) struct strbuf sb = STRBUF_INIT; struct object_id oid; - if (!(fp = fopen(filename, "r"))) - die_errno(_("could not open '%s' for reading"), filename); + fp = xfopen(filename, "r"); while (strbuf_getline_lf(&sb, fp) != EOF) { if (get_oid_hex(sb.buf, &oid)) continue; /* invalid line: does not start with SHA1 */ @@ -772,6 +771,7 @@ int cmd_pull(int argc, const char **argv, const char *prefix) struct oid_array merge_heads = OID_ARRAY_INIT; struct object_id orig_head, curr_head; struct object_id rebase_fork_point; + int autostash; if (!getenv("GIT_REFLOG_ACTION")) set_reflog_message(argc, argv); @@ -800,8 +800,8 @@ int cmd_pull(int argc, const char **argv, const char *prefix) if (!opt_rebase && opt_autostash != -1) die(_("--[no-]autostash option is only valid with --rebase.")); + autostash = config_autostash; if (opt_rebase) { - int autostash = config_autostash; if (opt_autostash != -1) autostash = opt_autostash; @@ -862,16 +862,18 @@ int cmd_pull(int argc, const char **argv, const char *prefix) die(_("Cannot rebase onto multiple branches.")); if (opt_rebase) { - struct commit_list *list = NULL; - struct commit *merge_head, *head; - - head = lookup_commit_reference(&orig_head); - commit_list_insert(head, &list); - merge_head = lookup_commit_reference(&merge_heads.oid[0]); - if (is_descendant_of(merge_head, list)) { - /* we can fast-forward this without invoking rebase */ - opt_ff = "--ff-only"; - return run_merge(); + if (!autostash) { + struct commit_list *list = NULL; + struct commit *merge_head, *head; + + head = lookup_commit_reference(&orig_head); + commit_list_insert(head, &list); + merge_head = lookup_commit_reference(&merge_heads.oid[0]); + if (is_descendant_of(merge_head, list)) { + /* we can fast-forward this without invoking rebase */ + opt_ff = "--ff-only"; + return run_merge(); + } } return run_rebase(&curr_head, merge_heads.oid, &rebase_fork_point); } else { diff --git a/builtin/push.c b/builtin/push.c index a597759d8f..258648d5fd 100644 --- a/builtin/push.c +++ b/builtin/push.c @@ -498,6 +498,10 @@ static int git_push_config(const char *k, const char *v, void *cb) const char *value; if (!git_config_get_value("push.recursesubmodules", &value)) recurse_submodules = parse_push_recurse_submodules_arg(k, value); + } else if (!strcmp(k, "submodule.recurse")) { + int val = git_config_bool(k, v) ? + RECURSE_SUBMODULES_ON_DEMAND : RECURSE_SUBMODULES_OFF; + recurse_submodules = val; } return git_default_config(k, v, NULL); diff --git a/builtin/read-tree.c b/builtin/read-tree.c index 78d3193659..5bfd4c9f76 100644 --- a/builtin/read-tree.c +++ b/builtin/read-tree.c @@ -21,7 +21,6 @@ static int nr_trees; static int read_empty; static struct tree *trees[MAX_UNPACK_TREES]; -static int recurse_submodules = RECURSE_SUBMODULES_DEFAULT; static int list_tree(struct object_id *oid) { @@ -99,21 +98,12 @@ static int debug_merge(const struct cache_entry * const *stages, return 0; } -static int option_parse_recurse_submodules(const struct option *opt, - const char *arg, int unset) +static int git_read_tree_config(const char *var, const char *value, void *cb) { - if (unset) { - recurse_submodules = RECURSE_SUBMODULES_OFF; - return 0; - } - if (arg) - recurse_submodules = - parse_update_recurse_submodules_arg(opt->long_name, - arg); - else - recurse_submodules = RECURSE_SUBMODULES_ON; + if (!strcmp(var, "submodule.recurse")) + return git_default_submodule_config(var, value, cb); - return 0; + return git_default_config(var, value, cb); } static struct lock_file lock_file; @@ -157,9 +147,9 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix) N_("skip applying sparse checkout filter")), OPT_BOOL(0, "debug-unpack", &opts.debug_unpack, N_("debug unpack-trees")), - { OPTION_CALLBACK, 0, "recurse-submodules", &recurse_submodules, + { OPTION_CALLBACK, 0, "recurse-submodules", NULL, "checkout", "control recursive updating of submodules", - PARSE_OPT_OPTARG, option_parse_recurse_submodules }, + PARSE_OPT_OPTARG, option_parse_recurse_submodules_worktree_updater }, OPT_END() }; @@ -168,18 +158,14 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix) opts.src_index = &the_index; opts.dst_index = &the_index; - git_config(git_default_config, NULL); + git_config(git_read_tree_config, NULL); argc = parse_options(argc, argv, unused_prefix, read_tree_options, read_tree_usage, 0); - hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR); + load_submodule_cache(); - if (recurse_submodules != RECURSE_SUBMODULES_DEFAULT) { - gitmodules_config(); - git_config(submodule_config, NULL); - set_config_update_recurse_submodules(RECURSE_SUBMODULES_ON); - } + hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR); prefix_set = opts.prefix ? 1 : 0; if (1 < opts.merge + opts.reset + prefix_set) diff --git a/builtin/remote.c b/builtin/remote.c index addf97ad29..f1a88fe265 100644 --- a/builtin/remote.c +++ b/builtin/remote.c @@ -786,7 +786,7 @@ static int rm(int argc, const char **argv) strbuf_release(&buf); if (!result) - result = delete_refs(&branches, REF_NODEREF); + result = delete_refs("remote: remove", &branches, REF_NODEREF); string_list_clear(&branches, 0); if (skipped.nr) { @@ -1151,8 +1151,11 @@ static int show(int argc, const char **argv) url_nr = states.remote->url_nr; } for (i = 0; i < url_nr; i++) - /* TRANSLATORS: the colon ':' should align with - the one in " Fetch URL: %s" translation */ + /* + * TRANSLATORS: the colon ':' should align + * with the one in " Fetch URL: %s" + * translation. + */ printf_ln(_(" Push URL: %s"), url[i]); if (!i) printf_ln(_(" Push URL: %s"), _("(no URL)")); @@ -1301,7 +1304,7 @@ static int prune_remote(const char *remote, int dry_run) string_list_sort(&refs_to_prune); if (!dry_run) - result |= delete_refs(&refs_to_prune, 0); + result |= delete_refs("remote: prune", &refs_to_prune, 0); for_each_string_list_item(item, &states.stale) { const char *refname = item->util; diff --git a/builtin/reset.c b/builtin/reset.c index 430602d102..45001e5200 100644 --- a/builtin/reset.c +++ b/builtin/reset.c @@ -24,25 +24,6 @@ #include "submodule.h" #include "submodule-config.h" -static int recurse_submodules = RECURSE_SUBMODULES_DEFAULT; - -static int option_parse_recurse_submodules(const struct option *opt, - const char *arg, int unset) -{ - if (unset) { - recurse_submodules = RECURSE_SUBMODULES_OFF; - return 0; - } - if (arg) - recurse_submodules = - parse_update_recurse_submodules_arg(opt->long_name, - arg); - else - recurse_submodules = RECURSE_SUBMODULES_ON; - - return 0; -} - static const char * const git_reset_usage[] = { N_("git reset [--mixed | --soft | --hard | --merge | --keep] [-q] [<commit>]"), N_("git reset [-q] [<tree-ish>] [--] <paths>..."), @@ -284,6 +265,14 @@ static int reset_refs(const char *rev, const struct object_id *oid) return update_ref_status; } +static int git_reset_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "submodule.recurse")) + return git_default_submodule_config(var, value, cb); + + return git_default_config(var, value, cb); +} + int cmd_reset(int argc, const char **argv, const char *prefix) { int reset_type = NONE, update_ref_status = 0, quiet = 0; @@ -303,26 +292,22 @@ int cmd_reset(int argc, const char **argv, const char *prefix) N_("reset HEAD, index and working tree"), MERGE), OPT_SET_INT(0, "keep", &reset_type, N_("reset HEAD but keep local changes"), KEEP), - { OPTION_CALLBACK, 0, "recurse-submodules", &recurse_submodules, + { OPTION_CALLBACK, 0, "recurse-submodules", NULL, "reset", "control recursive updating of submodules", - PARSE_OPT_OPTARG, option_parse_recurse_submodules }, + PARSE_OPT_OPTARG, option_parse_recurse_submodules_worktree_updater }, OPT_BOOL('p', "patch", &patch_mode, N_("select hunks interactively")), OPT_BOOL('N', "intent-to-add", &intent_to_add, N_("record only the fact that removed paths will be added later")), OPT_END() }; - git_config(git_default_config, NULL); + git_config(git_reset_config, NULL); argc = parse_options(argc, argv, prefix, options, git_reset_usage, PARSE_OPT_KEEP_DASHDASH); parse_args(&pathspec, argv, prefix, patch_mode, &rev); - if (recurse_submodules != RECURSE_SUBMODULES_DEFAULT) { - gitmodules_config(); - git_config(submodule_config, NULL); - set_config_update_recurse_submodules(RECURSE_SUBMODULES_ON); - } + load_submodule_cache(); unborn = !strcmp(rev, "HEAD") && get_sha1("HEAD", oid.hash); if (unborn) { diff --git a/builtin/rm.c b/builtin/rm.c index 7c323d0123..b39f10fcb6 100644 --- a/builtin/rm.c +++ b/builtin/rm.c @@ -129,7 +129,7 @@ static int check_local_mod(struct object_id *head, int index_only) ce = active_cache[pos]; if (lstat(ce->name, &st) < 0) { - if (errno != ENOENT && errno != ENOTDIR) + if (!is_missing_file_error(errno)) warning_errno(_("failed to stat '%s'"), ce->name); /* It already vanished from the working tree */ continue; diff --git a/builtin/update-index.c b/builtin/update-index.c index ebfc09faa0..f99b1e5790 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -257,7 +257,7 @@ static int remove_one_path(const char *path) */ static int process_lstat_error(const char *path, int err) { - if (err == ENOENT || err == ENOTDIR) + if (is_missing_file_error(err)) return remove_one_path(path); return error("lstat(\"%s\"): %s", path, strerror(err)); } @@ -1341,13 +1341,18 @@ static inline int hex2chr(const char *s) struct object_context { unsigned char tree[20]; - char path[PATH_MAX]; unsigned mode; /* * symlink_path is only used by get_tree_entry_follow_symlinks, * and only for symlinks that point outside the repository. */ struct strbuf symlink_path; + /* + * If GET_SHA1_RECORD_PATH is set, this will record path (if any) + * found when resolving the name. The caller is responsible for + * releasing the memory. + */ + char *path; }; #define GET_SHA1_QUIETLY 01 @@ -1357,6 +1362,7 @@ struct object_context { #define GET_SHA1_TREEISH 020 #define GET_SHA1_BLOB 040 #define GET_SHA1_FOLLOW_SYMLINKS 0100 +#define GET_SHA1_RECORD_PATH 0200 #define GET_SHA1_ONLY_TO_DIE 04000 #define GET_SHA1_DISAMBIGUATORS \ @@ -1371,7 +1377,7 @@ extern int get_sha1_tree(const char *str, unsigned char *sha1); extern int get_sha1_treeish(const char *str, unsigned char *sha1); extern int get_sha1_blob(const char *str, unsigned char *sha1); extern void maybe_die_on_misspelt_object_name(const char *name, const char *prefix); -extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc); +extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *oc); extern int get_oid(const char *str, struct object_id *oid); @@ -168,7 +168,7 @@ bad_graft_data: static int read_graft_file(const char *graft_file) { - FILE *fp = fopen(graft_file, "r"); + FILE *fp = fopen_or_warn(graft_file, "r"); struct strbuf buf = STRBUF_INIT; if (!fp) return -1; diff --git a/compat/fopen.c b/compat/fopen.c index b5ca142fed..107b3e8182 100644 --- a/compat/fopen.c +++ b/compat/fopen.c @@ -1,14 +1,14 @@ /* * The order of the following two lines is important. * - * FREAD_READS_DIRECTORIES is undefined before including git-compat-util.h + * SUPPRESS_FOPEN_REDEFINITION is defined before including git-compat-util.h * to avoid the redefinition of fopen within git-compat-util.h. This is * necessary since fopen is a macro on some platforms which may be set * based on compiler options. For example, on AIX fopen is set to fopen64 * when _LARGE_FILES is defined. The previous technique of merely undefining * fopen after including git-compat-util.h is inadequate in this case. */ -#undef FREAD_READS_DIRECTORIES +#define SUPPRESS_FOPEN_REDEFINITION #include "../git-compat-util.h" FILE *git_fopen(const char *path, const char *mode) diff --git a/compat/mingw.c b/compat/mingw.c index fe0e3ccd24..8b6fa0db44 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -423,6 +423,8 @@ FILE *mingw_fopen (const char *filename, const char *otype) return NULL; } file = _wfopen(wfilename, wotype); + if (!file && GetLastError() == ERROR_INVALID_NAME) + errno = ENOENT; if (file && hide && set_hidden_flag(wfilename, 1)) warning("could not mark '%s' as hidden.", filename); return file; @@ -941,66 +943,14 @@ static const char *parse_interpreter(const char *cmd) } /* - * Splits the PATH into parts. - */ -static char **get_path_split(void) -{ - char *p, **path, *envpath = mingw_getenv("PATH"); - int i, n = 0; - - if (!envpath || !*envpath) - return NULL; - - envpath = xstrdup(envpath); - p = envpath; - while (p) { - char *dir = p; - p = strchr(p, ';'); - if (p) *p++ = '\0'; - if (*dir) { /* not earlier, catches series of ; */ - ++n; - } - } - if (!n) { - free(envpath); - return NULL; - } - - ALLOC_ARRAY(path, n + 1); - p = envpath; - i = 0; - do { - if (*p) - path[i++] = xstrdup(p); - p = p+strlen(p)+1; - } while (i < n); - path[i] = NULL; - - free(envpath); - - return path; -} - -static void free_path_split(char **path) -{ - char **p = path; - - if (!path) - return; - - while (*p) - free(*p++); - free(path); -} - -/* * exe_only means that we only want to detect .exe files, but not scripts * (which do not have an extension) */ -static char *lookup_prog(const char *dir, const char *cmd, int isexe, int exe_only) +static char *lookup_prog(const char *dir, int dirlen, const char *cmd, + int isexe, int exe_only) { char path[MAX_PATH]; - snprintf(path, sizeof(path), "%s/%s.exe", dir, cmd); + snprintf(path, sizeof(path), "%.*s\\%s.exe", dirlen, dir, cmd); if (!isexe && access(path, F_OK) == 0) return xstrdup(path); @@ -1015,17 +965,29 @@ static char *lookup_prog(const char *dir, const char *cmd, int isexe, int exe_on * Determines the absolute path of cmd using the split path in path. * If cmd contains a slash or backslash, no lookup is performed. */ -static char *path_lookup(const char *cmd, char **path, int exe_only) +static char *path_lookup(const char *cmd, int exe_only) { + const char *path; char *prog = NULL; int len = strlen(cmd); int isexe = len >= 4 && !strcasecmp(cmd+len-4, ".exe"); if (strchr(cmd, '/') || strchr(cmd, '\\')) - prog = xstrdup(cmd); + return xstrdup(cmd); - while (!prog && *path) - prog = lookup_prog(*path++, cmd, isexe, exe_only); + path = mingw_getenv("PATH"); + if (!path) + return NULL; + + while (!prog) { + const char *sep = strchrnul(path, ';'); + int dirlen = sep - path; + if (dirlen) + prog = lookup_prog(path, dirlen, cmd, isexe, exe_only); + if (!*sep) + break; + path = sep + 1; + } return prog; } @@ -1192,8 +1154,7 @@ pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **deltaenv, int fhin, int fhout, int fherr) { pid_t pid; - char **path = get_path_split(); - char *prog = path_lookup(cmd, path, 0); + char *prog = path_lookup(cmd, 0); if (!prog) { errno = ENOENT; @@ -1204,7 +1165,7 @@ pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **deltaenv, if (interpr) { const char *argv0 = argv[0]; - char *iprog = path_lookup(interpr, path, 1); + char *iprog = path_lookup(interpr, 1); argv[0] = prog; if (!iprog) { errno = ENOENT; @@ -1222,21 +1183,18 @@ pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **deltaenv, fhin, fhout, fherr); free(prog); } - free_path_split(path); return pid; } static int try_shell_exec(const char *cmd, char *const *argv) { const char *interpr = parse_interpreter(cmd); - char **path; char *prog; int pid = 0; if (!interpr) return 0; - path = get_path_split(); - prog = path_lookup(interpr, path, 1); + prog = path_lookup(interpr, 1); if (prog) { int argc = 0; const char **argv2; @@ -1255,7 +1213,6 @@ static int try_shell_exec(const char *cmd, char *const *argv) free(prog); free(argv2); } - free_path_split(path); return pid; } @@ -1277,8 +1234,7 @@ int mingw_execv(const char *cmd, char *const *argv) int mingw_execvp(const char *cmd, char *const *argv) { - char **path = get_path_split(); - char *prog = path_lookup(cmd, path, 0); + char *prog = path_lookup(cmd, 0); if (prog) { mingw_execv(prog, argv); @@ -1286,7 +1242,6 @@ int mingw_execvp(const char *cmd, char *const *argv) } else errno = ENOENT; - free_path_split(path); return -1; } diff --git a/compat/mingw.h b/compat/mingw.h index 3350169555..e03aecfe2e 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -398,7 +398,11 @@ HANDLE winansi_get_osfhandle(int fd); (isalpha(*(path)) && (path)[1] == ':' ? 2 : 0) int mingw_skip_dos_drive_prefix(char **path); #define skip_dos_drive_prefix mingw_skip_dos_drive_prefix -#define is_dir_sep(c) ((c) == '/' || (c) == '\\') +static inline int mingw_is_dir_sep(int c) +{ + return c == '/' || c == '\\'; +} +#define is_dir_sep mingw_is_dir_sep static inline char *mingw_find_last_dir_sep(const char *path) { char *ret = NULL; @@ -1438,7 +1438,7 @@ int git_config_from_file(config_fn_t fn, const char *filename, void *data) int ret = -1; FILE *f; - f = fopen(filename, "r"); + f = fopen_or_warn(filename, "r"); if (f) { flockfile(f); ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename, filename, f, data); @@ -2656,6 +2656,9 @@ int git_config_rename_section_in_file(const char *config_filename, } if (!(config_file = fopen(config_filename, "rb"))) { + ret = warn_on_fopen_errors(config_filename); + if (ret) + goto out; /* no config file means nothing to rename, no error */ goto commit_and_out; } diff --git a/config.mak.uname b/config.mak.uname index 192629f143..adfb90b601 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -36,6 +36,7 @@ ifeq ($(uname_S),Linux) NEEDS_LIBRT = YesPlease HAVE_GETDELIM = YesPlease SANE_TEXT_GREP=-a + FREAD_READS_DIRECTORIES = UnfortunatelyYes endif ifeq ($(uname_S),GNU/kFreeBSD) HAVE_ALLOCA_H = YesPlease @@ -43,6 +44,7 @@ ifeq ($(uname_S),GNU/kFreeBSD) HAVE_PATHS_H = YesPlease DIR_HAS_BSD_GROUP_SEMANTICS = YesPlease LIBC_CONTAINS_LIBINTL = YesPlease + FREAD_READS_DIRECTORIES = UnfortunatelyYes endif ifeq ($(uname_S),UnixWare) CC = cc @@ -108,6 +110,7 @@ ifeq ($(uname_S),Darwin) BASIC_CFLAGS += -DPRECOMPOSE_UNICODE BASIC_CFLAGS += -DPROTECT_HFS_DEFAULT=1 HAVE_BSD_SYSCTL = YesPlease + FREAD_READS_DIRECTORIES = UnfortunatelyYes endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease @@ -201,6 +204,7 @@ ifeq ($(uname_S),FreeBSD) GMTIME_UNRELIABLE_ERRORS = UnfortunatelyYes HAVE_BSD_SYSCTL = YesPlease PAGER_ENV = LESS=FRX LV=-c MORE=FRX + FREAD_READS_DIRECTORIES = UnfortunatelyYes endif ifeq ($(uname_S),OpenBSD) NO_STRCASESTR = YesPlease @@ -551,6 +555,7 @@ else NO_GETTEXT = USE_GETTEXT_SCHEME = fallthrough USE_LIBPCRE= YesPlease + NO_LIBPCRE1_JIT = UnfortunatelyYes NO_CURL = USE_NED_ALLOCATOR = YesPlease else diff --git a/configure.ac b/configure.ac index 128165529f..11d083fbe0 100644 --- a/configure.ac +++ b/configure.ac @@ -250,24 +250,66 @@ AS_HELP_STRING([--with-openssl],[use OpenSSL library (default is YES)]) AS_HELP_STRING([], [ARG can be prefix for openssl library and headers]), GIT_PARSE_WITH([openssl])) -# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be -# able to use Perl-compatible regular expressions. +# Define USE_LIBPCRE if you have and want to use libpcre. Various +# commands such as log and grep offer runtime options to use +# Perl-compatible regular expressions instead of standard or extended +# POSIX regular expressions. # -# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in +# Currently USE_LIBPCRE is a synonym for USE_LIBPCRE1, define +# USE_LIBPCRE2 instead if you'd like to use version 2 of the PCRE +# library. The USE_LIBPCRE flag will likely be changed to mean v2 by +# default in future releases. +# +# Define LIBPCREDIR=/foo/bar if your PCRE header and library files are in # /foo/bar/include and /foo/bar/lib directories. # AC_ARG_WITH(libpcre, -AS_HELP_STRING([--with-libpcre],[support Perl-compatible regexes (default is NO)]) +AS_HELP_STRING([--with-libpcre],[synonym for --with-libpcre1]), + if test "$withval" = "no"; then + USE_LIBPCRE1= + elif test "$withval" = "yes"; then + USE_LIBPCRE1=YesPlease + else + USE_LIBPCRE1=YesPlease + LIBPCREDIR=$withval + AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR]) + dnl USE_LIBPCRE1 can still be modified below, so don't substitute + dnl it yet. + GIT_CONF_SUBST([LIBPCREDIR]) + fi) + +AC_ARG_WITH(libpcre1, +AS_HELP_STRING([--with-libpcre1],[support Perl-compatible regexes via libpcre1 (default is NO)]) +AS_HELP_STRING([], [ARG can be also prefix for libpcre library and headers]), + if test "$withval" = "no"; then + USE_LIBPCRE1= + elif test "$withval" = "yes"; then + USE_LIBPCRE1=YesPlease + else + USE_LIBPCRE1=YesPlease + LIBPCREDIR=$withval + AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR]) + dnl USE_LIBPCRE1 can still be modified below, so don't substitute + dnl it yet. + GIT_CONF_SUBST([LIBPCREDIR]) + fi) + +AC_ARG_WITH(libpcre2, +AS_HELP_STRING([--with-libpcre2],[support Perl-compatible regexes via libpcre2 (default is NO)]) AS_HELP_STRING([], [ARG can be also prefix for libpcre library and headers]), + if test -n "$USE_LIBPCRE1"; then + AC_MSG_ERROR([Only supply one of --with-libpcre1 or --with-libpcre2!]) + fi + if test "$withval" = "no"; then - USE_LIBPCRE= + USE_LIBPCRE2= elif test "$withval" = "yes"; then - USE_LIBPCRE=YesPlease + USE_LIBPCRE2=YesPlease else - USE_LIBPCRE=YesPlease + USE_LIBPCRE2=YesPlease LIBPCREDIR=$withval AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR]) - dnl USE_LIBPCRE can still be modified below, so don't substitute + dnl USE_LIBPCRE2 can still be modified below, so don't substitute dnl it yet. GIT_CONF_SUBST([LIBPCREDIR]) fi) @@ -499,11 +541,11 @@ GIT_CONF_SUBST([NEEDS_SSL_WITH_CRYPTO]) GIT_CONF_SUBST([NO_OPENSSL]) # -# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be -# able to use Perl-compatible regular expressions. +# Handle the USE_LIBPCRE1 and USE_LIBPCRE2 options potentially set +# above. # -if test -n "$USE_LIBPCRE"; then +if test -n "$USE_LIBPCRE1"; then GIT_STASH_FLAGS($LIBPCREDIR) @@ -513,7 +555,22 @@ AC_CHECK_LIB([pcre], [pcre_version], GIT_UNSTASH_FLAGS($LIBPCREDIR) -GIT_CONF_SUBST([USE_LIBPCRE]) +GIT_CONF_SUBST([USE_LIBPCRE1]) + +fi + + +if test -n "$USE_LIBPCRE2"; then + +GIT_STASH_FLAGS($LIBPCREDIR) + +AC_CHECK_LIB([pcre2-8], [pcre2_config_8], +[USE_LIBPCRE2=YesPlease], +[USE_LIBPCRE2=]) + +GIT_UNSTASH_FLAGS($LIBPCREDIR) + +GIT_CONF_SUBST([USE_LIBPCRE2]) fi @@ -71,7 +71,7 @@ static void parse_one_symref_info(struct string_list *symref, const char *val, i check_refname_format(target, REFNAME_ALLOW_ONELEVEL)) /* "symref=bogus:pair */ goto reject; - item = string_list_append(symref, sym); + item = string_list_append_nodup(symref, sym); item->util = target; return; reject: diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index 45a78a0953..48a2f26622 100644 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -2336,14 +2336,23 @@ _git_config () esac __gitcomp " add.ignoreErrors + advice.amWorkDir advice.commitBeforeMerge advice.detachedHead advice.implicitIdentity - advice.pushNonFastForward + advice.pushAlreadyExists + advice.pushFetchFirst + advice.pushNeedsForce + advice.pushNonFFCurrent + advice.pushNonFFMatching + advice.pushUpdateRejected advice.resolveConflict + advice.rmHints advice.statusHints + advice.statusUoption alias. am.keepcr + am.threeWay apply.ignorewhitespace apply.whitespace branch.autosetupmerge @@ -2395,14 +2404,19 @@ _git_config () color.status.untracked color.status.updated color.ui + commit.cleanup + commit.gpgSign commit.status commit.template + commit.verbose core.abbrev core.askpass core.attributesfile core.autocrlf core.bare core.bigFileThreshold + core.checkStat + core.commentChar core.compression core.createObject core.deltaBaseCacheLimit @@ -2412,6 +2426,8 @@ _git_config () core.fileMode core.fsyncobjectfiles core.gitProxy + core.hideDotFiles + core.hooksPath core.ignoreStat core.ignorecase core.logAllRefUpdates @@ -2419,20 +2435,30 @@ _git_config () core.notesRef core.packedGitLimit core.packedGitWindowSize + core.packedRefsTimeout core.pager + core.precomposeUnicode core.preferSymlinkRefs core.preloadindex + core.protectHFS + core.protectNTFS core.quotepath core.repositoryFormatVersion core.safecrlf core.sharedRepository core.sparseCheckout + core.splitIndex + core.sshCommand core.symlinks core.trustctime core.untrackedCache core.warnAmbiguousRefs core.whitespace core.worktree + credential.helper + credential.useHttpPath + credential.username + credentialCache.ignoreSIGHUP diff.autorefreshindex diff.external diff.ignoreSubmodules @@ -2464,15 +2490,19 @@ _git_config () format.thread format.to gc. + gc.aggressiveDepth gc.aggressiveWindow gc.auto + gc.autoDetach gc.autopacklimit + gc.logExpiry gc.packrefs gc.pruneexpire gc.reflogexpire gc.reflogexpireunreachable gc.rerereresolved gc.rerereunresolved + gc.worktreePruneExpire gitcvs.allbinary gitcvs.commitmsgannotation gitcvs.dbTableNamePrefix diff --git a/contrib/persistent-https/README b/contrib/persistent-https/README index f784dd2e66..7c4cd8d257 100644 --- a/contrib/persistent-https/README +++ b/contrib/persistent-https/README @@ -35,6 +35,16 @@ to use persistent-https: [url "persistent-http"] insteadof = http +You may also want to allow the use of the persistent-https helper for +submodule URLs (since any https URLs pointing to submodules will be +rewritten, and Git's out-of-the-box defaults forbid submodules from +using unknown remote helpers): + +[protocol "persistent-https"] + allow = always +[protocol "persistent-http"] + allow = always + ##################################################################### # BUILDING FROM SOURCE diff --git a/diff-lib.c b/diff-lib.c index 9e076a4886..0c0e20f7c0 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -29,7 +29,7 @@ static int check_removed(const struct cache_entry *ce, struct stat *st) { if (lstat(ce->name, st) < 0) { - if (errno != ENOENT && errno != ENOTDIR) + if (!is_missing_file_error(errno)) return -1; return 1; } @@ -27,7 +27,7 @@ #endif static int diff_detect_rename_default; -static int diff_indent_heuristic; /* experimental */ +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; @@ -290,9 +290,6 @@ int git_diff_ui_config(const char *var, const char *value, void *cb) return 0; } - if (git_diff_heuristic_config(var, value, cb) < 0) - return -1; - if (!strcmp(var, "diff.wserrorhighlight")) { int val = parse_ws_error_highlight(value); if (val < 0) @@ -351,6 +348,9 @@ int git_diff_basic_config(const char *var, const char *value, void *cb) if (starts_with(var, "submodule.")) return parse_submodule_config_option(var, value); + if (git_diff_heuristic_config(var, value, cb) < 0) + return -1; + return git_default_config(var, value, cb); } @@ -4071,9 +4071,7 @@ int diff_opt_parse(struct diff_options *options, DIFF_OPT_CLR(options, FUNCCONTEXT); else if ((argcount = parse_long_opt("output", av, &optarg))) { char *path = prefix_filename(prefix, optarg); - options->file = fopen(path, "w"); - if (!options->file) - die_errno("Could not open '%s'", path); + options->file = xfopen(path, "w"); options->close_file = 1; if (options->use_color != GIT_COLOR_ALWAYS) options->use_color = GIT_COLOR_NEVER; @@ -4807,9 +4805,7 @@ void diff_flush(struct diff_options *options) */ if (options->close_file) fclose(options->file); - options->file = fopen("/dev/null", "w"); - if (!options->file) - die_errno("Could not open /dev/null"); + options->file = xfopen("/dev/null", "w"); options->close_file = 1; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; @@ -5270,6 +5266,29 @@ size_t fill_textconv(struct userdiff_driver *driver, return size; } +int textconv_object(const char *path, + unsigned mode, + const struct object_id *oid, + int oid_valid, + char **buf, + unsigned long *buf_size) +{ + struct diff_filespec *df; + struct userdiff_driver *textconv; + + df = alloc_filespec(path); + fill_filespec(df, oid, oid_valid, mode); + textconv = get_textconv(df); + if (!textconv) { + free_filespec(df); + return 0; + } + + *buf_size = fill_textconv(textconv, df, buf); + free_filespec(df); + return 1; +} + void setup_diff_pager(struct diff_options *opt) { /* @@ -385,6 +385,13 @@ extern size_t fill_textconv(struct userdiff_driver *driver, */ extern struct userdiff_driver *get_textconv(struct diff_filespec *one); +/* + * Prepare diff_filespec and convert it using diff textconv API + * if the textconv driver exists. + * Return 1 if the conversion succeeds, 0 otherwise. + */ +extern int textconv_object(const char *path, unsigned mode, const struct object_id *oid, int oid_valid, char **buf, unsigned long *buf_size); + extern int parse_rename_score(const char **cp_p); extern long parse_algorithm_value(const char *value); @@ -752,9 +752,9 @@ static int add_excludes(const char *fname, const char *base, int baselen, fd = open(fname, O_RDONLY); if (fd < 0 || fstat(fd, &st) < 0) { - if (errno != ENOENT) - warn_on_inaccessible(fname); - if (0 <= fd) + if (fd < 0) + warn_on_fopen_errors(fname); + else close(fd); if (!istate || (buf = read_skip_worktree_file_from_index(istate, fname, &size, sha1_stat)) == NULL) @@ -1813,7 +1813,10 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, dir_state = state; /* recurse into subdir if instructed by treat_path */ - if (state == path_recurse) { + if ((state == path_recurse) || + ((state == path_untracked) && + (dir->flags & DIR_SHOW_IGNORED_TOO) && + (get_dtype(cdir.de, istate, path.buf, path.len) == DT_DIR))) { struct untracked_cache_dir *ud; ud = lookup_untracked(dir->untracked, untracked, path.buf + baselen, @@ -1868,7 +1871,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, return dir_state; } -static int cmp_name(const void *p1, const void *p2) +int cmp_dir_entry(const void *p1, const void *p2) { const struct dir_entry *e1 = *(const struct dir_entry **)p1; const struct dir_entry *e2 = *(const struct dir_entry **)p2; @@ -1876,6 +1879,14 @@ static int cmp_name(const void *p1, const void *p2) return name_compare(e1->name, e1->len, e2->name, e2->len); } +/* check if *out lexically strictly contains *in */ +int check_dir_entry_contains(const struct dir_entry *out, const struct dir_entry *in) +{ + return (out->len < in->len) && + (out->name[out->len - 1] == '/') && + !memcmp(out->name, in->name, out->len); +} + static int treat_leading_path(struct dir_struct *dir, struct index_state *istate, const char *path, int len, @@ -2090,8 +2101,32 @@ int read_directory(struct dir_struct *dir, struct index_state *istate, dir->untracked = NULL; if (!len || treat_leading_path(dir, istate, path, len, pathspec)) read_directory_recursive(dir, istate, path, len, untracked, 0, pathspec); - QSORT(dir->entries, dir->nr, cmp_name); - QSORT(dir->ignored, dir->ignored_nr, cmp_name); + QSORT(dir->entries, dir->nr, cmp_dir_entry); + QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry); + + /* + * If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will + * also pick up untracked contents of untracked dirs; by default + * we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not. + */ + if ((dir->flags & DIR_SHOW_IGNORED_TOO) && + !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) { + int i, j; + + /* remove from dir->entries untracked contents of untracked dirs */ + for (i = j = 0; j < dir->nr; j++) { + if (i && + check_dir_entry_contains(dir->entries[i - 1], dir->entries[j])) { + free(dir->entries[j]); + dir->entries[j] = NULL; + } else { + dir->entries[i++] = dir->entries[j]; + } + } + + dir->nr = i; + } + if (dir->untracked) { static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS); trace_printf_key(&trace_untracked_stats, @@ -2302,7 +2337,7 @@ int remove_path(const char *name) { char *slash; - if (unlink(name) && errno != ENOENT && errno != ENOTDIR) + if (unlink(name) && !is_missing_file_error(errno)) return -1; slash = strrchr(name, '/'); @@ -151,7 +151,8 @@ struct dir_struct { DIR_NO_GITLINKS = 1<<3, DIR_COLLECT_IGNORED = 1<<4, DIR_SHOW_IGNORED_TOO = 1<<5, - DIR_COLLECT_KILLED_ONLY = 1<<6 + DIR_COLLECT_KILLED_ONLY = 1<<6, + DIR_KEEP_UNTRACKED_CONTENTS = 1<<7 } flags; struct dir_entry **entries; struct dir_entry **ignored; @@ -337,6 +338,9 @@ static inline int dir_path_match(const struct dir_entry *ent, has_trailing_dir); } +int cmp_dir_entry(const void *p1, const void *p2); +int check_dir_entry_contains(const struct dir_entry *out, const struct dir_entry *in); + void untracked_cache_invalidate_path(struct index_state *, const char *); void untracked_cache_remove_from_index(struct index_state *, const char *); void untracked_cache_add_to_index(struct index_state *, const char *); diff --git a/fast-import.c b/fast-import.c index e69d219682..9a22fc92c0 100644 --- a/fast-import.c +++ b/fast-import.c @@ -3285,9 +3285,7 @@ static void option_export_pack_edges(const char *edges) { if (pack_edges) fclose(pack_edges); - pack_edges = fopen(edges, "a"); - if (!pack_edges) - die_errno("Cannot open '%s'", edges); + pack_edges = xfopen(edges, "a"); } static int parse_one_option(const char *option) diff --git a/git-add--interactive.perl b/git-add--interactive.perl index 709a5f6ce6..79d675b5b0 100755 --- a/git-add--interactive.perl +++ b/git-add--interactive.perl @@ -46,7 +46,6 @@ my ($diff_new_color) = my $normal_color = $repo->get_color("", "reset"); my $diff_algorithm = $repo->config('diff.algorithm'); -my $diff_indent_heuristic = $repo->config_bool('diff.indentheuristic'); my $diff_filter = $repo->config('interactive.difffilter'); my $use_readkey = 0; @@ -730,9 +729,6 @@ sub parse_diff { if (defined $diff_algorithm) { splice @diff_cmd, 1, 0, "--diff-algorithm=${diff_algorithm}"; } - if ($diff_indent_heuristic) { - splice @diff_cmd, 1, 0, "--indent-heuristic"; - } if (defined $patch_mode_revision) { push @diff_cmd, get_diff_reference($patch_mode_revision); } diff --git a/git-compat-util.h b/git-compat-util.h index 4b7dcf21ad..51ba4e6b3b 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -693,10 +693,12 @@ char *gitstrdup(const char *s); #endif #ifdef FREAD_READS_DIRECTORIES -#ifdef fopen -#undef fopen -#endif -#define fopen(a,b) git_fopen(a,b) +# if !defined(SUPPRESS_FOPEN_REDEFINITION) +# ifdef fopen +# undef fopen +# endif +# define fopen(a,b) git_fopen(a,b) +# endif extern FILE *git_fopen(const char*, const char*); #endif @@ -804,6 +806,7 @@ extern int xmkstemp(char *template); extern int xmkstemp_mode(char *template, int mode); extern char *xgetcwd(void); extern FILE *fopen_for_writing(const char *path); +extern FILE *fopen_or_warn(const char *path, const char *mode); #define ALLOC_ARRAY(x, alloc) (x) = xmalloc(st_mult(sizeof(*(x)), (alloc))) #define REALLOC_ARRAY(x, alloc) (x) = xrealloc((x), st_mult(sizeof(*(x)), (alloc))) @@ -1110,8 +1113,8 @@ int remove_or_warn(unsigned int mode, const char *path); int access_or_warn(const char *path, int mode, unsigned flag); int access_or_die(const char *path, int mode, unsigned flag); -/* Warn on an inaccessible file that ought to be accessible */ -void warn_on_inaccessible(const char *path); +/* Warn on an inaccessible file if errno indicates this is an error */ +int warn_on_fopen_errors(const char *path); #ifdef GMTIME_UNRELIABLE_ERRORS struct tm *git_gmtime(const time_t *); @@ -1134,6 +1137,21 @@ struct tm *git_gmtime_r(const time_t *, struct tm *); #define getc_unlocked(fh) getc(fh) #endif +/* + * Our code often opens a path to an optional file, to work on its + * contents when we can successfully open it. We can ignore a failure + * to open if such an optional file does not exist, but we do want to + * report a failure in opening for other reasons (e.g. we got an I/O + * error, or the file is there, but we lack the permission to open). + * + * Call this function after seeing an error from open() or fopen() to + * see if the errno indicates a missing file that we can safely ignore. + */ +static inline int is_missing_file_error(int errno_) +{ + return (errno_ == ENOENT || errno_ == ENOTDIR); +} + extern int cmd_main(int, const char **); #endif diff --git a/git-send-email.perl b/git-send-email.perl index f0417f64e7..7fd5874436 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -1355,7 +1355,7 @@ EOF } require Net::SMTP; - my $use_net_smtp_ssl = version->parse($Net::SMTP::VERSION) < version->parse("1.28"); + my $use_net_smtp_ssl = version->parse($Net::SMTP::VERSION) < version->parse("2.34"); $smtp_domain ||= maildomain(); if ($smtp_encryption eq 'ssl') { @@ -1755,21 +1755,23 @@ sub unique_email_list { sub validate_patch { my $fn = shift; - my $validate_hook = catfile(catdir($repo->repo_path(), 'hooks'), - 'sendemail-validate'); - my $hook_error; - if (-x $validate_hook) { - my $target = abs_path($fn); - # The hook needs a correct cwd and GIT_DIR. - my $cwd_save = cwd(); - chdir($repo->wc_path() or $repo->repo_path()) - or die("chdir: $!"); - local $ENV{"GIT_DIR"} = $repo->repo_path(); - $hook_error = "rejected by sendemail-validate hook" - if system($validate_hook, $target); - chdir($cwd_save) or die("chdir: $!"); - } - return $hook_error if $hook_error; + if ($repo) { + my $validate_hook = catfile(catdir($repo->repo_path(), 'hooks'), + 'sendemail-validate'); + my $hook_error; + if (-x $validate_hook) { + my $target = abs_path($fn); + # The hook needs a correct cwd and GIT_DIR. + my $cwd_save = cwd(); + chdir($repo->wc_path() or $repo->repo_path()) + or die("chdir: $!"); + local $ENV{"GIT_DIR"} = $repo->repo_path(); + $hook_error = "rejected by sendemail-validate hook" + if system($validate_hook, $target); + chdir($cwd_save) or die("chdir: $!"); + } + return $hook_error if $hook_error; + } open(my $fh, '<', $fn) or die sprintf(__("unable to open %s: %s\n"), $fn, $!); @@ -178,26 +178,38 @@ static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, st case GREP_PATTERN_TYPE_BRE: opt->fixed = 0; - opt->pcre = 0; - opt->regflags &= ~REG_EXTENDED; + opt->pcre1 = 0; + opt->pcre2 = 0; break; case GREP_PATTERN_TYPE_ERE: opt->fixed = 0; - opt->pcre = 0; + opt->pcre1 = 0; + opt->pcre2 = 0; opt->regflags |= REG_EXTENDED; break; case GREP_PATTERN_TYPE_FIXED: opt->fixed = 1; - opt->pcre = 0; - opt->regflags &= ~REG_EXTENDED; + opt->pcre1 = 0; + opt->pcre2 = 0; break; case GREP_PATTERN_TYPE_PCRE: opt->fixed = 0; - opt->pcre = 1; - opt->regflags &= ~REG_EXTENDED; +#ifdef USE_LIBPCRE2 + opt->pcre1 = 0; + opt->pcre2 = 1; +#else + /* + * It's important that pcre1 always be assigned to + * even when there's no USE_LIBPCRE* defined. We still + * call the PCRE stub function, it just dies with + * "cannot use Perl-compatible regexes[...]". + */ + opt->pcre1 = 1; + opt->pcre2 = 0; +#endif break; } } @@ -324,8 +336,32 @@ static NORETURN void compile_regexp_failed(const struct grep_pat *p, die("%s'%s': %s", where, p->pattern, error); } -#ifdef USE_LIBPCRE -static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) +static int is_fixed(const char *s, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (is_regex_special(s[i])) + return 0; + } + + return 1; +} + +static int has_null(const char *s, size_t len) +{ + /* + * regcomp cannot accept patterns with NULs so when using it + * we consider any pattern containing a NUL fixed. + */ + if (memchr(s, 0, len)) + return 1; + + return 0; +} + +#ifdef USE_LIBPCRE1 +static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) { const char *error; int erroffset; @@ -333,23 +369,36 @@ static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) if (opt->ignore_case) { if (has_non_ascii(p->pattern)) - p->pcre_tables = pcre_maketables(); + p->pcre1_tables = pcre_maketables(); options |= PCRE_CASELESS; } if (is_utf8_locale() && has_non_ascii(p->pattern)) options |= PCRE_UTF8; - p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset, - p->pcre_tables); - if (!p->pcre_regexp) + p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset, + p->pcre1_tables); + if (!p->pcre1_regexp) compile_regexp_failed(p, error); - p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error); - if (!p->pcre_extra_info && error) + p->pcre1_extra_info = pcre_study(p->pcre1_regexp, PCRE_STUDY_JIT_COMPILE, &error); + if (!p->pcre1_extra_info && error) die("%s", error); + +#ifdef GIT_PCRE1_USE_JIT + pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on); + if (p->pcre1_jit_on == 1) { + p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024); + if (!p->pcre1_jit_stack) + die("Couldn't allocate PCRE JIT stack"); + pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack); + } else if (p->pcre1_jit_on != 0) { + die("BUG: The pcre1_jit_on variable should be 0 or 1, not %d", + p->pcre1_jit_on); + } +#endif } -static int pcrematch(struct grep_pat *p, const char *line, const char *eol, +static int pcre1match(struct grep_pat *p, const char *line, const char *eol, regmatch_t *match, int eflags) { int ovector[30], ret, flags = 0; @@ -357,8 +406,19 @@ static int pcrematch(struct grep_pat *p, const char *line, const char *eol, if (eflags & REG_NOTBOL) flags |= PCRE_NOTBOL; - ret = pcre_exec(p->pcre_regexp, p->pcre_extra_info, line, eol - line, - 0, flags, ovector, ARRAY_SIZE(ovector)); +#ifdef GIT_PCRE1_USE_JIT + if (p->pcre1_jit_on) { + ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line, + eol - line, 0, flags, ovector, + ARRAY_SIZE(ovector), p->pcre1_jit_stack); + } else +#endif + { + ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, + eol - line, 0, flags, ovector, + ARRAY_SIZE(ovector)); + } + if (ret < 0 && ret != PCRE_ERROR_NOMATCH) die("pcre_exec failed with error code %d", ret); if (ret > 0) { @@ -370,55 +430,165 @@ static int pcrematch(struct grep_pat *p, const char *line, const char *eol, return ret; } -static void free_pcre_regexp(struct grep_pat *p) +static void free_pcre1_regexp(struct grep_pat *p) { - pcre_free(p->pcre_regexp); - pcre_free(p->pcre_extra_info); - pcre_free((void *)p->pcre_tables); + pcre_free(p->pcre1_regexp); +#ifdef GIT_PCRE1_USE_JIT + if (p->pcre1_jit_on) { + pcre_free_study(p->pcre1_extra_info); + pcre_jit_stack_free(p->pcre1_jit_stack); + } else +#endif + { + pcre_free(p->pcre1_extra_info); + } + pcre_free((void *)p->pcre1_tables); } -#else /* !USE_LIBPCRE */ -static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) +#else /* !USE_LIBPCRE1 */ +static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) { die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); } -static int pcrematch(struct grep_pat *p, const char *line, const char *eol, +static int pcre1match(struct grep_pat *p, const char *line, const char *eol, regmatch_t *match, int eflags) { return 1; } -static void free_pcre_regexp(struct grep_pat *p) +static void free_pcre1_regexp(struct grep_pat *p) { } -#endif /* !USE_LIBPCRE */ +#endif /* !USE_LIBPCRE1 */ -static int is_fixed(const char *s, size_t len) +#ifdef USE_LIBPCRE2 +static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { - size_t i; + int error; + PCRE2_UCHAR errbuf[256]; + PCRE2_SIZE erroffset; + int options = PCRE2_MULTILINE; + const uint8_t *character_tables = NULL; + int jitret; - /* regcomp cannot accept patterns with NULs so we - * consider any pattern containing a NUL fixed. - */ - if (memchr(s, 0, len)) - return 1; + assert(opt->pcre2); - for (i = 0; i < len; i++) { - if (is_regex_special(s[i])) - return 0; + p->pcre2_compile_context = NULL; + + if (opt->ignore_case) { + if (has_non_ascii(p->pattern)) { + character_tables = pcre2_maketables(NULL); + p->pcre2_compile_context = pcre2_compile_context_create(NULL); + pcre2_set_character_tables(p->pcre2_compile_context, character_tables); + } + options |= PCRE2_CASELESS; + } + if (is_utf8_locale() && has_non_ascii(p->pattern)) + options |= PCRE2_UTF; + + p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern, + p->patternlen, options, &error, &erroffset, + p->pcre2_compile_context); + + if (p->pcre2_pattern) { + p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL); + if (!p->pcre2_match_data) + die("Couldn't allocate PCRE2 match data"); + } else { + pcre2_get_error_message(error, errbuf, sizeof(errbuf)); + compile_regexp_failed(p, (const char *)&errbuf); + } + + pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on); + if (p->pcre2_jit_on == 1) { + jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE); + if (jitret) + die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret); + p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL); + if (!p->pcre2_jit_stack) + die("Couldn't allocate PCRE2 JIT stack"); + p->pcre2_match_context = pcre2_match_context_create(NULL); + if (!p->pcre2_jit_stack) + die("Couldn't allocate PCRE2 match context"); + pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack); + } else if (p->pcre2_jit_on != 0) { + die("BUG: The pcre2_jit_on variable should be 0 or 1, not %d", + p->pcre1_jit_on); } +} + +static int pcre2match(struct grep_pat *p, const char *line, const char *eol, + regmatch_t *match, int eflags) +{ + int ret, flags = 0; + PCRE2_SIZE *ovector; + PCRE2_UCHAR errbuf[256]; + + if (eflags & REG_NOTBOL) + flags |= PCRE2_NOTBOL; + if (p->pcre2_jit_on) + ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line, + eol - line, 0, flags, p->pcre2_match_data, + NULL); + else + ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line, + eol - line, 0, flags, p->pcre2_match_data, + NULL); + + if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) { + pcre2_get_error_message(ret, errbuf, sizeof(errbuf)); + die("%s failed with error code %d: %s", + (p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret, + errbuf); + } + if (ret > 0) { + ovector = pcre2_get_ovector_pointer(p->pcre2_match_data); + ret = 0; + match->rm_so = (int)ovector[0]; + match->rm_eo = (int)ovector[1]; + } + + return ret; +} + +static void free_pcre2_pattern(struct grep_pat *p) +{ + pcre2_compile_context_free(p->pcre2_compile_context); + pcre2_code_free(p->pcre2_pattern); + pcre2_match_data_free(p->pcre2_match_data); + pcre2_jit_stack_free(p->pcre2_jit_stack); + pcre2_match_context_free(p->pcre2_match_context); +} +#else /* !USE_LIBPCRE2 */ +static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) +{ + /* + * Unreachable until USE_LIBPCRE2 becomes synonymous with + * USE_LIBPCRE. See the sibling comment in + * grep_set_pattern_type_option(). + */ + die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); +} + +static int pcre2match(struct grep_pat *p, const char *line, const char *eol, + regmatch_t *match, int eflags) +{ return 1; } +static void free_pcre2_pattern(struct grep_pat *p) +{ +} +#endif /* !USE_LIBPCRE2 */ + static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt) { struct strbuf sb = STRBUF_INIT; int err; - int regflags; + int regflags = opt->regflags; basic_regex_quote_buf(&sb, p->pattern); - regflags = opt->regflags & ~REG_EXTENDED; if (opt->ignore_case) regflags |= REG_ICASE; err = regcomp(&p->regexp, sb.buf, regflags); @@ -455,7 +625,9 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) * simple string match using kws. p->fixed tells us if we * want to use kws. */ - if (opt->fixed || is_fixed(p->pattern, p->patternlen)) + if (opt->fixed || + has_null(p->pattern, p->patternlen) || + is_fixed(p->pattern, p->patternlen)) p->fixed = !icase || ascii_only; else p->fixed = 0; @@ -475,8 +647,13 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) return; } - if (opt->pcre) { - compile_pcre_regexp(p, opt); + if (opt->pcre2) { + compile_pcre2_pattern(p, opt); + return; + } + + if (opt->pcre1) { + compile_pcre1_regexp(p, opt); return; } @@ -832,8 +1009,10 @@ void free_grep_patterns(struct grep_opt *opt) case GREP_PATTERN_BODY: if (p->kws) kwsfree(p->kws); - else if (p->pcre_regexp) - free_pcre_regexp(p); + else if (p->pcre1_regexp) + free_pcre1_regexp(p); + else if (p->pcre2_pattern) + free_pcre2_pattern(p); else regfree(&p->regexp); free(p->pattern); @@ -912,8 +1091,10 @@ static int patmatch(struct grep_pat *p, char *line, char *eol, if (p->fixed) hit = !fixmatch(p, line, eol, match); - else if (p->pcre_regexp) - hit = !pcrematch(p, line, eol, match, eflags); + else if (p->pcre1_regexp) + hit = !pcre1match(p, line, eol, match, eflags); + else if (p->pcre2_pattern) + hit = !pcre2match(p, line, eol, match, eflags); else hit = !regexec_buf(&p->regexp, line, eol - line, 1, match, eflags); @@ -1,11 +1,35 @@ #ifndef GREP_H #define GREP_H #include "color.h" -#ifdef USE_LIBPCRE +#ifdef USE_LIBPCRE1 #include <pcre.h> +#ifdef PCRE_CONFIG_JIT +#if PCRE_MAJOR >= 8 && PCRE_MINOR >= 32 +#ifndef NO_LIBPCRE1_JIT +#define GIT_PCRE1_USE_JIT +#endif +#endif +#endif +#ifndef PCRE_STUDY_JIT_COMPILE +#define PCRE_STUDY_JIT_COMPILE 0 +#endif +#if PCRE_MAJOR <= 8 && PCRE_MINOR < 20 +typedef int pcre_jit_stack; +#endif #else typedef int pcre; typedef int pcre_extra; +typedef int pcre_jit_stack; +#endif +#ifdef USE_LIBPCRE2 +#define PCRE2_CODE_UNIT_WIDTH 8 +#include <pcre2.h> +#else +typedef int pcre2_code; +typedef int pcre2_match_data; +typedef int pcre2_compile_context; +typedef int pcre2_match_context; +typedef int pcre2_jit_stack; #endif #include "kwset.h" #include "thread-utils.h" @@ -46,9 +70,17 @@ struct grep_pat { size_t patternlen; enum grep_header_field field; regex_t regexp; - pcre *pcre_regexp; - pcre_extra *pcre_extra_info; - const unsigned char *pcre_tables; + pcre *pcre1_regexp; + pcre_extra *pcre1_extra_info; + pcre_jit_stack *pcre1_jit_stack; + const unsigned char *pcre1_tables; + int pcre1_jit_on; + pcre2_code *pcre2_pattern; + pcre2_match_data *pcre2_match_data; + pcre2_compile_context *pcre2_compile_context; + pcre2_match_context *pcre2_match_context; + pcre2_jit_stack *pcre2_jit_stack; + uint32_t pcre2_jit_on; kwset_t kws; unsigned fixed:1; unsigned ignore_case:1; @@ -111,7 +143,8 @@ struct grep_opt { int allow_textconv; int extended; int use_reflog_filter; - int pcre; + int pcre1; + int pcre2; int relative; int pathname; int null_following_name; @@ -72,12 +72,10 @@ static int add_mailname_host(struct strbuf *buf) FILE *mailname; struct strbuf mailnamebuf = STRBUF_INIT; - mailname = fopen("/etc/mailname", "r"); - if (!mailname) { - if (errno != ENOENT) - warning_errno("cannot open /etc/mailname"); + mailname = fopen_or_warn("/etc/mailname", "r"); + if (!mailname) return -1; - } + if (strbuf_getline(&mailnamebuf, mailname) == EOF) { if (ferror(mailname)) warning_errno("cannot read /etc/mailname"); diff --git a/lockfile.h b/lockfile.h index 7b715f9e77..572064939c 100644 --- a/lockfile.h +++ b/lockfile.h @@ -176,6 +176,14 @@ static inline int hold_lock_file_for_update( } /* + * Return a nonzero value iff `lk` is currently locked. + */ +static inline int is_lock_file_locked(struct lock_file *lk) +{ + return is_tempfile_active(&lk->tempfile); +} + +/* * Append an appropriate error message to `buf` following the failure * of `hold_lock_file_for_update()` to lock `path`. `err` should be the * `errno` set by the failing call. diff --git a/notes-utils.c b/notes-utils.c index b2aada90a2..9ebf841956 100644 --- a/notes-utils.c +++ b/notes-utils.c @@ -132,8 +132,11 @@ struct notes_rewrite_cfg *init_copy_notes_for_rewrite(const char *cmd) c->mode_from_env = 1; c->combine = parse_combine_notes_fn(rewrite_mode_env); if (!c->combine) - /* TRANSLATORS: The first %s is the name of the - environment variable, the second %s is its value */ + /* + * TRANSLATORS: The first %s is the name of + * the environment variable, the second %s is + * its value. + */ error(_("Bad %s value: '%s'"), GIT_NOTES_REWRITE_MODE_ENVIRONMENT, rewrite_mode_env); } diff --git a/parse-options.c b/parse-options.c index a23a1e67f0..e5ad34a2c3 100644 --- a/parse-options.c +++ b/parse-options.c @@ -589,8 +589,10 @@ static int usage_with_options_internal(struct parse_opt_ctx_t *ctx, fprintf_ln(outfile, _("usage: %s"), _(*usagestr++)); while (*usagestr && **usagestr) - /* TRANSLATORS: the colon here should align with the - one in "usage: %s" translation */ + /* + * TRANSLATORS: the colon here should align with the + * one in "usage: %s" translation. + */ fprintf_ln(outfile, _(" or: %s"), _(*usagestr++)); while (*usagestr) { if (**usagestr) diff --git a/read-cache.c b/read-cache.c index 92eb15c000..bc156a133e 100644 --- a/read-cache.c +++ b/read-cache.c @@ -2181,9 +2181,10 @@ void update_index_if_able(struct index_state *istate, struct lock_file *lockfile rollback_lock_file(lockfile); } -static int do_write_index(struct index_state *istate, int newfd, +static int do_write_index(struct index_state *istate, struct tempfile *tempfile, int strip_extensions) { + int newfd = tempfile->fd; git_SHA_CTX c; struct cache_header hdr; int i, err, removed, extended, hdr_version; @@ -2295,7 +2296,11 @@ static int do_write_index(struct index_state *istate, int newfd, return -1; } - if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st)) + if (ce_flush(&c, newfd, istate->sha1)) + return -1; + if (close_tempfile(tempfile)) + return error(_("could not close '%s'"), tempfile->filename.buf); + if (stat(tempfile->filename.buf, &st)) return -1; istate->timestamp.sec = (unsigned int)st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); @@ -2318,7 +2323,7 @@ static int commit_locked_index(struct lock_file *lk) static int do_write_locked_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { - int ret = do_write_index(istate, get_lock_file_fd(lock), 0); + int ret = do_write_index(istate, &lock->tempfile, 0); if (ret) return ret; assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) != @@ -2415,7 +2420,7 @@ static int write_shared_index(struct index_state *istate, return do_write_locked_index(istate, lock, flags); } move_cache_to_base_index(istate); - ret = do_write_index(si->base, fd, 1); + ret = do_write_index(si->base, &temporary_sharedindex, 1); if (ret) { delete_tempfile(&temporary_sharedindex); return ret; diff --git a/ref-filter.c b/ref-filter.c index 3742abbf85..ab32bc9c31 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -1258,13 +1258,17 @@ char *get_head_description(void) state.branch); else if (state.detached_from) { if (state.detached_at) - /* TRANSLATORS: make sure this matches - "HEAD detached at " in wt-status.c */ + /* + * TRANSLATORS: make sure this matches "HEAD + * detached at " in wt-status.c + */ strbuf_addf(&desc, _("(HEAD detached at %s)"), state.detached_from); else - /* TRANSLATORS: make sure this matches - "HEAD detached from " in wt-status.c */ + /* + * TRANSLATORS: make sure this matches "HEAD + * detached from " in wt-status.c + */ strbuf_addf(&desc, _("(HEAD detached from %s)"), state.detached_from); } @@ -1668,6 +1672,68 @@ static int filter_pattern_match(struct ref_filter *filter, const char *refname) } /* + * Find the longest prefix of pattern we can pass to + * `for_each_fullref_in()`, namely the part of pattern preceding the + * first glob character. (Note that `for_each_fullref_in()` is + * perfectly happy working with a prefix that doesn't end at a + * pathname component boundary.) + */ +static void find_longest_prefix(struct strbuf *out, const char *pattern) +{ + const char *p; + + for (p = pattern; *p && !is_glob_special(*p); p++) + ; + + strbuf_add(out, pattern, p - pattern); +} + +/* + * This is the same as for_each_fullref_in(), but it tries to iterate + * only over the patterns we'll care about. Note that it _doesn't_ do a full + * pattern match, so the callback still has to match each ref individually. + */ +static int for_each_fullref_in_pattern(struct ref_filter *filter, + each_ref_fn cb, + void *cb_data, + int broken) +{ + struct strbuf prefix = STRBUF_INIT; + int ret; + + if (!filter->match_as_path) { + /* + * in this case, the patterns are applied after + * prefixes like "refs/heads/" etc. are stripped off, + * so we have to look at everything: + */ + return for_each_fullref_in("", cb, cb_data, broken); + } + + if (!filter->name_patterns[0]) { + /* no patterns; we have to look at everything */ + return for_each_fullref_in("", cb, cb_data, broken); + } + + if (filter->name_patterns[1]) { + /* + * multiple patterns; in theory this could still work as long + * as the patterns are disjoint. We'd just make multiple calls + * to for_each_ref(). But if they're not disjoint, we'd end up + * reporting the same ref multiple times. So let's punt on that + * for now. + */ + return for_each_fullref_in("", cb, cb_data, broken); + } + + find_longest_prefix(&prefix, filter->name_patterns[0]); + + ret = for_each_fullref_in(prefix.buf, cb, cb_data, broken); + strbuf_release(&prefix); + return ret; +} + +/* * Given a ref (sha1, refname), check if the ref belongs to the array * of sha1s. If the given ref is a tag, check if the given tag points * at one of the sha1s in the given sha1 array. @@ -1913,7 +1979,7 @@ int filter_refs(struct ref_array *array, struct ref_filter *filter, unsigned int else if (filter->kind == FILTER_REFS_TAGS) ret = for_each_fullref_in("refs/tags/", ref_filter_handler, &ref_cbdata, broken); else if (filter->kind & FILTER_REFS_ALL) - ret = for_each_fullref_in("", ref_filter_handler, &ref_cbdata, broken); + ret = for_each_fullref_in_pattern(filter, ref_filter_handler, &ref_cbdata, broken); if (!ret && (filter->kind & FILTER_REFS_DETACHED_HEAD)) head_ref(ref_filter_handler, &ref_cbdata); } @@ -848,11 +848,24 @@ struct ref_transaction *ref_transaction_begin(struct strbuf *err) void ref_transaction_free(struct ref_transaction *transaction) { - int i; + size_t i; if (!transaction) return; + switch (transaction->state) { + case REF_TRANSACTION_OPEN: + case REF_TRANSACTION_CLOSED: + /* OK */ + break; + case REF_TRANSACTION_PREPARED: + die("BUG: free called on a prepared reference transaction"); + break; + default: + die("BUG: unexpected reference transaction state"); + break; + } + for (i = 0; i < transaction->nr; i++) { free(transaction->updates[i]->msg); free(transaction->updates[i]); @@ -1246,8 +1259,19 @@ struct ref_iterator *refs_ref_iterator_begin( { struct ref_iterator *iter; + if (ref_paranoia < 0) + ref_paranoia = git_env_bool("GIT_REF_PARANOIA", 0); + if (ref_paranoia) + flags |= DO_FOR_EACH_INCLUDE_BROKEN; + iter = refs->be->iterator_begin(refs, prefix, flags); - iter = prefix_ref_iterator_begin(iter, prefix, trim); + + /* + * `iterator_begin()` already takes care of prefix, but we + * might need to do some trimming: + */ + if (trim) + iter = prefix_ref_iterator_begin(iter, "", trim); return iter; } @@ -1683,18 +1707,108 @@ int create_symref(const char *ref_target, const char *refs_heads_master, refs_heads_master, logmsg); } -int ref_transaction_commit(struct ref_transaction *transaction, - struct strbuf *err) +int ref_update_reject_duplicates(struct string_list *refnames, + struct strbuf *err) +{ + size_t i, n = refnames->nr; + + assert(err); + + for (i = 1; i < n; i++) { + int cmp = strcmp(refnames->items[i - 1].string, + refnames->items[i].string); + + if (!cmp) { + strbuf_addf(err, + "multiple updates for ref '%s' not allowed.", + refnames->items[i].string); + return 1; + } else if (cmp > 0) { + die("BUG: ref_update_reject_duplicates() received unsorted list"); + } + } + return 0; +} + +int ref_transaction_prepare(struct ref_transaction *transaction, + struct strbuf *err) { struct ref_store *refs = transaction->ref_store; + switch (transaction->state) { + case REF_TRANSACTION_OPEN: + /* Good. */ + break; + case REF_TRANSACTION_PREPARED: + die("BUG: prepare called twice on reference transaction"); + break; + case REF_TRANSACTION_CLOSED: + die("BUG: prepare called on a closed reference transaction"); + break; + default: + die("BUG: unexpected reference transaction state"); + break; + } + if (getenv(GIT_QUARANTINE_ENVIRONMENT)) { strbuf_addstr(err, _("ref updates forbidden inside quarantine environment")); return -1; } - return refs->be->transaction_commit(refs, transaction, err); + return refs->be->transaction_prepare(refs, transaction, err); +} + +int ref_transaction_abort(struct ref_transaction *transaction, + struct strbuf *err) +{ + struct ref_store *refs = transaction->ref_store; + int ret = 0; + + switch (transaction->state) { + case REF_TRANSACTION_OPEN: + /* No need to abort explicitly. */ + break; + case REF_TRANSACTION_PREPARED: + ret = refs->be->transaction_abort(refs, transaction, err); + break; + case REF_TRANSACTION_CLOSED: + die("BUG: abort called on a closed reference transaction"); + break; + default: + die("BUG: unexpected reference transaction state"); + break; + } + + ref_transaction_free(transaction); + return ret; +} + +int ref_transaction_commit(struct ref_transaction *transaction, + struct strbuf *err) +{ + struct ref_store *refs = transaction->ref_store; + int ret; + + switch (transaction->state) { + case REF_TRANSACTION_OPEN: + /* Need to prepare first. */ + ret = ref_transaction_prepare(transaction, err); + if (ret) + return ret; + break; + case REF_TRANSACTION_PREPARED: + /* Fall through to finish. */ + break; + case REF_TRANSACTION_CLOSED: + die("BUG: commit called on a closed reference transaction"); + break; + default: + die("BUG: unexpected reference transaction state"); + break; + } + + return refs->be->transaction_finish(refs, transaction, err); } int refs_verify_refname_available(struct ref_store *refs, @@ -1896,15 +2010,16 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, return refs->be->initial_transaction_commit(refs, transaction, err); } -int refs_delete_refs(struct ref_store *refs, struct string_list *refnames, - unsigned int flags) +int refs_delete_refs(struct ref_store *refs, const char *msg, + struct string_list *refnames, unsigned int flags) { - return refs->be->delete_refs(refs, refnames, flags); + return refs->be->delete_refs(refs, msg, refnames, flags); } -int delete_refs(struct string_list *refnames, unsigned int flags) +int delete_refs(const char *msg, struct string_list *refnames, + unsigned int flags) { - return refs_delete_refs(get_main_ref_store(), refnames, flags); + return refs_delete_refs(get_main_ref_store(), msg, refnames, flags); } int refs_rename_ref(struct ref_store *refs, const char *oldref, @@ -143,30 +143,71 @@ int dwim_ref(const char *str, int len, unsigned char *sha1, char **ref); int dwim_log(const char *str, int len, unsigned char *sha1, char **ref); /* - * A ref_transaction represents a collection of ref updates - * that should succeed or fail together. + * A ref_transaction represents a collection of reference updates that + * should succeed or fail together. * * Calling sequence * ---------------- + * * - Allocate and initialize a `struct ref_transaction` by calling * `ref_transaction_begin()`. * - * - List intended ref updates by calling functions like - * `ref_transaction_update()` and `ref_transaction_create()`. - * - * - Call `ref_transaction_commit()` to execute the transaction. - * If this succeeds, the ref updates will have taken place and - * the transaction cannot be rolled back. - * - * - Instead of `ref_transaction_commit`, use - * `initial_ref_transaction_commit()` if the ref database is known - * to be empty (e.g. during clone). This is likely to be much - * faster. - * - * - At any time call `ref_transaction_free()` to discard the - * transaction and free associated resources. In particular, - * this rolls back the transaction if it has not been - * successfully committed. + * - Specify the intended ref updates by calling one or more of the + * following functions: + * - `ref_transaction_update()` + * - `ref_transaction_create()` + * - `ref_transaction_delete()` + * - `ref_transaction_verify()` + * + * - Then either: + * + * - Optionally call `ref_transaction_prepare()` to prepare the + * transaction. This locks all references, checks preconditions, + * etc. but doesn't finalize anything. If this step fails, the + * transaction has been closed and can only be freed. If this step + * succeeds, then `ref_transaction_commit()` is almost certain to + * succeed. However, you can still call `ref_transaction_abort()` + * if you decide not to commit the transaction after all. + * + * - Call `ref_transaction_commit()` to execute the transaction, + * make the changes permanent, and release all locks. If you + * haven't already called `ref_transaction_prepare()`, then + * `ref_transaction_commit()` calls it for you. + * + * Or + * + * - Call `initial_ref_transaction_commit()` if the ref database is + * known to be empty and have no other writers (e.g. during + * clone). This is likely to be much faster than + * `ref_transaction_commit()`. `ref_transaction_prepare()` should + * *not* be called before `initial_ref_transaction_commit()`. + * + * - Then finally, call `ref_transaction_free()` to free the + * `ref_transaction` data structure. + * + * At any time before calling `ref_transaction_commit()`, you can call + * `ref_transaction_abort()` to abort the transaction, rollback any + * locks, and free any associated resources (including the + * `ref_transaction` data structure). + * + * Putting it all together, a complete reference update looks like + * + * struct ref_transaction *transaction; + * struct strbuf err = STRBUF_INIT; + * int ret = 0; + * + * transaction = ref_store_transaction_begin(refs, &err); + * if (!transaction || + * ref_transaction_update(...) || + * ref_transaction_create(...) || + * ...etc... || + * ref_transaction_commit(transaction, &err)) { + * error("%s", err.buf); + * ret = -1; + * } + * ref_transaction_free(transaction); + * strbuf_release(&err); + * return ret; * * Error handling * -------------- @@ -183,8 +224,9 @@ int dwim_log(const char *str, int len, unsigned char *sha1, char **ref); * ------- * * Note that no locks are taken, and no refs are read, until - * `ref_transaction_commit` is called. So `ref_transaction_verify` - * won't report a verification failure until the commit is attempted. + * `ref_transaction_prepare()` or `ref_transaction_commit()` is + * called. So, for example, `ref_transaction_verify()` won't report a + * verification failure until the commit is attempted. */ struct ref_transaction; @@ -331,7 +373,8 @@ int reflog_exists(const char *refname); * verify that the current value of the reference is old_sha1 before * deleting it. If old_sha1 is NULL, delete the reference if it * exists, regardless of its old value. It is an error for old_sha1 to - * be NULL_SHA1. flags is passed through to ref_transaction_delete(). + * be NULL_SHA1. msg and flags are passed through to + * ref_transaction_delete(). */ int refs_delete_ref(struct ref_store *refs, const char *msg, const char *refname, @@ -343,12 +386,13 @@ int delete_ref(const char *msg, const char *refname, /* * Delete the specified references. If there are any problems, emit * errors but attempt to keep going (i.e., the deletes are not done in - * an all-or-nothing transaction). flags is passed through to + * an all-or-nothing transaction). msg and flags are passed through to * ref_transaction_delete(). */ -int refs_delete_refs(struct ref_store *refs, struct string_list *refnames, - unsigned int flags); -int delete_refs(struct string_list *refnames, unsigned int flags); +int refs_delete_refs(struct ref_store *refs, const char *msg, + struct string_list *refnames, unsigned int flags); +int delete_refs(const char *msg, struct string_list *refnames, + unsigned int flags); /** Delete a reflog */ int refs_delete_reflog(struct ref_store *refs, const char *refname); @@ -427,6 +471,19 @@ struct ref_transaction *ref_transaction_begin(struct strbuf *err); * * refname -- the name of the reference to be affected. * + * new_sha1 -- the SHA-1 that should be set to be the new value of + * the reference. Some functions allow this parameter to be + * NULL, meaning that the reference is not changed, or + * null_sha1, meaning that the reference should be deleted. A + * copy of this value is made in the transaction. + * + * old_sha1 -- the SHA-1 value that the reference must have before + * the update. Some functions allow this parameter to be NULL, + * meaning that the old value of the reference is not checked, + * or null_sha1, meaning that the reference must not exist + * before the update. A copy of this value is made in the + * transaction. + * * flags -- flags affecting the update, passed to * update_ref_lock(). Can be REF_NODEREF, which means that * symbolic references should not be followed. @@ -508,20 +565,48 @@ int ref_transaction_verify(struct ref_transaction *transaction, unsigned int flags, struct strbuf *err); -/* - * Commit all of the changes that have been queued in transaction, as - * atomically as possible. - * - * Returns 0 for success, or one of the below error codes for errors. - */ /* Naming conflict (for example, the ref names A and A/B conflict). */ #define TRANSACTION_NAME_CONFLICT -1 /* All other errors. */ #define TRANSACTION_GENERIC_ERROR -2 + +/* + * Perform the preparatory stages of commiting `transaction`. Acquire + * any needed locks, check preconditions, etc.; basically, do as much + * as possible to ensure that the transaction will be able to go + * through, stopping just short of making any irrevocable or + * user-visible changes. The updates that this function prepares can + * be finished up by calling `ref_transaction_commit()` or rolled back + * by calling `ref_transaction_abort()`. + * + * On success, return 0 and leave the transaction in "prepared" state. + * On failure, abort the transaction, write an error message to `err`, + * and return one of the `TRANSACTION_*` constants. + * + * Callers who don't need such fine-grained control over commiting + * reference transactions should just call `ref_transaction_commit()`. + */ +int ref_transaction_prepare(struct ref_transaction *transaction, + struct strbuf *err); + +/* + * Commit all of the changes that have been queued in transaction, as + * atomically as possible. On success, return 0 and leave the + * transaction in "closed" state. On failure, roll back the + * transaction, write an error message to `err`, and return one of the + * `TRANSACTION_*` constants + */ int ref_transaction_commit(struct ref_transaction *transaction, struct strbuf *err); /* + * Abort `transaction`, which has been begun and possibly prepared, + * but not yet committed. + */ +int ref_transaction_abort(struct ref_transaction *transaction, + struct strbuf *err); + +/* * Like ref_transaction_commit(), but optimized for creating * references when originally initializing a repository (e.g., by "git * clone"). It writes the new references directly to packed-refs @@ -536,7 +621,7 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, struct strbuf *err); /* - * Free an existing transaction and all associated data. + * Free `*transaction` and all associated data. */ void ref_transaction_free(struct ref_transaction *transaction); diff --git a/refs/files-backend.c b/refs/files-backend.c index cb1f528cbe..d8b3f73147 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -43,15 +43,6 @@ struct packed_ref_cache { */ unsigned int referrers; - /* - * Iff the packed-refs file associated with this instance is - * currently locked for writing, this points at the associated - * lock (which is owned by somebody else). The referrer count - * is also incremented when the file is locked and decremented - * when it is unlocked. - */ - struct lock_file *lock; - /* The metadata from when this packed-refs cache was read */ struct stat_validity validity; }; @@ -70,10 +61,13 @@ struct files_ref_store { struct ref_cache *loose; struct packed_ref_cache *packed; -}; -/* Lock used for the main packed-refs file: */ -static struct lock_file packlock; + /* + * Lock used for the "packed-refs" file. Note that this (and + * thus the enclosing `files_ref_store`) must not be freed. + */ + struct lock_file packed_refs_lock; +}; /* * Increment the reference count of *packed_refs. @@ -104,8 +98,8 @@ static void clear_packed_ref_cache(struct files_ref_store *refs) if (refs->packed) { struct packed_ref_cache *packed_refs = refs->packed; - if (packed_refs->lock) - die("internal error: packed-ref cache cleared while locked"); + if (is_lock_file_locked(&refs->packed_refs_lock)) + die("BUG: packed-ref cache cleared while locked"); refs->packed = NULL; release_packed_ref_cache(packed_refs); } @@ -215,7 +209,9 @@ static const char *parse_ref_line(struct strbuf *line, struct object_id *oid) } /* - * Read f, which is a packed-refs file, into dir. + * Read from `packed_refs_file` into a newly-allocated + * `packed_ref_cache` and return it. The return value will already + * have its reference count incremented. * * A comment line of the form "# pack-refs with: " may contain zero or * more traits. We interpret the traits as follows: @@ -241,12 +237,36 @@ static const char *parse_ref_line(struct strbuf *line, struct object_id *oid) * compatibility with older clients, but we do not require it * (i.e., "peeled" is a no-op if "fully-peeled" is set). */ -static void read_packed_refs(FILE *f, struct ref_dir *dir) +static struct packed_ref_cache *read_packed_refs(const char *packed_refs_file) { + FILE *f; + struct packed_ref_cache *packed_refs = xcalloc(1, sizeof(*packed_refs)); struct ref_entry *last = NULL; struct strbuf line = STRBUF_INIT; enum { PEELED_NONE, PEELED_TAGS, PEELED_FULLY } peeled = PEELED_NONE; + struct ref_dir *dir; + + acquire_packed_ref_cache(packed_refs); + packed_refs->cache = create_ref_cache(NULL, NULL); + packed_refs->cache->root->flag &= ~REF_INCOMPLETE; + + f = fopen(packed_refs_file, "r"); + if (!f) { + if (errno == ENOENT) { + /* + * This is OK; it just means that no + * "packed-refs" file has been written yet, + * which is equivalent to it being empty. + */ + return packed_refs; + } else { + die_errno("couldn't read %s", packed_refs_file); + } + } + + stat_validity_update(&packed_refs->validity, fileno(f)); + dir = get_ref_dir(packed_refs->cache->root); while (strbuf_getwholeline(&line, f, '\n') != EOF) { struct object_id oid; const char *refname; @@ -271,7 +291,7 @@ static void read_packed_refs(FILE *f, struct ref_dir *dir) oidclr(&oid); flag |= REF_BAD_NAME | REF_ISBROKEN; } - last = create_ref_entry(refname, &oid, flag, 0); + last = create_ref_entry(refname, &oid, flag); if (peeled == PEELED_FULLY || (peeled == PEELED_TAGS && starts_with(refname, "refs/tags/"))) last->flag |= REF_KNOWS_PEELED; @@ -293,7 +313,10 @@ static void read_packed_refs(FILE *f, struct ref_dir *dir) } } + fclose(f); strbuf_release(&line); + + return packed_refs; } static const char *files_packed_refs_path(struct files_ref_store *refs) @@ -348,30 +371,24 @@ static void files_ref_path(struct files_ref_store *refs, /* * Get the packed_ref_cache for the specified files_ref_store, - * creating it if necessary. + * creating and populating it if it hasn't been read before or if the + * file has been changed (according to its `validity` field) since it + * was last read. On the other hand, if we hold the lock, then assume + * that the file hasn't been changed out from under us, so skip the + * extra `stat()` call in `stat_validity_check()`. */ static struct packed_ref_cache *get_packed_ref_cache(struct files_ref_store *refs) { const char *packed_refs_file = files_packed_refs_path(refs); if (refs->packed && + !is_lock_file_locked(&refs->packed_refs_lock) && !stat_validity_check(&refs->packed->validity, packed_refs_file)) clear_packed_ref_cache(refs); - if (!refs->packed) { - FILE *f; - - refs->packed = xcalloc(1, sizeof(*refs->packed)); - acquire_packed_ref_cache(refs->packed); - refs->packed->cache = create_ref_cache(&refs->base, NULL); - refs->packed->cache->root->flag &= ~REF_INCOMPLETE; - f = fopen(packed_refs_file, "r"); - if (f) { - stat_validity_update(&refs->packed->validity, fileno(f)); - read_packed_refs(f, get_ref_dir(refs->packed->cache->root)); - fclose(f); - } - } + if (!refs->packed) + refs->packed = read_packed_refs(packed_refs_file); + return refs->packed; } @@ -396,10 +413,14 @@ static void add_packed_ref(struct files_ref_store *refs, { struct packed_ref_cache *packed_ref_cache = get_packed_ref_cache(refs); - if (!packed_ref_cache->lock) - die("internal error: packed refs not locked"); + if (!is_lock_file_locked(&refs->packed_refs_lock)) + die("BUG: packed refs not locked"); + + if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) + die("Reference has invalid format: '%s'", refname); + add_ref_entry(get_packed_ref_dir(packed_ref_cache), - create_ref_entry(refname, oid, REF_ISPACKED, 1)); + create_ref_entry(refname, oid, REF_ISPACKED)); } /* @@ -476,7 +497,7 @@ static void loose_fill_ref_dir(struct ref_store *ref_store, flag |= REF_BAD_NAME | REF_ISBROKEN; } add_entry_to_dir(dir, - create_ref_entry(refname.buf, &oid, flag, 0)); + create_ref_entry(refname.buf, &oid, flag)); } strbuf_setlen(&refname, dirnamelen); strbuf_setlen(&path, path_baselen); @@ -1057,15 +1078,12 @@ static struct ref_iterator *files_ref_iterator_begin( struct ref_iterator *loose_iter, *packed_iter; struct files_ref_iterator *iter; struct ref_iterator *ref_iterator; + unsigned int required_flags = REF_STORE_READ; - if (ref_paranoia < 0) - ref_paranoia = git_env_bool("GIT_REF_PARANOIA", 0); - if (ref_paranoia) - flags |= DO_FOR_EACH_INCLUDE_BROKEN; + if (!(flags & DO_FOR_EACH_INCLUDE_BROKEN)) + required_flags |= REF_STORE_ODB; - refs = files_downcast(ref_store, - REF_STORE_READ | (ref_paranoia ? 0 : REF_STORE_ODB), - "ref_iterator_begin"); + refs = files_downcast(ref_store, required_flags, "ref_iterator_begin"); iter = xcalloc(1, sizeof(*iter)); ref_iterator = &iter->base; @@ -1290,17 +1308,17 @@ static int lock_packed_refs(struct files_ref_store *refs, int flags) } if (hold_lock_file_for_update_timeout( - &packlock, files_packed_refs_path(refs), + &refs->packed_refs_lock, files_packed_refs_path(refs), flags, timeout_value) < 0) return -1; /* - * Get the current packed-refs while holding the lock. If the - * packed-refs file has been modified since we last read it, - * this will automatically invalidate the cache and re-read - * the packed-refs file. + * Get the current packed-refs while holding the lock. It is + * important that we call `get_packed_ref_cache()` before + * setting `packed_ref_cache->lock`, because otherwise the + * former will see that the file is locked and assume that the + * cache can't be stale. */ packed_ref_cache = get_packed_ref_cache(refs); - packed_ref_cache->lock = &packlock; /* Increment the reference count to prevent it from being freed: */ acquire_packed_ref_cache(packed_ref_cache); return 0; @@ -1323,10 +1341,10 @@ static int commit_packed_refs(struct files_ref_store *refs) files_assert_main_repository(refs, "commit_packed_refs"); - if (!packed_ref_cache->lock) - die("internal error: packed-refs not locked"); + if (!is_lock_file_locked(&refs->packed_refs_lock)) + die("BUG: packed-refs not locked"); - out = fdopen_lock_file(packed_ref_cache->lock, "w"); + out = fdopen_lock_file(&refs->packed_refs_lock, "w"); if (!out) die_errno("unable to fdopen packed-refs descriptor"); @@ -1344,11 +1362,10 @@ static int commit_packed_refs(struct files_ref_store *refs) if (ok != ITER_DONE) die("error while iterating over references"); - if (commit_lock_file(packed_ref_cache->lock)) { + if (commit_lock_file(&refs->packed_refs_lock)) { save_errno = errno; error = -1; } - packed_ref_cache->lock = NULL; release_packed_ref_cache(packed_ref_cache); errno = save_errno; return error; @@ -1366,10 +1383,9 @@ static void rollback_packed_refs(struct files_ref_store *refs) files_assert_main_repository(refs, "rollback_packed_refs"); - if (!packed_ref_cache->lock) - die("internal error: packed-refs not locked"); - rollback_lock_file(packed_ref_cache->lock); - packed_ref_cache->lock = NULL; + if (!is_lock_file_locked(&refs->packed_refs_lock)) + die("BUG: packed-refs not locked"); + rollback_lock_file(&refs->packed_refs_lock); release_packed_ref_cache(packed_ref_cache); clear_packed_ref_cache(refs); } @@ -1464,6 +1480,32 @@ static void prune_refs(struct files_ref_store *refs, struct ref_to_prune *r) } } +/* + * Return true if the specified reference should be packed. + */ +static int should_pack_ref(const char *refname, + const struct object_id *oid, unsigned int ref_flags, + unsigned int pack_flags) +{ + /* Do not pack per-worktree refs: */ + if (ref_type(refname) != REF_TYPE_NORMAL) + return 0; + + /* Do not pack non-tags unless PACK_REFS_ALL is set: */ + if (!(pack_flags & PACK_REFS_ALL) && !starts_with(refname, "refs/tags/")) + return 0; + + /* Do not pack symbolic refs: */ + if (ref_flags & REF_ISSYMREF) + return 0; + + /* Do not pack broken refs: */ + if (!ref_resolves_to_object(refname, oid, ref_flags)) + return 0; + + return 1; +} + static int files_pack_refs(struct ref_store *ref_store, unsigned int flags) { struct files_ref_store *refs = @@ -1485,21 +1527,9 @@ static int files_pack_refs(struct ref_store *ref_store, unsigned int flags) * pruned, also add it to refs_to_prune. */ struct ref_entry *packed_entry; - int is_tag_ref = starts_with(iter->refname, "refs/tags/"); - - /* Do not pack per-worktree refs: */ - if (ref_type(iter->refname) != REF_TYPE_NORMAL) - continue; - - /* ALWAYS pack tags */ - if (!(flags & PACK_REFS_ALL) && !is_tag_ref) - continue; - - /* Do not pack symbolic or broken refs: */ - if (iter->flags & REF_ISSYMREF) - continue; - if (!ref_resolves_to_object(iter->refname, iter->oid, iter->flags)) + if (!should_pack_ref(iter->refname, iter->oid, iter->flags, + flags)) continue; /* @@ -1515,7 +1545,7 @@ static int files_pack_refs(struct ref_store *ref_store, unsigned int flags) oidcpy(&packed_entry->u.value.oid, iter->oid); } else { packed_entry = create_ref_entry(iter->refname, iter->oid, - REF_ISPACKED, 0); + REF_ISPACKED); add_ref_entry(packed_refs, packed_entry); } oidclr(&packed_entry->u.value.peeled); @@ -1595,7 +1625,7 @@ static int repack_without_refs(struct files_ref_store *refs, return ret; } -static int files_delete_refs(struct ref_store *ref_store, +static int files_delete_refs(struct ref_store *ref_store, const char *msg, struct string_list *refnames, unsigned int flags) { struct files_ref_store *refs = @@ -1627,7 +1657,7 @@ static int files_delete_refs(struct ref_store *ref_store, for (i = 0; i < refnames->nr; i++) { const char *refname = refnames->items[i].string; - if (refs_delete_ref(&refs->base, NULL, refname, NULL, flags)) + if (refs_delete_ref(&refs->base, msg, refname, NULL, flags)) result |= error(_("could not remove reference %s"), refname); } @@ -2521,23 +2551,6 @@ static struct ref_iterator *files_reflog_iterator_begin(struct ref_store *ref_st return ref_iterator; } -static int ref_update_reject_duplicates(struct string_list *refnames, - struct strbuf *err) -{ - int i, n = refnames->nr; - - assert(err); - - for (i = 1; i < n; i++) - if (!strcmp(refnames->items[i - 1].string, refnames->items[i].string)) { - strbuf_addf(err, - "multiple updates for ref '%s' not allowed.", - refnames->items[i].string); - return 1; - } - return 0; -} - /* * If update is a direct update of head_ref (the reference pointed to * by HEAD), then add an extra REF_LOG_ONLY update for HEAD. @@ -2843,31 +2856,45 @@ static int lock_ref_for_update(struct files_ref_store *refs, return 0; } -static int files_transaction_commit(struct ref_store *ref_store, - struct ref_transaction *transaction, - struct strbuf *err) +/* + * Unlock any references in `transaction` that are still locked, and + * mark the transaction closed. + */ +static void files_transaction_cleanup(struct ref_transaction *transaction) +{ + size_t i; + + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct ref_lock *lock = update->backend_data; + + if (lock) { + unlock_ref(lock); + update->backend_data = NULL; + } + } + + transaction->state = REF_TRANSACTION_CLOSED; +} + +static int files_transaction_prepare(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) { struct files_ref_store *refs = files_downcast(ref_store, REF_STORE_WRITE, - "ref_transaction_commit"); - int ret = 0, i; - struct string_list refs_to_delete = STRING_LIST_INIT_NODUP; - struct string_list_item *ref_to_delete; + "ref_transaction_prepare"); + size_t i; + int ret = 0; struct string_list affected_refnames = STRING_LIST_INIT_NODUP; char *head_ref = NULL; int head_type; struct object_id head_oid; - struct strbuf sb = STRBUF_INIT; assert(err); - if (transaction->state != REF_TRANSACTION_OPEN) - die("BUG: commit called for transaction that is not open"); - - if (!transaction->nr) { - transaction->state = REF_TRANSACTION_CLOSED; - return 0; - } + if (!transaction->nr) + goto cleanup; /* * Fail if a refname appears more than once in the @@ -2926,6 +2953,8 @@ static int files_transaction_commit(struct ref_store *ref_store, * that new values are valid, and write new values to the * lockfiles, ready to be activated. Only keep one lockfile * open at a time to avoid running out of file descriptors. + * Note that lock_ref_for_update() might append more updates + * to the transaction. */ for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; @@ -2933,7 +2962,38 @@ static int files_transaction_commit(struct ref_store *ref_store, ret = lock_ref_for_update(refs, update, transaction, head_ref, &affected_refnames, err); if (ret) - goto cleanup; + break; + } + +cleanup: + free(head_ref); + string_list_clear(&affected_refnames, 0); + + if (ret) + files_transaction_cleanup(transaction); + else + transaction->state = REF_TRANSACTION_PREPARED; + + return ret; +} + +static int files_transaction_finish(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "ref_transaction_finish"); + size_t i; + int ret = 0; + struct string_list refs_to_delete = STRING_LIST_INIT_NODUP; + struct string_list_item *ref_to_delete; + struct strbuf sb = STRBUF_INIT; + + assert(err); + + if (!transaction->nr) { + transaction->state = REF_TRANSACTION_CLOSED; + return 0; } /* Perform updates first so live commits remain referenced */ @@ -3013,15 +3073,10 @@ static int files_transaction_commit(struct ref_store *ref_store, clear_loose_ref_cache(refs); cleanup: - strbuf_release(&sb); - transaction->state = REF_TRANSACTION_CLOSED; + files_transaction_cleanup(transaction); for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; - struct ref_lock *lock = update->backend_data; - - if (lock) - unlock_ref(lock); if (update->flags & REF_DELETED_LOOSE) { /* @@ -3035,13 +3090,19 @@ cleanup: } } + strbuf_release(&sb); string_list_clear(&refs_to_delete, 0); - free(head_ref); - string_list_clear(&affected_refnames, 0); - return ret; } +static int files_transaction_abort(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + files_transaction_cleanup(transaction); + return 0; +} + static int ref_present(const char *refname, const struct object_id *oid, int flags, void *cb_data) { @@ -3057,7 +3118,8 @@ static int files_initial_transaction_commit(struct ref_store *ref_store, struct files_ref_store *refs = files_downcast(ref_store, REF_STORE_WRITE, "initial_ref_transaction_commit"); - int ret = 0, i; + size_t i; + int ret = 0; struct string_list affected_refnames = STRING_LIST_INIT_NODUP; assert(err); @@ -3311,7 +3373,9 @@ struct ref_storage_be refs_be_files = { "files", files_ref_store_create, files_init_db, - files_transaction_commit, + files_transaction_prepare, + files_transaction_finish, + files_transaction_abort, files_initial_transaction_commit, files_pack_refs, diff --git a/refs/iterator.c b/refs/iterator.c index bce1f192f7..4cf449ef66 100644 --- a/refs/iterator.c +++ b/refs/iterator.c @@ -292,7 +292,23 @@ static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) if (!starts_with(iter->iter0->refname, iter->prefix)) continue; - iter->base.refname = iter->iter0->refname + iter->trim; + if (iter->trim) { + /* + * It is nonsense to trim off characters that + * you haven't already checked for via a + * prefix check, whether via this + * `prefix_ref_iterator` or upstream in + * `iter0`). So if there wouldn't be at least + * one character left in the refname after + * trimming, report it as a bug: + */ + if (strlen(iter->iter0->refname) <= iter->trim) + die("BUG: attempt to trim too many characters"); + iter->base.refname = iter->iter0->refname + iter->trim; + } else { + iter->base.refname = iter->iter0->refname; + } + iter->base.oid = iter->iter0->oid; iter->base.flags = iter->iter0->flags; return ITER_OK; diff --git a/refs/ref-cache.c b/refs/ref-cache.c index 6b11d9cd12..af2fcb2c12 100644 --- a/refs/ref-cache.c +++ b/refs/ref-cache.c @@ -32,14 +32,10 @@ struct ref_dir *get_ref_dir(struct ref_entry *entry) } struct ref_entry *create_ref_entry(const char *refname, - const struct object_id *oid, int flag, - int check_name) + const struct object_id *oid, int flag) { struct ref_entry *ref; - if (check_name && - check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) - die("Reference has invalid format: '%s'", refname); FLEX_ALLOC_STR(ref, name, refname); oidcpy(&ref->u.value.oid, oid); oidclr(&ref->u.value.peeled); @@ -316,11 +312,42 @@ static void sort_ref_dir(struct ref_dir *dir) dir->sorted = dir->nr = i; } +enum prefix_state { + /* All refs within the directory would match prefix: */ + PREFIX_CONTAINS_DIR, + + /* Some, but not all, refs within the directory might match prefix: */ + PREFIX_WITHIN_DIR, + + /* No refs within the directory could possibly match prefix: */ + PREFIX_EXCLUDES_DIR +}; + /* - * Load all of the refs from `dir` (recursively) into our in-memory - * cache. + * Return a `prefix_state` constant describing the relationship + * between the directory with the specified `dirname` and `prefix`. */ -static void prime_ref_dir(struct ref_dir *dir) +static enum prefix_state overlaps_prefix(const char *dirname, + const char *prefix) +{ + while (*prefix && *dirname == *prefix) { + dirname++; + prefix++; + } + if (!*prefix) + return PREFIX_CONTAINS_DIR; + else if (!*dirname) + return PREFIX_WITHIN_DIR; + else + return PREFIX_EXCLUDES_DIR; +} + +/* + * Load all of the refs from `dir` (recursively) that could possibly + * contain references matching `prefix` into our in-memory cache. If + * `prefix` is NULL, prime unconditionally. + */ +static void prime_ref_dir(struct ref_dir *dir, const char *prefix) { /* * The hard work of loading loose refs is done by get_ref_dir(), so we @@ -331,8 +358,29 @@ static void prime_ref_dir(struct ref_dir *dir) int i; for (i = 0; i < dir->nr; i++) { struct ref_entry *entry = dir->entries[i]; - if (entry->flag & REF_DIR) - prime_ref_dir(get_ref_dir(entry)); + if (!(entry->flag & REF_DIR)) { + /* Not a directory; no need to recurse. */ + } else if (!prefix) { + /* Recurse in any case: */ + prime_ref_dir(get_ref_dir(entry), NULL); + } else { + switch (overlaps_prefix(entry->name, prefix)) { + case PREFIX_CONTAINS_DIR: + /* + * Recurse, and from here down we + * don't have to check the prefix + * anymore: + */ + prime_ref_dir(get_ref_dir(entry), NULL); + break; + case PREFIX_WITHIN_DIR: + prime_ref_dir(get_ref_dir(entry), prefix); + break; + case PREFIX_EXCLUDES_DIR: + /* No need to prime this directory. */ + break; + } + } } } @@ -347,6 +395,8 @@ struct cache_ref_iterator_level { */ struct ref_dir *dir; + enum prefix_state prefix_state; + /* * The index of the current entry within dir (which might * itself be a directory). If index == -1, then the iteration @@ -374,6 +424,13 @@ struct cache_ref_iterator { size_t levels_alloc; /* + * Only include references with this prefix in the iteration. + * The prefix is matched textually, without regard for path + * component boundaries. + */ + const char *prefix; + + /* * A stack of levels. levels[0] is the uppermost level that is * being iterated over in this iteration. (This is not * necessary the top level in the references hierarchy. If we @@ -394,6 +451,7 @@ static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) &iter->levels[iter->levels_nr - 1]; struct ref_dir *dir = level->dir; struct ref_entry *entry; + enum prefix_state entry_prefix_state; if (level->index == -1) sort_ref_dir(dir); @@ -408,6 +466,14 @@ static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) entry = dir->entries[level->index]; + if (level->prefix_state == PREFIX_WITHIN_DIR) { + entry_prefix_state = overlaps_prefix(entry->name, iter->prefix); + if (entry_prefix_state == PREFIX_EXCLUDES_DIR) + continue; + } else { + entry_prefix_state = level->prefix_state; + } + if (entry->flag & REF_DIR) { /* push down a level */ ALLOC_GROW(iter->levels, iter->levels_nr + 1, @@ -415,6 +481,7 @@ static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) level = &iter->levels[iter->levels_nr++]; level->dir = get_ref_dir(entry); + level->prefix_state = entry_prefix_state; level->index = -1; } else { iter->base.refname = entry->name; @@ -475,6 +542,7 @@ static int cache_ref_iterator_abort(struct ref_iterator *ref_iterator) struct cache_ref_iterator *iter = (struct cache_ref_iterator *)ref_iterator; + free((char *)iter->prefix); free(iter->levels); base_ref_iterator_free(ref_iterator); return ITER_DONE; @@ -500,10 +568,10 @@ struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache, dir = find_containing_dir(dir, prefix, 0); if (!dir) /* There's nothing to iterate over. */ - return empty_ref_iterator_begin(); + return empty_ref_iterator_begin(); if (prime_dir) - prime_ref_dir(dir); + prime_ref_dir(dir, prefix); iter = xcalloc(1, sizeof(*iter)); ref_iterator = &iter->base; @@ -515,9 +583,12 @@ struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache, level->index = -1; level->dir = dir; - if (prefix && *prefix) - ref_iterator = prefix_ref_iterator_begin(ref_iterator, - prefix, 0); + if (prefix && *prefix) { + iter->prefix = xstrdup(prefix); + level->prefix_state = PREFIX_WITHIN_DIR; + } else { + level->prefix_state = PREFIX_CONTAINS_DIR; + } return ref_iterator; } diff --git a/refs/ref-cache.h b/refs/ref-cache.h index 1f65e2f9ed..794f000fd3 100644 --- a/refs/ref-cache.h +++ b/refs/ref-cache.h @@ -185,8 +185,7 @@ struct ref_entry *create_dir_entry(struct ref_cache *cache, int incomplete); struct ref_entry *create_ref_entry(const char *refname, - const struct object_id *oid, int flag, - int check_name); + const struct object_id *oid, int flag); /* * Return a pointer to a new `ref_cache`. Its top-level starts out @@ -194,7 +193,8 @@ struct ref_entry *create_ref_entry(const char *refname, * function called to fill in incomplete directories in the * `ref_cache` when they are accessed. If it is NULL, then the whole * `ref_cache` must be filled (including clearing its directories' - * `REF_INCOMPLETE` bits) before it is used. + * `REF_INCOMPLETE` bits) before it is used, and `refs` can be NULL, + * too. */ struct ref_cache *create_ref_cache(struct ref_store *refs, fill_ref_dir_fn *fill_ref_dir); diff --git a/refs/refs-internal.h b/refs/refs-internal.h index b6b291cf00..192f9f85c9 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -170,6 +170,14 @@ int refs_read_raw_ref(struct ref_store *ref_store, struct strbuf *referent, unsigned int *type); /* + * Write an error to `err` and return a nonzero value iff the same + * refname appears multiple times in `refnames`. `refnames` must be + * sorted on entry to this function. + */ +int ref_update_reject_duplicates(struct string_list *refnames, + struct strbuf *err); + +/* * Add a ref_update with the specified properties to transaction, and * return a pointer to the new object. This function does not verify * that refname is well-formed. new_sha1 and old_sha1 are only @@ -185,17 +193,27 @@ struct ref_update *ref_transaction_add_update( /* * Transaction states. - * OPEN: The transaction is in a valid state and can accept new updates. - * An OPEN transaction can be committed. - * CLOSED: A closed transaction is no longer active and no other operations - * than free can be used on it in this state. - * A transaction can either become closed by successfully committing - * an active transaction or if there is a failure while building - * the transaction thus rendering it failed/inactive. + * + * OPEN: The transaction is initialized and new updates can still be + * added to it. An OPEN transaction can be prepared, + * committed, freed, or aborted (freeing and aborting an open + * transaction are equivalent). + * + * PREPARED: ref_transaction_prepare(), which locks all of the + * references involved in the update and checks that the + * update has no errors, has been called successfully for the + * transaction. A PREPARED transaction can be committed or + * aborted. + * + * CLOSED: The transaction is no longer active. A transaction becomes + * CLOSED if there is a failure while building the transaction + * or if a transaction is committed or aborted. A CLOSED + * transaction can only be freed. */ enum ref_transaction_state { - REF_TRANSACTION_OPEN = 0, - REF_TRANSACTION_CLOSED = 1 + REF_TRANSACTION_OPEN = 0, + REF_TRANSACTION_PREPARED = 1, + REF_TRANSACTION_CLOSED = 2 }; /* @@ -497,6 +515,18 @@ typedef struct ref_store *ref_store_init_fn(const char *gitdir, typedef int ref_init_db_fn(struct ref_store *refs, struct strbuf *err); +typedef int ref_transaction_prepare_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int ref_transaction_finish_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int ref_transaction_abort_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + typedef int ref_transaction_commit_fn(struct ref_store *refs, struct ref_transaction *transaction, struct strbuf *err); @@ -508,16 +538,17 @@ typedef int create_symref_fn(struct ref_store *ref_store, const char *ref_target, const char *refs_heads_master, const char *logmsg); -typedef int delete_refs_fn(struct ref_store *ref_store, +typedef int delete_refs_fn(struct ref_store *ref_store, const char *msg, struct string_list *refnames, unsigned int flags); typedef int rename_ref_fn(struct ref_store *ref_store, const char *oldref, const char *newref, const char *logmsg); /* - * Iterate over the references in the specified ref_store that are - * within find_containing_dir(prefix). If prefix is NULL or the empty - * string, iterate over all references in the submodule. + * Iterate over the references in `ref_store` whose names start with + * `prefix`. `prefix` is matched as a literal string, without regard + * for path separators. If prefix is NULL or the empty string, iterate + * over all references in `ref_store`. */ typedef struct ref_iterator *ref_iterator_begin_fn( struct ref_store *ref_store, @@ -599,7 +630,10 @@ struct ref_storage_be { const char *name; ref_store_init_fn *init; ref_init_db_fn *init_db; - ref_transaction_commit_fn *transaction_commit; + + ref_transaction_prepare_fn *transaction_prepare; + ref_transaction_finish_fn *transaction_finish; + ref_transaction_abort_fn *transaction_abort; ref_transaction_commit_fn *initial_transaction_commit; pack_refs_fn *pack_refs; diff --git a/remote-testsvn.c b/remote-testsvn.c index 8e8d5c7947..e034ea00d4 100644 --- a/remote-testsvn.c +++ b/remote-testsvn.c @@ -124,10 +124,8 @@ static int note2mark_cb(const struct object_id *object_oid, static void regenerate_marks(void) { int ret; - FILE *marksfile = fopen(marksfilename, "w+"); + FILE *marksfile = xfopen(marksfilename, "w+"); - if (!marksfile) - die_errno("Couldn't create mark file %s.", marksfilename); ret = for_each_note(NULL, 0, note2mark_cb, marksfile); if (ret) die("Regeneration of marks failed, returned %d.", ret); @@ -148,9 +146,7 @@ static void check_or_regenerate_marks(int latestrev) marksfile = fopen(marksfilename, "r"); if (!marksfile) { regenerate_marks(); - marksfile = fopen(marksfilename, "r"); - if (!marksfile) - die_errno("cannot read marks file %s!", marksfilename); + marksfile = xfopen(marksfilename, "r"); fclose(marksfile); } else { strbuf_addf(&sb, ":%d ", latestrev); @@ -251,7 +251,7 @@ static const char *skip_spaces(const char *s) static void read_remotes_file(struct remote *remote) { struct strbuf buf = STRBUF_INIT; - FILE *f = fopen(git_path("remotes/%s", remote->name), "r"); + FILE *f = fopen_or_warn(git_path("remotes/%s", remote->name), "r"); if (!f) return; @@ -277,7 +277,7 @@ static void read_branches_file(struct remote *remote) { char *frag; struct strbuf buf = STRBUF_INIT; - FILE *f = fopen(git_path("branches/%s", remote->name), "r"); + FILE *f = fopen_or_warn(git_path("branches/%s", remote->name), "r"); if (!f) return; @@ -477,26 +477,6 @@ static void read_config(void) alias_all_urls(); } -/* - * This function frees a refspec array. - * Warning: code paths should be checked to ensure that the src - * and dst pointers are always freeable pointers as well - * as the refspec pointer itself. - */ -static void free_refspecs(struct refspec *refspec, int nr_refspec) -{ - int i; - - if (!refspec) - return; - - for (i = 0; i < nr_refspec; i++) { - free(refspec[i].src); - free(refspec[i].dst); - } - free(refspec); -} - static struct refspec *parse_refspec_internal(int nr_refspec, const char **refspec, int fetch, int verify) { int i; @@ -610,7 +590,7 @@ static struct refspec *parse_refspec_internal(int nr_refspec, const char **refsp * since it is only possible to reach this point from within * the for loop above. */ - free_refspecs(rs, i+1); + free_refspec(i+1, rs); return NULL; } die("Invalid refspec '%s'", refspec[i]); @@ -621,7 +601,7 @@ int valid_fetch_refspec(const char *fetch_refspec_str) struct refspec *refspec; refspec = parse_refspec_internal(1, &fetch_refspec_str, 1, 1); - free_refspecs(refspec, 1); + free_refspec(1, refspec); return !!refspec; } @@ -638,6 +618,10 @@ struct refspec *parse_push_refspec(int nr_refspec, const char **refspec) void free_refspec(int nr_refspec, struct refspec *refspec) { int i; + + if (!refspec) + return; + for (i = 0; i < nr_refspec; i++) { free(refspec[i].src); free(refspec[i].dst); @@ -649,7 +633,12 @@ static int valid_remote_nick(const char *name) { if (!name[0] || is_dot_or_dotdot(name)) return 0; - return !strchr(name, '/'); /* no slash */ + + /* remote nicknames cannot contain slashes */ + while (*name) + if (is_dir_sep(*name++)) + return 0; + return 1; } const char *remote_for_branch(struct branch *branch, int *explicit) @@ -200,7 +200,7 @@ static struct rerere_id *new_rerere_id(unsigned char *sha1) static void read_rr(struct string_list *rr) { struct strbuf buf = STRBUF_INIT; - FILE *in = fopen(git_path_merge_rr(), "r"); + FILE *in = fopen_or_warn(git_path_merge_rr(), "r"); if (!in) return; @@ -484,13 +484,14 @@ static int handle_file(const char *path, unsigned char *sha1, const char *output io.input = fopen(path, "r"); io.io.wrerror = 0; if (!io.input) - return error("Could not open %s", path); + return error_errno("Could not open %s", path); if (output) { io.io.output = fopen(output, "w"); if (!io.io.output) { + error_errno("Could not write %s", output); fclose(io.input); - return error("Could not write %s", output); + return -1; } } diff --git a/revision.c b/revision.c index 3030f33eed..12eb332350 100644 --- a/revision.c +++ b/revision.c @@ -1429,134 +1429,168 @@ static void prepare_show_merge(struct rev_info *revs) revs->limited = 1; } +static int dotdot_missing(const char *arg, char *dotdot, + struct rev_info *revs, int symmetric) +{ + if (revs->ignore_missing) + return 0; + /* de-munge so we report the full argument */ + *dotdot = '.'; + die(symmetric + ? "Invalid symmetric difference expression %s" + : "Invalid revision range %s", arg); +} + +static int handle_dotdot_1(const char *arg, char *dotdot, + struct rev_info *revs, int flags, + int cant_be_filename, + struct object_context *a_oc, + struct object_context *b_oc) +{ + const char *a_name, *b_name; + struct object_id a_oid, b_oid; + struct object *a_obj, *b_obj; + unsigned int a_flags, b_flags; + int symmetric = 0; + unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM); + unsigned int oc_flags = GET_SHA1_COMMITTISH | GET_SHA1_RECORD_PATH; + + a_name = arg; + if (!*a_name) + a_name = "HEAD"; + + b_name = dotdot + 2; + if (*b_name == '.') { + symmetric = 1; + b_name++; + } + if (!*b_name) + b_name = "HEAD"; + + if (get_sha1_with_context(a_name, oc_flags, a_oid.hash, a_oc) || + get_sha1_with_context(b_name, oc_flags, b_oid.hash, b_oc)) + return -1; + + if (!cant_be_filename) { + *dotdot = '.'; + verify_non_filename(revs->prefix, arg); + *dotdot = '\0'; + } + + a_obj = parse_object(&a_oid); + b_obj = parse_object(&b_oid); + if (!a_obj || !b_obj) + return dotdot_missing(arg, dotdot, revs, symmetric); + + if (!symmetric) { + /* just A..B */ + b_flags = flags; + a_flags = flags_exclude; + } else { + /* A...B -- find merge bases between the two */ + struct commit *a, *b; + struct commit_list *exclude; + + a = lookup_commit_reference(&a_obj->oid); + b = lookup_commit_reference(&b_obj->oid); + if (!a || !b) + return dotdot_missing(arg, dotdot, revs, symmetric); + + exclude = get_merge_bases(a, b); + add_rev_cmdline_list(revs, exclude, REV_CMD_MERGE_BASE, + flags_exclude); + add_pending_commit_list(revs, exclude, flags_exclude); + free_commit_list(exclude); + + b_flags = flags; + a_flags = flags | SYMMETRIC_LEFT; + } + + a_obj->flags |= a_flags; + b_obj->flags |= b_flags; + add_rev_cmdline(revs, a_obj, a_name, REV_CMD_LEFT, a_flags); + add_rev_cmdline(revs, b_obj, b_name, REV_CMD_RIGHT, b_flags); + add_pending_object_with_path(revs, a_obj, a_name, a_oc->mode, a_oc->path); + add_pending_object_with_path(revs, b_obj, b_name, b_oc->mode, b_oc->path); + return 0; +} + +static int handle_dotdot(const char *arg, + struct rev_info *revs, int flags, + int cant_be_filename) +{ + struct object_context a_oc, b_oc; + char *dotdot = strstr(arg, ".."); + int ret; + + if (!dotdot) + return -1; + + memset(&a_oc, 0, sizeof(a_oc)); + memset(&b_oc, 0, sizeof(b_oc)); + + *dotdot = '\0'; + ret = handle_dotdot_1(arg, dotdot, revs, flags, cant_be_filename, + &a_oc, &b_oc); + *dotdot = '.'; + + free(a_oc.path); + free(b_oc.path); + + return ret; +} + int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt) { struct object_context oc; - char *dotdot; + char *mark; struct object *object; struct object_id oid; int local_flags; const char *arg = arg_; int cant_be_filename = revarg_opt & REVARG_CANNOT_BE_FILENAME; - unsigned get_sha1_flags = 0; + unsigned get_sha1_flags = GET_SHA1_RECORD_PATH; flags = flags & UNINTERESTING ? flags | BOTTOM : flags & ~BOTTOM; - dotdot = strstr(arg, ".."); - if (dotdot) { - struct object_id from_oid; - const char *next = dotdot + 2; - const char *this = arg; - int symmetric = *next == '.'; - unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM); - static const char head_by_default[] = "HEAD"; - unsigned int a_flags; - - *dotdot = 0; - next += symmetric; - - if (!*next) - next = head_by_default; - if (dotdot == arg) - this = head_by_default; - if (this == head_by_default && next == head_by_default && - !symmetric) { - /* - * Just ".."? That is not a range but the - * pathspec for the parent directory. - */ - if (!cant_be_filename) { - *dotdot = '.'; - return -1; - } - } - if (!get_sha1_committish(this, from_oid.hash) && - !get_sha1_committish(next, oid.hash)) { - struct object *a_obj, *b_obj; - - if (!cant_be_filename) { - *dotdot = '.'; - verify_non_filename(revs->prefix, arg); - } - - a_obj = parse_object(&from_oid); - b_obj = parse_object(&oid); - if (!a_obj || !b_obj) { - missing: - if (revs->ignore_missing) - return 0; - die(symmetric - ? "Invalid symmetric difference expression %s" - : "Invalid revision range %s", arg); - } - - if (!symmetric) { - /* just A..B */ - a_flags = flags_exclude; - } else { - /* A...B -- find merge bases between the two */ - struct commit *a, *b; - struct commit_list *exclude; - - a = (a_obj->type == OBJ_COMMIT - ? (struct commit *)a_obj - : lookup_commit_reference(&a_obj->oid)); - b = (b_obj->type == OBJ_COMMIT - ? (struct commit *)b_obj - : lookup_commit_reference(&b_obj->oid)); - if (!a || !b) - goto missing; - exclude = get_merge_bases(a, b); - add_rev_cmdline_list(revs, exclude, - REV_CMD_MERGE_BASE, - flags_exclude); - add_pending_commit_list(revs, exclude, - flags_exclude); - free_commit_list(exclude); - - a_flags = flags | SYMMETRIC_LEFT; - } - - a_obj->flags |= a_flags; - b_obj->flags |= flags; - add_rev_cmdline(revs, a_obj, this, - REV_CMD_LEFT, a_flags); - add_rev_cmdline(revs, b_obj, next, - REV_CMD_RIGHT, flags); - add_pending_object(revs, a_obj, this); - add_pending_object(revs, b_obj, next); - return 0; - } - *dotdot = '.'; + if (!cant_be_filename && !strcmp(arg, "..")) { + /* + * Just ".."? That is not a range but the + * pathspec for the parent directory. + */ + return -1; } - dotdot = strstr(arg, "^@"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; + if (!handle_dotdot(arg, revs, flags, revarg_opt)) + return 0; + + mark = strstr(arg, "^@"); + if (mark && !mark[2]) { + *mark = 0; if (add_parents_only(revs, arg, flags, 0)) return 0; - *dotdot = '^'; + *mark = '^'; } - dotdot = strstr(arg, "^!"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; + mark = strstr(arg, "^!"); + if (mark && !mark[2]) { + *mark = 0; if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), 0)) - *dotdot = '^'; + *mark = '^'; } - dotdot = strstr(arg, "^-"); - if (dotdot) { + mark = strstr(arg, "^-"); + if (mark) { int exclude_parent = 1; - if (dotdot[2]) { + if (mark[2]) { char *end; - exclude_parent = strtoul(dotdot + 2, &end, 10); + exclude_parent = strtoul(mark + 2, &end, 10); if (*end != '\0' || !exclude_parent) return -1; } - *dotdot = 0; + *mark = 0; if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), exclude_parent)) - *dotdot = '^'; + *mark = '^'; } local_flags = 0; @@ -1566,7 +1600,7 @@ int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsi } if (revarg_opt & REVARG_COMMITTISH) - get_sha1_flags = GET_SHA1_COMMITTISH; + get_sha1_flags |= GET_SHA1_COMMITTISH; if (get_sha1_with_context(arg, get_sha1_flags, oid.hash, &oc)) return revs->ignore_missing ? 0 : -1; @@ -1574,7 +1608,8 @@ int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsi verify_non_filename(revs->prefix, arg); object = get_reference(revs, arg, &oid, flags ^ local_flags); add_rev_cmdline(revs, object, arg_, REV_CMD_REV, flags ^ local_flags); - add_pending_object_with_mode(revs, object, arg, oc.mode); + add_pending_object_with_path(revs, object, arg, oc.mode, oc.path); + free(oc.path); return 0; } @@ -1991,11 +2026,12 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg } else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE; } else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) { + revs->grep_filter.ignore_case = 1; revs->grep_filter.regflags |= REG_ICASE; DIFF_OPT_SET(&revs->diffopt, PICKAXE_IGNORE_CASE); } else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED; - } else if (!strcmp(arg, "--perl-regexp")) { + } else if (!strcmp(arg, "--perl-regexp") || !strcmp(arg, "-P")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_PCRE; } else if (!strcmp(arg, "--all-match")) { revs->grep_filter.all_match = 1; diff --git a/sequencer.c b/sequencer.c index 7a114def84..d63099d50f 100644 --- a/sequencer.c +++ b/sequencer.c @@ -464,7 +464,8 @@ static int do_recursive_merge(struct commit *base, struct commit *next, if (active_cache_changed && write_locked_index(&the_index, &index_lock, COMMIT_LOCK)) - /* TRANSLATORS: %s will be "revert", "cherry-pick" or + /* + * TRANSLATORS: %s will be "revert", "cherry-pick" or * "rebase -i". */ return error(_("%s: Unable to write new index file"), @@ -898,8 +899,8 @@ static void flush_rewritten_pending(void) { FILE *out; if (strbuf_read_file(&buf, rebase_path_rewritten_pending(), 82) > 0 && - !get_sha1("HEAD", newsha1) && - (out = fopen(rebase_path_rewritten_list(), "a"))) { + !get_sha1("HEAD", newsha1) && + (out = fopen_or_warn(rebase_path_rewritten_list(), "a"))) { char *bol = buf.buf, *eol; while (*bol) { @@ -918,7 +919,7 @@ static void flush_rewritten_pending(void) { static void record_in_rewritten(struct object_id *oid, enum todo_command next_command) { - FILE *out = fopen(rebase_path_rewritten_pending(), "a"); + FILE *out = fopen_or_warn(rebase_path_rewritten_pending(), "a"); if (!out) return; @@ -1380,7 +1381,7 @@ static int read_populate_todo(struct todo_list *todo_list, if (is_rebase_i(opts)) { struct todo_list done = TODO_LIST_INIT; - FILE *f = fopen(rebase_path_msgtotal(), "w"); + FILE *f = fopen_or_warn(rebase_path_msgtotal(), "w"); if (strbuf_read_file(&done.buf, rebase_path_done(), 0) > 0 && !parse_insn_buffer(done.buf.buf, &done)) diff --git a/server-info.c b/server-info.c index 6f865b73a3..5ec5b1d827 100644 --- a/server-info.c +++ b/server-info.c @@ -133,7 +133,7 @@ static int read_pack_info_file(const char *infofile) char line[1000]; int old_cnt = 0; - fp = fopen(infofile, "r"); + fp = fopen_or_warn(infofile, "r"); if (!fp) return 1; /* nonexistent is not an error. */ @@ -134,23 +134,27 @@ int path_inside_repo(const char *prefix, const char *path) int check_filename(const char *prefix, const char *arg) { - const char *name; char *to_free = NULL; struct stat st; - if (starts_with(arg, ":/")) { - if (arg[2] == '\0') /* ":/" is root dir, always exists */ + if (skip_prefix(arg, ":/", &arg)) { + if (!*arg) /* ":/" is root dir, always exists */ return 1; - name = arg + 2; - } else if (prefix) - name = to_free = prefix_filename(prefix, arg); - else - name = arg; - if (!lstat(name, &st)) { + prefix = NULL; + } else if (skip_prefix(arg, ":!", &arg) || + skip_prefix(arg, ":^", &arg)) { + if (!*arg) /* excluding everything is silly, but allowed */ + return 1; + } + + if (prefix) + arg = to_free = prefix_filename(prefix, arg); + + if (!lstat(arg, &st)) { free(to_free); return 1; /* file exists */ } - if (errno == ENOENT || errno == ENOTDIR) { + if (is_missing_file_error(errno)) { free(to_free); return 0; /* file does not exist */ } @@ -182,6 +186,24 @@ static void NORETURN die_verify_filename(const char *prefix, } /* + * Check for arguments that don't resolve as actual files, + * but which look sufficiently like pathspecs that we'll consider + * them such for the purposes of rev/pathspec DWIM parsing. + */ +static int looks_like_pathspec(const char *arg) +{ + /* anything with a wildcard character */ + if (!no_wildcard(arg)) + return 1; + + /* long-form pathspec magic */ + if (starts_with(arg, ":(")) + return 1; + + return 0; +} + +/* * Verify a filename that we got as an argument for a pathspec * entry. Note that a filename that begins with "-" never verifies * as true, because even if such a filename were to exist, we want @@ -207,7 +229,7 @@ void verify_filename(const char *prefix, { if (*arg == '-') die("bad flag '%s' used after filename", arg); - if (check_filename(prefix, arg) || !no_wildcard(arg)) + if (looks_like_pathspec(arg) || check_filename(prefix, arg)) return; die_verify_filename(prefix, arg, diagnose_misspelt_rev); } diff --git a/sha1_name.c b/sha1_name.c index 389276e9d3..5126853bb5 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -1408,7 +1408,7 @@ static void diagnose_invalid_sha1_path(const char *prefix, if (file_exists(filename)) die("Path '%s' exists on disk, but not in '%.*s'.", filename, object_name_len, object_name); - if (errno == ENOENT || errno == ENOTDIR) { + if (is_missing_file_error(errno)) { char *fullname = xstrfmt("%s%s", prefix, filename); if (!get_tree_entry(tree_sha1, fullname, @@ -1473,7 +1473,7 @@ static void diagnose_invalid_index_path(int stage, if (file_exists(filename)) die("Path '%s' exists on disk, but not in the index.", filename); - if (errno == ENOENT || errno == ENOTDIR) + if (is_missing_file_error(errno)) die("Path '%s' does not exist (neither on disk nor in the index).", filename); @@ -1511,6 +1511,7 @@ static int get_sha1_with_context_1(const char *name, memset(oc, 0, sizeof(*oc)); oc->mode = S_IFINVALID; + strbuf_init(&oc->symlink_path, 0); ret = get_sha1_1(name, namelen, sha1, flags); if (!ret) return ret; @@ -1549,7 +1550,8 @@ static int get_sha1_with_context_1(const char *name, namelen = strlen(cp); } - strlcpy(oc->path, cp, sizeof(oc->path)); + if (flags & GET_SHA1_RECORD_PATH) + oc->path = xstrdup(cp); if (!active_cache) read_cache(); @@ -1612,7 +1614,8 @@ static int get_sha1_with_context_1(const char *name, } } hashcpy(oc->tree, tree_sha1); - strlcpy(oc->path, filename, sizeof(oc->path)); + if (flags & GET_SHA1_RECORD_PATH) + oc->path = xstrdup(filename); free(new_filename); return ret; @@ -1638,9 +1641,9 @@ void maybe_die_on_misspelt_object_name(const char *name, const char *prefix) get_sha1_with_context_1(name, GET_SHA1_ONLY_TO_DIE, prefix, sha1, &oc); } -int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc) +int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *oc) { if (flags & GET_SHA1_FOLLOW_SYMLINKS && flags & GET_SHA1_ONLY_TO_DIE) die("BUG: incompatible flags for get_sha1_with_context"); - return get_sha1_with_context_1(str, flags, NULL, sha1, orc); + return get_sha1_with_context_1(str, flags, NULL, sha1, oc); } diff --git a/sha1dc/.gitattributes b/sha1dc/.gitattributes new file mode 100644 index 0000000000..da53f40548 --- /dev/null +++ b/sha1dc/.gitattributes @@ -0,0 +1 @@ +* whitespace=-indent-with-non-tab diff --git a/sha1dc/sha1.c b/sha1dc/sha1.c index 35e9dd5bf4..facea1bb56 100644 --- a/sha1dc/sha1.c +++ b/sha1dc/sha1.c @@ -5,9 +5,23 @@ * https://opensource.org/licenses/MIT ***/ -#include "cache.h" -#include "sha1dc/sha1.h" -#include "sha1dc/ubc_check.h" +#ifndef SHA1DC_NO_STANDARD_INCLUDES +#include <string.h> +#include <memory.h> +#include <stdio.h> +#include <stdlib.h> +#endif + +#ifdef SHA1DC_CUSTOM_INCLUDE_SHA1_C +#include SHA1DC_CUSTOM_INCLUDE_SHA1_C +#endif + +#ifndef SHA1DC_INIT_SAFE_HASH_DEFAULT +#define SHA1DC_INIT_SAFE_HASH_DEFAULT 1 +#endif + +#include "sha1.h" +#include "ubc_check.h" /* @@ -18,15 +32,48 @@ If you are compiling on a big endian platform and your compiler does not define one of these, you will have to add whatever macros your tool chain defines to indicate Big-Endianness. */ -#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || \ - (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __BIG_ENDIAN__)) || \ - defined(__BIG_ENDIAN__) || defined(__ARMEB__) || defined(__THUMBEB__) || defined(__AARCH64EB__) || \ - defined(_MIPSEB) || defined(__MIPSEB) || defined(__MIPSEB__) +#ifdef SHA1DC_BIGENDIAN +#undef SHA1DC_BIGENDIAN +#endif + +#if (defined(_BYTE_ORDER) || defined(__BYTE_ORDER) || defined(__BYTE_ORDER__)) + +#if ((defined(_BYTE_ORDER) && (_BYTE_ORDER == _BIG_ENDIAN)) || \ + (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || \ + (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __BIG_ENDIAN__)) ) +#define SHA1DC_BIGENDIAN +#endif -#define SHA1DC_BIGENDIAN 1 #else + +#if (defined(_BIG_ENDIAN) || defined(__BIG_ENDIAN) || defined(__BIG_ENDIAN__) || \ + defined(__ARMEB__) || defined(__THUMBEB__) || defined(__AARCH64EB__) || \ + defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || \ + defined(__sparc)) +#define SHA1DC_BIGENDIAN +#endif + +#endif + +#if (defined(SHA1DC_FORCE_LITTLEENDIAN) && defined(SHA1DC_BIGENDIAN)) #undef SHA1DC_BIGENDIAN -#endif /*ENDIANNESS SELECTION*/ +#endif +#if (defined(SHA1DC_FORCE_BIGENDIAN) && !defined(SHA1DC_BIGENDIAN)) +#define SHA1DC_BIGENDIAN +#endif +/*ENDIANNESS SELECTION*/ + +#if (defined SHA1DC_FORCE_UNALIGNED_ACCESS || \ + defined(__amd64__) || defined(__amd64) || defined(__x86_64__) || defined(__x86_64) || \ + defined(i386) || defined(__i386) || defined(__i386__) || defined(__i486__) || \ + defined(__i586__) || defined(__i686__) || defined(_M_IX86) || defined(__X86__) || \ + defined(_X86_) || defined(__THW_INTEL__) || defined(__I86__) || defined(__INTEL__) || \ + defined(__386) || defined(_M_X64) || defined(_M_AMD64)) + +#define SHA1DC_ALLOW_UNALIGNED_ACCESS + +#endif /*UNALIGNMENT DETECTION*/ + #define rotate_right(x,n) (((x)>>(n))|((x)<<(32-(n)))) #define rotate_left(x,n) (((x)<<(n))|((x)>>(32-(n)))) @@ -36,11 +83,11 @@ #define sha1_mix(W, t) (rotate_left(W[t - 3] ^ W[t - 8] ^ W[t - 14] ^ W[t - 16], 1)) -#if defined(SHA1DC_BIGENDIAN) +#ifdef SHA1DC_BIGENDIAN #define sha1_load(m, t, temp) { temp = m[t]; } #else #define sha1_load(m, t, temp) { temp = m[t]; sha1_bswap32(temp); } -#endif /* !defined(SHA1DC_BIGENDIAN) */ +#endif #define sha1_store(W, t, x) *(volatile uint32_t *)&W[t] = x @@ -869,6 +916,11 @@ static void sha1recompress_fast_ ## t (uint32_t ihvin[5], uint32_t ihvout[5], co ihvout[0] = ihvin[0] + a; ihvout[1] = ihvin[1] + b; ihvout[2] = ihvin[2] + c; ihvout[3] = ihvin[3] + d; ihvout[4] = ihvin[4] + e; \ } +#ifdef _MSC_VER +#pragma warning(push) +#pragma warning(disable: 4127) /* Complier complains about the checks in the above macro being constant. */ +#endif + #ifdef DOSTORESTATE0 SHA1_RECOMPRESS(0) #endif @@ -1189,6 +1241,10 @@ SHA1_RECOMPRESS(78) SHA1_RECOMPRESS(79) #endif +#ifdef _MSC_VER +#pragma warning(pop) +#endif + static void sha1_recompression_step(uint32_t step, uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5]) { switch (step) @@ -1662,7 +1718,7 @@ void SHA1DCInit(SHA1_CTX* ctx) ctx->ihv[3] = 0x10325476; ctx->ihv[4] = 0xC3D2E1F0; ctx->found_collision = 0; - ctx->safe_hash = 0; + ctx->safe_hash = SHA1DC_INIT_SAFE_HASH_DEFAULT; ctx->ubc_check = 1; ctx->detect_coll = 1; ctx->reduced_round_coll = 0; @@ -1710,6 +1766,7 @@ void SHA1DCSetCallback(SHA1_CTX* ctx, collision_block_callback callback) void SHA1DCUpdate(SHA1_CTX* ctx, const char* buf, size_t len) { unsigned left, fill; + if (len == 0) return; @@ -1728,7 +1785,13 @@ void SHA1DCUpdate(SHA1_CTX* ctx, const char* buf, size_t len) while (len >= 64) { ctx->total += 64; + +#if defined(SHA1DC_ALLOW_UNALIGNED_ACCESS) sha1_process(ctx, (uint32_t*)(buf)); +#else + memcpy(ctx->buffer, buf, 64); + sha1_process(ctx, (uint32_t*)(ctx->buffer)); +#endif /* defined(SHA1DC_ALLOW_UNALIGNED_ACCESS) */ buf += 64; len -= 64; } @@ -1788,22 +1851,6 @@ int SHA1DCFinal(unsigned char output[20], SHA1_CTX *ctx) return ctx->found_collision; } -void git_SHA1DCFinal(unsigned char hash[20], SHA1_CTX *ctx) -{ - if (!SHA1DCFinal(hash, ctx)) - return; - die("SHA-1 appears to be part of a collision attack: %s", - sha1_to_hex(hash)); -} - -void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, unsigned long len) -{ - const char *data = vdata; - /* We expect an unsigned long, but sha1dc only takes an int */ - while (len > INT_MAX) { - SHA1DCUpdate(ctx, data, INT_MAX); - data += INT_MAX; - len -= INT_MAX; - } - SHA1DCUpdate(ctx, data, len); -} +#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C +#include SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C +#endif diff --git a/sha1dc/sha1.h b/sha1dc/sha1.h index bd8bd928fb..1e4e94be54 100644 --- a/sha1dc/sha1.h +++ b/sha1dc/sha1.h @@ -4,6 +4,7 @@ * See accompanying file LICENSE.txt or copy at * https://opensource.org/licenses/MIT ***/ + #ifndef SHA1DC_SHA1_H #define SHA1DC_SHA1_H @@ -11,36 +12,30 @@ extern "C" { #endif -/* uses SHA-1 message expansion to expand the first 16 words of W[] to 80 words */ -/* void sha1_message_expansion(uint32_t W[80]); */ - -/* sha-1 compression function; first version takes a message block pre-parsed as 16 32-bit integers, second version takes an already expanded message) */ -/* void sha1_compression(uint32_t ihv[5], const uint32_t m[16]); -void sha1_compression_W(uint32_t ihv[5], const uint32_t W[80]); */ +#ifndef SHA1DC_NO_STANDARD_INCLUDES +#include <stdint.h> +#endif -/* same as sha1_compression_W, but additionally store intermediate states */ +/* sha-1 compression function that takes an already expanded message, and additionally store intermediate states */ /* only stores states ii (the state between step ii-1 and step ii) when DOSTORESTATEii is defined in ubc_check.h */ void sha1_compression_states(uint32_t[5], const uint32_t[16], uint32_t[80], uint32_t[80][5]); /* -// function type for sha1_recompression_step_T (uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5]) -// where 0 <= T < 80 -// me2 is an expanded message (the expansion of an original message block XOR'ed with a disturbance vector's message block difference) -// state is the internal state (a,b,c,d,e) before step T of the SHA-1 compression function while processing the original message block -// the function will return: -// ihvin: the reconstructed input chaining value -// ihvout: the reconstructed output chaining value +// Function type for sha1_recompression_step_T (uint32_t ihvin[5], uint32_t ihvout[5], const uint32_t me2[80], const uint32_t state[5]). +// Where 0 <= T < 80 +// me2 is an expanded message (the expansion of an original message block XOR'ed with a disturbance vector's message block difference.) +// state is the internal state (a,b,c,d,e) before step T of the SHA-1 compression function while processing the original message block. +// The function will return: +// ihvin: The reconstructed input chaining value. +// ihvout: The reconstructed output chaining value. */ typedef void(*sha1_recompression_type)(uint32_t*, uint32_t*, const uint32_t*, const uint32_t*); -/* table of sha1_recompression_step_0, ... , sha1_recompression_step_79 */ -/* extern sha1_recompression_type sha1_recompression_step[80];*/ - -/* a callback function type that can be set to be called when a collision block has been found: */ +/* A callback function type that can be set to be called when a collision block has been found: */ /* void collision_block_callback(uint64_t byteoffset, const uint32_t ihvin1[5], const uint32_t ihvin2[5], const uint32_t m1[80], const uint32_t m2[80]) */ typedef void(*collision_block_callback)(uint64_t, const uint32_t*, const uint32_t*, const uint32_t*, const uint32_t*); -/* the SHA-1 context */ +/* The SHA-1 context. */ typedef struct { uint64_t total; uint32_t ihv[5]; @@ -59,30 +54,34 @@ typedef struct { uint32_t states[80][5]; } SHA1_CTX; -/* initialize SHA-1 context */ +/* Initialize SHA-1 context. */ void SHA1DCInit(SHA1_CTX*); /* -// function to enable safe SHA-1 hashing: -// collision attacks are thwarted by hashing a detected near-collision block 3 times -// think of it as extending SHA-1 from 80-steps to 240-steps for such blocks: -// the best collision attacks against SHA-1 have complexity about 2^60, -// thus for 240-steps an immediate lower-bound for the best cryptanalytic attacks would 2^180 -// an attacker would be better off using a generic birthday search of complexity 2^80 -// -// enabling safe SHA-1 hashing will result in the correct SHA-1 hash for messages where no collision attack was detected -// but it will result in a different SHA-1 hash for messages where a collision attack was detected -// this will automatically invalidate SHA-1 based digital signature forgeries -// enabled by default + Function to enable safe SHA-1 hashing: + Collision attacks are thwarted by hashing a detected near-collision block 3 times. + Think of it as extending SHA-1 from 80-steps to 240-steps for such blocks: + The best collision attacks against SHA-1 have complexity about 2^60, + thus for 240-steps an immediate lower-bound for the best cryptanalytic attacks would be 2^180. + An attacker would be better off using a generic birthday search of complexity 2^80. + + Enabling safe SHA-1 hashing will result in the correct SHA-1 hash for messages where no collision attack was detected, + but it will result in a different SHA-1 hash for messages where a collision attack was detected. + This will automatically invalidate SHA-1 based digital signature forgeries. + Enabled by default. */ void SHA1DCSetSafeHash(SHA1_CTX*, int); -/* function to disable or enable the use of Unavoidable Bitconditions (provides a significant speed up) */ -/* enabled by default */ +/* + Function to disable or enable the use of Unavoidable Bitconditions (provides a significant speed up). + Enabled by default + */ void SHA1DCSetUseUBC(SHA1_CTX*, int); -/* function to disable or enable the use of Collision Detection */ -/* enabled by default */ +/* + Function to disable or enable the use of Collision Detection. + Enabled by default. + */ void SHA1DCSetUseDetectColl(SHA1_CTX*, int); /* function to disable or enable the detection of reduced-round SHA-1 collisions */ @@ -100,23 +99,12 @@ void SHA1DCUpdate(SHA1_CTX*, const char*, size_t); /* returns: 0 = no collision detected, otherwise = collision found => warn user for active attack */ int SHA1DCFinal(unsigned char[20], SHA1_CTX*); -/* - * Same as SHA1DCFinal, but convert collision attack case into a verbose die(). - */ -void git_SHA1DCFinal(unsigned char [20], SHA1_CTX *); - -/* - * Same as SHA1DCUpdate, but adjust types to match git's usual interface. - */ -void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, unsigned long len); - -#define platform_SHA_CTX SHA1_CTX -#define platform_SHA1_Init SHA1DCInit -#define platform_SHA1_Update git_SHA1DCUpdate -#define platform_SHA1_Final git_SHA1DCFinal - #if defined(__cplusplus) } #endif -#endif /* SHA1DC_SHA1_H */ +#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H +#include SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H +#endif + +#endif diff --git a/sha1dc/ubc_check.c b/sha1dc/ubc_check.c index 089dd4743d..b3beff2afb 100644 --- a/sha1dc/ubc_check.c +++ b/sha1dc/ubc_check.c @@ -24,8 +24,13 @@ // ubc_check has been verified against ubc_check_verify using the 'ubc_check_test' program in the tools section */ -#include "git-compat-util.h" -#include "sha1dc/ubc_check.h" +#ifndef SHA1DC_NO_STANDARD_INCLUDES +#include <stdint.h> +#endif +#ifdef SHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C +#include SHA1DC_CUSTOM_INCLUDE_UBC_CHECK_C +#endif +#include "ubc_check.h" static const uint32_t DV_I_43_0_bit = (uint32_t)(1) << 0; static const uint32_t DV_I_44_0_bit = (uint32_t)(1) << 1; @@ -361,3 +366,7 @@ if (mask) { dvmask[0]=mask; } + +#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_C +#include SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_C +#endif diff --git a/sha1dc/ubc_check.h b/sha1dc/ubc_check.h index b64c306d77..d7e17dc734 100644 --- a/sha1dc/ubc_check.h +++ b/sha1dc/ubc_check.h @@ -20,13 +20,17 @@ // thus one needs to do the recompression check for each DV that has its bit set */ -#ifndef UBC_CHECK_H -#define UBC_CHECK_H +#ifndef SHA1DC_UBC_CHECK_H +#define SHA1DC_UBC_CHECK_H #if defined(__cplusplus) extern "C" { #endif +#ifndef SHA1DC_NO_STANDARD_INCLUDES +#include <stdint.h> +#endif + #define DVMASKSIZE 1 typedef struct { int dvType; int dvK; int dvB; int testt; int maski; int maskb; uint32_t dm[80]; } dv_info_t; extern dv_info_t sha1_dvs[]; @@ -41,4 +45,8 @@ void ubc_check(const uint32_t W[80], uint32_t dvmask[DVMASKSIZE]); } #endif -#endif /* UBC_CHECK_H */ +#ifdef SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_H +#include SHA1DC_CUSTOM_TRAILING_INCLUDE_UBC_CHECK_H +#endif + +#endif diff --git a/sha1dc_git.c b/sha1dc_git.c new file mode 100644 index 0000000000..4d32b4f77e --- /dev/null +++ b/sha1dc_git.c @@ -0,0 +1,24 @@ +/* + * This code is included at the end of sha1dc/sha1.c with the + * SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_C macro. + */ + +void git_SHA1DCFinal(unsigned char hash[20], SHA1_CTX *ctx) +{ + if (!SHA1DCFinal(hash, ctx)) + return; + die("SHA-1 appears to be part of a collision attack: %s", + sha1_to_hex(hash)); +} + +void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, unsigned long len) +{ + const char *data = vdata; + /* We expect an unsigned long, but sha1dc only takes an int */ + while (len > INT_MAX) { + SHA1DCUpdate(ctx, data, INT_MAX); + data += INT_MAX; + len -= INT_MAX; + } + SHA1DCUpdate(ctx, data, len); +} diff --git a/sha1dc_git.h b/sha1dc_git.h new file mode 100644 index 0000000000..a8a5c1da16 --- /dev/null +++ b/sha1dc_git.h @@ -0,0 +1,19 @@ +/* + * This code is included at the end of sha1dc/sha1.h with the + * SHA1DC_CUSTOM_TRAILING_INCLUDE_SHA1_H macro. + */ + +/* + * Same as SHA1DCFinal, but convert collision attack case into a verbose die(). + */ +void git_SHA1DCFinal(unsigned char [20], SHA1_CTX *); + +/* + * Same as SHA1DCUpdate, but adjust types to match git's usual interface. + */ +void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, unsigned long len); + +#define platform_SHA_CTX SHA1_CTX +#define platform_SHA1_Init SHA1DCInit +#define platform_SHA1_Update git_SHA1DCUpdate +#define platform_SHA1_Final git_SHA1DCFinal diff --git a/sub-process.h b/sub-process.h index 7d451e1cde..d9a45cd359 100644 --- a/sub-process.h +++ b/sub-process.h @@ -7,7 +7,7 @@ /* * Generic implementation of background process infrastructure. - * See Documentation/technical/api-background-process.txt. + * See: Documentation/technical/api-sub-process.txt */ /* data structures */ diff --git a/submodule.c b/submodule.c index bf5a93d16f..1b8a3b575d 100644 --- a/submodule.c +++ b/submodule.c @@ -16,9 +16,10 @@ #include "quote.h" #include "remote.h" #include "worktree.h" +#include "parse-options.h" static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND; -static int config_update_recurse_submodules = RECURSE_SUBMODULES_DEFAULT; +static int config_update_recurse_submodules = RECURSE_SUBMODULES_OFF; static int parallel_jobs = 1; static struct string_list changed_submodule_paths = STRING_LIST_INIT_DUP; static int initialized_fetch_ref_tips; @@ -153,7 +154,8 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt, } } -int submodule_config(const char *var, const char *value, void *cb) +/* For loading from the .gitmodules file. */ +static int git_modules_config(const char *var, const char *value, void *cb) { if (!strcmp(var, "submodule.fetchjobs")) { parallel_jobs = git_config_int(var, value); @@ -169,6 +171,56 @@ int submodule_config(const char *var, const char *value, void *cb) return 0; } +/* 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); + } +} + +/* Cheap function that only determines if we're interested in submodules at all */ +int git_default_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; +} + +int option_parse_recurse_submodules_worktree_updater(const struct option *opt, + const char *arg, int unset) +{ + if (unset) { + config_update_recurse_submodules = RECURSE_SUBMODULES_OFF; + return 0; + } + if (arg) + config_update_recurse_submodules = + parse_update_recurse_submodules_arg(opt->long_name, + arg); + else + config_update_recurse_submodules = RECURSE_SUBMODULES_ON; + + return 0; +} + +void load_submodule_cache(void) +{ + if (config_update_recurse_submodules == RECURSE_SUBMODULES_OFF) + return; + + gitmodules_config(); + git_config(submodule_config, NULL); +} + void gitmodules_config(void) { const char *work_tree = get_git_work_tree(); @@ -196,7 +248,8 @@ void gitmodules_config(void) } if (!gitmodules_is_unmerged) - git_config_from_file(submodule_config, gitmodules_path.buf, NULL); + git_config_from_file(git_modules_config, + gitmodules_path.buf, NULL); strbuf_release(&gitmodules_path); } } @@ -207,7 +260,7 @@ void gitmodules_config_sha1(const unsigned char *commit_sha1) unsigned char sha1[20]; if (gitmodule_sha1_from_commit(commit_sha1, sha1, &rev)) { - git_config_from_blob_sha1(submodule_config, rev.buf, + git_config_from_blob_sha1(git_modules_config, rev.buf, sha1, NULL); } strbuf_release(&rev); @@ -660,11 +713,6 @@ void set_config_fetch_recurse_submodules(int value) config_fetch_recurse_submodules = value; } -void set_config_update_recurse_submodules(int value) -{ - config_update_recurse_submodules = value; -} - int should_update_submodules(void) { return config_update_recurse_submodules == RECURSE_SUBMODULES_ON; diff --git a/submodule.h b/submodule.h index 8fb0f25498..cbe5c1726f 100644 --- a/submodule.h +++ b/submodule.h @@ -39,6 +39,12 @@ 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 gitmodules_config_sha1(const unsigned char *commit_sha1); extern int is_submodule_initialized(const char *path); @@ -69,7 +75,6 @@ extern void show_submodule_inline_diff(FILE *f, const char *path, const char *del, const char *add, const char *reset, const struct diff_options *opt); extern void set_config_fetch_recurse_submodules(int value); -extern void set_config_update_recurse_submodules(int value); /* Check if we want to update any submodule.*/ extern int should_update_submodules(void); /* @@ -803,9 +803,9 @@ use these, and "test_set_prereq" for how to define your own. Test is not run by root user, and an attempt to write to an unwritable file is expected to fail correctly. - - LIBPCRE + - PCRE - Git was compiled with USE_LIBPCRE=YesPlease. Wrap any tests + Git was compiled with support for PCRE. Wrap any tests that use git-grep --perl-regexp or git-grep -P in these. - CASE_INSENSITIVE_FS @@ -817,6 +817,10 @@ use these, and "test_set_prereq" for how to define your own. Test is run on a filesystem which converts decomposed utf-8 (nfd) to precomposed utf-8 (nfc). + - PTHREADS + + Git wasn't compiled with NO_PTHREADS=YesPlease. + Tips for Writing Tests ---------------------- diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c index fba85e7da5..05d8c4d8af 100644 --- a/t/helper/test-ref-store.c +++ b/t/helper/test-ref-store.c @@ -93,12 +93,13 @@ static int cmd_create_symref(struct ref_store *refs, const char **argv) static int cmd_delete_refs(struct ref_store *refs, const char **argv) { unsigned int flags = arg_flags(*argv++, "flags"); + const char *msg = *argv++; struct string_list refnames = STRING_LIST_INIT_NODUP; while (*argv) string_list_append(&refnames, *argv++); - return refs_delete_refs(refs, &refnames, flags); + return refs_delete_refs(refs, msg, &refnames, flags); } static int cmd_rename_ref(struct ref_store *refs, const char **argv) diff --git a/t/lib-submodule-update.sh b/t/lib-submodule-update.sh index 58bd4aeb2c..2d26f86800 100755 --- a/t/lib-submodule-update.sh +++ b/t/lib-submodule-update.sh @@ -781,8 +781,9 @@ test_submodule_forced_switch () { # - Removing a submodule with a git directory absorbs the submodules # git directory first into the superproject. -test_submodule_switch_recursing () { - command="$1" +test_submodule_switch_recursing_with_args () { + cmd_args="$1" + command="git $cmd_args --recurse-submodules" RESULTDS=success if test "$KNOWN_FAILURE_DIRECTORY_SUBMODULE_CONFLICTS" = 1 then @@ -984,6 +985,18 @@ test_submodule_switch_recursing () { ) ' + test_expect_success "git -c submodule.recurse=true $cmd_args: modified submodule updates submodule work tree" ' + prolog && + reset_work_tree_to_interested add_sub1 && + ( + cd submodule_update && + git branch -t modify_sub1 origin/modify_sub1 && + git -c submodule.recurse=true $cmd_args modify_sub1 && + test_superproject_content origin/modify_sub1 && + test_submodule_content sub1 origin/modify_sub1 + ) + ' + # Updating a submodule to an invalid sha1 doesn't update the # superproject nor the submodule's work tree. test_expect_success "$command: updating to a missing submodule commit fails" ' @@ -1016,8 +1029,9 @@ test_submodule_switch_recursing () { # Test that submodule contents are updated when switching between commits # that change a submodule, but throwing away local changes in # the superproject as well as the submodule is allowed. -test_submodule_forced_switch_recursing () { - command="$1" +test_submodule_forced_switch_recursing_with_args () { + cmd_args="$1" + command="git $cmd_args --recurse-submodules" RESULT=success if test "$KNOWN_FAILURE_DIRECTORY_SUBMODULE_CONFLICTS" = 1 then diff --git a/t/perf/README b/t/perf/README index de2fe15696..21321a0f36 100644 --- a/t/perf/README +++ b/t/perf/README @@ -60,7 +60,22 @@ You can set the following variables (also in your config.mak): GIT_PERF_MAKE_OPTS Options to use when automatically building a git tree for - performance testing. E.g., -j6 would be useful. + performance testing. E.g., -j6 would be useful. Passed + directly to make as "make $GIT_PERF_MAKE_OPTS". + + GIT_PERF_MAKE_COMMAND + An arbitrary command that'll be run in place of the make + command, if set the GIT_PERF_MAKE_OPTS variable is + ignored. Useful in cases where source tree changes might + require issuing a different make command to different + revisions. + + This can be (ab)used to monkeypatch or otherwise change the + tree about to be built. Note that the build directory can be + re-used for subsequent runs so the make command might get + executed multiple times on the same tree, but don't count on + any of that, that's an implementation detail that might change + in the future. GIT_PERF_REPO GIT_PERF_LARGE_REPO diff --git a/t/perf/p4220-log-grep-engines.sh b/t/perf/p4220-log-grep-engines.sh new file mode 100755 index 0000000000..2bc47ded4d --- /dev/null +++ b/t/perf/p4220-log-grep-engines.sh @@ -0,0 +1,53 @@ +#!/bin/sh + +test_description="Comparison of git-log's --grep regex engines + +Set GIT_PERF_4220_LOG_OPTS in the environment to pass options to +git-grep. Make sure to include a leading space, +e.g. GIT_PERF_4220_LOG_OPTS=' -i'. Some options to try: + + -i + --invert-grep + -i --invert-grep +" + +. ./perf-lib.sh + +test_perf_large_repo +test_checkout_worktree + +for pattern in \ + 'how.to' \ + '^how to' \ + '[how] to' \ + '\(e.t[^ ]*\|v.ry\) rare' \ + 'm\(ú\|u\)lt.b\(æ\|y\)te' +do + for engine in basic extended perl + do + if test $engine != "basic" + then + # Poor man's basic -> extended converter. + pattern=$(echo $pattern | sed 's/\\//g') + fi + if test $engine = "perl" && ! test_have_prereq PCRE + then + prereq="PCRE" + else + prereq="" + fi + test_perf $prereq "$engine log$GIT_PERF_4220_LOG_OPTS --grep='$pattern'" " + git -c grep.patternType=$engine log --pretty=format:%h$GIT_PERF_4220_LOG_OPTS --grep='$pattern' >'out.$engine' || : + " + done + + test_expect_success "assert that all engines found the same for$GIT_PERF_4220_LOG_OPTS '$pattern'" ' + test_cmp out.basic out.extended && + if test_have_prereq PCRE + then + test_cmp out.basic out.perl + fi + ' +done + +test_done diff --git a/t/perf/p4221-log-grep-engines-fixed.sh b/t/perf/p4221-log-grep-engines-fixed.sh new file mode 100755 index 0000000000..060971265a --- /dev/null +++ b/t/perf/p4221-log-grep-engines-fixed.sh @@ -0,0 +1,44 @@ +#!/bin/sh + +test_description="Comparison of git-log's --grep regex engines with -F + +Set GIT_PERF_4221_LOG_OPTS in the environment to pass options to +git-grep. Make sure to include a leading space, +e.g. GIT_PERF_4221_LOG_OPTS=' -i'. Some options to try: + + -i + --invert-grep + -i --invert-grep +" + +. ./perf-lib.sh + +test_perf_large_repo +test_checkout_worktree + +for pattern in 'int' 'uncommon' 'æ' +do + for engine in fixed basic extended perl + do + if test $engine = "perl" && ! test_have_prereq PCRE + then + prereq="PCRE" + else + prereq="" + fi + test_perf $prereq "$engine log$GIT_PERF_4221_LOG_OPTS --grep='$pattern'" " + git -c grep.patternType=$engine log --pretty=format:%h$GIT_PERF_4221_LOG_OPTS --grep='$pattern' >'out.$engine' || : + " + done + + test_expect_success "assert that all engines found the same for$GIT_PERF_4221_LOG_OPTS '$pattern'" ' + test_cmp out.fixed out.basic && + test_cmp out.fixed out.extended && + if test_have_prereq PCRE + then + test_cmp out.fixed out.perl + fi + ' +done + +test_done diff --git a/t/perf/p7820-grep-engines.sh b/t/perf/p7820-grep-engines.sh new file mode 100755 index 0000000000..62aba19e76 --- /dev/null +++ b/t/perf/p7820-grep-engines.sh @@ -0,0 +1,56 @@ +#!/bin/sh + +test_description="Comparison of git-grep's regex engines + +Set GIT_PERF_7820_GREP_OPTS in the environment to pass options to +git-grep. Make sure to include a leading space, +e.g. GIT_PERF_7820_GREP_OPTS=' -i'. Some options to try: + + -i + -w + -v + -vi + -vw + -viw +" + +. ./perf-lib.sh + +test_perf_large_repo +test_checkout_worktree + +for pattern in \ + 'how.to' \ + '^how to' \ + '[how] to' \ + '\(e.t[^ ]*\|v.ry\) rare' \ + 'm\(ú\|u\)lt.b\(æ\|y\)te' +do + for engine in basic extended perl + do + if test $engine != "basic" + then + # Poor man's basic -> extended converter. + pattern=$(echo "$pattern" | sed 's/\\//g') + fi + if test $engine = "perl" && ! test_have_prereq PCRE + then + prereq="PCRE" + else + prereq="" + fi + test_perf $prereq "$engine grep$GIT_PERF_7820_GREP_OPTS '$pattern'" " + git -c grep.patternType=$engine grep$GIT_PERF_7820_GREP_OPTS -- '$pattern' >'out.$engine' || : + " + done + + test_expect_success "assert that all engines found the same for$GIT_PERF_7820_GREP_OPTS '$pattern'" ' + test_cmp out.basic out.extended && + if test_have_prereq PCRE + then + test_cmp out.basic out.perl + fi + ' +done + +test_done diff --git a/t/perf/p7821-grep-engines-fixed.sh b/t/perf/p7821-grep-engines-fixed.sh new file mode 100755 index 0000000000..c7ef1e198f --- /dev/null +++ b/t/perf/p7821-grep-engines-fixed.sh @@ -0,0 +1,41 @@ +#!/bin/sh + +test_description="Comparison of git-grep's regex engines with -F + +Set GIT_PERF_7821_GREP_OPTS in the environment to pass options to +git-grep. Make sure to include a leading space, +e.g. GIT_PERF_7821_GREP_OPTS=' -w'. See p7820-grep-engines.sh for more +options to try. +" + +. ./perf-lib.sh + +test_perf_large_repo +test_checkout_worktree + +for pattern in 'int' 'uncommon' 'æ' +do + for engine in fixed basic extended perl + do + if test $engine = "perl" && ! test_have_prereq PCRE + then + prereq="PCRE" + else + prereq="" + fi + test_perf $prereq "$engine grep$GIT_PERF_7821_GREP_OPTS $pattern" " + git -c grep.patternType=$engine grep$GIT_PERF_7821_GREP_OPTS $pattern >'out.$engine' || : + " + done + + test_expect_success "assert that all engines found the same for$GIT_PERF_7821_GREP_OPTS $pattern" ' + test_cmp out.fixed out.basic && + test_cmp out.fixed out.extended && + if test_have_prereq PCRE + then + test_cmp out.fixed out.perl + fi + ' +done + +test_done diff --git a/t/perf/run b/t/perf/run index c788d713ae..beb4acc0e4 100755 --- a/t/perf/run +++ b/t/perf/run @@ -24,6 +24,7 @@ run_one_dir () { unpack_git_rev () { rev=$1 + echo "=== Unpacking $rev in build/$rev ===" mkdir -p build/$rev (cd "$(git rev-parse --show-cdup)" && git archive --format=tar $rev) | (cd build/$rev && tar x) @@ -37,8 +38,16 @@ build_git_rev () { cp "../../$config" "build/$rev/" fi done - (cd build/$rev && make $GIT_PERF_MAKE_OPTS) || - die "failed to build revision '$mydir'" + echo "=== Building $rev ===" + ( + cd build/$rev && + if test -n "$GIT_PERF_MAKE_COMMAND" + then + sh -c "$GIT_PERF_MAKE_COMMAND" + else + make $GIT_PERF_MAKE_OPTS + fi + ) || die "failed to build revision '$mydir'" } run_dirs_helper () { diff --git a/t/t1013-read-tree-submodule.sh b/t/t1013-read-tree-submodule.sh index 7019d0a04f..91a6fafcb4 100755 --- a/t/t1013-read-tree-submodule.sh +++ b/t/t1013-read-tree-submodule.sh @@ -8,9 +8,9 @@ test_description='read-tree can handle submodules' KNOWN_FAILURE_DIRECTORY_SUBMODULE_CONFLICTS=1 KNOWN_FAILURE_SUBMODULE_OVERWRITE_IGNORED_UNTRACKED=1 -test_submodule_switch_recursing "git read-tree --recurse-submodules -u -m" +test_submodule_switch_recursing_with_args "read-tree -u -m" -test_submodule_forced_switch_recursing "git read-tree --recurse-submodules -u --reset" +test_submodule_forced_switch_recursing_with_args "read-tree -u --reset" test_submodule_switch "git read-tree -u -m" diff --git a/t/t1308-config-set.sh b/t/t1308-config-set.sh index ff50960cca..e495a61616 100755 --- a/t/t1308-config-set.sh +++ b/t/t1308-config-set.sh @@ -183,11 +183,22 @@ test_expect_success 'proper error on non-existent files' ' test_cmp expect actual ' +test_expect_success 'proper error on directory "files"' ' + echo "Error (-1) reading configuration file a-directory." >expect && + mkdir a-directory && + test_expect_code 2 test-config configset_get_value foo.bar a-directory 2>output && + grep "^warning:" output && + grep "^Error" output >actual && + test_cmp expect actual +' + test_expect_success POSIXPERM,SANITY 'proper error on non-accessible files' ' chmod -r .git/config && test_when_finished "chmod +r .git/config" && echo "Error (-1) reading configuration file .git/config." >expect && - test_expect_code 2 test-config configset_get_value foo.bar .git/config 2>actual && + test_expect_code 2 test-config configset_get_value foo.bar .git/config 2>output && + grep "^warning:" output && + grep "^Error" output >actual && test_cmp expect actual ' diff --git a/t/t1405-main-ref-store.sh b/t/t1405-main-ref-store.sh index 490521f8cb..e8115df5ba 100755 --- a/t/t1405-main-ref-store.sh +++ b/t/t1405-main-ref-store.sh @@ -31,7 +31,7 @@ test_expect_success 'create_symref(FOO, refs/heads/master)' ' test_expect_success 'delete_refs(FOO, refs/tags/new-tag)' ' git rev-parse FOO -- && git rev-parse refs/tags/new-tag -- && - $RUN delete-refs 0 FOO refs/tags/new-tag && + $RUN delete-refs 0 nothing FOO refs/tags/new-tag && test_must_fail git rev-parse FOO -- && test_must_fail git rev-parse refs/tags/new-tag -- ' diff --git a/t/t1406-submodule-ref-store.sh b/t/t1406-submodule-ref-store.sh index 13b5454c56..c32d4cc465 100755 --- a/t/t1406-submodule-ref-store.sh +++ b/t/t1406-submodule-ref-store.sh @@ -31,7 +31,7 @@ test_expect_success 'create_symref() not allowed' ' ' test_expect_success 'delete_refs() not allowed' ' - test_must_fail $RUN delete-refs 0 FOO refs/tags/new-tag + test_must_fail $RUN delete-refs 0 nothing FOO refs/tags/new-tag ' test_expect_success 'rename_refs() not allowed' ' diff --git a/t/t2013-checkout-submodule.sh b/t/t2013-checkout-submodule.sh index aa35223369..6ef15738e4 100755 --- a/t/t2013-checkout-submodule.sh +++ b/t/t2013-checkout-submodule.sh @@ -64,9 +64,9 @@ test_expect_success '"checkout <submodule>" honors submodule.*.ignore from .git/ ' KNOWN_FAILURE_DIRECTORY_SUBMODULE_CONFLICTS=1 -test_submodule_switch_recursing "git checkout --recurse-submodules" +test_submodule_switch_recursing_with_args "checkout" -test_submodule_forced_switch_recursing "git checkout -f --recurse-submodules" +test_submodule_forced_switch_recursing_with_args "checkout -f" test_submodule_switch "git checkout" diff --git a/t/t3070-wildmatch.sh b/t/t3070-wildmatch.sh index ef509df351..7ca69f4bed 100755 --- a/t/t3070-wildmatch.sh +++ b/t/t3070-wildmatch.sh @@ -135,7 +135,6 @@ match 1 x '5' '[[:xdigit:]]' match 1 x 'f' '[[:xdigit:]]' match 1 x 'D' '[[:xdigit:]]' match 1 x '_' '[[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]' -match 1 x '_' '[[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]' match 1 x '.' '[^[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:lower:][:space:][:upper:][:xdigit:]]' match 1 x '5' '[a-c[:digit:]x-z]' match 1 x 'b' '[a-c[:digit:]x-z]' diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh index fe62e7c775..10f8f026ff 100755 --- a/t/t3200-branch.sh +++ b/t/t3200-branch.sh @@ -338,7 +338,7 @@ test_expect_success 'git branch -m s/s s should work when s/t is deleted' ' test_expect_success 'config information was renamed, too' ' test $(git config branch.s.dummy) = Hello && - test_must_fail git config branch.s/s/dummy + test_must_fail git config branch.s/s.dummy ' test_expect_success 'deleting a symref' ' diff --git a/t/t3600-rm.sh b/t/t3600-rm.sh index 5f9913ba33..f8568f8841 100755 --- a/t/t3600-rm.sh +++ b/t/t3600-rm.sh @@ -97,9 +97,9 @@ test_expect_success FUNNYNAMES \ embedded'" test_expect_success SANITY 'Test that "git rm -f" fails if its rm fails' ' + test_when_finished "chmod 775 ." && chmod a-w . && - test_must_fail git rm -f baz && - chmod 775 . + test_must_fail git rm -f baz ' test_expect_success \ diff --git a/t/t4051-diff-function-context.sh b/t/t4051-diff-function-context.sh index 6154acb456..3e6b485ecb 100755 --- a/t/t4051-diff-function-context.sh +++ b/t/t4051-diff-function-context.sh @@ -72,7 +72,8 @@ test_expect_success 'setup' ' # overlap function context of 1st change and -u context of 2nd change grep -v "delete me from hello" <"$dir/hello.c" >file.c && - sed 2p <"$dir/dummy.c" >>file.c && + sed "2a\\ + extra line" <"$dir/dummy.c" >>file.c && commit_and_tag changed_hello_dummy file.c && git checkout initial && diff --git a/t/t4061-diff-indent.sh b/t/t4061-diff-indent.sh index 556450609b..2affd7a100 100755 --- a/t/t4061-diff-indent.sh +++ b/t/t4061-diff-indent.sh @@ -152,26 +152,28 @@ test_expect_success 'prepare' ' EOF ' +# --- diff tests ---------------------------------------------------------- + test_expect_success 'diff: ugly spaces' ' - git diff old new -- spaces.txt >out && + git diff --no-indent-heuristic old new -- spaces.txt >out && compare_diff spaces-expect out ' +test_expect_success 'diff: --no-indent-heuristic overrides config' ' + git -c diff.indentHeuristic=true diff --no-indent-heuristic old new -- spaces.txt >out2 && + compare_diff spaces-expect out2 +' + test_expect_success 'diff: nice spaces with --indent-heuristic' ' - git diff --indent-heuristic old new -- spaces.txt >out-compacted && + git -c diff.indentHeuristic=false diff --indent-heuristic old new -- spaces.txt >out-compacted && compare_diff spaces-compacted-expect out-compacted ' -test_expect_success 'diff: nice spaces with diff.indentHeuristic' ' +test_expect_success 'diff: nice spaces with diff.indentHeuristic=true' ' git -c diff.indentHeuristic=true diff old new -- spaces.txt >out-compacted2 && compare_diff spaces-compacted-expect out-compacted2 ' -test_expect_success 'diff: --no-indent-heuristic overrides config' ' - git -c diff.indentHeuristic=true diff --no-indent-heuristic old new -- spaces.txt >out2 && - compare_diff spaces-expect out2 -' - test_expect_success 'diff: --indent-heuristic with --patience' ' git diff --indent-heuristic --patience old new -- spaces.txt >out-compacted3 && compare_diff spaces-compacted-expect out-compacted3 @@ -183,7 +185,7 @@ test_expect_success 'diff: --indent-heuristic with --histogram' ' ' test_expect_success 'diff: ugly functions' ' - git diff old new -- functions.c >out && + git diff --no-indent-heuristic old new -- functions.c >out && compare_diff functions-expect out ' @@ -192,25 +194,175 @@ test_expect_success 'diff: nice functions with --indent-heuristic' ' compare_diff functions-compacted-expect out-compacted ' -test_expect_success 'blame: ugly spaces' ' - git blame old..new -- spaces.txt >out-blame && - compare_blame spaces-expect out-blame -' +# --- blame tests --------------------------------------------------------- test_expect_success 'blame: nice spaces with --indent-heuristic' ' git blame --indent-heuristic old..new -- spaces.txt >out-blame-compacted && compare_blame spaces-compacted-expect out-blame-compacted ' -test_expect_success 'blame: nice spaces with diff.indentHeuristic' ' +test_expect_success 'blame: nice spaces with diff.indentHeuristic=true' ' git -c diff.indentHeuristic=true blame old..new -- spaces.txt >out-blame-compacted2 && compare_blame spaces-compacted-expect out-blame-compacted2 ' +test_expect_success 'blame: ugly spaces with --no-indent-heuristic' ' + git blame --no-indent-heuristic old..new -- spaces.txt >out-blame && + compare_blame spaces-expect out-blame +' + +test_expect_success 'blame: ugly spaces with diff.indentHeuristic=false' ' + git -c diff.indentHeuristic=false blame old..new -- spaces.txt >out-blame2 && + compare_blame spaces-expect out-blame2 +' + test_expect_success 'blame: --no-indent-heuristic overrides config' ' - git -c diff.indentHeuristic=true blame --no-indent-heuristic old..new -- spaces.txt >out-blame2 && + git -c diff.indentHeuristic=true blame --no-indent-heuristic old..new -- spaces.txt >out-blame3 && git blame old..new -- spaces.txt >out-blame && - compare_blame spaces-expect out-blame2 + compare_blame spaces-expect out-blame3 +' + +test_expect_success 'blame: --indent-heuristic overrides config' ' + git -c diff.indentHeuristic=false blame --indent-heuristic old..new -- spaces.txt >out-blame-compacted3 && + compare_blame spaces-compacted-expect out-blame-compacted2 +' + +# --- diff-tree tests ----------------------------------------------------- + +test_expect_success 'diff-tree: nice spaces with --indent-heuristic' ' + git diff-tree --indent-heuristic -p old new -- spaces.txt >out-diff-tree-compacted && + compare_diff spaces-compacted-expect out-diff-tree-compacted +' + +test_expect_success 'diff-tree: nice spaces with diff.indentHeuristic=true' ' + git -c diff.indentHeuristic=true diff-tree -p old new -- spaces.txt >out-diff-tree-compacted2 && + compare_diff spaces-compacted-expect out-diff-tree-compacted2 +' + +test_expect_success 'diff-tree: ugly spaces with --no-indent-heuristic' ' + git diff-tree --no-indent-heuristic -p old new -- spaces.txt >out-diff-tree && + compare_diff spaces-expect out-diff-tree +' + +test_expect_success 'diff-tree: ugly spaces with diff.indentHeuristic=false' ' + git -c diff.indentHeuristic=false diff-tree -p old new -- spaces.txt >out-diff-tree2 && + compare_diff spaces-expect out-diff-tree2 +' + +test_expect_success 'diff-tree: --indent-heuristic overrides config' ' + git -c diff.indentHeuristic=false diff-tree --indent-heuristic -p old new -- spaces.txt >out-diff-tree-compacted3 && + compare_diff spaces-compacted-expect out-diff-tree-compacted3 +' + +test_expect_success 'diff-tree: --no-indent-heuristic overrides config' ' + git -c diff.indentHeuristic=true diff-tree --no-indent-heuristic -p old new -- spaces.txt >out-diff-tree3 && + compare_diff spaces-expect out-diff-tree3 +' + +# --- diff-index tests ---------------------------------------------------- + +test_expect_success 'diff-index: nice spaces with --indent-heuristic' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git diff-index --indent-heuristic -p old -- spaces.txt >out-diff-index-compacted && + compare_diff spaces-compacted-expect out-diff-index-compacted && + git checkout -f master +' + +test_expect_success 'diff-index: nice spaces with diff.indentHeuristic=true' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git -c diff.indentHeuristic=true diff-index -p old -- spaces.txt >out-diff-index-compacted2 && + compare_diff spaces-compacted-expect out-diff-index-compacted2 && + git checkout -f master +' + +test_expect_success 'diff-index: ugly spaces with --no-indent-heuristic' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git diff-index --no-indent-heuristic -p old -- spaces.txt >out-diff-index && + compare_diff spaces-expect out-diff-index && + git checkout -f master +' + +test_expect_success 'diff-index: ugly spaces with diff.indentHeuristic=false' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git -c diff.indentHeuristic=false diff-index -p old -- spaces.txt >out-diff-index2 && + compare_diff spaces-expect out-diff-index2 && + git checkout -f master +' + +test_expect_success 'diff-index: --indent-heuristic overrides config' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git -c diff.indentHeuristic=false diff-index --indent-heuristic -p old -- spaces.txt >out-diff-index-compacted3 && + compare_diff spaces-compacted-expect out-diff-index-compacted3 && + git checkout -f master +' + +test_expect_success 'diff-index: --no-indent-heuristic overrides config' ' + git checkout -B diff-index && + git reset --soft HEAD~ && + git -c diff.indentHeuristic=true diff-index --no-indent-heuristic -p old -- spaces.txt >out-diff-index3 && + compare_diff spaces-expect out-diff-index3 && + git checkout -f master +' + +# --- diff-files tests ---------------------------------------------------- + +test_expect_success 'diff-files: nice spaces with --indent-heuristic' ' + git checkout -B diff-files && + git reset HEAD~ && + git diff-files --indent-heuristic -p spaces.txt >out-diff-files-raw && + grep -v index out-diff-files-raw >out-diff-files-compacted && + compare_diff spaces-compacted-expect out-diff-files-compacted && + git checkout -f master +' + +test_expect_success 'diff-files: nice spaces with diff.indentHeuristic=true' ' + git checkout -B diff-files && + git reset HEAD~ && + git -c diff.indentHeuristic=true diff-files -p spaces.txt >out-diff-files-raw2 && + grep -v index out-diff-files-raw2 >out-diff-files-compacted2 && + compare_diff spaces-compacted-expect out-diff-files-compacted2 && + git checkout -f master +' + +test_expect_success 'diff-files: ugly spaces with --no-indent-heuristic' ' + git checkout -B diff-files && + git reset HEAD~ && + git diff-files --no-indent-heuristic -p spaces.txt >out-diff-files-raw && + grep -v index out-diff-files-raw >out-diff-files && + compare_diff spaces-expect out-diff-files && + git checkout -f master +' + +test_expect_success 'diff-files: ugly spaces with diff.indentHeuristic=false' ' + git checkout -B diff-files && + git reset HEAD~ && + git -c diff.indentHeuristic=false diff-files -p spaces.txt >out-diff-files-raw2 && + grep -v index out-diff-files-raw2 >out-diff-files && + compare_diff spaces-expect out-diff-files && + git checkout -f master +' + +test_expect_success 'diff-files: --indent-heuristic overrides config' ' + git checkout -B diff-files && + git reset HEAD~ && + git -c diff.indentHeuristic=false diff-files --indent-heuristic -p spaces.txt >out-diff-files-raw3 && + grep -v index out-diff-files-raw3 >out-diff-files-compacted && + compare_diff spaces-compacted-expect out-diff-files-compacted && + git checkout -f master +' + +test_expect_success 'diff-files: --no-indent-heuristic overrides config' ' + git checkout -B diff-files && + git reset HEAD~ && + git -c diff.indentHeuristic=true diff-files --no-indent-heuristic -p spaces.txt >out-diff-files-raw4 && + grep -v index out-diff-files-raw4 >out-diff-files && + compare_diff spaces-expect out-diff-files && + git checkout -f master ' test_done diff --git a/t/t4063-diff-blobs.sh b/t/t4063-diff-blobs.sh new file mode 100755 index 0000000000..bc69e26c52 --- /dev/null +++ b/t/t4063-diff-blobs.sh @@ -0,0 +1,96 @@ +#!/bin/sh + +test_description='test direct comparison of blobs via git-diff' +. ./test-lib.sh + +run_diff () { + # use full-index to make it easy to match the index line + git diff --full-index "$@" >diff +} + +check_index () { + grep "^index $1\\.\\.$2" diff +} + +check_mode () { + grep "^old mode $1" diff && + grep "^new mode $2" diff +} + +check_paths () { + grep "^diff --git a/$1 b/$2" diff +} + +test_expect_success 'create some blobs' ' + echo one >one && + echo two >two && + chmod +x two && + git add . && + + # cover systems where modes are ignored + git update-index --chmod=+x two && + + git commit -m base && + + sha1_one=$(git rev-parse HEAD:one) && + sha1_two=$(git rev-parse HEAD:two) +' + +test_expect_success 'diff by sha1' ' + run_diff $sha1_one $sha1_two +' +test_expect_success 'index of sha1 diff' ' + check_index $sha1_one $sha1_two +' +test_expect_success 'sha1 diff uses arguments as paths' ' + check_paths $sha1_one $sha1_two +' +test_expect_success 'sha1 diff has no mode change' ' + ! grep mode diff +' + +test_expect_success 'diff by tree:path (run)' ' + run_diff HEAD:one HEAD:two +' +test_expect_success 'index of tree:path diff' ' + check_index $sha1_one $sha1_two +' +test_expect_success 'tree:path diff uses filenames as paths' ' + check_paths one two +' +test_expect_success 'tree:path diff shows mode change' ' + check_mode 100644 100755 +' + +test_expect_success 'diff by ranged tree:path' ' + run_diff HEAD:one..HEAD:two +' +test_expect_success 'index of ranged tree:path diff' ' + check_index $sha1_one $sha1_two +' +test_expect_success 'ranged tree:path diff uses filenames as paths' ' + check_paths one two +' +test_expect_success 'ranged tree:path diff shows mode change' ' + check_mode 100644 100755 +' + +test_expect_success 'diff blob against file' ' + run_diff HEAD:one two +' +test_expect_success 'index of blob-file diff' ' + check_index $sha1_one $sha1_two +' +test_expect_success 'blob-file diff uses filename as paths' ' + check_paths one two +' +test_expect_success FILEMODE 'blob-file diff shows mode change' ' + check_mode 100644 100755 +' + +test_expect_success 'blob-file diff prefers filename to sha1' ' + run_diff $sha1_one two && + check_paths two two +' + +test_done diff --git a/t/t4202-log.sh b/t/t4202-log.sh index 6499cdf6ff..3f3531f0a4 100755 --- a/t/t4202-log.sh +++ b/t/t4202-log.sh @@ -231,14 +231,47 @@ second initial EOF test_expect_success 'log --invert-grep --grep' ' - git log --pretty="tformat:%s" --invert-grep --grep=th --grep=Sec >actual && - test_cmp expect actual + # Fixed + git -c grep.patternType=fixed log --pretty="tformat:%s" --invert-grep --grep=th --grep=Sec >actual && + test_cmp expect actual && + + # POSIX basic + git -c grep.patternType=basic log --pretty="tformat:%s" --invert-grep --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual && + + # POSIX extended + git -c grep.patternType=basic log --pretty="tformat:%s" --invert-grep --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual && + + # PCRE + if test_have_prereq PCRE + then + git -c grep.patternType=perl log --pretty="tformat:%s" --invert-grep --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual + fi ' test_expect_success 'log --invert-grep --grep -i' ' echo initial >expect && - git log --pretty="tformat:%s" --invert-grep -i --grep=th --grep=Sec >actual && - test_cmp expect actual + + # Fixed + git -c grep.patternType=fixed log --pretty="tformat:%s" --invert-grep -i --grep=th --grep=Sec >actual && + test_cmp expect actual && + + # POSIX basic + git -c grep.patternType=basic log --pretty="tformat:%s" --invert-grep -i --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual && + + # POSIX extended + git -c grep.patternType=extended log --pretty="tformat:%s" --invert-grep -i --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual && + + # PCRE + if test_have_prereq PCRE + then + git -c grep.patternType=perl log --pretty="tformat:%s" --invert-grep -i --grep=t[h] --grep=S[e]c >actual && + test_cmp expect actual + fi ' test_expect_success 'log --grep option parsing' ' @@ -256,13 +289,53 @@ test_expect_success 'log -i --grep' ' test_expect_success 'log --grep -i' ' echo Second >expect && + + # Fixed git log -1 --pretty="tformat:%s" --grep=sec -i >actual && - test_cmp expect actual + test_cmp expect actual && + + # POSIX basic + git -c grep.patternType=basic log -1 --pretty="tformat:%s" --grep=s[e]c -i >actual && + test_cmp expect actual && + + # POSIX extended + git -c grep.patternType=extended log -1 --pretty="tformat:%s" --grep=s[e]c -i >actual && + test_cmp expect actual && + + # PCRE + if test_have_prereq PCRE + then + git -c grep.patternType=perl log -1 --pretty="tformat:%s" --grep=s[e]c -i >actual && + test_cmp expect actual + fi ' test_expect_success 'log -F -E --grep=<ere> uses ere' ' echo second >expect && - git log -1 --pretty="tformat:%s" -F -E --grep=s.c.nd >actual && + # basic would need \(s\) to do the same + git log -1 --pretty="tformat:%s" -F -E --grep="(s).c.nd" >actual && + test_cmp expect actual +' + +test_expect_success PCRE 'log -F -E --perl-regexp --grep=<pcre> uses PCRE' ' + test_when_finished "rm -rf num_commits" && + git init num_commits && + ( + cd num_commits && + test_commit 1d && + test_commit 2e + ) && + + # In PCRE \d in [\d] is like saying "0-9", and matches the 2 + # in 2e... + echo 2e >expect && + git -C num_commits log -1 --pretty="tformat:%s" -F -E --perl-regexp --grep="[\d]" >actual && + test_cmp expect actual && + + # ...in POSIX basic and extended it is the same as [d], + # i.e. "d", which matches 1d, but does not match 2e. + echo 1d >expect && + git -C num_commits log -1 --pretty="tformat:%s" -F -E --grep="[\d]" >actual && test_cmp expect actual ' @@ -280,6 +353,93 @@ test_expect_success 'log with grep.patternType configuration and command line' ' test_cmp expect actual ' +test_expect_success 'log with various grep.patternType configurations & command-lines' ' + git init pattern-type && + ( + cd pattern-type && + test_commit 1 file A && + + # The tagname is overridden here because creating a + # tag called "(1|2)" as test_commit would otherwise + # implicitly do would fail on e.g. MINGW. + test_commit "(1|2)" file B 2 && + + echo "(1|2)" >expect.fixed && + cp expect.fixed expect.basic && + cp expect.fixed expect.extended && + cp expect.fixed expect.perl && + + # A strcmp-like match with fixed. + git -c grep.patternType=fixed log --pretty=tformat:%s \ + --grep="(1|2)" >actual.fixed && + + # POSIX basic matches (, | and ) literally. + git -c grep.patternType=basic log --pretty=tformat:%s \ + --grep="(.|.)" >actual.basic && + + # POSIX extended needs to have | escaped to match it + # literally, whereas under basic this is the same as + # (|2), i.e. it would also match "1". This test checks + # for extended by asserting that it is not matching + # what basic would match. + git -c grep.patternType=extended log --pretty=tformat:%s \ + --grep="\|2" >actual.extended && + if test_have_prereq PCRE + then + # Only PCRE would match [\d]\| with only + # "(1|2)" due to [\d]. POSIX basic would match + # both it and "1" since similarly to the + # extended match above it is the same as + # \([\d]\|\). POSIX extended would + # match neither. + git -c grep.patternType=perl log --pretty=tformat:%s \ + --grep="[\d]\|" >actual.perl && + test_cmp expect.perl actual.perl + fi && + test_cmp expect.fixed actual.fixed && + test_cmp expect.basic actual.basic && + test_cmp expect.extended actual.extended && + + git log --pretty=tformat:%s -F \ + --grep="(1|2)" >actual.fixed.short-arg && + git log --pretty=tformat:%s -E \ + --grep="\|2" >actual.extended.short-arg && + if test_have_prereq PCRE + then + git log --pretty=tformat:%s -P \ + --grep="[\d]\|" >actual.perl.short-arg + else + test_must_fail git log -P \ + --grep="[\d]\|" + fi && + test_cmp expect.fixed actual.fixed.short-arg && + test_cmp expect.extended actual.extended.short-arg && + if test_have_prereq PCRE + then + test_cmp expect.perl actual.perl.short-arg + fi && + + git log --pretty=tformat:%s --fixed-strings \ + --grep="(1|2)" >actual.fixed.long-arg && + git log --pretty=tformat:%s --basic-regexp \ + --grep="(.|.)" >actual.basic.long-arg && + git log --pretty=tformat:%s --extended-regexp \ + --grep="\|2" >actual.extended.long-arg && + if test_have_prereq PCRE + then + git log --pretty=tformat:%s --perl-regexp \ + --grep="[\d]\|" >actual.perl.long-arg && + test_cmp expect.perl actual.perl.long-arg + else + test_must_fail git log --perl-regexp \ + --grep="[\d]\|" + fi && + test_cmp expect.fixed actual.fixed.long-arg && + test_cmp expect.basic actual.basic.long-arg && + test_cmp expect.extended actual.extended.long-arg + ) +' + cat > expect <<EOF * Second * sixth @@ -1392,4 +1552,13 @@ test_expect_success 'log --source paints tag names' ' test_cmp expect actual ' +test_expect_success 'log --source paints symmetric ranges' ' + cat >expect <<-\EOF && + 09e12a9 source-b three + 8e393e1 source-a two + EOF + git log --oneline --source source-a...source-b >actual && + test_cmp expect actual +' + test_done diff --git a/t/t4208-log-magic-pathspec.sh b/t/t4208-log-magic-pathspec.sh index 001343e2fc..935df6a65c 100755 --- a/t/t4208-log-magic-pathspec.sh +++ b/t/t4208-log-magic-pathspec.sh @@ -29,6 +29,12 @@ test_expect_success '"git log -- :/a" should not be ambiguous' ' git log -- :/a ' +# This differs from the ":/a" check above in that :/in looks like a pathspec, +# but doesn't match an actual file. +test_expect_success '"git log :/in" should not be ambiguous' ' + git log :/in +' + test_expect_success '"git log :" should be ambiguous' ' test_must_fail git log : 2>error && test_i18ngrep ambiguous error @@ -46,6 +52,32 @@ test_expect_success 'git log HEAD -- :/' ' test_cmp expected actual ' +test_expect_success '"git log :^sub" is not ambiguous' ' + git log :^sub +' + +test_expect_success '"git log :^does-not-exist" does not match anything' ' + test_must_fail git log :^does-not-exist +' + +test_expect_success '"git log :!" behaves the same as :^' ' + git log :!sub && + test_must_fail git log :!does-not-exist +' + +test_expect_success '"git log :(exclude)sub" is not ambiguous' ' + git log ":(exclude)sub" +' + +test_expect_success '"git log :(exclude)sub --" must resolve as an object' ' + test_must_fail git log ":(exclude)sub" -- +' + +test_expect_success '"git log :(unknown-magic) complains of bogus magic' ' + test_must_fail git log ":(unknown-magic)" 2>error && + test_i18ngrep pathspec.magic error +' + test_expect_success 'command line pathspec parsing for "git log"' ' git reset --hard && >a && diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh index 43a672c345..9c68b99251 100755 --- a/t/t5300-pack-object.sh +++ b/t/t5300-pack-object.sh @@ -421,6 +421,42 @@ test_expect_success 'index-pack <pack> works in non-repo' ' test_path_is_file foo.idx ' +test_expect_success !PTHREADS,C_LOCALE_OUTPUT 'index-pack --threads=N or pack.threads=N warns when no pthreads' ' + test_must_fail git index-pack --threads=2 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring --threads=2" err && + + test_must_fail git -c pack.threads=2 index-pack 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring pack.threads" err && + + test_must_fail git -c pack.threads=2 index-pack --threads=4 2>err && + grep ^warning: err >warnings && + test_line_count = 2 warnings && + grep -F "no threads support, ignoring --threads=4" err && + grep -F "no threads support, ignoring pack.threads" err +' + +test_expect_success !PTHREADS,C_LOCALE_OUTPUT 'pack-objects --threads=N or pack.threads=N warns when no pthreads' ' + git pack-objects --threads=2 --stdout --all </dev/null >/dev/null 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring --threads" err && + + git -c pack.threads=2 pack-objects --stdout --all </dev/null >/dev/null 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring pack.threads" err && + + git -c pack.threads=2 pack-objects --threads=4 --stdout --all </dev/null >/dev/null 2>err && + grep ^warning: err >warnings && + test_line_count = 2 warnings && + grep -F "no threads support, ignoring --threads" err && + grep -F "no threads support, ignoring pack.threads" err +' + # # WARNING! # diff --git a/t/t5313-pack-bounds-checks.sh b/t/t5313-pack-bounds-checks.sh index a8a587abc3..9372508c99 100755 --- a/t/t5313-pack-bounds-checks.sh +++ b/t/t5313-pack-bounds-checks.sh @@ -139,7 +139,13 @@ test_expect_success 'bogus offset into v2 extended table' ' test_expect_success 'bogus offset inside v2 extended table' ' # We need two objects here, so we can plausibly require # an extended table (if the first object were larger than 2^31). - do_pack "$object $(git rev-parse HEAD)" --index-version=2 && + # + # Note that the value is important here. We want $object as + # the second entry in sorted-sha1 order. The sha1 of 1485 starts + # with "000", which sorts before that of $object (which starts + # with "fff"). + second=$(echo 1485 | git hash-object -w --stdin) && + do_pack "$object $second" --index-version=2 && # We have to make extra room for the table, so we cannot # just munge in place as usual. diff --git a/t/t5512-ls-remote.sh b/t/t5512-ls-remote.sh index 94fc9be9ce..02106c9226 100755 --- a/t/t5512-ls-remote.sh +++ b/t/t5512-ls-remote.sh @@ -85,8 +85,15 @@ test_expect_success 'use branch.<name>.remote if possible' ' ' test_expect_success 'confuses pattern as remote when no remote specified' ' - cat >exp <<-\EOF && - fatal: '\''refs*master'\'' does not appear to be a git repository + if test_have_prereq MINGW + then + # Windows does not like asterisks in pathname + does_not_exist=master + else + does_not_exist="refs*master" + fi && + cat >exp <<-EOF && + fatal: '\''$does_not_exist'\'' does not appear to be a git repository fatal: Could not read from remote repository. Please make sure you have the correct access rights @@ -98,7 +105,7 @@ test_expect_success 'confuses pattern as remote when no remote specified' ' # fetch <branch>. # We could just as easily have used "master"; the "*" emphasizes its # role as a pattern. - test_must_fail git ls-remote refs*master >actual 2>&1 && + test_must_fail git ls-remote "$does_not_exist" >actual 2>&1 && test_i18ncmp exp actual ' diff --git a/t/t5520-pull.sh b/t/t5520-pull.sh index 17f4d0fe4e..f15f7a3329 100755 --- a/t/t5520-pull.sh +++ b/t/t5520-pull.sh @@ -272,6 +272,24 @@ test_expect_success '--rebase fast forward' ' test_cmp reflog.expected reflog.fuzzy ' +test_expect_success '--rebase --autostash fast forward' ' + test_when_finished " + git reset --hard + git checkout to-rebase + git branch -D to-rebase-ff + git branch -D behind" && + git branch behind && + git checkout -b to-rebase-ff && + echo another modification >>file && + git add file && + git commit -m mod && + + git checkout behind && + echo dirty >file && + git pull --rebase --autostash . to-rebase-ff && + test "$(git rev-parse HEAD)" = "$(git rev-parse to-rebase-ff)" +' + test_expect_success '--rebase with conflicts shows advice' ' test_when_finished "git rebase --abort; git checkout -f to-rebase" && git checkout -b seq && diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh index f3b0a8d30a..162baf101f 100755 --- a/t/t5526-fetch-submodules.sh +++ b/t/t5526-fetch-submodules.sh @@ -71,6 +71,16 @@ test_expect_success "fetch --recurse-submodules recurses into submodules" ' test_i18ncmp expect.err actual.err ' +test_expect_success "submodule.recurse option triggers recursive fetch" ' + add_upstream_commit && + ( + cd downstream && + git -c submodule.recurse fetch >../actual.out 2>../actual.err + ) && + test_must_be_empty actual.out && + test_i18ncmp expect.err actual.err +' + test_expect_success "fetch --recurse-submodules -j2 has the same output behaviour" ' add_upstream_commit && ( diff --git a/t/t5531-deep-submodule-push.sh b/t/t5531-deep-submodule-push.sh index 57ba322628..beff65b8ac 100755 --- a/t/t5531-deep-submodule-push.sh +++ b/t/t5531-deep-submodule-push.sh @@ -1,6 +1,6 @@ #!/bin/sh -test_description='unpack-objects' +test_description='test push with submodules' . ./test-lib.sh @@ -27,7 +27,7 @@ test_expect_success setup ' ) ' -test_expect_success push ' +test_expect_success 'push works with recorded gitlink' ' ( cd work && git push ../pub.git master @@ -126,6 +126,27 @@ test_expect_success 'push succeeds if submodule commit not on remote but using o ) ' +test_expect_success 'push succeeds if submodule commit not on remote but using auto-on-demand via submodule.recurse config' ' + ( + cd work/gar/bage && + >recurse-on-demand-from-submodule-recurse-config && + git add recurse-on-demand-from-submodule-recurse-config && + git commit -m "Recurse submodule.recurse from config junk" + ) && + ( + cd work && + git add gar/bage && + git commit -m "Recurse submodule.recurse from config for gar/bage" && + git -c submodule.recurse push ../pub.git master && + # Check that the supermodule commit got there + git fetch ../pub.git && + git diff --quiet FETCH_HEAD master && + # Check that the submodule commit got there too + cd gar/bage && + git diff --quiet origin/master master + ) +' + test_expect_success 'push recurse-submodules on command line overrides config' ' ( cd work/gar/bage && diff --git a/t/t5580-clone-push-unc.sh b/t/t5580-clone-push-unc.sh index b195f71ea9..b322c2f722 100755 --- a/t/t5580-clone-push-unc.sh +++ b/t/t5580-clone-push-unc.sh @@ -1,10 +1,10 @@ #!/bin/sh -test_description='various UNC path tests (Windows-only)' +test_description='various Windows-only path tests' . ./test-lib.sh if ! test_have_prereq MINGW; then - skip_all='skipping UNC path tests, requires Windows' + skip_all='skipping Windows-only path tests' test_done fi @@ -45,4 +45,10 @@ test_expect_success push ' test "$rev" = "$(git rev-parse --verify refs/heads/to-push)" ' +test_expect_success 'remote nick cannot contain backslashes' ' + BACKSLASHED="$(pwd | tr / \\\\)" && + git ls-remote "$BACKSLASHED" >out 2>err && + test_i18ngrep ! "unable to access" err +' + test_done diff --git a/t/t7008-grep-binary.sh b/t/t7008-grep-binary.sh index 9c9c378119..615e7e0162 100755 --- a/t/t7008-grep-binary.sh +++ b/t/t7008-grep-binary.sh @@ -4,8 +4,43 @@ test_description='git grep in binary files' . ./test-lib.sh +nul_match () { + matches=$1 + flags=$2 + pattern=$3 + pattern_human=$(echo "$pattern" | sed 's/Q/<NUL>/g') + + if test "$matches" = 1 + then + test_expect_success "git grep -f f $flags '$pattern_human' a" " + printf '$pattern' | q_to_nul >f && + git grep -f f $flags a + " + elif test "$matches" = 0 + then + test_expect_success "git grep -f f $flags '$pattern_human' a" " + printf '$pattern' | q_to_nul >f && + test_must_fail git grep -f f $flags a + " + elif test "$matches" = T1 + then + test_expect_failure "git grep -f f $flags '$pattern_human' a" " + printf '$pattern' | q_to_nul >f && + git grep -f f $flags a + " + elif test "$matches" = T0 + then + test_expect_failure "git grep -f f $flags '$pattern_human' a" " + printf '$pattern' | q_to_nul >f && + test_must_fail git grep -f f $flags a + " + else + test_expect_success "PANIC: Test framework error. Unknown matches value $matches" 'false' + fi +} + test_expect_success 'setup' " - echo 'binaryQfile' | q_to_nul >a && + echo 'binaryQfileQm[*]cQ*æQð' | q_to_nul >a && git add a && git commit -m. " @@ -69,35 +104,71 @@ test_expect_failure 'git grep .fi a' ' git grep .fi a ' -test_expect_success 'git grep -F y<NUL>f a' " - printf 'yQf' | q_to_nul >f && - git grep -f f -F a -" - -test_expect_success 'git grep -F y<NUL>x a' " - printf 'yQx' | q_to_nul >f && - test_must_fail git grep -f f -F a -" - -test_expect_success 'git grep -Fi Y<NUL>f a' " - printf 'YQf' | q_to_nul >f && - git grep -f f -Fi a -" - -test_expect_success 'git grep -Fi Y<NUL>x a' " - printf 'YQx' | q_to_nul >f && - test_must_fail git grep -f f -Fi a -" - -test_expect_success 'git grep y<NUL>f a' " - printf 'yQf' | q_to_nul >f && - git grep -f f a -" - -test_expect_success 'git grep y<NUL>x a' " - printf 'yQx' | q_to_nul >f && - test_must_fail git grep -f f a -" +nul_match 1 '-F' 'yQf' +nul_match 0 '-F' 'yQx' +nul_match 1 '-Fi' 'YQf' +nul_match 0 '-Fi' 'YQx' +nul_match 1 '' 'yQf' +nul_match 0 '' 'yQx' +nul_match 1 '' 'æQð' +nul_match 1 '-F' 'eQm[*]c' +nul_match 1 '-Fi' 'EQM[*]C' + +# Regex patterns that would match but shouldn't with -F +nul_match 0 '-F' 'yQ[f]' +nul_match 0 '-F' '[y]Qf' +nul_match 0 '-Fi' 'YQ[F]' +nul_match 0 '-Fi' '[Y]QF' +nul_match 0 '-F' 'æQ[ð]' +nul_match 0 '-F' '[æ]Qð' +nul_match 0 '-Fi' 'ÆQ[Ð]' +nul_match 0 '-Fi' '[Æ]QÐ' + +# kwset is disabled on -i & non-ASCII. No way to match non-ASCII \0 +# patterns case-insensitively. +nul_match T1 '-i' 'ÆQÐ' + +# \0 implicitly disables regexes. This is an undocumented internal +# limitation. +nul_match T1 '' 'yQ[f]' +nul_match T1 '' '[y]Qf' +nul_match T1 '-i' 'YQ[F]' +nul_match T1 '-i' '[Y]Qf' +nul_match T1 '' 'æQ[ð]' +nul_match T1 '' '[æ]Qð' +nul_match T1 '-i' 'ÆQ[Ð]' + +# ... because of \0 implicitly disabling regexes regexes that +# should/shouldn't match don't do the right thing. +nul_match T1 '' 'eQm.*cQ' +nul_match T1 '-i' 'EQM.*cQ' +nul_match T0 '' 'eQm[*]c' +nul_match T0 '-i' 'EQM[*]C' + +# Due to the REG_STARTEND extension when kwset() is disabled on -i & +# non-ASCII the string will be matched in its entirety, but the +# pattern will be cut off at the first \0. +nul_match 0 '-i' 'NOMATCHQð' +nul_match T0 '-i' '[Æ]QNOMATCH' +nul_match T0 '-i' '[æ]QNOMATCH' +# Matches, but for the wrong reasons, just stops at [æ] +nul_match 1 '-i' '[Æ]Qð' +nul_match 1 '-i' '[æ]Qð' + +# Ensure that the matcher doesn't regress to something that stops at +# \0 +nul_match 0 '-F' 'yQ[f]' +nul_match 0 '-Fi' 'YQ[F]' +nul_match 0 '' 'yQNOMATCH' +nul_match 0 '' 'QNOMATCH' +nul_match 0 '-i' 'YQNOMATCH' +nul_match 0 '-i' 'QNOMATCH' +nul_match 0 '-F' 'æQ[ð]' +nul_match 0 '-Fi' 'ÆQ[Ð]' +nul_match 0 '' 'yQNÓMATCH' +nul_match 0 '' 'QNÓMATCH' +nul_match 0 '-i' 'YQNÓMATCH' +nul_match 0 '-i' 'QNÓMATCH' test_expect_success 'grep respects binary diff attribute' ' echo text >t && @@ -162,7 +233,7 @@ test_expect_success 'grep does not honor textconv' ' ' test_expect_success 'grep --textconv honors textconv' ' - echo "a:binaryQfile" >expect && + echo "a:binaryQfileQm[*]cQ*æQð" >expect && git grep --textconv Qfile >actual && test_cmp expect actual ' @@ -172,7 +243,7 @@ test_expect_success 'grep --no-textconv does not honor textconv' ' ' test_expect_success 'grep --textconv blob honors textconv' ' - echo "HEAD:a:binaryQfile" >expect && + echo "HEAD:a:binaryQfileQm[*]cQ*æQð" >expect && git grep --textconv Qfile HEAD:a >actual && test_cmp expect actual ' diff --git a/t/t7061-wtstatus-ignore.sh b/t/t7061-wtstatus-ignore.sh index cdc0747bf0..fc6013ba3c 100755 --- a/t/t7061-wtstatus-ignore.sh +++ b/t/t7061-wtstatus-ignore.sh @@ -9,6 +9,7 @@ cat >expected <<\EOF ?? actual ?? expected ?? untracked/ +!! untracked/ignored EOF test_expect_success 'status untracked directory with --ignored' ' diff --git a/t/t7112-reset-submodule.sh b/t/t7112-reset-submodule.sh index f86ccdf215..a1cb9ff858 100755 --- a/t/t7112-reset-submodule.sh +++ b/t/t7112-reset-submodule.sh @@ -9,9 +9,9 @@ KNOWN_FAILURE_SUBMODULE_RECURSIVE_NESTED=1 KNOWN_FAILURE_DIRECTORY_SUBMODULE_CONFLICTS=1 KNOWN_FAILURE_SUBMODULE_OVERWRITE_IGNORED_UNTRACKED=1 -test_submodule_switch_recursing "git reset --recurse-submodules --keep" +test_submodule_switch_recursing_with_args "reset --keep" -test_submodule_forced_switch_recursing "git reset --hard --recurse-submodules" +test_submodule_forced_switch_recursing_with_args "reset --hard" test_submodule_switch "git reset --keep" diff --git a/t/t7300-clean.sh b/t/t7300-clean.sh index b89fd2a6ad..7b36954d63 100755 --- a/t/t7300-clean.sh +++ b/t/t7300-clean.sh @@ -653,4 +653,20 @@ test_expect_success 'git clean -d respects pathspecs (pathspec is prefix of dir) test_path_is_dir foobar ' +test_expect_success 'git clean -d skips untracked dirs containing ignored files' ' + echo /foo/bar >.gitignore && + echo ignoreme >>.gitignore && + rm -rf foo && + mkdir -p foo/a/aa/aaa foo/b/bb/bbb && + touch foo/bar foo/baz foo/a/aa/ignoreme foo/b/ignoreme foo/b/bb/1 foo/b/bb/2 && + git clean -df && + test_path_is_dir foo && + test_path_is_file foo/bar && + test_path_is_missing foo/baz && + test_path_is_file foo/a/aa/ignoreme && + test_path_is_missing foo/a/aa/aaa && + test_path_is_file foo/b/ignoreme && + test_path_is_missing foo/b/bb +' + test_done diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh index cee42097b0..f106387820 100755 --- a/t/t7810-grep.sh +++ b/t/t7810-grep.sh @@ -275,12 +275,16 @@ do test_cmp expected actual ' - test_expect_success LIBPCRE "grep $L with grep.patterntype=perl" ' + test_expect_success PCRE "grep $L with grep.patterntype=perl" ' echo "${HC}ab:a+b*c" >expected && git -c grep.patterntype=perl grep "a\x{2b}b\x{2a}c" $H ab >actual && test_cmp expected actual ' + test_expect_success !PCRE "grep $L with grep.patterntype=perl errors without PCRE" ' + test_must_fail git -c grep.patterntype=perl grep "foo.*bar" + ' + test_expect_success "grep $L with grep.patternType=default and grep.extendedRegexp=true" ' echo "${HC}ab:abc" >expected && git \ @@ -771,6 +775,40 @@ test_expect_success 'grep -W with userdiff' ' test_cmp expected actual ' +for threads in $(test_seq 0 10) +do + test_expect_success "grep --threads=$threads & -c grep.threads=$threads" " + git grep --threads=$threads . >actual.$threads && + if test $threads -ge 1 + then + test_cmp actual.\$(($threads - 1)) actual.$threads + fi && + git -c grep.threads=$threads grep . >actual.$threads && + if test $threads -ge 1 + then + test_cmp actual.\$(($threads - 1)) actual.$threads + fi + " +done + +test_expect_success !PTHREADS,C_LOCALE_OUTPUT 'grep --threads=N or pack.threads=N warns when no pthreads' ' + git grep --threads=2 Hello hello_world 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring --threads" err && + git -c grep.threads=2 grep Hello hello_world 2>err && + grep ^warning: err >warnings && + test_line_count = 1 warnings && + grep -F "no threads support, ignoring grep.threads" err && + git -c grep.threads=2 grep --threads=4 Hello hello_world 2>err && + grep ^warning: err >warnings && + test_line_count = 2 warnings && + grep -F "no threads support, ignoring --threads" err && + grep -F "no threads support, ignoring grep.threads" err && + git -c grep.threads=0 grep --threads=0 Hello hello_world 2>err && + test_line_count = 0 err +' + test_expect_success 'grep from a subdirectory to search wider area (1)' ' mkdir -p s && ( @@ -1053,16 +1091,24 @@ hello.c:int main(int argc, const char **argv) hello.c: printf("Hello world.\n"); EOF -test_expect_success LIBPCRE 'grep --perl-regexp pattern' ' +test_expect_success PCRE 'grep --perl-regexp pattern' ' git grep --perl-regexp "\p{Ps}.*?\p{Pe}" hello.c >actual && test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P pattern' ' +test_expect_success !PCRE 'grep --perl-regexp pattern errors without PCRE' ' + test_must_fail git grep --perl-regexp "foo.*bar" +' + +test_expect_success PCRE 'grep -P pattern' ' git grep -P "\p{Ps}.*?\p{Pe}" hello.c >actual && test_cmp expected actual ' +test_expect_success !PCRE 'grep -P pattern errors without PCRE' ' + test_must_fail git grep -P "foo.*bar" +' + test_expect_success 'grep pattern with grep.extendedRegexp=true' ' >empty && test_must_fail git -c grep.extendedregexp=true \ @@ -1070,13 +1116,13 @@ test_expect_success 'grep pattern with grep.extendedRegexp=true' ' test_cmp empty actual ' -test_expect_success LIBPCRE 'grep -P pattern with grep.extendedRegexp=true' ' +test_expect_success PCRE 'grep -P pattern with grep.extendedRegexp=true' ' git -c grep.extendedregexp=true \ grep -P "\p{Ps}.*?\p{Pe}" hello.c >actual && test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P -v pattern' ' +test_expect_success PCRE 'grep -P -v pattern' ' { echo "ab:a+b*c" echo "ab:a+bc" @@ -1085,7 +1131,7 @@ test_expect_success LIBPCRE 'grep -P -v pattern' ' test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P -i pattern' ' +test_expect_success PCRE 'grep -P -i pattern' ' cat >expected <<-EOF && hello.c: printf("Hello world.\n"); EOF @@ -1093,7 +1139,7 @@ test_expect_success LIBPCRE 'grep -P -i pattern' ' test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P -w pattern' ' +test_expect_success PCRE 'grep -P -w pattern' ' { echo "hello_world:Hello world" echo "hello_world:HeLLo world" @@ -1102,6 +1148,13 @@ test_expect_success LIBPCRE 'grep -P -w pattern' ' test_cmp expected actual ' +test_expect_success PCRE 'grep -P backreferences work (the PCRE NO_AUTO_CAPTURE flag is not set)' ' + git grep -P -h "(?P<one>.)(?P=one)" hello_world >actual && + test_cmp hello_world actual && + git grep -P -h "(.)\1" hello_world >actual && + test_cmp hello_world actual +' + test_expect_success 'grep -G invalidpattern properly dies ' ' test_must_fail git grep -G "a[" ' @@ -1118,11 +1171,11 @@ test_expect_success 'grep invalidpattern properly dies with grep.patternType=ext test_must_fail git -c grep.patterntype=extended grep "a[" ' -test_expect_success LIBPCRE 'grep -P invalidpattern properly dies ' ' +test_expect_success PCRE 'grep -P invalidpattern properly dies ' ' test_must_fail git grep -P "a[" ' -test_expect_success LIBPCRE 'grep invalidpattern properly dies with grep.patternType=perl' ' +test_expect_success PCRE 'grep invalidpattern properly dies with grep.patternType=perl' ' test_must_fail git -c grep.patterntype=perl grep "a[" ' @@ -1191,13 +1244,13 @@ test_expect_success 'grep pattern with grep.patternType=fixed, =basic, =perl, =e test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -G -F -E -P pattern' ' +test_expect_success PCRE 'grep -G -F -E -P pattern' ' echo "d0:0" >expected && git grep -G -F -E -P "[\d]" d0 >actual && test_cmp expected actual ' -test_expect_success LIBPCRE 'grep pattern with grep.patternType=fixed, =basic, =extended, =perl' ' +test_expect_success PCRE 'grep pattern with grep.patternType=fixed, =basic, =extended, =perl' ' echo "d0:0" >expected && git \ -c grep.patterntype=fixed \ @@ -1208,7 +1261,7 @@ test_expect_success LIBPCRE 'grep pattern with grep.patternType=fixed, =basic, = test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P pattern with grep.patternType=fixed' ' +test_expect_success PCRE 'grep -P pattern with grep.patternType=fixed' ' echo "ab:a+b*c" >expected && git \ -c grep.patterntype=fixed \ @@ -1343,12 +1396,12 @@ space: line with leading space2 space: line with leading space3 EOF -test_expect_success LIBPCRE 'grep -E "^ "' ' +test_expect_success PCRE 'grep -E "^ "' ' git grep -E "^ " space >actual && test_cmp expected actual ' -test_expect_success LIBPCRE 'grep -P "^ "' ' +test_expect_success PCRE 'grep -P "^ "' ' git grep -P "^ " space >actual && test_cmp expected actual ' diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh index 169fd8d706..0059a1f837 100755 --- a/t/t7812-grep-icase-non-ascii.sh +++ b/t/t7812-grep-icase-non-ascii.sh @@ -20,13 +20,13 @@ test_expect_success REGEX_LOCALE 'grep literal string, no -F' ' git grep -i "TILRAUN: HALLÓ HEIMUR!" ' -test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 icase' ' +test_expect_success GETTEXT_LOCALE,PCRE 'grep pcre utf-8 icase' ' git grep --perl-regexp "TILRAUN: H.lló Heimur!" && git grep --perl-regexp -i "TILRAUN: H.lló Heimur!" && git grep --perl-regexp -i "TILRAUN: H.LLÓ HEIMUR!" ' -test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' ' +test_expect_success GETTEXT_LOCALE,PCRE 'grep pcre utf-8 string with "+"' ' test_write_lines "TILRAUN: Hallóó Heimur!" >file2 && git add file2 && git grep -l --perl-regexp "TILRAUN: H.lló+ Heimur!" >actual && @@ -36,29 +36,14 @@ test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' ' ' test_expect_success REGEX_LOCALE 'grep literal string, with -F' ' - git grep --debug -i -F "TILRAUN: Halló Heimur!" 2>&1 >/dev/null | - grep fixed >debug1 && - test_write_lines "fixed TILRAUN: Halló Heimur!" >expect1 && - test_cmp expect1 debug1 && - - git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!" 2>&1 >/dev/null | - grep fixed >debug2 && - test_write_lines "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 && - test_cmp expect2 debug2 + git grep -i -F "TILRAUN: Halló Heimur!" && + git grep -i -F "TILRAUN: HALLÓ HEIMUR!" ' test_expect_success REGEX_LOCALE 'grep string with regex, with -F' ' - test_write_lines "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file && - - git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null | - grep fixed >debug1 && - test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 && - test_cmp expect1 debug1 && - - git grep --debug -i -F "^*TILR^AUN:.* \\HALLÓ \$HE[]IMUR!\$" 2>&1 >/dev/null | - grep fixed >debug2 && - test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 && - test_cmp expect2 debug2 + test_write_lines "TILRAUN: Halló Heimur [abc]!" >file3 && + git add file3 && + git grep -i -F "TILRAUN: Halló Heimur [abc]!" file3 ' test_expect_success REGEX_LOCALE 'pickaxe -i on non-ascii' ' diff --git a/t/t7813-grep-icase-iso.sh b/t/t7813-grep-icase-iso.sh index efef7fb81f..701e08a8e5 100755 --- a/t/t7813-grep-icase-iso.sh +++ b/t/t7813-grep-icase-iso.sh @@ -11,7 +11,7 @@ test_expect_success GETTEXT_ISO_LOCALE 'setup' ' export LC_ALL ' -test_expect_success GETTEXT_ISO_LOCALE,LIBPCRE 'grep pcre string' ' +test_expect_success GETTEXT_ISO_LOCALE,PCRE 'grep pcre string' ' git grep --perl-regexp -i "TILRAUN: H.ll Heimur!" && git grep --perl-regexp -i "TILRAUN: H.LL HEIMUR!" ' diff --git a/t/t7814-grep-recurse-submodules.sh b/t/t7814-grep-recurse-submodules.sh index 5b6eb3a65e..7184113b9b 100755 --- a/t/t7814-grep-recurse-submodules.sh +++ b/t/t7814-grep-recurse-submodules.sh @@ -9,13 +9,13 @@ submodules. . ./test-lib.sh test_expect_success 'setup directory structure and submodule' ' - echo "foobar" >a && + echo "(1|2)d(3|4)" >a && mkdir b && - echo "bar" >b/b && + echo "(3|4)" >b/b && git add a b && git commit -m "add a and b" && git init submodule && - echo "foobar" >submodule/a && + echo "(1|2)d(3|4)" >submodule/a && git -C submodule add a && git -C submodule commit -m "add a" && git submodule add ./submodule && @@ -24,18 +24,36 @@ test_expect_success 'setup directory structure and submodule' ' test_expect_success 'grep correctly finds patterns in a submodule' ' cat >expect <<-\EOF && - a:foobar - b/b:bar - submodule/a:foobar + a:(1|2)d(3|4) + b/b:(3|4) + submodule/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules >actual && + git grep -e "(3|4)" --recurse-submodules >actual && + test_cmp expect actual +' + +test_expect_success 'grep finds patterns in a submodule via config' ' + test_config submodule.recurse true && + # expect from previous test + git grep -e "(3|4)" >actual && + test_cmp expect actual +' + +test_expect_success 'grep --no-recurse-submodules overrides config' ' + test_config submodule.recurse true && + cat >expect <<-\EOF && + a:(1|2)d(3|4) + b/b:(3|4) + EOF + + git grep -e "(3|4)" --no-recurse-submodules >actual && test_cmp expect actual ' test_expect_success 'grep and basic pathspecs' ' cat >expect <<-\EOF && - submodule/a:foobar + submodule/a:(1|2)d(3|4) EOF git grep -e. --recurse-submodules -- submodule >actual && @@ -44,7 +62,7 @@ test_expect_success 'grep and basic pathspecs' ' test_expect_success 'grep and nested submodules' ' git init submodule/sub && - echo "foobar" >submodule/sub/a && + echo "(1|2)d(3|4)" >submodule/sub/a && git -C submodule/sub add a && git -C submodule/sub commit -m "add a" && git -C submodule submodule add ./sub && @@ -54,117 +72,117 @@ test_expect_success 'grep and nested submodules' ' git commit -m "updated submodule" && cat >expect <<-\EOF && - a:foobar - b/b:bar - submodule/a:foobar - submodule/sub/a:foobar + a:(1|2)d(3|4) + b/b:(3|4) + submodule/a:(1|2)d(3|4) + submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules >actual && + git grep -e "(3|4)" --recurse-submodules >actual && test_cmp expect actual ' test_expect_success 'grep and multiple patterns' ' cat >expect <<-\EOF && - a:foobar - submodule/a:foobar - submodule/sub/a:foobar + a:(1|2)d(3|4) + submodule/a:(1|2)d(3|4) + submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --and -e "foo" --recurse-submodules >actual && + git grep -e "(3|4)" --and -e "(1|2)" --recurse-submodules >actual && test_cmp expect actual ' test_expect_success 'grep and multiple patterns' ' cat >expect <<-\EOF && - b/b:bar + b/b:(3|4) EOF - git grep -e "bar" --and --not -e "foo" --recurse-submodules >actual && + git grep -e "(3|4)" --and --not -e "(1|2)" --recurse-submodules >actual && test_cmp expect actual ' test_expect_success 'basic grep tree' ' cat >expect <<-\EOF && - HEAD:a:foobar - HEAD:b/b:bar - HEAD:submodule/a:foobar - HEAD:submodule/sub/a:foobar + HEAD:a:(1|2)d(3|4) + HEAD:b/b:(3|4) + HEAD:submodule/a:(1|2)d(3|4) + HEAD:submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD >actual && + git grep -e "(3|4)" --recurse-submodules HEAD >actual && test_cmp expect actual ' test_expect_success 'grep tree HEAD^' ' cat >expect <<-\EOF && - HEAD^:a:foobar - HEAD^:b/b:bar - HEAD^:submodule/a:foobar + HEAD^:a:(1|2)d(3|4) + HEAD^:b/b:(3|4) + HEAD^:submodule/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD^ >actual && + git grep -e "(3|4)" --recurse-submodules HEAD^ >actual && test_cmp expect actual ' test_expect_success 'grep tree HEAD^^' ' cat >expect <<-\EOF && - HEAD^^:a:foobar - HEAD^^:b/b:bar + HEAD^^:a:(1|2)d(3|4) + HEAD^^:b/b:(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD^^ >actual && + git grep -e "(3|4)" --recurse-submodules HEAD^^ >actual && test_cmp expect actual ' test_expect_success 'grep tree and pathspecs' ' cat >expect <<-\EOF && - HEAD:submodule/a:foobar - HEAD:submodule/sub/a:foobar + HEAD:submodule/a:(1|2)d(3|4) + HEAD:submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD -- submodule >actual && + git grep -e "(3|4)" --recurse-submodules HEAD -- submodule >actual && test_cmp expect actual ' test_expect_success 'grep tree and pathspecs' ' cat >expect <<-\EOF && - HEAD:submodule/a:foobar - HEAD:submodule/sub/a:foobar + HEAD:submodule/a:(1|2)d(3|4) + HEAD:submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD -- "submodule*a" >actual && + git grep -e "(3|4)" --recurse-submodules HEAD -- "submodule*a" >actual && test_cmp expect actual ' test_expect_success 'grep tree and more pathspecs' ' cat >expect <<-\EOF && - HEAD:submodule/a:foobar + HEAD:submodule/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD -- "submodul?/a" >actual && + git grep -e "(3|4)" --recurse-submodules HEAD -- "submodul?/a" >actual && test_cmp expect actual ' test_expect_success 'grep tree and more pathspecs' ' cat >expect <<-\EOF && - HEAD:submodule/sub/a:foobar + HEAD:submodule/sub/a:(1|2)d(3|4) EOF - git grep -e "bar" --recurse-submodules HEAD -- "submodul*/sub/a" >actual && + git grep -e "(3|4)" --recurse-submodules HEAD -- "submodul*/sub/a" >actual && test_cmp expect actual ' test_expect_success !MINGW 'grep recurse submodule colon in name' ' git init parent && test_when_finished "rm -rf parent" && - echo "foobar" >"parent/fi:le" && + echo "(1|2)d(3|4)" >"parent/fi:le" && git -C parent add "fi:le" && git -C parent commit -m "add fi:le" && git init "su:b" && test_when_finished "rm -rf su:b" && - echo "foobar" >"su:b/fi:le" && + echo "(1|2)d(3|4)" >"su:b/fi:le" && git -C "su:b" add "fi:le" && git -C "su:b" commit -m "add fi:le" && @@ -172,30 +190,30 @@ test_expect_success !MINGW 'grep recurse submodule colon in name' ' git -C parent commit -m "add submodule" && cat >expect <<-\EOF && - fi:le:foobar - su:b/fi:le:foobar + fi:le:(1|2)d(3|4) + su:b/fi:le:(1|2)d(3|4) EOF - git -C parent grep -e "foobar" --recurse-submodules >actual && + git -C parent grep -e "(1|2)d(3|4)" --recurse-submodules >actual && test_cmp expect actual && cat >expect <<-\EOF && - HEAD:fi:le:foobar - HEAD:su:b/fi:le:foobar + HEAD:fi:le:(1|2)d(3|4) + HEAD:su:b/fi:le:(1|2)d(3|4) EOF - git -C parent grep -e "foobar" --recurse-submodules HEAD >actual && + git -C parent grep -e "(1|2)d(3|4)" --recurse-submodules HEAD >actual && test_cmp expect actual ' test_expect_success 'grep history with moved submoules' ' git init parent && test_when_finished "rm -rf parent" && - echo "foobar" >parent/file && + echo "(1|2)d(3|4)" >parent/file && git -C parent add file && git -C parent commit -m "add file" && git init sub && test_when_finished "rm -rf sub" && - echo "foobar" >sub/file && + echo "(1|2)d(3|4)" >sub/file && git -C sub add file && git -C sub commit -m "add file" && @@ -203,82 +221,82 @@ test_expect_success 'grep history with moved submoules' ' git -C parent commit -m "add submodule" && cat >expect <<-\EOF && - dir/sub/file:foobar - file:foobar + dir/sub/file:(1|2)d(3|4) + file:(1|2)d(3|4) EOF - git -C parent grep -e "foobar" --recurse-submodules >actual && + git -C parent grep -e "(1|2)d(3|4)" --recurse-submodules >actual && test_cmp expect actual && git -C parent mv dir/sub sub-moved && git -C parent commit -m "moved submodule" && cat >expect <<-\EOF && - file:foobar - sub-moved/file:foobar + file:(1|2)d(3|4) + sub-moved/file:(1|2)d(3|4) EOF - git -C parent grep -e "foobar" --recurse-submodules >actual && + git -C parent grep -e "(1|2)d(3|4)" --recurse-submodules >actual && test_cmp expect actual && cat >expect <<-\EOF && - HEAD^:dir/sub/file:foobar - HEAD^:file:foobar + HEAD^:dir/sub/file:(1|2)d(3|4) + HEAD^:file:(1|2)d(3|4) EOF - git -C parent grep -e "foobar" --recurse-submodules HEAD^ >actual && + git -C parent grep -e "(1|2)d(3|4)" --recurse-submodules HEAD^ >actual && test_cmp expect actual ' test_expect_success 'grep using relative path' ' test_when_finished "rm -rf parent sub" && git init sub && - echo "foobar" >sub/file && + echo "(1|2)d(3|4)" >sub/file && git -C sub add file && git -C sub commit -m "add file" && git init parent && - echo "foobar" >parent/file && + echo "(1|2)d(3|4)" >parent/file && git -C parent add file && mkdir parent/src && - echo "foobar" >parent/src/file2 && + echo "(1|2)d(3|4)" >parent/src/file2 && git -C parent add src/file2 && git -C parent submodule add ../sub && git -C parent commit -m "add files and submodule" && # From top works cat >expect <<-\EOF && - file:foobar - src/file2:foobar - sub/file:foobar + file:(1|2)d(3|4) + src/file2:(1|2)d(3|4) + sub/file:(1|2)d(3|4) EOF - git -C parent grep --recurse-submodules -e "foobar" >actual && + git -C parent grep --recurse-submodules -e "(1|2)d(3|4)" >actual && test_cmp expect actual && # Relative path to top cat >expect <<-\EOF && - ../file:foobar - file2:foobar - ../sub/file:foobar + ../file:(1|2)d(3|4) + file2:(1|2)d(3|4) + ../sub/file:(1|2)d(3|4) EOF - git -C parent/src grep --recurse-submodules -e "foobar" -- .. >actual && + git -C parent/src grep --recurse-submodules -e "(1|2)d(3|4)" -- .. >actual && test_cmp expect actual && # Relative path to submodule cat >expect <<-\EOF && - ../sub/file:foobar + ../sub/file:(1|2)d(3|4) EOF - git -C parent/src grep --recurse-submodules -e "foobar" -- ../sub >actual && + git -C parent/src grep --recurse-submodules -e "(1|2)d(3|4)" -- ../sub >actual && test_cmp expect actual ' test_expect_success 'grep from a subdir' ' test_when_finished "rm -rf parent sub" && git init sub && - echo "foobar" >sub/file && + echo "(1|2)d(3|4)" >sub/file && git -C sub add file && git -C sub commit -m "add file" && git init parent && mkdir parent/src && - echo "foobar" >parent/src/file && + echo "(1|2)d(3|4)" >parent/src/file && git -C parent add src/file && git -C parent submodule add ../sub src/sub && git -C parent submodule add ../sub sub && @@ -286,19 +304,19 @@ test_expect_success 'grep from a subdir' ' # Verify grep from root works cat >expect <<-\EOF && - src/file:foobar - src/sub/file:foobar - sub/file:foobar + src/file:(1|2)d(3|4) + src/sub/file:(1|2)d(3|4) + sub/file:(1|2)d(3|4) EOF - git -C parent grep --recurse-submodules -e "foobar" >actual && + git -C parent grep --recurse-submodules -e "(1|2)d(3|4)" >actual && test_cmp expect actual && # Verify grep from a subdir works cat >expect <<-\EOF && - file:foobar - sub/file:foobar + file:(1|2)d(3|4) + sub/file:(1|2)d(3|4) EOF - git -C parent/src grep --recurse-submodules -e "foobar" >actual && + git -C parent/src grep --recurse-submodules -e "(1|2)d(3|4)" >actual && test_cmp expect actual ' @@ -313,4 +331,53 @@ test_incompatible_with_recurse_submodules () test_incompatible_with_recurse_submodules --untracked test_incompatible_with_recurse_submodules --no-index +test_expect_success 'grep --recurse-submodules should pass the pattern type along' ' + # Fixed + test_must_fail git grep -F --recurse-submodules -e "(.|.)[\d]" && + test_must_fail git -c grep.patternType=fixed grep --recurse-submodules -e "(.|.)[\d]" && + + # Basic + git grep -G --recurse-submodules -e "(.|.)[\d]" >actual && + cat >expect <<-\EOF && + a:(1|2)d(3|4) + submodule/a:(1|2)d(3|4) + submodule/sub/a:(1|2)d(3|4) + EOF + test_cmp expect actual && + git -c grep.patternType=basic grep --recurse-submodules -e "(.|.)[\d]" >actual && + test_cmp expect actual && + + # Extended + git grep -E --recurse-submodules -e "(.|.)[\d]" >actual && + cat >expect <<-\EOF && + .gitmodules:[submodule "submodule"] + .gitmodules: path = submodule + .gitmodules: url = ./submodule + a:(1|2)d(3|4) + submodule/.gitmodules:[submodule "sub"] + submodule/a:(1|2)d(3|4) + submodule/sub/a:(1|2)d(3|4) + EOF + test_cmp expect actual && + git -c grep.patternType=extended grep --recurse-submodules -e "(.|.)[\d]" >actual && + test_cmp expect actual && + git -c grep.extendedRegexp=true grep --recurse-submodules -e "(.|.)[\d]" >actual && + test_cmp expect actual && + + # Perl + if test_have_prereq PCRE + then + git grep -P --recurse-submodules -e "(.|.)[\d]" >actual && + cat >expect <<-\EOF && + a:(1|2)d(3|4) + b/b:(3|4) + submodule/a:(1|2)d(3|4) + submodule/sub/a:(1|2)d(3|4) + EOF + test_cmp expect actual && + git -c grep.patternType=perl grep --recurse-submodules -e "(.|.)[\d]" >actual && + test_cmp expect actual + fi +' + test_done diff --git a/t/t9001-send-email.sh b/t/t9001-send-email.sh index 15128c755a..d1e4e8ad19 100755 --- a/t/t9001-send-email.sh +++ b/t/t9001-send-email.sh @@ -1953,4 +1953,12 @@ test_expect_success $PREREQ 'invoke hook' ' ) ' +test_expect_success $PREREQ 'test that send-email works outside a repo' ' + nongit git send-email \ + --from="Example <nobody@example.com>" \ + --to=nobody@example.com \ + --smtp-server="$(pwd)/fake.sendmail" \ + "$(pwd)/0001-add-master.patch" +' + test_done diff --git a/t/test-lib.sh b/t/test-lib.sh index ec2571f018..2306574dc9 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -1018,8 +1018,9 @@ esac ( COLUMNS=1 && test $COLUMNS = 1 ) && test_set_prereq COLUMNS_CAN_BE_1 test -z "$NO_PERL" && test_set_prereq PERL +test -z "$NO_PTHREADS" && test_set_prereq PTHREADS test -z "$NO_PYTHON" && test_set_prereq PYTHON -test -n "$USE_LIBPCRE" && test_set_prereq LIBPCRE +test -n "$USE_LIBPCRE1$USE_LIBPCRE2" && test_set_prereq PCRE test -z "$NO_GETTEXT" && test_set_prereq GETTEXT # Can we rely on git's output in the C locale? diff --git a/tree-walk.c b/tree-walk.c index f25a08fddf..6a42e402b0 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -589,7 +589,6 @@ enum follow_symlinks_result get_tree_entry_follow_symlinks(unsigned char *tree_s int i; init_tree_desc(&t, NULL, 0UL); - strbuf_init(result_path, 0); strbuf_addstr(&namebuf, name); hashcpy(current_tree_sha1, tree_sha1); @@ -418,6 +418,32 @@ FILE *fopen_for_writing(const char *path) return ret; } +static void warn_on_inaccessible(const char *path) +{ + warning_errno(_("unable to access '%s'"), path); +} + +int warn_on_fopen_errors(const char *path) +{ + if (errno != ENOENT && errno != ENOTDIR) { + warn_on_inaccessible(path); + return -1; + } + + return 0; +} + +FILE *fopen_or_warn(const char *path, const char *mode) +{ + FILE *fp = fopen(path, mode); + + if (fp) + return fp; + + warn_on_fopen_errors(path); + return NULL; +} + int xmkstemp(char *template) { int fd; @@ -576,15 +602,10 @@ int remove_or_warn(unsigned int mode, const char *file) return S_ISGITLINK(mode) ? rmdir_or_warn(file) : unlink_or_warn(file); } -void warn_on_inaccessible(const char *path) -{ - warning_errno(_("unable to access '%s'"), path); -} - static int access_error_is_ok(int err, unsigned flag) { - return err == ENOENT || err == ENOTDIR || - ((flag & ACCESS_EACCES_OK) && err == EACCES); + return (is_missing_file_error(err) || + ((flag & ACCESS_EACCES_OK) && err == EACCES)); } int access_or_warn(const char *path, int mode, unsigned flag) diff --git a/wt-status.c b/wt-status.c index 25aafc35c8..bf651f16fa 100644 --- a/wt-status.c +++ b/wt-status.c @@ -1066,7 +1066,8 @@ static void show_am_in_progress(struct wt_status *s, static char *read_line_from_git_path(const char *filename) { struct strbuf buf = STRBUF_INIT; - FILE *fp = fopen(git_path("%s", filename), "r"); + FILE *fp = fopen_or_warn(git_path("%s", filename), "r"); + if (!fp) { strbuf_release(&buf); return NULL; diff --git a/xdiff-interface.c b/xdiff-interface.c index 060038c2d6..d3f78ca2a7 100644 --- a/xdiff-interface.c +++ b/xdiff-interface.c @@ -164,9 +164,9 @@ int read_mmfile(mmfile_t *ptr, const char *filename) size_t sz; if (stat(filename, &st)) - return error("Could not stat %s", filename); + return error_errno("Could not stat %s", filename); if ((f = fopen(filename, "rb")) == NULL) - return error("Could not open %s", filename); + return error_errno("Could not open %s", filename); sz = xsize_t(st.st_size); ptr->ptr = xmalloc(sz ? sz : 1); if (sz && fread(ptr->ptr, sz, 1, f) != 1) { |