diff options
235 files changed, 6461 insertions, 3328 deletions
diff --git a/.gitattributes b/.gitattributes index 32583149c2..700743c3f5 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,13 +1,13 @@ -* whitespace=!indent,trail,space -*.[ch] whitespace=indent,trail,space diff=cpp -*.sh whitespace=indent,trail,space text eol=lf +* whitespace=trail,space +*.[ch] whitespace=indent,trail,space,incomplete diff=cpp +*.sh whitespace=indent,trail,space,incomplete text eol=lf *.perl text eol=lf diff=perl *.pl text eof=lf diff=perl *.pm text eol=lf diff=perl *.py text eol=lf diff=python *.bat text eol=crlf CODE_OF_CONDUCT.md -whitespace -/Documentation/**/*.adoc text eol=lf +/Documentation/**/*.adoc text eol=lf whitespace=trail,space,incomplete /command-list.txt text eol=lf /GIT-VERSION-GEN text eol=lf /mergetools/* text eol=lf diff --git a/.github/workflows/l10n.yml b/.github/workflows/l10n.yml index e2c3dbdcb5..95e55134bd 100644 --- a/.github/workflows/l10n.yml +++ b/.github/workflows/l10n.yml @@ -63,7 +63,7 @@ jobs: origin \ ${{ github.ref }} \ $args - - uses: actions/setup-go@v5 + - uses: actions/setup-go@v6 with: go-version: '>=1.16' cache: false diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 816d5a34c4..f2e93f5461 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -298,7 +298,17 @@ jobs: path: build - name: Test shell: pwsh - run: meson test -C build --no-rebuild --print-errorlogs --slice "$(1+${{ matrix.nr }})/10" + run: ci/run-test-slice-meson.sh build ${{matrix.nr}} 10 + - name: print test failures + if: failure() && env.FAILED_TEST_ARTIFACTS != '' + shell: bash + run: ci/print-test-failures.sh + - name: Upload failed tests' directories + if: failure() && env.FAILED_TEST_ARTIFACTS != '' + uses: actions/upload-artifact@v4 + with: + name: failed-tests-windows-meson-${{ matrix.nr }} + path: ${{env.FAILED_TEST_ARTIFACTS}} regular: name: ${{matrix.vector.jobname}} (${{matrix.vector.pool}}) @@ -433,7 +443,7 @@ jobs: - run: ci/install-dependencies.sh - run: useradd builder --create-home - run: chown -R builder . - - run: sudo --preserve-env --set-home --user=builder ci/run-build-and-tests.sh + - run: chmod a+w $GITHUB_ENV && sudo --preserve-env --set-home --user=builder ci/run-build-and-tests.sh - name: print test failures if: failure() && env.FAILED_TEST_ARTIFACTS != '' run: sudo --preserve-env --set-home --user=builder ci/print-test-failures.sh diff --git a/Documentation/Makefile b/Documentation/Makefile index 04e9e10b27..2699f0b24a 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -53,6 +53,7 @@ MAN7_TXT += gitcli.adoc MAN7_TXT += gitcore-tutorial.adoc MAN7_TXT += gitcredentials.adoc MAN7_TXT += gitcvs-migration.adoc +MAN7_TXT += gitdatamodel.adoc MAN7_TXT += gitdiffcore.adoc MAN7_TXT += giteveryday.adoc MAN7_TXT += gitfaq.adoc @@ -142,6 +143,7 @@ TECH_DOCS += technical/shallow TECH_DOCS += technical/sparse-checkout TECH_DOCS += technical/sparse-index TECH_DOCS += technical/trivial-merge +TECH_DOCS += technical/unambiguous-types TECH_DOCS += technical/unit-tests SP_ARTICLES += $(TECH_DOCS) SP_ARTICLES += technical/api-index diff --git a/Documentation/RelNotes/2.53.0.adoc b/Documentation/RelNotes/2.53.0.adoc new file mode 100644 index 0000000000..f28c820291 --- /dev/null +++ b/Documentation/RelNotes/2.53.0.adoc @@ -0,0 +1,186 @@ +Git v2.53 Release Notes +======================= + +UI, Workflows & Features +------------------------ + + * "git maintenance" command learned "is-needed" subcommand to tell if + it is necessary to perform various maintenance tasks. + + * "git replay" (experimental) learned to perform ref updates itself + in a transaction by default, instead of emitting where each refs + should point at and leaving the actual update to another command. + + * "git blame" learns "--diff-algorithm=<algo>" option. + + * "git repo info" learned "--all" option. + + * Both "git apply" and "git diff" learn a new whitespace error class, + "incomplete-line". + + * Add a new manual that describes the data model. + + * "git fast-import" learns "--strip-if-invalid" option to drop + invalid cryptographic signature from objects. + + * The use of "revision" (a connected set of commits) has been + clarified in the "git replay" documentation. + + * A help message from "git branch" now mentions "git help" instead of + "man" when suggesting to read some documentation. + + * "git repo struct" learned to take "-z" as a synonym to "--format=nul". + + +Performance, Internal Implementation, Development Support etc. +-------------------------------------------------------------- + + * The list of packfiles used in a running Git process is moved from + the packed_git structure into the packfile store. + + * Some ref backend storage can hold not just the object name of an + annotated tag, but the object name of the object the tag points at. + The code to handle this information has been streamlined. + + * As "git diff --quiet" only cares about the existence of any + changes, disable rename/copy detection to skip more expensive + processing whose result will be discarded anyway. + + * A part of code paths that deals with loose objects has been cleaned + up. + + * "make strip" has been taught to strip "scalar" as well as "git". + + * Dockerised jobs at the GitHub Actions CI have been taught to show + more details of failed tests. + + * Code refactoring around object database sources. + + * Halve the memory consumed by artificial filepairs created during + "git diff --find-copioes-harder", also making the operation run + faster. + + * The "git_istream" abstraction has been revamped to make it easier + to interface with pluggable object database design. + + * Rewrite the only use of "mktemp()" that is subject to TOCTOU race + and Stop using the insecure "mktemp()" function. + (merge 10bba537c4 rs/ban-mktemp later to maint). + + +Fixes since v2.52 +----------------- + + * Ever since we added whitespace rules for this project, we misspelt + an entry, which has been corrected. + (merge 358e94dc70 jc/gitattributes-whitespace-no-indent-fix later to maint). + + * The code to expand attribute macros has been rewritten to avoid + recursion to avoid running out of stack space in an uncontrolled + way. + (merge 42ed046866 jk/attr-macroexpand-wo-recursion later to maint). + + * Adding a repository that uses a different hash function is a no-no, + but "git submodule add" did nt prevent it, which has been corrected. + (merge 6fe288bfbc bc/submodule-force-same-hash later to maint). + + * An earlier check added to osx keychain credential helper to avoid + storing the credential itself supplied was overeager and rejected + credential material supplied by other helper backends that it would + have wanted to store, which has been corrected. + (merge 4580bcd235 kn/osxkeychain-idempotent-store-fix later to maint). + + * The "git repo structure" subcommand tried to align its output but + mixed up byte count and display column width, which has been + corrected. + (merge 7a03a10a3a jx/repo-struct-utf8width-fix later to maint). + + * Yet another corner case fix around renames in the "ort" merge + strategy. + (merge a562d90a35 en/ort-rename-another-fix later to maint). + + * Test leakfix. + (merge 14b561e768 jk/test-mktemp-leakfix later to maint). + + * Update a version of action used at the GitHub Actrions CI. + (merge cd99203f86 js/ci-github-setup-go-update later to maint). + + * The "return errno = EFOO, -1" construct, which is heavily used in + compat/mingw.c and triggers warnings under "-Wcomma", has been + rewritten to avoid the warnings. + (merge af3919816f js/mingw-assign-comma-fix later to maint). + + * Makefile based build have recently been updated to build a + libgit.a that also has reftable and xdiff objects; CMake based + build procedure has been updated to match. + (merge b0d5c88cca js/cmake-libgit-fix later to maint). + + * Under-allocation fix. + (merge d22a488482 js/wincred-get-credential-alloc-fix later to maint). + + * "git worktree list" attempts to show paths to worktrees while + aligning them, but miscounted display columns for the paths when + non-ASCII characters were involved, which has been corrected. + (merge 08dfa59835 pw/worktree-list-display-width-fix later to maint). + + * "Windows+meson" job at the GitHub Actions CI was hard to debug, as + it did not show and save failed test artifacts, which has been + corrected. + (merge 17bd1108ea jk/ci-windows-meson-test-fix later to maint). + + * Emulation code clean-up. + (merge 2367c6bcd6 gf/win32-pthread-cond-wait-err later to maint). + + * Various issues detected by Asan have been corrected. + (merge a031b6181a jk/asan-bonanza later to maint). + + * "git config get --path" segfaulted on an ":(optional)path" that + does not exist, which has been corrected. + (merge 0bd16856ff jc/optional-path later to maint). + + * The "--committer-date-is-author-date" option of "git am/rebase" is + a misguided one. The documentation is updated to discourage its + use. + (merge fbf3d0669f kh/doc-committer-date-is-author-date later to maint). + + * The option help text given by "git config unset -h" described + the "--all" option to "replace", not "unset", multiple variables, + which has been corrected. + (merge 18bf67b753 rs/config-unset-opthelp-fix later to maint). + + * The error message given by "git config set", when the variable + being updated has more than one values defined, used old style "git + config" syntax with an incorrect option in its hint, both of which + have been corrected. + (merge df963f0df4 rs/config-set-multi-error-message-fix later to maint). + + * "git replay" forgot to omit the "gpgsig-sha256" extended header + from the resulting commit the same way it omits "gpgsig", which has + been corrected. + (merge 9f3a115087 pw/replay-exclude-gpgsig-fix later to maint). + + * A few tests have been updated to work under the shell compatible + mode of zsh. + (merge a92f243a94 bc/zsh-testsuite later to maint). + + * The way patience diff finds LCS has been optimized. + (merge c7e3b8085b yc/xdiff-patience-optim later to maint). + + * Recent optimization to "last-modified" command introduced use of + uninitialized block of memory, which has been corrected. + (merge fe4e60759b tc/last-modified-active-paths-optimization later to maint). + + * "git last-modified" used to mishandle "--" to mark the beginning of + pathspec, which has been corrected. + (merge 05491b90ce js/last-modified-with-sparse-checkouts later to maint). + + * Emulation code clean-up. + (merge 42aa7603aa gf/win32-pthread-cond-init later to maint). + + * Other code cleanup, docfix, build fix, etc. + (merge 46207a54cc qj/doc-http-bad-want-response later to maint). + (merge df90eccd93 kh/doc-commit-extra-references later to maint). + (merge f18aa68861 rs/xmkstemp-simplify later to maint). + (merge fddba8f737 ja/doc-synopsis-style later to maint). + (merge 22ce0cb639 en/xdiff-cleanup-2 later to maint). + (merge 8ef7355a8f je/doc-pull later to maint). diff --git a/Documentation/config/core.adoc b/Documentation/config/core.adoc index 11efad189e..01202da7cd 100644 --- a/Documentation/config/core.adoc +++ b/Documentation/config/core.adoc @@ -629,6 +629,8 @@ core.whitespace:: part of the line terminator, i.e. with it, `trailing-space` does not trigger if the character before such a carriage-return is not a whitespace (not enabled by default). +* `incomplete-line` treats the last line of a file that is missing the + newline at the end as an error (not enabled by default). * `tabwidth=<n>` tells how many character positions a tab occupies; this is relevant for `indent-with-non-tab` and when Git fixes `tab-in-indent` errors. The default tab width is 8. Allowed values are 1 to 63. diff --git a/Documentation/config/fetch.adoc b/Documentation/config/fetch.adoc index d7dc461bd1..cd40db0cad 100644 --- a/Documentation/config/fetch.adoc +++ b/Documentation/config/fetch.adoc @@ -1,32 +1,32 @@ -fetch.recurseSubmodules:: +`fetch.recurseSubmodules`:: This option controls whether `git fetch` (and the underlying fetch in `git pull`) will recursively fetch into populated submodules. - This option can be set either to a boolean value or to 'on-demand'. + This option can be set either to a boolean value or to `on-demand`. Setting it to a boolean changes the behavior of fetch and pull to recurse unconditionally into submodules when set to true or to not - recurse at all when set to false. When set to 'on-demand', fetch and + recurse at all when set to false. When set to `on-demand`, fetch and pull will only recurse into a populated submodule when its superproject retrieves a commit that updates the submodule's reference. - Defaults to 'on-demand', or to the value of 'submodule.recurse' if set. + Defaults to `on-demand`, or to the value of `submodule.recurse` if set. -fetch.fsckObjects:: +`fetch.fsckObjects`:: If it is set to true, git-fetch-pack will check all fetched objects. See `transfer.fsckObjects` for what's - checked. Defaults to false. If not set, the value of + checked. Defaults to `false`. If not set, the value of `transfer.fsckObjects` is used instead. -fetch.fsck.<msg-id>:: +`fetch.fsck.<msg-id>`:: Acts like `fsck.<msg-id>`, but is used by linkgit:git-fetch-pack[1] instead of linkgit:git-fsck[1]. See the `fsck.<msg-id>` documentation for details. -fetch.fsck.skipList:: +`fetch.fsck.skipList`:: Acts like `fsck.skipList`, but is used by linkgit:git-fetch-pack[1] instead of linkgit:git-fsck[1]. See the `fsck.skipList` documentation for details. -fetch.unpackLimit:: +`fetch.unpackLimit`:: If the number of objects fetched over the Git native transfer is below this limit, then the objects will be unpacked into loose object @@ -37,12 +37,12 @@ fetch.unpackLimit:: especially on slow filesystems. If not set, the value of `transfer.unpackLimit` is used instead. -fetch.prune:: +`fetch.prune`:: If true, fetch will automatically behave as if the `--prune` option was given on the command line. See also `remote.<name>.prune` and the PRUNING section of linkgit:git-fetch[1]. -fetch.pruneTags:: +`fetch.pruneTags`:: If true, fetch will automatically behave as if the `refs/tags/*:refs/tags/*` refspec was provided when pruning, if not set already. This allows for setting both this option @@ -50,41 +50,41 @@ fetch.pruneTags:: refs. See also `remote.<name>.pruneTags` and the PRUNING section of linkgit:git-fetch[1]. -fetch.all:: +`fetch.all`:: If true, fetch will attempt to update all available remotes. This behavior can be overridden by passing `--no-all` or by explicitly specifying one or more remote(s) to fetch from. - Defaults to false. + Defaults to `false`. -fetch.output:: +`fetch.output`:: Control how ref update status is printed. Valid values are `full` and `compact`. Default value is `full`. See the OUTPUT section in linkgit:git-fetch[1] for details. -fetch.negotiationAlgorithm:: +`fetch.negotiationAlgorithm`:: Control how information about the commits in the local repository is sent when negotiating the contents of the packfile to be sent by - the server. Set to "consecutive" to use an algorithm that walks - over consecutive commits checking each one. Set to "skipping" to + the server. Set to `consecutive` to use an algorithm that walks + over consecutive commits checking each one. Set to `skipping` to use an algorithm that skips commits in an effort to converge faster, but may result in a larger-than-necessary packfile; or set - to "noop" to not send any information at all, which will almost + to `noop` to not send any information at all, which will almost certainly result in a larger-than-necessary packfile, but will skip - the negotiation step. Set to "default" to override settings made + the negotiation step. Set to `default` to override settings made previously and use the default behaviour. The default is normally - "consecutive", but if `feature.experimental` is true, then the - default is "skipping". Unknown values will cause 'git fetch' to + `consecutive`, but if `feature.experimental` is `true`, then the + default is `skipping`. Unknown values will cause `git fetch` to error out. + See also the `--negotiate-only` and `--negotiation-tip` options to linkgit:git-fetch[1]. -fetch.showForcedUpdates:: - Set to false to enable `--no-show-forced-updates` in +`fetch.showForcedUpdates`:: + Set to `false` to enable `--no-show-forced-updates` in linkgit:git-fetch[1] and linkgit:git-pull[1] commands. - Defaults to true. + Defaults to `true`. -fetch.parallel:: +`fetch.parallel`:: Specifies the maximal number of fetch operations to be run in parallel at a time (submodules, or remotes when the `--multiple` option of linkgit:git-fetch[1] is in effect). @@ -94,16 +94,16 @@ A value of 0 will give some reasonable default. If unset, it defaults to 1. For submodules, this setting can be overridden using the `submodule.fetchJobs` config setting. -fetch.writeCommitGraph:: +`fetch.writeCommitGraph`:: Set to true to write a commit-graph after every `git fetch` command that downloads a pack-file from a remote. Using the `--split` option, most executions will create a very small commit-graph file on top of the existing commit-graph file(s). Occasionally, these files will merge and the write may take longer. Having an updated commit-graph file helps performance of many Git commands, including `git merge-base`, - `git push -f`, and `git log --graph`. Defaults to false. + `git push -f`, and `git log --graph`. Defaults to `false`. -fetch.bundleURI:: +`fetch.bundleURI`:: This value stores a URI for downloading Git object data from a bundle URI before performing an incremental fetch from the origin Git server. This is similar to how the `--bundle-uri` option behaves in @@ -115,9 +115,9 @@ If you modify this value and your repository has a `fetch.bundleCreationToken` value, then remove that `fetch.bundleCreationToken` value before fetching from the new bundle URI. -fetch.bundleCreationToken:: +`fetch.bundleCreationToken`:: When using `fetch.bundleURI` to fetch incrementally from a bundle - list that uses the "creationToken" heuristic, this config value + list that uses the "`creationToken`" heuristic, this config value stores the maximum `creationToken` value of the downloaded bundles. This value is used to prevent downloading bundles in the future if the advertised `creationToken` is not strictly larger than this diff --git a/Documentation/config/gui.adoc b/Documentation/config/gui.adoc index 171be774d2..1565c0af19 100644 --- a/Documentation/config/gui.adoc +++ b/Documentation/config/gui.adoc @@ -55,3 +55,8 @@ gui.blamehistoryctx:: linkgit:gitk[1] for the selected commit, when the `Show History Context` menu item is invoked from 'git gui blame'. If this variable is set to zero, the whole history is shown. + +gui.GCWarning:: + Determines whether linkgit:git-gui[1] should prompt for garbage + collection when git detects a large number of loose objects in + the repository. The default value is "true". diff --git a/Documentation/config/push.adoc b/Documentation/config/push.adoc index 0acbbea18a..d9112b2260 100644 --- a/Documentation/config/push.adoc +++ b/Documentation/config/push.adoc @@ -1,15 +1,15 @@ -push.autoSetupRemote:: - If set to "true" assume `--set-upstream` on default push when no +`push.autoSetupRemote`:: + If set to `true` assume `--set-upstream` on default push when no upstream tracking exists for the current branch; this option - takes effect with push.default options 'simple', 'upstream', - and 'current'. It is useful if by default you want new branches + takes effect with `push.default` options `simple`, `upstream`, + and `current`. It is useful if by default you want new branches to be pushed to the default remote (like the behavior of - 'push.default=current') and you also want the upstream tracking + `push.default=current`) and you also want the upstream tracking to be set. Workflows most likely to benefit from this option are - 'simple' central workflows where all branches are expected to + `simple` central workflows where all branches are expected to have the same name on the remote. -push.default:: +`push.default`:: Defines the action `git push` should take if no refspec is given (whether from the command-line, config, or elsewhere). Different values are well-suited for @@ -18,24 +18,28 @@ push.default:: `upstream` is probably what you want. Possible values are: + -- - -* `nothing` - do not push anything (error out) unless a refspec is - given. This is primarily meant for people who want to - avoid mistakes by always being explicit. - -* `current` - push the current branch to update a branch with the same - name on the receiving end. Works in both central and non-central - workflows. - -* `upstream` - push the current branch back to the branch whose - changes are usually integrated into the current branch (which is - called `@{upstream}`). This mode only makes sense if you are - pushing to the same repository you would normally pull from - (i.e. central workflow). - -* `tracking` - This is a deprecated synonym for `upstream`. - -* `simple` - push the current branch with the same name on the remote. +`nothing`;; +do not push anything (error out) unless a refspec is +given. This is primarily meant for people who want to +avoid mistakes by always being explicit. + +`current`;; +push the current branch to update a branch with the same +name on the receiving end. Works in both central and non-central +workflows. + +`upstream`;; +push the current branch back to the branch whose +changes are usually integrated into the current branch (which is +called `@{upstream}`). This mode only makes sense if you are +pushing to the same repository you would normally pull from +(i.e. central workflow). + +`tracking`;; +this is a deprecated synonym for `upstream`. + +`simple`;; +push the current branch with the same name on the remote. + If you are working on a centralized workflow (pushing to the same repository you pull from, which is typically `origin`), then you need to configure an upstream @@ -44,16 +48,17 @@ branch with the same name. This mode is the default since Git 2.0, and is the safest option suited for beginners. -* `matching` - push all branches having the same name on both ends. - This makes the repository you are pushing to remember the set of - branches that will be pushed out (e.g. if you always push 'maint' - and 'master' there and no other branches, the repository you push - to will have these two branches, and your local 'maint' and - 'master' will be pushed there). +`matching`;; +push all branches having the same name on both ends. +This makes the repository you are pushing to remember the set of +branches that will be pushed out (e.g. if you always push `maint` +and `master` there and no other branches, the repository you push +to will have these two branches, and your local `maint` and +`master` will be pushed there). + To use this mode effectively, you have to make sure _all_ the branches you would push out are ready to be pushed out before -running 'git push', as the whole point of this mode is to allow you +running `git push`, as the whole point of this mode is to allow you to push all of the branches in one go. If you usually finish work on only one branch and push out the result, while other branches are unfinished, this mode is not for you. Also this mode is not @@ -66,24 +71,24 @@ new default). -- -push.followTags:: +`push.followTags`:: If set to true, enable `--follow-tags` option by default. You may override this configuration at time of push by specifying `--no-follow-tags`. -push.gpgSign:: - May be set to a boolean value, or the string 'if-asked'. A true +`push.gpgSign`:: + May be set to a boolean value, or the string `if-asked`. A true value causes all pushes to be GPG signed, as if `--signed` is - passed to linkgit:git-push[1]. The string 'if-asked' causes + passed to linkgit:git-push[1]. The string `if-asked` causes pushes to be signed if the server supports it, as if - `--signed=if-asked` is passed to 'git push'. A false value may + `--signed=if-asked` is passed to `git push`. A false value may override a value from a lower-priority config file. An explicit command-line flag always overrides this config option. -push.pushOption:: +`push.pushOption`:: When no `--push-option=<option>` argument is given from the - command line, `git push` behaves as if each <value> of - this variable is given as `--push-option=<value>`. + command line, `git push` behaves as if each _<option>_ of + this variable is given as `--push-option=<option>`. + This is a multi-valued variable, and an empty value can be used in a higher priority configuration file (e.g. `.git/config` in a @@ -109,26 +114,26 @@ This will result in only b (a and c are cleared). ---- -push.recurseSubmodules:: - May be "check", "on-demand", "only", or "no", with the same behavior - as that of "push --recurse-submodules". - If not set, 'no' is used by default, unless 'submodule.recurse' is - set (in which case a 'true' value means 'on-demand'). +`push.recurseSubmodules`:: + May be `check`, `on-demand`, `only`, or `no`, with the same behavior + as that of `push --recurse-submodules`. + If not set, `no` is used by default, unless `submodule.recurse` is + set (in which case a `true` value means `on-demand`). -push.useForceIfIncludes:: - If set to "true", it is equivalent to specifying +`push.useForceIfIncludes`:: + If set to `true`, it is equivalent to specifying `--force-if-includes` as an option to linkgit:git-push[1] in the command line. Adding `--no-force-if-includes` at the time of push overrides this configuration setting. -push.negotiate:: - If set to "true", attempt to reduce the size of the packfile +`push.negotiate`:: + If set to `true`, attempt to reduce the size of the packfile sent by rounds of negotiation in which the client and the - server attempt to find commits in common. If "false", Git will + server attempt to find commits in common. If `false`, Git will rely solely on the server's ref advertisement to find commits in common. -push.useBitmaps:: - If set to "false", disable use of bitmaps for "git push" even if - `pack.useBitmaps` is "true", without preventing other git operations - from using bitmaps. Default is true. +`push.useBitmaps`:: + If set to `false`, disable use of bitmaps for `git push` even if + `pack.useBitmaps` is `true`, without preventing other git operations + from using bitmaps. Default is `true`. diff --git a/Documentation/config/replay.adoc b/Documentation/config/replay.adoc new file mode 100644 index 0000000000..7d549d2f0e --- /dev/null +++ b/Documentation/config/replay.adoc @@ -0,0 +1,11 @@ +replay.refAction:: + Specifies the default mode for handling reference updates in + `git replay`. The value can be: ++ +-- + * `update`: Update refs directly using an atomic transaction (default behavior). + * `print`: Output update-ref commands for pipeline use. +-- ++ +This setting can be overridden with the `--ref-action` command-line option. +When not configured, `git replay` defaults to `update` mode. diff --git a/Documentation/diff-algorithm-option.adoc b/Documentation/diff-algorithm-option.adoc new file mode 100644 index 0000000000..8e3a0b63d7 --- /dev/null +++ b/Documentation/diff-algorithm-option.adoc @@ -0,0 +1,20 @@ +`--diff-algorithm=(patience|minimal|histogram|myers)`:: + Choose a diff algorithm. The variants are as follows: ++ +-- + `default`;; + `myers`;; + The basic greedy diff algorithm. Currently, this is the default. + `minimal`;; + Spend extra time to make sure the smallest possible diff is + produced. + `patience`;; + Use "patience diff" algorithm when generating patches. + `histogram`;; + This algorithm extends the patience algorithm to "support + low-occurrence common elements". +-- ++ +For instance, if you configured the `diff.algorithm` variable to a +non-default value and want to use the default one, then you +have to use `--diff-algorithm=default` option. diff --git a/Documentation/diff-options.adoc b/Documentation/diff-options.adoc index ae31520f7f..9cdad6f72a 100644 --- a/Documentation/diff-options.adoc +++ b/Documentation/diff-options.adoc @@ -197,26 +197,7 @@ and starts with _<text>_, this algorithm attempts to prevent it from appearing as a deletion or addition in the output. It uses the "patience diff" algorithm internally. -`--diff-algorithm=(patience|minimal|histogram|myers)`:: - Choose a diff algorithm. The variants are as follows: -+ --- - `default`;; - `myers`;; - The basic greedy diff algorithm. Currently, this is the default. - `minimal`;; - Spend extra time to make sure the smallest possible diff is - produced. - `patience`;; - Use "patience diff" algorithm when generating patches. - `histogram`;; - This algorithm extends the patience algorithm to "support - low-occurrence common elements". --- -+ -For instance, if you configured the `diff.algorithm` variable to a -non-default value and want to use the default one, then you -have to use `--diff-algorithm=default` option. +include::diff-algorithm-option.adoc[] `--stat[=<width>[,<name-width>[,<count>]]]`:: Generate a diffstat. By default, as much space as necessary diff --git a/Documentation/fetch-options.adoc b/Documentation/fetch-options.adoc index ad1e1f49be..fcba46ee9e 100644 --- a/Documentation/fetch-options.adoc +++ b/Documentation/fetch-options.adoc @@ -1,41 +1,41 @@ ---all:: ---no-all:: +`--all`:: +`--no-all`:: Fetch all remotes, except for the ones that has the `remote.<name>.skipFetchAll` configuration variable set. This overrides the configuration variable `fetch.all`. --a:: ---append:: +`-a`:: +`--append`:: Append ref names and object names of fetched refs to the existing contents of `.git/FETCH_HEAD`. Without this option old data in `.git/FETCH_HEAD` will be overwritten. ---atomic:: +`--atomic`:: Use an atomic transaction to update local refs. Either all refs are updated, or on error, no refs are updated. ---depth=<depth>:: +`--depth=<depth>`:: Limit fetching to the specified number of commits from the tip of each remote branch history. If fetching to a 'shallow' repository created by `git clone` with `--depth=<depth>` option (see linkgit:git-clone[1]), deepen or shorten the history to the specified number of commits. Tags for the deepened commits are not fetched. ---deepen=<depth>:: - Similar to --depth, except it specifies the number of commits +`--deepen=<depth>`:: + Similar to `--depth`, except it specifies the number of commits from the current shallow boundary instead of from the tip of each remote branch history. ---shallow-since=<date>:: +`--shallow-since=<date>`:: Deepen or shorten the history of a shallow repository to - include all reachable commits after <date>. + include all reachable commits after _<date>_. ---shallow-exclude=<ref>:: +`--shallow-exclude=<ref>`:: Deepen or shorten the history of a shallow repository to exclude commits reachable from a specified remote branch or tag. This option can be specified multiple times. ---unshallow:: +`--unshallow`:: If the source repository is complete, convert a shallow repository to a complete one, removing all the limitations imposed by shallow repositories. @@ -43,13 +43,13 @@ If the source repository is shallow, fetch as much as possible so that the current repository has the same history as the source repository. ---update-shallow:: +`--update-shallow`:: By default when fetching from a shallow repository, `git fetch` refuses refs that require updating - .git/shallow. This option updates .git/shallow and accepts such + `.git/shallow`. This option updates `.git/shallow` and accepts such refs. ---negotiation-tip=<commit|glob>:: +`--negotiation-tip=(<commit>|<glob>)`:: By default, Git will report, to the server, commits reachable from all local refs to find common commits in an attempt to reduce the size of the to-be-received packfile. If specified, @@ -69,28 +69,28 @@ See also the `fetch.negotiationAlgorithm` and `push.negotiate` configuration variables documented in linkgit:git-config[1], and the `--negotiate-only` option below. ---negotiate-only:: +`--negotiate-only`:: Do not fetch anything from the server, and instead print the - ancestors of the provided `--negotiation-tip=*` arguments, + ancestors of the provided `--negotiation-tip=` arguments, which we have in common with the server. + -This is incompatible with `--recurse-submodules=[yes|on-demand]`. +This is incompatible with `--recurse-submodules=(yes|on-demand)`. Internally this is used to implement the `push.negotiate` option, see linkgit:git-config[1]. ---dry-run:: +`--dry-run`:: Show what would be done, without making any changes. ---porcelain:: +`--porcelain`:: Print the output to standard output in an easy-to-parse format for scripts. See section OUTPUT in linkgit:git-fetch[1] for details. + -This is incompatible with `--recurse-submodules=[yes|on-demand]` and takes +This is incompatible with `--recurse-submodules=(yes|on-demand)` and takes precedence over the `fetch.output` config option. ifndef::git-pull[] ---write-fetch-head:: ---no-write-fetch-head:: +`--write-fetch-head`:: +`--no-write-fetch-head`:: Write the list of remote refs fetched in the `FETCH_HEAD` file directly under `$GIT_DIR`. This is the default. Passing `--no-write-fetch-head` from the command line tells @@ -98,64 +98,65 @@ ifndef::git-pull[] file is never written. endif::git-pull[] --f:: ---force:: - When 'git fetch' is used with `<src>:<dst>` refspec, it may - refuse to update the local branch as discussed +`-f`:: +`--force`:: ifdef::git-pull[] - in the `<refspec>` part of the linkgit:git-fetch[1] - documentation. +When `git fetch` is used with `<src>:<dst>` refspec, it may +refuse to update the local branch as discussed +in the _<refspec>_ part of the linkgit:git-fetch[1] +documentation. endif::git-pull[] ifndef::git-pull[] - in the `<refspec>` part below. +When `git fetch` is used with `<src>:<dst>` refspec, it may +refuse to update the local branch as discussed in the _<refspec>_ part below. endif::git-pull[] - This option overrides that check. +This option overrides that check. --k:: ---keep:: +`-k`:: +`--keep`:: Keep downloaded pack. ifndef::git-pull[] ---multiple:: - Allow several <repository> and <group> arguments to be - specified. No <refspec>s may be specified. - ---auto-maintenance:: ---no-auto-maintenance:: ---auto-gc:: ---no-auto-gc:: +`--multiple`:: + Allow several _<repository>_ and _<group>_ arguments to be + specified. No __<refspec>__s may be specified. + +`--auto-maintenance`:: +`--no-auto-maintenance`:: +`--auto-gc`:: +`--no-auto-gc`:: Run `git maintenance run --auto` at the end to perform automatic - repository maintenance if needed. (`--[no-]auto-gc` is a synonym.) + repository maintenance if needed. This is enabled by default. ---write-commit-graph:: ---no-write-commit-graph:: +`--write-commit-graph`:: +`--no-write-commit-graph`:: Write a commit-graph after fetching. This overrides the config setting `fetch.writeCommitGraph`. endif::git-pull[] ---prefetch:: +`--prefetch`:: Modify the configured refspec to place all refs into the `refs/prefetch/` namespace. See the `prefetch` task in linkgit:git-maintenance[1]. --p:: ---prune:: +`-p`:: +`--prune`:: Before fetching, remove any remote-tracking references that no longer exist on the remote. Tags are not subject to pruning if they are fetched only because of the default tag - auto-following or due to a --tags option. However, if tags + auto-following or due to a `--tags` option. However, if tags are fetched due to an explicit refspec (either on the command line or in the remote configuration, for example if the remote - was cloned with the --mirror option), then they are also + was cloned with the `--mirror` option), then they are also subject to pruning. Supplying `--prune-tags` is a shorthand for providing the tag refspec. ifndef::git-pull[] + See the PRUNING section below for more details. --P:: ---prune-tags:: +`-P`:: +`--prune-tags`:: Before fetching, remove any local tags that no longer exist on the remote if `--prune` is enabled. This option should be used more carefully, unlike `--prune` it will remove any local @@ -168,17 +169,17 @@ See the PRUNING section below for more details. endif::git-pull[] ifndef::git-pull[] --n:: +`-n`:: endif::git-pull[] ---no-tags:: +`--no-tags`:: By default, tags that point at objects that are downloaded from the remote repository are fetched and stored locally. This option disables this automatic tag following. The default - behavior for a remote may be specified with the remote.<name>.tagOpt + behavior for a remote may be specified with the `remote.<name>.tagOpt` setting. See linkgit:git-config[1]. ifndef::git-pull[] ---refetch:: +`--refetch`:: Instead of negotiating with the server to avoid transferring commits and associated objects that are already present locally, this option fetches all objects as a fresh clone would. Use this to reapply a partial clone @@ -187,29 +188,29 @@ ifndef::git-pull[] object database pack consolidation to remove any duplicate objects. endif::git-pull[] ---refmap=<refspec>:: +`--refmap=<refspec>`:: When fetching refs listed on the command line, use the specified refspec (can be given more than once) to map the refs to remote-tracking branches, instead of the values of - `remote.*.fetch` configuration variables for the remote - repository. Providing an empty `<refspec>` to the + `remote.<name>.fetch` configuration variables for the remote + repository. Providing an empty _<refspec>_ to the `--refmap` option causes Git to ignore the configured refspecs and rely entirely on the refspecs supplied as command-line arguments. See section on "Configured Remote-tracking Branches" for details. --t:: ---tags:: +`-t`:: +`--tags`:: Fetch all tags from the remote (i.e., fetch remote tags `refs/tags/*` into local tags with the same name), in addition to whatever else would otherwise be fetched. Using this - option alone does not subject tags to pruning, even if --prune + option alone does not subject tags to pruning, even if `--prune` is used (though tags may be pruned anyway if they are also the destination of an explicit refspec; see `--prune`). ifndef::git-pull[] ---recurse-submodules[=(yes|on-demand|no)]:: - This option controls if and under what conditions new commits of +`--recurse-submodules[=(yes|on-demand|no)]`:: + Control if and under what conditions new commits of submodules should be fetched too. When recursing through submodules, `git fetch` always attempts to fetch "changed" submodules, that is, a submodule that has commits that are referenced by a newly fetched @@ -219,19 +220,19 @@ ifndef::git-pull[] adds a new submodule, that submodule cannot be fetched until it is cloned e.g. by `git submodule update`. + -When set to 'on-demand', only changed submodules are fetched. When set -to 'yes', all populated submodules are fetched and submodules that are -both unpopulated and changed are fetched. When set to 'no', submodules +When set to `on-demand`, only changed submodules are fetched. When set +to `yes`, all populated submodules are fetched and submodules that are +both unpopulated and changed are fetched. When set to `no`, submodules are never fetched. + When unspecified, this uses the value of `fetch.recurseSubmodules` if it -is set (see linkgit:git-config[1]), defaulting to 'on-demand' if unset. -When this option is used without any value, it defaults to 'yes'. +is set (see linkgit:git-config[1]), defaulting to `on-demand` if unset. +When this option is used without any value, it defaults to `yes`. endif::git-pull[] --j:: ---jobs=<n>:: - Number of parallel children to be used for all forms of fetching. +`-j <n>`:: +`--jobs=<n>`:: + Parallelize all forms of fetching up to _<n>_ jobs at a time. + If the `--multiple` option was specified, the different remotes will be fetched in parallel. If multiple submodules are fetched, they will be fetched in @@ -242,12 +243,12 @@ Typically, parallel recursive and multi-remote fetches will be faster. By default fetches are performed sequentially, not in parallel. ifndef::git-pull[] ---no-recurse-submodules:: +`--no-recurse-submodules`:: Disable recursive fetching of submodules (this has the same effect as using the `--recurse-submodules=no` option). endif::git-pull[] ---set-upstream:: +`--set-upstream`:: If the remote is fetched successfully, add upstream (tracking) reference, used by argument-less linkgit:git-pull[1] and other commands. For more information, @@ -255,57 +256,57 @@ endif::git-pull[] linkgit:git-config[1]. ifndef::git-pull[] ---submodule-prefix=<path>:: - Prepend <path> to paths printed in informative messages +`--submodule-prefix=<path>`:: + Prepend _<path>_ to paths printed in informative messages such as "Fetching submodule foo". This option is used internally when recursing over submodules. ---recurse-submodules-default=[yes|on-demand]:: +`--recurse-submodules-default=(yes|on-demand)`:: This option is used internally to temporarily provide a - non-negative default value for the --recurse-submodules + non-negative default value for the `--recurse-submodules` option. All other methods of configuring fetch's submodule recursion (such as settings in linkgit:gitmodules[5] and linkgit:git-config[1]) override this option, as does - specifying --[no-]recurse-submodules directly. + specifying `--[no-]recurse-submodules` directly. --u:: ---update-head-ok:: - By default 'git fetch' refuses to update the head which +`-u`:: +`--update-head-ok`:: + By default `git fetch` refuses to update the head which corresponds to the current branch. This flag disables the - check. This is purely for the internal use for 'git pull' - to communicate with 'git fetch', and unless you are + check. This is purely for the internal use for `git pull` + to communicate with `git fetch`, and unless you are implementing your own Porcelain you are not supposed to use it. endif::git-pull[] ---upload-pack <upload-pack>:: +`--upload-pack <upload-pack>`:: When given, and the repository to fetch from is handled - by 'git fetch-pack', `--exec=<upload-pack>` is passed to + by `git fetch-pack`, `--exec=<upload-pack>` is passed to the command to specify non-default path for the command run on the other end. ifndef::git-pull[] --q:: ---quiet:: - Pass --quiet to git-fetch-pack and silence any other internally +`-q`:: +`--quiet`:: + Pass `--quiet` to `git-fetch-pack` and silence any other internally used git commands. Progress is not reported to the standard error stream. --v:: ---verbose:: +`-v`:: +`--verbose`:: Be verbose. endif::git-pull[] ---progress:: +`--progress`:: Progress status is reported on the standard error stream - by default when it is attached to a terminal, unless -q + by default when it is attached to a terminal, unless `-q` is specified. This flag forces progress status even if the standard error stream is not directed to a terminal. --o <option>:: ---server-option=<option>:: +`-o <option>`:: +`--server-option=<option>`:: Transmit the given string to the server when communicating using - protocol version 2. The given string must not contain a NUL or LF + protocol version 2. The given string must not contain a _NUL_ or _LF_ character. The server's handling of server options, including unknown ones, is server-specific. When multiple `--server-option=<option>` are given, they are all @@ -314,23 +315,23 @@ endif::git-pull[] the values of configuration variable `remote.<name>.serverOption` are used instead. ---show-forced-updates:: +`--show-forced-updates`:: By default, git checks if a branch is force-updated during - fetch. This can be disabled through fetch.showForcedUpdates, but - the --show-forced-updates option guarantees this check occurs. + fetch. This can be disabled through `fetch.showForcedUpdates`, but + the `--show-forced-updates` option guarantees this check occurs. See linkgit:git-config[1]. ---no-show-forced-updates:: +`--no-show-forced-updates`:: By default, git checks if a branch is force-updated during - fetch. Pass --no-show-forced-updates or set fetch.showForcedUpdates + fetch. Pass `--no-show-forced-updates` or set `fetch.showForcedUpdates` to false to skip this check for performance reasons. If used during - 'git-pull' the --ff-only option will still check for forced updates + `git-pull` the `--ff-only` option will still check for forced updates before attempting a fast-forward update. See linkgit:git-config[1]. --4:: ---ipv4:: +`-4`:: +`--ipv4`:: Use IPv4 addresses only, ignoring IPv6 addresses. --6:: ---ipv6:: +`-6`:: +`--ipv6`:: Use IPv6 addresses only, ignoring IPv4 addresses. diff --git a/Documentation/git-am.adoc b/Documentation/git-am.adoc index b23b4fba20..0c94776e29 100644 --- a/Documentation/git-am.adoc +++ b/Documentation/git-am.adoc @@ -162,6 +162,13 @@ Valid <action> for the `--whitespace` option are: commit creation as the committer date. This allows the user to lie about the committer date by using the same value as the author date. ++ +WARNING: The history walking machinery assumes that commits have +non-decreasing commit timestamps. You should consider if you really need +to use this option. Then you should only use this option to override the +committer date when applying commits on top of a base which commit is +older (in terms of the commit date) than the oldest patch you are +applying. --ignore-date:: By default the command records the date from the e-mail diff --git a/Documentation/git-blame.adoc b/Documentation/git-blame.adoc index e438d28625..adcbb6f5dc 100644 --- a/Documentation/git-blame.adoc +++ b/Documentation/git-blame.adoc @@ -85,6 +85,8 @@ include::blame-options.adoc[] Ignore whitespace when comparing the parent's version and the child's to find where the lines came from. +include::diff-algorithm-option.adoc[] + --abbrev=<n>:: Instead of using the default 7+1 hexadecimal digits as the abbreviated object name, use <m>+1 digits, where <m> is at diff --git a/Documentation/git-commit.adoc b/Documentation/git-commit.adoc index 54c207ad45..8329c1034b 100644 --- a/Documentation/git-commit.adoc +++ b/Documentation/git-commit.adoc @@ -146,7 +146,8 @@ See linkgit:git-rebase[1] for details. linkgit:git-status[1] for details. Implies `--dry-run`. `--branch`:: - Show the branch and tracking info even in short-format. + Show the branch and tracking info even in short-format. See + linkgit:git-status[1] for details. `--porcelain`:: When doing a dry-run, give the output in a porcelain-ready @@ -154,12 +155,13 @@ See linkgit:git-rebase[1] for details. `--dry-run`. `--long`:: - When doing a dry-run, give the output in the long-format. - Implies `--dry-run`. + When doing a dry-run, give the output in the long-format. This + is the default output of linkgit:git-status[1]. Implies + `--dry-run`. `-z`:: `--null`:: - When showing `short` or `porcelain` status output, print the + When showing `short` or `porcelain` linkgit:git-status[1] output, print the filename verbatim and terminate the entries with _NUL_, instead of _LF_. If no format is given, implies the `--porcelain` output format. Without the `-z` option, filenames with "unusual" characters are diff --git a/Documentation/git-fast-import.adoc b/Documentation/git-fast-import.adoc index b74179a6c8..479c4081da 100644 --- a/Documentation/git-fast-import.adoc +++ b/Documentation/git-fast-import.adoc @@ -66,15 +66,26 @@ fast-import stream! This option is enabled automatically for remote-helpers that use the `import` capability, as they are already trusted to run their own code. ---signed-tags=(verbatim|warn-verbatim|warn-strip|strip|abort):: - Specify how to handle signed tags. Behaves in the same way - as the same option in linkgit:git-fast-export[1], except that - default is 'verbatim' (instead of 'abort'). - ---signed-commits=(verbatim|warn-verbatim|warn-strip|strip|abort):: - Specify how to handle signed commits. Behaves in the same way - as the same option in linkgit:git-fast-export[1], except that - default is 'verbatim' (instead of 'abort'). +`--signed-tags=(verbatim|warn-verbatim|warn-strip|strip|abort)`:: + Specify how to handle signed tags. Behaves in the same way as + the `--signed-commits=<mode>` below, except that the + `strip-if-invalid` mode is not yet supported. Like for signed + commits, the default mode is `verbatim`. + +`--signed-commits=<mode>`:: + Specify how to handle signed commits. The following <mode>s + are supported: ++ +* `verbatim`, which is the default, will silently import commit + signatures. +* `warn-verbatim` will import them, but will display a warning. +* `abort` will make this program die when encountering a signed + commit. +* `strip` will silently make the commits unsigned. +* `warn-strip` will make them unsigned, but will display a warning. +* `strip-if-invalid` will check signatures and, if they are invalid, + will strip them and display a warning. The validation is performed + in the same way as linkgit:git-verify-commit[1] does it. Options for Frontends ~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/git-fetch.adoc b/Documentation/git-fetch.adoc index 16f5d9d69a..db03541915 100644 --- a/Documentation/git-fetch.adoc +++ b/Documentation/git-fetch.adoc @@ -8,11 +8,11 @@ git-fetch - Download objects and refs from another repository SYNOPSIS -------- -[verse] -'git fetch' [<options>] [<repository> [<refspec>...]] -'git fetch' [<options>] <group> -'git fetch' --multiple [<options>] [(<repository> | <group>)...] -'git fetch' --all [<options>] +[synopsis] +git fetch [<options>] [<repository> [<refspec>...]] +git fetch [<options>] <group> +git fetch --multiple [<options>] [(<repository>|<group>)...] +git fetch --all [<options>] DESCRIPTION @@ -20,19 +20,19 @@ DESCRIPTION Fetch branches and/or tags (collectively, "refs") from one or more other repositories, along with the objects necessary to complete their histories. Remote-tracking branches are updated (see the description -of <refspec> below for ways to control this behavior). +of _<refspec>_ below for ways to control this behavior). By default, any tag that points into the histories being fetched is also fetched; the effect is to fetch tags that point at branches that you are interested in. This default behavior -can be changed by using the --tags or --no-tags options or by -configuring remote.<name>.tagOpt. By using a refspec that fetches tags +can be changed by using the `--tags` or `--no-tags` options or by +configuring `remote.<name>.tagOpt`. By using a refspec that fetches tags explicitly, you can fetch tags that do not point into branches you are interested in as well. -'git fetch' can fetch from either a single named repository or URL, -or from several repositories at once if <group> is given and -there is a remotes.<group> entry in the configuration file. +`git fetch` can fetch from either a single named repository or URL, +or from several repositories at once if _<group>_ is given and +there is a `remotes.<group>` entry in the configuration file. (See linkgit:git-config[1]). When no remote is specified, by default the `origin` remote will be used, @@ -48,15 +48,15 @@ include::fetch-options.adoc[] include::pull-fetch-param.adoc[] ---stdin:: +`--stdin`:: Read refspecs, one per line, from stdin in addition to those provided - as arguments. The "tag <name>" format is not supported. + as arguments. The "tag _<name>_" format is not supported. include::urls-remotes.adoc[] - -CONFIGURED REMOTE-TRACKING BRANCHES[[CRTB]] -------------------------------------------- +[[CRTB]] +CONFIGURED REMOTE-TRACKING BRANCHES +----------------------------------- You often interact with the same remote repository by regularly and repeatedly fetching from it. In order to keep track @@ -84,13 +84,13 @@ This configuration is used in two ways: * When `git fetch` is run with explicit branches and/or tags to fetch on the command line, e.g. `git fetch origin master`, the - <refspec>s given on the command line determine what are to be + _<refspec>s_ given on the command line determine what are to be fetched (e.g. `master` in the example, which is a short-hand for `master:`, which in turn means - "fetch the 'master' branch but I do not explicitly say what + "fetch the `master` branch but I do not explicitly say what remote-tracking branch to update with it from the command line"), and the example command will - fetch _only_ the 'master' branch. The `remote.<repository>.fetch` + fetch _only_ the `master` branch. The `remote.<repository>.fetch` values determine which remote-tracking branch, if any, is updated. When used in this way, the `remote.<repository>.fetch` values do not have any @@ -144,9 +144,9 @@ tracking branches that are deleted, but any local tag that doesn't exist on the remote. This might not be what you expect, i.e. you want to prune remote -`<name>`, but also explicitly fetch tags from it, so when you fetch +_<name>_, but also explicitly fetch tags from it, so when you fetch from it you delete all your local tags, most of which may not have -come from the `<name>` remote in the first place. +come from the _<name>_ remote in the first place. So be careful when using this with a refspec like `refs/tags/*:refs/tags/*`, or any other refspec which might map @@ -213,11 +213,11 @@ of the form: <flag> <old-object-id> <new-object-id> <local-reference> ------------------------------- -The status of up-to-date refs is shown only if the --verbose option is +The status of up-to-date refs is shown only if the `--verbose` option is used. In compact output mode, specified with configuration variable -fetch.output, if either entire `<from>` or `<to>` is found in the +fetch.output, if either entire _<from>_ or _<to>_ is found in the other string, it will be substituted with `*` in the other string. For example, `master -> origin/master` becomes `master -> origin/*`. @@ -303,7 +303,7 @@ include::config/fetch.adoc[] BUGS ---- -Using --recurse-submodules can only fetch new commits in submodules that are +Using `--recurse-submodules` can only fetch new commits in submodules that are present locally e.g. in `$GIT_DIR/modules/`. If the upstream adds a new submodule, that submodule cannot be fetched until it is cloned e.g. by `git submodule update`. This is expected to be fixed in a future Git version. diff --git a/Documentation/git-maintenance.adoc b/Documentation/git-maintenance.adoc index 540b5cf68b..bda616f14c 100644 --- a/Documentation/git-maintenance.adoc +++ b/Documentation/git-maintenance.adoc @@ -12,6 +12,7 @@ SYNOPSIS 'git maintenance' run [<options>] 'git maintenance' start [--scheduler=<scheduler>] 'git maintenance' (stop|register|unregister) [<options>] +'git maintenance' is-needed [<options>] DESCRIPTION @@ -84,6 +85,16 @@ The `unregister` subcommand will report an error if the current repository is not already registered. Use the `--force` option to return success even when the current repository is not registered. +is-needed:: + Check whether maintenance needs to be run without actually running it. + Exits with a 0 status code if maintenance needs to be run, 1 otherwise. + Ideally used with the '--auto' flag. ++ +If one or more `--task` options are specified, then those tasks are checked +in that order. Otherwise, the tasks are determined by which +`maintenance.<task>.enabled` config options are true. By default, only +`maintenance.gc.enabled` is true. + TASKS ----- @@ -183,6 +194,8 @@ OPTIONS in the `gc.auto` config setting, or when the number of pack-files exceeds the `gc.autoPackLimit` config setting. Not compatible with the `--schedule` option. + When combined with the `is-needed` subcommand, check if the required + thresholds are met without actually running maintenance. --schedule:: When combined with the `run` subcommand, run maintenance tasks diff --git a/Documentation/git-pull.adoc b/Documentation/git-pull.adoc index cd3bbc90e3..88f4fd3926 100644 --- a/Documentation/git-pull.adoc +++ b/Documentation/git-pull.adoc @@ -8,8 +8,8 @@ git-pull - Fetch from and integrate with another repository or a local branch SYNOPSIS -------- -[verse] -'git pull' [<options>] [<repository> [<refspec>...]] +[synopsis] +git pull [<options>] [<repository> [<refspec>...]] DESCRIPTION @@ -37,13 +37,13 @@ You can also set the configuration options `pull.rebase`, `pull.squash`, or `pull.ff` with your preferred behaviour. If there's a merge conflict during the merge or rebase that you don't -want to handle, you can safely abort it with `git merge --abort` or `git ---rebase abort`. +want to handle, you can safely abort it with `git merge --abort` or +`git rebase --abort`. OPTIONS ------- -<repository>:: +_<repository>_:: The "remote" repository to pull from. This can be either a URL (see the section <<URLS,GIT URLS>> below) or the name of a remote (see the section <<REMOTES,REMOTES>> below). @@ -52,29 +52,29 @@ Defaults to the configured upstream for the current branch, or `origin`. See <<UPSTREAM-BRANCHES,UPSTREAM BRANCHES>> below for more on how to configure upstreams. -<refspec>:: +_<refspec>_:: Which branch or other reference(s) to fetch and integrate into the current branch, for example `main` in `git pull origin main`. Defaults to the configured upstream for the current branch. + This can be a branch, tag, or other collection of reference(s). -See <<fetch-refspec,<refspec>>> below under "Options related to fetching" +See <<fetch-refspec,_<refspec>_>> below under "Options related to fetching" for the full syntax, and <<DEFAULT-BEHAVIOUR,DEFAULT BEHAVIOUR>> below for how `git pull` uses this argument to determine which remote branch to integrate. --q:: ---quiet:: +`-q`:: +`--quiet`:: This is passed to both underlying git-fetch to squelch reporting of during transfer, and underlying git-merge to squelch output during merging. --v:: ---verbose:: - Pass --verbose to git-fetch and git-merge. +`-v`:: +`--verbose`:: + Pass `--verbose` to git-fetch and git-merge. ---recurse-submodules[=(yes|on-demand|no)]:: ---no-recurse-submodules:: +`--recurse-submodules[=(yes|on-demand|no)]`:: +`--no-recurse-submodules`:: This option controls if new commits of populated submodules should be fetched, and if the working trees of active submodules should be updated, too (see linkgit:git-fetch[1], linkgit:git-config[1] and @@ -91,21 +91,20 @@ Options related to merging include::merge-options.adoc[] --r:: ---rebase[=(false|true|merges|interactive)]:: - When true, rebase the current branch on top of the upstream +`-r`:: +`--rebase[=(true|merges|false|interactive)]`:: +`true`;; rebase the current branch on top of the upstream branch after fetching. If there is a remote-tracking branch corresponding to the upstream branch and the upstream branch was rebased since last fetched, the rebase uses that information - to avoid rebasing non-local changes. -+ -When set to `merges`, rebase using `git rebase --rebase-merges` so that + to avoid rebasing non-local changes. This is the default. + +`merges`;; rebase using `git rebase --rebase-merges` so that the local merge commits are included in the rebase (see linkgit:git-rebase[1] for details). -+ -When false, merge the upstream branch into the current branch. -+ -When `interactive`, enable the interactive mode of rebase. +`false`;; merge the upstream branch into the current branch. +`interactive`;; enable the interactive mode of rebase. + + See `pull.rebase`, `branch.<name>.rebase` and `branch.autoSetupRebase` in linkgit:git-config[1] if you want to make `git pull` always use @@ -117,8 +116,8 @@ It rewrites history, which does not bode well when you published that history already. Do *not* use this option unless you have read linkgit:git-rebase[1] carefully. ---no-rebase:: - This is shorthand for --rebase=false. +`--no-rebase`:: + This is shorthand for `--rebase=false`. Options related to fetching ~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -178,7 +177,7 @@ uses the refspec from the configuration or rules apply: . If `branch.<name>.merge` configuration for the current - branch `<name>` exists, that is the name of the branch at the + branch _<name>_ exists, that is the name of the branch at the remote site that is merged. . If the refspec is a globbing one, nothing is merged. @@ -198,9 +197,9 @@ $ git pull $ git pull origin ------------------------------------------------ + -Normally the branch merged in is the HEAD of the remote repository, -but the choice is determined by the branch.<name>.remote and -branch.<name>.merge options; see linkgit:git-config[1] for details. +Normally the branch merged in is the `HEAD` of the remote repository, +but the choice is determined by the `branch.<name>.remote` and +`branch.<name>.merge` options; see linkgit:git-config[1] for details. * Merge into the current branch the remote branch `next`: + @@ -208,7 +207,7 @@ branch.<name>.merge options; see linkgit:git-config[1] for details. $ git pull origin next ------------------------------------------------ + -This leaves a copy of `next` temporarily in FETCH_HEAD, and +This leaves a copy of `next` temporarily in `FETCH_HEAD`, and updates the remote-tracking branch `origin/next`. The same can be done by invoking fetch and merge: + @@ -219,14 +218,14 @@ $ git merge origin/next If you tried a pull which resulted in complex conflicts and -would want to start over, you can recover with 'git reset'. +would want to start over, you can recover with `git reset`. include::transfer-data-leaks.adoc[] BUGS ---- -Using --recurse-submodules can only fetch new commits in already checked +Using `--recurse-submodules` can only fetch new commits in already checked out submodules right now. When e.g. upstream added a new submodule in the just fetched commits of the superproject the submodule itself cannot be fetched, making it impossible to check out that submodule later without diff --git a/Documentation/git-push.adoc b/Documentation/git-push.adoc index 864b0d0467..e5ba3a6742 100644 --- a/Documentation/git-push.adoc +++ b/Documentation/git-push.adoc @@ -8,13 +8,13 @@ git-push - Update remote refs along with associated objects SYNOPSIS -------- -[verse] -'git push' [--all | --branches | --mirror | --tags] [--follow-tags] [--atomic] [-n | --dry-run] [--receive-pack=<git-receive-pack>] - [--repo=<repository>] [-f | --force] [-d | --delete] [--prune] [-q | --quiet] [-v | --verbose] - [-u | --set-upstream] [-o <string> | --push-option=<string>] - [--[no-]signed|--signed=(true|false|if-asked)] - [--force-with-lease[=<refname>[:<expect>]] [--force-if-includes]] - [--no-verify] [<repository> [<refspec>...]] +[synopsis] +git push [--all | --branches | --mirror | --tags] [--follow-tags] [--atomic] [-n | --dry-run] [--receive-pack=<git-receive-pack>] + [--repo=<repository>] [-f | --force] [-d | --delete] [--prune] [-q | --quiet] [-v | --verbose] + [-u | --set-upstream] [-o <string> | --push-option=<string>] + [--[no-]signed | --signed=(true|false|if-asked)] + [--force-with-lease[=<refname>[:<expect>]] [--force-if-includes]] + [--no-verify] [<repository> [<refspec>...]] DESCRIPTION ----------- @@ -35,7 +35,7 @@ To decide which branches, tags, or other refs to push, Git uses 1. The `<refspec>` argument(s) (for example `main` in `git push origin main`) or the `--all`, `--mirror`, or `--tags` options -2. The `remote.*.push` configuration for the repository being pushed to +2. The `remote.<name>.push` configuration for the repository being pushed to 3. The `push.default` configuration. The default is `push.default=simple`, which will push to a branch with the same name as the current branch. See the <<CONFIGURATION,CONFIGURATION>> section below for more on `push.default`. @@ -49,25 +49,25 @@ You can make interesting things happen to a repository every time you push into it, by setting up 'hooks' there. See documentation for linkgit:git-receive-pack[1]. - -OPTIONS[[OPTIONS]] ------------------- -<repository>:: +[[OPTIONS]] +OPTIONS +------- +_<repository>_:: The "remote" repository that is the destination of a push operation. This parameter can be either a URL (see the section <<URLS,GIT URLS>> below) or the name of a remote (see the section <<REMOTES,REMOTES>> below). -<refspec>...:: +`<refspec>...`:: Specify what destination ref to update with what source object. + -The format for a refspec is [+]<src>[:<dst>], for example `main`, +The format for a refspec is `[+]<src>[:<dst>]`, for example `main`, `main:other`, or `HEAD^:refs/heads/main`. + -The `<src>` is often the name of the local branch to push, but it can be +The _<src>_ is often the name of the local branch to push, but it can be any arbitrary "SHA-1 expression" (see linkgit:gitrevisions[7]). + -The `<dst>` determines what ref to update on the remote side. It must be the +The _<dst>_ determines what ref to update on the remote side. It must be the name of a branch, tag, or other ref, not an arbitrary expression. + The `+` is optional and does the same thing as `--force`. @@ -78,23 +78,23 @@ and destination, or with a shorter form (for example `main` or `main:other`). Here are the rules for how refspecs are expanded, as well as various other special refspec forms: + - * `<src>` without a `:<dst>` means to update the same ref as the - `<src>`, unless the `remote.<repository>.push` configuration specifies a - different <dst>. For example, if `main` is a branch, then the refspec + * _<src>_ without a `:<dst>` means to update the same ref as the + _<src>_, unless the `remote.<repository>.push` configuration specifies a + different _<dst>_. For example, if `main` is a branch, then the refspec `main` expands to `main:refs/heads/main`. - * If `<dst>` unambiguously refers to a ref on the <repository> remote, + * If _<dst>_ unambiguously refers to a ref on the <repository> remote, then expand it to that ref. For example, if `v1.0` is a tag on the remote, then `HEAD:v1.0` expands to `HEAD:refs/tags/v1.0`. - * If `<src>` resolves to a ref starting with `refs/heads/` or `refs/tags/`, + * If _<src>_ resolves to a ref starting with `refs/heads/` or `refs/tags/`, then prepend that to <dst>. For example, if `main` is a branch, then `main:other` expands to `main:refs/heads/other` * The special refspec `:` (or `+:` to allow non-fast-forward updates) directs Git to push "matching" branches: for every branch that exists on the local side, the remote side is updated if a branch of the same name already exists on the remote side. - * <src> may contain a * to indicate a simple pattern match. + * _<src>_ may contain a `*` to indicate a simple pattern match. This works like a glob that matches any ref matching the pattern. - There must be only one * in both the `<src>` and `<dst>`. + There must be only one `*` in both the `<src>` and `<dst>`. It will map refs to the destination by replacing the * with the contents matched from the source. For example, `refs/heads/*:refs/heads/*` will push all branches. @@ -102,11 +102,11 @@ as well as various other special refspec forms: This specifies refs to exclude. A ref will be considered to match if it matches at least one positive refspec, and does not match any negative refspec. Negative refspecs can be pattern refspecs. - They must only contain a `<src>`. + They must only contain a _<src>_. Fully spelled out hex object names are also not supported. For example, `git push origin 'refs/heads/*' '^refs/heads/dev-*'` will push all branches except for those starting with `dev-` - * If `<src>` is empty, it deletes the `<dst>` ref from the remote + * If _<src>_ is empty, it deletes the _<dst>_ ref from the remote repository. For example, `git push origin :dev` will delete the `dev` branch. * `tag <tag>` expands to `refs/tags/<tag>:refs/tags/<tag>`. @@ -121,12 +121,12 @@ as well as various other special refspec forms: Not all updates are allowed: see PUSH RULES below for the details. ---all:: ---branches:: +`--all`:: +`--branches`:: Push all branches (i.e. refs under `refs/heads/`); cannot be used with other <refspec>. ---prune:: +`--prune`:: Remove remote branches that don't have a local counterpart. For example a remote branch `tmp` will be removed if a local branch with the same name doesn't exist any more. This also respects refspecs, e.g. @@ -134,7 +134,7 @@ Not all updates are allowed: see PUSH RULES below for the details. make sure that remote `refs/tmp/foo` will be removed if `refs/heads/foo` doesn't exist. ---mirror:: +`--mirror`:: Instead of naming each ref to push, specifies that all refs under `refs/` (which includes but is not limited to `refs/heads/`, `refs/remotes/`, and `refs/tags/`) @@ -145,26 +145,26 @@ Not all updates are allowed: see PUSH RULES below for the details. if the configuration option `remote.<remote>.mirror` is set. --n:: ---dry-run:: +`-n`:: +`--dry-run`:: Do everything except actually send the updates. ---porcelain:: +`--porcelain`:: Produce machine-readable output. The output status line for each ref will be tab-separated and sent to stdout instead of stderr. The full symbolic names of the refs will be given. --d:: ---delete:: +`-d`:: +`--delete`:: All listed refs are deleted from the remote repository. This is the same as prefixing all refs with a colon. ---tags:: +`--tags`:: All refs under `refs/tags` are pushed, in addition to refspecs explicitly listed on the command line. ---follow-tags:: +`--follow-tags`:: Push all the refs that would be pushed without this option, and also push annotated tags in `refs/tags` that are missing from the remote but are pointing at commit-ish that are @@ -172,29 +172,34 @@ Not all updates are allowed: see PUSH RULES below for the details. with configuration variable `push.followTags`. For more information, see `push.followTags` in linkgit:git-config[1]. ---signed:: ---no-signed:: ---signed=(true|false|if-asked):: +`--signed`:: +`--no-signed`:: +`--signed=(true|false|if-asked)`:: GPG-sign the push request to update refs on the receiving side, to allow it to be checked by the hooks and/or be - logged. If `false` or `--no-signed`, no signing will be - attempted. If `true` or `--signed`, the push will fail if the - server does not support signed pushes. If set to `if-asked`, - sign if and only if the server supports signed pushes. The push - will also fail if the actual call to `gpg --sign` fails. See - linkgit:git-receive-pack[1] for the details on the receiving end. - ---atomic:: ---no-atomic:: + logged. Possible values are: +`false`;; +`--no-signed`;; +no signing will be attempted. +`true`;; +`--signed`;; +the push will fail if the server does not support signed pushes. +`if-asked`;; +sign if and only if the server supports signed pushes. The push +will also fail if the actual call to `gpg --sign` fails. See +linkgit:git-receive-pack[1] for the details on the receiving end. + +`--atomic`:: +`--no-atomic`:: Use an atomic transaction on the remote side if available. Either all refs are updated, or on error, no refs are updated. If the server does not support atomic pushes the push will fail. --o <option>:: ---push-option=<option>:: +`-o <option>`:: +`--push-option=<option>`:: Transmit the given string to the server, which passes them to the pre-receive as well as the post-receive hook. The given string - must not contain a NUL or LF character. + must not contain a _NUL_ or _LF_ character. When multiple `--push-option=<option>` are given, they are all sent to the other side in the order listed on the command line. @@ -202,22 +207,22 @@ Not all updates are allowed: see PUSH RULES below for the details. line, the values of configuration variable `push.pushOption` are used instead. ---receive-pack=<git-receive-pack>:: ---exec=<git-receive-pack>:: +`--receive-pack=<git-receive-pack>`:: +`--exec=<git-receive-pack>`:: Path to the 'git-receive-pack' program on the remote end. Sometimes useful when pushing to a remote repository over ssh, and you do not have the program in - a directory on the default $PATH. + a directory on the default `$PATH`. ---force-with-lease:: ---no-force-with-lease:: ---force-with-lease=<refname>:: ---force-with-lease=<refname>:<expect>:: - Usually, "git push" refuses to update a remote ref that is +`--force-with-lease`:: +`--no-force-with-lease`:: +`--force-with-lease=<refname>`:: +`--force-with-lease=<refname>:<expect>`:: + Usually, `git push` refuses to update a remote ref that is not an ancestor of the local ref used to overwrite it. + This option overrides this restriction if the current value of the -remote ref is the expected value. "git push" fails otherwise. +remote ref is the expected value. `git push` fails otherwise. + Imagine that you have to rebase what you have already published. You will have to bypass the "must fast-forward" rule in order to @@ -239,16 +244,16 @@ current value to be the same as the remote-tracking branch we have for them. + `--force-with-lease=<refname>`, without specifying the expected value, will -protect the named ref (alone), if it is going to be updated, by +protect _<refname>_ (alone), if it is going to be updated, by requiring its current value to be the same as the remote-tracking branch we have for it. + -`--force-with-lease=<refname>:<expect>` will protect the named ref (alone), +`--force-with-lease=<refname>:<expect>` will protect _<refname>_ (alone), if it is going to be updated, by requiring its current value to be -the same as the specified value `<expect>` (which is allowed to be +the same as the specified value _<expect>_ (which is allowed to be different from the remote-tracking branch we have for the refname, or we do not even have to have such a remote-tracking branch when -this form is used). If `<expect>` is the empty string, then the named ref +this form is used). If _<expect>_ is the empty string, then the named ref must not already exist. + Note that all forms other than `--force-with-lease=<refname>:<expect>` @@ -256,7 +261,7 @@ that specifies the expected current value of the ref explicitly are still experimental and their semantics may change as we gain experience with this feature. + -"--no-force-with-lease" will cancel all the previous --force-with-lease on the +`--no-force-with-lease` will cancel all the previous `--force-with-lease` on the command line. + A general note on safety: supplying this option without an expected @@ -276,23 +281,29 @@ If your editor or some other system is running `git fetch` in the background for you a way to mitigate this is to simply set up another remote: + - git remote add origin-push $(git config remote.origin.url) - git fetch origin-push +---- +git remote add origin-push $(git config remote.origin.url) +git fetch origin-push +---- + Now when the background process runs `git fetch origin` the references on `origin-push` won't be updated, and thus commands like: + - git push --force-with-lease origin-push +---- +git push --force-with-lease origin-push +---- + Will fail unless you manually run `git fetch origin-push`. This method is of course entirely defeated by something that runs `git fetch --all`, in that case you'd need to either disable it or do something more tedious like: + - git fetch # update 'master' from remote - git tag base master # mark our base point - git rebase -i master # rewrite some commits - git push --force-with-lease=master:base master:master +---- +git fetch # update 'master' from remote +git tag base master # mark our base point +git rebase -i master # rewrite some commits +git push --force-with-lease=master:base master:master +---- + I.e. create a `base` tag for versions of the upstream code that you've seen and are willing to overwrite, then rewrite history, and finally @@ -308,26 +319,26 @@ verify if updates from the remote-tracking refs that may have been implicitly updated in the background are integrated locally before allowing a forced update. --f:: ---force:: +`-f`:: +`--force`:: Usually, `git push` will refuse to update a branch that is not an ancestor of the commit being pushed. + This flag disables that check, the other safety checks in PUSH RULES -below, and the checks in --force-with-lease. It can cause the remote +below, and the checks in `--force-with-lease`. It can cause the remote repository to lose commits; use it with care. + Note that `--force` applies to all the refs that are pushed, hence using it with `push.default` set to `matching` or with multiple push -destinations configured with `remote.*.push` may overwrite refs +destinations configured with `remote.<name>.push` may overwrite refs other than the current branch (including local refs that are strictly behind their remote counterpart). To force a push to only one branch, use a `+` in front of the refspec to push (e.g `git push origin +master` to force a push to the `master` branch). See the `<refspec>...` section above for details. ---force-if-includes:: ---no-force-if-includes:: +`--force-if-includes`:: +`--no-force-if-includes`:: Force an update only if the tip of the remote-tracking ref has been integrated locally. + @@ -343,72 +354,78 @@ a "no-op". + Specifying `--no-force-if-includes` disables this behavior. ---repo=<repository>:: - This option is equivalent to the <repository> argument. If both +`--repo=<repository>`:: + This option is equivalent to the _<repository>_ argument. If both are specified, the command-line argument takes precedence. --u:: ---set-upstream:: +`-u`:: +`--set-upstream`:: For every branch that is up to date or successfully pushed, add upstream (tracking) reference, used by argument-less linkgit:git-pull[1] and other commands. For more information, see `branch.<name>.merge` in linkgit:git-config[1]. ---thin:: ---no-thin:: +`--thin`:: +`--no-thin`:: These options are passed to linkgit:git-send-pack[1]. A thin transfer significantly reduces the amount of sent data when the sender and receiver share many of the same objects in common. The default is `--thin`. --q:: ---quiet:: +`-q`:: +`--quiet`:: Suppress all output, including the listing of updated refs, unless an error occurs. Progress is not reported to the standard error stream. --v:: ---verbose:: +`-v`:: +`--verbose`:: Run verbosely. ---progress:: +`--progress`:: Progress status is reported on the standard error stream - by default when it is attached to a terminal, unless -q + by default when it is attached to a terminal, unless `-q` is specified. This flag forces progress status even if the standard error stream is not directed to a terminal. ---no-recurse-submodules:: ---recurse-submodules=check|on-demand|only|no:: +`--no-recurse-submodules`:: +`--recurse-submodules=(check|on-demand|only|no)`:: May be used to make sure all submodule commits used by the revisions to be pushed are available on a remote-tracking branch. - If 'check' is used Git will verify that all submodule commits that + Possible values are: +`check`;; + Git will verify that all submodule commits that changed in the revisions to be pushed are available on at least one remote of the submodule. If any commits are missing the push will - be aborted and exit with non-zero status. If 'on-demand' is used + be aborted and exit with non-zero status. +`on-demand`;; all submodules that changed in the revisions to be pushed will be - pushed. If on-demand was not able to push all necessary revisions it will - also be aborted and exit with non-zero status. If 'only' is used all - submodules will be pushed while the superproject is left - unpushed. A value of 'no' or using `--no-recurse-submodules` can be used - to override the push.recurseSubmodules configuration variable when no - submodule recursion is required. -+ -When using 'on-demand' or 'only', if a submodule has a -"push.recurseSubmodules={on-demand,only}" or "submodule.recurse" configuration, -further recursion will occur. In this case, "only" is treated as "on-demand". - ---verify:: ---no-verify:: + pushed. If `on-demand` was not able to push all necessary revisions it will + also be aborted and exit with non-zero status. +`only`;; + all submodules will be pushed while the superproject is left + unpushed. +`no`;; + override the `push.recurseSubmodules` configuration variable when no + submodule recursion is required. Similar to using `--no-recurse-submodules`. + ++ +When using `on-demand` or `only`, if a submodule has a +`push.recurseSubmodules=(on-demand|only)` or `submodule.recurse` configuration, +further recursion will occur. In this case, `only` is treated as `on-demand`. + +`--verify`:: +`--no-verify`:: Toggle the pre-push hook (see linkgit:githooks[5]). The - default is --verify, giving the hook a chance to prevent the - push. With --no-verify, the hook is bypassed completely. + default is `--verify`, giving the hook a chance to prevent the + push. With `--no-verify`, the hook is bypassed completely. --4:: ---ipv4:: +`-4`:: +`--ipv4`:: Use IPv4 addresses only, ignoring IPv6 addresses. --6:: ---ipv6:: +`-6`:: +`--ipv6`:: Use IPv6 addresses only, ignoring IPv4 addresses. include::urls-remotes.adoc[] @@ -427,16 +444,16 @@ representing the status of a single ref. Each line is of the form: <flag> <summary> <from> -> <to> (<reason>) ------------------------------- -If --porcelain is used, then each line of the output is of the form: +If `--porcelain` is used, then each line of the output is of the form: ------------------------------- <flag> \t <from>:<to> \t <summary> (<reason>) ------------------------------- -The status of up-to-date refs is shown only if --porcelain or --verbose +The status of up-to-date refs is shown only if `--porcelain` or `--verbose` option is used. -flag:: +_<flag>_:: A single character indicating the status of the ref: (space);; for a successfully pushed fast-forward; `+`;; for a successful forced update; @@ -445,7 +462,7 @@ flag:: `!`;; for a ref that was rejected or failed to push; and `=`;; for a ref that was up to date and did not need pushing. -summary:: +_<summary>_:: For a successfully pushed ref, the summary shows the old and new values of the ref in a form suitable for using as an argument to `git log` (this is `<old>..<new>` in most cases, and @@ -586,7 +603,7 @@ Updating A with the resulting merge commit will fast-forward and your push will be accepted. Alternatively, you can rebase your change between X and B on top of A, -with "git pull --rebase", and push the result back. The rebase will +with `git pull --rebase`, and push the result back. The rebase will create a new commit D that builds the change between X and B on top of A. @@ -604,12 +621,12 @@ accepted. There is another common situation where you may encounter non-fast-forward rejection when you try to push, and it is possible even when you are pushing into a repository nobody else pushes into. After you push commit -A yourself (in the first picture in this section), replace it with "git -commit --amend" to produce commit B, and you try to push it out, because +A yourself (in the first picture in this section), replace it with `git +commit --amend` to produce commit B, and you try to push it out, because forgot that you have pushed A out already. In such a case, and only if you are certain that nobody in the meantime fetched your earlier commit A -(and started building on top of it), you can run "git push --force" to -overwrite it. In other words, "git push --force" is a method reserved for +(and started building on top of it), you can run `git push --force` to +overwrite it. In other words, `git push --force` is a method reserved for a case where you do mean to lose history. @@ -627,18 +644,18 @@ EXAMPLES variable) if it has the same name as the current branch, and errors out without pushing otherwise. + -The default behavior of this command when no <refspec> is given can be +The default behavior of this command when no _<refspec>_ is given can be configured by setting the `push` option of the remote, or the `push.default` configuration variable. + For example, to default to pushing only the current branch to `origin` -use `git config remote.origin.push HEAD`. Any valid <refspec> (like +use `git config remote.origin.push HEAD`. Any valid _<refspec>_ (like the ones in the examples below) can be configured as the default for `git push origin`. `git push origin :`:: Push "matching" branches to `origin`. See - <refspec> in the <<OPTIONS,OPTIONS>> section above for a + _<refspec>_ in the <<OPTIONS,OPTIONS>> section above for a description of "matching" branches. `git push origin master`:: diff --git a/Documentation/git-rebase.adoc b/Documentation/git-rebase.adoc index 005caf6164..9742833ebe 100644 --- a/Documentation/git-rebase.adoc +++ b/Documentation/git-rebase.adoc @@ -474,6 +474,13 @@ See also INCOMPATIBLE OPTIONS below. Instead of using the current time as the committer date, use the author date of the commit being rebased as the committer date. This option implies `--force-rebase`. ++ +WARNING: The history walking machinery assumes that commits have +non-decreasing commit timestamps. You should consider if you really need +to use this option. Then you should only use this option to override the +committer date when rebasing commits on top of a base which commit is +older (in terms of the commit date) than the oldest commit you are +applying (in terms of the author date). --ignore-date:: --reset-author-date:: diff --git a/Documentation/git-replay.adoc b/Documentation/git-replay.adoc index 0b12bf8aa4..d03235cca0 100644 --- a/Documentation/git-replay.adoc +++ b/Documentation/git-replay.adoc @@ -9,15 +9,16 @@ git-replay - EXPERIMENTAL: Replay commits on a new base, works with bare repos t SYNOPSIS -------- [verse] -(EXPERIMENTAL!) 'git replay' ([--contained] --onto <newbase> | --advance <branch>) <revision-range>... +(EXPERIMENTAL!) 'git replay' ([--contained] --onto <newbase> | --advance <branch>) [--ref-action[=<mode>]] <revision-range> DESCRIPTION ----------- -Takes ranges of commits and replays them onto a new location. Leaves -the working tree and the index untouched, and updates no references. -The output of this command is meant to be used as input to -`git update-ref --stdin`, which would update the relevant branches +Takes a range of commits and replays them onto a new location. Leaves +the working tree and the index untouched. By default, updates the +relevant references using an atomic transaction (all refs update or +none). Use `--ref-action=print` to avoid automatic ref updates and +instead get update commands that can be piped to `git update-ref --stdin` (see the OUTPUT section below). THIS COMMAND IS EXPERIMENTAL. THE BEHAVIOR MAY CHANGE. @@ -29,33 +30,46 @@ OPTIONS Starting point at which to create the new commits. May be any valid commit, and not just an existing branch name. + -When `--onto` is specified, the update-ref command(s) in the output will -update the branch(es) in the revision range to point at the new -commits, similar to the way how `git rebase --update-refs` updates -multiple branches in the affected range. +When `--onto` is specified, the branch(es) in the revision range will be +updated to point at the new commits, similar to the way `git rebase --update-refs` +updates multiple branches in the affected range. --advance <branch>:: Starting point at which to create the new commits; must be a branch name. + -When `--advance` is specified, the update-ref command(s) in the output -will update the branch passed as an argument to `--advance` to point at -the new commits (in other words, this mimics a cherry-pick operation). +The history is replayed on top of the <branch> and <branch> is updated to +point at the tip of the resulting history. This is different from `--onto`, +which uses the target only as a starting point without updating it. + +--ref-action[=<mode>]:: + Control how references are updated. The mode can be: ++ +-- + * `update` (default): Update refs directly using an atomic transaction. + All refs are updated or none are (all-or-nothing behavior). + * `print`: Output update-ref commands for pipeline use. This is the + traditional behavior where output can be piped to `git update-ref --stdin`. +-- ++ +The default mode can be configured via the `replay.refAction` configuration variable. <revision-range>:: - Range of commits to replay. More than one <revision-range> can - be passed, but in `--advance <branch>` mode, they should have - a single tip, so that it's clear where <branch> should point - to. See "Specifying Ranges" in linkgit:git-rev-parse[1] and the - "Commit Limiting" options below. + Range of commits to replay; see "Specifying Ranges" in + linkgit:git-rev-parse[1]. In `--advance <branch>` mode, the + range should have a single tip, so that it's clear to which tip the + advanced <branch> should point. include::rev-list-options.adoc[] OUTPUT ------ -When there are no conflicts, the output of this command is usable as -input to `git update-ref --stdin`. It is of the form: +By default, or with `--ref-action=update`, this command produces no output on +success, as refs are updated directly using an atomic transaction. + +When using `--ref-action=print`, the output is usable as input to +`git update-ref --stdin`. It is of the form: update refs/heads/branch1 ${NEW_branch1_HASH} ${OLD_branch1_HASH} update refs/heads/branch2 ${NEW_branch2_HASH} ${OLD_branch2_HASH} @@ -81,6 +95,14 @@ To simply rebase `mybranch` onto `target`: ------------ $ git replay --onto target origin/main..mybranch +------------ + +The refs are updated atomically and no output is produced on success. + +To see what would be updated without actually updating: + +------------ +$ git replay --ref-action=print --onto target origin/main..mybranch update refs/heads/mybranch ${NEW_mybranch_HASH} ${OLD_mybranch_HASH} ------------ @@ -88,33 +110,29 @@ To cherry-pick the commits from mybranch onto target: ------------ $ git replay --advance target origin/main..mybranch -update refs/heads/target ${NEW_target_HASH} ${OLD_target_HASH} ------------ Note that the first two examples replay the exact same commits and on top of the exact same new base, they only differ in that the first -provides instructions to make mybranch point at the new commits and -the second provides instructions to make target point at them. +updates mybranch to point at the new commits and the second updates +target to point at them. What if you have a stack of branches, one depending upon another, and you'd really like to rebase the whole set? ------------ $ git replay --contained --onto origin/main origin/main..tipbranch -update refs/heads/branch1 ${NEW_branch1_HASH} ${OLD_branch1_HASH} -update refs/heads/branch2 ${NEW_branch2_HASH} ${OLD_branch2_HASH} -update refs/heads/tipbranch ${NEW_tipbranch_HASH} ${OLD_tipbranch_HASH} ------------ +All three branches (`branch1`, `branch2`, and `tipbranch`) are updated +atomically. + When calling `git replay`, one does not need to specify a range of commits to replay using the syntax `A..B`; any range expression will do: ------------ $ git replay --onto origin/main ^base branch1 branch2 branch3 -update refs/heads/branch1 ${NEW_branch1_HASH} ${OLD_branch1_HASH} -update refs/heads/branch2 ${NEW_branch2_HASH} ${OLD_branch2_HASH} -update refs/heads/branch3 ${NEW_branch3_HASH} ${OLD_branch3_HASH} ------------ This will simultaneously rebase `branch1`, `branch2`, and `branch3`, diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc index ce43cb19c8..c4a78277df 100644 --- a/Documentation/git-repo.adoc +++ b/Documentation/git-repo.adoc @@ -8,8 +8,8 @@ git-repo - Retrieve information about the repository SYNOPSIS -------- [synopsis] -git repo info [--format=(keyvalue|nul)] [-z] [<key>...] -git repo structure [--format=(table|keyvalue|nul)] +git repo info [--format=(keyvalue|nul) | -z] [--all | <key>...] +git repo structure [--format=(table|keyvalue|nul) | -z] DESCRIPTION ----------- @@ -19,13 +19,13 @@ THIS COMMAND IS EXPERIMENTAL. THE BEHAVIOR MAY CHANGE. COMMANDS -------- -`info [--format=(keyvalue|nul)] [-z] [<key>...]`:: +`info [--format=(keyvalue|nul) | -z] [--all | <key>...]`:: Retrieve metadata-related information about the current repository. Only the requested data will be returned based on their keys (see "INFO KEYS" section below). + The values are returned in the same order in which their respective keys were -requested. +requested. The `--all` flag requests the values for all the available keys. + The output format can be chosen through the flag `--format`. Two formats are supported: @@ -44,13 +44,12 @@ supported: + `-z` is an alias for `--format=nul`. -`structure [--format=(table|keyvalue|nul)]`:: +`structure [--format=(table|keyvalue|nul) | -z]`:: Retrieve statistics about the current repository structure. The following kinds of information are reported: + * Reference counts categorized by type * Reachable object counts categorized by type - + The output format can be chosen through the flag `--format`. Three formats are supported: @@ -72,6 +71,8 @@ supported: the delimiter between the key and value instead of '='. Unlike the `keyvalue` format, values containing "unusual" characters are never quoted. ++ +`-z` is an alias for `--format=nul`. INFO KEYS --------- diff --git a/Documentation/gitdatamodel.adoc b/Documentation/gitdatamodel.adoc new file mode 100644 index 0000000000..dcfdff0346 --- /dev/null +++ b/Documentation/gitdatamodel.adoc @@ -0,0 +1,305 @@ +gitdatamodel(7) +=============== + +NAME +---- +gitdatamodel - Git's core data model + +SYNOPSIS +-------- +gitdatamodel + +DESCRIPTION +----------- + +It's not necessary to understand Git's data model to use Git, but it's +very helpful when reading Git's documentation so that you know what it +means when the documentation says "object", "reference" or "index". + +Git's core operations use 4 kinds of data: + +1. <<objects,Objects>>: commits, trees, blobs, and tag objects +2. <<references,References>>: branches, tags, + remote-tracking branches, etc +3. <<index,The index>>, also known as the staging area +4. <<reflogs,Reflogs>>: logs of changes to references ("ref log") + +[[objects]] +OBJECTS +------- + +All of the commits and files in a Git repository are stored as "Git objects". +Git objects never change after they're created, and every object has an ID, +like `1b61de420a21a2f1aaef93e38ecd0e45e8bc9f0a`. + +This means that if you have an object's ID, you can always recover its +exact contents as long as the object hasn't been deleted. + +Every object has: + +[[object-id]] +1. an *ID* (aka "object name"), which is a cryptographic hash of its + type and contents. + It's fast to look up a Git object using its ID. + This is usually represented in hexadecimal, like + `1b61de420a21a2f1aaef93e38ecd0e45e8bc9f0a`. +2. a *type*. There are 4 types of objects: + <<commit,commits>>, <<tree,trees>>, <<blob,blobs>>, + and <<tag-object,tag objects>>. +3. *contents*. The structure of the contents depends on the type. + +Here's how each type of object is structured: + +[[commit]] +commit:: + A commit contains these required fields + (though there are other optional fields): ++ +1. The full directory structure of all the files in that version of the + repository and each file's contents, stored as the *<<tree,tree>>* ID + of the commit's top-level directory +2. Its *parent commit ID(s)*. The first commit in a repository has 0 parents, + regular commits have 1 parent, merge commits have 2 or more parents +3. An *author* and the time the commit was authored +4. A *committer* and the time the commit was committed +5. A *commit message* ++ +Here's how an example commit is stored: ++ +---- +tree 1b61de420a21a2f1aaef93e38ecd0e45e8bc9f0a +parent 4ccb6d7b8869a86aae2e84c56523f8705b50c647 +author Maya <maya@example.com> 1759173425 -0400 +committer Maya <maya@example.com> 1759173425 -0400 + +Add README +---- ++ +Like all other objects, commits can never be changed after they're created. +For example, "amending" a commit with `git commit --amend` creates a new +commit with the same parent. ++ +Git does not store the diff for a commit: when you ask Git to show +the commit with linkgit:git-show[1], it calculates the diff from its +parent on the fly. + +[[tree]] +tree:: + A tree is how Git represents a directory. + It can contain files or other trees (which are subdirectories). + It lists, for each item in the tree: ++ +1. The *filename*, for example `hello.py` +2. The *file type*, which must be one of these five types: + - *regular file* + - *executable file* + - *symbolic link* + - *directory* + - *gitlink* (for use with submodules) +3. The <<object-id,*object ID*>> with the contents of the file, directory, + or gitlink. ++ +For example, this is how a tree containing one directory (`src`) and one file +(`README.md`) is stored: ++ +---- +100644 blob 8728a858d9d21a8c78488c8b4e70e531b659141f README.md +040000 tree 89b1d2e0495f66d6929f4ff76ff1bb07fc41947d src +---- + +NOTE: In the output above, Git displays the file type of each tree entry +using a format that's loosely modelled on Unix file modes (`100644` is +"regular file", `100755` is "executable file", `120000` is "symbolic +link", `040000` is "directory", and `160000` is "gitlink"). It also +displays the object's type: `blob` for files and symlinks, `tree` for +directories, and `commit` for gitlinks. + +[[blob]] +blob:: + A blob object contains a file's contents. ++ +When you make a commit, Git stores the full contents of each file that +you changed as a blob. +For example, if you have a commit that changes 2 files in a repository +with 1000 files, that commit will create 2 new blobs, and use the +previous blob ID for the other 998 files. +This means that commits can use relatively little disk space even in a +very large repository. + +[[tag-object]] +tag object:: + Tag objects contain these required fields + (though there are other optional fields): ++ +1. The *ID* of the object it references +2. The *type* of the object it references +3. The *tagger* and tag date +4. A *tag message*, similar to a commit message + +Here's how an example tag object is stored: + +---- +object 750b4ead9c87ceb3ddb7a390e6c7074521797fb3 +type commit +tag v1.0.0 +tagger Maya <maya@example.com> 1759927359 -0400 + +Release version 1.0.0 +---- + +NOTE: All of the examples in this section were generated with +`git cat-file -p <object-id>`. + +[[references]] +REFERENCES +---------- + +References are a way to give a name to a commit. +It's easier to remember "the changes I'm working on are on the `turtle` +branch" than "the changes are in commit bb69721404348e". +Git often uses "ref" as shorthand for "reference". + +References can either refer to: + +1. An object ID, usually a <<commit,commit>> ID +2. Another reference. This is called a "symbolic reference" + +References are stored in a hierarchy, and Git handles references +differently based on where they are in the hierarchy. +Most references are under `refs/`. Here are the main types: + +[[branch]] +branches: `refs/heads/<name>`:: + A branch refers to a commit ID. + That commit is the latest commit on the branch. ++ +To get the history of commits on a branch, Git will start at the commit +ID the branch references, and then look at the commit's parent(s), +the parent's parent, etc. + +[[tag]] +tags: `refs/tags/<name>`:: + A tag refers to a commit ID, tag object ID, or other object ID. + There are two types of tags: + 1. "Annotated tags", which reference a <<tag-object,tag object>> ID + which contains a tag message + 2. "Lightweight tags", which reference a commit, blob, or tree ID + directly ++ +Even though branches and tags both refer to a commit ID, Git +treats them very differently. +Branches are expected to change over time: when you make a commit, Git +will update your <<HEAD,current branch>> to point to the new commit. +Tags are usually not changed after they're created. + +[[HEAD]] +HEAD: `HEAD`:: + `HEAD` is where Git stores your current <<branch,branch>>, + if there is a current branch. `HEAD` can either be: ++ +1. A symbolic reference to your current branch, for example `ref: + refs/heads/main` if your current branch is `main`. +2. A direct reference to a commit ID. In this case there is no current branch. + This is called "detached HEAD state", see the DETACHED HEAD section + of linkgit:git-checkout[1] for more. + +[[remote-tracking-branch]] +remote-tracking branches: `refs/remotes/<remote>/<branch>`:: + A remote-tracking branch refers to a commit ID. + It's how Git stores the last-known state of a branch in a remote + repository. `git fetch` updates remote-tracking branches. When + `git status` says "you're up to date with origin/main", it's looking at + this. ++ +`refs/remotes/<remote>/HEAD` is a symbolic reference to the remote's +default branch. This is the branch that `git clone` checks out by default. + +[[other-refs]] +Other references:: + Git tools may create references anywhere under `refs/`. + For example, linkgit:git-stash[1], linkgit:git-bisect[1], + and linkgit:git-notes[1] all create their own references + in `refs/stash`, `refs/bisect`, etc. + Third-party Git tools may also create their own references. ++ +Git may also create references other than `HEAD` at the base of the +hierarchy, like `ORIG_HEAD`. + +NOTE: Git may delete objects that aren't "reachable" from any reference +or <<reflogs,reflog>>. +An object is "reachable" if we can find it by following tags to whatever +they tag, commits to their parents or trees, and trees to the trees or +blobs that they contain. +For example, if you amend a commit with `git commit --amend`, +there will no longer be a branch that points at the old commit. +The old commit is recorded in the current branch's <<reflogs,reflog>>, +so it is still "reachable", but when the reflog entry expires it may +become unreachable and get deleted. +Reachable objects will never be deleted. + +[[index]] +THE INDEX +--------- +The index, also known as the "staging area", is a list of files and +the contents of each file, stored as a <<blob,blob>>. +You can add files to the index or update the contents of a file in the +index with linkgit:git-add[1]. This is called "staging" the file for commit. + +Unlike a <<tree,tree>>, the index is a flat list of files. +When you commit, Git converts the list of files in the index to a +directory <<tree,tree>> and uses that tree in the new <<commit,commit>>. + +Each index entry has 4 fields: + +1. The *file type*, which must be one of: + - *regular file* + - *executable file* + - *symbolic link* + - *gitlink* (for use with submodules) +2. The *<<blob,blob>>* ID of the file, + or (rarely) the *<<commit,commit>>* ID of the submodule +3. The *stage number*, either 0, 1, 2, or 3. This is normally 0, but if + there's a merge conflict there can be multiple versions of the same + filename in the index. +4. The *file path*, for example `src/hello.py` + +It's extremely uncommon to look at the index directly: normally you'd +run `git status` to see a list of changes between the index and <<HEAD,HEAD>>. +But you can use `git ls-files --stage` to see the index. +Here's the output of `git ls-files --stage` in a repository with 2 files: + +---- +100644 8728a858d9d21a8c78488c8b4e70e531b659141f 0 README.md +100644 665c637a360874ce43bf74018768a96d2d4d219a 0 src/hello.py +---- + +[[reflogs]] +REFLOGS +------- + +Every time a branch, remote-tracking branch, or HEAD is updated, Git +updates a log called a "reflog" for that <<references,reference>>. +This means that if you make a mistake and "lose" a commit, you can +generally recover the commit ID by running `git reflog <reference>`. + +A reflog is a list of log entries. Each entry has: + +1. The *commit ID* +2. *Timestamp* when the change was made +3. *Log message*, for example `pull: Fast-forward` + +Reflogs only log changes made in your local repository. +They are not shared with remotes. + +You can view a reflog with `git reflog <reference>`. +For example, here's the reflog for a `main` branch which has changed twice: + +---- +$ git reflog main --date=iso --no-decorate +750b4ea main@{2025-09-29 15:17:05 -0400}: commit: Add README +4ccb6d7 main@{2025-09-29 15:16:48 -0400}: commit (initial): Initial commit +---- + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/Documentation/githooks.adoc b/Documentation/githooks.adoc index 0397dec64d..056553788d 100644 --- a/Documentation/githooks.adoc +++ b/Documentation/githooks.adoc @@ -103,17 +103,14 @@ invoked before obtaining the proposed commit log message and making a commit. Exiting with a non-zero status from this script causes the `git commit` command to abort before creating a commit. -The default 'pre-commit' hook, when enabled, catches introduction -of lines with trailing whitespaces and aborts the commit when -such a line is found. - All the `git commit` hooks are invoked with the environment variable `GIT_EDITOR=:` if the command will not bring up an editor to modify the commit message. -The default 'pre-commit' hook, when enabled--and with the -`hooks.allownonascii` config option unset or set to false--prevents -the use of non-ASCII filenames. +The default 'pre-commit' hook, when enabled, prevents the introduction +of non-ASCII filenames and lines with trailing whitespace. The non-ASCII +check can be turned off by setting the `hooks.allownonascii` config +option to `true`. pre-merge-commit ~~~~~~~~~~~~~~~~ diff --git a/Documentation/gitprotocol-http.adoc b/Documentation/gitprotocol-http.adoc index d024010414..e2ef7f0459 100644 --- a/Documentation/gitprotocol-http.adoc +++ b/Documentation/gitprotocol-http.adoc @@ -443,7 +443,8 @@ If no "want" objects are received, send an error: TODO: Define error if no "want" lines are requested. If any "want" object is not reachable, send an error: -TODO: Define error if an invalid "want" is requested. +When a Git server receives an invalid or malformed `want` line, it +responds with an error message that includes the offending object name. Create an empty list, `s_common`. diff --git a/Documentation/glossary-content.adoc b/Documentation/glossary-content.adoc index e423e4765b..20ba121314 100644 --- a/Documentation/glossary-content.adoc +++ b/Documentation/glossary-content.adoc @@ -297,8 +297,8 @@ This commit is referred to as a "merge commit", or sometimes just a identified by its <<def_object_name,object name>>. The objects usually live in `$GIT_DIR/objects/`. -[[def_object_identifier]]object identifier (oid):: - Synonym for <<def_object_name,object name>>. +[[def_object_identifier]]object identifier, object ID, oid:: + Synonyms for <<def_object_name,object name>>. [[def_object_name]]object name:: The unique identifier of an <<def_object,object>>. The diff --git a/Documentation/merge-options.adoc b/Documentation/merge-options.adoc index 9d433265b2..952cb85e9a 100644 --- a/Documentation/merge-options.adoc +++ b/Documentation/merge-options.adoc @@ -56,7 +56,7 @@ ifdef::git-pull[] `--ff-only`:: Only update to the new history if there is no divergent local history. This is the default when no method for reconciling - divergent histories is provided (via the --rebase=* flags). + divergent histories is provided (via the `--rebase` flags). `--ff`:: `--no-ff`:: diff --git a/Documentation/meson.build b/Documentation/meson.build index c00c9fe7f4..f02dbc20cb 100644 --- a/Documentation/meson.build +++ b/Documentation/meson.build @@ -193,6 +193,7 @@ manpages = { 'gitcore-tutorial.adoc' : 7, 'gitcredentials.adoc' : 7, 'gitcvs-migration.adoc' : 7, + 'gitdatamodel.adoc' : 7, 'gitdiffcore.adoc' : 7, 'giteveryday.adoc' : 7, 'gitfaq.adoc' : 7, diff --git a/Documentation/pull-fetch-param.adoc b/Documentation/pull-fetch-param.adoc index bb2cf6a462..d903dc8900 100644 --- a/Documentation/pull-fetch-param.adoc +++ b/Documentation/pull-fetch-param.adoc @@ -1,20 +1,20 @@ -<repository>:: +_<repository>_:: The "remote" repository that is the source of a fetch or pull operation. This parameter can be either a URL (see the section <<URLS,GIT URLS>> below) or the name of a remote (see the section <<REMOTES,REMOTES>> below). ifndef::git-pull[] -<group>:: +_<group>_:: A name referring to a list of repositories as the value - of remotes.<group> in the configuration file. + of `remotes.<group>` in the configuration file. (See linkgit:git-config[1]). endif::git-pull[] [[fetch-refspec]] -<refspec>:: +_<refspec>_:: Specifies which refs to fetch and which local refs to update. - When no <refspec>s appear on the command line, the refs to fetch + When no __<refspec>__s appear on the command line, the refs to fetch are read from `remote.<repository>.fetch` variables instead ifndef::git-pull[] (see <<CRTB,CONFIGURED REMOTE-TRACKING BRANCHES>> below). @@ -24,18 +24,18 @@ ifdef::git-pull[] in linkgit:git-fetch[1]). endif::git-pull[] + -The format of a <refspec> parameter is an optional plus -`+`, followed by the source <src>, followed -by a colon `:`, followed by the destination <dst>. -The colon can be omitted when <dst> is empty. <src> is +The format of a _<refspec>_ parameter is an optional plus +`+`, followed by the source _<src>_, followed +by a colon `:`, followed by the destination _<dst>_. +The colon can be omitted when _<dst>_ is empty. _<src>_ is typically a ref, or a glob pattern with a single `*` that is used to match a set of refs, but it can also be a fully spelled hex object name. + -A <refspec> may contain a `*` in its <src> to indicate a simple pattern +A _<refspec>_ may contain a `*` in its _<src>_ to indicate a simple pattern match. Such a refspec functions like a glob that matches any ref with the -pattern. A pattern <refspec> must have one and only one `*` in both the <src> and -<dst>. It will map refs to the destination by replacing the `*` with the +pattern. A pattern _<refspec>_ must have one and only one `*` in both the _<src>_ and +_<dst>_. It will map refs to the destination by replacing the `*` with the contents matched from the source. + If a refspec is prefixed by `^`, it will be interpreted as a negative @@ -45,14 +45,14 @@ considered to match if it matches at least one positive refspec, and does not match any negative refspec. Negative refspecs can be useful to restrict the scope of a pattern refspec so that it will not include specific refs. Negative refspecs can themselves be pattern refspecs. However, they may only -contain a <src> and do not specify a <dst>. Fully spelled out hex object +contain a _<src>_ and do not specify a _<dst>_. Fully spelled out hex object names are also not supported. + `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`; it requests fetching everything up to the given tag. + -The remote ref that matches <src> -is fetched, and if <dst> is not an empty string, an attempt +The remote ref that matches _<src>_ +is fetched, and if _<dst>_ is not an empty string, an attempt is made to update the local ref that matches it. + Whether that update is allowed without `--force` depends on the ref @@ -60,7 +60,7 @@ namespace it's being fetched to, the type of object being fetched, and whether the update is considered to be a fast-forward. Generally, the same rules apply for fetching as when pushing, see the `<refspec>...` section of linkgit:git-push[1] for what those are. Exceptions to those -rules particular to 'git fetch' are noted below. +rules particular to `git fetch` are noted below. + Until Git version 2.20, and unlike when pushing with linkgit:git-push[1], any updates to `refs/tags/*` would be accepted @@ -101,19 +101,19 @@ must know this is the expected usage pattern for a branch. ifdef::git-pull[] + [NOTE] -There is a difference between listing multiple <refspec> -directly on 'git pull' command line and having multiple +There is a difference between listing multiple _<refspec>_ +directly on `git pull` command line and having multiple `remote.<repository>.fetch` entries in your configuration -for a <repository> and running a -'git pull' command without any explicit <refspec> parameters. -<refspec>s listed explicitly on the command line are always +for a _<repository>_ and running a +`git pull` command without any explicit _<refspec>_ parameters. +__<refspec>__s listed explicitly on the command line are always merged into the current branch after fetching. In other words, -if you list more than one remote ref, 'git pull' will create +if you list more than one remote ref, `git pull` will create an Octopus merge. On the other hand, if you do not list any -explicit <refspec> parameter on the command line, 'git pull' -will fetch all the <refspec>s it finds in the +explicit _<refspec>_ parameter on the command line, `git pull` +will fetch all the __<refspec>__s it finds in the `remote.<repository>.fetch` configuration and merge -only the first <refspec> found into the current branch. +only the first _<refspec>_ found into the current branch. This is because making an Octopus from remote refs is rarely done, while keeping track of multiple remote heads in one-go by fetching more than one diff --git a/Documentation/technical/meson.build b/Documentation/technical/meson.build index faff3964a9..ec07088c57 100644 --- a/Documentation/technical/meson.build +++ b/Documentation/technical/meson.build @@ -32,6 +32,7 @@ articles = [ 'sparse-checkout.adoc', 'sparse-index.adoc', 'trivial-merge.adoc', + 'unambiguous-types.adoc', 'unit-tests.adoc', ] diff --git a/Documentation/technical/unambiguous-types.adoc b/Documentation/technical/unambiguous-types.adoc new file mode 100644 index 0000000000..9a4990847c --- /dev/null +++ b/Documentation/technical/unambiguous-types.adoc @@ -0,0 +1,224 @@ += Unambiguous types + +Most of these mappings are obvious, but there are some nuances and gotchas with +Rust FFI (Foreign Function Interface). + +This document defines clear, one-to-one mappings between primitive types in C, +Rust (and possible other languages in the future). Its purpose is to eliminate +ambiguity in type widths, signedness, and binary representation across +platforms and languages. + +For Git, the only header required to use these unambiguous types in C is +`git-compat-util.h`. + +== Boolean types +[cols="1,1", options="header"] +|=== +| C Type | Rust Type +| bool^1^ | bool +|=== + +== Integer types + +In C, `<stdint.h>` (or an equivalent) must be included. + +[cols="1,1", options="header"] +|=== +| C Type | Rust Type +| uint8_t | u8 +| uint16_t | u16 +| uint32_t | u32 +| uint64_t | u64 + +| int8_t | i8 +| int16_t | i16 +| int32_t | i32 +| int64_t | i64 +|=== + +== Floating-point types + +Rust requires IEEE-754 semantics. +In C, that is typically true, but not guaranteed by the standard. + +[cols="1,1", options="header"] +|=== +| C Type | Rust Type +| float^2^ | f32 +| double^2^ | f64 +|=== + +== Size types + +These types represent pointer-sized integers and are typically defined in +`<stddef.h>` or an equivalent header. + +Size types should be used any time pointer arithmetic is performed e.g. +indexing an array, describing the number of elements in memory, etc... + +[cols="1,1", options="header"] +|=== +| C Type | Rust Type +| size_t^3^ | usize +| ptrdiff_t^3^ | isize +|=== + +== Character types + +This is where C and Rust don't have a clean one-to-one mapping. + +A C `char` and a Rust `u8` share the same bit width, so any C struct containing +a `char` will have the same size as the corresponding Rust struct using `u8`. +In that sense, such structs are safe to pass over the FFI boundary, because +their fields will be laid out identically. However, beyond bit width, C `char` +has additional semantics and platform-dependent behavior that can cause +problems, as discussed below. + +The C language leaves the signedness of `char` implementation defined. Because +our developer build enables -Wsign-compare, comparison of a value of `char` +type with either signed or unsigned integers may trigger warnings from the +compiler. + +Note: Rust's `char` type is an unsigned 32-bit integer that is used to describe +Unicode code points. + +=== Notes +^1^ This is only true if stdbool.h (or equivalent) is used. + +^2^ C does not enforce IEEE-754 compatibility, but Rust expects it. If the +platform/arch for C does not follow IEEE-754 then this equivalence does not +hold. Also, it's assumed that `float` is 32 bits and `double` is 64, but +there may be a strange platform/arch where even this isn't true. + +^3^ C also defines uintptr_t, ssize_t and intptr_t, but these types are +discouraged for FFI purposes. For functions like `read()` and `write()` ssize_t +should be cast to a different, and unambiguous, type before being passed over +the FFI boundary. + + +== Problems with std::ffi::c_* types in Rust +TL;DR: In practice, Rust's `c_*` types aren't guaranteed to match C types for +all possible C compilers, platforms, or architectures, because Rust only +ensures correctness of C types on officially supported targets. These +definitions have changed over time to match more targets which means that the +c_* definitions will differ based on which Rust version Git chooses to use. + +Current list of safe, Rust side, FFI types in Git: + + +* `c_void` +* `CStr` +* `CString` + +Even then, they should be used sparingly, and only where the semantics match +exactly. + +The std::os::raw::c_* directly inherits the problems of core::ffi, which +changes over time and seems to make a best guess at the correct definition for +a given platform/target. This probably isn't a problem for all other platforms +that Rust supports currently, but can anyone say that Rust got it right for all +C compilers of all platforms/targets? + +To give an example: c_long is defined in +footnote:[https://doc.rust-lang.org/1.63.0/src/core/ffi/mod.rs.html#175-189[c_long in 1.63.0]] +footnote:[https://doc.rust-lang.org/1.89.0/src/core/ffi/primitives.rs.html#135-151[c_long in 1.89.0]] + +=== Rust version 1.63.0 + +``` +mod c_long_definition { + cfg_if! { + if #[cfg(all(target_pointer_width = "64", not(windows)))] { + pub type c_long = i64; + pub type NonZero_c_long = crate::num::NonZeroI64; + pub type c_ulong = u64; + pub type NonZero_c_ulong = crate::num::NonZeroU64; + } else { + // The minimal size of `long` in the C standard is 32 bits + pub type c_long = i32; + pub type NonZero_c_long = crate::num::NonZeroI32; + pub type c_ulong = u32; + pub type NonZero_c_ulong = crate::num::NonZeroU32; + } + } +} +``` + +=== Rust version 1.89.0 + +``` +mod c_long_definition { + crate::cfg_select! { + any( + all(target_pointer_width = "64", not(windows)), + // wasm32 Linux ABI uses 64-bit long + all(target_arch = "wasm32", target_os = "linux") + ) => { + pub(super) type c_long = i64; + pub(super) type c_ulong = u64; + } + _ => { + // The minimal size of `long` in the C standard is 32 bits + pub(super) type c_long = i32; + pub(super) type c_ulong = u32; + } + } +} +``` + +Even for the cases where C types are correctly mapped to Rust types via +std::ffi::c_* there are still problems. Let's take c_char for example. On some +platforms it's u8 on others it's i8. + +=== Subtraction underflow in debug mode + +The following code will panic in debug on platforms that define c_char as u8, +but won't if it's an i8. + +``` +let mut x: std::ffi::c_char = 0; +x -= 1; +``` + +=== Inconsistent shift behavior + +`x` will be 0xC0 for platforms that use i8, but will be 0x40 where it's u8. + +``` +let mut x: std::ffi::c_char = 0x80; +x >>= 1; +``` + +=== Equality fails to compile on some platforms + +The following will not compile on platforms that define c_char as i8, but will +if it's u8. You can cast x e.g. `assert_eq!(x as u8, b'a');`, but then you get +a warning on platforms that use u8 and a clean compilation where i8 is used. + +``` +let mut x: std::ffi::c_char = 0x61; +assert_eq!(x, b'a'); +``` + +== Enum types +Rust enum types should not be used as FFI types. Rust enum types are more like +C union types than C enum's. For something like: + +``` +#[repr(C, u8)] +enum Fruit { + Apple, + Banana, + Cherry, +} +``` + +It's easy enough to make sure the Rust enum matches what C would expect, but a +more complex type like. + +``` +enum HashResult { + SHA1([u8; 20]), + SHA256([u8; 32]), +} +``` + +The Rust compiler has to add a discriminant to the enum to distinguish between +the variants. The width, location, and values for that discriminant is up to +the Rust compiler and is not ABI stable. diff --git a/Documentation/urls-remotes.adoc b/Documentation/urls-remotes.adoc index 57b1646d3e..6878bbe093 100644 --- a/Documentation/urls-remotes.adoc +++ b/Documentation/urls-remotes.adoc @@ -4,7 +4,7 @@ REMOTES[[REMOTES]] ------------------ The name of one of the following can be used instead -of a URL as `<repository>` argument: +of a URL as _<repository>_ argument: * a remote in the Git configuration file: `$GIT_DIR/config`, * a file in the `$GIT_DIR/remotes` directory, or @@ -32,8 +32,8 @@ config file would appear like this: fetch = <refspec> ------------ -The `<pushurl>` is used for pushes only. It is optional and defaults -to `<URL>`. Pushing to a remote affects all defined pushurls or all +The _<pushurl>_ is used for pushes only. It is optional and defaults +to _<URL>_. Pushing to a remote affects all defined pushurls or all defined urls if no pushurls are defined. Fetch, however, will only fetch from the first defined url if multiple urls are defined. @@ -54,8 +54,8 @@ following format: ------------ -`Push:` lines are used by 'git push' and -`Pull:` lines are used by 'git pull' and 'git fetch'. +`Push:` lines are used by `git push` and +`Pull:` lines are used by `git pull` and `git fetch`. Multiple `Push:` and `Pull:` lines may be specified for additional branch mappings. @@ -72,12 +72,12 @@ This file should have the following format: <URL>#<head> ------------ -`<URL>` is required; `#<head>` is optional. +_<URL>_ is required; `#<head>` is optional. Depending on the operation, git will use one of the following refspecs, if you don't provide one on the command line. -`<branch>` is the name of this file in `$GIT_DIR/branches` and -`<head>` defaults to `master`. +_<branch>_ is the name of this file in `$GIT_DIR/branches` and +_<head>_ defaults to `master`. git fetch uses: @@ -111,7 +111,7 @@ Git defaults to using the upstream branch for remote operations, for example: 'origin/main' have diverged, and have 2 and 3 different commits each respectively". -The upstream is stored in `.git/config`, in the "remote" and "merge" +The upstream is stored in `.git/config`, in the "`remote`" and "`merge`" fields. For example, if `main`'s upstream is `origin/main`: ------------ diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index 8d5bbf7b6d..1f7af0328a 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,6 +1,6 @@ #!/bin/sh -DEF_VER=v2.52.0 +DEF_VER=v2.52.GIT LF=' ' @@ -1201,6 +1201,7 @@ LIB_OBJS += object-file.o LIB_OBJS += object-name.o LIB_OBJS += object.o LIB_OBJS += odb.o +LIB_OBJS += odb/streaming.o LIB_OBJS += oid-array.o LIB_OBJS += oidmap.o LIB_OBJS += oidset.o @@ -1294,7 +1295,6 @@ LIB_OBJS += split-index.o LIB_OBJS += stable-qsort.o LIB_OBJS += statinfo.o LIB_OBJS += strbuf.o -LIB_OBJS += streaming.o LIB_OBJS += string-list.o LIB_OBJS += strmap.o LIB_OBJS += strvec.o @@ -1525,6 +1525,7 @@ CLAR_TEST_SUITES += u-string-list CLAR_TEST_SUITES += u-strvec CLAR_TEST_SUITES += u-trailer CLAR_TEST_SUITES += u-urlmatch-normalization +CLAR_TEST_SUITES += u-utf8-width CLAR_TEST_PROG = $(UNIT_TEST_BIN)/unit-tests$(X) CLAR_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(CLAR_TEST_SUITES)) CLAR_TEST_OBJS += $(UNIT_TEST_DIR)/clar/clar.o @@ -1587,6 +1588,7 @@ SANITIZE_LEAK = YesCompiledWithIt endif ifneq ($(filter address,$(SANITIZERS)),) NO_REGEX = NeededForASAN +NO_MMAP = NeededForASAN SANITIZE_ADDRESS = YesCompiledWithIt endif endif @@ -1917,7 +1919,6 @@ ifdef NO_SETENV endif ifdef NO_MKDTEMP COMPAT_CFLAGS += -DNO_MKDTEMP - COMPAT_OBJS += compat/mkdtemp.o endif ifdef MKDIR_WO_TRAILING_SLASH COMPAT_CFLAGS += -DMKDIR_WO_TRAILING_SLASH @@ -2565,7 +2566,7 @@ please_set_SHELL_PATH_to_a_more_modern_shell: shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell -strip: $(PROGRAMS) git$X +strip: $(PROGRAMS) git$X scalar$X $(STRIP) $(STRIP_OPTS) $^ ### Target-specific flags and dependencies @@ -1 +1 @@ -Documentation/RelNotes/2.52.0.adoc
\ No newline at end of file +Documentation/RelNotes/2.53.0.adoc
\ No newline at end of file @@ -1640,6 +1640,14 @@ static void record_ws_error(struct apply_state *state, state->squelch_whitespace_errors < state->whitespace_error) return; + /* + * line[len] for an incomplete line points at the "\n" at the end + * of patch input line, so "%.*s" would drop the last letter on line; + * compensate for it. + */ + if (result & WS_INCOMPLETE_LINE) + len++; + err = whitespace_error_string(result); if (state->apply_verbosity > verbosity_silent) fprintf(stderr, "%s:%d: %s.\n%.*s\n", @@ -1671,6 +1679,35 @@ static void check_old_for_crlf(struct patch *patch, const char *line, int len) /* + * Just saw a single line in a fragment. If it is a part of this hunk + * that is a context " ", an added "+", or a removed "-" line, it may + * be followed by "\\ No newline..." to signal that the last "\n" on + * this line needs to be dropped. Depending on locale settings when + * the patch was produced we don't know what this line would exactly + * say. The only thing we do know is that it begins with "\ ". + * Checking for 12 is just for sanity check; "\ No newline..." would + * be at least that long in any l10n. + * + * Return 0 if the line we saw is not followed by "\ No newline...", + * or length of that line. The caller will use it to skip over the + * "\ No newline..." line. + */ +static int adjust_incomplete(const char *line, int len, + unsigned long size) +{ + int nextlen; + + if (*line != '\n' && *line != ' ' && *line != '+' && *line != '-') + return 0; + if (size - len < 12 || memcmp(line + len, "\\ ", 2)) + return 0; + nextlen = linelen(line + len, size - len); + if (nextlen < 12) + return 0; + return nextlen; +} + +/* * Parse a unified diff. Note that this really needs to parse each * fragment separately, since the only way to know the difference * between a "---" that is part of a patch, and a "---" that starts @@ -1684,6 +1721,7 @@ static int parse_fragment(struct apply_state *state, { int added, deleted; int len = linelen(line, size), offset; + int skip_len = 0; unsigned long oldlines, newlines; unsigned long leading, trailing; @@ -1710,6 +1748,22 @@ static int parse_fragment(struct apply_state *state, len = linelen(line, size); if (!len || line[len-1] != '\n') return -1; + + /* + * For an incomplete line, skip_len counts the bytes + * on "\\ No newline..." marker line that comes next + * to the current line. + * + * Reduce "len" to drop the newline at the end of + * line[], but add one to "skip_len", which will be + * added back to "len" for the next iteration, to + * compensate. + */ + skip_len = adjust_incomplete(line, len, size); + if (skip_len) { + len--; + skip_len++; + } switch (*line) { default: return -1; @@ -1745,19 +1799,12 @@ static int parse_fragment(struct apply_state *state, newlines--; trailing = 0; break; + } - /* - * We allow "\ No newline at end of file". Depending - * on locale settings when the patch was produced we - * don't know what this line looks like. The only - * thing we do know is that it begins with "\ ". - * Checking for 12 is just for sanity check -- any - * l10n of "\ No newline..." is at least that long. - */ - case '\\': - if (len < 12 || memcmp(line, "\\ ", 2)) - return -1; - break; + /* eat the "\\ No newline..." as well, if exists */ + if (skip_len) { + len += skip_len; + state->linenr++; } } if (oldlines || newlines) @@ -1768,14 +1815,6 @@ static int parse_fragment(struct apply_state *state, fragment->leading = leading; fragment->trailing = trailing; - /* - * If a fragment ends with an incomplete line, we failed to include - * it in the above loop because we hit oldlines == newlines == 0 - * before seeing it. - */ - if (12 < size && !memcmp(line, "\\ ", 2)) - offset += linelen(line, size); - patch->lines_added += added; patch->lines_deleted += deleted; diff --git a/archive-tar.c b/archive-tar.c index 73b63ddc41..0fc70d13a8 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -12,8 +12,8 @@ #include "tar.h" #include "archive.h" #include "odb.h" +#include "odb/streaming.h" #include "strbuf.h" -#include "streaming.h" #include "run-command.h" #include "write-or-die.h" @@ -129,22 +129,20 @@ static void write_trailer(void) */ static int stream_blocked(struct repository *r, const struct object_id *oid) { - struct git_istream *st; - enum object_type type; - unsigned long sz; + struct odb_read_stream *st; char buf[BLOCKSIZE]; ssize_t readlen; - st = open_istream(r, oid, &type, &sz, NULL); + st = odb_read_stream_open(r->objects, oid, NULL); if (!st) return error(_("cannot stream blob %s"), oid_to_hex(oid)); for (;;) { - readlen = read_istream(st, buf, sizeof(buf)); + readlen = odb_read_stream_read(st, buf, sizeof(buf)); if (readlen <= 0) break; do_write_blocked(buf, readlen); } - close_istream(st); + odb_read_stream_close(st); if (!readlen) finish_record(); return readlen; diff --git a/archive-zip.c b/archive-zip.c index bea5bdd43d..97ea8d60d6 100644 --- a/archive-zip.c +++ b/archive-zip.c @@ -10,9 +10,9 @@ #include "gettext.h" #include "git-zlib.h" #include "hex.h" -#include "streaming.h" #include "utf8.h" #include "odb.h" +#include "odb/streaming.h" #include "strbuf.h" #include "userdiff.h" #include "write-or-die.h" @@ -309,7 +309,7 @@ static int write_zip_entry(struct archiver_args *args, enum zip_method method; unsigned char *out; void *deflated = NULL; - struct git_istream *stream = NULL; + struct odb_read_stream *stream = NULL; unsigned long flags = 0; int is_binary = -1; const char *path_without_prefix = path + args->baselen; @@ -347,12 +347,11 @@ static int write_zip_entry(struct archiver_args *args, method = ZIP_METHOD_DEFLATE; if (!buffer) { - enum object_type type; - stream = open_istream(args->repo, oid, &type, &size, - NULL); + stream = odb_read_stream_open(args->repo->objects, oid, NULL); if (!stream) return error(_("cannot stream blob %s"), oid_to_hex(oid)); + size = stream->size; flags |= ZIP_STREAM; out = NULL; } else { @@ -429,7 +428,7 @@ static int write_zip_entry(struct archiver_args *args, ssize_t readlen; for (;;) { - readlen = read_istream(stream, buf, sizeof(buf)); + readlen = odb_read_stream_read(stream, buf, sizeof(buf)); if (readlen <= 0) break; crc = crc32(crc, buf, readlen); @@ -439,7 +438,7 @@ static int write_zip_entry(struct archiver_args *args, buf, readlen); write_or_die(1, buf, readlen); } - close_istream(stream); + odb_read_stream_close(stream); if (readlen) return readlen; @@ -462,7 +461,7 @@ static int write_zip_entry(struct archiver_args *args, zstream.avail_out = sizeof(compressed); for (;;) { - readlen = read_istream(stream, buf, sizeof(buf)); + readlen = odb_read_stream_read(stream, buf, sizeof(buf)); if (readlen <= 0) break; crc = crc32(crc, buf, readlen); @@ -486,7 +485,7 @@ static int write_zip_entry(struct archiver_args *args, } } - close_istream(stream); + odb_read_stream_close(stream); if (readlen) return readlen; @@ -1064,24 +1064,52 @@ static int path_matches(const char *pathname, int pathlen, pattern, prefix, pat->patternlen); } -static int macroexpand_one(struct all_attrs_item *all_attrs, int nr, int rem); +struct attr_state_queue { + const struct attr_state **items; + size_t alloc, nr; +}; + +static void attr_state_queue_push(struct attr_state_queue *t, + const struct match_attr *a) +{ + for (size_t i = 0; i < a->num_attr; i++) { + ALLOC_GROW(t->items, t->nr + 1, t->alloc); + t->items[t->nr++] = &a->state[i]; + } +} + +static const struct attr_state *attr_state_queue_pop(struct attr_state_queue *t) +{ + return t->nr ? t->items[--t->nr] : NULL; +} + +static void attr_state_queue_release(struct attr_state_queue *t) +{ + free(t->items); +} static int fill_one(struct all_attrs_item *all_attrs, const struct match_attr *a, int rem) { - size_t i; + struct attr_state_queue todo = { 0 }; + const struct attr_state *state; - for (i = a->num_attr; rem > 0 && i > 0; i--) { - const struct git_attr *attr = a->state[i - 1].attr; + attr_state_queue_push(&todo, a); + while (rem > 0 && (state = attr_state_queue_pop(&todo))) { + const struct git_attr *attr = state->attr; const char **n = &(all_attrs[attr->attr_nr].value); - const char *v = a->state[i - 1].setto; + const char *v = state->setto; if (*n == ATTR__UNKNOWN) { + const struct all_attrs_item *item = + &all_attrs[attr->attr_nr]; *n = v; rem--; - rem = macroexpand_one(all_attrs, attr->attr_nr, rem); + if (item->macro && item->value == ATTR__TRUE) + attr_state_queue_push(&todo, item->macro); } } + attr_state_queue_release(&todo); return rem; } @@ -1106,16 +1134,6 @@ static int fill(const char *path, int pathlen, int basename_offset, return rem; } -static int macroexpand_one(struct all_attrs_item *all_attrs, int nr, int rem) -{ - const struct all_attrs_item *item = &all_attrs[nr]; - - if (item->macro && item->value == ATTR__TRUE) - return fill_one(all_attrs, item->macro, rem); - else - return rem; -} - /* * Marks the attributes which are macros based on the attribute stack. * This prevents having to search through the attribute stack each time @@ -41,4 +41,7 @@ #undef asctime_r #define asctime_r(t, buf) BANNED(asctime_r) +#undef mktemp +#define mktemp(x) BANNED(mktemp) + #endif /* BANNED_H */ @@ -450,21 +450,20 @@ void find_bisection(struct commit_list **commit_list, int *reaches, clear_commit_weight(&commit_weight); } -static int register_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags UNUSED, void *cb_data UNUSED) +static int register_ref(const struct reference *ref, void *cb_data UNUSED) { struct strbuf good_prefix = STRBUF_INIT; strbuf_addstr(&good_prefix, term_good); strbuf_addstr(&good_prefix, "-"); - if (!strcmp(refname, term_bad)) { + if (!strcmp(ref->name, term_bad)) { free(current_bad_oid); current_bad_oid = xmalloc(sizeof(*current_bad_oid)); - oidcpy(current_bad_oid, oid); - } else if (starts_with(refname, good_prefix.buf)) { - oid_array_append(&good_revs, oid); - } else if (starts_with(refname, "skip-")) { - oid_array_append(&skipped_revs, oid); + oidcpy(current_bad_oid, ref->oid); + } else if (starts_with(ref->name, good_prefix.buf)) { + oid_array_append(&good_revs, ref->oid); + } else if (starts_with(ref->name, "skip-")) { + oid_array_append(&skipped_revs, ref->oid); } strbuf_release(&good_prefix); @@ -1178,14 +1177,11 @@ int estimate_bisect_steps(int all) return (e < 3 * x) ? n : n - 1; } -static int mark_for_removal(const char *refname, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flag UNUSED, void *cb_data) +static int mark_for_removal(const struct reference *ref, void *cb_data) { struct string_list *refs = cb_data; - char *ref = xstrfmt("refs/bisect%s", refname); - string_list_append(refs, ref); + char *bisect_ref = xstrfmt("refs/bisect%s", ref->name); + string_list_append(refs, bisect_ref); return 0; } @@ -375,7 +375,7 @@ int validate_branchname(const char *name, struct strbuf *ref) if (check_branch_ref(ref, name)) { int code = die_message(_("'%s' is not a valid branch name"), name); advise_if_enabled(ADVICE_REF_SYNTAX, - _("See `man git check-ref-format`")); + _("See 'git help check-ref-format'")); exit(code); } diff --git a/builtin/bisect.c b/builtin/bisect.c index ccff4e1a1b..4cc118fb57 100644 --- a/builtin/bisect.c +++ b/builtin/bisect.c @@ -363,10 +363,7 @@ static int check_and_set_terms(struct bisect_terms *terms, const char *cmd) return 0; } -static int inc_nr(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flag UNUSED, void *cb_data) +static int inc_nr(const struct reference *ref UNUSED, void *cb_data) { unsigned int *nr = (unsigned int *)cb_data; (*nr)++; @@ -554,12 +551,11 @@ finish: return res; } -static int add_bisect_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags UNUSED, void *cb) +static int add_bisect_ref(const struct reference *ref, void *cb) { struct add_bisect_ref_data *data = cb; - add_pending_oid(data->revs, refname, oid, data->object_flags); + add_pending_oid(data->revs, ref->name, ref->oid, data->object_flags); return 0; } @@ -1170,12 +1166,9 @@ static int bisect_visualize(struct bisect_terms *terms, int argc, return run_command(&cmd); } -static int get_first_good(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, void *cb_data) +static int get_first_good(const struct reference *ref, void *cb_data) { - oidcpy(cb_data, oid); + oidcpy(cb_data, ref->oid); return 1; } diff --git a/builtin/blame.c b/builtin/blame.c index 2703820258..6044973462 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -739,7 +739,8 @@ static int git_blame_config(const char *var, const char *value, ret = git_config_pathname(&str, var, value); if (ret) return ret; - string_list_insert(&ignore_revs_file_list, str); + if (str) + string_list_insert(&ignore_revs_file_list, str); free(str); return 0; } @@ -779,6 +780,19 @@ static int git_blame_config(const char *var, const char *value, } } + if (!strcmp(var, "diff.algorithm")) { + long diff_algorithm; + if (!value) + return config_error_nonbool(var); + diff_algorithm = parse_algorithm_value(value); + if (diff_algorithm < 0) + return error(_("unknown value for config '%s': %s"), + var, value); + xdl_opts &= ~XDF_DIFF_ALGORITHM_MASK; + xdl_opts |= diff_algorithm; + return 0; + } + if (git_diff_heuristic_config(var, value, cb) < 0) return -1; if (userdiff_config(var, value) < 0) @@ -824,6 +838,38 @@ static int blame_move_callback(const struct option *option, const char *arg, int return 0; } +static int blame_diff_algorithm_minimal(const struct option *option, + const char *arg, int unset) +{ + int *opt = option->value; + + BUG_ON_OPT_ARG(arg); + + *opt &= ~XDF_DIFF_ALGORITHM_MASK; + if (!unset) + *opt |= XDF_NEED_MINIMAL; + + return 0; +} + +static int blame_diff_algorithm_callback(const struct option *option, + const char *arg, int unset) +{ + int *opt = option->value; + long value = parse_algorithm_value(arg); + + BUG_ON_OPT_NEG(unset); + + if (value < 0) + return error(_("option diff-algorithm accepts \"myers\", " + "\"minimal\", \"patience\" and \"histogram\"")); + + *opt &= ~XDF_DIFF_ALGORITHM_MASK; + *opt |= value; + + return 0; +} + static int is_a_rev(const char *name) { struct object_id oid; @@ -915,11 +961,16 @@ int cmd_blame(int argc, OPT_BIT('s', NULL, &output_option, N_("suppress author name and timestamp (Default: off)"), OUTPUT_NO_AUTHOR), OPT_BIT('e', "show-email", &output_option, N_("show author email instead of name (Default: off)"), OUTPUT_SHOW_EMAIL), OPT_BIT('w', NULL, &xdl_opts, N_("ignore whitespace differences"), XDF_IGNORE_WHITESPACE), + OPT_CALLBACK_F(0, "diff-algorithm", &xdl_opts, N_("<algorithm>"), + N_("choose a diff algorithm"), + PARSE_OPT_NONEG, blame_diff_algorithm_callback), OPT_STRING_LIST(0, "ignore-rev", &ignore_rev_list, N_("rev"), N_("ignore <rev> when blaming")), OPT_STRING_LIST(0, "ignore-revs-file", &ignore_revs_file_list, N_("file"), N_("ignore revisions from <file>")), OPT_BIT(0, "color-lines", &output_option, N_("color redundant metadata from previous line differently"), OUTPUT_COLOR_LINE), OPT_BIT(0, "color-by-age", &output_option, N_("color lines by age"), OUTPUT_SHOW_AGE_WITH_COLOR), - OPT_BIT(0, "minimal", &xdl_opts, N_("spend extra cycles to find better match"), XDF_NEED_MINIMAL), + OPT_CALLBACK_F(0, "minimal", &xdl_opts, NULL, + N_("spend extra cycles to find a better match"), + PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, blame_diff_algorithm_minimal), OPT_STRING('S', NULL, &revs_file, N_("file"), N_("use revisions from <file> instead of calling git-rev-list")), OPT_STRING(0, "contents", &contents_from, N_("file"), N_("use <file>'s contents as the final image")), OPT_CALLBACK_F('C', NULL, &opt, N_("score"), N_("find line copies within and across files"), PARSE_OPT_OPTARG, blame_copy_callback), diff --git a/builtin/branch.c b/builtin/branch.c index 9fcf04bebb..c577b5d20f 100644 --- a/builtin/branch.c +++ b/builtin/branch.c @@ -591,7 +591,7 @@ static void copy_or_rename_branch(const char *oldname, const char *newname, int else { int code = die_message(_("invalid branch name: '%s'"), oldname); advise_if_enabled(ADVICE_REF_SYNTAX, - _("See `man git check-ref-format`")); + _("See 'git help check-ref-format'")); exit(code); } } diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 983ecec837..505ddaa12f 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -18,13 +18,13 @@ #include "list-objects-filter-options.h" #include "parse-options.h" #include "userdiff.h" -#include "streaming.h" #include "oid-array.h" #include "packfile.h" #include "pack-bitmap.h" #include "object-file.h" #include "object-name.h" #include "odb.h" +#include "odb/streaming.h" #include "replace-object.h" #include "promisor-remote.h" #include "mailmap.h" @@ -95,7 +95,7 @@ static int filter_object(const char *path, unsigned mode, static int stream_blob(const struct object_id *oid) { - if (stream_blob_to_fd(1, oid, NULL, 0)) + if (odb_stream_blob_to_fd(the_repository->objects, 1, oid, NULL, 0)) die("unable to stream %s to stdout", oid_to_hex(oid)); return 0; } diff --git a/builtin/checkout.c b/builtin/checkout.c index f9453473fe..66b69df6e6 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -1063,11 +1063,9 @@ static void update_refs_for_switch(const struct checkout_opts *opts, report_tracking(new_branch_info); } -static int add_pending_uninteresting_ref(const char *refname, const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, void *cb_data) +static int add_pending_uninteresting_ref(const struct reference *ref, void *cb_data) { - add_pending_oid(cb_data, refname, oid, UNINTERESTING); + add_pending_oid(cb_data, ref->name, ref->oid, UNINTERESTING); return 0; } diff --git a/builtin/clone.c b/builtin/clone.c index c990f398ef..b19b302b06 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -1617,7 +1617,7 @@ int cmd_clone(int argc, transport_disconnect(transport); if (option_dissociate) { - close_object_store(the_repository->objects); + odb_close(the_repository->objects); dissociate_from_references(); } diff --git a/builtin/config.c b/builtin/config.c index 75852bd79d..288ebdfdaa 100644 --- a/builtin/config.c +++ b/builtin/config.c @@ -261,6 +261,12 @@ struct strbuf_list { int alloc; }; +/* + * Format the configuration key-value pair (`key_`, `value_`) and + * append it into strbuf `buf`. Returns a negative value on failure, + * 0 on success, 1 on a missing optional value (i.e., telling the + * caller to pretend that <key_,value_> did not exist). + */ static int format_config(const struct config_display_options *opts, struct strbuf *buf, const char *key_, const char *value_, const struct key_value_info *kvi) @@ -299,7 +305,10 @@ static int format_config(const struct config_display_options *opts, char *v; if (git_config_pathname(&v, key_, value_) < 0) return -1; - strbuf_addstr(buf, v); + if (v) + strbuf_addstr(buf, v); + else + return 1; /* :(optional)no-such-file */ free((char *)v); } else if (opts->type == TYPE_EXPIRY_DATE) { timestamp_t t; @@ -344,6 +353,7 @@ static int collect_config(const char *key_, const char *value_, struct collect_config_data *data = cb; struct strbuf_list *values = data->values; const struct key_value_info *kvi = ctx->kvi; + int status; if (!(data->get_value_flags & GET_VALUE_KEY_REGEXP) && strcmp(key_, data->key)) @@ -361,8 +371,15 @@ static int collect_config(const char *key_, const char *value_, ALLOC_GROW(values->items, values->nr + 1, values->alloc); strbuf_init(&values->items[values->nr], 0); - return format_config(data->display_opts, &values->items[values->nr++], - key_, value_, kvi); + status = format_config(data->display_opts, &values->items[values->nr++], + key_, value_, kvi); + if (status < 0) + return status; + if (status) { + strbuf_release(&values->items[--values->nr]); + status = 0; + } + return status; } static int get_value(const struct config_location_options *opts, @@ -438,15 +455,23 @@ static int get_value(const struct config_location_options *opts, if (!values.nr && display_opts->default_value) { struct key_value_info kvi = KVI_INIT; struct strbuf *item; + int status; kvi_from_param(&kvi); ALLOC_GROW(values.items, values.nr + 1, values.alloc); item = &values.items[values.nr++]; strbuf_init(item, 0); - if (format_config(display_opts, item, key_, - display_opts->default_value, &kvi) < 0) + + status = format_config(display_opts, item, key_, + display_opts->default_value, &kvi); + if (status < 0) die(_("failed to format default config value: %s"), display_opts->default_value); + if (status) { + /* default was a missing optional value */ + values.nr--; + strbuf_release(item); + } } ret = !values.nr; @@ -714,11 +739,13 @@ static int get_urlmatch(const struct config_location_options *opts, for_each_string_list_item(item, &values) { struct urlmatch_current_candidate_value *matched = item->util; struct strbuf buf = STRBUF_INIT; + int status; - format_config(&display_opts, &buf, item->string, - matched->value_is_null ? NULL : matched->value.buf, - &matched->kvi); - fwrite(buf.buf, 1, buf.len, stdout); + status = format_config(&display_opts, &buf, item->string, + matched->value_is_null ? NULL : matched->value.buf, + &matched->kvi); + if (!status) + fwrite(buf.buf, 1, buf.len, stdout); strbuf_release(&buf); strbuf_release(&matched->value); @@ -985,7 +1012,7 @@ static int cmd_config_set(int argc, const char **argv, const char *prefix, argv[0], comment, value); if (ret == CONFIG_NOTHING_SET) error(_("cannot overwrite multiple values with a single value\n" - " Use a regexp, --add or --replace-all to change %s."), argv[0]); + " Use --value=<pattern>, --append or --all to change %s."), argv[0]); } location_options_release(&location_opts); @@ -1003,8 +1030,8 @@ static int cmd_config_unset(int argc, const char **argv, const char *prefix, struct option opts[] = { CONFIG_LOCATION_OPTIONS(location_opts), OPT_GROUP(N_("Filter")), - OPT_BIT(0, "all", &flags, N_("replace multi-valued config option with new value"), CONFIG_FLAGS_MULTI_REPLACE), - OPT_STRING(0, "value", &value_pattern, N_("pattern"), N_("show config with values matching the pattern")), + OPT_BIT(0, "all", &flags, N_("unset all multi-valued config options"), CONFIG_FLAGS_MULTI_REPLACE), + OPT_STRING(0, "value", &value_pattern, N_("pattern"), N_("unset multi-valued config options with matching values")), OPT_BIT(0, "fixed-value", &flags, N_("use string equality when comparing values to value pattern"), CONFIG_FLAGS_FIXED_VALUE), OPT_END(), }; diff --git a/builtin/describe.c b/builtin/describe.c index ffaf8d9f0a..443546aaac 100644 --- a/builtin/describe.c +++ b/builtin/describe.c @@ -154,20 +154,19 @@ static void add_to_known_names(const char *path, } } -static int get_name(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int get_name(const struct reference *ref, void *cb_data UNUSED) { int is_tag = 0; struct object_id peeled; int is_annotated, prio; const char *path_to_match = NULL; - if (skip_prefix(path, "refs/tags/", &path_to_match)) { + if (skip_prefix(ref->name, "refs/tags/", &path_to_match)) { is_tag = 1; } else if (all) { if ((exclude_patterns.nr || patterns.nr) && - !skip_prefix(path, "refs/heads/", &path_to_match) && - !skip_prefix(path, "refs/remotes/", &path_to_match)) { + !skip_prefix(ref->name, "refs/heads/", &path_to_match) && + !skip_prefix(ref->name, "refs/remotes/", &path_to_match)) { /* Only accept reference of known type if there are match/exclude patterns */ return 0; } @@ -209,10 +208,10 @@ static int get_name(const char *path, const char *referent UNUSED, const struct } /* Is it annotated? */ - if (!peel_iterated_oid(the_repository, oid, &peeled)) { - is_annotated = !oideq(oid, &peeled); + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) { + is_annotated = !oideq(ref->oid, &peeled); } else { - oidcpy(&peeled, oid); + oidcpy(&peeled, ref->oid); is_annotated = 0; } @@ -229,7 +228,8 @@ static int get_name(const char *path, const char *referent UNUSED, const struct else prio = 0; - add_to_known_names(all ? path + 5 : path + 10, &peeled, prio, oid); + add_to_known_names(all ? ref->name + 5 : ref->name + 10, + &peeled, prio, ref->oid); return 0; } diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 0421360ab7..b90da5e616 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -797,10 +797,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, (int)(committer_end - committer), committer); if (signatures.nr) { switch (signed_commit_mode) { - case SIGN_ABORT: - die(_("encountered signed commit %s; use " - "--signed-commits=<mode> to handle it"), - oid_to_hex(&commit->object.oid)); + /* Exporting modes */ case SIGN_WARN_VERBATIM: warning(_("exporting %"PRIuMAX" signature(s) for commit %s"), (uintmax_t)signatures.nr, oid_to_hex(&commit->object.oid)); @@ -811,12 +808,25 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, print_signature(item->string, item->util); } break; + + /* Stripping modes */ case SIGN_WARN_STRIP: warning(_("stripping signature(s) from commit %s"), oid_to_hex(&commit->object.oid)); /* fallthru */ case SIGN_STRIP: break; + + /* Aborting modes */ + case SIGN_ABORT: + die(_("encountered signed commit %s; use " + "--signed-commits=<mode> to handle it"), + oid_to_hex(&commit->object.oid)); + case SIGN_STRIP_IF_INVALID: + die(_("'strip-if-invalid' is not a valid mode for " + "git fast-export with --signed-commits=<mode>")); + default: + BUG("invalid signed_commit_mode value %d", signed_commit_mode); } string_list_clear(&signatures, 0); } @@ -935,16 +945,15 @@ static void handle_tag(const char *name, struct tag *tag) size_t sig_offset = parse_signed_buffer(message, message_size); if (sig_offset < message_size) switch (signed_tag_mode) { - case SIGN_ABORT: - die(_("encountered signed tag %s; use " - "--signed-tags=<mode> to handle it"), - oid_to_hex(&tag->object.oid)); + /* Exporting modes */ case SIGN_WARN_VERBATIM: warning(_("exporting signed tag %s"), oid_to_hex(&tag->object.oid)); /* fallthru */ case SIGN_VERBATIM: break; + + /* Stripping modes */ case SIGN_WARN_STRIP: warning(_("stripping signature from tag %s"), oid_to_hex(&tag->object.oid)); @@ -952,6 +961,17 @@ static void handle_tag(const char *name, struct tag *tag) case SIGN_STRIP: message_size = sig_offset; break; + + /* Aborting modes */ + case SIGN_ABORT: + die(_("encountered signed tag %s; use " + "--signed-tags=<mode> to handle it"), + oid_to_hex(&tag->object.oid)); + case SIGN_STRIP_IF_INVALID: + die(_("'strip-if-invalid' is not a valid mode for " + "git fast-export with --signed-tags=<mode>")); + default: + BUG("invalid signed_commit_mode value %d", signed_commit_mode); } } diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 7c194e71cb..7849005ccb 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -979,7 +979,7 @@ static int store_object( if (e->idx.offset) { duplicate_count_by_type[type]++; return 1; - } else if (find_oid_pack(&oid, packfile_store_get_packs(packs))) { + } else if (packfile_list_find_oid(packfile_store_get_packs(packs), &oid)) { e->type = type; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ @@ -1180,7 +1180,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark) duplicate_count_by_type[OBJ_BLOB]++; truncate_pack(&checkpoint); - } else if (find_oid_pack(&oid, packfile_store_get_packs(packs))) { + } else if (packfile_list_find_oid(packfile_store_get_packs(packs), &oid)) { e->type = OBJ_BLOB; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ @@ -2772,7 +2772,7 @@ static void add_gpgsig_to_commit(struct strbuf *commit_data, { struct string_list siglines = STRING_LIST_INIT_NODUP; - if (!sig->hash_algo) + if (!sig || !sig->hash_algo) return; strbuf_addstr(commit_data, header); @@ -2815,6 +2815,57 @@ static void import_one_signature(struct signature_data *sig_sha1, die(_("parse_one_signature() returned unknown hash algo")); } +static void finalize_commit_buffer(struct strbuf *new_data, + struct signature_data *sig_sha1, + struct signature_data *sig_sha256, + struct strbuf *msg) +{ + add_gpgsig_to_commit(new_data, "gpgsig ", sig_sha1); + add_gpgsig_to_commit(new_data, "gpgsig-sha256 ", sig_sha256); + + strbuf_addch(new_data, '\n'); + strbuf_addbuf(new_data, msg); +} + +static void handle_strip_if_invalid(struct strbuf *new_data, + struct signature_data *sig_sha1, + struct signature_data *sig_sha256, + struct strbuf *msg) +{ + struct strbuf tmp_buf = STRBUF_INIT; + struct signature_check signature_check = { 0 }; + int ret; + + /* Check signature in a temporary commit buffer */ + strbuf_addbuf(&tmp_buf, new_data); + finalize_commit_buffer(&tmp_buf, sig_sha1, sig_sha256, msg); + ret = verify_commit_buffer(tmp_buf.buf, tmp_buf.len, &signature_check); + + if (ret) { + const char *signer = signature_check.signer ? + signature_check.signer : _("unknown"); + const char *subject; + int subject_len = find_commit_subject(msg->buf, &subject); + + if (subject_len > 100) + warning(_("stripping invalid signature for commit '%.100s...'\n" + " allegedly by %s"), subject, signer); + else if (subject_len > 0) + warning(_("stripping invalid signature for commit '%.*s'\n" + " allegedly by %s"), subject_len, subject, signer); + else + warning(_("stripping invalid signature for commit\n" + " allegedly by %s"), signer); + + finalize_commit_buffer(new_data, NULL, NULL, msg); + } else { + strbuf_swap(new_data, &tmp_buf); + } + + signature_check_clear(&signature_check); + strbuf_release(&tmp_buf); +} + static void parse_new_commit(const char *arg) { static struct strbuf msg = STRBUF_INIT; @@ -2866,6 +2917,7 @@ static void parse_new_commit(const char *arg) warning(_("importing a commit signature verbatim")); /* fallthru */ case SIGN_VERBATIM: + case SIGN_STRIP_IF_INVALID: import_one_signature(&sig_sha1, &sig_sha256, v); break; @@ -2950,11 +3002,12 @@ static void parse_new_commit(const char *arg) "encoding %s\n", encoding); - add_gpgsig_to_commit(&new_data, "gpgsig ", &sig_sha1); - add_gpgsig_to_commit(&new_data, "gpgsig-sha256 ", &sig_sha256); + if (signed_commit_mode == SIGN_STRIP_IF_INVALID && + (sig_sha1.hash_algo || sig_sha256.hash_algo)) + handle_strip_if_invalid(&new_data, &sig_sha1, &sig_sha256, &msg); + else + finalize_commit_buffer(&new_data, &sig_sha1, &sig_sha256, &msg); - strbuf_addch(&new_data, '\n'); - strbuf_addbuf(&new_data, &msg); free(author); free(committer); free(encoding); @@ -2975,9 +3028,6 @@ static void handle_tag_signature(struct strbuf *msg, const char *name) switch (signed_tag_mode) { /* First, modes that don't change anything */ - case SIGN_ABORT: - die(_("encountered signed tag; use " - "--signed-tags=<mode> to handle it")); case SIGN_WARN_VERBATIM: warning(_("importing a tag signature verbatim for tag '%s'"), name); /* fallthru */ @@ -2994,7 +3044,13 @@ static void handle_tag_signature(struct strbuf *msg, const char *name) strbuf_setlen(msg, sig_offset); break; - /* Third, BUG */ + /* Third, aborting modes */ + case SIGN_ABORT: + die(_("encountered signed tag; use " + "--signed-tags=<mode> to handle it")); + case SIGN_STRIP_IF_INVALID: + die(_("'strip-if-invalid' is not a valid mode for " + "git fast-import with --signed-tags=<mode>")); default: BUG("invalid signed_tag_mode value %d from tag '%s'", signed_tag_mode, name); diff --git a/builtin/fetch.c b/builtin/fetch.c index c7ff3480fb..d1c475a22c 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -47,7 +47,7 @@ static const char * const builtin_fetch_usage[] = { N_("git fetch [<options>] [<repository> [<refspec>...]]"), N_("git fetch [<options>] <group>"), - N_("git fetch --multiple [<options>] [(<repository> | <group>)...]"), + N_("git fetch --multiple [<options>] [(<repository>|<group>)...]"), N_("git fetch --all [<options>]"), NULL }; @@ -289,13 +289,11 @@ static struct refname_hash_entry *refname_hash_add(struct hashmap *map, return ent; } -static int add_one_refname(const char *refname, const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, void *cbdata) +static int add_one_refname(const struct reference *ref, void *cbdata) { struct hashmap *refname_map = cbdata; - (void) refname_hash_add(refname_map, refname, oid); + (void) refname_hash_add(refname_map, ref->name, ref->oid); return 0; } @@ -1416,14 +1414,11 @@ static void set_option(struct transport *transport, const char *name, const char } -static int add_oid(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, void *cb_data) +static int add_oid(const struct reference *ref, void *cb_data) { struct oid_array *oids = cb_data; - oid_array_append(oids, oid); + oid_array_append(oids, ref->oid); return 0; } diff --git a/builtin/fsck.c b/builtin/fsck.c index b1a650c673..4979bc795e 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -13,11 +13,11 @@ #include "fsck.h" #include "parse-options.h" #include "progress.h" -#include "streaming.h" #include "packfile.h" #include "object-file.h" #include "object-name.h" #include "odb.h" +#include "odb/streaming.h" #include "path.h" #include "read-cache-ll.h" #include "replace-object.h" @@ -340,7 +340,8 @@ static void check_unreachable_object(struct object *obj) } f = xfopen(filename, "w"); if (obj->type == OBJ_BLOB) { - if (stream_blob_to_fd(fileno(f), &obj->oid, NULL, 1)) + if (odb_stream_blob_to_fd(the_repository->objects, fileno(f), + &obj->oid, NULL, 1)) die_errno(_("could not write '%s'"), filename); } else fprintf(f, "%s\n", describe_object(&obj->oid)); @@ -530,14 +531,13 @@ static int fsck_handle_reflog(const char *logname, void *cb_data) return 0; } -static int fsck_handle_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int fsck_handle_ref(const struct reference *ref, void *cb_data UNUSED) { struct object *obj; - obj = parse_object(the_repository, oid); + obj = parse_object(the_repository, ref->oid); if (!obj) { - if (is_promisor_object(the_repository, oid)) { + if (is_promisor_object(the_repository, ref->oid)) { /* * Increment default_refs anyway, because this is a * valid ref. @@ -546,19 +546,19 @@ static int fsck_handle_ref(const char *refname, const char *referent UNUSED, con return 0; } error(_("%s: invalid sha1 pointer %s"), - refname, oid_to_hex(oid)); + ref->name, oid_to_hex(ref->oid)); errors_found |= ERROR_REACHABLE; /* We'll continue with the rest despite the error.. */ return 0; } - if (obj->type != OBJ_COMMIT && is_branch(refname)) { - error(_("%s: not a commit"), refname); + if (obj->type != OBJ_COMMIT && is_branch(ref->name)) { + error(_("%s: not a commit"), ref->name); errors_found |= ERROR_REFS; } default_refs++; obj->flags |= USED; fsck_put_object_name(&fsck_walk_options, - oid, "%s", refname); + ref->oid, "%s", ref->name); mark_object_reachable(obj); return 0; @@ -580,13 +580,19 @@ static void get_default_heads(void) worktrees = get_worktrees(); for (p = worktrees; *p; p++) { struct worktree *wt = *p; - struct strbuf ref = STRBUF_INIT; + struct strbuf refname = STRBUF_INIT; - strbuf_worktree_ref(wt, &ref, "HEAD"); - fsck_head_link(ref.buf, &head_points_at, &head_oid); - if (head_points_at && !is_null_oid(&head_oid)) - fsck_handle_ref(ref.buf, NULL, &head_oid, 0, NULL); - strbuf_release(&ref); + strbuf_worktree_ref(wt, &refname, "HEAD"); + fsck_head_link(refname.buf, &head_points_at, &head_oid); + if (head_points_at && !is_null_oid(&head_oid)) { + struct reference ref = { + .name = refname.buf, + .oid = &head_oid, + }; + + fsck_handle_ref(&ref, NULL); + } + strbuf_release(&refname); if (include_reflogs) refs_for_each_reflog(get_worktree_ref_store(wt), diff --git a/builtin/gc.c b/builtin/gc.c index d212cbb9b8..92c6e7b954 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -36,6 +36,7 @@ #include "reflog.h" #include "repack.h" #include "rerere.h" +#include "revision.h" #include "blob.h" #include "tree.h" #include "promisor-remote.h" @@ -286,12 +287,26 @@ static void maintenance_run_opts_release(struct maintenance_run_opts *opts) static int pack_refs_condition(UNUSED struct gc_config *cfg) { - /* - * The auto-repacking logic for refs is handled by the ref backends and - * exposed via `git pack-refs --auto`. We thus always return truish - * here and let the backend decide for us. - */ - return 1; + struct string_list included_refs = STRING_LIST_INIT_NODUP; + struct ref_exclusions excludes = REF_EXCLUSIONS_INIT; + struct refs_optimize_opts optimize_opts = { + .exclusions = &excludes, + .includes = &included_refs, + .flags = REFS_OPTIMIZE_PRUNE | REFS_OPTIMIZE_AUTO, + }; + bool required; + + /* Check for all refs, similar to 'git refs optimize --all'. */ + string_list_append(optimize_opts.includes, "*"); + + if (refs_optimize_required(get_main_ref_store(the_repository), + &optimize_opts, &required)) + return 0; + + clear_ref_exclusions(&excludes); + string_list_clear(&included_refs, 0); + + return required; } static int maintenance_task_pack_refs(struct maintenance_run_opts *opts, @@ -1048,7 +1063,7 @@ int cmd_gc(int argc, report_garbage = report_pack_garbage; odb_reprepare(the_repository->objects); if (pack_garbage.nr > 0) { - close_object_store(the_repository->objects); + odb_close(the_repository->objects); clean_pack_garbage(); } @@ -1095,32 +1110,26 @@ static int maintenance_opt_schedule(const struct option *opt, const char *arg, return 0; } -/* Remember to update object flag allocation in object.h */ -#define SEEN (1u<<0) - struct cg_auto_data { int num_not_in_graph; int limit; }; -static int dfs_on_ref(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *cb_data) +static int dfs_on_ref(const struct reference *ref, void *cb_data) { struct cg_auto_data *data = (struct cg_auto_data *)cb_data; int result = 0; + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; struct commit_list *stack = NULL; struct commit *commit; - if (!peel_iterated_oid(the_repository, oid, &peeled)) - oid = &peeled; - if (odb_read_object_info(the_repository->objects, oid, NULL) != OBJ_COMMIT) + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) + maybe_peeled = &peeled; + if (odb_read_object_info(the_repository->objects, maybe_peeled, NULL) != OBJ_COMMIT) return 0; - commit = lookup_commit(the_repository, oid); + commit = lookup_commit(the_repository, maybe_peeled); if (!commit) return 0; if (repo_parse_commit(the_repository, commit) || @@ -3447,7 +3456,67 @@ static int maintenance_stop(int argc, const char **argv, const char *prefix, return update_background_schedule(NULL, 0); } -static const char * const builtin_maintenance_usage[] = { +static const char *const builtin_maintenance_is_needed_usage[] = { + "git maintenance is-needed [--task=<task>] [--schedule]", + NULL +}; + +static int maintenance_is_needed(int argc, const char **argv, const char *prefix, + struct repository *repo UNUSED) +{ + struct maintenance_run_opts opts = MAINTENANCE_RUN_OPTS_INIT; + struct string_list selected_tasks = STRING_LIST_INIT_DUP; + struct gc_config cfg = GC_CONFIG_INIT; + struct option options[] = { + OPT_BOOL(0, "auto", &opts.auto_flag, + N_("run tasks based on the state of the repository")), + OPT_CALLBACK_F(0, "task", &selected_tasks, N_("task"), + N_("check a specific task"), + PARSE_OPT_NONEG, task_option_parse), + OPT_END() + }; + bool is_needed = false; + + argc = parse_options(argc, argv, prefix, options, + builtin_maintenance_is_needed_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc) + usage_with_options(builtin_maintenance_is_needed_usage, options); + + gc_config(&cfg); + initialize_task_config(&opts, &selected_tasks); + + if (opts.auto_flag) { + for (size_t i = 0; i < opts.tasks_nr; i++) { + if (tasks[opts.tasks[i]].auto_condition && + tasks[opts.tasks[i]].auto_condition(&cfg)) { + is_needed = true; + break; + } + } + } else { + /* + * When not using --auto we always require maintenance right now. + * + * TODO: this certainly is too eager, as some maintenance tasks may + * decide to not do anything because the data structures are already + * fully optimized. We may eventually want to extend the auto + * condition to also cover non-auto runs so that we can detect such + * cases. + */ + is_needed = true; + } + + string_list_clear(&selected_tasks, 0); + maintenance_run_opts_release(&opts); + gc_config_release(&cfg); + + if (is_needed) + return 0; + return 1; +} + +static const char *const builtin_maintenance_usage[] = { N_("git maintenance <subcommand> [<options>]"), NULL, }; @@ -3464,6 +3533,7 @@ int cmd_maintenance(int argc, OPT_SUBCOMMAND("stop", &fn, maintenance_stop), OPT_SUBCOMMAND("register", &fn, maintenance_register), OPT_SUBCOMMAND("unregister", &fn, maintenance_unregister), + OPT_SUBCOMMAND("is-needed", &fn, maintenance_is_needed), OPT_END(), }; diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 2b78ba7fe4..a7e901e49c 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -16,12 +16,12 @@ #include "progress.h" #include "fsck.h" #include "strbuf.h" -#include "streaming.h" #include "thread-utils.h" #include "packfile.h" #include "pack-revindex.h" #include "object-file.h" #include "odb.h" +#include "odb/streaming.h" #include "oid-array.h" #include "oidset.h" #include "path.h" @@ -762,7 +762,7 @@ static void find_ref_delta_children(const struct object_id *oid, struct compare_data { struct object_entry *entry; - struct git_istream *st; + struct odb_read_stream *st; unsigned char *buf; unsigned long buf_size; }; @@ -779,7 +779,7 @@ static int compare_objects(const unsigned char *buf, unsigned long size, } while (size) { - ssize_t len = read_istream(data->st, data->buf, size); + ssize_t len = odb_read_stream_read(data->st, data->buf, size); if (len == 0) die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(&data->entry->idx.oid)); @@ -798,8 +798,6 @@ static int compare_objects(const unsigned char *buf, unsigned long size, static int check_collison(struct object_entry *entry) { struct compare_data data; - enum object_type type; - unsigned long size; if (entry->size <= repo_settings_get_big_file_threshold(the_repository) || entry->type != OBJ_BLOB) @@ -807,15 +805,14 @@ static int check_collison(struct object_entry *entry) memset(&data, 0, sizeof(data)); data.entry = entry; - data.st = open_istream(the_repository, &entry->idx.oid, &type, &size, - NULL); + data.st = odb_read_stream_open(the_repository->objects, &entry->idx.oid, NULL); if (!data.st) return -1; - if (size != entry->size || type != entry->type) + if (data.st->size != entry->size || data.st->type != entry->type) die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(&entry->idx.oid)); unpack_data(entry, compare_objects, &data); - close_istream(data.st); + odb_read_stream_close(data.st); free(data.buf); return 0; } @@ -1640,7 +1637,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name, rename_tmp_packfile(&final_index_name, curr_index_name, &index_name, hash, "idx", 1); - if (do_fsck_object) + if (do_fsck_object && startup_info->have_repository) packfile_store_load_pack(the_repository->objects->packfiles, final_index_name, 0); @@ -2110,8 +2107,23 @@ int cmd_index_pack(int argc, else close(input_fd); - if (do_fsck_object && fsck_finish(&fsck_options)) - die(_("fsck error in pack objects")); + if (do_fsck_object) { + /* + * We cannot perform queued consistency checks when running + * outside of a repository because those require us to read + * from the object database, which is uninitialized. + * + * TODO: we may eventually set up an in-memory object database, + * which would allow us to perform these queued checks. + */ + if (!startup_info->have_repository && + fsck_has_queued_checks(&fsck_options)) + die(_("cannot perform queued object checks outside " + "of a repository")); + + if (fsck_finish(&fsck_options)) + die(_("fsck error in pack objects")); + } free(opts.anomaly); free(objects); diff --git a/builtin/last-modified.c b/builtin/last-modified.c index b0ecbdc540..7345665a92 100644 --- a/builtin/last-modified.c +++ b/builtin/last-modified.c @@ -327,7 +327,7 @@ static void process_parent(struct last_modified *lm, if (!(parent->object.flags & PARENT1)) active_paths_free(lm, parent); - memset(lm->scratch->words, 0x0, lm->scratch->word_alloc); + memset(lm->scratch->words, 0x0, lm->scratch->word_alloc * sizeof(eword_t)); diff_queue_clear(&diff_queued_diff); } @@ -525,7 +525,8 @@ int cmd_last_modified(int argc, const char **argv, const char *prefix, argc = parse_options(argc, argv, prefix, last_modified_options, last_modified_usage, - PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN_OPT); + PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN_OPT | + PARSE_OPT_KEEP_DASHDASH); repo_config(repo, git_default_config, NULL); diff --git a/builtin/log.c b/builtin/log.c index c8319b8af3..d4cf9c59c8 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -16,6 +16,7 @@ #include "refs.h" #include "object-name.h" #include "odb.h" +#include "odb/streaming.h" #include "pager.h" #include "color.h" #include "commit.h" @@ -35,7 +36,6 @@ #include "parse-options.h" #include "line-log.h" #include "branch.h" -#include "streaming.h" #include "version.h" #include "mailmap.h" #include "progress.h" @@ -584,7 +584,7 @@ static int show_blob_object(const struct object_id *oid, struct rev_info *rev, c fflush(rev->diffopt.file); if (!rev->diffopt.flags.textconv_set_via_cmdline || !rev->diffopt.flags.allow_textconv) - return stream_blob_to_fd(1, oid, NULL, 0); + return odb_stream_blob_to_fd(the_repository->objects, 1, oid, NULL, 0); if (get_oid_with_context(the_repository, obj_name, GET_OID_RECORD_PATH, @@ -594,7 +594,7 @@ static int show_blob_object(const struct object_id *oid, struct rev_info *rev, c !textconv_object(the_repository, obj_context.path, obj_context.mode, &oidc, 1, &buf, &size)) { object_context_release(&obj_context); - return stream_blob_to_fd(1, oid, NULL, 0); + return odb_stream_blob_to_fd(the_repository->objects, 1, oid, NULL, 0); } if (!buf) diff --git a/builtin/ls-remote.c b/builtin/ls-remote.c index df09000b30..fe77829557 100644 --- a/builtin/ls-remote.c +++ b/builtin/ls-remote.c @@ -156,7 +156,7 @@ int cmd_ls_remote(int argc, continue; if (!tail_match(&pattern, ref->name)) continue; - item = ref_array_push(&ref_array, ref->name, &ref->old_oid); + item = ref_array_push(&ref_array, ref->name, &ref->old_oid, NULL); item->symref = xstrdup_or_null(ref->symref); } diff --git a/builtin/name-rev.c b/builtin/name-rev.c index 74512e54a3..615f7d1aae 100644 --- a/builtin/name-rev.c +++ b/builtin/name-rev.c @@ -339,10 +339,9 @@ static int cmp_by_tag_and_age(const void *a_, const void *b_) return a->taggerdate != b->taggerdate; } -static int name_ref(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flags UNUSED, void *cb_data) +static int name_ref(const struct reference *ref, void *cb_data) { - struct object *o = parse_object(the_repository, oid); + struct object *o = parse_object(the_repository, ref->oid); struct name_ref_data *data = cb_data; int can_abbreviate_output = data->tags_only && data->name_only; int deref = 0; @@ -350,14 +349,14 @@ static int name_ref(const char *path, const char *referent UNUSED, const struct struct commit *commit = NULL; timestamp_t taggerdate = TIME_MAX; - if (data->tags_only && !starts_with(path, "refs/tags/")) + if (data->tags_only && !starts_with(ref->name, "refs/tags/")) return 0; if (data->exclude_filters.nr) { struct string_list_item *item; for_each_string_list_item(item, &data->exclude_filters) { - if (subpath_matches(path, item->string) >= 0) + if (subpath_matches(ref->name, item->string) >= 0) return 0; } } @@ -378,7 +377,7 @@ static int name_ref(const char *path, const char *referent UNUSED, const struct * shouldn't stop when seeing 'refs/tags/v1.4' matches * 'refs/tags/v*'. We should show it as 'v1.4'. */ - switch (subpath_matches(path, item->string)) { + switch (subpath_matches(ref->name, item->string)) { case -1: /* did not match */ break; case 0: /* matched fully */ @@ -406,13 +405,13 @@ static int name_ref(const char *path, const char *referent UNUSED, const struct } if (o && o->type == OBJ_COMMIT) { commit = (struct commit *)o; - from_tag = starts_with(path, "refs/tags/"); + from_tag = starts_with(ref->name, "refs/tags/"); if (taggerdate == TIME_MAX) taggerdate = commit->date; } - add_to_tip_table(oid, path, can_abbreviate_output, commit, taggerdate, - from_tag, deref); + add_to_tip_table(ref->oid, ref->name, can_abbreviate_output, + commit, taggerdate, from_tag, deref); return 0; } diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index b5454e5df1..1ce8d6ee21 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -22,7 +22,6 @@ #include "pack-objects.h" #include "progress.h" #include "refs.h" -#include "streaming.h" #include "thread-utils.h" #include "pack-bitmap.h" #include "delta-islands.h" @@ -33,6 +32,7 @@ #include "packfile.h" #include "object-file.h" #include "odb.h" +#include "odb/streaming.h" #include "replace-object.h" #include "dir.h" #include "midx.h" @@ -404,7 +404,7 @@ static unsigned long do_compress(void **pptr, unsigned long size) return stream.total_out; } -static unsigned long write_large_blob_data(struct git_istream *st, struct hashfile *f, +static unsigned long write_large_blob_data(struct odb_read_stream *st, struct hashfile *f, const struct object_id *oid) { git_zstream stream; @@ -417,7 +417,7 @@ static unsigned long write_large_blob_data(struct git_istream *st, struct hashfi for (;;) { ssize_t readlen; int zret = Z_OK; - readlen = read_istream(st, ibuf, sizeof(ibuf)); + readlen = odb_read_stream_read(st, ibuf, sizeof(ibuf)); if (readlen == -1) die(_("unable to read %s"), oid_to_hex(oid)); @@ -513,17 +513,19 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent unsigned hdrlen; enum object_type type; void *buf; - struct git_istream *st = NULL; + struct odb_read_stream *st = NULL; const unsigned hashsz = the_hash_algo->rawsz; if (!usable_delta) { if (oe_type(entry) == OBJ_BLOB && oe_size_greater_than(&to_pack, entry, repo_settings_get_big_file_threshold(the_repository)) && - (st = open_istream(the_repository, &entry->idx.oid, &type, - &size, NULL)) != NULL) + (st = odb_read_stream_open(the_repository->objects, &entry->idx.oid, + NULL)) != NULL) { buf = NULL; - else { + type = st->type; + size = st->size; + } else { buf = odb_read_object(the_repository->objects, &entry->idx.oid, &type, &size); @@ -577,7 +579,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent dheader[--pos] = 128 | (--ofs & 127); if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { if (st) - close_istream(st); + odb_read_stream_close(st); free(buf); return 0; } @@ -591,7 +593,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent */ if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { if (st) - close_istream(st); + odb_read_stream_close(st); free(buf); return 0; } @@ -601,7 +603,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent } else { if (limit && hdrlen + datalen + hashsz >= limit) { if (st) - close_istream(st); + odb_read_stream_close(st); free(buf); return 0; } @@ -609,7 +611,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent } if (st) { datalen = write_large_blob_data(st, f, &entry->idx.oid); - close_istream(st); + odb_read_stream_close(st); } else { hashwrite(f, buf, datalen); free(buf); @@ -831,15 +833,14 @@ static enum write_one_status write_one(struct hashfile *f, return WRITE_ONE_WRITTEN; } -static int mark_tagged(const char *path UNUSED, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int mark_tagged(const struct reference *ref, void *cb_data UNUSED) { struct object_id peeled; - struct object_entry *entry = packlist_find(&to_pack, oid); + struct object_entry *entry = packlist_find(&to_pack, ref->oid); if (entry) entry->tagged = 1; - if (!peel_iterated_oid(the_repository, oid, &peeled)) { + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) { entry = packlist_find(&to_pack, &peeled); if (entry) entry->tagged = 1; @@ -1706,8 +1707,8 @@ static int want_object_in_pack_mtime(const struct object_id *oid, uint32_t found_mtime) { int want; + struct packfile_list_entry *e; struct odb_source *source; - struct list_head *pos; if (!exclude && local) { /* @@ -1716,7 +1717,7 @@ static int want_object_in_pack_mtime(const struct object_id *oid, */ struct odb_source *source = the_repository->objects->sources->next; for (; source; source = source->next) - if (has_loose_object(source, oid)) + if (odb_source_loose_has_object(source, oid)) return 0; } @@ -1748,12 +1749,11 @@ static int want_object_in_pack_mtime(const struct object_id *oid, } } - list_for_each(pos, packfile_store_get_packs_mru(the_repository->objects->packfiles)) { - struct packed_git *p = list_entry(pos, struct packed_git, mru); + for (e = the_repository->objects->packfiles->packs.head; e; e = e->next) { + struct packed_git *p = e->pack; want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset, found_mtime); if (!exclude && want > 0) - list_move(&p->mru, - packfile_store_get_packs_mru(the_repository->objects->packfiles)); + packfile_list_prepend(&the_repository->objects->packfiles->packs, p); if (want != -1) return want; } @@ -3306,13 +3306,13 @@ static void add_tag_chain(const struct object_id *oid) } } -static int add_ref_tag(const char *tag UNUSED, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int add_ref_tag(const struct reference *ref, void *cb_data UNUSED) { struct object_id peeled; - if (!peel_iterated_oid(the_repository, oid, &peeled) && obj_is_packed(&peeled)) - add_tag_chain(oid); + if (!reference_get_peeled_oid(the_repository, ref, &peeled) && + obj_is_packed(&peeled)) + add_tag_chain(ref->oid); return 0; } @@ -3978,7 +3978,7 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type int found = 0; for (; !found && source; source = source->next) - if (has_loose_object(source, oid)) + if (odb_source_loose_has_object(source, oid)) found = 1; /* @@ -4389,27 +4389,27 @@ static void add_unreachable_loose_objects(struct rev_info *revs) static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) { - struct packfile_store *packs = the_repository->objects->packfiles; - static struct packed_git *last_found = (void *)1; + static struct packed_git *last_found = NULL; struct packed_git *p; - p = (last_found != (void *)1) ? last_found : - packfile_store_get_packs(packs); + if (last_found && find_pack_entry_one(oid, last_found)) + return 1; - while (p) { - if ((!p->pack_local || p->pack_keep || - p->pack_keep_in_core) && - find_pack_entry_one(oid, p)) { + repo_for_each_pack(the_repository, p) { + /* + * We have already checked `last_found`, so there is no need to + * re-check here. + */ + if (p == last_found) + continue; + + if ((!p->pack_local || p->pack_keep || p->pack_keep_in_core) && + find_pack_entry_one(oid, p)) { last_found = p; return 1; } - if (p == last_found) - p = packfile_store_get_packs(packs); - else - p = p->next; - if (p == last_found) - p = p->next; } + return 0; } @@ -4528,19 +4528,16 @@ static void record_recent_commit(struct commit *commit, void *data UNUSED) oid_array_append(&recent_objects, &commit->object.oid); } -static int mark_bitmap_preferred_tip(const char *refname, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *data UNUSED) +static int mark_bitmap_preferred_tip(const struct reference *ref, void *data UNUSED) { + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; struct object *object; - if (!peel_iterated_oid(the_repository, oid, &peeled)) - oid = &peeled; + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) + maybe_peeled = &peeled; - object = parse_object_or_die(the_repository, oid, refname); + object = parse_object_or_die(the_repository, maybe_peeled, ref->name); if (object->type == OBJ_COMMIT) object->flags |= NEEDS_BITMAP; diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index c9288a9c7e..9c49174616 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -34,7 +34,6 @@ #include "object-file.h" #include "object-name.h" #include "odb.h" -#include "path.h" #include "protocol.h" #include "commit-reach.h" #include "server-info.h" @@ -42,6 +41,7 @@ #include "trace2.h" #include "worktree.h" #include "shallow.h" +#include "setup.h" #include "parse-options.h" static const char * const receive_pack_usage[] = { @@ -177,8 +177,9 @@ static int receive_pack_config(const char *var, const char *value, if (git_config_pathname(&path, var, value)) return -1; - strbuf_addf(&fsck_msg_types, "%cskiplist=%s", - fsck_msg_types.len ? ',' : '=', path); + if (path) + strbuf_addf(&fsck_msg_types, "%cskiplist=%s", + fsck_msg_types.len ? ',' : '=', path); free(path); return 0; } @@ -305,13 +306,12 @@ static void show_ref(const char *path, const struct object_id *oid) } } -static int show_ref_cb(const char *path_full, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *data) +static int show_ref_cb(const struct reference *ref, void *data) { struct oidset *seen = data; - const char *path = strip_namespace(path_full); + const char *path = strip_namespace(ref->name); - if (ref_is_hidden(path, path_full, &hidden_refs)) + if (ref_is_hidden(path, ref->name, &hidden_refs)) return 0; /* @@ -320,13 +320,13 @@ static int show_ref_cb(const char *path_full, const char *referent UNUSED, const * transfer but will otherwise ignore them. */ if (!path) { - if (oidset_insert(seen, oid)) + if (oidset_insert(seen, ref->oid)) return 0; path = ".have"; } else { - oidset_insert(seen, oid); + oidset_insert(seen, ref->oid); } - show_ref(path, oid); + show_ref(path, ref->oid); return 0; } diff --git a/builtin/remote.c b/builtin/remote.c index 8a7ed4299a..7ffc14ba15 100644 --- a/builtin/remote.c +++ b/builtin/remote.c @@ -570,17 +570,14 @@ struct branches_for_remote { struct known_remotes *keep; }; -static int add_branch_for_removal(const char *refname, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, void *cb_data) +static int add_branch_for_removal(const struct reference *ref, void *cb_data) { struct branches_for_remote *branches = cb_data; struct refspec_item refspec; struct known_remote *kr; memset(&refspec, 0, sizeof(refspec)); - refspec.dst = (char *)refname; + refspec.dst = (char *)ref->name; if (remote_find_tracking(branches->remote, &refspec)) return 0; free(refspec.src); @@ -588,7 +585,7 @@ static int add_branch_for_removal(const char *refname, /* don't delete a branch if another remote also uses it */ for (kr = branches->keep->list; kr; kr = kr->next) { memset(&refspec, 0, sizeof(refspec)); - refspec.dst = (char *)refname; + refspec.dst = (char *)ref->name; if (!remote_find_tracking(kr->remote, &refspec)) { free(refspec.src); return 0; @@ -596,16 +593,16 @@ static int add_branch_for_removal(const char *refname, } /* don't delete non-remote-tracking refs */ - if (!starts_with(refname, "refs/remotes/")) { + if (!starts_with(ref->name, "refs/remotes/")) { /* advise user how to delete local branches */ - if (starts_with(refname, "refs/heads/")) + if (starts_with(ref->name, "refs/heads/")) string_list_append(branches->skipped, - abbrev_branch(refname)); + abbrev_branch(ref->name)); /* silently skip over other non-remote refs */ return 0; } - string_list_append(branches->branches, refname); + string_list_append(branches->branches, ref->name); return 0; } @@ -713,18 +710,18 @@ out: return error; } -static int rename_one_ref(const char *old_refname, const char *referent, - const struct object_id *oid, - int flags, void *cb_data) +static int rename_one_ref(const struct reference *ref, void *cb_data) { struct strbuf new_referent = STRBUF_INIT; struct strbuf new_refname = STRBUF_INIT; struct rename_info *rename = cb_data; + const struct object_id *oid = ref->oid; + const char *referent = ref->target; int error; - compute_renamed_ref(rename, old_refname, &new_refname); + compute_renamed_ref(rename, ref->name, &new_refname); - if (flags & REF_ISSYMREF) { + if (ref->flags & REF_ISSYMREF) { /* * Stupidly enough `referent` is not pointing to the immediate * target of a symref, but it's the recursively resolved value. @@ -732,25 +729,25 @@ static int rename_one_ref(const char *old_refname, const char *referent, * unborn symrefs don't have any value for the `referent` at all. */ referent = refs_resolve_ref_unsafe(get_main_ref_store(the_repository), - old_refname, RESOLVE_REF_NO_RECURSE, + ref->name, RESOLVE_REF_NO_RECURSE, NULL, NULL); compute_renamed_ref(rename, referent, &new_referent); oid = NULL; } - error = ref_transaction_delete(rename->transaction, old_refname, + error = ref_transaction_delete(rename->transaction, ref->name, oid, referent, REF_NO_DEREF, NULL, rename->err); if (error < 0) goto out; error = ref_transaction_update(rename->transaction, new_refname.buf, oid, null_oid(the_hash_algo), - (flags & REF_ISSYMREF) ? new_referent.buf : NULL, NULL, + (ref->flags & REF_ISSYMREF) ? new_referent.buf : NULL, NULL, REF_SKIP_CREATE_REFLOG | REF_NO_DEREF | REF_SKIP_OID_VERIFICATION, NULL, rename->err); if (error < 0) goto out; - error = rename_one_reflog(old_refname, oid, rename); + error = rename_one_reflog(ref->name, oid, rename); if (error < 0) goto out; @@ -1125,19 +1122,16 @@ static void free_remote_ref_states(struct ref_states *states) string_list_clear_func(&states->push, clear_push_info); } -static int append_ref_to_tracked_list(const char *refname, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags, void *cb_data) +static int append_ref_to_tracked_list(const struct reference *ref, void *cb_data) { struct ref_states *states = cb_data; struct refspec_item refspec; - if (flags & REF_ISSYMREF) + if (ref->flags & REF_ISSYMREF) return 0; memset(&refspec, 0, sizeof(refspec)); - refspec.dst = (char *)refname; + refspec.dst = (char *)ref->name; if (!remote_find_tracking(states->remote, &refspec)) { string_list_append(&states->tracked, abbrev_branch(refspec.src)); free(refspec.src); diff --git a/builtin/repack.c b/builtin/repack.c index cfdb4c0920..d9012141f6 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -488,7 +488,7 @@ int cmd_repack(int argc, string_list_sort(&names); - close_object_store(repo->objects); + odb_close(repo->objects); /* * Ok we have prepared all new packfiles. diff --git a/builtin/replace.c b/builtin/replace.c index 900b560a77..4c62c5ab58 100644 --- a/builtin/replace.c +++ b/builtin/replace.c @@ -47,30 +47,27 @@ struct show_data { enum replace_format format; }; -static int show_reference(const char *refname, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, void *cb_data) +static int show_reference(const struct reference *ref, void *cb_data) { struct show_data *data = cb_data; - if (!wildmatch(data->pattern, refname, 0)) { + if (!wildmatch(data->pattern, ref->name, 0)) { if (data->format == REPLACE_FORMAT_SHORT) - printf("%s\n", refname); + printf("%s\n", ref->name); else if (data->format == REPLACE_FORMAT_MEDIUM) - printf("%s -> %s\n", refname, oid_to_hex(oid)); + printf("%s -> %s\n", ref->name, oid_to_hex(ref->oid)); else { /* data->format == REPLACE_FORMAT_LONG */ struct object_id object; enum object_type obj_type, repl_type; - if (repo_get_oid(data->repo, refname, &object)) - return error(_("failed to resolve '%s' as a valid ref"), refname); + if (repo_get_oid(data->repo, ref->name, &object)) + return error(_("failed to resolve '%s' as a valid ref"), ref->name); obj_type = odb_read_object_info(data->repo->objects, &object, NULL); - repl_type = odb_read_object_info(data->repo->objects, oid, NULL); + repl_type = odb_read_object_info(data->repo->objects, ref->oid, NULL); - printf("%s (%s) -> %s (%s)\n", refname, type_name(obj_type), - oid_to_hex(oid), type_name(repl_type)); + printf("%s (%s) -> %s (%s)\n", ref->name, type_name(obj_type), + oid_to_hex(ref->oid), type_name(repl_type)); } } diff --git a/builtin/replay.c b/builtin/replay.c index 6172c8aacc..507b909df7 100644 --- a/builtin/replay.c +++ b/builtin/replay.c @@ -8,6 +8,7 @@ #include "git-compat-util.h" #include "builtin.h" +#include "config.h" #include "environment.h" #include "hex.h" #include "lockfile.h" @@ -20,6 +21,11 @@ #include <oidset.h> #include <tree.h> +enum ref_action_mode { + REF_ACTION_UPDATE, + REF_ACTION_PRINT, +}; + static const char *short_commit_name(struct repository *repo, struct commit *commit) { @@ -67,7 +73,7 @@ static struct commit *create_commit(struct repository *repo, const char *message = repo_logmsg_reencode(repo, based_on, NULL, out_enc); const char *orig_message = NULL; - const char *exclude_gpgsig[] = { "gpgsig", NULL }; + const char *exclude_gpgsig[] = { "gpgsig", "gpgsig-sha256", NULL }; commit_list_insert(parent, &parents); extra = read_commit_extra_headers(based_on, exclude_gpgsig); @@ -284,6 +290,54 @@ static struct commit *pick_regular_commit(struct repository *repo, return create_commit(repo, result->tree, pickme, replayed_base); } +static enum ref_action_mode parse_ref_action_mode(const char *ref_action, const char *source) +{ + if (!ref_action || !strcmp(ref_action, "update")) + return REF_ACTION_UPDATE; + if (!strcmp(ref_action, "print")) + return REF_ACTION_PRINT; + die(_("invalid %s value: '%s'"), source, ref_action); +} + +static enum ref_action_mode get_ref_action_mode(struct repository *repo, const char *ref_action) +{ + const char *config_value = NULL; + + /* Command line option takes precedence */ + if (ref_action) + return parse_ref_action_mode(ref_action, "--ref-action"); + + /* Check config value */ + if (!repo_config_get_string_tmp(repo, "replay.refAction", &config_value)) + return parse_ref_action_mode(config_value, "replay.refAction"); + + /* Default to update mode */ + return REF_ACTION_UPDATE; +} + +static int handle_ref_update(enum ref_action_mode mode, + struct ref_transaction *transaction, + const char *refname, + const struct object_id *new_oid, + const struct object_id *old_oid, + const char *reflog_msg, + struct strbuf *err) +{ + switch (mode) { + case REF_ACTION_PRINT: + printf("update %s %s %s\n", + refname, + oid_to_hex(new_oid), + oid_to_hex(old_oid)); + return 0; + case REF_ACTION_UPDATE: + return ref_transaction_update(transaction, refname, new_oid, old_oid, + NULL, NULL, 0, reflog_msg, err); + default: + BUG("unknown ref_action_mode %d", mode); + } +} + int cmd_replay(int argc, const char **argv, const char *prefix, @@ -294,6 +348,8 @@ int cmd_replay(int argc, struct commit *onto = NULL; const char *onto_name = NULL; int contained = 0; + const char *ref_action = NULL; + enum ref_action_mode ref_mode; struct rev_info revs; struct commit *last_commit = NULL; @@ -302,12 +358,15 @@ int cmd_replay(int argc, struct merge_result result; struct strset *update_refs = NULL; kh_oid_map_t *replayed_commits; + struct ref_transaction *transaction = NULL; + struct strbuf transaction_err = STRBUF_INIT; + struct strbuf reflog_msg = STRBUF_INIT; int ret = 0; - const char * const replay_usage[] = { + const char *const replay_usage[] = { N_("(EXPERIMENTAL!) git replay " "([--contained] --onto <newbase> | --advance <branch>) " - "<revision-range>..."), + "[--ref-action[=<mode>]] <revision-range>"), NULL }; struct option replay_options[] = { @@ -319,6 +378,9 @@ int cmd_replay(int argc, N_("replay onto given commit")), OPT_BOOL(0, "contained", &contained, N_("advance all branches contained in revision-range")), + OPT_STRING(0, "ref-action", &ref_action, + N_("mode"), + N_("control ref update behavior (update|print)")), OPT_END() }; @@ -330,9 +392,12 @@ int cmd_replay(int argc, usage_with_options(replay_usage, replay_options); } - if (advance_name_opt && contained) - die(_("options '%s' and '%s' cannot be used together"), - "--advance", "--contained"); + die_for_incompatible_opt2(!!advance_name_opt, "--advance", + contained, "--contained"); + + /* Parse ref action mode from command line or config */ + ref_mode = get_ref_action_mode(repo, ref_action); + advance_name = xstrdup_or_null(advance_name_opt); repo_init_revisions(repo, &revs, prefix); @@ -389,6 +454,24 @@ int cmd_replay(int argc, determine_replay_mode(repo, &revs.cmdline, onto_name, &advance_name, &onto, &update_refs); + /* Build reflog message */ + if (advance_name_opt) + strbuf_addf(&reflog_msg, "replay --advance %s", advance_name_opt); + else + strbuf_addf(&reflog_msg, "replay --onto %s", + oid_to_hex(&onto->object.oid)); + + /* Initialize ref transaction if using update mode */ + if (ref_mode == REF_ACTION_UPDATE) { + transaction = ref_store_transaction_begin(get_main_ref_store(repo), + 0, &transaction_err); + if (!transaction) { + ret = error(_("failed to begin ref transaction: %s"), + transaction_err.buf); + goto cleanup; + } + } + if (!onto) /* FIXME: Should handle replaying down to root commit */ die("Replaying down to root commit is not supported yet!"); @@ -434,10 +517,16 @@ int cmd_replay(int argc, if (decoration->type == DECORATION_REF_LOCAL && (contained || strset_contains(update_refs, decoration->name))) { - printf("update %s %s %s\n", - decoration->name, - oid_to_hex(&last_commit->object.oid), - oid_to_hex(&commit->object.oid)); + if (handle_ref_update(ref_mode, transaction, + decoration->name, + &last_commit->object.oid, + &commit->object.oid, + reflog_msg.buf, + &transaction_err) < 0) { + ret = error(_("failed to update ref '%s': %s"), + decoration->name, transaction_err.buf); + goto cleanup; + } } decoration = decoration->next; } @@ -445,10 +534,24 @@ int cmd_replay(int argc, /* In --advance mode, advance the target ref */ if (result.clean == 1 && advance_name) { - printf("update %s %s %s\n", - advance_name, - oid_to_hex(&last_commit->object.oid), - oid_to_hex(&onto->object.oid)); + if (handle_ref_update(ref_mode, transaction, advance_name, + &last_commit->object.oid, + &onto->object.oid, + reflog_msg.buf, + &transaction_err) < 0) { + ret = error(_("failed to update ref '%s': %s"), + advance_name, transaction_err.buf); + goto cleanup; + } + } + + /* Commit the ref transaction if we have one */ + if (transaction && result.clean == 1) { + if (ref_transaction_commit(transaction, &transaction_err)) { + ret = error(_("failed to commit ref transaction: %s"), + transaction_err.buf); + goto cleanup; + } } merge_finalize(&merge_opt, &result); @@ -460,6 +563,10 @@ int cmd_replay(int argc, ret = result.clean; cleanup: + if (transaction) + ref_transaction_free(transaction); + strbuf_release(&transaction_err); + strbuf_release(&reflog_msg); release_revisions(&revs); free(advance_name); diff --git a/builtin/repo.c b/builtin/repo.c index 9d4749f79b..0dd41b1778 100644 --- a/builtin/repo.c +++ b/builtin/repo.c @@ -15,8 +15,8 @@ #include "utf8.h" static const char *const repo_usage[] = { - "git repo info [--format=(keyvalue|nul)] [-z] [<key>...]", - "git repo structure [--format=(table|keyvalue|nul)]", + "git repo info [--format=(keyvalue|nul) | -z] [--all | <key>...]", + "git repo structure [--format=(table|keyvalue|nul) | -z]", NULL }; @@ -85,13 +85,29 @@ static get_value_fn *get_value_fn_for_key(const char *key) return found ? found->get_value : NULL; } +static void print_field(enum output_format format, const char *key, + const char *value) +{ + switch (format) { + case FORMAT_KEYVALUE: + printf("%s=", key); + quote_c_style(value, NULL, stdout, 0); + putchar('\n'); + break; + case FORMAT_NUL_TERMINATED: + printf("%s\n%s%c", key, value, '\0'); + break; + default: + BUG("not a valid output format: %d", format); + } +} + static int print_fields(int argc, const char **argv, struct repository *repo, enum output_format format) { int ret = 0; struct strbuf valbuf = STRBUF_INIT; - struct strbuf quotbuf = STRBUF_INIT; for (int i = 0; i < argc; i++) { get_value_fn *get_value; @@ -105,28 +121,31 @@ static int print_fields(int argc, const char **argv, } strbuf_reset(&valbuf); - strbuf_reset("buf); - get_value(repo, &valbuf); - - switch (format) { - case FORMAT_KEYVALUE: - quote_c_style(valbuf.buf, "buf, NULL, 0); - printf("%s=%s\n", key, quotbuf.buf); - break; - case FORMAT_NUL_TERMINATED: - printf("%s\n%s%c", key, valbuf.buf, '\0'); - break; - default: - BUG("not a valid output format: %d", format); - } + print_field(format, key, valbuf.buf); } strbuf_release(&valbuf); - strbuf_release("buf); return ret; } +static int print_all_fields(struct repository *repo, + enum output_format format) +{ + struct strbuf valbuf = STRBUF_INIT; + + for (size_t i = 0; i < ARRAY_SIZE(repo_info_fields); i++) { + const struct field *field = &repo_info_fields[i]; + + strbuf_reset(&valbuf); + field->get_value(repo, &valbuf); + print_field(format, field->key, valbuf.buf); + } + + strbuf_release(&valbuf); + return 0; +} + static int parse_format_cb(const struct option *opt, const char *arg, int unset UNUSED) { @@ -150,6 +169,7 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix, struct repository *repo) { enum output_format format = FORMAT_KEYVALUE; + int all_keys = 0; struct option options[] = { OPT_CALLBACK_F(0, "format", &format, N_("format"), N_("output format"), @@ -158,6 +178,7 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix, N_("synonym for --format=nul"), PARSE_OPT_NONEG | PARSE_OPT_NOARG, parse_format_cb), + OPT_BOOL(0, "all", &all_keys, N_("print all keys/values")), OPT_END() }; @@ -165,7 +186,13 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix, if (format != FORMAT_KEYVALUE && format != FORMAT_NUL_TERMINATED) die(_("unsupported output format")); - return print_fields(argc, argv, repo, format); + if (all_keys && argc) + die(_("--all and <key> cannot be used together")); + + if (all_keys) + return print_all_fields(repo, format); + else + return print_fields(argc, argv, repo, format); } struct ref_stats { @@ -292,14 +319,20 @@ static void stats_table_print_structure(const struct stats_table *table) int name_col_width = utf8_strwidth(name_col_title); int value_col_width = utf8_strwidth(value_col_title); struct string_list_item *item; + struct strbuf buf = STRBUF_INIT; if (table->name_col_width > name_col_width) name_col_width = table->name_col_width; if (table->value_col_width > value_col_width) value_col_width = table->value_col_width; - printf("| %-*s | %-*s |\n", name_col_width, name_col_title, - value_col_width, value_col_title); + strbuf_addstr(&buf, "| "); + strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width, name_col_title); + strbuf_addstr(&buf, " | "); + strbuf_utf8_align(&buf, ALIGN_LEFT, value_col_width, value_col_title); + strbuf_addstr(&buf, " |"); + printf("%s\n", buf.buf); + printf("| "); for (int i = 0; i < name_col_width; i++) putchar('-'); @@ -317,9 +350,16 @@ static void stats_table_print_structure(const struct stats_table *table) value = entry->value; } - printf("| %-*s | %*s |\n", name_col_width, item->string, - value_col_width, value); + strbuf_reset(&buf); + strbuf_addstr(&buf, "| "); + strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width, item->string); + strbuf_addstr(&buf, " | "); + strbuf_utf8_align(&buf, ALIGN_RIGHT, value_col_width, value); + strbuf_addstr(&buf, " |"); + printf("%s\n", buf.buf); } + + strbuf_release(&buf); } static void stats_table_clear(struct stats_table *table) @@ -366,16 +406,13 @@ struct count_references_data { struct progress *progress; }; -static int count_references(const char *refname, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, void *cb_data) +static int count_references(const struct reference *ref, void *cb_data) { struct count_references_data *data = cb_data; struct ref_stats *stats = data->stats; size_t ref_count; - switch (ref_kind_from_refname(refname)) { + switch (ref_kind_from_refname(ref->name)) { case FILTER_REFS_BRANCHES: stats->branches++; break; @@ -396,7 +433,7 @@ static int count_references(const char *refname, * While iterating through references for counting, also add OIDs in * preparation for the path walk. */ - add_pending_oid(data->revs, NULL, oid, 0); + add_pending_oid(data->revs, NULL, ref->oid, 0); ref_count = get_total_reference_count(stats); display_progress(data->progress, ref_count); @@ -492,6 +529,10 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix, OPT_CALLBACK_F(0, "format", &format, N_("format"), N_("output format"), PARSE_OPT_NONEG, parse_format_cb), + OPT_CALLBACK_F('z', NULL, &format, NULL, + N_("synonym for --format=nul"), + PARSE_OPT_NONEG | PARSE_OPT_NOARG, + parse_format_cb), OPT_BOOL(0, "progress", &show_progress, N_("show progress")), OPT_END() }; diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index 7b3711cf34..9032cc6327 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -217,19 +217,17 @@ static int show_default(void) return 0; } -static int show_reference(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int show_reference(const struct reference *ref, void *cb_data UNUSED) { - if (ref_excluded(&ref_excludes, refname)) + if (ref_excluded(&ref_excludes, ref->name)) return 0; - show_rev(NORMAL, oid, refname); + show_rev(NORMAL, ref->oid, ref->name); return 0; } -static int anti_reference(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int anti_reference(const struct reference *ref, void *cb_data UNUSED) { - show_rev(REVERSED, oid, refname); + show_rev(REVERSED, ref->oid, ref->name); return 0; } diff --git a/builtin/show-branch.c b/builtin/show-branch.c index 441babf2e3..10475a6b5e 100644 --- a/builtin/show-branch.c +++ b/builtin/show-branch.c @@ -413,34 +413,32 @@ static int append_ref(const char *refname, const struct object_id *oid, return 0; } -static int append_head_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int append_head_ref(const struct reference *ref, void *cb_data UNUSED) { struct object_id tmp; int ofs = 11; - if (!starts_with(refname, "refs/heads/")) + if (!starts_with(ref->name, "refs/heads/")) return 0; /* If both heads/foo and tags/foo exists, get_sha1 would * get confused. */ - if (repo_get_oid(the_repository, refname + ofs, &tmp) || !oideq(&tmp, oid)) + if (repo_get_oid(the_repository, ref->name + ofs, &tmp) || !oideq(&tmp, ref->oid)) ofs = 5; - return append_ref(refname + ofs, oid, 0); + return append_ref(ref->name + ofs, ref->oid, 0); } -static int append_remote_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data UNUSED) +static int append_remote_ref(const struct reference *ref, void *cb_data UNUSED) { struct object_id tmp; int ofs = 13; - if (!starts_with(refname, "refs/remotes/")) + if (!starts_with(ref->name, "refs/remotes/")) return 0; /* If both heads/foo and tags/foo exists, get_sha1 would * get confused. */ - if (repo_get_oid(the_repository, refname + ofs, &tmp) || !oideq(&tmp, oid)) + if (repo_get_oid(the_repository, ref->name + ofs, &tmp) || !oideq(&tmp, ref->oid)) ofs = 5; - return append_ref(refname + ofs, oid, 0); + return append_ref(ref->name + ofs, ref->oid, 0); } static int append_tag_ref(const char *refname, const struct object_id *oid, @@ -454,27 +452,26 @@ static int append_tag_ref(const char *refname, const struct object_id *oid, static const char *match_ref_pattern = NULL; static int match_ref_slash = 0; -static int append_matching_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag, void *cb_data) +static int append_matching_ref(const struct reference *ref, void *cb_data) { /* we want to allow pattern hold/<asterisk> to show all * branches under refs/heads/hold/, and v0.99.9? to show * refs/tags/v0.99.9a and friends. */ const char *tail; - int slash = count_slashes(refname); - for (tail = refname; *tail && match_ref_slash < slash; ) + int slash = count_slashes(ref->name); + for (tail = ref->name; *tail && match_ref_slash < slash; ) if (*tail++ == '/') slash--; if (!*tail) return 0; if (wildmatch(match_ref_pattern, tail, 0)) return 0; - if (starts_with(refname, "refs/heads/")) - return append_head_ref(refname, NULL, oid, flag, cb_data); - if (starts_with(refname, "refs/tags/")) - return append_tag_ref(refname, oid, flag, cb_data); - return append_ref(refname, oid, 0); + if (starts_with(ref->name, "refs/heads/")) + return append_head_ref(ref, cb_data); + if (starts_with(ref->name, "refs/tags/")) + return append_tag_ref(ref->name, ref->oid, ref->flags, cb_data); + return append_ref(ref->name, ref->oid, 0); } static void snarf_refs(int head, int remotes) diff --git a/builtin/show-ref.c b/builtin/show-ref.c index 0b6f9edf86..4d4984e4e0 100644 --- a/builtin/show-ref.c +++ b/builtin/show-ref.c @@ -31,31 +31,31 @@ struct show_one_options { }; static void show_one(const struct show_one_options *opts, - const char *refname, const struct object_id *oid) + const struct reference *ref) { const char *hex; struct object_id peeled; - if (!odb_has_object(the_repository->objects, oid, + if (!odb_has_object(the_repository->objects, ref->oid, HAS_OBJECT_RECHECK_PACKED | HAS_OBJECT_FETCH_PROMISOR)) - die("git show-ref: bad ref %s (%s)", refname, - oid_to_hex(oid)); + die("git show-ref: bad ref %s (%s)", ref->name, + oid_to_hex(ref->oid)); if (opts->quiet) return; - hex = repo_find_unique_abbrev(the_repository, oid, opts->abbrev); + hex = repo_find_unique_abbrev(the_repository, ref->oid, opts->abbrev); if (opts->hash_only) printf("%s\n", hex); else - printf("%s %s\n", hex, refname); + printf("%s %s\n", hex, ref->name); if (!opts->deref_tags) return; - if (!peel_iterated_oid(the_repository, oid, &peeled)) { + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) { hex = repo_find_unique_abbrev(the_repository, &peeled, opts->abbrev); - printf("%s %s^{}\n", hex, refname); + printf("%s %s^{}\n", hex, ref->name); } } @@ -66,26 +66,25 @@ struct show_ref_data { int show_head; }; -static int show_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cbdata) +static int show_ref(const struct reference *ref, void *cbdata) { struct show_ref_data *data = cbdata; - if (data->show_head && !strcmp(refname, "HEAD")) + if (data->show_head && !strcmp(ref->name, "HEAD")) goto match; if (data->patterns) { - int reflen = strlen(refname); + int reflen = strlen(ref->name); const char **p = data->patterns, *m; while ((m = *p++) != NULL) { int len = strlen(m); if (len > reflen) continue; - if (memcmp(m, refname + reflen - len, len)) + if (memcmp(m, ref->name + reflen - len, len)) continue; if (len == reflen) goto match; - if (refname[reflen - len - 1] == '/') + if (ref->name[reflen - len - 1] == '/') goto match; } return 0; @@ -94,18 +93,15 @@ static int show_ref(const char *refname, const char *referent UNUSED, const stru match: data->found_match++; - show_one(data->show_one_opts, refname, oid); + show_one(data->show_one_opts, ref); return 0; } -static int add_existing(const char *refname, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flag UNUSED, void *cbdata) +static int add_existing(const struct reference *ref, void *cbdata) { struct string_list *list = (struct string_list *)cbdata; - string_list_insert(list, refname); + string_list_insert(list, ref->name); return 0; } @@ -179,12 +175,18 @@ static int cmd_show_ref__verify(const struct show_one_options *show_one_opts, if ((starts_with(*refs, "refs/") || refname_is_safe(*refs)) && !refs_read_ref(get_main_ref_store(the_repository), *refs, &oid)) { - show_one(show_one_opts, *refs, &oid); - } - else if (!show_one_opts->quiet) + struct reference ref = { + .name = *refs, + .oid = &oid, + }; + + show_one(show_one_opts, &ref); + } else if (!show_one_opts->quiet) { die("'%s' - not a valid ref", *refs); - else + } else { return 1; + } + refs++; } diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c index fcd73abe53..35f6cf735e 100644 --- a/builtin/submodule--helper.c +++ b/builtin/submodule--helper.c @@ -593,16 +593,12 @@ static void print_status(unsigned int flags, char state, const char *path, printf("\n"); } -static int handle_submodule_head_ref(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *cb_data) +static int handle_submodule_head_ref(const struct reference *ref, void *cb_data) { struct object_id *output = cb_data; - if (oid) - oidcpy(output, oid); + if (ref->oid) + oidcpy(output, ref->oid); return 0; } diff --git a/builtin/tag.c b/builtin/tag.c index f0665af3ac..01eba90c5c 100644 --- a/builtin/tag.c +++ b/builtin/tag.c @@ -153,7 +153,7 @@ static int verify_tag(const char *name, const char *ref UNUSED, return -1; if (format->format) - pretty_print_ref(name, oid, format); + pretty_print_ref(name, oid, NULL, format); return 0; } diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c index ef79e43715..6fc64e9e4b 100644 --- a/builtin/unpack-objects.c +++ b/builtin/unpack-objects.c @@ -363,7 +363,7 @@ struct input_zstream_data { int status; }; -static const void *feed_input_zstream(struct input_stream *in_stream, +static const void *feed_input_zstream(struct odb_write_stream *in_stream, unsigned long *readlen) { struct input_zstream_data *data = in_stream->data; @@ -393,7 +393,7 @@ static void stream_blob(unsigned long size, unsigned nr) { git_zstream zstream = { 0 }; struct input_zstream_data data = { 0 }; - struct input_stream in_stream = { + struct odb_write_stream in_stream = { .read = feed_input_zstream, .data = &data, }; @@ -402,8 +402,7 @@ static void stream_blob(unsigned long size, unsigned nr) data.zstream = &zstream; git_inflate_init(&zstream); - if (stream_loose_object(the_repository->objects->sources, - &in_stream, size, &info->oid)) + if (odb_write_object_stream(the_repository->objects, &in_stream, size, &info->oid)) die(_("failed to write object in stream")); if (data.status != Z_STREAM_END) diff --git a/builtin/upload-archive.c b/builtin/upload-archive.c index 97d7c9522f..25312bb2a5 100644 --- a/builtin/upload-archive.c +++ b/builtin/upload-archive.c @@ -4,8 +4,8 @@ #define USE_THE_REPOSITORY_VARIABLE #include "builtin.h" #include "archive.h" -#include "path.h" #include "pkt-line.h" +#include "setup.h" #include "sideband.h" #include "run-command.h" #include "strvec.h" diff --git a/builtin/upload-pack.c b/builtin/upload-pack.c index c2bbc035ab..30498fafea 100644 --- a/builtin/upload-pack.c +++ b/builtin/upload-pack.c @@ -5,11 +5,11 @@ #include "gettext.h" #include "pkt-line.h" #include "parse-options.h" -#include "path.h" #include "protocol.h" #include "replace-object.h" #include "upload-pack.h" #include "serve.h" +#include "setup.h" #include "commit.h" #include "environment.h" diff --git a/builtin/verify-tag.c b/builtin/verify-tag.c index cd6bc11095..558121eaa1 100644 --- a/builtin/verify-tag.c +++ b/builtin/verify-tag.c @@ -67,7 +67,7 @@ int cmd_verify_tag(int argc, } if (format.format) - pretty_print_ref(name, &oid, &format); + pretty_print_ref(name, &oid, NULL, &format); } return had_error; } diff --git a/builtin/worktree.c b/builtin/worktree.c index 812774a5ca..fbdaf2eb2e 100644 --- a/builtin/worktree.c +++ b/builtin/worktree.c @@ -635,11 +635,7 @@ static void print_preparing_worktree_line(int detach, * * Returns 0 on failure and non-zero on success. */ -static int first_valid_ref(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, - void *cb_data UNUSED) +static int first_valid_ref(const struct reference *ref UNUSED, void *cb_data UNUSED) { return 1; } @@ -979,14 +975,18 @@ static void show_worktree_porcelain(struct worktree *wt, int line_terminator) fputc(line_terminator, stdout); } -static void show_worktree(struct worktree *wt, int path_maxlen, int abbrev_len) +struct worktree_display { + char *path; + int width; +}; + +static void show_worktree(struct worktree *wt, struct worktree_display *display, + int path_maxwidth, int abbrev_len) { struct strbuf sb = STRBUF_INIT; - int cur_path_len = strlen(wt->path); - int path_adj = cur_path_len - utf8_strwidth(wt->path); const char *reason; - strbuf_addf(&sb, "%-*s ", 1 + path_maxlen + path_adj, wt->path); + strbuf_addf(&sb, "%s%*s", display->path, 1 + path_maxwidth - display->width, ""); if (wt->is_bare) strbuf_addstr(&sb, "(bare)"); else { @@ -1020,20 +1020,27 @@ static void show_worktree(struct worktree *wt, int path_maxlen, int abbrev_len) strbuf_release(&sb); } -static void measure_widths(struct worktree **wt, int *abbrev, int *maxlen) +static void measure_widths(struct worktree **wt, int *abbrev, + struct worktree_display **d, int *maxwidth) { - int i; + int i, display_alloc = 0; + struct worktree_display *display = NULL; + struct strbuf buf = STRBUF_INIT; for (i = 0; wt[i]; i++) { int sha1_len; - int path_len = strlen(wt[i]->path); + ALLOC_GROW(display, i + 1, display_alloc); + quote_path(wt[i]->path, NULL, &buf, 0); + display[i].width = utf8_strwidth(buf.buf); + display[i].path = strbuf_detach(&buf, NULL); - if (path_len > *maxlen) - *maxlen = path_len; + if (display[i].width > *maxwidth) + *maxwidth = display[i].width; sha1_len = strlen(repo_find_unique_abbrev(the_repository, &wt[i]->head_oid, *abbrev)); if (sha1_len > *abbrev) *abbrev = sha1_len; } + *d = display; } static int pathcmp(const void *a_, const void *b_) @@ -1079,21 +1086,27 @@ static int list(int ac, const char **av, const char *prefix, die(_("the option '%s' requires '%s'"), "-z", "--porcelain"); else { struct worktree **worktrees = get_worktrees(); - int path_maxlen = 0, abbrev = DEFAULT_ABBREV, i; + int path_maxwidth = 0, abbrev = DEFAULT_ABBREV, i; + struct worktree_display *display = NULL; /* sort worktrees by path but keep main worktree at top */ pathsort(worktrees + 1); if (!porcelain) - measure_widths(worktrees, &abbrev, &path_maxlen); + measure_widths(worktrees, &abbrev, + &display, &path_maxwidth); for (i = 0; worktrees[i]; i++) { if (porcelain) show_worktree_porcelain(worktrees[i], line_terminator); else - show_worktree(worktrees[i], path_maxlen, abbrev); + show_worktree(worktrees[i], + &display[i], path_maxwidth, abbrev); } + for (i = 0; display && worktrees[i]; i++) + free(display[i].path); + free(display); free_worktrees(worktrees); } return 0; diff --git a/cache-tree.c b/cache-tree.c index 2aba47060e..2d8947b518 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -548,12 +548,41 @@ void cache_tree_write(struct strbuf *sb, struct cache_tree *root) trace2_region_leave("cache_tree", "write", the_repository); } +static int parse_int(const char **ptr, unsigned long *len_p, int *out) +{ + const char *s = *ptr; + unsigned long len = *len_p; + int ret = 0; + int sign = 1; + + while (len && *s == '-') { + sign *= -1; + s++; + len--; + } + + while (len) { + if (!isdigit(*s)) + break; + ret *= 10; + ret += *s - '0'; + s++; + len--; + } + + if (s == *ptr) + return -1; + + *ptr = s; + *len_p = len; + *out = sign * ret; + return 0; +} + static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) { const char *buf = *buffer; unsigned long size = *size_p; - const char *cp; - char *ep; struct cache_tree *it; int i, subtree_nr; const unsigned rawsz = the_hash_algo->rawsz; @@ -569,19 +598,14 @@ static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) buf++; size--; it = cache_tree(); - cp = buf; - it->entry_count = strtol(cp, &ep, 10); - if (cp == ep) + if (parse_int(&buf, &size, &it->entry_count) < 0) goto free_return; - cp = ep; - subtree_nr = strtol(cp, &ep, 10); - if (cp == ep) + if (!size || *buf != ' ') goto free_return; - while (size && *buf && *buf != '\n') { - size--; - buf++; - } - if (!size) + buf++; size--; + if (parse_int(&buf, &size, &subtree_nr) < 0) + goto free_return; + if (!size || *buf != '\n') goto free_return; buf++; size--; if (0 <= it->entry_count) { diff --git a/chdir-notify.c b/chdir-notify.c index 0d7bc04607..f8bfe3cbef 100644 --- a/chdir-notify.c +++ b/chdir-notify.c @@ -25,6 +25,24 @@ void chdir_notify_register(const char *name, list_add_tail(&e->list, &chdir_notify_entries); } +void chdir_notify_unregister(const char *name, chdir_notify_callback cb, + void *data) +{ + struct list_head *pos, *p; + + list_for_each_safe(pos, p, &chdir_notify_entries) { + struct chdir_notify_entry *e = + list_entry(pos, struct chdir_notify_entry, list); + + if (e->cb != cb || e->data != data || !e->name != !name || + (e->name && strcmp(e->name, name))) + continue; + + list_del(pos); + free(e); + } +} + static void reparent_cb(const char *name, const char *old_cwd, const char *new_cwd, diff --git a/chdir-notify.h b/chdir-notify.h index 366e4c1ee9..81eb69d846 100644 --- a/chdir-notify.h +++ b/chdir-notify.h @@ -41,6 +41,8 @@ typedef void (*chdir_notify_callback)(const char *name, const char *new_cwd, void *data); void chdir_notify_register(const char *name, chdir_notify_callback cb, void *data); +void chdir_notify_unregister(const char *name, chdir_notify_callback cb, + void *data); void chdir_notify_reparent(const char *name, char **path); /* diff --git a/ci/run-test-slice-meson.sh b/ci/run-test-slice-meson.sh new file mode 100755 index 0000000000..961c94fba0 --- /dev/null +++ b/ci/run-test-slice-meson.sh @@ -0,0 +1,13 @@ +#!/bin/sh + +# We must load the build options so we know where to find +# things like TEST_OUTPUT_DIRECTORY. This has to come before +# loading lib.sh, though, because it may clobber some CI lib +# variables like our custom GIT_TEST_OPTS. +. "$1"/GIT-BUILD-OPTIONS +. ${0%/*}/lib.sh + +group "Run tests" \ + meson test -C "$1" --no-rebuild --print-errorlogs \ + --test-args="$GIT_TEST_OPTS" --slice "$((1+$2))/$3" || +handle_failed_tests diff --git a/commit-graph.c b/commit-graph.c index 474454db73..80be2ff2c3 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1851,18 +1851,16 @@ struct refs_cb_data { struct progress *progress; }; -static int add_ref_to_set(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, void *cb_data) +static int add_ref_to_set(const struct reference *ref, void *cb_data) { + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; struct refs_cb_data *data = (struct refs_cb_data *)cb_data; - if (!peel_iterated_oid(data->repo, oid, &peeled)) - oid = &peeled; - if (odb_read_object_info(data->repo->objects, oid, NULL) == OBJ_COMMIT) - oidset_insert(data->commits, oid); + if (!reference_get_peeled_oid(data->repo, ref, &peeled)) + maybe_peeled = &peeled; + if (odb_read_object_info(data->repo->objects, maybe_peeled, NULL) == OBJ_COMMIT) + oidset_insert(data->commits, maybe_peeled); display_progress(data->progress, oidset_size(data->commits)); @@ -1315,7 +1315,8 @@ free_return: free(buf); } -int check_commit_signature(const struct commit *commit, struct signature_check *sigc) +int verify_commit_buffer(const char *buffer, size_t size, + struct signature_check *sigc) { struct strbuf payload = STRBUF_INIT; struct strbuf signature = STRBUF_INIT; @@ -1323,7 +1324,8 @@ int check_commit_signature(const struct commit *commit, struct signature_check * sigc->result = 'N'; - if (parse_signed_commit(commit, &payload, &signature, the_hash_algo) <= 0) + if (parse_buffer_signed_by_header(buffer, size, &payload, + &signature, the_hash_algo) <= 0) goto out; sigc->payload_type = SIGNATURE_PAYLOAD_COMMIT; @@ -1337,6 +1339,17 @@ int check_commit_signature(const struct commit *commit, struct signature_check * return ret; } +int check_commit_signature(const struct commit *commit, struct signature_check *sigc) +{ + unsigned long size; + const char *buffer = repo_get_commit_buffer(the_repository, commit, &size); + int ret = verify_commit_buffer(buffer, size, sigc); + + repo_unuse_commit_buffer(the_repository, commit, buffer); + + return ret; +} + void verify_merge_signature(struct commit *commit, int verbosity, int check_trust) { @@ -333,6 +333,13 @@ int remove_signature(struct strbuf *buf); */ int check_commit_signature(const struct commit *commit, struct signature_check *sigc); +/* + * Same as check_commit_signature() but accepts a commit buffer and + * its size, instead of a `struct commit *`. + */ +int verify_commit_buffer(const char *buffer, size_t size, + struct signature_check *sigc); + /* record author-date for each commit object */ struct author_date_slab; void record_author_date(struct author_date_slab *author_date, diff --git a/compat/mingw-posix.h b/compat/mingw-posix.h index 631a208684..0939feff27 100644 --- a/compat/mingw-posix.h +++ b/compat/mingw-posix.h @@ -241,9 +241,6 @@ int mingw_chdir(const char *dirname); int mingw_chmod(const char *filename, int mode); #define chmod mingw_chmod -char *mingw_mktemp(char *template); -#define mktemp mingw_mktemp - char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd diff --git a/compat/mingw.c b/compat/mingw.c index 736a07a028..939f938fe2 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -491,8 +491,10 @@ static int mingw_open_append(wchar_t const *wfilename, int oflags, ...) DWORD create = (oflags & O_CREAT) ? OPEN_ALWAYS : OPEN_EXISTING; /* only these flags are supported */ - if ((oflags & ~O_CREAT) != (O_WRONLY | O_APPEND)) - return errno = ENOSYS, -1; + if ((oflags & ~O_CREAT) != (O_WRONLY | O_APPEND)) { + errno = ENOSYS; + return -1; + } /* * FILE_SHARE_WRITE is required to permit child processes @@ -1162,18 +1164,6 @@ unsigned int sleep (unsigned int seconds) return 0; } -char *mingw_mktemp(char *template) -{ - wchar_t wtemplate[MAX_PATH]; - if (xutftowcs_path(wtemplate, template) < 0) - return NULL; - if (!_wmktemp(wtemplate)) - return NULL; - if (xwcstoutf(template, wtemplate, strlen(template) + 1) < 0) - return NULL; - return template; -} - int mkstemp(char *template) { return git_mkstemp_mode(template, 0600); @@ -2450,12 +2440,14 @@ static int start_timer_thread(void) timer_event = CreateEvent(NULL, FALSE, FALSE, NULL); if (timer_event) { timer_thread = (HANDLE) _beginthreadex(NULL, 0, ticktack, NULL, 0, NULL); - if (!timer_thread ) - return errno = ENOMEM, - error("cannot start timer thread"); - } else - return errno = ENOMEM, - error("cannot allocate resources for timer"); + if (!timer_thread ) { + errno = ENOMEM; + return error("cannot start timer thread"); + } + } else { + errno = ENOMEM; + return error("cannot allocate resources for timer"); + } return 0; } @@ -2488,13 +2480,15 @@ int setitimer(int type UNUSED, struct itimerval *in, struct itimerval *out) static const struct timeval zero; static int atexit_done; - if (out) - return errno = EINVAL, - error("setitimer param 3 != NULL not implemented"); + if (out) { + errno = EINVAL; + return error("setitimer param 3 != NULL not implemented"); + } if (!is_timeval_eq(&in->it_interval, &zero) && - !is_timeval_eq(&in->it_interval, &in->it_value)) - return errno = EINVAL, - error("setitimer: it_interval must be zero or eq it_value"); + !is_timeval_eq(&in->it_interval, &in->it_value)) { + errno = EINVAL; + return error("setitimer: it_interval must be zero or eq it_value"); + } if (timer_thread) stop_timer_thread(); @@ -2516,12 +2510,14 @@ int sigaction(int sig, struct sigaction *in, struct sigaction *out) { if (sig == SIGCHLD) return -1; - else if (sig != SIGALRM) - return errno = EINVAL, - error("sigaction only implemented for SIGALRM"); - if (out) - return errno = EINVAL, - error("sigaction: param 3 != NULL not implemented"); + else if (sig != SIGALRM) { + errno = EINVAL; + return error("sigaction only implemented for SIGALRM"); + } + if (out) { + errno = EINVAL; + return error("sigaction: param 3 != NULL not implemented"); + } timer_fn = in->sa_handler; return 0; diff --git a/compat/mkdtemp.c b/compat/mkdtemp.c deleted file mode 100644 index 1136119592..0000000000 --- a/compat/mkdtemp.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "../git-compat-util.h" - -char *gitmkdtemp(char *template) -{ - if (!*mktemp(template) || mkdir(template, 0700)) - return NULL; - return template; -} diff --git a/compat/mmap.c b/compat/mmap.c index 2fe1c7732e..1a118711f7 100644 --- a/compat/mmap.c +++ b/compat/mmap.c @@ -38,7 +38,7 @@ void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t of return start; } -int git_munmap(void *start, size_t length) +int git_munmap(void *start, size_t length UNUSED) { free(start); return 0; diff --git a/compat/posix.h b/compat/posix.h index 067a00f33b..245386fa4a 100644 --- a/compat/posix.h +++ b/compat/posix.h @@ -329,8 +329,7 @@ int gitsetenv(const char *, const char *, int); #endif #ifdef NO_MKDTEMP -#define mkdtemp gitmkdtemp -char *gitmkdtemp(char *); +#define mkdtemp git_mkdtemp #endif #ifdef NO_UNSETENV diff --git a/compat/win32/pthread.c b/compat/win32/pthread.c index 58980a529c..7e93146963 100644 --- a/compat/win32/pthread.c +++ b/compat/win32/pthread.c @@ -59,3 +59,10 @@ pthread_t pthread_self(void) t.tid = GetCurrentThreadId(); return t; } + +int pthread_cond_wait(pthread_cond_t *cond, pthread_mutex_t *mutex) +{ + if (SleepConditionVariableCS(cond, mutex, INFINITE) == 0) + return err_win_to_posix(GetLastError()); + return 0; +} diff --git a/compat/win32/pthread.h b/compat/win32/pthread.h index e2b5c4f64c..ccacc5a53b 100644 --- a/compat/win32/pthread.h +++ b/compat/win32/pthread.h @@ -34,9 +34,8 @@ typedef int pthread_mutexattr_t; #define pthread_cond_t CONDITION_VARIABLE -#define pthread_cond_init(a,b) InitializeConditionVariable((a)) +#define pthread_cond_init(a,b) return_0((InitializeConditionVariable((a)), 0)) #define pthread_cond_destroy(a) do {} while (0) -#define pthread_cond_wait(a,b) return_0(SleepConditionVariableCS((a), (b), INFINITE)) #define pthread_cond_signal WakeConditionVariable #define pthread_cond_broadcast WakeAllConditionVariable @@ -64,6 +63,8 @@ int win32_pthread_join(pthread_t *thread, void **value_ptr); #define pthread_equal(t1, t2) ((t1).tid == (t2).tid) pthread_t pthread_self(void); +int pthread_cond_wait(pthread_cond_t *cond, pthread_mutex_t *mutex); + static inline void NORETURN pthread_exit(void *ret) { _endthreadex((unsigned)(uintptr_t)ret); @@ -1291,6 +1291,7 @@ int git_config_pathname(char **dest, const char *var, const char *value) if (is_optional && is_missing_file(path)) { free(path); + *dest = NULL; return 0; } @@ -1953,7 +1954,7 @@ int git_configset_get_maybe_bool(struct config_set *set, const char *key, int *d return 1; } -int git_configset_get_pathname(struct config_set *set, const char *key, char **dest) +static int git_configset_get_pathname(struct config_set *set, const char *key, char **dest) { const char *value; if (!git_configset_get_value(set, key, &value, NULL)) @@ -564,7 +564,6 @@ int git_configset_get_ulong(struct config_set *cs, const char *key, unsigned lon int git_configset_get_bool(struct config_set *cs, const char *key, int *dest); int git_configset_get_bool_or_int(struct config_set *cs, const char *key, int *is_bool, int *dest); int git_configset_get_maybe_bool(struct config_set *cs, const char *key, int *dest); -int git_configset_get_pathname(struct config_set *cs, const char *key, char **dest); /** * Run only the discover part of the repo_config_get_*() functions @@ -240,6 +240,8 @@ static void process_capabilities(struct packet_reader *reader, size_t *linelen) size_t nul_location = strlen(line); if (nul_location == *linelen) return; + + free(server_capabilities_v1); server_capabilities_v1 = xstrdup(line + nul_location + 1); *linelen = nul_location; diff --git a/contrib/buildsystems/CMakeLists.txt b/contrib/buildsystems/CMakeLists.txt index edb0fc04ad..28877feb9d 100644 --- a/contrib/buildsystems/CMakeLists.txt +++ b/contrib/buildsystems/CMakeLists.txt @@ -411,10 +411,6 @@ if(NOT HAVE_SETENV) list(APPEND compat_SOURCES compat/setenv.c) endif() -if(NOT HAVE_MKDTEMP) - list(APPEND compat_SOURCES compat/mkdtemp.c) -endif() - if(NOT HAVE_PREAD) list(APPEND compat_SOURCES compat/pread.c) endif() @@ -679,18 +675,6 @@ list(APPEND libgit_SOURCES "${CMAKE_BINARY_DIR}/version-def.h") add_library(libgit ${libgit_SOURCES} ${compat_SOURCES}) -#libxdiff -parse_makefile_for_sources(libxdiff_SOURCES ${CMAKE_SOURCE_DIR}/Makefile "XDIFF_OBJS") - -list(TRANSFORM libxdiff_SOURCES PREPEND "${CMAKE_SOURCE_DIR}/") -add_library(xdiff STATIC ${libxdiff_SOURCES}) - -#reftable -parse_makefile_for_sources(reftable_SOURCES ${CMAKE_SOURCE_DIR}/Makefile "REFTABLE_OBJS") - -list(TRANSFORM reftable_SOURCES PREPEND "${CMAKE_SOURCE_DIR}/") -add_library(reftable STATIC ${reftable_SOURCES}) - if(WIN32) add_custom_command(OUTPUT ${CMAKE_BINARY_DIR}/git.rc COMMAND "${SH_EXE}" "${CMAKE_SOURCE_DIR}/GIT-VERSION-GEN" @@ -720,7 +704,7 @@ endif() #link all required libraries to common-main add_library(common-main OBJECT ${CMAKE_SOURCE_DIR}/common-main.c) -target_link_libraries(common-main libgit xdiff reftable ${ZLIB_LIBRARIES}) +target_link_libraries(common-main libgit ${ZLIB_LIBRARIES}) if(Intl_FOUND) target_link_libraries(common-main ${Intl_LIBRARIES}) endif() diff --git a/contrib/credential/osxkeychain/Makefile b/contrib/credential/osxkeychain/Makefile index 9680717abe..c68445b82d 100644 --- a/contrib/credential/osxkeychain/Makefile +++ b/contrib/credential/osxkeychain/Makefile @@ -1,21 +1,55 @@ # The default target of this Makefile is... all:: git-credential-osxkeychain +include ../../../config.mak.uname -include ../../../config.mak.autogen -include ../../../config.mak +ifdef ZLIB_NG + BASIC_CFLAGS += -DHAVE_ZLIB_NG + ifdef ZLIB_NG_PATH + BASIC_CFLAGS += -I$(ZLIB_NG_PATH)/include + EXTLIBS += $(call libpath_template,$(ZLIB_NG_PATH)/$(lib)) + endif + EXTLIBS += -lz-ng +else + ifdef ZLIB_PATH + BASIC_CFLAGS += -I$(ZLIB_PATH)/include + EXTLIBS += $(call libpath_template,$(ZLIB_PATH)/$(lib)) + endif + EXTLIBS += -lz +endif +ifndef NO_ICONV + ifdef NEEDS_LIBICONV + ifdef ICONVDIR + BASIC_CFLAGS += -I$(ICONVDIR)/include + ICONV_LINK = $(call libpath_template,$(ICONVDIR)/$(lib)) + else + ICONV_LINK = + endif + ifdef NEEDS_LIBINTL_BEFORE_LIBICONV + ICONV_LINK += -lintl + endif + EXTLIBS += $(ICONV_LINK) -liconv + endif +endif +ifndef LIBC_CONTAINS_LIBINTL + EXTLIBS += -lintl +endif + prefix ?= /usr/local gitexecdir ?= $(prefix)/libexec/git-core CC ?= gcc -CFLAGS ?= -g -O2 -Wall +CFLAGS ?= -g -O2 -Wall -I../../.. $(BASIC_CFLAGS) +LDFLAGS ?= $(BASIC_LDFLAGS) $(EXTLIBS) INSTALL ?= install RM ?= rm -f %.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) -o $@ -c $< -git-credential-osxkeychain: git-credential-osxkeychain.o +git-credential-osxkeychain: git-credential-osxkeychain.o ../../../libgit.a $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) \ -framework Security -framework CoreFoundation @@ -23,6 +57,9 @@ install: git-credential-osxkeychain $(INSTALL) -d -m 755 $(DESTDIR)$(gitexecdir) $(INSTALL) -m 755 $< $(DESTDIR)$(gitexecdir) +../../../libgit.a: + cd ../../..; make libgit.a + clean: $(RM) git-credential-osxkeychain git-credential-osxkeychain.o diff --git a/contrib/credential/osxkeychain/git-credential-osxkeychain.c b/contrib/credential/osxkeychain/git-credential-osxkeychain.c index 611c9798b3..b180267034 100644 --- a/contrib/credential/osxkeychain/git-credential-osxkeychain.c +++ b/contrib/credential/osxkeychain/git-credential-osxkeychain.c @@ -2,6 +2,9 @@ #include <string.h> #include <stdlib.h> #include <Security/Security.h> +#include "git-compat-util.h" +#include "strbuf.h" +#include "wrapper.h" #define ENCODING kCFStringEncodingUTF8 static CFStringRef protocol; /* Stores constant strings - not memory managed */ @@ -12,7 +15,7 @@ static CFStringRef username; static CFDataRef password; static CFDataRef password_expiry_utc; static CFDataRef oauth_refresh_token; -static int state_seen; +static char *state_seen; static void clear_credential(void) { @@ -48,27 +51,6 @@ static void clear_credential(void) #define STRING_WITH_LENGTH(s) s, sizeof(s) - 1 -__attribute__((format (printf, 1, 2), __noreturn__)) -static void die(const char *err, ...) -{ - char msg[4096]; - va_list params; - va_start(params, err); - vsnprintf(msg, sizeof(msg), err, params); - fprintf(stderr, "%s\n", msg); - va_end(params); - clear_credential(); - exit(1); -} - -static void *xmalloc(size_t len) -{ - void *ret = malloc(len); - if (!ret) - die("Out of memory"); - return ret; -} - static CFDictionaryRef create_dictionary(CFAllocatorRef allocator, ...) { va_list args; @@ -112,6 +94,66 @@ static void write_item(const char *what, const char *buf, size_t len) putchar('\n'); } +static void write_item_strbuf(struct strbuf *sb, const char *what, const char *buf, int n) +{ + char s[32]; + + xsnprintf(s, sizeof(s), "__%s=", what); + strbuf_add(sb, s, strlen(s)); + strbuf_add(sb, buf, n); +} + +static void write_item_strbuf_cfstring(struct strbuf *sb, const char *what, CFStringRef ref) +{ + char *buf; + int len; + + if (!ref) + return; + len = CFStringGetMaximumSizeForEncoding(CFStringGetLength(ref), ENCODING) + 1; + buf = xmalloc(len); + if (CFStringGetCString(ref, buf, len, ENCODING)) + write_item_strbuf(sb, what, buf, strlen(buf)); + free(buf); +} + +static void write_item_strbuf_cfnumber(struct strbuf *sb, const char *what, CFNumberRef ref) +{ + short n; + char buf[32]; + + if (!ref) + return; + if (!CFNumberGetValue(ref, kCFNumberShortType, &n)) + return; + xsnprintf(buf, sizeof(buf), "%d", n); + write_item_strbuf(sb, what, buf, strlen(buf)); +} + +static void write_item_strbuf_cfdata(struct strbuf *sb, const char *what, CFDataRef ref) +{ + char *buf; + int len; + + if (!ref) + return; + buf = (char *)CFDataGetBytePtr(ref); + if (!buf || strlen(buf) == 0) + return; + len = CFDataGetLength(ref); + write_item_strbuf(sb, what, buf, len); +} + +static void encode_state_seen(struct strbuf *sb) +{ + strbuf_add(sb, "osxkeychain:seen=", strlen("osxkeychain:seen=")); + write_item_strbuf_cfstring(sb, "host", host); + write_item_strbuf_cfnumber(sb, "port", port); + write_item_strbuf_cfstring(sb, "path", path); + write_item_strbuf_cfstring(sb, "username", username); + write_item_strbuf_cfdata(sb, "password", password); +} + static void find_username_in_item(CFDictionaryRef item) { CFStringRef account_ref; @@ -124,6 +166,7 @@ static void find_username_in_item(CFDictionaryRef item) write_item("username", "", 0); return; } + username = CFStringCreateCopy(kCFAllocatorDefault, account_ref); username_buf = (char *)CFStringGetCStringPtr(account_ref, ENCODING); if (username_buf) @@ -163,6 +206,7 @@ static OSStatus find_internet_password(void) } data = CFDictionaryGetValue(item, kSecValueData); + password = CFDataCreateCopy(kCFAllocatorDefault, data); write_item("password", (const char *)CFDataGetBytePtr(data), @@ -173,7 +217,14 @@ static OSStatus find_internet_password(void) CFRelease(item); write_item("capability[]", "state", strlen("state")); - write_item("state[]", "osxkeychain:seen=1", strlen("osxkeychain:seen=1")); + { + struct strbuf sb; + + strbuf_init(&sb, 1024); + encode_state_seen(&sb); + write_item("state[]", sb.buf, strlen(sb.buf)); + strbuf_release(&sb); + } out: CFRelease(attrs); @@ -288,13 +339,22 @@ static OSStatus add_internet_password(void) CFDictionaryRef attrs; OSStatus result; - if (state_seen) - return errSecSuccess; - /* Only store complete credentials */ if (!protocol || !host || !username || !password) return -1; + if (state_seen) { + struct strbuf sb; + + strbuf_init(&sb, 1024); + encode_state_seen(&sb); + if (!strcmp(state_seen, sb.buf)) { + strbuf_release(&sb); + return errSecSuccess; + } + strbuf_release(&sb); + } + data = CFDataCreateMutableCopy(kCFAllocatorDefault, 0, password); if (password_expiry_utc) { CFDataAppendBytes(data, @@ -403,8 +463,9 @@ static void read_credential(void) (UInt8 *)v, strlen(v)); else if (!strcmp(buf, "state[]")) { - if (!strcmp(v, "osxkeychain:seen=1")) - state_seen = 1; + int len = strlen("osxkeychain:seen="); + if (!strncmp(v, "osxkeychain:seen=", len)) + state_seen = xstrdup(v); } /* * Ignore other lines; we don't know what they mean, but @@ -443,5 +504,8 @@ int main(int argc, const char **argv) clear_credential(); + if (state_seen) + free(state_seen); + return 0; } diff --git a/contrib/credential/osxkeychain/meson.build b/contrib/credential/osxkeychain/meson.build index 3c7677f736..ec91d0c14b 100644 --- a/contrib/credential/osxkeychain/meson.build +++ b/contrib/credential/osxkeychain/meson.build @@ -1,6 +1,7 @@ executable('git-credential-osxkeychain', sources: 'git-credential-osxkeychain.c', dependencies: [ + libgit, dependency('CoreFoundation'), dependency('Security'), ], diff --git a/contrib/credential/wincred/git-credential-wincred.c b/contrib/credential/wincred/git-credential-wincred.c index 5683846b4b..73c2b9b72a 100644 --- a/contrib/credential/wincred/git-credential-wincred.c +++ b/contrib/credential/wincred/git-credential-wincred.c @@ -165,7 +165,7 @@ static void get_credential(void) write_item("username", creds[i]->UserName, creds[i]->UserName ? wcslen(creds[i]->UserName) : 0); if (creds[i]->CredentialBlobSize > 0) { - secret = xmalloc(creds[i]->CredentialBlobSize); + secret = xmalloc(creds[i]->CredentialBlobSize + sizeof(WCHAR)); wcsncpy_s(secret, creds[i]->CredentialBlobSize, (LPCWSTR)creds[i]->CredentialBlob, creds[i]->CredentialBlobSize / sizeof(WCHAR)); line = wcstok_s(secret, L"\r\n", &remaining_lines); write_item("password", line, line ? wcslen(line) : 0); diff --git a/delta-islands.c b/delta-islands.c index 36c94799d6..7cfebc4162 100644 --- a/delta-islands.c +++ b/delta-islands.c @@ -390,8 +390,7 @@ static void add_ref_to_island(kh_str_t *remote_islands, const char *island_name, rl->hash += sha_core; } -static int find_island_for_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags UNUSED, void *cb) +static int find_island_for_ref(const struct reference *ref, void *cb) { struct island_load_data *ild = cb; @@ -406,7 +405,7 @@ static int find_island_for_ref(const char *refname, const char *referent UNUSED, /* walk backwards to get last-one-wins ordering */ for (i = ild->nr - 1; i >= 0; i--) { - if (!regexec(&ild->rx[i], refname, + if (!regexec(&ild->rx[i], ref->name, ARRAY_SIZE(matches), matches, 0)) break; } @@ -428,10 +427,10 @@ static int find_island_for_ref(const char *refname, const char *referent UNUSED, if (island_name.len) strbuf_addch(&island_name, '-'); - strbuf_add(&island_name, refname + match->rm_so, match->rm_eo - match->rm_so); + strbuf_add(&island_name, ref->name + match->rm_so, match->rm_eo - match->rm_so); } - add_ref_to_island(ild->remote_islands, island_name.buf, oid); + add_ref_to_island(ild->remote_islands, island_name.buf, ref->oid); strbuf_release(&island_name); return 0; } diff --git a/diff-lib.c b/diff-lib.c index b8f8f3bc31..8e624f38c6 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -418,13 +418,12 @@ static int show_modified(struct rev_info *revs, } oldmode = old_entry->ce_mode; - if (mode == oldmode && oideq(oid, &old_entry->oid) && !dirty_submodule && - !revs->diffopt.flags.find_copies_harder) - return 0; - - diff_change(&revs->diffopt, oldmode, mode, - &old_entry->oid, oid, 1, !is_null_oid(oid), - old_entry->name, 0, dirty_submodule); + if (mode != oldmode || !oideq(oid, &old_entry->oid) || dirty_submodule) + diff_change(&revs->diffopt, oldmode, mode, + &old_entry->oid, oid, 1, !is_null_oid(oid), + old_entry->name, 0, dirty_submodule); + else if (revs->diffopt.flags.find_copies_harder) + diff_same(&revs->diffopt, mode, oid, old_entry->name); return 0; } @@ -601,6 +601,7 @@ struct emit_callback { int blank_at_eof_in_postimage; int lno_in_preimage; int lno_in_postimage; + int last_line_kind; const char **label_path; struct diff_words_data *diff_words; struct diff_options *opt; @@ -796,21 +797,23 @@ enum diff_symbol { DIFF_SYMBOL_CONTEXT_INCOMPLETE, DIFF_SYMBOL_PLUS, DIFF_SYMBOL_MINUS, - DIFF_SYMBOL_NO_LF_EOF, DIFF_SYMBOL_CONTEXT_FRAGINFO, DIFF_SYMBOL_CONTEXT_MARKER, DIFF_SYMBOL_SEPARATOR }; + /* * Flags for content lines: - * 0..12 are whitespace rules - * 13-15 are WSEH_NEW | WSEH_OLD | WSEH_CONTEXT - * 16 is marking if the line is blank at EOF + * 0..15 are whitespace rules (see ws.h) + * 16..18 are WSEH_NEW | WSEH_CONTEXT | WSEH_OLD + * 19 is marking if the line is blank at EOF + * 20..22 are used for color-moved. */ -#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<16) -#define DIFF_SYMBOL_MOVED_LINE (1<<17) -#define DIFF_SYMBOL_MOVED_LINE_ALT (1<<18) -#define DIFF_SYMBOL_MOVED_LINE_UNINTERESTING (1<<19) +#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<19) +#define DIFF_SYMBOL_MOVED_LINE (1<<20) +#define DIFF_SYMBOL_MOVED_LINE_ALT (1<<21) +#define DIFF_SYMBOL_MOVED_LINE_UNINTERESTING (1<<22) + #define DIFF_SYMBOL_CONTENT_WS_MASK (WSEH_NEW | WSEH_OLD | WSEH_CONTEXT | WS_RULE_MASK) /* @@ -1318,20 +1321,25 @@ static void emit_line_ws_markup(struct diff_options *o, const char *ws = NULL; int sign = o->output_indicators[sign_index]; + if (diff_suppress_blank_empty && + sign_index == OUTPUT_INDICATOR_CONTEXT && + len == 1 && line[0] == '\n') + sign = 0; + if (o->ws_error_highlight & ws_rule) { ws = diff_get_color_opt(o, DIFF_WHITESPACE); if (!*ws) ws = NULL; } - if (!ws && !set_sign) + if (!ws && !set_sign) { emit_line_0(o, set, NULL, 0, reset, sign, line, len); - else if (!ws) { + } else if (!ws) { emit_line_0(o, set_sign, set, !!set_sign, reset, sign, line, len); - } else if (blank_at_eof) + } else if (blank_at_eof) { /* Blank line at EOF - paint '+' as well */ emit_line_0(o, ws, NULL, 0, reset, sign, line, len); - else { + } else { /* Emit just the prefix, then the rest. */ emit_line_0(o, set_sign ? set_sign : set, NULL, !!set_sign, reset, sign, "", 0); @@ -1343,7 +1351,6 @@ static void emit_line_ws_markup(struct diff_options *o, static void emit_diff_symbol_from_struct(struct diff_options *o, struct emitted_diff_symbol *eds) { - static const char *nneof = " No newline at end of file\n"; const char *context, *reset, *set, *set_sign, *meta, *fraginfo; enum diff_symbol s = eds->s; @@ -1355,13 +1362,6 @@ static void emit_diff_symbol_from_struct(struct diff_options *o, return; switch (s) { - case DIFF_SYMBOL_NO_LF_EOF: - context = diff_get_color_opt(o, DIFF_CONTEXT); - reset = diff_get_color_opt(o, DIFF_RESET); - putc('\n', o->file); - emit_line_0(o, context, NULL, 0, reset, '\\', - nneof, strlen(nneof)); - break; case DIFF_SYMBOL_SUBMODULE_HEADER: case DIFF_SYMBOL_SUBMODULE_ERROR: case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH: @@ -1373,6 +1373,14 @@ static void emit_diff_symbol_from_struct(struct diff_options *o, emit_line(o, "", "", line, len); break; case DIFF_SYMBOL_CONTEXT_INCOMPLETE: + if ((flags & WS_INCOMPLETE_LINE) && + (flags & o->ws_error_highlight)) + set = diff_get_color_opt(o, DIFF_WHITESPACE); + else + set = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, set, reset, line, len); + break; case DIFF_SYMBOL_CONTEXT_MARKER: context = diff_get_color_opt(o, DIFF_CONTEXT); reset = diff_get_color_opt(o, DIFF_RESET); @@ -1498,15 +1506,9 @@ static void emit_diff_symbol_from_struct(struct diff_options *o, case DIFF_SYMBOL_WORDS: context = diff_get_color_opt(o, DIFF_CONTEXT); reset = diff_get_color_opt(o, DIFF_RESET); - /* - * Skip the prefix character, if any. With - * diff_suppress_blank_empty, there may be - * none. - */ - if (line[0] != '\n') { - line++; - len--; - } + + /* Skip the prefix character */ + line++; len--; emit_line(o, context, reset, line, len); break; case DIFF_SYMBOL_FILEPAIR_PLUS: @@ -1668,6 +1670,19 @@ static void emit_context_line(struct emit_callback *ecbdata, emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT, line, len, flags); } +static void emit_incomplete_line_marker(struct emit_callback *ecbdata, + const char *line, int len) +{ + int last_line_kind = ecbdata->last_line_kind; + unsigned flags = (last_line_kind == '+' + ? WSEH_NEW + : last_line_kind == '-' + ? WSEH_OLD + : WSEH_CONTEXT) | ecbdata->ws_rule; + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT_INCOMPLETE, + line, len, flags); +} + static void emit_hunk_header(struct emit_callback *ecbdata, const char *line, int len) { @@ -1769,28 +1784,44 @@ static void add_line_count(struct strbuf *out, int count) } } -static void emit_rewrite_lines(struct emit_callback *ecb, +static void emit_rewrite_lines(struct emit_callback *ecbdata, int prefix, const char *data, int size) { const char *endp = NULL; while (0 < size) { - int len; + int len, plen; + char *pdata = NULL; endp = memchr(data, '\n', size); - len = endp ? (endp - data + 1) : size; + + if (endp) { + len = endp - data + 1; + plen = len; + } else { + len = size; + plen = len + 1; + pdata = xmalloc(plen + 2); + memcpy(pdata, data, len); + pdata[len] = '\n'; + pdata[len + 1] = '\0'; + } if (prefix != '+') { - ecb->lno_in_preimage++; - emit_del_line(ecb, data, len); + ecbdata->lno_in_preimage++; + emit_del_line(ecbdata, pdata ? pdata : data, plen); } else { - ecb->lno_in_postimage++; - emit_add_line(ecb, data, len); + ecbdata->lno_in_postimage++; + emit_add_line(ecbdata, pdata ? pdata : data, plen); } + free(pdata); size -= len; data += len; } - if (!endp) - emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0, 0); + if (!endp) { + static const char nneof[] = "\\ No newline at end of file\n"; + ecbdata->last_line_kind = prefix; + emit_incomplete_line_marker(ecbdata, nneof, sizeof(nneof) - 1); + } } static void emit_rewrite_diff(const char *name_a, @@ -2375,12 +2406,6 @@ static int fn_out_consume(void *priv, char *line, unsigned long len) ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; } - if (diff_suppress_blank_empty - && len == 2 && line[0] == ' ' && line[1] == '\n') { - line[0] = '\n'; - len = 1; - } - if (line[0] == '@') { if (ecbdata->diff_words) diff_words_flush(ecbdata); @@ -2431,13 +2456,24 @@ static int fn_out_consume(void *priv, char *line, unsigned long len) ecbdata->lno_in_preimage++; emit_context_line(ecbdata, line + 1, len - 1); break; - default: + case '\\': /* incomplete line at the end */ + switch (ecbdata->last_line_kind) { + case '+': + case '-': + case ' ': + break; + default: + BUG("fn_out_consume: '\\No newline' after unknown line (%c)", + ecbdata->last_line_kind); + } ecbdata->lno_in_preimage++; - emit_diff_symbol(o, DIFF_SYMBOL_CONTEXT_INCOMPLETE, - line, len, 0); + emit_incomplete_line_marker(ecbdata, line, len); break; + default: + BUG("fn_out_consume: unknown line '%s'", line); } + ecbdata->last_line_kind = line[0]; return 0; } @@ -3231,6 +3267,7 @@ struct checkdiff_t { struct diff_options *o; unsigned ws_rule; unsigned status; + int last_line_kind; }; static int is_conflict_marker(const char *line, int marker_size, unsigned long len) @@ -3269,6 +3306,7 @@ static void checkdiff_consume_hunk(void *priv, static int checkdiff_consume(void *priv, char *line, unsigned long len) { struct checkdiff_t *data = priv; + int last_line_kind; int marker_size = data->conflict_marker_size; const char *ws = diff_get_color(data->o->use_color, DIFF_WHITESPACE); const char *reset = diff_get_color(data->o->use_color, DIFF_RESET); @@ -3279,6 +3317,8 @@ static int checkdiff_consume(void *priv, char *line, unsigned long len) assert(data->o); line_prefix = diff_line_prefix(data->o); + last_line_kind = data->last_line_kind; + data->last_line_kind = line[0]; if (line[0] == '+') { unsigned bad; data->lineno++; @@ -3301,6 +3341,17 @@ static int checkdiff_consume(void *priv, char *line, unsigned long len) data->o->file, set, reset, ws); } else if (line[0] == ' ') { data->lineno++; + } else if (line[0] == '\\') { + /* no newline at the end of the line */ + if ((data->ws_rule & WS_INCOMPLETE_LINE) && + (last_line_kind == '+')) { + unsigned bad = WS_INCOMPLETE_LINE; + data->status |= bad; + err = whitespace_error_string(bad); + fprintf(data->o->file, "%s%s:%d: %s.\n", + line_prefix, data->filename, data->lineno, err); + free(err); + } } return 0; } @@ -3530,7 +3581,6 @@ static int set_diff_algorithm(struct diff_options *opts, return -1; /* clear out previous settings */ - DIFF_XDL_CLR(opts, NEED_MINIMAL); opts->xdl_opts &= ~XDF_DIFF_ALGORITHM_MASK; opts->xdl_opts |= value; @@ -4987,6 +5037,8 @@ void diff_setup_done(struct diff_options *options) if (options->flags.quick) { options->output_format = DIFF_FORMAT_NO_OUTPUT; options->flags.exit_with_status = 1; + options->detect_rename = 0; + options->flags.find_copies_harder = 0; } /* @@ -7347,6 +7399,26 @@ void diff_change(struct diff_options *options, concatpath, old_dirty_submodule, new_dirty_submodule); } +void diff_same(struct diff_options *options, + unsigned mode, + const struct object_id *oid, + const char *concatpath) +{ + struct diff_filespec *one; + + if (S_ISGITLINK(mode) && is_submodule_ignored(concatpath, options)) + return; + + if (options->prefix && + strncmp(concatpath, options->prefix, options->prefix_length)) + return; + + one = alloc_filespec(concatpath); + fill_filespec(one, oid, 1, mode); + one->count++; + diff_queue(&diff_queued_diff, one, one); +} + struct diff_filepair *diff_unmerge(struct diff_options *options, const char *path) { struct diff_filepair *pair; @@ -331,9 +331,9 @@ struct diff_options { int ita_invisible_in_index; /* white-space error highlighting */ -#define WSEH_NEW (1<<12) -#define WSEH_CONTEXT (1<<13) -#define WSEH_OLD (1<<14) +#define WSEH_NEW (1<<16) +#define WSEH_CONTEXT (1<<17) +#define WSEH_OLD (1<<18) unsigned ws_error_highlight; const char *prefix; int prefix_length; @@ -572,6 +572,11 @@ void diff_change(struct diff_options *, const char *fullpath, unsigned dirty_submodule1, unsigned dirty_submodule2); +void diff_same(struct diff_options *, + unsigned mode, + const struct object_id *oid, + const char *fullpath); + struct diff_filepair *diff_unmerge(struct diff_options *, const char *path); void compute_diffstat(struct diff_options *options, struct diffstat_t *diffstat, @@ -2,13 +2,13 @@ #include "git-compat-util.h" #include "odb.h" +#include "odb/streaming.h" #include "dir.h" #include "environment.h" #include "gettext.h" #include "hex.h" #include "name-hash.h" #include "sparse-index.h" -#include "streaming.h" #include "submodule.h" #include "symlinks.h" #include "progress.h" @@ -139,7 +139,7 @@ static int streaming_write_entry(const struct cache_entry *ce, char *path, if (fd < 0) return -1; - result |= stream_blob_to_fd(fd, &ce->oid, filter, 1); + result |= odb_stream_blob_to_fd(the_repository->objects, fd, &ce->oid, filter, 1); *fstat_done = fstat_checkout_output(fd, state, statbuf); result |= close(fd); diff --git a/fetch-pack.c b/fetch-pack.c index fe7a84bf2f..40316c9a34 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -188,13 +188,9 @@ static int rev_list_insert_ref(struct fetch_negotiator *negotiator, return 0; } -static int rev_list_insert_ref_oid(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int rev_list_insert_ref_oid(const struct reference *ref, void *cb_data) { - return rev_list_insert_ref(cb_data, oid); + return rev_list_insert_ref(cb_data, ref->oid); } enum ack_type { @@ -616,13 +612,9 @@ static int mark_complete(const struct object_id *oid) return 0; } -static int mark_complete_oid(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, - void *cb_data UNUSED) +static int mark_complete_oid(const struct reference *ref, void *cb_data UNUSED) { - return mark_complete(oid); + return mark_complete(ref->oid); } static void mark_recent_complete_commits(struct fetch_pack_args *args, @@ -1873,8 +1865,9 @@ int fetch_pack_fsck_config(const char *var, const char *value, if (git_config_pathname(&path, var, value)) return -1; - strbuf_addf(msg_types, "%cskiplist=%s", - msg_types->len ? ',' : '=', path); + if (path) + strbuf_addf(msg_types, "%cskiplist=%s", + msg_types->len ? ',' : '=', path); free(path); return 0; } @@ -860,31 +860,60 @@ static int verify_headers(const void *data, unsigned long size, FSCK_MSG_UNTERMINATED_HEADER, "unterminated header"); } -static int fsck_ident(const char **ident, +static timestamp_t parse_timestamp_from_buf(const char **start, const char *end) +{ + const char *p = *start; + char buf[24]; /* big enough for 2^64 */ + size_t i = 0; + + while (p < end && isdigit(*p)) { + if (i >= ARRAY_SIZE(buf) - 1) + return TIME_MAX; + buf[i++] = *p++; + } + buf[i] = '\0'; + *start = p; + return parse_timestamp(buf, NULL, 10); +} + +static int fsck_ident(const char **ident, const char *ident_end, const struct object_id *oid, enum object_type type, struct fsck_options *options) { const char *p = *ident; - char *end; + const char *nl; - *ident = strchrnul(*ident, '\n'); - if (**ident == '\n') - (*ident)++; + nl = memchr(p, '\n', ident_end - p); + if (!nl) + BUG("verify_headers() should have made sure we have a newline"); + *ident = nl + 1; if (*p == '<') return report(options, oid, type, FSCK_MSG_MISSING_NAME_BEFORE_EMAIL, "invalid author/committer line - missing space before email"); - p += strcspn(p, "<>\n"); - if (*p == '>') - return report(options, oid, type, FSCK_MSG_BAD_NAME, "invalid author/committer line - bad name"); - if (*p != '<') - return report(options, oid, type, FSCK_MSG_MISSING_EMAIL, "invalid author/committer line - missing email"); + for (;;) { + if (p >= ident_end || *p == '\n') + return report(options, oid, type, FSCK_MSG_MISSING_EMAIL, "invalid author/committer line - missing email"); + if (*p == '>') + return report(options, oid, type, FSCK_MSG_BAD_NAME, "invalid author/committer line - bad name"); + if (*p == '<') + break; /* end of name, beginning of email */ + + /* otherwise, skip past arbitrary name char */ + p++; + } if (p[-1] != ' ') return report(options, oid, type, FSCK_MSG_MISSING_SPACE_BEFORE_EMAIL, "invalid author/committer line - missing space before email"); - p++; - p += strcspn(p, "<>\n"); - if (*p != '>') - return report(options, oid, type, FSCK_MSG_BAD_EMAIL, "invalid author/committer line - bad email"); - p++; + p++; /* skip past '<' we found */ + for (;;) { + if (p >= ident_end || *p == '<' || *p == '\n') + return report(options, oid, type, FSCK_MSG_BAD_EMAIL, "invalid author/committer line - bad email"); + if (*p == '>') + break; /* end of email */ + + /* otherwise, skip past arbitrary email char */ + p++; + } + p++; /* skip past '>' we found */ if (*p != ' ') return report(options, oid, type, FSCK_MSG_MISSING_SPACE_BEFORE_DATE, "invalid author/committer line - missing space before date"); p++; @@ -904,11 +933,11 @@ static int fsck_ident(const char **ident, "invalid author/committer line - bad date"); if (*p == '0' && p[1] != ' ') return report(options, oid, type, FSCK_MSG_ZERO_PADDED_DATE, "invalid author/committer line - zero-padded date"); - if (date_overflows(parse_timestamp(p, &end, 10))) + if (date_overflows(parse_timestamp_from_buf(&p, ident_end))) return report(options, oid, type, FSCK_MSG_BAD_DATE_OVERFLOW, "invalid author/committer line - date causes integer overflow"); - if ((end == p || *end != ' ')) + if (*p != ' ') return report(options, oid, type, FSCK_MSG_BAD_DATE, "invalid author/committer line - bad date"); - p = end + 1; + p++; if ((*p != '+' && *p != '-') || !isdigit(p[1]) || !isdigit(p[2]) || @@ -958,7 +987,7 @@ static int fsck_commit(const struct object_id *oid, author_count = 0; while (buffer < buffer_end && skip_prefix(buffer, "author ", &buffer)) { author_count++; - err = fsck_ident(&buffer, oid, OBJ_COMMIT, options); + err = fsck_ident(&buffer, buffer_end, oid, OBJ_COMMIT, options); if (err) return err; } @@ -970,7 +999,7 @@ static int fsck_commit(const struct object_id *oid, return err; if (buffer >= buffer_end || !skip_prefix(buffer, "committer ", &buffer)) return report(options, oid, OBJ_COMMIT, FSCK_MSG_MISSING_COMMITTER, "invalid format - expected 'committer' line"); - err = fsck_ident(&buffer, oid, OBJ_COMMIT, options); + err = fsck_ident(&buffer, buffer_end, oid, OBJ_COMMIT, options); if (err) return err; if (memchr(buffer_begin, '\0', size)) { @@ -1065,7 +1094,7 @@ int fsck_tag_standalone(const struct object_id *oid, const char *buffer, goto done; } else - ret = fsck_ident(&buffer, oid, OBJ_TAG, options); + ret = fsck_ident(&buffer, buffer_end, oid, OBJ_TAG, options); if (buffer < buffer_end && (skip_prefix(buffer, "gpgsig ", &buffer) || skip_prefix(buffer, "gpgsig-sha256 ", &buffer))) { eol = memchr(buffer, '\n', buffer_end - buffer); @@ -1350,6 +1379,12 @@ int fsck_finish(struct fsck_options *options) return ret; } +bool fsck_has_queued_checks(struct fsck_options *options) +{ + return !oidset_equal(&options->gitmodules_found, &options->gitmodules_done) || + !oidset_equal(&options->gitattributes_found, &options->gitattributes_done); +} + void fsck_options_clear(struct fsck_options *options) { free(options->msg_type); @@ -1369,14 +1404,16 @@ int git_fsck_config(const char *var, const char *value, if (strcmp(var, "fsck.skiplist") == 0) { char *path; - struct strbuf sb = STRBUF_INIT; if (git_config_pathname(&path, var, value)) return -1; - strbuf_addf(&sb, "skiplist=%s", path); - free(path); - fsck_set_msg_types(options, sb.buf); - strbuf_release(&sb); + if (path) { + struct strbuf sb = STRBUF_INIT; + strbuf_addf(&sb, "skiplist=%s", path); + free(path); + fsck_set_msg_types(options, sb.buf); + strbuf_release(&sb); + } return 0; } @@ -249,6 +249,13 @@ int fsck_tag_standalone(const struct object_id *oid, const char *buffer, int fsck_finish(struct fsck_options *options); /* + * Check whether there are any checks that have been queued up and that still + * need to be run. Returns `false` iff `fsck_finish()` wouldn't perform any + * actions, `true` otherwise. + */ +bool fsck_has_queued_checks(struct fsck_options *options); + +/* * Clear the fsck_options struct, freeing any allocated memory. */ void fsck_options_clear(struct fsck_options *options); diff --git a/gitk-git/gitk b/gitk-git/gitk index c02db0194d..7f62c8041d 100755 --- a/gitk-git/gitk +++ b/gitk-git/gitk @@ -2131,12 +2131,14 @@ proc ttk_toplevel {w args} { return $w } -proc make_transient {window origin} { +proc make_transient {window origin {geometry ""}} { wm transient $window $origin - # Windows fails to place transient windows normally, so - # schedule a callback to center them on the parent. - if {[tk windowingsystem] eq {win32}} { + if {$geometry ne ""} { + after idle [list wm geometry $window $geometry] + } elseif {[tk windowingsystem] eq {win32}} { + # Windows fails to place transient windows normally, so + # schedule a callback to center them on the parent. after idle [list tk::PlaceWindow $window widget $origin] } } @@ -2723,17 +2725,9 @@ proc makewindow {} { .pwbottom add .bright .ctop add .pwbottom - # restore window width & height if known + # restore window position if known if {[info exists geometry(main)]} { - if {[scan $geometry(main) "%dx%d" w h] >= 2} { - if {$w > [winfo screenwidth .]} { - set w [winfo screenwidth .] - } - if {$h > [winfo screenheight .]} { - set h [winfo screenheight .] - } - wm geometry . "${w}x$h" - } + wm geometry . "$geometry(main)" } if {[info exists geometry(state)] && $geometry(state) eq "zoomed"} { @@ -3073,6 +3067,11 @@ proc savestuff {w} { puts $f "set geometry(pwsash1) \"[.tf.histframe.pwclist sashpos 1] 1\"" puts $f "set geometry(botwidth) [winfo width .bleft]" puts $f "set geometry(botheight) [winfo height .bleft]" + unset -nocomplain geometry + global geometry + if {[info exists geometry(showrefs)]} { + puts $f "set geometry(showrefs) $geometry(showrefs)" + } array set view_save {} array set views {} @@ -3788,6 +3787,34 @@ proc external_diff_get_one_file {diffid filename diffdir} { "revision $diffid"] } +proc check_for_renames_in_diff {filepath} { # renames + global difffilestart ctext + + set filename [file tail $filepath] + set renames {} + + foreach loc $difffilestart { + set loclineend [string map {.0 .end} $loc] + set fromlineloc "$loc + 2 lines" + set tolineloc "$loc + 3 lines" + set renfromline [$ctext get $fromlineloc [string map {.0 .end} $fromlineloc]] + set rentoline [$ctext get $tolineloc [string map {.0 .end} $tolineloc]] + if {[string equal -length 12 "rename from " $renfromline] + && [string equal -length 10 "rename to " $rentoline]} { + set renfrom [string range $renfromline 12 end] + set rento [string range $rentoline 10 end] + if {[string first $filename $renfrom] != -1 + || [string first $filename $rento] != -1} { + lappend renames $renfrom + lappend renames $rento + break + } + } + } + + return $renames +} + proc external_diff {} { global nullid nullid2 global flist_menu_file @@ -3818,8 +3845,16 @@ proc external_diff {} { if {$diffdir eq {}} return # gather files to diff - set difffromfile [external_diff_get_one_file $diffidfrom $flist_menu_file $diffdir] - set difftofile [external_diff_get_one_file $diffidto $flist_menu_file $diffdir] + set renames [check_for_renames_in_diff $flist_menu_file] + set renamefrom [lindex $renames 0] + set renameto [lindex $renames 1] + if {$renamefrom ne {} && $renameto ne {}} { + set difffromfile [external_diff_get_one_file $diffidfrom $renamefrom $diffdir] + set difftofile [external_diff_get_one_file $diffidto $renameto $diffdir] + } else { + set difffromfile [external_diff_get_one_file $diffidfrom $flist_menu_file $diffdir] + set difftofile [external_diff_get_one_file $diffidto $flist_menu_file $diffdir] + } if {$difffromfile ne {} && $difftofile ne {}} { set cmd [list [shellsplit $extdifftool] $difffromfile $difftofile] @@ -8296,7 +8331,7 @@ proc parseblobdiffline {ids line} { if {![regexp {^diff (--cc|--git) } $line m type]} { set line [convertfrom utf-8 $line] $ctext insert end "$line\n" hunksep - continue + return } # start of a new file set diffinhdr 1 @@ -8401,6 +8436,7 @@ proc parseblobdiffline {ids line} { if {$i >= 0} { setinlist difffilestart $i $curdiffstart } + set line "rename from $fname" } elseif {![string compare -length 10 $line "rename to "] || ![string compare -length 8 $line "copy to "]} { set fname [string range $line [expr 4 + [string first " to " $line] ] end] @@ -8408,6 +8444,13 @@ proc parseblobdiffline {ids line} { set fname [lindex $fname 0] } makediffhdr $fname $ids + set line "[lindex $line 0] to $fname" + } elseif {![string compare -length 10 $line "copy from "]} { + set fname [string range $line 10 end] + if {[string index $fname 0] eq "\""} { + set fname [lindex $fname 0] + } + set line "copy from $fname" } elseif {[string compare -length 3 $line "---"] == 0} { # do nothing return @@ -10160,6 +10203,7 @@ proc rmbranch {} { proc showrefs {} { global showrefstop bgcolor fgcolor selectbgcolor global bglist fglist reflistfilter reflist maincursor + global geometry set top .showrefs set showrefstop $top @@ -10170,7 +10214,11 @@ proc showrefs {} { } ttk_toplevel $top wm title $top [mc "Tags and heads: %s" [file tail [pwd]]] - make_transient $top . + if {[info exists geometry(showrefs)]} { + make_transient $top . $geometry(showrefs) + } else { + make_transient $top . + } text $top.list -background $bgcolor -foreground $fgcolor \ -selectbackground $selectbgcolor -font mainfont \ -xscrollcommand "$top.xsb set" -yscrollcommand "$top.ysb set" \ @@ -10206,6 +10254,9 @@ proc showrefs {} { bind $top.list <ButtonRelease-1> {sel_reflist %W %x %y; break} set reflist {} refill_reflist + # avoid <Configure> being bound to child windows + bindtags $top [linsert [bindtags $top] 1 bind$top] + bind bind$top <Configure> {set geometry(showrefs) [wm geometry %W]} } proc sel_reflist {w x y} { diff --git a/gpg-interface.c b/gpg-interface.c index f680ed38c0..47222bf31b 100644 --- a/gpg-interface.c +++ b/gpg-interface.c @@ -794,8 +794,16 @@ static int git_gpg_config(const char *var, const char *value, fmtname = "ssh"; if (fmtname) { + char *program; + int status; + fmt = get_format_by_name(fmtname); - return git_config_pathname((char **) &fmt->program, var, value); + status = git_config_pathname(&program, var, value); + if (status) + return status; + if (program) + fmt->program = program; + return status; } return 0; @@ -1146,6 +1154,8 @@ int parse_sign_mode(const char *arg, enum sign_mode *mode) *mode = SIGN_WARN_STRIP; else if (!strcmp(arg, "strip")) *mode = SIGN_STRIP; + else if (!strcmp(arg, "strip-if-invalid")) + *mode = SIGN_STRIP_IF_INVALID; else return -1; return 0; diff --git a/gpg-interface.h b/gpg-interface.h index ead1ed6967..789d1ffac4 100644 --- a/gpg-interface.h +++ b/gpg-interface.h @@ -111,6 +111,7 @@ enum sign_mode { SIGN_VERBATIM, SIGN_WARN_STRIP, SIGN_STRIP, + SIGN_STRIP_IF_INVALID, }; /* @@ -851,18 +851,16 @@ struct similar_ref_cb { struct string_list *similar_refs; }; -static int append_similar_ref(const char *refname, const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, void *cb_data) +static int append_similar_ref(const struct reference *ref, void *cb_data) { struct similar_ref_cb *cb = (struct similar_ref_cb *)(cb_data); - char *branch = strrchr(refname, '/') + 1; + char *branch = strrchr(ref->name, '/') + 1; /* A remote branch of the same name is deemed similar */ - if (starts_with(refname, "refs/remotes/") && + if (starts_with(ref->name, "refs/remotes/") && !strcmp(branch, cb->base_ref)) string_list_append_nodup(cb->similar_refs, - refs_shorten_unambiguous_ref(get_main_ref_store(the_repository), refname, 1)); + refs_shorten_unambiguous_ref(get_main_ref_store(the_repository), ref->name, 1)); return 0; } diff --git a/http-backend.c b/http-backend.c index 52f0483dd3..24f0dc119a 100644 --- a/http-backend.c +++ b/http-backend.c @@ -16,6 +16,7 @@ #include "run-command.h" #include "string-list.h" #include "url.h" +#include "setup.h" #include "strvec.h" #include "packfile.h" #include "odb.h" @@ -513,18 +514,17 @@ static void run_service(const char **argv, int buffer_input) exit(1); } -static int show_text_ref(const char *name, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data) +static int show_text_ref(const struct reference *ref, void *cb_data) { - const char *name_nons = strip_namespace(name); + const char *name_nons = strip_namespace(ref->name); struct strbuf *buf = cb_data; - struct object *o = parse_object(the_repository, oid); + struct object *o = parse_object(the_repository, ref->oid); if (!o) return 0; - strbuf_addf(buf, "%s\t%s\n", oid_to_hex(oid), name_nons); + strbuf_addf(buf, "%s\t%s\n", oid_to_hex(ref->oid), name_nons); if (o->type == OBJ_TAG) { - o = deref_tag(the_repository, o, name, 0); + o = deref_tag(the_repository, o, ref->name, 0); if (!o) return 0; strbuf_addf(buf, "%s\t%s^{}\n", oid_to_hex(&o->oid), @@ -569,21 +569,20 @@ static void get_info_refs(struct strbuf *hdr, char *arg UNUSED) strbuf_release(&buf); } -static int show_head_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag, void *cb_data) +static int show_head_ref(const struct reference *ref, void *cb_data) { struct strbuf *buf = cb_data; - if (flag & REF_ISSYMREF) { + if (ref->flags & REF_ISSYMREF) { const char *target = refs_resolve_ref_unsafe(get_main_ref_store(the_repository), - refname, + ref->name, RESOLVE_REF_READING, NULL, NULL); if (target) strbuf_addf(buf, "ref: %s\n", strip_namespace(target)); } else { - strbuf_addf(buf, "%s\n", oid_to_hex(oid)); + strbuf_addf(buf, "%s\n", oid_to_hex(ref->oid)); } return 0; diff --git a/http-push.c b/http-push.c index a1c01e3b9b..60a9b75620 100644 --- a/http-push.c +++ b/http-push.c @@ -104,7 +104,7 @@ struct repo { int has_info_refs; int can_update_info_refs; int has_info_packs; - struct packed_git *packs; + struct packfile_list packs; struct remote_lock *locks; }; @@ -311,7 +311,7 @@ static void start_fetch_packed(struct transfer_request *request) struct transfer_request *check_request = request_queue_head; struct http_pack_request *preq; - target = find_oid_pack(&request->obj->oid, repo->packs); + target = packfile_list_find_oid(repo->packs.head, &request->obj->oid); if (!target) { fprintf(stderr, "Unable to fetch %s, will not be able to update server info refs\n", oid_to_hex(&request->obj->oid)); repo->can_update_info_refs = 0; @@ -683,7 +683,7 @@ static int add_send_request(struct object *obj, struct remote_lock *lock) get_remote_object_list(obj->oid.hash[0]); if (obj->flags & (REMOTE | PUSHING)) return 0; - target = find_oid_pack(&obj->oid, repo->packs); + target = packfile_list_find_oid(repo->packs.head, &obj->oid); if (target) { obj->flags |= REMOTE; return 0; @@ -1725,6 +1725,7 @@ int cmd_main(int argc, const char **argv) int i; int new_refs; struct ref *ref, *local_refs = NULL; + const char *gitdir; CALLOC_ARRAY(repo, 1); @@ -1787,7 +1788,7 @@ int cmd_main(int argc, const char **argv) if (delete_branch && rs.nr != 1) die("You must specify only one branch name when deleting a remote branch"); - setup_git_directory(); + gitdir = setup_git_directory(); memset(remote_dir_exists, -1, 256); @@ -1941,7 +1942,7 @@ int cmd_main(int argc, const char **argv) if (!push_all && !is_null_oid(&ref->old_oid)) strvec_pushf(&commit_argv, "^%s", oid_to_hex(&ref->old_oid)); - repo_init_revisions(the_repository, &revs, setup_git_directory()); + repo_init_revisions(the_repository, &revs, gitdir); setup_revisions_from_strvec(&commit_argv, &revs, NULL); revs.edge_hint = 0; /* just in case */ diff --git a/http-walker.c b/http-walker.c index 0f7ae46d7f..e886e64866 100644 --- a/http-walker.c +++ b/http-walker.c @@ -15,7 +15,7 @@ struct alt_base { char *base; int got_indices; - struct packed_git *packs; + struct packfile_list packs; struct alt_base *next; }; @@ -324,11 +324,8 @@ static void process_alternates_response(void *callback_data) } else if (is_alternate_allowed(target.buf)) { warning("adding alternate object store: %s", target.buf); - newalt = xmalloc(sizeof(*newalt)); - newalt->next = NULL; + CALLOC_ARRAY(newalt, 1); newalt->base = strbuf_detach(&target, NULL); - newalt->got_indices = 0; - newalt->packs = NULL; while (tail->next != NULL) tail = tail->next; @@ -435,7 +432,7 @@ static int http_fetch_pack(struct walker *walker, struct alt_base *repo, if (fetch_indices(walker, repo)) return -1; - target = find_oid_pack(oid, repo->packs); + target = packfile_list_find_oid(repo->packs.head, oid); if (!target) return -1; close_pack_index(target); @@ -584,17 +581,15 @@ static void cleanup(struct walker *walker) if (data) { alt = data->alt; while (alt) { - struct packed_git *pack; + struct packfile_list_entry *e; alt_next = alt->next; - pack = alt->packs; - while (pack) { - struct packed_git *pack_next = pack->next; - close_pack(pack); - free(pack); - pack = pack_next; + for (e = alt->packs.head; e; e = e->next) { + close_pack(e->pack); + free(e->pack); } + packfile_list_clear(&alt->packs); free(alt->base); free(alt); @@ -612,14 +607,11 @@ struct walker *get_http_walker(const char *url) struct walker_data *data = xmalloc(sizeof(struct walker_data)); struct walker *walker = xmalloc(sizeof(struct walker)); - data->alt = xmalloc(sizeof(*data->alt)); + CALLOC_ARRAY(data->alt, 1); data->alt->base = xstrdup(url); for (s = data->alt->base + strlen(data->alt->base) - 1; *s == '/'; --s) *s = 0; - data->alt->got_indices = 0; - data->alt->packs = NULL; - data->alt->next = NULL; data->got_alternates = -1; walker->corrupt_object_found = 0; @@ -2413,8 +2413,9 @@ static char *fetch_pack_index(unsigned char *hash, const char *base_url) return tmp; } -static int fetch_and_setup_pack_index(struct packed_git **packs_head, - unsigned char *sha1, const char *base_url) +static int fetch_and_setup_pack_index(struct packfile_list *packs, + unsigned char *sha1, + const char *base_url) { struct packed_git *new_pack, *p; char *tmp_idx = NULL; @@ -2448,12 +2449,11 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head, if (ret) return -1; - new_pack->next = *packs_head; - *packs_head = new_pack; + packfile_list_prepend(packs, new_pack); return 0; } -int http_get_info_packs(const char *base_url, struct packed_git **packs_head) +int http_get_info_packs(const char *base_url, struct packfile_list *packs) { struct http_get_options options = {0}; int ret = 0; @@ -2477,7 +2477,7 @@ int http_get_info_packs(const char *base_url, struct packed_git **packs_head) !parse_oid_hex(data, &oid, &data) && skip_prefix(data, ".pack", &data) && (*data == '\n' || *data == '\0')) { - fetch_and_setup_pack_index(packs_head, oid.hash, base_url); + fetch_and_setup_pack_index(packs, oid.hash, base_url); } else { data = strchrnul(data, '\n'); } @@ -2541,14 +2541,9 @@ cleanup: } void http_install_packfile(struct packed_git *p, - struct packed_git **list_to_remove_from) + struct packfile_list *list_to_remove_from) { - struct packed_git **lst = list_to_remove_from; - - while (*lst != p) - lst = &((*lst)->next); - *lst = (*lst)->next; - + packfile_list_remove(list_to_remove_from, p); packfile_store_add_pack(the_repository->objects->packfiles, p); } @@ -2,6 +2,7 @@ #define HTTP_H struct packed_git; +struct packfile_list; #include "git-zlib.h" @@ -190,7 +191,7 @@ struct curl_slist *http_append_auth_header(const struct credential *c, /* Helpers for fetching packs */ int http_get_info_packs(const char *base_url, - struct packed_git **packs_head); + struct packfile_list *packs); /* Helper for getting Accept-Language header */ const char *http_get_accept_language_header(void); @@ -226,7 +227,7 @@ void release_http_pack_request(struct http_pack_request *preq); * from http_get_info_packs() and have chosen a specific pack to fetch. */ void http_install_packfile(struct packed_git *p, - struct packed_git **list_to_remove_from); + struct packfile_list *list_to_remove_from); /* Helpers for fetching object */ struct http_object_request { diff --git a/log-tree.c b/log-tree.c index 7d917f2a83..1729b0c201 100644 --- a/log-tree.c +++ b/log-tree.c @@ -147,9 +147,7 @@ static int ref_filter_match(const char *refname, return 1; } -static int add_ref_decoration(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags UNUSED, - void *cb_data) +static int add_ref_decoration(const struct reference *ref, void *cb_data) { int i; struct object *obj; @@ -158,16 +156,16 @@ static int add_ref_decoration(const char *refname, const char *referent UNUSED, struct decoration_filter *filter = (struct decoration_filter *)cb_data; const char *git_replace_ref_base = ref_namespace[NAMESPACE_REPLACE].ref; - if (filter && !ref_filter_match(refname, filter)) + if (filter && !ref_filter_match(ref->name, filter)) return 0; - if (starts_with(refname, git_replace_ref_base)) { + if (starts_with(ref->name, git_replace_ref_base)) { struct object_id original_oid; if (!replace_refs_enabled(the_repository)) return 0; - if (get_oid_hex(refname + strlen(git_replace_ref_base), + if (get_oid_hex(ref->name + strlen(git_replace_ref_base), &original_oid)) { - warning("invalid replace ref %s", refname); + warning("invalid replace ref %s", ref->name); return 0; } obj = parse_object(the_repository, &original_oid); @@ -176,10 +174,10 @@ static int add_ref_decoration(const char *refname, const char *referent UNUSED, return 0; } - objtype = odb_read_object_info(the_repository->objects, oid, NULL); + objtype = odb_read_object_info(the_repository->objects, ref->oid, NULL); if (objtype < 0) return 0; - obj = lookup_object_by_type(the_repository, oid, objtype); + obj = lookup_object_by_type(the_repository, ref->oid, objtype); for (i = 0; i < ARRAY_SIZE(ref_namespace); i++) { struct ref_namespace_info *info = &ref_namespace[i]; @@ -187,24 +185,24 @@ static int add_ref_decoration(const char *refname, const char *referent UNUSED, if (!info->decoration) continue; if (info->exact) { - if (!strcmp(refname, info->ref)) { + if (!strcmp(ref->name, info->ref)) { deco_type = info->decoration; break; } - } else if (starts_with(refname, info->ref)) { + } else if (starts_with(ref->name, info->ref)) { deco_type = info->decoration; break; } } - add_name_decoration(deco_type, refname, obj); + add_name_decoration(deco_type, ref->name, obj); while (obj->type == OBJ_TAG) { if (!obj->parsed) parse_object(the_repository, &obj->oid); obj = ((struct tag *)obj)->tagged; if (!obj) break; - add_name_decoration(DECORATION_REF_TAG, refname, obj); + add_name_decoration(DECORATION_REF_TAG, ref->name, obj); } return 0; } @@ -1,6 +1,7 @@ #include "git-compat-util.h" #include "hash.h" #include "path.h" +#include "object-file.h" #include "odb.h" #include "hex.h" #include "repository.h" @@ -48,13 +49,13 @@ static int insert_loose_map(struct odb_source *source, const struct object_id *oid, const struct object_id *compat_oid) { - struct loose_object_map *map = source->loose_map; + struct loose_object_map *map = source->loose->map; int inserted = 0; inserted |= insert_oid_pair(map->to_compat, oid, compat_oid); inserted |= insert_oid_pair(map->to_storage, compat_oid, oid); if (inserted) - oidtree_insert(source->loose_objects_cache, compat_oid); + oidtree_insert(source->loose->cache, compat_oid); return inserted; } @@ -64,11 +65,11 @@ static int load_one_loose_object_map(struct repository *repo, struct odb_source struct strbuf buf = STRBUF_INIT, path = STRBUF_INIT; FILE *fp; - if (!source->loose_map) - loose_object_map_init(&source->loose_map); - if (!source->loose_objects_cache) { - ALLOC_ARRAY(source->loose_objects_cache, 1); - oidtree_init(source->loose_objects_cache); + if (!source->loose->map) + loose_object_map_init(&source->loose->map); + if (!source->loose->cache) { + ALLOC_ARRAY(source->loose->cache, 1); + oidtree_init(source->loose->cache); } insert_loose_map(source, repo->hash_algo->empty_tree, repo->compat_hash_algo->empty_tree); @@ -124,7 +125,7 @@ int repo_read_loose_object_map(struct repository *repo) int repo_write_loose_object_map(struct repository *repo) { - kh_oid_map_t *map = repo->objects->sources->loose_map->to_compat; + kh_oid_map_t *map = repo->objects->sources->loose->map->to_compat; struct lock_file lock; int fd; khiter_t iter; @@ -230,7 +231,7 @@ int repo_loose_object_map_oid(struct repository *repo, khiter_t pos; for (source = repo->objects->sources; source; source = source->next) { - struct loose_object_map *loose_map = source->loose_map; + struct loose_object_map *loose_map = source->loose->map; if (!loose_map) continue; map = (to == repo->compat_hash_algo) ? @@ -75,42 +75,42 @@ struct ls_refs_data { unsigned unborn : 1; }; -static int send_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag, void *cb_data) +static int send_ref(const struct reference *ref, void *cb_data) { struct ls_refs_data *data = cb_data; - const char *refname_nons = strip_namespace(refname); + const char *refname_nons = strip_namespace(ref->name); strbuf_reset(&data->buf); - if (ref_is_hidden(refname_nons, refname, &data->hidden_refs)) + if (ref_is_hidden(refname_nons, ref->name, &data->hidden_refs)) return 0; if (!ref_match(&data->prefixes, refname_nons)) return 0; - if (oid) - strbuf_addf(&data->buf, "%s %s", oid_to_hex(oid), refname_nons); + if (ref->oid) + strbuf_addf(&data->buf, "%s %s", oid_to_hex(ref->oid), refname_nons); else strbuf_addf(&data->buf, "unborn %s", refname_nons); - if (data->symrefs && flag & REF_ISSYMREF) { + if (data->symrefs && ref->flags & REF_ISSYMREF) { + int unused_flag; struct object_id unused; const char *symref_target = refs_resolve_ref_unsafe(get_main_ref_store(the_repository), - refname, + ref->name, 0, &unused, - &flag); + &unused_flag); if (!symref_target) - die("'%s' is a symref but it is not?", refname); + die("'%s' is a symref but it is not?", ref->name); strbuf_addf(&data->buf, " symref-target:%s", strip_namespace(symref_target)); } - if (data->peel && oid) { + if (data->peel && ref->oid) { struct object_id peeled; - if (!peel_iterated_oid(the_repository, oid, &peeled)) + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) strbuf_addf(&data->buf, " peeled:%s", oid_to_hex(&peeled)); } @@ -131,9 +131,17 @@ static void send_possibly_unborn_head(struct ls_refs_data *data) if (!refs_resolve_ref_unsafe(get_main_ref_store(the_repository), namespaced.buf, 0, &oid, &flag)) return; /* bad ref */ oid_is_null = is_null_oid(&oid); + if (!oid_is_null || - (data->unborn && data->symrefs && (flag & REF_ISSYMREF))) - send_ref(namespaced.buf, NULL, oid_is_null ? NULL : &oid, flag, data); + (data->unborn && data->symrefs && (flag & REF_ISSYMREF))) { + struct reference ref = { + .name = namespaced.buf, + .oid = oid_is_null ? NULL : &oid, + .flags = flag, + }; + + send_ref(&ref, data); + } strbuf_release(&namespaced); } diff --git a/merge-ort.c b/merge-ort.c index 29858074f9..9e85a5e60a 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -2913,6 +2913,32 @@ static int process_renames(struct merge_options *opt, continue; /* + * Rename caching from a previous commit might give us an + * irrelevant rename for the current commit. + * + * Imagine: + * foo/A -> bar/A + * was a cached rename for the upstream side from the + * previous commit (without the directories being renamed), + * but the next commit being replayed + * * does NOT add or delete files + * * does NOT have directory renames + * * does NOT modify any files under bar/ + * * does NOT modify foo/A + * * DOES modify other files under foo/ (otherwise the + * !oldinfo check above would have already exited for + * us) + * In such a case, our trivial directory resolution will + * have already merged bar/, and our attempt to process + * the cached + * foo/A -> bar/A + * would be counterproductive, and lack the necessary + * information anyway. Skip such renames. + */ + if (!newinfo) + continue; + + /* * diff_filepairs have copies of pathnames, thus we have to * use standard 'strcmp()' (negated) instead of '=='. */ @@ -3438,7 +3464,7 @@ static int collect_renames(struct merge_options *opt, continue; } if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_NONE && - p->status == 'R' && 1) { + p->status == 'R') { possibly_cache_new_pair(renames, p, side_index, NULL); goto skip_directory_renames; } @@ -5118,7 +5144,8 @@ static void merge_check_renames_reusable(struct merge_options *opt, * optimization" comment near that case). * * This could be revisited in the future; see the commit message - * where this comment was added for some possible pointers. + * where this comment was added for some possible pointers, or the + * later commit where this comment was added. */ if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_NONE) { renames->cached_pairs_valid_side = 0; /* neither side valid */ @@ -5496,7 +5523,6 @@ int parse_merge_opt(struct merge_options *opt, const char *s) if (value < 0) return -1; /* clear out previous settings */ - DIFF_XDL_CLR(opt, NEED_MINIMAL); opt->xdl_opts &= ~XDF_DIFF_ALGORITHM_MASK; opt->xdl_opts |= value; } diff --git a/meson.build b/meson.build index 1f95a06edb..dd52efd1c8 100644 --- a/meson.build +++ b/meson.build @@ -397,6 +397,7 @@ libgit_sources = [ 'object-name.c', 'object.c', 'odb.c', + 'odb/streaming.c', 'oid-array.c', 'oidmap.c', 'oidset.c', @@ -490,7 +491,6 @@ libgit_sources = [ 'stable-qsort.c', 'statinfo.c', 'strbuf.c', - 'streaming.c', 'string-list.c', 'strmap.c', 'strvec.c', @@ -1064,7 +1064,7 @@ if iconv.found() } ''' - if compiler.run(iconv_omits_bom_source, + if meson.can_run_host_binaries() and compiler.run(iconv_omits_bom_source, dependencies: iconv, name: 'iconv omits BOM', ).returncode() != 0 @@ -1401,7 +1401,7 @@ checkfuncs = { 'strlcpy' : ['strlcpy.c'], 'strtoull' : [], 'setenv' : ['setenv.c'], - 'mkdtemp' : ['mkdtemp.c'], + 'mkdtemp' : [], 'initgroups' : [], 'strtoumax' : ['strtoumax.c', 'strtoimax.c'], 'pread' : ['pread.c'], @@ -1411,12 +1411,18 @@ if host_machine.system() == 'windows' libgit_c_args += '-DUSE_WIN32_MMAP' else checkfuncs += { - 'mmap' : ['mmap.c'], # provided by compat/mingw.c. 'unsetenv' : ['unsetenv.c'], # provided by compat/mingw.c. 'getpagesize' : [], } + + if get_option('b_sanitize').contains('address') + libgit_c_args += '-DNO_MMAP' + libgit_sources += 'compat/mmap.c' + else + checkfuncs += { 'mmap': ['mmap.c'] } + endif endif foreach func, impls : checkfuncs @@ -1486,7 +1492,7 @@ if not has_bsd_sysctl endif endif -if not meson.is_cross_build() and compiler.run(''' +if meson.can_run_host_binaries() and compiler.run(''' #include <stdio.h> int main(int argc, const char **argv) diff --git a/midx-write.c b/midx-write.c index c73010df6d..e3e9be6d03 100644 --- a/midx-write.c +++ b/midx-write.c @@ -697,28 +697,27 @@ static void prepare_midx_packing_data(struct packing_data *pdata, trace2_region_leave("midx", "prepare_midx_packing_data", ctx->repo); } -static int add_ref_to_pending(const char *refname, const char *referent UNUSED, - const struct object_id *oid, - int flag, void *cb_data) +static int add_ref_to_pending(const struct reference *ref, void *cb_data) { struct rev_info *revs = (struct rev_info*)cb_data; + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; struct object *object; - if ((flag & REF_ISSYMREF) && (flag & REF_ISBROKEN)) { - warning("symbolic ref is dangling: %s", refname); + if ((ref->flags & REF_ISSYMREF) && (ref->flags & REF_ISBROKEN)) { + warning("symbolic ref is dangling: %s", ref->name); return 0; } - if (!peel_iterated_oid(revs->repo, oid, &peeled)) - oid = &peeled; + if (!reference_get_peeled_oid(revs->repo, ref, &peeled)) + maybe_peeled = &peeled; - object = parse_object_or_die(revs->repo, oid, refname); + object = parse_object_or_die(revs->repo, maybe_peeled, ref->name); if (object->type != OBJ_COMMIT) return 0; add_pending_object(revs, object, ""); - if (bitmap_is_preferred_refname(revs->repo, refname)) + if (bitmap_is_preferred_refname(revs->repo, ref->name)) object->flags |= NEEDS_BITMAP; return 0; } @@ -1459,7 +1458,7 @@ static int write_midx_internal(struct odb_source *source, } if (ctx.m || ctx.base_midx) - close_object_store(ctx.repo->objects); + odb_close(ctx.repo->objects); if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); @@ -462,8 +462,6 @@ int prepare_midx_pack(struct multi_pack_index *m, m->pack_names[pack_int_id]); p = packfile_store_load_pack(r->objects->packfiles, pack_name.buf, m->source->local); - if (p) - list_add_tail(&p->mru, &r->objects->packfiles->mru); strbuf_release(&pack_name); if (!p) { diff --git a/negotiator/default.c b/negotiator/default.c index c479da9b09..116dedcf83 100644 --- a/negotiator/default.c +++ b/negotiator/default.c @@ -38,11 +38,10 @@ static void rev_list_push(struct negotiation_state *ns, } } -static int clear_marks(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data UNUSED) +static int clear_marks(const struct reference *ref, void *cb_data UNUSED) { - struct object *o = deref_tag(the_repository, parse_object(the_repository, oid), refname, 0); + struct object *o = deref_tag(the_repository, parse_object(the_repository, ref->oid), + ref->name, 0); if (o && o->type == OBJ_COMMIT) clear_commit_marks((struct commit *)o, diff --git a/negotiator/skipping.c b/negotiator/skipping.c index 616df6bf3a..0a272130fb 100644 --- a/negotiator/skipping.c +++ b/negotiator/skipping.c @@ -75,11 +75,10 @@ static struct entry *rev_list_push(struct data *data, struct commit *commit, int return entry; } -static int clear_marks(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data UNUSED) +static int clear_marks(const struct reference *ref, void *cb_data UNUSED) { - struct object *o = deref_tag(the_repository, parse_object(the_repository, oid), refname, 0); + struct object *o = deref_tag(the_repository, parse_object(the_repository, ref->oid), + ref->name, 0); if (o && o->type == OBJ_COMMIT) clear_commit_marks((struct commit *)o, @@ -938,13 +938,11 @@ out: return ret; } -static int string_list_add_one_ref(const char *refname, const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flag UNUSED, void *cb) +static int string_list_add_one_ref(const struct reference *ref, void *cb) { struct string_list *refs = cb; - if (!unsorted_string_list_has_string(refs, refname)) - string_list_append(refs, refname); + if (!unsorted_string_list_has_string(refs, ref->name)) + string_list_append(refs, ref->name); return 0; } diff --git a/object-file.c b/object-file.c index 4675c8ed6b..af1c3f972d 100644 --- a/object-file.c +++ b/object-file.c @@ -20,13 +20,13 @@ #include "object-file-convert.h" #include "object-file.h" #include "odb.h" +#include "odb/streaming.h" #include "oidtree.h" #include "pack.h" #include "packfile.h" #include "path.h" #include "read-cache-ll.h" #include "setup.h" -#include "streaming.h" #include "tempfile.h" #include "tmp-objdir.h" @@ -99,8 +99,8 @@ static int check_and_freshen_source(struct odb_source *source, return check_and_freshen_file(path.buf, freshen); } -int has_loose_object(struct odb_source *source, - const struct object_id *oid) +int odb_source_loose_has_object(struct odb_source *source, + const struct object_id *oid) { return check_and_freshen_source(source, oid, 0); } @@ -132,29 +132,27 @@ int check_object_signature(struct repository *r, const struct object_id *oid, int stream_object_signature(struct repository *r, const struct object_id *oid) { struct object_id real_oid; - unsigned long size; - enum object_type obj_type; - struct git_istream *st; + struct odb_read_stream *st; struct git_hash_ctx c; char hdr[MAX_HEADER_LEN]; int hdrlen; - st = open_istream(r, oid, &obj_type, &size, NULL); + st = odb_read_stream_open(r->objects, oid, NULL); if (!st) return -1; /* Generate the header */ - hdrlen = format_object_header(hdr, sizeof(hdr), obj_type, size); + hdrlen = format_object_header(hdr, sizeof(hdr), st->type, st->size); /* Sha1.. */ r->hash_algo->init_fn(&c); git_hash_update(&c, hdr, hdrlen); for (;;) { char buf[1024 * 16]; - ssize_t readlen = read_istream(st, buf, sizeof(buf)); + ssize_t readlen = odb_read_stream_read(st, buf, sizeof(buf)); if (readlen < 0) { - close_istream(st); + odb_read_stream_close(st); return -1; } if (!readlen) @@ -162,30 +160,27 @@ int stream_object_signature(struct repository *r, const struct object_id *oid) git_hash_update(&c, buf, readlen); } git_hash_final_oid(&real_oid, &c); - close_istream(st); + odb_read_stream_close(st); return !oideq(oid, &real_oid) ? -1 : 0; } /* - * Find "oid" as a loose object in the local repository or in an alternate. + * Find "oid" as a loose object in given source. * Returns 0 on success, negative on failure. * * The "path" out-parameter will give the path of the object we found (if any). * Note that it may point to static storage and is only valid until another * call to stat_loose_object(). */ -static int stat_loose_object(struct repository *r, const struct object_id *oid, +static int stat_loose_object(struct odb_source_loose *loose, + const struct object_id *oid, struct stat *st, const char **path) { - struct odb_source *source; static struct strbuf buf = STRBUF_INIT; - odb_prepare_alternates(r->objects); - for (source = r->objects->sources; source; source = source->next) { - *path = odb_loose_path(source, &buf, oid); - if (!lstat(*path, st)) - return 0; - } + *path = odb_loose_path(loose->source, &buf, oid); + if (!lstat(*path, st)) + return 0; return -1; } @@ -194,39 +189,24 @@ static int stat_loose_object(struct repository *r, const struct object_id *oid, * Like stat_loose_object(), but actually open the object and return the * descriptor. See the caveats on the "path" parameter above. */ -static int open_loose_object(struct repository *r, +static int open_loose_object(struct odb_source_loose *loose, const struct object_id *oid, const char **path) { - int fd; - struct odb_source *source; - int most_interesting_errno = ENOENT; static struct strbuf buf = STRBUF_INIT; + int fd; - odb_prepare_alternates(r->objects); - for (source = r->objects->sources; source; source = source->next) { - *path = odb_loose_path(source, &buf, oid); - fd = git_open(*path); - if (fd >= 0) - return fd; + *path = odb_loose_path(loose->source, &buf, oid); + fd = git_open(*path); + if (fd >= 0) + return fd; - if (most_interesting_errno == ENOENT) - most_interesting_errno = errno; - } - errno = most_interesting_errno; return -1; } -static int quick_has_loose(struct repository *r, +static int quick_has_loose(struct odb_source_loose *loose, const struct object_id *oid) { - struct odb_source *source; - - odb_prepare_alternates(r->objects); - for (source = r->objects->sources; source; source = source->next) { - if (oidtree_contains(odb_loose_cache(source, oid), oid)) - return 1; - } - return 0; + return !!oidtree_contains(odb_source_loose_cache(loose->source, oid), oid); } /* @@ -252,23 +232,41 @@ static void *map_fd(int fd, const char *path, unsigned long *size) return map; } -void *map_loose_object(struct repository *r, - const struct object_id *oid, - unsigned long *size) +static void *odb_source_loose_map_object(struct odb_source *source, + const struct object_id *oid, + unsigned long *size) { const char *p; - int fd = open_loose_object(r, oid, &p); + int fd = open_loose_object(source->loose, oid, &p); if (fd < 0) return NULL; return map_fd(fd, p, size); } -enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, - unsigned char *map, - unsigned long mapsize, - void *buffer, - unsigned long bufsiz) +enum unpack_loose_header_result { + ULHR_OK, + ULHR_BAD, + ULHR_TOO_LONG, +}; + +/** + * unpack_loose_header() initializes the data stream needed to unpack + * a loose object header. + * + * Returns: + * + * - ULHR_OK on success + * - ULHR_BAD on error + * - ULHR_TOO_LONG if the header was too long + * + * It will only parse up to MAX_HEADER_LEN bytes. + */ +static enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, + unsigned char *map, + unsigned long mapsize, + void *buffer, + unsigned long bufsiz) { int status; @@ -347,11 +345,18 @@ static void *unpack_loose_rest(git_zstream *stream, } /* + * parse_loose_header() parses the starting "<type> <len>\0" of an + * object. If it doesn't follow that format -1 is returned. To check + * the validity of the <type> populate the "typep" in the "struct + * object_info". It will be OBJ_BAD if the object type is unknown. The + * parsed <len> can be retrieved via "oi->sizep", and from there + * passed to unpack_loose_rest(). + * * We used to just use "sscanf()", but that's actually way * too permissive for what we want to check. So do an anal * object header parse by hand. */ -int parse_loose_header(const char *hdr, struct object_info *oi) +static int parse_loose_header(const char *hdr, struct object_info *oi) { const char *type_buf = hdr; size_t size; @@ -407,9 +412,9 @@ int parse_loose_header(const char *hdr, struct object_info *oi) return 0; } -int loose_object_info(struct repository *r, - const struct object_id *oid, - struct object_info *oi, int flags) +int odb_source_loose_read_object_info(struct odb_source *source, + const struct object_id *oid, + struct object_info *oi, int flags) { int status = 0; int fd; @@ -422,7 +427,7 @@ int loose_object_info(struct repository *r, enum object_type type_scratch; if (oi->delta_base_oid) - oidclr(oi->delta_base_oid, r->hash_algo); + oidclr(oi->delta_base_oid, source->odb->repo->hash_algo); /* * If we don't care about type or size, then we don't @@ -435,15 +440,15 @@ int loose_object_info(struct repository *r, if (!oi->typep && !oi->sizep && !oi->contentp) { struct stat st; if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK)) - return quick_has_loose(r, oid) ? 0 : -1; - if (stat_loose_object(r, oid, &st, &path) < 0) + return quick_has_loose(source->loose, oid) ? 0 : -1; + if (stat_loose_object(source->loose, oid, &st, &path) < 0) return -1; if (oi->disk_sizep) *oi->disk_sizep = st.st_size; return 0; } - fd = open_loose_object(r, oid, &path); + fd = open_loose_object(source->loose, oid, &path); if (fd < 0) { if (errno != ENOENT) error_errno(_("unable to open loose object %s"), oid_to_hex(oid)); @@ -986,35 +991,15 @@ static int write_loose_object(struct odb_source *source, FOF_SKIP_COLLISION_CHECK); } -static int freshen_loose_object(struct object_database *odb, - const struct object_id *oid) +int odb_source_loose_freshen_object(struct odb_source *source, + const struct object_id *oid) { - odb_prepare_alternates(odb); - for (struct odb_source *source = odb->sources; source; source = source->next) - if (check_and_freshen_source(source, oid, 1)) - return 1; - return 0; -} - -static int freshen_packed_object(struct object_database *odb, - const struct object_id *oid) -{ - struct pack_entry e; - if (!find_pack_entry(odb->repo, oid, &e)) - return 0; - if (e.p->is_cruft) - return 0; - if (e.p->freshened) - return 1; - if (!freshen_file(e.p->pack_name)) - return 0; - e.p->freshened = 1; - return 1; + return !!check_and_freshen_source(source, oid, 1); } -int stream_loose_object(struct odb_source *source, - struct input_stream *in_stream, size_t len, - struct object_id *oid) +int odb_source_loose_write_stream(struct odb_source *source, + struct odb_write_stream *in_stream, size_t len, + struct object_id *oid) { const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; struct object_id compat_oid; @@ -1091,12 +1076,10 @@ int stream_loose_object(struct odb_source *source, die(_("deflateEnd on stream object failed (%d)"), ret); close_loose_object(source, fd, tmp_file.buf); - if (freshen_packed_object(source->odb, oid) || - freshen_loose_object(source->odb, oid)) { + if (odb_freshen_object(source->odb, oid)) { unlink_or_warn(tmp_file.buf); goto cleanup; } - odb_loose_path(source, &filename, oid); /* We finally know the object path, and create the missing dir. */ @@ -1124,10 +1107,10 @@ cleanup: return err; } -int write_object_file(struct odb_source *source, - const void *buf, unsigned long len, - enum object_type type, struct object_id *oid, - struct object_id *compat_oid_in, unsigned flags) +int odb_source_loose_write_object(struct odb_source *source, + const void *buf, unsigned long len, + enum object_type type, struct object_id *oid, + struct object_id *compat_oid_in, unsigned flags) { const struct git_hash_algo *algo = source->odb->repo->hash_algo; const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; @@ -1155,8 +1138,7 @@ int write_object_file(struct odb_source *source, * it out into .git/objects/??/?{38} file. */ write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen); - if (freshen_packed_object(source->odb, oid) || - freshen_loose_object(source->odb, oid)) + if (odb_freshen_object(source->odb, oid)) return 0; if (write_loose_object(source, oid, hdr, hdrlen, buf, len, 0, flags)) return -1; @@ -1179,7 +1161,7 @@ int force_object_loose(struct odb_source *source, int ret; for (struct odb_source *s = source->odb->sources; s; s = s->next) - if (has_loose_object(s, oid)) + if (odb_source_loose_has_object(s, oid)) return 0; oi.typep = &type; @@ -1661,7 +1643,11 @@ int index_path(struct index_state *istate, struct object_id *oid, strbuf_release(&sb); break; case S_IFDIR: - return repo_resolve_gitlink_ref(istate->repo, path, "HEAD", oid); + if (repo_resolve_gitlink_ref(istate->repo, path, "HEAD", oid)) + return error(_("'%s' does not have a commit checked out"), path); + if (&hash_algos[oid->algo] != istate->repo->hash_algo) + return error(_("cannot add a submodule of a different hash algorithm")); + break; default: return error(_("%s: unsupported file type"), path); } @@ -1802,44 +1788,49 @@ static int append_loose_object(const struct object_id *oid, return 0; } -struct oidtree *odb_loose_cache(struct odb_source *source, - const struct object_id *oid) +struct oidtree *odb_source_loose_cache(struct odb_source *source, + const struct object_id *oid) { int subdir_nr = oid->hash[0]; struct strbuf buf = STRBUF_INIT; - size_t word_bits = bitsizeof(source->loose_objects_subdir_seen[0]); + size_t word_bits = bitsizeof(source->loose->subdir_seen[0]); size_t word_index = subdir_nr / word_bits; size_t mask = (size_t)1u << (subdir_nr % word_bits); uint32_t *bitmap; if (subdir_nr < 0 || - (size_t) subdir_nr >= bitsizeof(source->loose_objects_subdir_seen)) + (size_t) subdir_nr >= bitsizeof(source->loose->subdir_seen)) BUG("subdir_nr out of range"); - bitmap = &source->loose_objects_subdir_seen[word_index]; + bitmap = &source->loose->subdir_seen[word_index]; if (*bitmap & mask) - return source->loose_objects_cache; - if (!source->loose_objects_cache) { - ALLOC_ARRAY(source->loose_objects_cache, 1); - oidtree_init(source->loose_objects_cache); + return source->loose->cache; + if (!source->loose->cache) { + ALLOC_ARRAY(source->loose->cache, 1); + oidtree_init(source->loose->cache); } strbuf_addstr(&buf, source->path); for_each_file_in_obj_subdir(subdir_nr, &buf, source->odb->repo->hash_algo, append_loose_object, NULL, NULL, - source->loose_objects_cache); + source->loose->cache); *bitmap |= mask; strbuf_release(&buf); - return source->loose_objects_cache; + return source->loose->cache; +} + +static void odb_source_loose_clear_cache(struct odb_source_loose *loose) +{ + oidtree_clear(loose->cache); + FREE_AND_NULL(loose->cache); + memset(&loose->subdir_seen, 0, + sizeof(loose->subdir_seen)); } -void odb_clear_loose_cache(struct odb_source *source) +void odb_source_loose_reprepare(struct odb_source *source) { - oidtree_clear(source->loose_objects_cache); - FREE_AND_NULL(source->loose_objects_cache); - memset(&source->loose_objects_subdir_seen, 0, - sizeof(source->loose_objects_subdir_seen)); + odb_source_loose_clear_cache(source->loose); } static int check_stream_oid(git_zstream *stream, @@ -1995,3 +1986,144 @@ void object_file_transaction_commit(struct odb_transaction *transaction) transaction->odb->transaction = NULL; free(transaction); } + +struct odb_source_loose *odb_source_loose_new(struct odb_source *source) +{ + struct odb_source_loose *loose; + CALLOC_ARRAY(loose, 1); + loose->source = source; + return loose; +} + +void odb_source_loose_free(struct odb_source_loose *loose) +{ + if (!loose) + return; + odb_source_loose_clear_cache(loose); + loose_object_map_clear(&loose->map); + free(loose); +} + +struct odb_loose_read_stream { + struct odb_read_stream base; + git_zstream z; + enum { + ODB_LOOSE_READ_STREAM_INUSE, + ODB_LOOSE_READ_STREAM_DONE, + ODB_LOOSE_READ_STREAM_ERROR, + } z_state; + void *mapped; + unsigned long mapsize; + char hdr[32]; + int hdr_avail; + int hdr_used; +}; + +static ssize_t read_istream_loose(struct odb_read_stream *_st, char *buf, size_t sz) +{ + struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st; + size_t total_read = 0; + + switch (st->z_state) { + case ODB_LOOSE_READ_STREAM_DONE: + return 0; + case ODB_LOOSE_READ_STREAM_ERROR: + return -1; + default: + break; + } + + if (st->hdr_used < st->hdr_avail) { + size_t to_copy = st->hdr_avail - st->hdr_used; + if (sz < to_copy) + to_copy = sz; + memcpy(buf, st->hdr + st->hdr_used, to_copy); + st->hdr_used += to_copy; + total_read += to_copy; + } + + while (total_read < sz) { + int status; + + st->z.next_out = (unsigned char *)buf + total_read; + st->z.avail_out = sz - total_read; + status = git_inflate(&st->z, Z_FINISH); + + total_read = st->z.next_out - (unsigned char *)buf; + + if (status == Z_STREAM_END) { + git_inflate_end(&st->z); + st->z_state = ODB_LOOSE_READ_STREAM_DONE; + break; + } + if (status != Z_OK && (status != Z_BUF_ERROR || total_read < sz)) { + git_inflate_end(&st->z); + st->z_state = ODB_LOOSE_READ_STREAM_ERROR; + return -1; + } + } + return total_read; +} + +static int close_istream_loose(struct odb_read_stream *_st) +{ + struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st; + if (st->z_state == ODB_LOOSE_READ_STREAM_INUSE) + git_inflate_end(&st->z); + munmap(st->mapped, st->mapsize); + return 0; +} + +int odb_source_loose_read_object_stream(struct odb_read_stream **out, + struct odb_source *source, + const struct object_id *oid) +{ + struct object_info oi = OBJECT_INFO_INIT; + struct odb_loose_read_stream *st; + unsigned long mapsize; + void *mapped; + + mapped = odb_source_loose_map_object(source, oid, &mapsize); + if (!mapped) + return -1; + + /* + * Note: we must allocate this structure early even though we may still + * fail. This is because we need to initialize the zlib stream, and it + * is not possible to copy the stream around after the fact because it + * has self-referencing pointers. + */ + CALLOC_ARRAY(st, 1); + + switch (unpack_loose_header(&st->z, mapped, mapsize, st->hdr, + sizeof(st->hdr))) { + case ULHR_OK: + break; + case ULHR_BAD: + case ULHR_TOO_LONG: + goto error; + } + + oi.sizep = &st->base.size; + oi.typep = &st->base.type; + + if (parse_loose_header(st->hdr, &oi) < 0 || st->base.type < 0) + goto error; + + st->mapped = mapped; + st->mapsize = mapsize; + st->hdr_used = strlen(st->hdr) + 1; + st->hdr_avail = st->z.total_out; + st->z_state = ODB_LOOSE_READ_STREAM_INUSE; + st->base.close = close_istream_loose; + st->base.read = read_istream_loose; + + *out = &st->base; + + return 0; +error: + git_inflate_end(&st->z); + munmap(st->mapped, st->mapsize); + free(st); + return -1; +} diff --git a/object-file.h b/object-file.h index 3fd48dcafb..1229d5f675 100644 --- a/object-file.h +++ b/object-file.h @@ -7,14 +7,6 @@ struct index_state; -/* - * Set this to 0 to prevent odb_read_object_info_extended() from fetching missing - * blobs. This has a difference only if extensions.partialClone is set. - * - * Its default value is 1. - */ -extern int fetch_if_missing; - enum { INDEX_WRITE_OBJECT = (1 << 0), INDEX_FORMAT_CHECK = (1 << 1), @@ -24,17 +16,69 @@ enum { int index_fd(struct index_state *istate, struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags); int index_path(struct index_state *istate, struct object_id *oid, const char *path, struct stat *st, unsigned flags); +struct object_info; +struct odb_read_stream; struct odb_source; +struct odb_source_loose { + struct odb_source *source; + + /* + * Used to store the results of readdir(3) calls when we are OK + * sacrificing accuracy due to races for speed. That includes + * object existence with OBJECT_INFO_QUICK, as well as + * our search for unique abbreviated hashes. Don't use it for tasks + * requiring greater accuracy! + * + * Be sure to call odb_load_loose_cache() before using. + */ + uint32_t subdir_seen[8]; /* 256 bits */ + struct oidtree *cache; + + /* Map between object IDs for loose objects. */ + struct loose_object_map *map; +}; + +struct odb_source_loose *odb_source_loose_new(struct odb_source *source); +void odb_source_loose_free(struct odb_source_loose *loose); + +/* Reprepare the loose source by emptying the loose object cache. */ +void odb_source_loose_reprepare(struct odb_source *source); + +int odb_source_loose_read_object_info(struct odb_source *source, + const struct object_id *oid, + struct object_info *oi, int flags); + +int odb_source_loose_read_object_stream(struct odb_read_stream **out, + struct odb_source *source, + const struct object_id *oid); + /* - * Populate and return the loose object cache array corresponding to the - * given object ID. + * Return true iff an object database source has a loose object + * with the specified name. This function does not respect replace + * references. */ -struct oidtree *odb_loose_cache(struct odb_source *source, +int odb_source_loose_has_object(struct odb_source *source, const struct object_id *oid); -/* Empty the loose object cache for the specified object directory. */ -void odb_clear_loose_cache(struct odb_source *source); +int odb_source_loose_freshen_object(struct odb_source *source, + const struct object_id *oid); + +int odb_source_loose_write_object(struct odb_source *source, + const void *buf, unsigned long len, + enum object_type type, struct object_id *oid, + struct object_id *compat_oid_in, unsigned flags); + +int odb_source_loose_write_stream(struct odb_source *source, + struct odb_write_stream *stream, size_t len, + struct object_id *oid); + +/* + * Populate and return the loose object cache array corresponding to the + * given object ID. + */ +struct oidtree *odb_source_loose_cache(struct odb_source *source, + const struct object_id *oid); /* * Put in `buf` the name of the file in the local object database that @@ -45,17 +89,6 @@ const char *odb_loose_path(struct odb_source *source, const struct object_id *oid); /* - * Return true iff an object database source has a loose object - * with the specified name. This function does not respect replace - * references. - */ -int has_loose_object(struct odb_source *source, - const struct object_id *oid); - -void *map_loose_object(struct repository *r, const struct object_id *oid, - unsigned long *size); - -/* * Iterate over the files in the loose-object parts of the object * directory "path", triggering the following callbacks: * @@ -112,55 +145,6 @@ int for_each_loose_object(struct object_database *odb, int format_object_header(char *str, size_t size, enum object_type type, size_t objsize); -/** - * unpack_loose_header() initializes the data stream needed to unpack - * a loose object header. - * - * Returns: - * - * - ULHR_OK on success - * - ULHR_BAD on error - * - ULHR_TOO_LONG if the header was too long - * - * It will only parse up to MAX_HEADER_LEN bytes. - */ -enum unpack_loose_header_result { - ULHR_OK, - ULHR_BAD, - ULHR_TOO_LONG, -}; -enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, - unsigned char *map, - unsigned long mapsize, - void *buffer, - unsigned long bufsiz); - -/** - * parse_loose_header() parses the starting "<type> <len>\0" of an - * object. If it doesn't follow that format -1 is returned. To check - * the validity of the <type> populate the "typep" in the "struct - * object_info". It will be OBJ_BAD if the object type is unknown. The - * parsed <len> can be retrieved via "oi->sizep", and from there - * passed to unpack_loose_rest(). - */ -struct object_info; -int parse_loose_header(const char *hdr, struct object_info *oi); - -int write_object_file(struct odb_source *source, - const void *buf, unsigned long len, - enum object_type type, struct object_id *oid, - struct object_id *compat_oid_in, unsigned flags); - -struct input_stream { - const void *(*read)(struct input_stream *, unsigned long *len); - void *data; - int is_finished; -}; - -int stream_loose_object(struct odb_source *source, - struct input_stream *in_stream, size_t len, - struct object_id *oid); - int force_object_loose(struct odb_source *source, const struct object_id *oid, time_t mtime); @@ -182,10 +166,6 @@ int check_object_signature(struct repository *r, const struct object_id *oid, */ int stream_object_signature(struct repository *r, const struct object_id *oid); -int loose_object_info(struct repository *r, - const struct object_id *oid, - struct object_info *oi, int flags); - enum finalize_object_file_flags { FOF_SKIP_COLLISION_CHECK = 1, }; diff --git a/object-name.c b/object-name.c index 766c757042..fed5de5153 100644 --- a/object-name.c +++ b/object-name.c @@ -116,7 +116,7 @@ static void find_short_object_filename(struct disambiguate_state *ds) struct odb_source *source; for (source = ds->repo->objects->sources; source && !ds->ambiguous; source = source->next) - oidtree_each(odb_loose_cache(source, &ds->bin_pfx), + oidtree_each(odb_source_loose_cache(source, &ds->bin_pfx), &ds->bin_pfx, ds->len, match_prefix, ds); } @@ -1446,18 +1446,16 @@ struct handle_one_ref_cb { struct commit_list **list; }; -static int handle_one_ref(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int handle_one_ref(const struct reference *ref, void *cb_data) { struct handle_one_ref_cb *cb = cb_data; struct commit_list **list = cb->list; - struct object *object = parse_object(cb->repo, oid); + struct object *object = parse_object(cb->repo, ref->oid); if (!object) return 0; if (object->type == OBJ_TAG) { - object = deref_tag(cb->repo, object, path, - strlen(path)); + object = deref_tag(cb->repo, object, ref->name, + strlen(ref->name)); if (!object) return 0; } @@ -209,7 +209,8 @@ struct object *lookup_object_by_type(struct repository *r, enum peel_status peel_object(struct repository *r, const struct object_id *name, - struct object_id *oid) + struct object_id *oid, + unsigned flags) { struct object *o = lookup_unknown_object(r, name); @@ -222,7 +223,20 @@ enum peel_status peel_object(struct repository *r, if (o->type != OBJ_TAG) return PEEL_NON_TAG; - o = deref_tag_noverify(r, o); + while (o && o->type == OBJ_TAG) { + o = parse_object(r, &o->oid); + if (o && o->type == OBJ_TAG && ((struct tag *)o)->tagged) { + o = ((struct tag *)o)->tagged; + + if (flags & PEEL_OBJECT_VERIFY_TAGGED_OBJECT_TYPE) { + int type = odb_read_object_info(r->objects, &o->oid, NULL); + if (type < 0 || !object_as_type(o, type, 0)) + return PEEL_INVALID; + } + } else { + o = NULL; + } + } if (!o) return PEEL_INVALID; @@ -80,7 +80,6 @@ void object_array_init(struct object_array *array); * list-objects-filter.c: 21 * bloom.c: 2122 * builtin/fsck.c: 0--3 - * builtin/gc.c: 0 * builtin/index-pack.c: 2021 * reflog.c: 10--12 * builtin/show-branch.c: 0-------------------------------------------26 @@ -288,6 +287,17 @@ enum peel_status { PEEL_BROKEN = -4 }; +enum peel_object_flags { + /* + * Always verify the object type of the tagged object, even in the case + * where the looked-up object already has an object type. This can be + * useful when the tagged object type may be invalid. One such case is + * when looking up objects via tags, where we blindly trust the object + * type declared by the tag. + */ + PEEL_OBJECT_VERIFY_TAGGED_OBJECT_TYPE = (1 << 0), +}; + /* * Peel the named object; i.e., if the object is a tag, resolve the * tag recursively until a non-tag is found. If successful, store the @@ -296,7 +306,9 @@ enum peel_status { * and leave oid unchanged. */ enum peel_status peel_object(struct repository *r, - const struct object_id *name, struct object_id *oid); + const struct object_id *name, + struct object_id *oid, + unsigned flags); struct object_list *object_list_insert(struct object *item, struct object_list **list_p); @@ -1,5 +1,6 @@ #include "git-compat-util.h" #include "abspath.h" +#include "chdir-notify.h" #include "commit-graph.h" #include "config.h" #include "dir.h" @@ -9,6 +10,7 @@ #include "khash.h" #include "lockfile.h" #include "loose.h" +#include "midx.h" #include "object-file-convert.h" #include "object-file.h" #include "odb.h" @@ -22,6 +24,7 @@ #include "strbuf.h" #include "strvec.h" #include "submodule.h" +#include "tmp-objdir.h" #include "trace2.h" #include "write-or-die.h" @@ -86,17 +89,16 @@ int odb_mkstemp(struct object_database *odb, /* * Return non-zero iff the path is usable as an alternate object database. */ -static int alt_odb_usable(struct object_database *o, - struct strbuf *path, - const char *normalized_objdir, khiter_t *pos) +static int alt_odb_usable(struct object_database *o, const char *path, + const char *normalized_objdir) { int r; /* Detect cases where alternate disappeared */ - if (!is_directory(path->buf)) { + if (!is_directory(path)) { error(_("object directory %s does not exist; " "check .git/objects/info/alternates"), - path->buf); + path); return 0; } @@ -113,11 +115,14 @@ static int alt_odb_usable(struct object_database *o, assert(r == 1); /* never used */ kh_value(o->source_by_path, p) = o->sources; } - if (fspatheq(path->buf, normalized_objdir)) + + if (fspatheq(path, normalized_objdir)) + return 0; + + if (kh_get_odb_path_map(o->source_by_path, path) < kh_end(o->source_by_path)) return 0; - *pos = kh_put_odb_path_map(o->source_by_path, path->buf, &r); - /* r: 0 = exists, 1 = never used, 2 = deleted */ - return r == 0 ? 0 : 1; + + return 1; } /* @@ -139,6 +144,21 @@ static void read_info_alternates(struct object_database *odb, const char *relative_base, int depth); +static struct odb_source *odb_source_new(struct object_database *odb, + const char *path, + bool local) +{ + struct odb_source *source; + + CALLOC_ARRAY(source, 1); + source->odb = odb; + source->local = local; + source->path = xstrdup(path); + source->loose = odb_source_loose_new(source); + + return source; +} + static struct odb_source *link_alt_odb_entry(struct object_database *odb, const char *dir, const char *relative_base, @@ -148,6 +168,7 @@ static struct odb_source *link_alt_odb_entry(struct object_database *odb, struct strbuf pathbuf = STRBUF_INIT; struct strbuf tmp = STRBUF_INIT; khiter_t pos; + int ret; if (!is_absolute_path(dir) && relative_base) { strbuf_realpath(&pathbuf, relative_base, 1); @@ -172,20 +193,18 @@ static struct odb_source *link_alt_odb_entry(struct object_database *odb, strbuf_reset(&tmp); strbuf_realpath(&tmp, odb->sources->path, 1); - if (!alt_odb_usable(odb, &pathbuf, tmp.buf, &pos)) + if (!alt_odb_usable(odb, pathbuf.buf, tmp.buf)) goto error; - CALLOC_ARRAY(alternate, 1); - alternate->odb = odb; - alternate->local = false; - /* pathbuf.buf is already in r->objects->source_by_path */ - alternate->path = strbuf_detach(&pathbuf, NULL); + alternate = odb_source_new(odb, pathbuf.buf, false); /* add the alternate entry */ *odb->sources_tail = alternate; odb->sources_tail = &(alternate->next); - alternate->next = NULL; - assert(odb->source_by_path); + + pos = kh_put_odb_path_map(odb->source_by_path, alternate->path, &ret); + if (!ret) + BUG("source must not yet exist"); kh_value(odb->source_by_path, pos) = alternate; /* recursively add alternates */ @@ -337,26 +356,23 @@ struct odb_source *odb_set_temporary_primary_source(struct object_database *odb, * Make a new primary odb and link the old primary ODB in as an * alternate */ - source = xcalloc(1, sizeof(*source)); - source->odb = odb; - source->path = xstrdup(dir); + source = odb_source_new(odb, dir, false); /* * Disable ref updates while a temporary odb is active, since * the objects in the database may roll back. */ - source->disable_ref_updates = 1; + odb->repo->disable_ref_updates = true; source->will_destroy = will_destroy; source->next = odb->sources; odb->sources = source; return source->next; } -static void free_object_directory(struct odb_source *source) +static void odb_source_free(struct odb_source *source) { free(source->path); - odb_clear_loose_cache(source); - loose_object_map_clear(&source->loose_map); + odb_source_loose_free(source->loose); free(source); } @@ -373,8 +389,9 @@ void odb_restore_primary_source(struct object_database *odb, if (cur_source->next != restore_source) BUG("we expect the old primary object store to be the first alternate"); + odb->repo->disable_ref_updates = false; odb->sources = restore_source; - free_object_directory(cur_source); + odb_source_free(cur_source); } char *compute_alternate_path(const char *path, struct strbuf *err) @@ -653,8 +670,6 @@ static int do_oid_object_info_extended(struct object_database *odb, { static struct object_info blank_oi = OBJECT_INFO_INIT; const struct cached_object *co; - struct pack_entry e; - int rtype; const struct object_id *real = oid; int already_retried = 0; @@ -684,19 +699,24 @@ static int do_oid_object_info_extended(struct object_database *odb, return 0; } + odb_prepare_alternates(odb); + while (1) { - if (find_pack_entry(odb->repo, real, &e)) - break; + struct odb_source *source; - /* Most likely it's a loose object. */ - if (!loose_object_info(odb->repo, real, oi, flags)) + if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags)) return 0; + /* Most likely it's a loose object. */ + for (source = odb->sources; source; source = source->next) + if (!odb_source_loose_read_object_info(source, real, oi, flags)) + return 0; + /* Not a loose object; someone else may have just packed it. */ if (!(flags & OBJECT_INFO_QUICK)) { odb_reprepare(odb->repo->objects); - if (find_pack_entry(odb->repo, real, &e)) - break; + if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags)) + return 0; } /* @@ -729,25 +749,6 @@ static int do_oid_object_info_extended(struct object_database *odb, } return -1; } - - if (oi == &blank_oi) - /* - * We know that the caller doesn't actually need the - * information below, so return early. - */ - return 0; - rtype = packed_object_info(odb->repo, e.p, e.offset, oi); - if (rtype < 0) { - mark_bad_packed_object(e.p, real); - return do_oid_object_info_extended(odb, real, oi, 0); - } else if (oi->whence == OI_PACKED) { - oi->u.packed.offset = e.offset; - oi->u.packed.pack = e.p; - oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || - rtype == OBJ_OFS_DELTA); - } - - return 0; } static int oid_object_info_convert(struct repository *r, @@ -969,6 +970,22 @@ int odb_has_object(struct object_database *odb, const struct object_id *oid, return odb_read_object_info_extended(odb, oid, NULL, object_info_flags) >= 0; } +int odb_freshen_object(struct object_database *odb, + const struct object_id *oid) +{ + struct odb_source *source; + + if (packfile_store_freshen_object(odb->packfiles, oid)) + return 1; + + odb_prepare_alternates(odb); + for (source = odb->sources; source; source = source->next) + if (odb_source_loose_freshen_object(source, oid)) + return 1; + + return 0; +} + void odb_assert_oid_type(struct object_database *odb, const struct object_id *oid, enum object_type expect) { @@ -987,58 +1004,126 @@ int odb_write_object_ext(struct object_database *odb, struct object_id *compat_oid, unsigned flags) { - return write_object_file(odb->sources, buf, len, type, oid, compat_oid, flags); + return odb_source_loose_write_object(odb->sources, buf, len, type, + oid, compat_oid, flags); } -struct object_database *odb_new(struct repository *repo) +int odb_write_object_stream(struct object_database *odb, + struct odb_write_stream *stream, size_t len, + struct object_id *oid) +{ + return odb_source_loose_write_stream(odb->sources, stream, len, oid); +} + +static void odb_update_commondir(const char *name UNUSED, + const char *old_cwd, + const char *new_cwd, + void *cb_data) +{ + struct object_database *odb = cb_data; + struct tmp_objdir *tmp_objdir; + struct odb_source *source; + + tmp_objdir = tmp_objdir_unapply_primary_odb(); + + /* + * In theory, we only have to do this for the primary object source, as + * alternates' paths are always resolved to an absolute path. + */ + for (source = odb->sources; source; source = source->next) { + char *path; + + if (is_absolute_path(source->path)) + continue; + + path = reparent_relative_path(old_cwd, new_cwd, + source->path); + + free(source->path); + source->path = path; + } + + if (tmp_objdir) + tmp_objdir_reapply_primary_odb(tmp_objdir, old_cwd, new_cwd); +} + +struct object_database *odb_new(struct repository *repo, + const char *primary_source, + const char *secondary_sources) { struct object_database *o = xmalloc(sizeof(*o)); + char *to_free = NULL; memset(o, 0, sizeof(*o)); o->repo = repo; o->packfiles = packfile_store_new(o); pthread_mutex_init(&o->replace_mutex, NULL); string_list_init_dup(&o->submodule_source_paths); + + if (!primary_source) + primary_source = to_free = xstrfmt("%s/objects", repo->commondir); + o->sources = odb_source_new(o, primary_source, true); + o->sources_tail = &o->sources->next; + o->alternate_db = xstrdup_or_null(secondary_sources); + + free(to_free); + + chdir_notify_register(NULL, odb_update_commondir, o); + return o; } -static void free_object_directories(struct object_database *o) +void odb_close(struct object_database *o) +{ + struct odb_source *source; + + packfile_store_close(o->packfiles); + + for (source = o->sources; source; source = source->next) { + if (source->midx) + close_midx(source->midx); + source->midx = NULL; + } + + close_commit_graph(o); +} + +static void odb_free_sources(struct object_database *o) { while (o->sources) { struct odb_source *next; next = o->sources->next; - free_object_directory(o->sources); + odb_source_free(o->sources); o->sources = next; } kh_destroy_odb_path_map(o->source_by_path); o->source_by_path = NULL; } -void odb_clear(struct object_database *o) +void odb_free(struct object_database *o) { - FREE_AND_NULL(o->alternate_db); + if (!o) + return; + + free(o->alternate_db); oidmap_clear(&o->replace_map, 1); pthread_mutex_destroy(&o->replace_mutex); - free_commit_graph(o->commit_graph); - o->commit_graph = NULL; - o->commit_graph_attempted = 0; - - free_object_directories(o); - o->sources_tail = NULL; - o->loaded_alternates = 0; + odb_free_sources(o); for (size_t i = 0; i < o->cached_object_nr; i++) free((char *) o->cached_objects[i].value.buf); - FREE_AND_NULL(o->cached_objects); + free(o->cached_objects); - close_object_store(o); + odb_close(o); packfile_store_free(o->packfiles); - o->packfiles = NULL; - string_list_clear(&o->submodule_source_paths, 0); + + chdir_notify_unregister(NULL, odb_update_commondir, o); + + free(o); } void odb_reprepare(struct object_database *o) @@ -1057,7 +1142,7 @@ void odb_reprepare(struct object_database *o) odb_prepare_alternates(o); for (source = o->sources; source; source = source->next) - odb_clear_loose_cache(source); + odb_source_loose_reprepare(source); o->approximate_object_count_valid = 0; @@ -15,6 +15,14 @@ struct repository; struct multi_pack_index; /* + * Set this to 0 to prevent odb_read_object_info_extended() from fetching missing + * blobs. This has a difference only if extensions.partialClone is set. + * + * Its default value is 1. + */ +extern int fetch_if_missing; + +/* * Compute the exact path an alternate is at and returns it. In case of * error NULL is returned and the human readable error is added to `err` * `path` may be relative and should point to $GIT_DIR. @@ -40,20 +48,8 @@ struct odb_source { /* Object database that owns this object source. */ struct object_database *odb; - /* - * Used to store the results of readdir(3) calls when we are OK - * sacrificing accuracy due to races for speed. That includes - * object existence with OBJECT_INFO_QUICK, as well as - * our search for unique abbreviated hashes. Don't use it for tasks - * requiring greater accuracy! - * - * Be sure to call odb_load_loose_cache() before using. - */ - uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ - struct oidtree *loose_objects_cache; - - /* Map between object IDs for loose objects. */ - struct loose_object_map *loose_map; + /* Private state for loose objects. */ + struct odb_source_loose *loose; /* * private data @@ -71,13 +67,6 @@ struct odb_source { bool local; /* - * This is a temporary object store created by the tmp_objdir - * facility. Disable ref updates since the objects in the store - * might be discarded on rollback. - */ - int disable_ref_updates; - - /* * This object store is ephemeral, so there is no need to fsync. */ int will_destroy; @@ -166,8 +155,30 @@ struct object_database { struct string_list submodule_source_paths; }; -struct object_database *odb_new(struct repository *repo); -void odb_clear(struct object_database *o); +/* + * Create a new object database for the given repository. + * + * If the primary source parameter is set it will override the usual primary + * object directory derived from the repository's common directory. The + * alternate sources are expected to be a PATH_SEP-separated list of secondary + * sources. Note that these alternate sources will be added in addition to, not + * instead of, the alternates identified by the primary source. + * + * Returns the newly created object database. + */ +struct object_database *odb_new(struct repository *repo, + const char *primary_source, + const char *alternate_sources); + +/* Free the object database and release all resources. */ +void odb_free(struct object_database *o); + +/* + * Close the object database and all of its sources so that any held resources + * will be released. The database can still be used after closing it, in which + * case these resources may be reallocated. + */ +void odb_close(struct object_database *o); /* * Clear caches, reload alternates and then reload object sources so that new @@ -396,6 +407,9 @@ int odb_has_object(struct object_database *odb, const struct object_id *oid, unsigned flags); +int odb_freshen_object(struct object_database *odb, + const struct object_id *oid); + void odb_assert_oid_type(struct object_database *odb, const struct object_id *oid, enum object_type expect); @@ -489,4 +503,14 @@ static inline int odb_write_object(struct object_database *odb, return odb_write_object_ext(odb, buf, len, type, oid, NULL, 0); } +struct odb_write_stream { + const void *(*read)(struct odb_write_stream *, unsigned long *len); + void *data; + int is_finished; +}; + +int odb_write_object_stream(struct object_database *odb, + struct odb_write_stream *stream, size_t len, + struct object_id *oid); + #endif /* ODB_H */ diff --git a/odb/streaming.c b/odb/streaming.c new file mode 100644 index 0000000000..745cd486fb --- /dev/null +++ b/odb/streaming.c @@ -0,0 +1,293 @@ +/* + * Copyright (c) 2011, Google Inc. + */ + +#include "git-compat-util.h" +#include "convert.h" +#include "environment.h" +#include "repository.h" +#include "object-file.h" +#include "odb.h" +#include "odb/streaming.h" +#include "replace-object.h" +#include "packfile.h" + +#define FILTER_BUFFER (1024*16) + +/***************************************************************** + * + * Filtered stream + * + *****************************************************************/ + +struct odb_filtered_read_stream { + struct odb_read_stream base; + struct odb_read_stream *upstream; + struct stream_filter *filter; + char ibuf[FILTER_BUFFER]; + char obuf[FILTER_BUFFER]; + int i_end, i_ptr; + int o_end, o_ptr; + int input_finished; +}; + +static int close_istream_filtered(struct odb_read_stream *_fs) +{ + struct odb_filtered_read_stream *fs = (struct odb_filtered_read_stream *)_fs; + free_stream_filter(fs->filter); + return odb_read_stream_close(fs->upstream); +} + +static ssize_t read_istream_filtered(struct odb_read_stream *_fs, char *buf, + size_t sz) +{ + struct odb_filtered_read_stream *fs = (struct odb_filtered_read_stream *)_fs; + size_t filled = 0; + + while (sz) { + /* do we already have filtered output? */ + if (fs->o_ptr < fs->o_end) { + size_t to_move = fs->o_end - fs->o_ptr; + if (sz < to_move) + to_move = sz; + memcpy(buf + filled, fs->obuf + fs->o_ptr, to_move); + fs->o_ptr += to_move; + sz -= to_move; + filled += to_move; + continue; + } + fs->o_end = fs->o_ptr = 0; + + /* do we have anything to feed the filter with? */ + if (fs->i_ptr < fs->i_end) { + size_t to_feed = fs->i_end - fs->i_ptr; + size_t to_receive = FILTER_BUFFER; + if (stream_filter(fs->filter, + fs->ibuf + fs->i_ptr, &to_feed, + fs->obuf, &to_receive)) + return -1; + fs->i_ptr = fs->i_end - to_feed; + fs->o_end = FILTER_BUFFER - to_receive; + continue; + } + + /* tell the filter to drain upon no more input */ + if (fs->input_finished) { + size_t to_receive = FILTER_BUFFER; + if (stream_filter(fs->filter, + NULL, NULL, + fs->obuf, &to_receive)) + return -1; + fs->o_end = FILTER_BUFFER - to_receive; + if (!fs->o_end) + break; + continue; + } + fs->i_end = fs->i_ptr = 0; + + /* refill the input from the upstream */ + if (!fs->input_finished) { + fs->i_end = odb_read_stream_read(fs->upstream, fs->ibuf, FILTER_BUFFER); + if (fs->i_end < 0) + return -1; + if (fs->i_end) + continue; + } + fs->input_finished = 1; + } + return filled; +} + +static struct odb_read_stream *attach_stream_filter(struct odb_read_stream *st, + struct stream_filter *filter) +{ + struct odb_filtered_read_stream *fs; + + CALLOC_ARRAY(fs, 1); + fs->base.close = close_istream_filtered; + fs->base.read = read_istream_filtered; + fs->upstream = st; + fs->filter = filter; + fs->base.size = -1; /* unknown */ + fs->base.type = st->type; + + return &fs->base; +} + +/***************************************************************** + * + * In-core stream + * + *****************************************************************/ + +struct odb_incore_read_stream { + struct odb_read_stream base; + char *buf; /* from odb_read_object_info_extended() */ + unsigned long read_ptr; +}; + +static int close_istream_incore(struct odb_read_stream *_st) +{ + struct odb_incore_read_stream *st = (struct odb_incore_read_stream *)_st; + free(st->buf); + return 0; +} + +static ssize_t read_istream_incore(struct odb_read_stream *_st, char *buf, size_t sz) +{ + struct odb_incore_read_stream *st = (struct odb_incore_read_stream *)_st; + size_t read_size = sz; + size_t remainder = st->base.size - st->read_ptr; + + if (remainder <= read_size) + read_size = remainder; + if (read_size) { + memcpy(buf, st->buf + st->read_ptr, read_size); + st->read_ptr += read_size; + } + return read_size; +} + +static int open_istream_incore(struct odb_read_stream **out, + struct object_database *odb, + const struct object_id *oid) +{ + struct object_info oi = OBJECT_INFO_INIT; + struct odb_incore_read_stream stream = { + .base.close = close_istream_incore, + .base.read = read_istream_incore, + }; + struct odb_incore_read_stream *st; + int ret; + + oi.typep = &stream.base.type; + oi.sizep = &stream.base.size; + oi.contentp = (void **)&stream.buf; + ret = odb_read_object_info_extended(odb, oid, &oi, + OBJECT_INFO_DIE_IF_CORRUPT); + if (ret) + return ret; + + CALLOC_ARRAY(st, 1); + *st = stream; + *out = &st->base; + + return 0; +} + +/***************************************************************************** + * static helpers variables and functions for users of streaming interface + *****************************************************************************/ + +static int istream_source(struct odb_read_stream **out, + struct object_database *odb, + const struct object_id *oid) +{ + struct odb_source *source; + + if (!packfile_store_read_object_stream(out, odb->packfiles, oid)) + return 0; + + odb_prepare_alternates(odb); + for (source = odb->sources; source; source = source->next) + if (!odb_source_loose_read_object_stream(out, source, oid)) + return 0; + + return open_istream_incore(out, odb, oid); +} + +/**************************************************************** + * Users of streaming interface + ****************************************************************/ + +int odb_read_stream_close(struct odb_read_stream *st) +{ + int r = st->close(st); + free(st); + return r; +} + +ssize_t odb_read_stream_read(struct odb_read_stream *st, void *buf, size_t sz) +{ + return st->read(st, buf, sz); +} + +struct odb_read_stream *odb_read_stream_open(struct object_database *odb, + const struct object_id *oid, + struct stream_filter *filter) +{ + struct odb_read_stream *st; + const struct object_id *real = lookup_replace_object(odb->repo, oid); + int ret = istream_source(&st, odb, real); + + if (ret) + return NULL; + + if (filter) { + /* Add "&& !is_null_stream_filter(filter)" for performance */ + struct odb_read_stream *nst = attach_stream_filter(st, filter); + if (!nst) { + odb_read_stream_close(st); + return NULL; + } + st = nst; + } + + return st; +} + +int odb_stream_blob_to_fd(struct object_database *odb, + int fd, + const struct object_id *oid, + struct stream_filter *filter, + int can_seek) +{ + struct odb_read_stream *st; + ssize_t kept = 0; + int result = -1; + + st = odb_read_stream_open(odb, oid, filter); + if (!st) { + if (filter) + free_stream_filter(filter); + return result; + } + if (st->type != OBJ_BLOB) + goto close_and_exit; + for (;;) { + char buf[1024 * 16]; + ssize_t wrote, holeto; + ssize_t readlen = odb_read_stream_read(st, buf, sizeof(buf)); + + if (readlen < 0) + goto close_and_exit; + if (!readlen) + break; + if (can_seek && sizeof(buf) == readlen) { + for (holeto = 0; holeto < readlen; holeto++) + if (buf[holeto]) + break; + if (readlen == holeto) { + kept += holeto; + continue; + } + } + + if (kept && lseek(fd, kept, SEEK_CUR) == (off_t) -1) + goto close_and_exit; + else + kept = 0; + wrote = write_in_full(fd, buf, readlen); + + if (wrote < 0) + goto close_and_exit; + } + if (kept && (lseek(fd, kept - 1, SEEK_CUR) == (off_t) -1 || + xwrite(fd, "", 1) != 1)) + goto close_and_exit; + result = 0; + + close_and_exit: + odb_read_stream_close(st); + return result; +} diff --git a/odb/streaming.h b/odb/streaming.h new file mode 100644 index 0000000000..c7861f7e13 --- /dev/null +++ b/odb/streaming.h @@ -0,0 +1,67 @@ +/* + * Copyright (c) 2011, Google Inc. + */ +#ifndef STREAMING_H +#define STREAMING_H 1 + +#include "object.h" + +struct object_database; +struct odb_read_stream; +struct stream_filter; + +typedef int (*odb_read_stream_close_fn)(struct odb_read_stream *); +typedef ssize_t (*odb_read_stream_read_fn)(struct odb_read_stream *, char *, size_t); + +/* + * A stream that can be used to read an object from the object database without + * loading all of it into memory. + */ +struct odb_read_stream { + odb_read_stream_close_fn close; + odb_read_stream_read_fn read; + enum object_type type; + unsigned long size; /* inflated size of full object */ +}; + +/* + * Create a new object stream for the given object database. An optional filter + * can be used to transform the object's content. + * + * Returns the stream on success, a `NULL` pointer otherwise. + */ +struct odb_read_stream *odb_read_stream_open(struct object_database *odb, + const struct object_id *oid, + struct stream_filter *filter); + +/* + * Close the given read stream and release all resources associated with it. + * Returns 0 on success, a negative error code otherwise. + */ +int odb_read_stream_close(struct odb_read_stream *stream); + +/* + * Read data from the stream into the buffer. Returns 0 on EOF and the number + * of bytes read on success. Returns a negative error code in case reading from + * the stream fails. + */ +ssize_t odb_read_stream_read(struct odb_read_stream *stream, void *buf, size_t len); + +/* + * Look up the object by its ID and write the full contents to the file + * descriptor. The object must be a blob, or the function will fail. When + * provided, the filter is used to transform the blob contents. + * + * `can_seek` should be set to 1 in case the given file descriptor can be + * seek(3p)'d on. This is used to support files with holes in case a + * significant portion of the blob contains NUL bytes. + * + * Returns a negative error code on failure, 0 on success. + */ +int odb_stream_blob_to_fd(struct object_database *odb, + int fd, + const struct object_id *oid, + struct stream_filter *filter, + int can_seek); + +#endif /* STREAMING_H */ @@ -16,6 +16,22 @@ int oidset_contains(const struct oidset *set, const struct object_id *oid) return pos != kh_end(&set->set); } +bool oidset_equal(const struct oidset *a, const struct oidset *b) +{ + struct oidset_iter iter; + struct object_id *a_oid; + + if (oidset_size(a) != oidset_size(b)) + return false; + + oidset_iter_init(a, &iter); + while ((a_oid = oidset_iter_next(&iter))) + if (!oidset_contains(b, a_oid)) + return false; + + return true; +} + int oidset_insert(struct oidset *set, const struct object_id *oid) { int added; @@ -39,6 +39,11 @@ void oidset_init(struct oidset *set, size_t initial_size); int oidset_contains(const struct oidset *set, const struct object_id *oid); /** + * Returns true iff `a` and `b` contain the exact same OIDs. + */ +bool oidset_equal(const struct oidset *a, const struct oidset *b); + +/** * Insert the oid into the set; a copy is made, so "oid" does not need * to persist after this function is called. * @@ -94,11 +99,11 @@ void oidset_parse_file_carefully(struct oidset *set, const char *path, oidset_parse_tweak_fn fn, void *cbdata); struct oidset_iter { - kh_oid_set_t *set; + const kh_oid_set_t *set; khiter_t iter; }; -static inline void oidset_iter_init(struct oidset *set, +static inline void oidset_iter_init(const struct oidset *set, struct oidset_iter *iter) { iter->set = &set->set; diff --git a/pack-bitmap.c b/pack-bitmap.c index 291e1a9cf4..8ca79725b1 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -213,6 +213,28 @@ static uint32_t bitmap_num_objects(struct bitmap_index *index) return index->pack->num_objects; } +static uint32_t bitmap_name_hash(struct bitmap_index *index, uint32_t pos) +{ + if (bitmap_is_midx(index)) { + while (index && pos < index->midx->num_objects_in_base) { + ASSERT(bitmap_is_midx(index)); + index = index->base; + } + + if (!index) + BUG("NULL base bitmap for object position: %"PRIu32, pos); + + pos -= index->midx->num_objects_in_base; + if (pos >= index->midx->num_objects) + BUG("out-of-bounds midx bitmap object at %"PRIu32, pos); + } + + if (!index->hashes) + return 0; + + return get_be32(index->hashes + pos); +} + static struct repository *bitmap_repo(struct bitmap_index *bitmap_git) { if (bitmap_is_midx(bitmap_git)) @@ -1724,8 +1746,7 @@ static void show_objects_for_type( pack = bitmap_git->pack; } - if (bitmap_git->hashes) - hash = get_be32(bitmap_git->hashes + index_pos); + hash = bitmap_name_hash(bitmap_git, index_pos); show_reach(&oid, object_type, 0, hash, pack, ofs, payload); } @@ -3124,8 +3145,8 @@ uint32_t *create_bitmap_mapping(struct bitmap_index *bitmap_git, if (oe) { reposition[i] = oe_in_pack_pos(mapping, oe) + 1; - if (bitmap_git->hashes && !oe->hash) - oe->hash = get_be32(bitmap_git->hashes + index_pos); + if (!oe->hash) + oe->hash = bitmap_name_hash(bitmap_git, index_pos); } } diff --git a/pack-refs.c b/pack-refs.c index 1a5e07d8b8..eb6b2ba2c2 100644 --- a/pack-refs.c +++ b/pack-refs.c @@ -14,10 +14,10 @@ int pack_refs_core(int argc, { struct ref_exclusions excludes = REF_EXCLUSIONS_INIT; struct string_list included_refs = STRING_LIST_INIT_NODUP; - struct pack_refs_opts pack_refs_opts = { + struct refs_optimize_opts optimize_opts = { .exclusions = &excludes, .includes = &included_refs, - .flags = PACK_REFS_PRUNE, + .flags = REFS_OPTIMIZE_PRUNE, }; struct string_list option_excluded_refs = STRING_LIST_INIT_NODUP; struct string_list_item *item; @@ -26,9 +26,9 @@ int pack_refs_core(int argc, struct option opts[] = { OPT_BOOL(0, "all", &pack_all, N_("pack everything")), - OPT_BIT(0, "prune", &pack_refs_opts.flags, N_("prune loose refs (default)"), PACK_REFS_PRUNE), - OPT_BIT(0, "auto", &pack_refs_opts.flags, N_("auto-pack refs as needed"), PACK_REFS_AUTO), - OPT_STRING_LIST(0, "include", pack_refs_opts.includes, N_("pattern"), + OPT_BIT(0, "prune", &optimize_opts.flags, N_("prune loose refs (default)"), REFS_OPTIMIZE_PRUNE), + OPT_BIT(0, "auto", &optimize_opts.flags, N_("auto-pack refs as needed"), REFS_OPTIMIZE_AUTO), + OPT_STRING_LIST(0, "include", optimize_opts.includes, N_("pattern"), N_("references to include")), OPT_STRING_LIST(0, "exclude", &option_excluded_refs, N_("pattern"), N_("references to exclude")), @@ -39,15 +39,15 @@ int pack_refs_core(int argc, usage_with_options(usage_opts, opts); for_each_string_list_item(item, &option_excluded_refs) - add_ref_exclusion(pack_refs_opts.exclusions, item->string); + add_ref_exclusion(optimize_opts.exclusions, item->string); if (pack_all) - string_list_append(pack_refs_opts.includes, "*"); + string_list_append(optimize_opts.includes, "*"); - if (!pack_refs_opts.includes->nr) - string_list_append(pack_refs_opts.includes, "refs/tags/*"); + if (!optimize_opts.includes->nr) + string_list_append(optimize_opts.includes, "refs/tags/*"); - ret = refs_optimize(get_main_ref_store(repo), &pack_refs_opts); + ret = refs_optimize(get_main_ref_store(repo), &optimize_opts); clear_ref_exclusions(&excludes); string_list_clear(&included_refs, 0); diff --git a/packfile.c b/packfile.c index 1ae2b2fe1e..c88bd92619 100644 --- a/packfile.c +++ b/packfile.c @@ -20,6 +20,7 @@ #include "tree.h" #include "object-file.h" #include "odb.h" +#include "odb/streaming.h" #include "midx.h" #include "commit-graph.h" #include "pack-revindex.h" @@ -47,6 +48,89 @@ static size_t pack_mapped; #define SZ_FMT PRIuMAX static inline uintmax_t sz_fmt(size_t s) { return s; } +void packfile_list_clear(struct packfile_list *list) +{ + struct packfile_list_entry *e, *next; + + for (e = list->head; e; e = next) { + next = e->next; + free(e); + } + + list->head = list->tail = NULL; +} + +static struct packfile_list_entry *packfile_list_remove_internal(struct packfile_list *list, + struct packed_git *pack) +{ + struct packfile_list_entry *e, *prev; + + for (e = list->head, prev = NULL; e; prev = e, e = e->next) { + if (e->pack != pack) + continue; + + if (prev) + prev->next = e->next; + if (list->head == e) + list->head = e->next; + if (list->tail == e) + list->tail = prev; + + return e; + } + + return NULL; +} + +void packfile_list_remove(struct packfile_list *list, struct packed_git *pack) +{ + free(packfile_list_remove_internal(list, pack)); +} + +void packfile_list_prepend(struct packfile_list *list, struct packed_git *pack) +{ + struct packfile_list_entry *entry; + + entry = packfile_list_remove_internal(list, pack); + if (!entry) { + entry = xmalloc(sizeof(*entry)); + entry->pack = pack; + } + entry->next = list->head; + + list->head = entry; + if (!list->tail) + list->tail = entry; +} + +void packfile_list_append(struct packfile_list *list, struct packed_git *pack) +{ + struct packfile_list_entry *entry; + + entry = packfile_list_remove_internal(list, pack); + if (!entry) { + entry = xmalloc(sizeof(*entry)); + entry->pack = pack; + } + entry->next = NULL; + + if (list->tail) { + list->tail->next = entry; + list->tail = entry; + } else { + list->head = list->tail = entry; + } +} + +struct packed_git *packfile_list_find_oid(struct packfile_list_entry *packs, + const struct object_id *oid) +{ + for (; packs; packs = packs->next) + if (find_pack_entry_one(oid, packs->pack)) + return packs->pack; + return NULL; +} + void pack_report(struct repository *repo) { fprintf(stderr, @@ -273,13 +357,14 @@ static void scan_windows(struct packed_git *p, static int unuse_one_window(struct packed_git *current) { - struct packed_git *p, *lru_p = NULL; + struct packfile_list_entry *e; + struct packed_git *lru_p = NULL; struct pack_window *lru_w = NULL, *lru_l = NULL; if (current) scan_windows(current, &lru_p, &lru_w, &lru_l); - for (p = current->repo->objects->packfiles->packs; p; p = p->next) - scan_windows(p, &lru_p, &lru_w, &lru_l); + for (e = current->repo->objects->packfiles->packs.head; e; e = e->next) + scan_windows(e->pack, &lru_p, &lru_w, &lru_l); if (lru_p) { munmap(lru_w->base, lru_w->len); pack_mapped -= lru_w->len; @@ -359,21 +444,6 @@ void close_pack(struct packed_git *p) oidset_clear(&p->bad_objects); } -void close_object_store(struct object_database *o) -{ - struct odb_source *source; - - packfile_store_close(o->packfiles); - - for (source = o->sources; source; source = source->next) { - if (source->midx) - close_midx(source->midx); - source->midx = NULL; - } - - close_commit_graph(o); -} - void unlink_pack_path(const char *pack_name, int force_delete) { static const char *exts[] = {".idx", ".pack", ".rev", ".keep", ".bitmap", ".promisor", ".mtimes"}; @@ -459,14 +529,15 @@ static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struc static int close_one_pack(struct repository *r) { - struct packed_git *p, *lru_p = NULL; + struct packfile_list_entry *e; + struct packed_git *lru_p = NULL; struct pack_window *mru_w = NULL; int accept_windows_inuse = 1; - for (p = r->objects->packfiles->packs; p; p = p->next) { - if (p->pack_fd == -1) + for (e = r->objects->packfiles->packs.head; e; e = e->next) { + if (e->pack->pack_fd == -1) continue; - find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); + find_lru_pack(e->pack, &lru_p, &mru_w, &accept_windows_inuse); } if (lru_p) @@ -785,11 +856,8 @@ void packfile_store_add_pack(struct packfile_store *store, if (pack->pack_fd != -1) pack_open_fds++; - pack->next = store->packs; - store->packs = pack; - - hashmap_entry_init(&pack->packmap_ent, strhash(pack->pack_name)); - hashmap_add(&store->map, &pack->packmap_ent); + packfile_list_append(&store->packs, pack); + strmap_put(&store->packs_by_path, pack->pack_name, pack); } struct packed_git *packfile_store_load_pack(struct packfile_store *store, @@ -806,8 +874,7 @@ struct packed_git *packfile_store_load_pack(struct packfile_store *store, strbuf_strip_suffix(&key, ".idx"); strbuf_addstr(&key, ".pack"); - p = hashmap_get_entry_from_hash(&store->map, strhash(key.buf), key.buf, - struct packed_git, packmap_ent); + p = strmap_get(&store->packs_by_path, key.buf); if (!p) { p = add_packed_git(store->odb->repo, idx_path, strlen(idx_path), local); @@ -965,9 +1032,10 @@ static void prepare_packed_git_one(struct odb_source *source) string_list_clear(data.garbage, 0); } -DEFINE_LIST_SORT(static, sort_packs, struct packed_git, next); +DEFINE_LIST_SORT(static, sort_packs, struct packfile_list_entry, next); -static int sort_pack(const struct packed_git *a, const struct packed_git *b) +static int sort_pack(const struct packfile_list_entry *a, + const struct packfile_list_entry *b) { int st; @@ -977,7 +1045,7 @@ static int sort_pack(const struct packed_git *a, const struct packed_git *b) * remote ones could be on a network mounted filesystem. * Favor local ones for these reasons. */ - st = a->pack_local - b->pack_local; + st = a->pack->pack_local - b->pack->pack_local; if (st) return -st; @@ -986,23 +1054,13 @@ static int sort_pack(const struct packed_git *a, const struct packed_git *b) * and more recent objects tend to get accessed more * often. */ - if (a->mtime < b->mtime) + if (a->pack->mtime < b->pack->mtime) return 1; - else if (a->mtime == b->mtime) + else if (a->pack->mtime == b->pack->mtime) return 0; return -1; } -static void packfile_store_prepare_mru(struct packfile_store *store) -{ - struct packed_git *p; - - INIT_LIST_HEAD(&store->mru); - - for (p = store->packs; p; p = p->next) - list_add_tail(&p->mru, &store->mru); -} - void packfile_store_prepare(struct packfile_store *store) { struct odb_source *source; @@ -1015,9 +1073,12 @@ void packfile_store_prepare(struct packfile_store *store) prepare_multi_pack_index_one(source); prepare_packed_git_one(source); } - sort_packs(&store->packs, sort_pack); - packfile_store_prepare_mru(store); + sort_packs(&store->packs.head, sort_pack); + for (struct packfile_list_entry *e = store->packs.head; e; e = e->next) + if (!e->next) + store->packs.tail = e; + store->initialized = true; } @@ -1027,7 +1088,7 @@ void packfile_store_reprepare(struct packfile_store *store) packfile_store_prepare(store); } -struct packed_git *packfile_store_get_packs(struct packfile_store *store) +struct packfile_list_entry *packfile_store_get_packs(struct packfile_store *store) { packfile_store_prepare(store); @@ -1039,13 +1100,7 @@ struct packed_git *packfile_store_get_packs(struct packfile_store *store) prepare_midx_pack(m, i); } - return store->packs; -} - -struct list_head *packfile_store_get_packs_mru(struct packfile_store *store) -{ - packfile_store_prepare(store); - return &store->mru; + return store->packs.head; } /* @@ -1062,16 +1117,16 @@ unsigned long repo_approximate_object_count(struct repository *r) unsigned long count = 0; struct packed_git *p; - packfile_store_prepare(r->objects->packfiles); + odb_prepare_alternates(r->objects); for (source = r->objects->sources; source; source = source->next) { struct multi_pack_index *m = get_multi_pack_index(source); if (m) - count += m->num_objects; + count += m->num_objects + m->num_objects_in_base; } - for (p = r->objects->packfiles->packs; p; p = p->next) { - if (open_pack_index(p)) + repo_for_each_pack(r, p) { + if (p->multi_pack_index || open_pack_index(p)) continue; count += p->num_objects; } @@ -1195,11 +1250,11 @@ void mark_bad_packed_object(struct packed_git *p, const struct object_id *oid) const struct packed_git *has_packed_and_bad(struct repository *r, const struct object_id *oid) { - struct packed_git *p; + struct packfile_list_entry *e; - for (p = r->objects->packfiles->packs; p; p = p->next) - if (oidset_contains(&p->bad_objects, oid)) - return p; + for (e = r->objects->packfiles->packs.head; e; e = e->next) + if (oidset_contains(&e->pack->bad_objects, oid)) + return e->pack; return NULL; } @@ -2007,19 +2062,6 @@ int is_pack_valid(struct packed_git *p) return !open_packed_git(p); } -struct packed_git *find_oid_pack(const struct object_id *oid, - struct packed_git *packs) -{ - struct packed_git *p; - - for (p = packs; p; p = p->next) { - if (find_pack_entry_one(oid, p)) - return p; - } - return NULL; - -} - static int fill_pack_entry(const struct object_id *oid, struct pack_entry *e, struct packed_git *p) @@ -2048,9 +2090,11 @@ static int fill_pack_entry(const struct object_id *oid, return 1; } -int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e) +static int find_pack_entry(struct repository *r, + const struct object_id *oid, + struct pack_entry *e) { - struct list_head *pos; + struct packfile_list_entry *l; packfile_store_prepare(r->objects->packfiles); @@ -2058,19 +2102,72 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa if (source->midx && fill_midx_entry(source->midx, oid, e)) return 1; - if (!r->objects->packfiles->packs) + if (!r->objects->packfiles->packs.head) return 0; - list_for_each(pos, &r->objects->packfiles->mru) { - struct packed_git *p = list_entry(pos, struct packed_git, mru); + for (l = r->objects->packfiles->packs.head; l; l = l->next) { + struct packed_git *p = l->pack; + if (!p->multi_pack_index && fill_pack_entry(oid, e, p)) { - list_move(&p->mru, &r->objects->packfiles->mru); + if (!r->objects->packfiles->skip_mru_updates) + packfile_list_prepend(&r->objects->packfiles->packs, p); return 1; } } return 0; } +int packfile_store_freshen_object(struct packfile_store *store, + const struct object_id *oid) +{ + struct pack_entry e; + if (!find_pack_entry(store->odb->repo, oid, &e)) + return 0; + if (e.p->is_cruft) + return 0; + if (e.p->freshened) + return 1; + if (utime(e.p->pack_name, NULL)) + return 0; + e.p->freshened = 1; + return 1; +} + +int packfile_store_read_object_info(struct packfile_store *store, + const struct object_id *oid, + struct object_info *oi, + unsigned flags UNUSED) +{ + static struct object_info blank_oi = OBJECT_INFO_INIT; + struct pack_entry e; + int rtype; + + if (!find_pack_entry(store->odb->repo, oid, &e)) + return 1; + + /* + * We know that the caller doesn't actually need the + * information below, so return early. + */ + if (oi == &blank_oi) + return 0; + + rtype = packed_object_info(store->odb->repo, e.p, e.offset, oi); + if (rtype < 0) { + mark_bad_packed_object(e.p, oid); + return -1; + } + + if (oi->whence == OI_PACKED) { + oi->u.packed.offset = e.offset; + oi->u.packed.pack = e.p; + oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || + rtype == OBJ_OFS_DELTA); + } + + return 0; +} + static void maybe_invalidate_kept_pack_cache(struct repository *r, unsigned flags) { @@ -2196,6 +2293,7 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, int r = 0; int pack_errors = 0; + repo->objects->packfiles->skip_mru_updates = true; repo_for_each_pack(repo, p) { if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) continue; @@ -2216,6 +2314,8 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, if (r) break; } + repo->objects->packfiles->skip_mru_updates = false; + return r ? r : pack_errors; } @@ -2311,45 +2411,157 @@ int parse_pack_header_option(const char *in, unsigned char *out, unsigned int *l return 0; } -static int pack_map_entry_cmp(const void *cmp_data UNUSED, - const struct hashmap_entry *entry, - const struct hashmap_entry *entry2, - const void *keydata) -{ - const char *key = keydata; - const struct packed_git *pg1, *pg2; - - pg1 = container_of(entry, const struct packed_git, packmap_ent); - pg2 = container_of(entry2, const struct packed_git, packmap_ent); - - return strcmp(pg1->pack_name, key ? key : pg2->pack_name); -} - struct packfile_store *packfile_store_new(struct object_database *odb) { struct packfile_store *store; CALLOC_ARRAY(store, 1); store->odb = odb; - INIT_LIST_HEAD(&store->mru); - hashmap_init(&store->map, pack_map_entry_cmp, NULL, 0); + strmap_init(&store->packs_by_path); return store; } void packfile_store_free(struct packfile_store *store) { - for (struct packed_git *p = store->packs, *next; p; p = next) { - next = p->next; - free(p); - } - hashmap_clear(&store->map); + for (struct packfile_list_entry *e = store->packs.head; e; e = e->next) + free(e->pack); + packfile_list_clear(&store->packs); + + strmap_clear(&store->packs_by_path, 0); free(store); } void packfile_store_close(struct packfile_store *store) { - for (struct packed_git *p = store->packs; p; p = p->next) { - if (p->do_not_close) + for (struct packfile_list_entry *e = store->packs.head; e; e = e->next) { + if (e->pack->do_not_close) BUG("want to close pack marked 'do-not-close'"); - close_pack(p); + close_pack(e->pack); } } + +struct odb_packed_read_stream { + struct odb_read_stream base; + struct packed_git *pack; + git_zstream z; + enum { + ODB_PACKED_READ_STREAM_UNINITIALIZED, + ODB_PACKED_READ_STREAM_INUSE, + ODB_PACKED_READ_STREAM_DONE, + ODB_PACKED_READ_STREAM_ERROR, + } z_state; + off_t pos; +}; + +static ssize_t read_istream_pack_non_delta(struct odb_read_stream *_st, char *buf, + size_t sz) +{ + struct odb_packed_read_stream *st = (struct odb_packed_read_stream *)_st; + size_t total_read = 0; + + switch (st->z_state) { + case ODB_PACKED_READ_STREAM_UNINITIALIZED: + memset(&st->z, 0, sizeof(st->z)); + git_inflate_init(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_INUSE; + break; + case ODB_PACKED_READ_STREAM_DONE: + return 0; + case ODB_PACKED_READ_STREAM_ERROR: + return -1; + case ODB_PACKED_READ_STREAM_INUSE: + break; + } + + while (total_read < sz) { + int status; + struct pack_window *window = NULL; + unsigned char *mapped; + + mapped = use_pack(st->pack, &window, + st->pos, &st->z.avail_in); + + st->z.next_out = (unsigned char *)buf + total_read; + st->z.avail_out = sz - total_read; + st->z.next_in = mapped; + status = git_inflate(&st->z, Z_FINISH); + + st->pos += st->z.next_in - mapped; + total_read = st->z.next_out - (unsigned char *)buf; + unuse_pack(&window); + + if (status == Z_STREAM_END) { + git_inflate_end(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_DONE; + break; + } + + /* + * Unlike the loose object case, we do not have to worry here + * about running out of input bytes and spinning infinitely. If + * we get Z_BUF_ERROR due to too few input bytes, then we'll + * replenish them in the next use_pack() call when we loop. If + * we truly hit the end of the pack (i.e., because it's corrupt + * or truncated), then use_pack() catches that and will die(). + */ + if (status != Z_OK && status != Z_BUF_ERROR) { + git_inflate_end(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_ERROR; + return -1; + } + } + return total_read; +} + +static int close_istream_pack_non_delta(struct odb_read_stream *_st) +{ + struct odb_packed_read_stream *st = (struct odb_packed_read_stream *)_st; + if (st->z_state == ODB_PACKED_READ_STREAM_INUSE) + git_inflate_end(&st->z); + return 0; +} + +int packfile_store_read_object_stream(struct odb_read_stream **out, + struct packfile_store *store, + const struct object_id *oid) +{ + struct odb_packed_read_stream *stream; + struct pack_window *window = NULL; + struct object_info oi = OBJECT_INFO_INIT; + enum object_type in_pack_type; + unsigned long size; + + oi.sizep = &size; + + if (packfile_store_read_object_info(store, oid, &oi, 0) || + oi.u.packed.is_delta || + repo_settings_get_big_file_threshold(store->odb->repo) >= size) + return -1; + + in_pack_type = unpack_object_header(oi.u.packed.pack, + &window, + &oi.u.packed.offset, + &size); + unuse_pack(&window); + switch (in_pack_type) { + default: + return -1; /* we do not do deltas for now */ + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + break; + } + + CALLOC_ARRAY(stream, 1); + stream->base.close = close_istream_pack_non_delta; + stream->base.read = read_istream_pack_non_delta; + stream->base.type = in_pack_type; + stream->base.size = size; + stream->z_state = ODB_PACKED_READ_STREAM_UNINITIALIZED; + stream->pack = oi.u.packed.pack; + stream->pos = oi.u.packed.offset; + + *out = &stream->base; + + return 0; +} diff --git a/packfile.h b/packfile.h index c9d0b93446..59d162a3f4 100644 --- a/packfile.h +++ b/packfile.h @@ -5,14 +5,13 @@ #include "object.h" #include "odb.h" #include "oidset.h" +#include "strmap.h" /* in odb.h */ struct object_info; +struct odb_read_stream; struct packed_git { - struct hashmap_entry packmap_ent; - struct packed_git *next; - struct list_head mru; struct pack_window *windows; off_t pack_size; const void *index_data; @@ -52,6 +51,28 @@ struct packed_git { char pack_name[FLEX_ARRAY]; /* more */ }; +struct packfile_list { + struct packfile_list_entry *head, *tail; +}; + +struct packfile_list_entry { + struct packfile_list_entry *next; + struct packed_git *pack; +}; + +void packfile_list_clear(struct packfile_list *list); +void packfile_list_remove(struct packfile_list *list, struct packed_git *pack); +void packfile_list_prepend(struct packfile_list *list, struct packed_git *pack); +void packfile_list_append(struct packfile_list *list, struct packed_git *pack); + +/* + * Find the pack within the "packs" list whose index contains the object + * "oid". For general object lookups, you probably don't want this; use + * find_pack_entry() instead. + */ +struct packed_git *packfile_list_find_oid(struct packfile_list_entry *packs, + const struct object_id *oid); + /* * A store that manages packfiles for a given object database. */ @@ -59,10 +80,10 @@ struct packfile_store { struct object_database *odb; /* - * The list of packfiles in the order in which they are being added to - * the store. + * The list of packfiles in the order in which they have been most + * recently used. */ - struct packed_git *packs; + struct packfile_list packs; /* * Cache of packfiles which are marked as "kept", either because there @@ -78,20 +99,32 @@ struct packfile_store { unsigned flags; } kept_cache; - /* A most-recently-used ordered version of the packs list. */ - struct list_head mru; - /* * A map of packfile names to packed_git structs for tracking which * packs have been loaded already. */ - struct hashmap map; + struct strmap packs_by_path; /* * Whether packfiles have already been populated with this store's * packs. */ bool initialized; + + /* + * Usually, packfiles will be reordered to the front of the `packs` + * list whenever an object is looked up via them. This has the effect + * that packs that contain a lot of accessed objects will be located + * towards the front. + * + * This is usually desireable, but there are exceptions. One exception + * is when the looking up multiple objects in a loop for each packfile. + * In that case, we may easily end up with an infinite loop as the + * packfiles get reordered to the front repeatedly. + * + * Setting this field to `true` thus disables these reorderings. + */ + bool skip_mru_updates; }; /* @@ -142,18 +175,29 @@ void packfile_store_add_pack(struct packfile_store *store, * repository. */ #define repo_for_each_pack(repo, p) \ - for (p = packfile_store_get_packs(repo->objects->packfiles); p; p = p->next) + for (struct packfile_list_entry *e = packfile_store_get_packs(repo->objects->packfiles); \ + ((p) = (e ? e->pack : NULL)); e = e->next) + +int packfile_store_read_object_stream(struct odb_read_stream **out, + struct packfile_store *store, + const struct object_id *oid); /* - * Get all packs managed by the given store, including packfiles that are - * referenced by multi-pack indices. + * Try to read the object identified by its ID from the object store and + * populate the object info with its data. Returns 1 in case the object was + * not found, 0 if it was and read successfully, and a negative error code in + * case the object was corrupted. */ -struct packed_git *packfile_store_get_packs(struct packfile_store *store); +int packfile_store_read_object_info(struct packfile_store *store, + const struct object_id *oid, + struct object_info *oi, + unsigned flags); /* - * Get all packs in most-recently-used order. + * Get all packs managed by the given store, including packfiles that are + * referenced by multi-pack indices. */ -struct list_head *packfile_store_get_packs_mru(struct packfile_store *store); +struct packfile_list_entry *packfile_store_get_packs(struct packfile_store *store); /* * Open the packfile and add it to the store if it isn't yet known. Returns @@ -163,6 +207,9 @@ struct list_head *packfile_store_get_packs_mru(struct packfile_store *store); struct packed_git *packfile_store_load_pack(struct packfile_store *store, const char *idx_path, int local); +int packfile_store_freshen_object(struct packfile_store *store, + const struct object_id *oid); + struct pack_window { struct pack_window *next; unsigned char *base; @@ -245,14 +292,6 @@ extern void (*report_garbage)(unsigned seen_bits, const char *path); */ unsigned long repo_approximate_object_count(struct repository *r); -/* - * Find the pack within the "packs" list whose index contains the object "oid". - * For general object lookups, you probably don't want this; use - * find_pack_entry() instead. - */ -struct packed_git *find_oid_pack(const struct object_id *oid, - struct packed_git *packs); - void pack_report(struct repository *repo); /* @@ -276,7 +315,6 @@ struct object_database; unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); void close_pack_windows(struct packed_git *); void close_pack(struct packed_git *); -void close_object_store(struct object_database *o); void unuse_pack(struct pack_window **); void clear_delta_base_cache(void); struct packed_git *add_packed_git(struct repository *r, const char *path, @@ -354,7 +392,6 @@ const struct packed_git *has_packed_and_bad(struct repository *, const struct ob * Iff a pack file in the given repository contains the object named by sha1, * return true and store its location to e. */ -int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e); int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsigned flags, struct pack_entry *e); int has_object_pack(struct repository *r, const struct object_id *oid); diff --git a/parallel-checkout.c b/parallel-checkout.c index fba6aa65a6..0bf4bd6d4a 100644 --- a/parallel-checkout.c +++ b/parallel-checkout.c @@ -13,7 +13,7 @@ #include "read-cache-ll.h" #include "run-command.h" #include "sigchain.h" -#include "streaming.h" +#include "odb/streaming.h" #include "symlinks.h" #include "thread-utils.h" #include "trace2.h" @@ -281,7 +281,8 @@ static int write_pc_item_to_fd(struct parallel_checkout_item *pc_item, int fd, filter = get_stream_filter_ca(&pc_item->ca, &pc_item->ce->oid); if (filter) { - if (stream_blob_to_fd(fd, &pc_item->ce->oid, filter, 1)) { + if (odb_stream_blob_to_fd(the_repository->objects, fd, + &pc_item->ce->oid, filter, 1)) { /* On error, reset fd to try writing without streaming */ if (reset_fd(fd, path)) return -1; @@ -738,106 +738,6 @@ return_null: return NULL; } -/* - * First, one directory to try is determined by the following algorithm. - * - * (0) If "strict" is given, the path is used as given and no DWIM is - * done. Otherwise: - * (1) "~/path" to mean path under the running user's home directory; - * (2) "~user/path" to mean path under named user's home directory; - * (3) "relative/path" to mean cwd relative directory; or - * (4) "/absolute/path" to mean absolute directory. - * - * Unless "strict" is given, we check "%s/.git", "%s", "%s.git/.git", "%s.git" - * in this order. We select the first one that is a valid git repository, and - * chdir() to it. If none match, or we fail to chdir, we return NULL. - * - * If all goes well, we return the directory we used to chdir() (but - * before ~user is expanded), avoiding getcwd() resolving symbolic - * links. User relative paths are also returned as they are given, - * except DWIM suffixing. - */ -const char *enter_repo(const char *path, unsigned flags) -{ - static struct strbuf validated_path = STRBUF_INIT; - static struct strbuf used_path = STRBUF_INIT; - - if (!path) - return NULL; - - if (!(flags & ENTER_REPO_STRICT)) { - static const char *suffix[] = { - "/.git", "", ".git/.git", ".git", NULL, - }; - const char *gitfile; - int len = strlen(path); - int i; - while ((1 < len) && (path[len-1] == '/')) - len--; - - /* - * We can handle arbitrary-sized buffers, but this remains as a - * sanity check on untrusted input. - */ - if (PATH_MAX <= len) - return NULL; - - strbuf_reset(&used_path); - strbuf_reset(&validated_path); - strbuf_add(&used_path, path, len); - strbuf_add(&validated_path, path, len); - - if (used_path.buf[0] == '~') { - char *newpath = interpolate_path(used_path.buf, 0); - if (!newpath) - return NULL; - strbuf_attach(&used_path, newpath, strlen(newpath), - strlen(newpath)); - } - for (i = 0; suffix[i]; i++) { - struct stat st; - size_t baselen = used_path.len; - strbuf_addstr(&used_path, suffix[i]); - if (!stat(used_path.buf, &st) && - (S_ISREG(st.st_mode) || - (S_ISDIR(st.st_mode) && is_git_directory(used_path.buf)))) { - strbuf_addstr(&validated_path, suffix[i]); - break; - } - strbuf_setlen(&used_path, baselen); - } - if (!suffix[i]) - return NULL; - gitfile = read_gitfile(used_path.buf); - if (!(flags & ENTER_REPO_ANY_OWNER_OK)) - die_upon_dubious_ownership(gitfile, NULL, used_path.buf); - if (gitfile) { - strbuf_reset(&used_path); - strbuf_addstr(&used_path, gitfile); - } - if (chdir(used_path.buf)) - return NULL; - path = validated_path.buf; - } - else { - const char *gitfile = read_gitfile(path); - if (!(flags & ENTER_REPO_ANY_OWNER_OK)) - die_upon_dubious_ownership(gitfile, NULL, path); - if (gitfile) - path = gitfile; - if (chdir(path)) - return NULL; - } - - if (is_git_directory(".")) { - set_git_dir(".", 0); - check_repository_format(NULL); - return path; - } - - return NULL; -} - int calc_shared_perm(struct repository *repo, int mode) { @@ -146,21 +146,6 @@ int adjust_shared_perm(struct repository *repo, const char *path); char *interpolate_path(const char *path, int real_home); -/* The bits are as follows: - * - * - ENTER_REPO_STRICT: callers that require exact paths (as opposed - * to allowing known suffixes like ".git", ".git/.git" to be - * omitted) can set this bit. - * - * - ENTER_REPO_ANY_OWNER_OK: callers that are willing to run without - * ownership check can set this bit. - */ -enum { - ENTER_REPO_STRICT = (1<<0), - ENTER_REPO_ANY_OWNER_OK = (1<<1), -}; - -const char *enter_repo(const char *path, unsigned flags); const char *remove_leading_path(const char *in, const char *prefix); const char *relative_path(const char *in, const char *prefix, struct strbuf *sb); int normalize_path_copy_len(char *dst, const char *src, int *prefix_len); diff --git a/pseudo-merge.c b/pseudo-merge.c index 893b763fe4..a2d5bd85f9 100644 --- a/pseudo-merge.c +++ b/pseudo-merge.c @@ -221,28 +221,25 @@ void load_pseudo_merges_from_config(struct repository *r, } } -static int find_pseudo_merge_group_for_ref(const char *refname, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *_data) +static int find_pseudo_merge_group_for_ref(const struct reference *ref, void *_data) { struct bitmap_writer *writer = _data; + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; struct commit *c; uint32_t i; int has_bitmap; - if (!peel_iterated_oid(the_repository, oid, &peeled)) - oid = &peeled; + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) + maybe_peeled = &peeled; - c = lookup_commit(the_repository, oid); + c = lookup_commit(the_repository, maybe_peeled); if (!c) return 0; - if (!packlist_find(writer->to_pack, oid)) + if (!packlist_find(writer->to_pack, maybe_peeled)) return 0; - has_bitmap = bitmap_writer_has_bitmapped_object_id(writer, oid); + has_bitmap = bitmap_writer_has_bitmapped_object_id(writer, maybe_peeled); for (i = 0; i < writer->pseudo_merge_groups.nr; i++) { struct pseudo_merge_group *group; @@ -252,7 +249,7 @@ static int find_pseudo_merge_group_for_ref(const char *refname, size_t j; group = writer->pseudo_merge_groups.items[i].util; - if (regexec(group->pattern, refname, ARRAY_SIZE(captures), + if (regexec(group->pattern, ref->name, ARRAY_SIZE(captures), captures, 0)) continue; @@ -269,7 +266,7 @@ static int find_pseudo_merge_group_for_ref(const char *refname, if (group_name.len) strbuf_addch(&group_name, '-'); - strbuf_add(&group_name, refname + match->rm_so, + strbuf_add(&group_name, ref->name + match->rm_so, match->rm_eo - match->rm_so); } diff --git a/reachable.c b/reachable.c index 22266db523..b753c39553 100644 --- a/reachable.c +++ b/reachable.c @@ -83,18 +83,17 @@ static void add_rebase_files(struct rev_info *revs) free_worktrees(worktrees); } -static int add_one_ref(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flag, void *cb_data) +static int add_one_ref(const struct reference *ref, void *cb_data) { struct rev_info *revs = (struct rev_info *)cb_data; struct object *object; - if ((flag & REF_ISSYMREF) && (flag & REF_ISBROKEN)) { - warning("symbolic ref is dangling: %s", path); + if ((ref->flags & REF_ISSYMREF) && (ref->flags & REF_ISBROKEN)) { + warning("symbolic ref is dangling: %s", ref->name); return 0; } - object = parse_object_or_die(the_repository, oid, path); + object = parse_object_or_die(the_repository, ref->oid, ref->name); add_pending_object(revs, object, ""); return 0; diff --git a/read-cache.c b/read-cache.c index 032480d0c7..990d4ead0d 100644 --- a/read-cache.c +++ b/read-cache.c @@ -706,7 +706,6 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE| (intent_only ? ADD_CACHE_NEW_ONLY : 0)); unsigned hash_flags = pretend ? 0 : INDEX_WRITE_OBJECT; - struct object_id oid; if (flags & ADD_CACHE_RENORMALIZE) hash_flags |= INDEX_RENORMALIZE; @@ -716,8 +715,6 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, namelen = strlen(path); if (S_ISDIR(st_mode)) { - if (repo_resolve_gitlink_ref(the_repository, path, "HEAD", &oid) < 0) - return error(_("'%s' does not have a commit checked out"), path); while (namelen && path[namelen-1] == '/') namelen--; } diff --git a/ref-filter.c b/ref-filter.c index 30cc488d8a..d7454269e8 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -91,6 +91,7 @@ static struct expand_data { struct object_id delta_base_oid; void *content; + struct object *maybe_object; struct object_info info; } oi, oi_deref; @@ -1475,11 +1476,29 @@ static void grab_common_values(struct atom_value *val, int deref, struct expand_ } } +static struct object *get_or_parse_object(struct expand_data *data, const char *refname, + struct strbuf *err, int *eaten) +{ + if (!data->maybe_object) { + data->maybe_object = parse_object_buffer(the_repository, &data->oid, data->type, + data->size, data->content, eaten); + if (!data->maybe_object) { + strbuf_addf(err, _("parse_object_buffer failed on %s for %s"), + oid_to_hex(&data->oid), refname); + return NULL; + } + } + + return data->maybe_object; +} + /* See grab_values */ -static void grab_tag_values(struct atom_value *val, int deref, struct object *obj) +static int grab_tag_values(struct atom_value *val, int deref, + struct expand_data *data, const char *refname, + struct strbuf *err, int *eaten) { + struct tag *tag = NULL; int i; - struct tag *tag = (struct tag *) obj; for (i = 0; i < used_atom_cnt; i++) { const char *name = used_atom[i].name; @@ -1487,6 +1506,14 @@ static void grab_tag_values(struct atom_value *val, int deref, struct object *ob struct atom_value *v = &val[i]; if (!!deref != (*name == '*')) continue; + + if (!tag) { + tag = (struct tag *) get_or_parse_object(data, refname, + err, eaten); + if (!tag) + return -1; + } + if (deref) name++; if (atom_type == ATOM_TAG) @@ -1496,22 +1523,35 @@ static void grab_tag_values(struct atom_value *val, int deref, struct object *ob else if (atom_type == ATOM_OBJECT && tag->tagged) v->s = xstrdup(oid_to_hex(&tag->tagged->oid)); } + + return 0; } /* See grab_values */ -static void grab_commit_values(struct atom_value *val, int deref, struct object *obj) +static int grab_commit_values(struct atom_value *val, int deref, + struct expand_data *data, const char *refname, + struct strbuf *err, int *eaten) { int i; - struct commit *commit = (struct commit *) obj; + struct commit *commit = NULL; for (i = 0; i < used_atom_cnt; i++) { const char *name = used_atom[i].name; enum atom_type atom_type = used_atom[i].atom_type; struct atom_value *v = &val[i]; + if (!!deref != (*name == '*')) continue; if (deref) name++; + + if (!commit) { + commit = (struct commit *) get_or_parse_object(data, refname, + err, eaten); + if (!commit) + return -1; + } + if (atom_type == ATOM_TREE && grab_oid(name, "tree", get_commit_tree_oid(commit), v, &used_atom[i])) continue; @@ -1531,6 +1571,8 @@ static void grab_commit_values(struct atom_value *val, int deref, struct object v->s = strbuf_detach(&s, NULL); } } + + return 0; } static const char *find_wholine(const char *who, int wholen, const char *buf) @@ -1759,10 +1801,12 @@ static void grab_person(const char *who, struct atom_value *val, int deref, void } } -static void grab_signature(struct atom_value *val, int deref, struct object *obj) +static int grab_signature(struct atom_value *val, int deref, + struct expand_data *data, const char *refname, + struct strbuf *err, int *eaten) { int i; - struct commit *commit = (struct commit *) obj; + struct commit *commit = NULL; struct signature_check sigc = { 0 }; int signature_checked = 0; @@ -1790,6 +1834,13 @@ static void grab_signature(struct atom_value *val, int deref, struct object *obj continue; if (!signature_checked) { + if (!commit) { + commit = (struct commit *) get_or_parse_object(data, refname, + err, eaten); + if (!commit) + return -1; + } + check_commit_signature(commit, &sigc); signature_checked = 1; } @@ -1843,6 +1894,8 @@ static void grab_signature(struct atom_value *val, int deref, struct object *obj if (signature_checked) signature_check_clear(&sigc); + + return 0; } static void find_subpos(const char *buf, @@ -1920,9 +1973,8 @@ static void append_lines(struct strbuf *out, const char *buf, unsigned long size } static void grab_describe_values(struct atom_value *val, int deref, - struct object *obj) + struct expand_data *data) { - struct commit *commit = (struct commit *)obj; int i; for (i = 0; i < used_atom_cnt; i++) { @@ -1944,7 +1996,7 @@ static void grab_describe_values(struct atom_value *val, int deref, cmd.git_cmd = 1; strvec_push(&cmd.args, "describe"); strvec_pushv(&cmd.args, atom->u.describe_args.v); - strvec_push(&cmd.args, oid_to_hex(&commit->object.oid)); + strvec_push(&cmd.args, oid_to_hex(&data->oid)); if (pipe_command(&cmd, NULL, 0, &out, 0, &err, 0) < 0) { error(_("failed to run 'describe'")); v->s = xstrdup(""); @@ -2066,24 +2118,36 @@ static void fill_missing_values(struct atom_value *val) * pointed at by the ref itself; otherwise it is the object the * ref (which is a tag) refers to. */ -static void grab_values(struct atom_value *val, int deref, struct object *obj, struct expand_data *data) +static int grab_values(struct atom_value *val, int deref, struct expand_data *data, + const char *refname, struct strbuf *err, int *eaten) { void *buf = data->content; + int ret; - switch (obj->type) { + switch (data->type) { case OBJ_TAG: - grab_tag_values(val, deref, obj); + ret = grab_tag_values(val, deref, data, refname, err, eaten); + if (ret < 0) + goto out; + grab_sub_body_contents(val, deref, data); grab_person("tagger", val, deref, buf); - grab_describe_values(val, deref, obj); + grab_describe_values(val, deref, data); break; case OBJ_COMMIT: - grab_commit_values(val, deref, obj); + ret = grab_commit_values(val, deref, data, refname, err, eaten); + if (ret < 0) + goto out; + grab_sub_body_contents(val, deref, data); grab_person("author", val, deref, buf); grab_person("committer", val, deref, buf); - grab_signature(val, deref, obj); - grab_describe_values(val, deref, obj); + + ret = grab_signature(val, deref, data, refname, err, eaten); + if (ret < 0) + goto out; + + grab_describe_values(val, deref, data); break; case OBJ_TREE: /* grab_tree_values(val, deref, obj, buf, sz); */ @@ -2094,8 +2158,12 @@ static void grab_values(struct atom_value *val, int deref, struct object *obj, s grab_sub_body_contents(val, deref, data); break; default: - die("Eh? Object of type %d?", obj->type); + die("Eh? Object of type %d?", data->type); } + + ret = 0; +out: + return ret; } static inline char *copy_advance(char *dst, const char *src) @@ -2292,38 +2360,43 @@ static const char *get_refname(struct used_atom *atom, struct ref_array_item *re return show_ref(&atom->u.refname, ref->refname); } -static int get_object(struct ref_array_item *ref, int deref, struct object **obj, +static int get_object(struct ref_array_item *ref, int deref, struct expand_data *oi, struct strbuf *err) { - /* parse_object_buffer() will set eaten to 0 if free() will be needed */ - int eaten = 1; + /* parse_object_buffer() will set eaten to 1 if free() will be needed */ + int eaten = 0; + int ret; + + oi->maybe_object = NULL; + if (oi->info.contentp) { /* We need to know that to use parse_object_buffer properly */ oi->info.sizep = &oi->size; oi->info.typep = &oi->type; } + if (odb_read_object_info_extended(the_repository->objects, &oi->oid, &oi->info, - OBJECT_INFO_LOOKUP_REPLACE)) - return strbuf_addf_ret(err, -1, _("missing object %s for %s"), - oid_to_hex(&oi->oid), ref->refname); + OBJECT_INFO_LOOKUP_REPLACE)) { + ret = strbuf_addf_ret(err, -1, _("missing object %s for %s"), + oid_to_hex(&oi->oid), ref->refname); + goto out; + } if (oi->info.disk_sizep && oi->disk_size < 0) BUG("Object size is less than zero."); if (oi->info.contentp) { - *obj = parse_object_buffer(the_repository, &oi->oid, oi->type, oi->size, oi->content, &eaten); - if (!*obj) { - if (!eaten) - free(oi->content); - return strbuf_addf_ret(err, -1, _("parse_object_buffer failed on %s for %s"), - oid_to_hex(&oi->oid), ref->refname); - } - grab_values(ref->value, deref, *obj, oi); + ret = grab_values(ref->value, deref, oi, ref->refname, err, &eaten); + if (ret < 0) + goto out; } grab_common_values(ref->value, deref, oi); + ret = 0; + +out: if (!eaten) free(oi->content); - return 0; + return ret; } static void populate_worktree_map(struct hashmap *map, struct worktree **worktrees) @@ -2376,7 +2449,6 @@ static char *get_worktree_path(const struct ref_array_item *ref) */ static int populate_value(struct ref_array_item *ref, struct strbuf *err) { - struct object *obj; int i; struct object_info empty = OBJECT_INFO_INIT; int ahead_behind_atoms = 0; @@ -2564,24 +2636,32 @@ static int populate_value(struct ref_array_item *ref, struct strbuf *err) oi.oid = ref->objectname; - if (get_object(ref, 0, &obj, &oi, err)) + if (get_object(ref, 0, &oi, err)) return -1; /* * If there is no atom that wants to know about tagged * object, we are done. */ - if (!need_tagged || (obj->type != OBJ_TAG)) + if (!need_tagged || (oi.type != OBJ_TAG)) return 0; /* * If it is a tag object, see if we use the peeled value. If we do, * grab the peeled OID. */ - if (need_tagged && peel_iterated_oid(the_repository, &obj->oid, &oi_deref.oid)) - die("bad tag"); + if (need_tagged) { + if (!is_null_oid(&ref->peeled_oid)) { + oidcpy(&oi_deref.oid, &ref->peeled_oid); + } else if (!peel_object(the_repository, &oi.oid, &oi_deref.oid, + PEEL_OBJECT_VERIFY_TAGGED_OBJECT_TYPE)) { + /* We managed to peel the object ourselves. */ + } else { + die("bad tag"); + } + } - return get_object(ref, 1, &obj, &oi_deref, err); + return get_object(ref, 1, &oi_deref, err); } /* @@ -2807,12 +2887,15 @@ static int match_points_at(struct oid_array *points_at, * Callers can then fill in other struct members at their leisure. */ static struct ref_array_item *new_ref_array_item(const char *refname, - const struct object_id *oid) + const struct object_id *oid, + const struct object_id *peeled_oid) { struct ref_array_item *ref; FLEX_ALLOC_STR(ref, refname, refname); oidcpy(&ref->objectname, oid); + if (peeled_oid) + oidcpy(&ref->peeled_oid, peeled_oid); ref->rest = NULL; return ref; @@ -2826,9 +2909,10 @@ static void ref_array_append(struct ref_array *array, struct ref_array_item *ref struct ref_array_item *ref_array_push(struct ref_array *array, const char *refname, - const struct object_id *oid) + const struct object_id *oid, + const struct object_id *peeled_oid) { - struct ref_array_item *ref = new_ref_array_item(refname, oid); + struct ref_array_item *ref = new_ref_array_item(refname, oid, peeled_oid); ref_array_append(array, ref); return ref; } @@ -2871,25 +2955,25 @@ static int filter_ref_kind(struct ref_filter *filter, const char *refname) return ref_kind_from_refname(refname); } -static struct ref_array_item *apply_ref_filter(const char *refname, const char *referent, const struct object_id *oid, - int flag, struct ref_filter *filter) +static struct ref_array_item *apply_ref_filter(const struct reference *ref, + struct ref_filter *filter) { - struct ref_array_item *ref; + struct ref_array_item *item; struct commit *commit = NULL; unsigned int kind; - if (flag & REF_BAD_NAME) { - warning(_("ignoring ref with broken name %s"), refname); + if (ref->flags & REF_BAD_NAME) { + warning(_("ignoring ref with broken name %s"), ref->name); return NULL; } - if (flag & REF_ISBROKEN) { - warning(_("ignoring broken ref %s"), refname); + if (ref->flags & REF_ISBROKEN) { + warning(_("ignoring broken ref %s"), ref->name); return NULL; } /* Obtain the current ref kind from filter_ref_kind() and ignore unwanted refs. */ - kind = filter_ref_kind(filter, refname); + kind = filter_ref_kind(filter, ref->name); /* * Generally HEAD refs are printed with special description denoting a rebase, @@ -2902,13 +2986,13 @@ static struct ref_array_item *apply_ref_filter(const char *refname, const char * else if (!(kind & filter->kind)) return NULL; - if (!filter_pattern_match(filter, refname)) + if (!filter_pattern_match(filter, ref->name)) return NULL; - if (filter_exclude_match(filter, refname)) + if (filter_exclude_match(filter, ref->name)) return NULL; - if (filter->points_at.nr && !match_points_at(&filter->points_at, oid, refname)) + if (filter->points_at.nr && !match_points_at(&filter->points_at, ref->oid, ref->name)) return NULL; /* @@ -2918,7 +3002,7 @@ static struct ref_array_item *apply_ref_filter(const char *refname, const char * */ if (filter->reachable_from || filter->unreachable_from || filter->with_commit || filter->no_commit || filter->verbose) { - commit = lookup_commit_reference_gently(the_repository, oid, 1); + commit = lookup_commit_reference_gently(the_repository, ref->oid, 1); if (!commit) return NULL; /* We perform the filtering for the '--contains' option... */ @@ -2936,13 +3020,13 @@ static struct ref_array_item *apply_ref_filter(const char *refname, const char * * to do its job and the resulting list may yet to be pruned * by maxcount logic. */ - ref = new_ref_array_item(refname, oid); - ref->commit = commit; - ref->flag = flag; - ref->kind = kind; - ref->symref = xstrdup_or_null(referent); + item = new_ref_array_item(ref->name, ref->oid, ref->peeled_oid); + item->commit = commit; + item->flag = ref->flags; + item->kind = kind; + item->symref = xstrdup_or_null(ref->target); - return ref; + return item; } struct ref_filter_cbdata { @@ -2954,14 +3038,14 @@ struct ref_filter_cbdata { * A call-back given to for_each_ref(). Filter refs and keep them for * later object processing. */ -static int filter_one(const char *refname, const char *referent, const struct object_id *oid, int flag, void *cb_data) +static int filter_one(const struct reference *ref, void *cb_data) { struct ref_filter_cbdata *ref_cbdata = cb_data; - struct ref_array_item *ref; + struct ref_array_item *item; - ref = apply_ref_filter(refname, referent, oid, flag, ref_cbdata->filter); - if (ref) - ref_array_append(ref_cbdata->array, ref); + item = apply_ref_filter(ref, ref_cbdata->filter); + if (item) + ref_array_append(ref_cbdata->array, item); return 0; } @@ -2990,17 +3074,17 @@ struct ref_filter_and_format_cbdata { } internal; }; -static int filter_and_format_one(const char *refname, const char *referent, const struct object_id *oid, int flag, void *cb_data) +static int filter_and_format_one(const struct reference *ref, void *cb_data) { struct ref_filter_and_format_cbdata *ref_cbdata = cb_data; - struct ref_array_item *ref; + struct ref_array_item *item; struct strbuf output = STRBUF_INIT, err = STRBUF_INIT; - ref = apply_ref_filter(refname, referent, oid, flag, ref_cbdata->filter); - if (!ref) + item = apply_ref_filter(ref, ref_cbdata->filter); + if (!item) return 0; - if (format_ref_array_item(ref, ref_cbdata->format, &output, &err)) + if (format_ref_array_item(item, ref_cbdata->format, &output, &err)) die("%s", err.buf); if (output.len || !ref_cbdata->format->array_opts.omit_empty) { @@ -3010,7 +3094,7 @@ static int filter_and_format_one(const char *refname, const char *referent, cons strbuf_release(&output); strbuf_release(&err); - free_array_item(ref); + free_array_item(item); /* * Increment the running count of refs that match the filter. If @@ -3583,13 +3667,14 @@ void print_formatted_ref_array(struct ref_array *array, struct ref_format *forma } void pretty_print_ref(const char *name, const struct object_id *oid, + const struct object_id *peeled_oid, struct ref_format *format) { struct ref_array_item *ref_item; struct strbuf output = STRBUF_INIT; struct strbuf err = STRBUF_INIT; - ref_item = new_ref_array_item(name, oid); + ref_item = new_ref_array_item(name, oid, peeled_oid); ref_item->kind = ref_kind_from_refname(name); if (format_ref_array_item(ref_item, format, &output, &err)) die("%s", err.buf); diff --git a/ref-filter.h b/ref-filter.h index 235c60f79c..120221b47f 100644 --- a/ref-filter.h +++ b/ref-filter.h @@ -41,6 +41,7 @@ enum ref_sorting_order { struct ref_array_item { struct object_id objectname; + struct object_id peeled_oid; const char *rest; int flag; unsigned int kind; @@ -187,6 +188,7 @@ void print_formatted_ref_array(struct ref_array *array, struct ref_format *forma * name must be a fully qualified refname. */ void pretty_print_ref(const char *name, const struct object_id *oid, + const struct object_id *peeled_oid, struct ref_format *format); /* @@ -195,7 +197,8 @@ void pretty_print_ref(const char *name, const struct object_id *oid, */ struct ref_array_item *ref_array_push(struct ref_array *array, const char *refname, - const struct object_id *oid); + const struct object_id *oid, + const struct object_id *peeled_oid); /* * If the provided format includes ahead-behind atoms, then compute the @@ -423,16 +423,13 @@ int should_expire_reflog_ent_verbose(struct object_id *ooid, return expire; } -static int push_tip_to_list(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags, void *cb_data) +static int push_tip_to_list(const struct reference *ref, void *cb_data) { struct commit_list **list = cb_data; struct commit *tip_commit; - if (flags & REF_ISSYMREF) + if (ref->flags & REF_ISSYMREF) return 0; - tip_commit = lookup_commit_reference_gently(the_repository, oid, 1); + tip_commit = lookup_commit_reference_gently(the_repository, ref->oid, 1); if (!tip_commit) return 0; commit_list_insert(tip_commit, list); @@ -426,17 +426,19 @@ int refs_ref_exists(struct ref_store *refs, const char *refname) NULL, NULL); } -static int for_each_filter_refs(const char *refname, const char *referent, - const struct object_id *oid, - int flags, void *data) +static int for_each_filter_refs(const struct reference *ref, void *data) { struct for_each_ref_filter *filter = data; - if (wildmatch(filter->pattern, refname, 0)) + if (wildmatch(filter->pattern, ref->name, 0)) return 0; - if (filter->prefix) - skip_prefix(refname, filter->prefix, &refname); - return filter->fn(refname, referent, oid, flags, filter->cb_data); + if (filter->prefix) { + struct reference skipped = *ref; + skip_prefix(skipped.name, filter->prefix, &skipped.name); + return filter->fn(&skipped, filter->cb_data); + } else { + return filter->fn(ref, filter->cb_data); + } } struct warn_if_dangling_data { @@ -447,17 +449,15 @@ struct warn_if_dangling_data { int dry_run; }; -static int warn_if_dangling_symref(const char *refname, const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags, void *cb_data) +static int warn_if_dangling_symref(const struct reference *ref, void *cb_data) { struct warn_if_dangling_data *d = cb_data; const char *resolves_to, *msg; - if (!(flags & REF_ISSYMREF)) + if (!(ref->flags & REF_ISSYMREF)) return 0; - resolves_to = refs_resolve_ref_unsafe(d->refs, refname, 0, NULL, NULL); + resolves_to = refs_resolve_ref_unsafe(d->refs, ref->name, 0, NULL, NULL); if (!resolves_to || !string_list_has_string(d->refnames, resolves_to)) { return 0; @@ -466,7 +466,7 @@ static int warn_if_dangling_symref(const char *refname, const char *referent UNU msg = d->dry_run ? _("%s%s will become dangling after %s is deleted\n") : _("%s%s has become dangling after %s was deleted\n"); - fprintf(d->fp, msg, d->indent, refname, resolves_to); + fprintf(d->fp, msg, d->indent, ref->name, resolves_to); return 0; } @@ -507,8 +507,15 @@ int refs_head_ref_namespaced(struct ref_store *refs, each_ref_fn fn, void *cb_da int flag; strbuf_addf(&buf, "%sHEAD", get_git_namespace()); - if (!refs_read_ref_full(refs, buf.buf, RESOLVE_REF_READING, &oid, &flag)) - ret = fn(buf.buf, NULL, &oid, flag, cb_data); + if (!refs_read_ref_full(refs, buf.buf, RESOLVE_REF_READING, &oid, &flag)) { + struct reference ref = { + .name = buf.buf, + .oid = &oid, + .flags = flag, + }; + + ret = fn(&ref, cb_data); + } strbuf_release(&buf); return ret; @@ -1741,8 +1748,15 @@ int refs_head_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) int flag; if (refs_resolve_ref_unsafe(refs, "HEAD", RESOLVE_REF_READING, - &oid, &flag)) - return fn("HEAD", NULL, &oid, flag, cb_data); + &oid, &flag)) { + struct reference ref = { + .name = "HEAD", + .oid = &oid, + .flags = flag, + }; + + return fn(&ref, cb_data); + } return 0; } @@ -2299,25 +2313,28 @@ void base_ref_store_init(struct ref_store *refs, struct repository *repo, refs->gitdir = xstrdup(path); } -/* backend functions */ -int refs_pack_refs(struct ref_store *refs, struct pack_refs_opts *opts) +int refs_optimize(struct ref_store *refs, struct refs_optimize_opts *opts) { - return refs->be->pack_refs(refs, opts); + return refs->be->optimize(refs, opts); } -int refs_optimize(struct ref_store *refs, struct pack_refs_opts *opts) +int refs_optimize_required(struct ref_store *refs, + struct refs_optimize_opts *opts, + bool *required) { - return refs->be->optimize(refs, opts); + return refs->be->optimize_required(refs, opts, required); } -int peel_iterated_oid(struct repository *r, const struct object_id *base, struct object_id *peeled) +int reference_get_peeled_oid(struct repository *repo, + const struct reference *ref, + struct object_id *peeled_oid) { - if (current_ref_iter && - (current_ref_iter->oid == base || - oideq(current_ref_iter->oid, base))) - return ref_iterator_peel(current_ref_iter, peeled); + if (ref->peeled_oid) { + oidcpy(peeled_oid, ref->peeled_oid); + return 0; + } - return peel_object(r, base, peeled) ? -1 : 0; + return peel_object(repo, ref->oid, peeled_oid, 0) ? -1 : 0; } int refs_update_symref(struct ref_store *refs, const char *ref, @@ -2491,7 +2508,7 @@ int ref_transaction_prepare(struct ref_transaction *transaction, break; } - if (refs->repo->objects->sources->disable_ref_updates) { + if (refs->repo->disable_ref_updates) { strbuf_addstr(err, _("ref updates forbidden inside quarantine environment")); return -1; @@ -2689,7 +2706,7 @@ enum ref_transaction_error refs_verify_refnames_available(struct ref_store *refs while ((ok = ref_iterator_advance(iter)) == ITER_OK) { if (skip && - string_list_has_string(skip, iter->refname)) + string_list_has_string(skip, iter->ref.name)) continue; if (transaction && ref_transaction_maybe_set_rejected( @@ -2698,7 +2715,7 @@ enum ref_transaction_error refs_verify_refnames_available(struct ref_store *refs continue; strbuf_addf(err, _("'%s' exists; cannot create '%s'"), - iter->refname, refname); + iter->ref.name, refname); goto cleanup; } @@ -2753,14 +2770,10 @@ struct do_for_each_reflog_help { void *cb_data; }; -static int do_for_each_reflog_helper(const char *refname, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, - void *cb_data) +static int do_for_each_reflog_helper(const struct reference *ref, void *cb_data) { struct do_for_each_reflog_help *hp = cb_data; - return hp->fn(refname, hp->cb_data); + return hp->fn(ref->name, hp->cb_data); } int refs_for_each_reflog(struct ref_store *refs, each_reflog_fn fn, void *cb_data) @@ -2976,25 +2989,24 @@ struct migration_data { uint64_t index; }; -static int migrate_one_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags, void *cb_data) +static int migrate_one_ref(const struct reference *ref, void *cb_data) { struct migration_data *data = cb_data; struct strbuf symref_target = STRBUF_INIT; int ret; - if (flags & REF_ISSYMREF) { - ret = refs_read_symbolic_ref(data->old_refs, refname, &symref_target); + if (ref->flags & REF_ISSYMREF) { + ret = refs_read_symbolic_ref(data->old_refs, ref->name, &symref_target); if (ret < 0) goto done; - ret = ref_transaction_update(data->transaction, refname, NULL, null_oid(the_hash_algo), + ret = ref_transaction_update(data->transaction, ref->name, NULL, null_oid(the_hash_algo), symref_target.buf, NULL, REF_SKIP_CREATE_REFLOG | REF_NO_DEREF, NULL, data->errbuf); if (ret < 0) goto done; } else { - ret = ref_transaction_create(data->transaction, refname, oid, NULL, + ret = ref_transaction_create(data->transaction, ref->name, ref->oid, NULL, REF_SKIP_CREATE_REFLOG | REF_SKIP_OID_VERIFICATION, NULL, data->errbuf); if (ret < 0) @@ -333,36 +333,74 @@ struct ref_transaction; * stored in ref_iterator::flags. Other bits are for internal use * only: */ +enum reference_status { + /* Reference is a symbolic reference. */ + REF_ISSYMREF = (1 << 0), -/* Reference is a symbolic reference. */ -#define REF_ISSYMREF 0x01 + /* Reference is a packed reference. */ + REF_ISPACKED = (1 << 1), -/* Reference is a packed reference. */ -#define REF_ISPACKED 0x02 + /* + * Reference cannot be resolved to an object name: dangling symbolic + * reference (directly or indirectly), corrupt reference file, + * reference exists but name is bad, or symbolic reference refers to + * ill-formatted reference name. + */ + REF_ISBROKEN = (1 << 2), -/* - * Reference cannot be resolved to an object name: dangling symbolic - * reference (directly or indirectly), corrupt reference file, - * reference exists but name is bad, or symbolic reference refers to - * ill-formatted reference name. - */ -#define REF_ISBROKEN 0x04 + /* + * Reference name is not well formed. + * + * See git-check-ref-format(1) for the definition of well formed ref names. + */ + REF_BAD_NAME = (1 << 3), +}; + +/* A reference passed to `for_each_ref()`-style callbacks. */ +struct reference { + /* The fully-qualified name of the reference. */ + const char *name; + + /* The target of a symbolic ref. `NULL` for direct references. */ + const char *target; + + /* + * The object ID of a reference. Either the direct object ID or the + * resolved object ID in the case of a symbolic ref. May be the zero + * object ID in case the symbolic ref cannot be resolved. + */ + const struct object_id *oid; + + /* + * An optional peeled object ID. This field _may_ be set for tags in + * case the peeled value is present in the backend. Please refer to + * `reference_get_peeled_oid()`. + */ + const struct object_id *peeled_oid; + + /* A bitfield of `enum reference_status` flags. */ + unsigned flags; +}; /* - * Reference name is not well formed. + * Peel the tag to a non-tag commit. If present, this uses the peeled object ID + * exposed by the reference backend. Otherwise, the object is peeled via the + * object database, which is less efficient. * - * See git-check-ref-format(1) for the definition of well formed ref names. + * Return `0` if the reference could be peeled, a negative error code + * otherwise. */ -#define REF_BAD_NAME 0x08 +int reference_get_peeled_oid(struct repository *repo, + const struct reference *ref, + struct object_id *peeled_oid); /* * The signature for the callback function for the for_each_*() - * functions below. The memory pointed to by the refname and oid - * arguments is only guaranteed to be valid for the duration of a + * functions below. The memory pointed to by the `struct reference` + * argument is only guaranteed to be valid for the duration of a * single callback invocation. */ -typedef int each_ref_fn(const char *refname, const char *referent, - const struct object_id *oid, int flags, void *cb_data); +typedef int each_ref_fn(const struct reference *ref, void *cb_data); /* * The following functions invoke the specified callback function for @@ -461,32 +499,33 @@ void refs_warn_dangling_symrefs(struct ref_store *refs, FILE *fp, const struct string_list *refnames); /* - * Flags for controlling behaviour of pack_refs() - * PACK_REFS_PRUNE: Prune loose refs after packing - * PACK_REFS_AUTO: Pack refs on a best effort basis. The heuristics and end - * result are decided by the ref backend. Backends may ignore - * this flag and fall back to a normal repack. + * Flags for controlling behaviour of refs_optimize() + * REFS_OPTIMIZE_PRUNE: Prune loose refs after packing + * REFS_OPTIMIZE_AUTO: Pack refs on a best effort basis. The heuristics and end + * result are decided by the ref backend. Backends may ignore + * this flag and fall back to a normal repack. */ -#define PACK_REFS_PRUNE (1 << 0) -#define PACK_REFS_AUTO (1 << 1) +#define REFS_OPTIMIZE_PRUNE (1 << 0) +#define REFS_OPTIMIZE_AUTO (1 << 1) -struct pack_refs_opts { +struct refs_optimize_opts { unsigned int flags; struct ref_exclusions *exclusions; struct string_list *includes; }; /* - * Write a packed-refs file for the current repository. - * flags: Combination of the above PACK_REFS_* flags. + * Optimize the ref store. The exact behavior is up to the backend. + * For the files backend, this is equivalent to packing refs. */ -int refs_pack_refs(struct ref_store *refs, struct pack_refs_opts *opts); +int refs_optimize(struct ref_store *refs, struct refs_optimize_opts *opts); /* - * Optimize the ref store. The exact behavior is up to the backend. - * For the files backend, this is equivalent to packing refs. + * Check if refs backend can be optimized by calling 'refs_optimize'. */ -int refs_optimize(struct ref_store *refs, struct pack_refs_opts *opts); +int refs_optimize_required(struct ref_store *ref_store, + struct refs_optimize_opts *opts, + bool *required); /* * Setup reflog before using. Fill in err and return -1 on failure. @@ -1251,10 +1290,6 @@ int repo_migrate_ref_storage_format(struct repository *repo, * to the next entry, ref_iterator_advance() aborts the iteration, * frees the ref_iterator, and returns ITER_ERROR. * - * The reference currently being looked at can be peeled by calling - * ref_iterator_peel(). This function is often faster than peel_ref(), - * so it should be preferred when iterating over references. - * * Putting it all together, a typical iteration looks like this: * * int ok; @@ -1269,9 +1304,6 @@ int repo_migrate_ref_storage_format(struct repository *repo, * // Access information about the current reference: * if (!(iter->flags & REF_ISSYMREF)) * printf("%s is %s\n", iter->refname, oid_to_hex(iter->oid)); - * - * // If you need to peel the reference: - * ref_iterator_peel(iter, &oid); * } * * if (ok != ITER_DONE) @@ -1362,13 +1394,6 @@ enum ref_iterator_seek_flag { int ref_iterator_seek(struct ref_iterator *ref_iterator, const char *refname, unsigned int flags); -/* - * If possible, peel the reference currently being viewed by the - * iterator. Return 0 on success. - */ -int ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled); - /* Free the reference iterator and any associated resources. */ void ref_iterator_free(struct ref_iterator *ref_iterator); diff --git a/refs/debug.c b/refs/debug.c index c59c1728a3..3e31228c9a 100644 --- a/refs/debug.c +++ b/refs/debug.c @@ -124,11 +124,22 @@ static int debug_transaction_abort(struct ref_store *refs, return res; } -static int debug_pack_refs(struct ref_store *ref_store, struct pack_refs_opts *opts) +static int debug_optimize(struct ref_store *ref_store, struct refs_optimize_opts *opts) { struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; - int res = drefs->refs->be->pack_refs(drefs->refs, opts); - trace_printf_key(&trace_refs, "pack_refs: %d\n", res); + int res = drefs->refs->be->optimize(drefs->refs, opts); + trace_printf_key(&trace_refs, "optimize: %d\n", res); + return res; +} + +static int debug_optimize_required(struct ref_store *ref_store, + struct refs_optimize_opts *opts, + bool *required) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->optimize_required(drefs->refs, opts, required); + trace_printf_key(&trace_refs, "optimize_required: %s, res: %d\n", + required ? "yes" : "no", res); return res; } @@ -168,11 +179,9 @@ static int debug_ref_iterator_advance(struct ref_iterator *ref_iterator) trace_printf_key(&trace_refs, "iterator_advance: (%d)\n", res); else trace_printf_key(&trace_refs, "iterator_advance: %s (0)\n", - diter->iter->refname); + diter->iter->ref.name); - diter->base.refname = diter->iter->refname; - diter->base.oid = diter->iter->oid; - diter->base.flags = diter->iter->flags; + diter->base.ref = diter->iter->ref; return res; } @@ -187,16 +196,6 @@ static int debug_ref_iterator_seek(struct ref_iterator *ref_iterator, return res; } -static int debug_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct debug_ref_iterator *diter = - (struct debug_ref_iterator *)ref_iterator; - int res = diter->iter->vtable->peel(diter->iter, peeled); - trace_printf_key(&trace_refs, "iterator_peel: %s: %d\n", diter->iter->refname, res); - return res; -} - static void debug_ref_iterator_release(struct ref_iterator *ref_iterator) { struct debug_ref_iterator *diter = @@ -208,7 +207,6 @@ static void debug_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable debug_ref_iterator_vtable = { .advance = debug_ref_iterator_advance, .seek = debug_ref_iterator_seek, - .peel = debug_ref_iterator_peel, .release = debug_ref_iterator_release, }; @@ -452,7 +450,9 @@ struct ref_storage_be refs_be_debug = { .transaction_finish = debug_transaction_finish, .transaction_abort = debug_transaction_abort, - .pack_refs = debug_pack_refs, + .optimize = debug_optimize, + .optimize_required = debug_optimize_required, + .rename_ref = debug_rename_ref, .copy_ref = debug_copy_ref, diff --git a/refs/files-backend.c b/refs/files-backend.c index 1adc4b5182..6f6f76a8d8 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -961,26 +961,23 @@ static int files_ref_iterator_advance(struct ref_iterator *ref_iterator) while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { if (iter->flags & DO_FOR_EACH_PER_WORKTREE_ONLY && - parse_worktree_ref(iter->iter0->refname, NULL, NULL, + parse_worktree_ref(iter->iter0->ref.name, NULL, NULL, NULL) != REF_WORKTREE_CURRENT) continue; if ((iter->flags & DO_FOR_EACH_OMIT_DANGLING_SYMREFS) && - (iter->iter0->flags & REF_ISSYMREF) && - (iter->iter0->flags & REF_ISBROKEN)) + (iter->iter0->ref.flags & REF_ISSYMREF) && + (iter->iter0->ref.flags & REF_ISBROKEN)) continue; if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && - !ref_resolves_to_object(iter->iter0->refname, + !ref_resolves_to_object(iter->iter0->ref.name, iter->repo, - iter->iter0->oid, - iter->iter0->flags)) + iter->iter0->ref.oid, + iter->iter0->ref.flags)) continue; - iter->base.refname = iter->iter0->refname; - iter->base.oid = iter->iter0->oid; - iter->base.flags = iter->iter0->flags; - iter->base.referent = iter->iter0->referent; + iter->base.ref = iter->iter0->ref; return ITER_OK; } @@ -996,15 +993,6 @@ static int files_ref_iterator_seek(struct ref_iterator *ref_iterator, return ref_iterator_seek(iter->iter0, refname, flags); } -static int files_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct files_ref_iterator *iter = - (struct files_ref_iterator *)ref_iterator; - - return ref_iterator_peel(iter->iter0, peeled); -} - static void files_ref_iterator_release(struct ref_iterator *ref_iterator) { struct files_ref_iterator *iter = @@ -1015,7 +1003,6 @@ static void files_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable files_ref_iterator_vtable = { .advance = files_ref_iterator_advance, .seek = files_ref_iterator_seek, - .peel = files_ref_iterator_peel, .release = files_ref_iterator_release, }; @@ -1367,37 +1354,36 @@ static void prune_refs(struct files_ref_store *refs, struct ref_to_prune **refs_ * Return true if the specified reference should be packed. */ static int should_pack_ref(struct files_ref_store *refs, - const char *refname, - const struct object_id *oid, unsigned int ref_flags, - struct pack_refs_opts *opts) + const struct reference *ref, + struct refs_optimize_opts *opts) { struct string_list_item *item; /* Do not pack per-worktree refs: */ - if (parse_worktree_ref(refname, NULL, NULL, NULL) != + if (parse_worktree_ref(ref->name, NULL, NULL, NULL) != REF_WORKTREE_SHARED) return 0; /* Do not pack symbolic refs: */ - if (ref_flags & REF_ISSYMREF) + if (ref->flags & REF_ISSYMREF) return 0; /* Do not pack broken refs: */ - if (!ref_resolves_to_object(refname, refs->base.repo, oid, ref_flags)) + if (!ref_resolves_to_object(ref->name, refs->base.repo, ref->oid, ref->flags)) return 0; - if (ref_excluded(opts->exclusions, refname)) + if (ref_excluded(opts->exclusions, ref->name)) return 0; for_each_string_list_item(item, opts->includes) - if (!wildmatch(item->string, refname, 0)) + if (!wildmatch(item->string, ref->name, 0)) return 1; return 0; } static int should_pack_refs(struct files_ref_store *refs, - struct pack_refs_opts *opts) + struct refs_optimize_opts *opts) { struct ref_iterator *iter; size_t packed_size; @@ -1405,7 +1391,7 @@ static int should_pack_refs(struct files_ref_store *refs, size_t limit; int ret; - if (!(opts->flags & PACK_REFS_AUTO)) + if (!(opts->flags & REFS_OPTIMIZE_AUTO)) return 1; ret = packed_refs_size(refs->packed_ref_store, &packed_size); @@ -1443,8 +1429,7 @@ static int should_pack_refs(struct files_ref_store *refs, iter = cache_ref_iterator_begin(get_loose_ref_cache(refs, 0), NULL, refs->base.repo, 0); while ((ret = ref_iterator_advance(iter)) == ITER_OK) { - if (should_pack_ref(refs, iter->refname, iter->oid, - iter->flags, opts)) + if (should_pack_ref(refs, &iter->ref, opts)) refcount++; if (refcount >= limit) { ref_iterator_free(iter); @@ -1459,8 +1444,8 @@ static int should_pack_refs(struct files_ref_store *refs, return 0; } -static int files_pack_refs(struct ref_store *ref_store, - struct pack_refs_opts *opts) +static int files_optimize(struct ref_store *ref_store, + struct refs_optimize_opts *opts) { struct files_ref_store *refs = files_downcast(ref_store, REF_STORE_WRITE | REF_STORE_ODB, @@ -1489,24 +1474,24 @@ static int files_pack_refs(struct ref_store *ref_store, * in the packed ref cache. If the reference should be * pruned, also add it to refs_to_prune. */ - if (!should_pack_ref(refs, iter->refname, iter->oid, iter->flags, opts)) + if (!should_pack_ref(refs, &iter->ref, opts)) continue; /* * Add a reference creation for this reference to the * packed-refs transaction: */ - if (ref_transaction_update(transaction, iter->refname, - iter->oid, NULL, NULL, NULL, + if (ref_transaction_update(transaction, iter->ref.name, + iter->ref.oid, NULL, NULL, NULL, REF_NO_DEREF, NULL, &err)) die("failure preparing to create packed reference %s: %s", - iter->refname, err.buf); + iter->ref.name, err.buf); /* Schedule the loose reference for pruning if requested. */ - if ((opts->flags & PACK_REFS_PRUNE)) { + if ((opts->flags & REFS_OPTIMIZE_PRUNE)) { struct ref_to_prune *n; - FLEX_ALLOC_STR(n, name, iter->refname); - oidcpy(&n->oid, iter->oid); + FLEX_ALLOC_STR(n, name, iter->ref.name); + oidcpy(&n->oid, iter->ref.oid); n->next = refs_to_prune; refs_to_prune = n; } @@ -1527,13 +1512,14 @@ static int files_pack_refs(struct ref_store *ref_store, return 0; } -static int files_optimize(struct ref_store *ref_store, struct pack_refs_opts *opts) +static int files_optimize_required(struct ref_store *ref_store, + struct refs_optimize_opts *opts, + bool *required) { - /* - * For the "files" backend, "optimizing" is the same as "packing". - * So, we just call the existing worker function for packing. - */ - return files_pack_refs(ref_store, opts); + struct files_ref_store *refs = files_downcast(ref_store, REF_STORE_READ, + "optimize_required"); + *required = should_pack_refs(refs, opts); + return 0; } /* @@ -2394,7 +2380,7 @@ static int files_reflog_iterator_advance(struct ref_iterator *ref_iterator) REFNAME_ALLOW_ONELEVEL)) continue; - iter->base.refname = diter->relative_path; + iter->base.ref.name = diter->relative_path; return ITER_OK; } @@ -2408,12 +2394,6 @@ static int files_reflog_iterator_seek(struct ref_iterator *ref_iterator UNUSED, BUG("ref_iterator_seek() called for reflog_iterator"); } -static int files_reflog_iterator_peel(struct ref_iterator *ref_iterator UNUSED, - struct object_id *peeled UNUSED) -{ - BUG("ref_iterator_peel() called for reflog_iterator"); -} - static void files_reflog_iterator_release(struct ref_iterator *ref_iterator) { struct files_reflog_iterator *iter = @@ -2424,7 +2404,6 @@ static void files_reflog_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable files_reflog_iterator_vtable = { .advance = files_reflog_iterator_advance, .seek = files_reflog_iterator_seek, - .peel = files_reflog_iterator_peel, .release = files_reflog_iterator_release, }; @@ -3165,14 +3144,11 @@ static int parse_and_write_reflog(struct files_ref_store *refs, return 0; } -static int ref_present(const char *refname, const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, - void *cb_data) +static int ref_present(const struct reference *ref, void *cb_data) { struct string_list *affected_refnames = cb_data; - return string_list_has_string(affected_refnames, refname); + return string_list_has_string(affected_refnames, ref->name); } static int files_transaction_finish_initial(struct files_ref_store *refs, @@ -4015,8 +3991,8 @@ struct ref_storage_be refs_be_files = { .transaction_finish = files_transaction_finish, .transaction_abort = files_transaction_abort, - .pack_refs = files_pack_refs, .optimize = files_optimize, + .optimize_required = files_optimize_required, .rename_ref = files_rename_ref, .copy_ref = files_copy_ref, diff --git a/refs/iterator.c b/refs/iterator.c index 17ef841d8a..d79aa5ec82 100644 --- a/refs/iterator.c +++ b/refs/iterator.c @@ -21,12 +21,6 @@ int ref_iterator_seek(struct ref_iterator *ref_iterator, const char *refname, return ref_iterator->vtable->seek(ref_iterator, refname, flags); } -int ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - return ref_iterator->vtable->peel(ref_iterator, peeled); -} - void ref_iterator_free(struct ref_iterator *ref_iterator) { if (ref_iterator) { @@ -41,10 +35,7 @@ void base_ref_iterator_init(struct ref_iterator *iter, struct ref_iterator_vtable *vtable) { iter->vtable = vtable; - iter->refname = NULL; - iter->referent = NULL; - iter->oid = NULL; - iter->flags = 0; + memset(&iter->ref, 0, sizeof(iter->ref)); } struct empty_ref_iterator { @@ -63,12 +54,6 @@ static int empty_ref_iterator_seek(struct ref_iterator *ref_iterator UNUSED, return 0; } -static int empty_ref_iterator_peel(struct ref_iterator *ref_iterator UNUSED, - struct object_id *peeled UNUSED) -{ - BUG("peel called for empty iterator"); -} - static void empty_ref_iterator_release(struct ref_iterator *ref_iterator UNUSED) { } @@ -76,7 +61,6 @@ static void empty_ref_iterator_release(struct ref_iterator *ref_iterator UNUSED) static struct ref_iterator_vtable empty_ref_iterator_vtable = { .advance = empty_ref_iterator_advance, .seek = empty_ref_iterator_seek, - .peel = empty_ref_iterator_peel, .release = empty_ref_iterator_release, }; @@ -127,8 +111,8 @@ enum iterator_selection ref_iterator_select(struct ref_iterator *iter_worktree, * latter. */ if (iter_worktree) { - int cmp = strcmp(iter_worktree->refname, - iter_common->refname); + int cmp = strcmp(iter_worktree->ref.name, + iter_common->ref.name); if (cmp < 0) return ITER_SELECT_0; else if (!cmp) @@ -139,7 +123,7 @@ enum iterator_selection ref_iterator_select(struct ref_iterator *iter_worktree, * We now know that the lexicographically-next ref is a common * ref. When the common ref is a shared one we return it. */ - if (parse_worktree_ref(iter_common->refname, NULL, NULL, + if (parse_worktree_ref(iter_common->ref.name, NULL, NULL, NULL) == REF_WORKTREE_SHARED) return ITER_SELECT_1; @@ -212,10 +196,7 @@ static int merge_ref_iterator_advance(struct ref_iterator *ref_iterator) } if (selection & ITER_YIELD_CURRENT) { - iter->base.referent = (*iter->current)->referent; - iter->base.refname = (*iter->current)->refname; - iter->base.oid = (*iter->current)->oid; - iter->base.flags = (*iter->current)->flags; + iter->base.ref = (*iter->current)->ref; return ITER_OK; } } @@ -246,18 +227,6 @@ static int merge_ref_iterator_seek(struct ref_iterator *ref_iterator, return 0; } -static int merge_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct merge_ref_iterator *iter = - (struct merge_ref_iterator *)ref_iterator; - - if (!iter->current) { - BUG("peel called before advance for merge iterator"); - } - return ref_iterator_peel(*iter->current, peeled); -} - static void merge_ref_iterator_release(struct ref_iterator *ref_iterator) { struct merge_ref_iterator *iter = @@ -269,7 +238,6 @@ static void merge_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable merge_ref_iterator_vtable = { .advance = merge_ref_iterator_advance, .seek = merge_ref_iterator_seek, - .peel = merge_ref_iterator_peel, .release = merge_ref_iterator_release, }; @@ -313,7 +281,7 @@ static enum iterator_selection overlay_iterator_select( else if (!front) return ITER_SELECT_1; - cmp = strcmp(front->refname, back->refname); + cmp = strcmp(front->ref.name, back->ref.name); if (cmp < 0) return ITER_SELECT_0; @@ -371,7 +339,7 @@ static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) int ok; while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { - int cmp = compare_prefix(iter->iter0->refname, iter->prefix); + int cmp = compare_prefix(iter->iter0->ref.name, iter->prefix); if (cmp < 0) continue; /* @@ -382,6 +350,8 @@ static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) if (cmp > 0) return ITER_DONE; + iter->base.ref = iter->iter0->ref; + if (iter->trim) { /* * It is nonsense to trim off characters that @@ -392,15 +362,11 @@ static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) * one character left in the refname after * trimming, report it as a bug: */ - if (strlen(iter->iter0->refname) <= iter->trim) + if (strlen(iter->base.ref.name) <= iter->trim) BUG("attempt to trim too many characters"); - iter->base.refname = iter->iter0->refname + iter->trim; - } else { - iter->base.refname = iter->iter0->refname; + iter->base.ref.name += iter->trim; } - iter->base.oid = iter->iter0->oid; - iter->base.flags = iter->iter0->flags; return ITER_OK; } @@ -420,15 +386,6 @@ static int prefix_ref_iterator_seek(struct ref_iterator *ref_iterator, return ref_iterator_seek(iter->iter0, refname, flags); } -static int prefix_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct prefix_ref_iterator *iter = - (struct prefix_ref_iterator *)ref_iterator; - - return ref_iterator_peel(iter->iter0, peeled); -} - static void prefix_ref_iterator_release(struct ref_iterator *ref_iterator) { struct prefix_ref_iterator *iter = @@ -440,7 +397,6 @@ static void prefix_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable prefix_ref_iterator_vtable = { .advance = prefix_ref_iterator_advance, .seek = prefix_ref_iterator_seek, - .peel = prefix_ref_iterator_peel, .release = prefix_ref_iterator_release, }; @@ -466,23 +422,18 @@ struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, return ref_iterator; } -struct ref_iterator *current_ref_iter = NULL; - int do_for_each_ref_iterator(struct ref_iterator *iter, each_ref_fn fn, void *cb_data) { int retval = 0, ok; - struct ref_iterator *old_ref_iter = current_ref_iter; - current_ref_iter = iter; while ((ok = ref_iterator_advance(iter)) == ITER_OK) { - retval = fn(iter->refname, iter->referent, iter->oid, iter->flags, cb_data); + retval = fn(&iter->ref, cb_data); if (retval) goto out; } out: - current_ref_iter = old_ref_iter; if (ok == ITER_ERROR) retval = -1; ref_iterator_free(iter); diff --git a/refs/packed-backend.c b/refs/packed-backend.c index a8c22a0a7f..4ea0c12299 100644 --- a/refs/packed-backend.c +++ b/refs/packed-backend.c @@ -882,6 +882,7 @@ static int next_record(struct packed_ref_iterator *iter) { const char *p, *eol; + memset(&iter->base.ref, 0, sizeof(iter->base.ref)); strbuf_reset(&iter->refname_buf); /* @@ -908,7 +909,7 @@ static int next_record(struct packed_ref_iterator *iter) if (iter->pos == iter->eof) return ITER_DONE; - iter->base.flags = REF_ISPACKED; + iter->base.ref.flags = REF_ISPACKED; p = iter->pos; if (iter->eof - p < snapshot_hexsz(iter->snapshot) + 2 || @@ -916,6 +917,7 @@ static int next_record(struct packed_ref_iterator *iter) !isspace(*p++)) die_invalid_line(iter->snapshot->refs->path, iter->pos, iter->eof - iter->pos); + iter->base.ref.oid = &iter->oid; eol = memchr(p, '\n', iter->eof - p); if (!eol) @@ -923,22 +925,22 @@ static int next_record(struct packed_ref_iterator *iter) iter->pos, iter->eof - iter->pos); strbuf_add(&iter->refname_buf, p, eol - p); - iter->base.refname = iter->refname_buf.buf; + iter->base.ref.name = iter->refname_buf.buf; if (refname_contains_nul(&iter->refname_buf)) - die("packed refname contains embedded NULL: %s", iter->base.refname); + die("packed refname contains embedded NULL: %s", iter->base.ref.name); - if (check_refname_format(iter->base.refname, REFNAME_ALLOW_ONELEVEL)) { - if (!refname_is_safe(iter->base.refname)) + if (check_refname_format(iter->base.ref.name, REFNAME_ALLOW_ONELEVEL)) { + if (!refname_is_safe(iter->base.ref.name)) die("packed refname is dangerous: %s", - iter->base.refname); + iter->base.ref.name); oidclr(&iter->oid, iter->repo->hash_algo); - iter->base.flags |= REF_BAD_NAME | REF_ISBROKEN; + iter->base.ref.flags |= REF_BAD_NAME | REF_ISBROKEN; } if (iter->snapshot->peeled == PEELED_FULLY || (iter->snapshot->peeled == PEELED_TAGS && - starts_with(iter->base.refname, "refs/tags/"))) - iter->base.flags |= REF_KNOWS_PEELED; + starts_with(iter->base.ref.name, "refs/tags/"))) + iter->base.ref.flags |= REF_KNOWS_PEELED; iter->pos = eol + 1; @@ -956,11 +958,12 @@ static int next_record(struct packed_ref_iterator *iter) * definitely know the value of *this* reference. But * we suppress it if the reference is broken: */ - if ((iter->base.flags & REF_ISBROKEN)) { + if ((iter->base.ref.flags & REF_ISBROKEN)) { oidclr(&iter->peeled, iter->repo->hash_algo); - iter->base.flags &= ~REF_KNOWS_PEELED; + iter->base.ref.flags &= ~REF_KNOWS_PEELED; } else { - iter->base.flags |= REF_KNOWS_PEELED; + iter->base.ref.flags |= REF_KNOWS_PEELED; + iter->base.ref.peeled_oid = &iter->peeled; } } else { oidclr(&iter->peeled, iter->repo->hash_algo); @@ -976,15 +979,15 @@ static int packed_ref_iterator_advance(struct ref_iterator *ref_iterator) int ok; while ((ok = next_record(iter)) == ITER_OK) { - const char *refname = iter->base.refname; + const char *refname = iter->base.ref.name; const char *prefix = iter->prefix; if (iter->flags & DO_FOR_EACH_PER_WORKTREE_ONLY && - !is_per_worktree_ref(iter->base.refname)) + !is_per_worktree_ref(iter->base.ref.name)) continue; if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && - !ref_resolves_to_object(iter->base.refname, iter->repo, + !ref_resolves_to_object(iter->base.ref.name, iter->repo, &iter->oid, iter->flags)) continue; @@ -1027,22 +1030,6 @@ static int packed_ref_iterator_seek(struct ref_iterator *ref_iterator, return 0; } -static int packed_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct packed_ref_iterator *iter = - (struct packed_ref_iterator *)ref_iterator; - - if ((iter->base.flags & REF_KNOWS_PEELED)) { - oidcpy(peeled, &iter->peeled); - return is_null_oid(&iter->peeled) ? -1 : 0; - } else if ((iter->base.flags & (REF_ISBROKEN | REF_ISSYMREF))) { - return -1; - } else { - return peel_object(iter->repo, &iter->oid, peeled) ? -1 : 0; - } -} - static void packed_ref_iterator_release(struct ref_iterator *ref_iterator) { struct packed_ref_iterator *iter = @@ -1056,7 +1043,6 @@ static void packed_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable packed_ref_iterator_vtable = { .advance = packed_ref_iterator_advance, .seek = packed_ref_iterator_seek, - .peel = packed_ref_iterator_peel, .release = packed_ref_iterator_release, }; @@ -1194,7 +1180,6 @@ static struct ref_iterator *packed_ref_iterator_begin( iter->snapshot = snapshot; acquire_snapshot(snapshot); strbuf_init(&iter->refname_buf, 0); - iter->base.oid = &iter->oid; iter->repo = ref_store->repo; iter->flags = flags; @@ -1436,7 +1421,7 @@ static enum ref_transaction_error write_with_updates(struct packed_ref_store *re if (!iter) cmp = +1; else - cmp = strcmp(iter->refname, update->refname); + cmp = strcmp(iter->ref.name, update->refname); } if (!cmp) { @@ -1459,11 +1444,11 @@ static enum ref_transaction_error write_with_updates(struct packed_ref_store *re } goto error; - } else if (!oideq(&update->old_oid, iter->oid)) { + } else if (!oideq(&update->old_oid, iter->ref.oid)) { strbuf_addf(err, "cannot update ref '%s': " "is at %s but expected %s", update->refname, - oid_to_hex(iter->oid), + oid_to_hex(iter->ref.oid), oid_to_hex(&update->old_oid)); ret = REF_TRANSACTION_ERROR_INCORRECT_OLD_VALUE; @@ -1523,13 +1508,8 @@ static enum ref_transaction_error write_with_updates(struct packed_ref_store *re if (cmp < 0) { /* Pass the old reference through. */ - - struct object_id peeled; - int peel_error = ref_iterator_peel(iter, &peeled); - - if (write_packed_entry(out, iter->refname, - iter->oid, - peel_error ? NULL : &peeled)) + if (write_packed_entry(out, iter->ref.name, + iter->ref.oid, iter->ref.peeled_oid)) goto write_error; if ((ok = ref_iterator_advance(iter)) != ITER_OK) { @@ -1547,9 +1527,8 @@ static enum ref_transaction_error write_with_updates(struct packed_ref_store *re i++; } else { struct object_id peeled; - int peel_error = peel_object(refs->base.repo, - &update->new_oid, - &peeled); + int peel_error = peel_object(refs->base.repo, &update->new_oid, + &peeled, PEEL_OBJECT_VERIFY_TAGGED_OBJECT_TYPE); if (write_packed_entry(out, update->refname, &update->new_oid, @@ -1794,8 +1773,8 @@ cleanup: return ret; } -static int packed_pack_refs(struct ref_store *ref_store UNUSED, - struct pack_refs_opts *pack_opts UNUSED) +static int packed_optimize(struct ref_store *ref_store UNUSED, + struct refs_optimize_opts *opts UNUSED) { /* * Packed refs are already packed. It might be that loose refs @@ -1805,6 +1784,17 @@ static int packed_pack_refs(struct ref_store *ref_store UNUSED, return 0; } +static int packed_optimize_required(struct ref_store *ref_store UNUSED, + struct refs_optimize_opts *opts UNUSED, + bool *required) +{ + /* + * Packed refs are already optimized. + */ + *required = false; + return 0; +} + static struct ref_iterator *packed_reflog_iterator_begin(struct ref_store *ref_store UNUSED) { return empty_ref_iterator_begin(); @@ -2150,7 +2140,9 @@ struct ref_storage_be refs_be_packed = { .transaction_finish = packed_transaction_finish, .transaction_abort = packed_transaction_abort, - .pack_refs = packed_pack_refs, + .optimize = packed_optimize, + .optimize_required = packed_optimize_required, + .rename_ref = NULL, .copy_ref = NULL, diff --git a/refs/ref-cache.c b/refs/ref-cache.c index e5e5df16d8..ffef01a597 100644 --- a/refs/ref-cache.c +++ b/refs/ref-cache.c @@ -425,10 +425,11 @@ static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) level->prefix_state = entry_prefix_state; level->index = -1; } else { - iter->base.refname = entry->name; - iter->base.referent = entry->u.value.referent; - iter->base.oid = &entry->u.value.oid; - iter->base.flags = entry->flag; + memset(&iter->base.ref, 0, sizeof(iter->base.ref)); + iter->base.ref.name = entry->name; + iter->base.ref.target = entry->u.value.referent; + iter->base.ref.oid = &entry->u.value.oid; + iter->base.ref.flags = entry->flag; return ITER_OK; } } @@ -545,14 +546,6 @@ static int cache_ref_iterator_seek(struct ref_iterator *ref_iterator, return 0; } -static int cache_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct cache_ref_iterator *iter = - (struct cache_ref_iterator *)ref_iterator; - return peel_object(iter->repo, ref_iterator->oid, peeled) ? -1 : 0; -} - static void cache_ref_iterator_release(struct ref_iterator *ref_iterator) { struct cache_ref_iterator *iter = @@ -564,7 +557,6 @@ static void cache_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable cache_ref_iterator_vtable = { .advance = cache_ref_iterator_advance, .seek = cache_ref_iterator_seek, - .peel = cache_ref_iterator_peel, .release = cache_ref_iterator_release, }; diff --git a/refs/refs-internal.h b/refs/refs-internal.h index 4ef3bd75c6..c7d2a6e50b 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -249,10 +249,7 @@ const char *find_descendant_ref(const char *dirname, */ struct ref_iterator { struct ref_iterator_vtable *vtable; - const char *refname; - const char *referent; - const struct object_id *oid; - unsigned int flags; + struct reference ref; }; /* @@ -361,12 +358,6 @@ typedef int ref_iterator_seek_fn(struct ref_iterator *ref_iterator, const char *refname, unsigned int flags); /* - * Peels the current ref, returning 0 for success or -1 for failure. - */ -typedef int ref_iterator_peel_fn(struct ref_iterator *ref_iterator, - struct object_id *peeled); - -/* * Implementations of this function should free any resources specific * to the derived class. */ @@ -375,23 +366,9 @@ typedef void ref_iterator_release_fn(struct ref_iterator *ref_iterator); struct ref_iterator_vtable { ref_iterator_advance_fn *advance; ref_iterator_seek_fn *seek; - ref_iterator_peel_fn *peel; ref_iterator_release_fn *release; }; -/* - * current_ref_iter is a performance hack: when iterating over - * references using the for_each_ref*() functions, current_ref_iter is - * set to the reference iterator before calling the callback function. - * If the callback function calls peel_ref(), then peel_ref() first - * checks whether the reference to be peeled is the one referred to by - * the iterator (it usually is) and if so, asks the iterator for the - * peeled version of the reference if it is available. This avoids a - * refname lookup in a common case. current_ref_iter is set to NULL - * when the iteration is over. - */ -extern struct ref_iterator *current_ref_iter; - struct ref_store; /* refs backends */ @@ -445,10 +422,13 @@ typedef int ref_transaction_commit_fn(struct ref_store *refs, struct ref_transaction *transaction, struct strbuf *err); -typedef int pack_refs_fn(struct ref_store *ref_store, - struct pack_refs_opts *opts); typedef int optimize_fn(struct ref_store *ref_store, - struct pack_refs_opts *opts); + struct refs_optimize_opts *opts); + +typedef int optimize_required_fn(struct ref_store *ref_store, + struct refs_optimize_opts *opts, + bool *required); + typedef int rename_ref_fn(struct ref_store *ref_store, const char *oldref, const char *newref, const char *logmsg); @@ -573,8 +553,8 @@ struct ref_storage_be { ref_transaction_finish_fn *transaction_finish; ref_transaction_abort_fn *transaction_abort; - pack_refs_fn *pack_refs; optimize_fn *optimize; + optimize_required_fn *optimize_required; rename_ref_fn *rename_ref; copy_ref_fn *copy_ref; diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index eeec64798f..4319a4eacb 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -547,6 +547,7 @@ struct reftable_ref_iterator { struct reftable_iterator iter; struct reftable_ref_record ref; struct object_id oid; + struct object_id peeled_oid; char *prefix; size_t prefix_len; @@ -671,6 +672,8 @@ static int reftable_ref_iterator_advance(struct ref_iterator *ref_iterator) case REFTABLE_REF_VAL2: oidread(&iter->oid, iter->ref.value.val2.value, refs->base.repo->hash_algo); + oidread(&iter->peeled_oid, iter->ref.value.val2.target_value, + refs->base.repo->hash_algo); break; case REFTABLE_REF_SYMREF: referent = refs_resolve_ref_unsafe(&iter->refs->base, @@ -704,10 +707,13 @@ static int reftable_ref_iterator_advance(struct ref_iterator *ref_iterator) &iter->oid, flags)) continue; - iter->base.refname = iter->ref.refname; - iter->base.referent = referent; - iter->base.oid = &iter->oid; - iter->base.flags = flags; + memset(&iter->base.ref, 0, sizeof(iter->base.ref)); + iter->base.ref.name = iter->ref.refname; + iter->base.ref.target = referent; + iter->base.ref.oid = &iter->oid; + if (iter->ref.value_type == REFTABLE_REF_VAL2) + iter->base.ref.peeled_oid = &iter->peeled_oid; + iter->base.ref.flags = flags; break; } @@ -738,21 +744,6 @@ static int reftable_ref_iterator_seek(struct ref_iterator *ref_iterator, return iter->err; } -static int reftable_ref_iterator_peel(struct ref_iterator *ref_iterator, - struct object_id *peeled) -{ - struct reftable_ref_iterator *iter = - (struct reftable_ref_iterator *)ref_iterator; - - if (iter->ref.value_type == REFTABLE_REF_VAL2) { - oidread(peeled, iter->ref.value.val2.target_value, - iter->refs->base.repo->hash_algo); - return 0; - } - - return -1; -} - static void reftable_ref_iterator_release(struct ref_iterator *ref_iterator) { struct reftable_ref_iterator *iter = @@ -770,7 +761,6 @@ static void reftable_ref_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable reftable_ref_iterator_vtable = { .advance = reftable_ref_iterator_advance, .seek = reftable_ref_iterator_seek, - .peel = reftable_ref_iterator_peel, .release = reftable_ref_iterator_release, }; @@ -828,7 +818,7 @@ static struct reftable_ref_iterator *ref_iterator_for_stack(struct reftable_ref_ iter = xcalloc(1, sizeof(*iter)); base_ref_iterator_init(&iter->base, &reftable_ref_iterator_vtable); - iter->base.oid = &iter->oid; + iter->base.ref.oid = &iter->oid; iter->flags = flags; iter->refs = refs; iter->exclude_patterns = filter_exclude_patterns(exclude_patterns); @@ -1642,7 +1632,8 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data ref.refname = (char *)u->refname; ref.update_index = ts; - peel_error = peel_object(arg->refs->base.repo, &u->new_oid, &peeled); + peel_error = peel_object(arg->refs->base.repo, &u->new_oid, &peeled, + PEEL_OBJECT_VERIFY_TAGGED_OBJECT_TYPE); if (!peel_error) { ref.value_type = REFTABLE_REF_VAL2; memcpy(ref.value.val2.target_value, peeled.hash, GIT_MAX_RAWSZ); @@ -1709,11 +1700,11 @@ done: return ret; } -static int reftable_be_pack_refs(struct ref_store *ref_store, - struct pack_refs_opts *opts) +static int reftable_be_optimize(struct ref_store *ref_store, + struct refs_optimize_opts *opts) { struct reftable_ref_store *refs = - reftable_be_downcast(ref_store, REF_STORE_WRITE | REF_STORE_ODB, "pack_refs"); + reftable_be_downcast(ref_store, REF_STORE_WRITE | REF_STORE_ODB, "optimize_refs"); struct reftable_stack *stack; int ret; @@ -1724,7 +1715,7 @@ static int reftable_be_pack_refs(struct ref_store *ref_store, if (!stack) stack = refs->main_backend.stack; - if (opts->flags & PACK_REFS_AUTO) + if (opts->flags & REFS_OPTIMIZE_AUTO) ret = reftable_stack_auto_compact(stack); else ret = reftable_stack_compact_all(stack, NULL); @@ -1742,10 +1733,27 @@ out: return ret; } -static int reftable_be_optimize(struct ref_store *ref_store, - struct pack_refs_opts *opts) +static int reftable_be_optimize_required(struct ref_store *ref_store, + struct refs_optimize_opts *opts, + bool *required) { - return reftable_be_pack_refs(ref_store, opts); + struct reftable_ref_store *refs = reftable_be_downcast(ref_store, REF_STORE_READ, + "optimize_refs_required"); + struct reftable_stack *stack; + bool use_heuristics = false; + + if (refs->err) + return refs->err; + + stack = refs->worktree_backend.stack; + if (!stack) + stack = refs->main_backend.stack; + + if (opts->flags & REFS_OPTIMIZE_AUTO) + use_heuristics = true; + + return reftable_stack_compaction_required(stack, use_heuristics, + required); } struct write_create_symref_arg { @@ -2072,7 +2080,7 @@ static int reftable_reflog_iterator_advance(struct ref_iterator *ref_iterator) strbuf_reset(&iter->last_name); strbuf_addstr(&iter->last_name, iter->log.refname); - iter->base.refname = iter->log.refname; + iter->base.ref.name = iter->log.refname; break; } @@ -2092,13 +2100,6 @@ static int reftable_reflog_iterator_seek(struct ref_iterator *ref_iterator UNUSE return -1; } -static int reftable_reflog_iterator_peel(struct ref_iterator *ref_iterator UNUSED, - struct object_id *peeled UNUSED) -{ - BUG("reftable reflog iterator cannot be peeled"); - return -1; -} - static void reftable_reflog_iterator_release(struct ref_iterator *ref_iterator) { struct reftable_reflog_iterator *iter = @@ -2111,7 +2112,6 @@ static void reftable_reflog_iterator_release(struct ref_iterator *ref_iterator) static struct ref_iterator_vtable reftable_reflog_iterator_vtable = { .advance = reftable_reflog_iterator_advance, .seek = reftable_reflog_iterator_seek, - .peel = reftable_reflog_iterator_peel, .release = reftable_reflog_iterator_release, }; @@ -2515,7 +2515,7 @@ static int write_reflog_expiry_table(struct reftable_writer *writer, void *cb_da ref.refname = (char *)arg->refname; ref.update_index = ts; - if (!peel_object(arg->refs->base.repo, &arg->update_oid, &peeled)) { + if (!peel_object(arg->refs->base.repo, &arg->update_oid, &peeled, 0)) { ref.value_type = REFTABLE_REF_VAL2; memcpy(ref.value.val2.target_value, peeled.hash, GIT_MAX_RAWSZ); memcpy(ref.value.val2.value, arg->update_oid.hash, GIT_MAX_RAWSZ); @@ -2778,8 +2778,9 @@ struct ref_storage_be refs_be_reftable = { .transaction_finish = reftable_be_transaction_finish, .transaction_abort = reftable_be_transaction_abort, - .pack_refs = reftable_be_pack_refs, .optimize = reftable_be_optimize, + .optimize_required = reftable_be_optimize_required, + .rename_ref = reftable_be_rename_ref, .copy_ref = reftable_be_copy_ref, diff --git a/reftable/reftable-stack.h b/reftable/reftable-stack.h index d70fcb705d..c2415cbc6e 100644 --- a/reftable/reftable-stack.h +++ b/reftable/reftable-stack.h @@ -123,6 +123,17 @@ struct reftable_log_expiry_config { int reftable_stack_compact_all(struct reftable_stack *st, struct reftable_log_expiry_config *config); +/* + * Check if compaction is required. + * + * When `use_heuristics` is false, check if all tables can be compacted to a + * single table. If true, use heuristics to determine if the tables need to be + * compacted to maintain geometric progression. + */ +int reftable_stack_compaction_required(struct reftable_stack *st, + bool use_heuristics, + bool *required); + /* heuristically compact unbalanced table stack. */ int reftable_stack_auto_compact(struct reftable_stack *st); diff --git a/reftable/stack.c b/reftable/stack.c index 65d89820bd..1c9f21dfe1 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -1626,7 +1626,8 @@ struct segment suggest_compaction_segment(uint64_t *sizes, size_t n, return seg; } -static uint64_t *stack_table_sizes_for_compaction(struct reftable_stack *st) +static int stack_segments_for_compaction(struct reftable_stack *st, + struct segment *seg) { int version = (st->opts.hash_id == REFTABLE_HASH_SHA1) ? 1 : 2; int overhead = header_size(version) - 1; @@ -1634,31 +1635,63 @@ static uint64_t *stack_table_sizes_for_compaction(struct reftable_stack *st) REFTABLE_CALLOC_ARRAY(sizes, st->merged->tables_len); if (!sizes) - return NULL; + return REFTABLE_OUT_OF_MEMORY_ERROR; for (size_t i = 0; i < st->merged->tables_len; i++) sizes[i] = st->tables[i]->size - overhead; - return sizes; + *seg = suggest_compaction_segment(sizes, st->merged->tables_len, + st->opts.auto_compaction_factor); + reftable_free(sizes); + + return 0; } -int reftable_stack_auto_compact(struct reftable_stack *st) +static int update_segment_if_compaction_required(struct reftable_stack *st, + struct segment *seg, + bool use_geometric, + bool *required) { - struct segment seg; - uint64_t *sizes; + int err; - if (st->merged->tables_len < 2) + if (st->merged->tables_len < 2) { + *required = false; return 0; + } - sizes = stack_table_sizes_for_compaction(st); - if (!sizes) - return REFTABLE_OUT_OF_MEMORY_ERROR; + if (!use_geometric) { + *required = true; + return 0; + } - seg = suggest_compaction_segment(sizes, st->merged->tables_len, - st->opts.auto_compaction_factor); - reftable_free(sizes); + err = stack_segments_for_compaction(st, seg); + if (err) + return err; + + *required = segment_size(seg) > 0; + return 0; +} + +int reftable_stack_compaction_required(struct reftable_stack *st, + bool use_heuristics, + bool *required) +{ + struct segment seg; + return update_segment_if_compaction_required(st, &seg, use_heuristics, + required); +} + +int reftable_stack_auto_compact(struct reftable_stack *st) +{ + struct segment seg; + bool required; + int err; + + err = update_segment_if_compaction_required(st, &seg, true, &required); + if (err) + return err; - if (segment_size(&seg) > 0) + if (required) return stack_compact_range(st, seg.start, seg.end - 1, NULL, STACK_COMPACT_RANGE_BEST_EFFORT); @@ -2315,21 +2315,19 @@ int format_tracking_info(struct branch *branch, struct strbuf *sb, return 1; } -static int one_local_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int one_local_ref(const struct reference *ref, void *cb_data) { struct ref ***local_tail = cb_data; - struct ref *ref; + struct ref *local_ref; /* we already know it starts with refs/ to get here */ - if (check_refname_format(refname + 5, 0)) + if (check_refname_format(ref->name + 5, 0)) return 0; - ref = alloc_ref(refname); - oidcpy(&ref->new_oid, oid); - **local_tail = ref; - *local_tail = &ref->next; + local_ref = alloc_ref(ref->name); + oidcpy(&local_ref->new_oid, ref->oid); + **local_tail = local_ref; + *local_tail = &local_ref->next; return 0; } @@ -2402,15 +2400,14 @@ struct stale_heads_info { struct refspec *rs; }; -static int get_stale_heads_cb(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags, void *cb_data) +static int get_stale_heads_cb(const struct reference *ref, void *cb_data) { struct stale_heads_info *info = cb_data; struct string_list matches = STRING_LIST_INIT_DUP; struct refspec_item query; int i, stale = 1; memset(&query, 0, sizeof(struct refspec_item)); - query.dst = (char *)refname; + query.dst = (char *)ref->name; refspec_find_all_matches(info->rs, &query, &matches); if (matches.nr == 0) @@ -2423,7 +2420,7 @@ static int get_stale_heads_cb(const char *refname, const char *referent UNUSED, * overlapping refspecs, we need to go over all of the * matching refs. */ - if (flags & REF_ISSYMREF) + if (ref->flags & REF_ISSYMREF) goto clean_exit; for (i = 0; stale && i < matches.nr; i++) @@ -2431,8 +2428,8 @@ static int get_stale_heads_cb(const char *refname, const char *referent UNUSED, stale = 0; if (stale) { - struct ref *ref = make_linked_ref(refname, &info->stale_refs_tail); - oidcpy(&ref->new_oid, oid); + struct ref *linked_ref = make_linked_ref(ref->name, &info->stale_refs_tail); + oidcpy(&linked_ref->new_oid, ref->oid); } clean_exit: diff --git a/repack-midx.c b/repack-midx.c index 6f6202c5bc..74bdfa3a6e 100644 --- a/repack-midx.c +++ b/repack-midx.c @@ -16,25 +16,23 @@ struct midx_snapshot_ref_data { int preferred; }; -static int midx_snapshot_ref_one(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, void *_data) +static int midx_snapshot_ref_one(const struct reference *ref, void *_data) { struct midx_snapshot_ref_data *data = _data; + const struct object_id *maybe_peeled = ref->oid; struct object_id peeled; - if (!peel_iterated_oid(data->repo, oid, &peeled)) - oid = &peeled; + if (!reference_get_peeled_oid(data->repo, ref, &peeled)) + maybe_peeled = &peeled; - if (oidset_insert(&data->seen, oid)) + if (oidset_insert(&data->seen, maybe_peeled)) return 0; /* already seen */ - if (odb_read_object_info(data->repo->objects, oid, NULL) != OBJ_COMMIT) + if (odb_read_object_info(data->repo->objects, maybe_peeled, NULL) != OBJ_COMMIT) return 0; fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "", - oid_to_hex(oid)); + oid_to_hex(maybe_peeled)); return 0; } diff --git a/replace-object.c b/replace-object.c index 3eae051074..03d0f1f083 100644 --- a/replace-object.c +++ b/replace-object.c @@ -8,31 +8,27 @@ #include "repository.h" #include "commit.h" -static int register_replace_ref(const char *refname, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int register_replace_ref(const struct reference *ref, void *cb_data) { struct repository *r = cb_data; /* Get sha1 from refname */ - const char *slash = strrchr(refname, '/'); - const char *hash = slash ? slash + 1 : refname; + const char *slash = strrchr(ref->name, '/'); + const char *hash = slash ? slash + 1 : ref->name; struct replace_object *repl_obj = xmalloc(sizeof(*repl_obj)); if (get_oid_hex_algop(hash, &repl_obj->original.oid, r->hash_algo)) { free(repl_obj); - warning(_("bad replace ref name: %s"), refname); + warning(_("bad replace ref name: %s"), ref->name); return 0; } /* Copy sha1 from the read ref */ - oidcpy(&repl_obj->replacement, oid); + oidcpy(&repl_obj->replacement, ref->oid); /* Register new object */ if (oidmap_put(&r->objects->replace_map, repl_obj)) - die(_("duplicate replace ref: %s"), refname); + die(_("duplicate replace ref: %s"), ref->name); return 0; } diff --git a/repository.c b/repository.c index 6faf5c7398..863f24411b 100644 --- a/repository.c +++ b/repository.c @@ -52,7 +52,6 @@ static void set_default_hash_algo(struct repository *repo) void initialize_repository(struct repository *repo) { - repo->objects = odb_new(repo); repo->remote_state = remote_state_new(); repo->parsed_objects = parsed_object_pool_new(repo); ALLOC_ARRAY(repo->index, 1); @@ -166,19 +165,13 @@ void repo_set_gitdir(struct repository *repo, repo_set_commondir(repo, o->commondir); - if (!repo->objects->sources) { - CALLOC_ARRAY(repo->objects->sources, 1); - repo->objects->sources->odb = repo->objects; - repo->objects->sources->local = true; - repo->objects->sources_tail = &repo->objects->sources->next; - } - expand_base_dir(&repo->objects->sources->path, o->object_dir, - repo->commondir, "objects"); + if (!repo->objects) + repo->objects = odb_new(repo, o->object_dir, o->alternate_db); + else if (!o->skip_initializing_odb) + BUG("cannot reinitialize an already-initialized object directory"); - repo->objects->sources->disable_ref_updates = o->disable_ref_updates; + repo->disable_ref_updates = o->disable_ref_updates; - free(repo->objects->alternate_db); - repo->objects->alternate_db = xstrdup_or_null(o->alternate_db); expand_base_dir(&repo->graft_file, o->graft_file, repo->commondir, "info/grafts"); expand_base_dir(&repo->index_file, o->index_file, @@ -378,8 +371,8 @@ void repo_clear(struct repository *repo) FREE_AND_NULL(repo->worktree); FREE_AND_NULL(repo->submodule_prefix); - odb_clear(repo->objects); - FREE_AND_NULL(repo->objects); + odb_free(repo->objects); + repo->objects = NULL; parsed_object_pool_clear(repo->parsed_objects); FREE_AND_NULL(repo->parsed_objects); diff --git a/repository.h b/repository.h index 5808a5d610..6063c4b846 100644 --- a/repository.h +++ b/repository.h @@ -72,6 +72,13 @@ struct repository { struct ref_store *refs_private; /* + * Disable ref updates. This is especially used in contexts where + * transactions may still be rolled back so that we don't start to + * reference objects that may vanish. + */ + bool disable_ref_updates; + + /* * A strmap of ref_stores, stored by submodule name, accessible via * `repo_get_submodule_ref_store()`. */ @@ -187,7 +194,8 @@ struct set_gitdir_args { const char *graft_file; const char *index_file; const char *alternate_db; - int disable_ref_updates; + bool disable_ref_updates; + bool skip_initializing_odb; }; void repo_set_gitdir(struct repository *repo, const char *root, diff --git a/revision.c b/revision.c index cf5e6c1ec9..5f0850ae5c 100644 --- a/revision.c +++ b/revision.c @@ -1644,19 +1644,17 @@ struct all_refs_cb { struct worktree *wt; }; -static int handle_one_ref(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int handle_one_ref(const struct reference *ref, void *cb_data) { struct all_refs_cb *cb = cb_data; struct object *object; - if (ref_excluded(&cb->all_revs->ref_excludes, path)) + if (ref_excluded(&cb->all_revs->ref_excludes, ref->name)) return 0; - object = get_reference(cb->all_revs, path, oid, cb->all_flags); - add_rev_cmdline(cb->all_revs, object, path, REV_CMD_REF, cb->all_flags); - add_pending_object(cb->all_revs, object, path); + object = get_reference(cb->all_revs, ref->name, ref->oid, cb->all_flags); + add_rev_cmdline(cb->all_revs, object, ref->name, REV_CMD_REF, cb->all_flags); + add_pending_object(cb->all_revs, object, ref->name); return 0; } diff --git a/run-command.c b/run-command.c index ed9575bd6a..e3e02475cc 100644 --- a/run-command.c +++ b/run-command.c @@ -743,7 +743,7 @@ fail_pipe: fflush(NULL); if (cmd->close_object_store) - close_object_store(the_repository->objects); + odb_close(the_repository->objects); #ifndef GIT_WINDOWS_NATIVE { @@ -931,7 +931,7 @@ static int cmd_delete(int argc, const char **argv) if (dir_inside_of(cwd, enlistment.buf) >= 0) res = error(_("refusing to delete current working directory")); else { - close_object_store(the_repository->objects); + odb_close(the_repository->objects); res = delete_enlistment(&enlistment); } strbuf_release(&enlistment); diff --git a/server-info.c b/server-info.c index b9a710544a..4243e24edc 100644 --- a/server-info.c +++ b/server-info.c @@ -148,23 +148,21 @@ out: return ret; } -static int add_info_ref(const char *path, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, - void *cb_data) +static int add_info_ref(const struct reference *ref, void *cb_data) { struct update_info_ctx *uic = cb_data; - struct object *o = parse_object(uic->repo, oid); + struct object *o = parse_object(uic->repo, ref->oid); if (!o) return -1; - if (uic_printf(uic, "%s %s\n", oid_to_hex(oid), path) < 0) + if (uic_printf(uic, "%s %s\n", oid_to_hex(ref->oid), ref->name) < 0) return -1; if (o->type == OBJ_TAG) { - o = deref_tag(uic->repo, o, path, 0); + o = deref_tag(uic->repo, o, ref->name, 0); if (o) if (uic_printf(uic, "%s %s^{}\n", - oid_to_hex(&o->oid), path) < 0) + oid_to_hex(&o->oid), ref->name) < 0) return -1; } return 0; @@ -22,7 +22,6 @@ #include "chdir-notify.h" #include "path.h" #include "quote.h" -#include "tmp-objdir.h" #include "trace.h" #include "trace2.h" #include "worktree.h" @@ -1002,6 +1001,83 @@ cleanup_return: return error_code ? NULL : path; } +static void setup_git_env_internal(const char *git_dir, + bool skip_initializing_odb) +{ + char *git_replace_ref_base; + const char *shallow_file; + const char *replace_ref_base; + struct set_gitdir_args args = { NULL }; + struct strvec to_free = STRVEC_INIT; + + args.commondir = getenv_safe(&to_free, GIT_COMMON_DIR_ENVIRONMENT); + args.object_dir = getenv_safe(&to_free, DB_ENVIRONMENT); + args.graft_file = getenv_safe(&to_free, GRAFT_ENVIRONMENT); + args.index_file = getenv_safe(&to_free, INDEX_ENVIRONMENT); + args.alternate_db = getenv_safe(&to_free, ALTERNATE_DB_ENVIRONMENT); + if (getenv(GIT_QUARANTINE_ENVIRONMENT)) + args.disable_ref_updates = true; + args.skip_initializing_odb = skip_initializing_odb; + + repo_set_gitdir(the_repository, git_dir, &args); + strvec_clear(&to_free); + + if (getenv(NO_REPLACE_OBJECTS_ENVIRONMENT)) + disable_replace_refs(); + replace_ref_base = getenv(GIT_REPLACE_REF_BASE_ENVIRONMENT); + git_replace_ref_base = xstrdup(replace_ref_base ? replace_ref_base + : "refs/replace/"); + update_ref_namespace(NAMESPACE_REPLACE, git_replace_ref_base); + + shallow_file = getenv(GIT_SHALLOW_FILE_ENVIRONMENT); + if (shallow_file) + set_alternate_shallow_file(the_repository, shallow_file, 0); + + if (git_env_bool(NO_LAZY_FETCH_ENVIRONMENT, 0)) + fetch_if_missing = 0; +} + +void setup_git_env(const char *git_dir) +{ + setup_git_env_internal(git_dir, false); +} + +static void set_git_dir_1(const char *path, bool skip_initializing_odb) +{ + xsetenv(GIT_DIR_ENVIRONMENT, path, 1); + setup_git_env_internal(path, skip_initializing_odb); +} + +static void update_relative_gitdir(const char *name UNUSED, + const char *old_cwd, + const char *new_cwd, + void *data UNUSED) +{ + char *path = reparent_relative_path(old_cwd, new_cwd, + repo_get_git_dir(the_repository)); + trace_printf_key(&trace_setup_key, + "setup: move $GIT_DIR to '%s'", + path); + set_git_dir_1(path, true); + free(path); +} + +static void set_git_dir(const char *path, int make_realpath) +{ + struct strbuf realpath = STRBUF_INIT; + + if (make_realpath) { + strbuf_realpath(&realpath, path, 1); + path = realpath.buf; + } + + set_git_dir_1(path, false); + if (!is_absolute_path(path)) + chdir_notify_register(NULL, update_relative_gitdir, NULL); + + strbuf_release(&realpath); +} + static const char *setup_explicit_git_dir(const char *gitdirenv, struct strbuf *cwd, struct repository_format *repo_fmt, @@ -1248,7 +1324,7 @@ static int safe_directory_cb(const char *key, const char *value, } else { char *allowed = NULL; - if (!git_config_pathname(&allowed, key, value)) { + if (!git_config_pathname(&allowed, key, value) && allowed) { char *normalized = NULL; /* @@ -1628,79 +1704,85 @@ enum discovery_result discover_git_directory_reason(struct strbuf *commondir, return result; } -void setup_git_env(const char *git_dir) -{ - char *git_replace_ref_base; - const char *shallow_file; - const char *replace_ref_base; - struct set_gitdir_args args = { NULL }; - struct strvec to_free = STRVEC_INIT; - - args.commondir = getenv_safe(&to_free, GIT_COMMON_DIR_ENVIRONMENT); - args.object_dir = getenv_safe(&to_free, DB_ENVIRONMENT); - args.graft_file = getenv_safe(&to_free, GRAFT_ENVIRONMENT); - args.index_file = getenv_safe(&to_free, INDEX_ENVIRONMENT); - args.alternate_db = getenv_safe(&to_free, ALTERNATE_DB_ENVIRONMENT); - if (getenv(GIT_QUARANTINE_ENVIRONMENT)) { - args.disable_ref_updates = 1; - } - - repo_set_gitdir(the_repository, git_dir, &args); - strvec_clear(&to_free); - - if (getenv(NO_REPLACE_OBJECTS_ENVIRONMENT)) - disable_replace_refs(); - replace_ref_base = getenv(GIT_REPLACE_REF_BASE_ENVIRONMENT); - git_replace_ref_base = xstrdup(replace_ref_base ? replace_ref_base - : "refs/replace/"); - update_ref_namespace(NAMESPACE_REPLACE, git_replace_ref_base); - - shallow_file = getenv(GIT_SHALLOW_FILE_ENVIRONMENT); - if (shallow_file) - set_alternate_shallow_file(the_repository, shallow_file, 0); - - if (git_env_bool(NO_LAZY_FETCH_ENVIRONMENT, 0)) - fetch_if_missing = 0; -} - -static void set_git_dir_1(const char *path) +const char *enter_repo(const char *path, unsigned flags) { - xsetenv(GIT_DIR_ENVIRONMENT, path, 1); - setup_git_env(path); -} + static struct strbuf validated_path = STRBUF_INIT; + static struct strbuf used_path = STRBUF_INIT; -static void update_relative_gitdir(const char *name UNUSED, - const char *old_cwd, - const char *new_cwd, - void *data UNUSED) -{ - char *path = reparent_relative_path(old_cwd, new_cwd, - repo_get_git_dir(the_repository)); - struct tmp_objdir *tmp_objdir = tmp_objdir_unapply_primary_odb(); + if (!path) + return NULL; - trace_printf_key(&trace_setup_key, - "setup: move $GIT_DIR to '%s'", - path); - set_git_dir_1(path); - if (tmp_objdir) - tmp_objdir_reapply_primary_odb(tmp_objdir, old_cwd, new_cwd); - free(path); -} + if (!(flags & ENTER_REPO_STRICT)) { + static const char *suffix[] = { + "/.git", "", ".git/.git", ".git", NULL, + }; + const char *gitfile; + int len = strlen(path); + int i; + while ((1 < len) && (path[len-1] == '/')) + len--; -void set_git_dir(const char *path, int make_realpath) -{ - struct strbuf realpath = STRBUF_INIT; + /* + * We can handle arbitrary-sized buffers, but this remains as a + * sanity check on untrusted input. + */ + if (PATH_MAX <= len) + return NULL; - if (make_realpath) { - strbuf_realpath(&realpath, path, 1); - path = realpath.buf; + strbuf_reset(&used_path); + strbuf_reset(&validated_path); + strbuf_add(&used_path, path, len); + strbuf_add(&validated_path, path, len); + + if (used_path.buf[0] == '~') { + char *newpath = interpolate_path(used_path.buf, 0); + if (!newpath) + return NULL; + strbuf_attach(&used_path, newpath, strlen(newpath), + strlen(newpath)); + } + for (i = 0; suffix[i]; i++) { + struct stat st; + size_t baselen = used_path.len; + strbuf_addstr(&used_path, suffix[i]); + if (!stat(used_path.buf, &st) && + (S_ISREG(st.st_mode) || + (S_ISDIR(st.st_mode) && is_git_directory(used_path.buf)))) { + strbuf_addstr(&validated_path, suffix[i]); + break; + } + strbuf_setlen(&used_path, baselen); + } + if (!suffix[i]) + return NULL; + gitfile = read_gitfile(used_path.buf); + if (!(flags & ENTER_REPO_ANY_OWNER_OK)) + die_upon_dubious_ownership(gitfile, NULL, used_path.buf); + if (gitfile) { + strbuf_reset(&used_path); + strbuf_addstr(&used_path, gitfile); + } + if (chdir(used_path.buf)) + return NULL; + path = validated_path.buf; + } + else { + const char *gitfile = read_gitfile(path); + if (!(flags & ENTER_REPO_ANY_OWNER_OK)) + die_upon_dubious_ownership(gitfile, NULL, path); + if (gitfile) + path = gitfile; + if (chdir(path)) + return NULL; } - set_git_dir_1(path); - if (!is_absolute_path(path)) - chdir_notify_register(NULL, update_relative_gitdir, NULL); + if (is_git_directory(".")) { + set_git_dir(".", 0); + check_repository_format(NULL); + return path; + } - strbuf_release(&realpath); + return NULL; } static int git_work_tree_initialized; @@ -94,9 +94,46 @@ static inline int discover_git_directory(struct strbuf *commondir, return 0; } -void set_git_dir(const char *path, int make_realpath); void set_git_work_tree(const char *tree); +/* Flags that can be passed to `enter_repo()`. */ +enum { + /* + * Callers that require exact paths (as opposed to allowing known + * suffixes like ".git", ".git/.git" to be omitted) can set this bit. + */ + ENTER_REPO_STRICT = (1<<0), + + /* + * Callers that are willing to run without ownership check can set this + * bit. + */ + ENTER_REPO_ANY_OWNER_OK = (1<<1), +}; + +/* + * Discover and enter a repository. + * + * First, one directory to try is determined by the following algorithm. + * + * (0) If "strict" is given, the path is used as given and no DWIM is + * done. Otherwise: + * (1) "~/path" to mean path under the running user's home directory; + * (2) "~user/path" to mean path under named user's home directory; + * (3) "relative/path" to mean cwd relative directory; or + * (4) "/absolute/path" to mean absolute directory. + * + * Unless "strict" is given, we check "%s/.git", "%s", "%s.git/.git", "%s.git" + * in this order. We select the first one that is a valid git repository, and + * chdir() to it. If none match, or we fail to chdir, we return NULL. + * + * If all goes well, we return the directory we used to chdir() (but + * before ~user is expanded), avoiding getcwd() resolving symbolic + * links. User relative paths are also returned as they are given, + * except DWIM suffixing. + */ +const char *enter_repo(const char *path, unsigned flags); + const char *setup_git_directory_gently(int *); const char *setup_git_directory(void); char *prefix_path(const char *prefix, int len, const char *path); @@ -626,14 +626,10 @@ static void paint_down(struct paint_info *info, const struct object_id *oid, free(tmp); } -static int mark_uninteresting(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *cb_data UNUSED) +static int mark_uninteresting(const struct reference *ref, void *cb_data UNUSED) { struct commit *commit = lookup_commit_reference_gently(the_repository, - oid, 1); + ref->oid, 1); if (!commit) return 0; commit->object.flags |= UNINTERESTING; @@ -742,16 +738,12 @@ struct commit_array { size_t nr, alloc; }; -static int add_ref(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, - void *cb_data) +static int add_ref(const struct reference *ref, void *cb_data) { struct commit_array *ca = cb_data; ALLOC_GROW(ca->commits, ca->nr + 1, ca->alloc); ca->commits[ca->nr] = lookup_commit_reference_gently(the_repository, - oid, 1); + ref->oid, 1); if (ca->commits[ca->nr]) ca->nr++; return 0; diff --git a/streaming.c b/streaming.c deleted file mode 100644 index 4b13827668..0000000000 --- a/streaming.c +++ /dev/null @@ -1,552 +0,0 @@ -/* - * Copyright (c) 2011, Google Inc. - */ - -#define USE_THE_REPOSITORY_VARIABLE - -#include "git-compat-util.h" -#include "convert.h" -#include "environment.h" -#include "streaming.h" -#include "repository.h" -#include "object-file.h" -#include "odb.h" -#include "replace-object.h" -#include "packfile.h" - -typedef int (*open_istream_fn)(struct git_istream *, - struct repository *, - const struct object_id *, - enum object_type *); -typedef int (*close_istream_fn)(struct git_istream *); -typedef ssize_t (*read_istream_fn)(struct git_istream *, char *, size_t); - -#define FILTER_BUFFER (1024*16) - -struct filtered_istream { - struct git_istream *upstream; - struct stream_filter *filter; - char ibuf[FILTER_BUFFER]; - char obuf[FILTER_BUFFER]; - int i_end, i_ptr; - int o_end, o_ptr; - int input_finished; -}; - -struct git_istream { - open_istream_fn open; - close_istream_fn close; - read_istream_fn read; - - unsigned long size; /* inflated size of full object */ - git_zstream z; - enum { z_unused, z_used, z_done, z_error } z_state; - - union { - struct { - char *buf; /* from odb_read_object_info_extended() */ - unsigned long read_ptr; - } incore; - - struct { - void *mapped; - unsigned long mapsize; - char hdr[32]; - int hdr_avail; - int hdr_used; - } loose; - - struct { - struct packed_git *pack; - off_t pos; - } in_pack; - - struct filtered_istream filtered; - } u; -}; - -/***************************************************************** - * - * Common helpers - * - *****************************************************************/ - -static void close_deflated_stream(struct git_istream *st) -{ - if (st->z_state == z_used) - git_inflate_end(&st->z); -} - - -/***************************************************************** - * - * Filtered stream - * - *****************************************************************/ - -static int close_istream_filtered(struct git_istream *st) -{ - free_stream_filter(st->u.filtered.filter); - return close_istream(st->u.filtered.upstream); -} - -static ssize_t read_istream_filtered(struct git_istream *st, char *buf, - size_t sz) -{ - struct filtered_istream *fs = &(st->u.filtered); - size_t filled = 0; - - while (sz) { - /* do we already have filtered output? */ - if (fs->o_ptr < fs->o_end) { - size_t to_move = fs->o_end - fs->o_ptr; - if (sz < to_move) - to_move = sz; - memcpy(buf + filled, fs->obuf + fs->o_ptr, to_move); - fs->o_ptr += to_move; - sz -= to_move; - filled += to_move; - continue; - } - fs->o_end = fs->o_ptr = 0; - - /* do we have anything to feed the filter with? */ - if (fs->i_ptr < fs->i_end) { - size_t to_feed = fs->i_end - fs->i_ptr; - size_t to_receive = FILTER_BUFFER; - if (stream_filter(fs->filter, - fs->ibuf + fs->i_ptr, &to_feed, - fs->obuf, &to_receive)) - return -1; - fs->i_ptr = fs->i_end - to_feed; - fs->o_end = FILTER_BUFFER - to_receive; - continue; - } - - /* tell the filter to drain upon no more input */ - if (fs->input_finished) { - size_t to_receive = FILTER_BUFFER; - if (stream_filter(fs->filter, - NULL, NULL, - fs->obuf, &to_receive)) - return -1; - fs->o_end = FILTER_BUFFER - to_receive; - if (!fs->o_end) - break; - continue; - } - fs->i_end = fs->i_ptr = 0; - - /* refill the input from the upstream */ - if (!fs->input_finished) { - fs->i_end = read_istream(fs->upstream, fs->ibuf, FILTER_BUFFER); - if (fs->i_end < 0) - return -1; - if (fs->i_end) - continue; - } - fs->input_finished = 1; - } - return filled; -} - -static struct git_istream *attach_stream_filter(struct git_istream *st, - struct stream_filter *filter) -{ - struct git_istream *ifs = xmalloc(sizeof(*ifs)); - struct filtered_istream *fs = &(ifs->u.filtered); - - ifs->close = close_istream_filtered; - ifs->read = read_istream_filtered; - fs->upstream = st; - fs->filter = filter; - fs->i_end = fs->i_ptr = 0; - fs->o_end = fs->o_ptr = 0; - fs->input_finished = 0; - ifs->size = -1; /* unknown */ - return ifs; -} - -/***************************************************************** - * - * Loose object stream - * - *****************************************************************/ - -static ssize_t read_istream_loose(struct git_istream *st, char *buf, size_t sz) -{ - size_t total_read = 0; - - switch (st->z_state) { - case z_done: - return 0; - case z_error: - return -1; - default: - break; - } - - if (st->u.loose.hdr_used < st->u.loose.hdr_avail) { - size_t to_copy = st->u.loose.hdr_avail - st->u.loose.hdr_used; - if (sz < to_copy) - to_copy = sz; - memcpy(buf, st->u.loose.hdr + st->u.loose.hdr_used, to_copy); - st->u.loose.hdr_used += to_copy; - total_read += to_copy; - } - - while (total_read < sz) { - int status; - - st->z.next_out = (unsigned char *)buf + total_read; - st->z.avail_out = sz - total_read; - status = git_inflate(&st->z, Z_FINISH); - - total_read = st->z.next_out - (unsigned char *)buf; - - if (status == Z_STREAM_END) { - git_inflate_end(&st->z); - st->z_state = z_done; - break; - } - if (status != Z_OK && (status != Z_BUF_ERROR || total_read < sz)) { - git_inflate_end(&st->z); - st->z_state = z_error; - return -1; - } - } - return total_read; -} - -static int close_istream_loose(struct git_istream *st) -{ - close_deflated_stream(st); - munmap(st->u.loose.mapped, st->u.loose.mapsize); - return 0; -} - -static int open_istream_loose(struct git_istream *st, struct repository *r, - const struct object_id *oid, - enum object_type *type) -{ - struct object_info oi = OBJECT_INFO_INIT; - oi.sizep = &st->size; - oi.typep = type; - - st->u.loose.mapped = map_loose_object(r, oid, &st->u.loose.mapsize); - if (!st->u.loose.mapped) - return -1; - switch (unpack_loose_header(&st->z, st->u.loose.mapped, - st->u.loose.mapsize, st->u.loose.hdr, - sizeof(st->u.loose.hdr))) { - case ULHR_OK: - break; - case ULHR_BAD: - case ULHR_TOO_LONG: - goto error; - } - if (parse_loose_header(st->u.loose.hdr, &oi) < 0 || *type < 0) - goto error; - - st->u.loose.hdr_used = strlen(st->u.loose.hdr) + 1; - st->u.loose.hdr_avail = st->z.total_out; - st->z_state = z_used; - st->close = close_istream_loose; - st->read = read_istream_loose; - - return 0; -error: - git_inflate_end(&st->z); - munmap(st->u.loose.mapped, st->u.loose.mapsize); - return -1; -} - - -/***************************************************************** - * - * Non-delta packed object stream - * - *****************************************************************/ - -static ssize_t read_istream_pack_non_delta(struct git_istream *st, char *buf, - size_t sz) -{ - size_t total_read = 0; - - switch (st->z_state) { - case z_unused: - memset(&st->z, 0, sizeof(st->z)); - git_inflate_init(&st->z); - st->z_state = z_used; - break; - case z_done: - return 0; - case z_error: - return -1; - case z_used: - break; - } - - while (total_read < sz) { - int status; - struct pack_window *window = NULL; - unsigned char *mapped; - - mapped = use_pack(st->u.in_pack.pack, &window, - st->u.in_pack.pos, &st->z.avail_in); - - st->z.next_out = (unsigned char *)buf + total_read; - st->z.avail_out = sz - total_read; - st->z.next_in = mapped; - status = git_inflate(&st->z, Z_FINISH); - - st->u.in_pack.pos += st->z.next_in - mapped; - total_read = st->z.next_out - (unsigned char *)buf; - unuse_pack(&window); - - if (status == Z_STREAM_END) { - git_inflate_end(&st->z); - st->z_state = z_done; - break; - } - - /* - * Unlike the loose object case, we do not have to worry here - * about running out of input bytes and spinning infinitely. If - * we get Z_BUF_ERROR due to too few input bytes, then we'll - * replenish them in the next use_pack() call when we loop. If - * we truly hit the end of the pack (i.e., because it's corrupt - * or truncated), then use_pack() catches that and will die(). - */ - if (status != Z_OK && status != Z_BUF_ERROR) { - git_inflate_end(&st->z); - st->z_state = z_error; - return -1; - } - } - return total_read; -} - -static int close_istream_pack_non_delta(struct git_istream *st) -{ - close_deflated_stream(st); - return 0; -} - -static int open_istream_pack_non_delta(struct git_istream *st, - struct repository *r UNUSED, - const struct object_id *oid UNUSED, - enum object_type *type UNUSED) -{ - struct pack_window *window; - enum object_type in_pack_type; - - window = NULL; - - in_pack_type = unpack_object_header(st->u.in_pack.pack, - &window, - &st->u.in_pack.pos, - &st->size); - unuse_pack(&window); - switch (in_pack_type) { - default: - return -1; /* we do not do deltas for now */ - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - break; - } - st->z_state = z_unused; - st->close = close_istream_pack_non_delta; - st->read = read_istream_pack_non_delta; - - return 0; -} - - -/***************************************************************** - * - * In-core stream - * - *****************************************************************/ - -static int close_istream_incore(struct git_istream *st) -{ - free(st->u.incore.buf); - return 0; -} - -static ssize_t read_istream_incore(struct git_istream *st, char *buf, size_t sz) -{ - size_t read_size = sz; - size_t remainder = st->size - st->u.incore.read_ptr; - - if (remainder <= read_size) - read_size = remainder; - if (read_size) { - memcpy(buf, st->u.incore.buf + st->u.incore.read_ptr, read_size); - st->u.incore.read_ptr += read_size; - } - return read_size; -} - -static int open_istream_incore(struct git_istream *st, struct repository *r, - const struct object_id *oid, enum object_type *type) -{ - struct object_info oi = OBJECT_INFO_INIT; - - st->u.incore.read_ptr = 0; - st->close = close_istream_incore; - st->read = read_istream_incore; - - oi.typep = type; - oi.sizep = &st->size; - oi.contentp = (void **)&st->u.incore.buf; - return odb_read_object_info_extended(r->objects, oid, &oi, - OBJECT_INFO_DIE_IF_CORRUPT); -} - -/***************************************************************************** - * static helpers variables and functions for users of streaming interface - *****************************************************************************/ - -static int istream_source(struct git_istream *st, - struct repository *r, - const struct object_id *oid, - enum object_type *type) -{ - unsigned long size; - int status; - struct object_info oi = OBJECT_INFO_INIT; - - oi.typep = type; - oi.sizep = &size; - status = odb_read_object_info_extended(r->objects, oid, &oi, 0); - if (status < 0) - return status; - - switch (oi.whence) { - case OI_LOOSE: - st->open = open_istream_loose; - return 0; - case OI_PACKED: - if (!oi.u.packed.is_delta && - repo_settings_get_big_file_threshold(the_repository) < size) { - st->u.in_pack.pack = oi.u.packed.pack; - st->u.in_pack.pos = oi.u.packed.offset; - st->open = open_istream_pack_non_delta; - return 0; - } - /* fallthru */ - default: - st->open = open_istream_incore; - return 0; - } -} - -/**************************************************************** - * Users of streaming interface - ****************************************************************/ - -int close_istream(struct git_istream *st) -{ - int r = st->close(st); - free(st); - return r; -} - -ssize_t read_istream(struct git_istream *st, void *buf, size_t sz) -{ - return st->read(st, buf, sz); -} - -struct git_istream *open_istream(struct repository *r, - const struct object_id *oid, - enum object_type *type, - unsigned long *size, - struct stream_filter *filter) -{ - struct git_istream *st = xmalloc(sizeof(*st)); - const struct object_id *real = lookup_replace_object(r, oid); - int ret = istream_source(st, r, real, type); - - if (ret) { - free(st); - return NULL; - } - - if (st->open(st, r, real, type)) { - if (open_istream_incore(st, r, real, type)) { - free(st); - return NULL; - } - } - if (filter) { - /* Add "&& !is_null_stream_filter(filter)" for performance */ - struct git_istream *nst = attach_stream_filter(st, filter); - if (!nst) { - close_istream(st); - return NULL; - } - st = nst; - } - - *size = st->size; - return st; -} - -int stream_blob_to_fd(int fd, const struct object_id *oid, struct stream_filter *filter, - int can_seek) -{ - struct git_istream *st; - enum object_type type; - unsigned long sz; - ssize_t kept = 0; - int result = -1; - - st = open_istream(the_repository, oid, &type, &sz, filter); - if (!st) { - if (filter) - free_stream_filter(filter); - return result; - } - if (type != OBJ_BLOB) - goto close_and_exit; - for (;;) { - char buf[1024 * 16]; - ssize_t wrote, holeto; - ssize_t readlen = read_istream(st, buf, sizeof(buf)); - - if (readlen < 0) - goto close_and_exit; - if (!readlen) - break; - if (can_seek && sizeof(buf) == readlen) { - for (holeto = 0; holeto < readlen; holeto++) - if (buf[holeto]) - break; - if (readlen == holeto) { - kept += holeto; - continue; - } - } - - if (kept && lseek(fd, kept, SEEK_CUR) == (off_t) -1) - goto close_and_exit; - else - kept = 0; - wrote = write_in_full(fd, buf, readlen); - - if (wrote < 0) - goto close_and_exit; - } - if (kept && (lseek(fd, kept - 1, SEEK_CUR) == (off_t) -1 || - xwrite(fd, "", 1) != 1)) - goto close_and_exit; - result = 0; - - close_and_exit: - close_istream(st); - return result; -} diff --git a/streaming.h b/streaming.h deleted file mode 100644 index bd27f59e57..0000000000 --- a/streaming.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Copyright (c) 2011, Google Inc. - */ -#ifndef STREAMING_H -#define STREAMING_H 1 - -#include "object.h" - -/* opaque */ -struct git_istream; -struct stream_filter; - -struct git_istream *open_istream(struct repository *, const struct object_id *, - enum object_type *, unsigned long *, - struct stream_filter *); -int close_istream(struct git_istream *); -ssize_t read_istream(struct git_istream *, void *, size_t); - -int stream_blob_to_fd(int fd, const struct object_id *, struct stream_filter *, int can_seek); - -#endif /* STREAMING_H */ diff --git a/submodule.c b/submodule.c index 35c55155f7..40a5c6fb9d 100644 --- a/submodule.c +++ b/submodule.c @@ -934,10 +934,7 @@ static void free_submodules_data(struct string_list *submodules) string_list_clear(submodules, 1); } -static int has_remote(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flags UNUSED, void *cb_data UNUSED) +static int has_remote(const struct reference *ref UNUSED, void *cb_data UNUSED) { return 1; } @@ -1255,13 +1252,10 @@ int push_unpushed_submodules(struct repository *r, return ret; } -static int append_oid_to_array(const char *ref UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flags UNUSED, void *data) +static int append_oid_to_array(const struct reference *ref, void *data) { struct oid_array *array = data; - oid_array_append(array, oid); + oid_array_append(array, ref->oid); return 0; } diff --git a/subprojects/.gitignore b/subprojects/.gitignore index 63ea916ef5..2bb68c8794 100644 --- a/subprojects/.gitignore +++ b/subprojects/.gitignore @@ -1 +1,2 @@ /*/ +.wraplock diff --git a/t/for-each-ref-tests.sh b/t/for-each-ref-tests.sh index e3ad19298a..4593be5fd5 100644 --- a/t/for-each-ref-tests.sh +++ b/t/for-each-ref-tests.sh @@ -1809,7 +1809,9 @@ test_expect_success "${git_for_each_ref} reports broken tags" ' bad=$(git hash-object -w -t tag bad) && git update-ref refs/tags/broken-tag-bad $bad && test_must_fail ${git_for_each_ref} --format="%(*objectname)" \ - refs/tags/broken-tag-* + refs/tags/broken-tag-* && + test_must_fail ${git_for_each_ref} --format="%(*objectname)" \ + refs/tags/broken-tag-bad ' test_expect_success 'set up tag with signature and no blank lines' ' diff --git a/t/helper/test-mktemp.c b/t/helper/test-mktemp.c index 2290688940..da195640a9 100644 --- a/t/helper/test-mktemp.c +++ b/t/helper/test-mktemp.c @@ -6,10 +6,16 @@ int cmd__mktemp(int argc, const char **argv) { + char *template; + int fd; + if (argc != 2) usage("Expected 1 parameter defining the temporary file template"); + template = xstrdup(argv[1]); - xmkstemp(xstrdup(argv[1])); + fd = xmkstemp(template); + close(fd); + free(template); return 0; } diff --git a/t/helper/test-reach.c b/t/helper/test-reach.c index 028ec00306..c58c93800f 100644 --- a/t/helper/test-reach.c +++ b/t/helper/test-reach.c @@ -63,7 +63,7 @@ int cmd__reach(int ac, const char **av) die("failed to resolve %s", buf.buf + 2); orig = parse_object(r, &oid); - peeled = deref_tag_noverify(the_repository, orig); + peeled = deref_tag(the_repository, orig, NULL, 0); if (!peeled) die("failed to load commit for input %s resulting in oid %s", diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c index 83b06d39a3..b1215947c5 100644 --- a/t/helper/test-ref-store.c +++ b/t/helper/test-ref-store.c @@ -154,10 +154,9 @@ static int cmd_rename_ref(struct ref_store *refs, const char **argv) return refs_rename_ref(refs, oldref, newref, logmsg); } -static int each_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flags, void *cb_data UNUSED) +static int each_ref(const struct reference *ref, void *cb_data UNUSED) { - printf("%s %s 0x%x\n", oid_to_hex(oid), refname, flags); + printf("%s %s 0x%x\n", oid_to_hex(ref->oid), ref->name, ref->flags); return 0; } diff --git a/t/helper/test-repository.c b/t/helper/test-repository.c index 63c37de33d..9ba94cdffa 100644 --- a/t/helper/test-repository.c +++ b/t/helper/test-repository.c @@ -17,10 +17,6 @@ static void test_parse_commit_in_graph(const char *gitdir, const char *worktree, struct commit *c; struct commit_list *parent; - setup_git_env(gitdir); - - repo_clear(the_repository); - if (repo_init(&r, gitdir, worktree)) die("Couldn't init repo"); @@ -47,10 +43,6 @@ static void test_get_commit_tree_in_graph(const char *gitdir, struct commit *c; struct tree *tree; - setup_git_env(gitdir); - - repo_clear(the_repository); - if (repo_init(&r, gitdir, worktree)) die("Couldn't init repo"); @@ -75,24 +67,20 @@ static void test_get_commit_tree_in_graph(const char *gitdir, int cmd__repository(int argc, const char **argv) { - int nongit_ok = 0; - - setup_git_directory_gently(&nongit_ok); - if (argc < 2) die("must have at least 2 arguments"); if (!strcmp(argv[1], "parse_commit_in_graph")) { struct object_id oid; if (argc < 5) die("not enough arguments"); - if (parse_oid_hex(argv[4], &oid, &argv[4])) + if (parse_oid_hex_any(argv[4], &oid, &argv[4]) == GIT_HASH_UNKNOWN) die("cannot parse oid '%s'", argv[4]); test_parse_commit_in_graph(argv[2], argv[3], &oid); } else if (!strcmp(argv[1], "get_commit_tree_in_graph")) { struct object_id oid; if (argc < 5) die("not enough arguments"); - if (parse_oid_hex(argv[4], &oid, &argv[4])) + if (parse_oid_hex_any(argv[4], &oid, &argv[4]) == GIT_HASH_UNKNOWN) die("cannot parse oid '%s'", argv[4]); test_get_commit_tree_in_graph(argv[2], argv[3], &oid); } else { diff --git a/t/meson.build b/t/meson.build index a5531df415..459c52a489 100644 --- a/t/meson.build +++ b/t/meson.build @@ -24,6 +24,7 @@ clar_test_suites = [ 'unit-tests/u-strvec.c', 'unit-tests/u-trailer.c', 'unit-tests/u-urlmatch-normalization.c', + 'unit-tests/u-utf8-width.c', ] clar_sources = [ @@ -184,6 +185,7 @@ integration_tests = [ 't1308-config-set.sh', 't1309-early-config.sh', 't1310-config-default.sh', + 't1311-config-optional.sh', 't1350-config-hooks-path.sh', 't1400-update-ref.sh', 't1401-symbolic-ref.sh', @@ -688,6 +690,7 @@ integration_tests = [ 't5562-http-backend-content-length.sh', 't5563-simple-http-auth.sh', 't5564-http-proxy.sh', + 't5565-push-multiple.sh', 't5570-git-daemon.sh', 't5571-pre-push-hook.sh', 't5572-pull-submodule.sh', @@ -956,6 +959,7 @@ integration_tests = [ 't8012-blame-colors.sh', 't8013-blame-ignore-revs.sh', 't8014-blame-ignore-fuzzy.sh', + 't8015-blame-diff-algorithm.sh', 't8020-last-modified.sh', 't9001-send-email.sh', 't9002-column.sh', diff --git a/t/pack-refs-tests.sh b/t/pack-refs-tests.sh index 3dbcc01718..81086c3690 100644 --- a/t/pack-refs-tests.sh +++ b/t/pack-refs-tests.sh @@ -428,4 +428,34 @@ do ' done -test_done +test_expect_success 'pack-refs does not store invalid peeled tag value' ' + test_when_finished rm -rf repo && + git init repo && + ( + cd repo && + git commit --allow-empty --message initial && + + echo garbage >blob-content && + blob_id=$(git hash-object -w -t blob blob-content) && + + # Write an invalid tag into the object database. The tag itself + # is well-formed, but the tagged object is a blob while we + # claim that it is a commit. + cat >tag-content <<-EOF && + object $blob_id + type commit + tag bad-tag + tagger C O Mitter <committer@example.com> 1112354055 +0200 + + annotated + EOF + tag_id=$(git hash-object -w -t tag tag-content) && + git update-ref refs/tags/bad-tag "$tag_id" && + + # The packed-refs file should not contain the peeled object ID. + # If it did this would cause commands that use the peeled value + # to not notice this corrupted tag. + git pack-refs --all && + test_grep ! "^\^" .git/packed-refs + ) +' diff --git a/t/t0003-attributes.sh b/t/t0003-attributes.sh index 3c98b622f2..582e207aa1 100755 --- a/t/t0003-attributes.sh +++ b/t/t0003-attributes.sh @@ -664,4 +664,24 @@ test_expect_success 'user defined builtin_objectmode values are ignored' ' test_cmp expect err ' +test_expect_success ULIMIT_STACK_SIZE 'deep macro recursion' ' + n=3000 && + { + i=0 && + while test $i -lt $n; do + echo "[attr]a$i a$((i+1))" && + i=$((i+1)) || + return 1 + done && + echo "[attr]a$n -text" && + echo "file a0" + } >.gitattributes && + { + echo "file: text: unset" && + test_seq -f "file: a%d: set" 0 $n + } >expect && + run_with_limited_stack git check-attr -a file >actual && + test_cmp expect actual +' + test_done diff --git a/t/t0601-reffiles-pack-refs.sh b/t/t0601-reffiles-pack-refs.sh index 12cf5d1dcb..3c706978ef 100755 --- a/t/t0601-reffiles-pack-refs.sh +++ b/t/t0601-reffiles-pack-refs.sh @@ -18,3 +18,5 @@ export GIT_TEST_DEFAULT_REF_FORMAT . ./test-lib.sh . "$TEST_DIRECTORY"/pack-refs-tests.sh + +test_done diff --git a/t/t0610-reftable-basics.sh b/t/t0610-reftable-basics.sh index 3ea5d51532..6575528f21 100755 --- a/t/t0610-reftable-basics.sh +++ b/t/t0610-reftable-basics.sh @@ -1135,4 +1135,32 @@ test_expect_success 'fetch: accessing FETCH_HEAD special ref works' ' test_cmp expect actual ' +test_expect_success 'writes do not persist peeled value for invalid tags' ' + test_when_finished rm -rf repo && + git init repo && + ( + cd repo && + git commit --allow-empty --message initial && + + # We cannot easily verify that the peeled value is not stored + # in the tables. Instead, we test this indirectly: we create + # two tags that both point to the same object, but they claim + # different object types. If we parse both tags we notice that + # the parsed tagged object has a mismatch between the two tags + # and bail out. + # + # If we instead use the persisted peeled value we would not + # even parse the tags. As such, we would not notice the + # discrepancy either and thus listing these tags would succeed. + git tag tag-1 -m "tag 1" && + git cat-file tag tag-1 >raw-tag && + sed "s/^type commit$/type blob/" <raw-tag >broken-tag && + broken_tag_id=$(git hash-object -w -t tag broken-tag) && + git update-ref refs/tags/tag-2 $broken_tag_id && + + test_must_fail git for-each-ref --format="%(*objectname)" refs/tags/ 2>err && + test_grep "bad tag pointer" err + ) +' + test_done diff --git a/t/t0614-reftable-fsck.sh b/t/t0614-reftable-fsck.sh index 85cc47d67e..677eb9143c 100755 --- a/t/t0614-reftable-fsck.sh +++ b/t/t0614-reftable-fsck.sh @@ -20,7 +20,7 @@ test_expect_success "no errors reported on a well formed repository" ' done && # The repository should end up with multiple tables. - test_line_count ">" 1 .git/reftable/tables.list && + test_line_count -gt 1 .git/reftable/tables.list && git refs verify 2>err && test_must_be_empty err diff --git a/t/t1311-config-optional.sh b/t/t1311-config-optional.sh new file mode 100755 index 0000000000..fbbacfc67b --- /dev/null +++ b/t/t1311-config-optional.sh @@ -0,0 +1,38 @@ +#!/bin/sh +# +# Copyright (c) 2025 Google LLC +# + +test_description=':(optional) paths' + +. ./test-lib.sh + +test_expect_success 'var=:(optional)path-exists' ' + test_config a.path ":(optional)path-exists" && + >path-exists && + echo path-exists >expect && + + git config get --path a.path >actual && + test_cmp expect actual +' + +test_expect_success 'missing optional value is ignored' ' + test_config a.path ":(optional)no-such-path" && + # Using --show-scope ensures we skip writing not only the value + # but also any meta-information about the ignored key. + test_must_fail git config get --show-scope --path a.path >actual && + test_line_count = 0 actual +' + +test_expect_success 'missing optional value is ignored in multi-value config' ' + test_when_finished "git config unset --all a.path" && + git config set --append a.path ":(optional)path-exists" && + git config set --append a.path ":(optional)no-such-path" && + >path-exists && + echo path-exists >expect && + + git config --get --path a.path >actual && + test_cmp expect actual +' + +test_done diff --git a/t/t1463-refs-optimize.sh b/t/t1463-refs-optimize.sh index c11c905d79..9afe3c1ed7 100755 --- a/t/t1463-refs-optimize.sh +++ b/t/t1463-refs-optimize.sh @@ -15,3 +15,5 @@ export GIT_TEST_DEFAULT_REF_FORMAT pack_refs='refs optimize' . "$TEST_DIRECTORY"/pack-refs-tests.sh + +test_done diff --git a/t/t1900-repo.sh b/t/t1900-repo.sh index 2beba67889..51d55f11a5 100755 --- a/t/t1900-repo.sh +++ b/t/t1900-repo.sh @@ -4,6 +4,15 @@ test_description='test git repo-info' . ./test-lib.sh +# git-repo-info keys. It must contain the same keys listed in the const +# repo_info_fields, in lexicographical order. +REPO_INFO_KEYS=' + layout.bare + layout.shallow + object.format + references.format +' + # Test whether a key-value pair is correctly returned # # Usage: test_repo_info <label> <init command> <repo_name> <key> <expected value> @@ -110,4 +119,16 @@ test_expect_success 'git repo info uses the last requested format' ' test_cmp expected actual ' +test_expect_success 'git repo info --all returns all key-value pairs' ' + git repo info $REPO_INFO_KEYS >expect && + git repo info --all >actual && + test_cmp expect actual +' + +test_expect_success 'git repo info --all <key> aborts' ' + echo "fatal: --all and <key> cannot be used together" >expect && + test_must_fail git repo info --all object.format 2>actual && + test_cmp expect actual +' + test_done diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh index 36a71a144e..df7d4ea524 100755 --- a/t/t1901-repo-structure.sh +++ b/t/t1901-repo-structure.sh @@ -102,6 +102,13 @@ test_expect_success 'keyvalue and nul format' ' git repo structure --format=nul >out 2>err && test_cmp expect_nul out && + test_line_count = 0 err && + + # "-z", as a synonym to "--format=nul", participates in the + # usual "last one wins" rule. + git repo structure --format=table -z >out 2>err && + + test_cmp expect_nul out && test_line_count = 0 err ) ' diff --git a/t/t2402-worktree-list.sh b/t/t2402-worktree-list.sh index 8ef1cad7f2..e0c6abd2f5 100755 --- a/t/t2402-worktree-list.sh +++ b/t/t2402-worktree-list.sh @@ -29,23 +29,34 @@ test_expect_success 'rev-parse --git-path objects linked worktree' ' test_cmp expect actual ' -test_expect_success '"list" all worktrees from main' ' - echo "$(git rev-parse --show-toplevel) $(git rev-parse --short HEAD) [$(git symbolic-ref --short HEAD)]" >expect && - test_when_finished "rm -rf here out actual expect && git worktree prune" && - git worktree add --detach here main && - echo "$(git -C here rev-parse --show-toplevel) $(git rev-parse --short HEAD) (detached HEAD)" >>expect && - git worktree list >out && - sed "s/ */ /g" <out >actual && +test_expect_success '"list" all worktrees from main core.quotepath=false' ' + test_config core.quotepath false && + echo "$(git rev-parse --show-toplevel) $(git rev-parse --short HEAD) [$(git symbolic-ref --short HEAD)]" >expect && + test_when_finished "rm -rf áááá out actual expect && git worktree prune" && + git worktree add --detach áááá main && + echo "$(git -C áááá rev-parse --show-toplevel) $(git rev-parse --short HEAD) (detached HEAD)" >>expect && + git worktree list >actual && + test_cmp expect actual +' + +test_expect_success '"list" all worktrees from main core.quotepath=true' ' + test_config core.quotepath true && + echo "$(git rev-parse --show-toplevel) $(git rev-parse --short HEAD) [$(git symbolic-ref --short HEAD)]" >expect && + test_when_finished "rm -rf á out actual expect && git worktree prune" && + git worktree add --detach á main && + echo "\"$(git -C á rev-parse --show-toplevel)\" $(git rev-parse --short HEAD) (detached HEAD)" | + sed s/á/\\\\303\\\\241/g >>expect && + git worktree list >actual && test_cmp expect actual ' test_expect_success '"list" all worktrees from linked' ' - echo "$(git rev-parse --show-toplevel) $(git rev-parse --short HEAD) [$(git symbolic-ref --short HEAD)]" >expect && - test_when_finished "rm -rf here out actual expect && git worktree prune" && - git worktree add --detach here main && - echo "$(git -C here rev-parse --show-toplevel) $(git rev-parse --short HEAD) (detached HEAD)" >>expect && - git -C here worktree list >out && - sed "s/ */ /g" <out >actual && + test_config core.quotepath false && + echo "$(git rev-parse --show-toplevel) $(git rev-parse --short HEAD) [$(git symbolic-ref --short HEAD)]" >expect && + test_when_finished "rm -rf áááá out actual expect && git worktree prune" && + git worktree add --detach áááá main && + echo "$(git -C áááá rev-parse --show-toplevel) $(git rev-parse --short HEAD) (detached HEAD)" >>expect && + git -C áááá worktree list >actual && test_cmp expect actual ' diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh index f3e720dc10..c58e505c43 100755 --- a/t/t3200-branch.sh +++ b/t/t3200-branch.sh @@ -1707,9 +1707,9 @@ test_expect_success '--track overrides branch.autoSetupMerge' ' ' test_expect_success 'errors if given a bad branch name' ' - cat <<-\EOF >expect && - fatal: '\''foo..bar'\'' is not a valid branch name - hint: See `man git check-ref-format` + cat <<-EOF >expect && + fatal: ${SQ}foo..bar${SQ} is not a valid branch name + hint: See ${SQ}git help check-ref-format${SQ} hint: Disable this message with "git config set advice.refSyntax false" EOF test_must_fail git branch foo..bar >actual 2>&1 && diff --git a/t/t3650-replay-basics.sh b/t/t3650-replay-basics.sh index 58b3759935..cf3aacf355 100755 --- a/t/t3650-replay-basics.sh +++ b/t/t3650-replay-basics.sh @@ -52,7 +52,7 @@ test_expect_success 'setup bare' ' ' test_expect_success 'using replay to rebase two branches, one on top of other' ' - git replay --onto main topic1..topic2 >result && + git replay --ref-action=print --onto main topic1..topic2 >result && test_line_count = 1 result && @@ -68,7 +68,7 @@ test_expect_success 'using replay to rebase two branches, one on top of other' ' ' test_expect_success 'using replay on bare repo to rebase two branches, one on top of other' ' - git -C bare replay --onto main topic1..topic2 >result-bare && + git -C bare replay --ref-action=print --onto main topic1..topic2 >result-bare && test_cmp expect result-bare ' @@ -86,7 +86,7 @@ test_expect_success 'using replay to perform basic cherry-pick' ' # 2nd field of result is refs/heads/main vs. refs/heads/topic2 # 4th field of result is hash for main instead of hash for topic2 - git replay --advance main topic1..topic2 >result && + git replay --ref-action=print --advance main topic1..topic2 >result && test_line_count = 1 result && @@ -102,7 +102,7 @@ test_expect_success 'using replay to perform basic cherry-pick' ' ' test_expect_success 'using replay on bare repo to perform basic cherry-pick' ' - git -C bare replay --advance main topic1..topic2 >result-bare && + git -C bare replay --ref-action=print --advance main topic1..topic2 >result-bare && test_cmp expect result-bare ' @@ -115,7 +115,7 @@ test_expect_success 'replay fails when both --advance and --onto are omitted' ' ' test_expect_success 'using replay to also rebase a contained branch' ' - git replay --contained --onto main main..topic3 >result && + git replay --ref-action=print --contained --onto main main..topic3 >result && test_line_count = 2 result && cut -f 3 -d " " result >new-branch-tips && @@ -139,12 +139,12 @@ test_expect_success 'using replay to also rebase a contained branch' ' ' test_expect_success 'using replay on bare repo to also rebase a contained branch' ' - git -C bare replay --contained --onto main main..topic3 >result-bare && + git -C bare replay --ref-action=print --contained --onto main main..topic3 >result-bare && test_cmp expect result-bare ' test_expect_success 'using replay to rebase multiple divergent branches' ' - git replay --onto main ^topic1 topic2 topic4 >result && + git replay --ref-action=print --onto main ^topic1 topic2 topic4 >result && test_line_count = 2 result && cut -f 3 -d " " result >new-branch-tips && @@ -168,7 +168,7 @@ test_expect_success 'using replay to rebase multiple divergent branches' ' ' test_expect_success 'using replay on bare repo to rebase multiple divergent branches, including contained ones' ' - git -C bare replay --contained --onto main ^main topic2 topic3 topic4 >result && + git -C bare replay --ref-action=print --contained --onto main ^main topic2 topic3 topic4 >result && test_line_count = 4 result && cut -f 3 -d " " result >new-branch-tips && @@ -217,4 +217,101 @@ test_expect_success 'merge.directoryRenames=false' ' --onto rename-onto rename-onto..rename-from ' +test_expect_success 'default atomic behavior updates refs directly' ' + # Use a separate branch to avoid contaminating topic2 for later tests + git branch test-atomic topic2 && + test_when_finished "git branch -D test-atomic" && + + # Test default atomic behavior (no output, refs updated) + git replay --onto main topic1..test-atomic >output && + test_must_be_empty output && + + # Verify ref was updated + git log --format=%s test-atomic >actual && + test_write_lines E D M L B A >expect && + test_cmp expect actual && + + # Verify reflog message includes SHA of onto commit + git reflog test-atomic -1 --format=%gs >reflog-msg && + ONTO_SHA=$(git rev-parse main) && + echo "replay --onto $ONTO_SHA" >expect-reflog && + test_cmp expect-reflog reflog-msg +' + +test_expect_success 'atomic behavior in bare repository' ' + # Store original state for cleanup + START=$(git -C bare rev-parse topic2) && + test_when_finished "git -C bare update-ref refs/heads/topic2 $START" && + + # Test atomic updates work in bare repo + git -C bare replay --onto main topic1..topic2 >output && + test_must_be_empty output && + + # Verify ref was updated in bare repo + git -C bare log --format=%s topic2 >actual && + test_write_lines E D M L B A >expect && + test_cmp expect actual +' + +test_expect_success 'reflog message for --advance mode' ' + # Store original state + START=$(git rev-parse main) && + test_when_finished "git update-ref refs/heads/main $START" && + + # Test --advance mode reflog message + git replay --advance main topic1..topic2 >output && + test_must_be_empty output && + + # Verify reflog message includes --advance and branch name + git reflog main -1 --format=%gs >reflog-msg && + echo "replay --advance main" >expect-reflog && + test_cmp expect-reflog reflog-msg +' + +test_expect_success 'replay.refAction=print config option' ' + # Store original state + START=$(git rev-parse topic2) && + test_when_finished "git branch -f topic2 $START" && + + # Test with config set to print + test_config replay.refAction print && + git replay --onto main topic1..topic2 >output && + test_line_count = 1 output && + test_grep "^update refs/heads/topic2 " output +' + +test_expect_success 'replay.refAction=update config option' ' + # Store original state + START=$(git rev-parse topic2) && + test_when_finished "git branch -f topic2 $START" && + + # Test with config set to update + test_config replay.refAction update && + git replay --onto main topic1..topic2 >output && + test_must_be_empty output && + + # Verify ref was updated + git log --format=%s topic2 >actual && + test_write_lines E D M L B A >expect && + test_cmp expect actual +' + +test_expect_success 'command-line --ref-action overrides config' ' + # Store original state + START=$(git rev-parse topic2) && + test_when_finished "git branch -f topic2 $START" && + + # Set config to update but use --ref-action=print + test_config replay.refAction update && + git replay --ref-action=print --onto main topic1..topic2 >output && + test_line_count = 1 output && + test_grep "^update refs/heads/topic2 " output +' + +test_expect_success 'invalid replay.refAction value' ' + test_config replay.refAction invalid && + test_must_fail git replay --onto main topic1..topic2 2>error && + test_grep "invalid.*replay.refAction.*value" error +' + test_done diff --git a/t/t3700-add.sh b/t/t3700-add.sh index df580a5806..af93e53c12 100755 --- a/t/t3700-add.sh +++ b/t/t3700-add.sh @@ -388,6 +388,7 @@ test_expect_success 'error on a repository with no commits' ' test_must_fail git add empty >actual 2>&1 && cat >expect <<-EOF && error: '"'empty/'"' does not have a commit checked out + error: unable to index file '"'empty/'"' fatal: adding files failed EOF test_cmp expect actual @@ -541,6 +542,31 @@ test_expect_success 'all statuses changed in folder if . is given' ' ) ' +test_expect_success 'cannot add a submodule of a different algorithm' ' + git init --object-format=sha256 sha256 && + ( + cd sha256 && + test_commit abc && + git init --object-format=sha1 submodule && + test_commit -C submodule def && + test_must_fail git add submodule 2>err && + test_grep "cannot add a submodule of a different hash algorithm" err && + git ls-files --stage >entries && + test_grep ! ^160000 entries + ) && + git init --object-format=sha1 sha1 && + ( + cd sha1 && + test_commit abc && + git init --object-format=sha256 submodule && + test_commit -C submodule def && + test_must_fail git add submodule 2>err && + test_grep "cannot add a submodule of a different hash algorithm" err && + git ls-files --stage >entries && + test_grep ! ^160000 entries + ) +' + test_expect_success CASE_INSENSITIVE_FS 'path is case-insensitive' ' path="$(pwd)/BLUB" && touch "$path" && diff --git a/t/t4007-rename-3.sh b/t/t4007-rename-3.sh index e8faf0dd2e..3fc81bcd76 100755 --- a/t/t4007-rename-3.sh +++ b/t/t4007-rename-3.sh @@ -41,6 +41,16 @@ test_expect_success 'copy detection, cached' ' compare_diff_raw current expected ' +test_expect_success 'exit code of quiet copy detection' ' + test_expect_code 1 \ + git diff --quiet --cached --find-copies-harder $tree +' + +test_expect_success 'exit code of quiet copy detection with --no-ext-diff' ' + test_expect_code 1 \ + git diff --quiet --cached --find-copies-harder --no-ext-diff $tree +' + # In the tree, there is only path0/COPYING. In the cache, path0 and # path1 both have COPYING and the latter is a copy of path0/COPYING. # However when we say we care only about path1, we should just see diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh index 9de7f73f42..3c8eb02e4f 100755 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@ -43,6 +43,53 @@ do ' done +test_expect_success "incomplete line in both pre- and post-image context" ' + (echo foo && echo baz | tr -d "\012") >x && + git add x && + (echo bar && echo baz | tr -d "\012") >x && + git diff x && + git -c core.whitespace=incomplete diff --check x && + git diff -R x && + git -c core.whitespace=incomplete diff -R --check x +' + +test_expect_success "incomplete lines on both pre- and post-image" ' + # The interpretation taken here is "since you are touching + # the line anyway, you would better fix the incomplete line + # while you are at it." but this is debatable. + echo foo | tr -d "\012" >x && + git add x && + echo bar | tr -d "\012" >x && + git diff x && + test_must_fail git -c core.whitespace=incomplete diff --check x >error && + test_grep "no newline at the end of file" error && + git diff -R x && + test_must_fail git -c core.whitespace=incomplete diff -R --check x >error && + test_grep "no newline at the end of file" error +' + +test_expect_success "fix incomplete line in pre-image" ' + echo foo | tr -d "\012" >x && + git add x && + echo bar >x && + git diff x && + git -c core.whitespace=incomplete diff --check x && + git diff -R x && + test_must_fail git -c core.whitespace=incomplete diff -R --check x >error && + test_grep "no newline at the end of file" error +' + +test_expect_success "new incomplete line in post-image" ' + echo foo >x && + git add x && + echo bar | tr -d "\012" >x && + git diff x && + test_must_fail git -c core.whitespace=incomplete diff --check x >error && + test_grep "no newline at the end of file" error && + git diff -R x && + git -c core.whitespace=incomplete diff -R --check x +' + test_expect_success "Ray Lehtiniemi's example" ' cat <<-\EOF >x && do { @@ -1040,7 +1087,8 @@ test_expect_success 'ws-error-highlight test setup' ' { echo "0. blank-at-eol " && echo "1. still-blank-at-eol " && - echo "2. and a new line " + echo "2. and a new line " && + printf "3. and more" } >x && new_hash_x=$(git hash-object x) && after=$(git rev-parse --short "$new_hash_x") && @@ -1050,11 +1098,13 @@ test_expect_success 'ws-error-highlight test setup' ' <BOLD>index $before..$after 100644<RESET> <BOLD>--- a/x<RESET> <BOLD>+++ b/x<RESET> - <CYAN>@@ -1,2 +1,3 @@<RESET> + <CYAN>@@ -1,2 +1,4 @@<RESET> 0. blank-at-eol <RESET> <RED>-<RESET><RED>1. blank-at-eol<RESET><BLUE> <RESET> <GREEN>+<RESET><GREEN>1. still-blank-at-eol<RESET><BLUE> <RESET> <GREEN>+<RESET><GREEN>2. and a new line<RESET><BLUE> <RESET> + <GREEN>+<RESET><GREEN>3. and more<RESET> + <BLUE>\ No newline at end of file<RESET> EOF cat >expect.all <<-EOF && @@ -1062,11 +1112,13 @@ test_expect_success 'ws-error-highlight test setup' ' <BOLD>index $before..$after 100644<RESET> <BOLD>--- a/x<RESET> <BOLD>+++ b/x<RESET> - <CYAN>@@ -1,2 +1,3 @@<RESET> + <CYAN>@@ -1,2 +1,4 @@<RESET> <RESET>0. blank-at-eol<RESET><BLUE> <RESET> <RED>-<RESET><RED>1. blank-at-eol<RESET><BLUE> <RESET> <GREEN>+<RESET><GREEN>1. still-blank-at-eol<RESET><BLUE> <RESET> <GREEN>+<RESET><GREEN>2. and a new line<RESET><BLUE> <RESET> + <GREEN>+<RESET><GREEN>3. and more<RESET> + <BLUE>\ No newline at end of file<RESET> EOF cat >expect.none <<-EOF @@ -1074,16 +1126,19 @@ test_expect_success 'ws-error-highlight test setup' ' <BOLD>index $before..$after 100644<RESET> <BOLD>--- a/x<RESET> <BOLD>+++ b/x<RESET> - <CYAN>@@ -1,2 +1,3 @@<RESET> + <CYAN>@@ -1,2 +1,4 @@<RESET> 0. blank-at-eol <RESET> <RED>-1. blank-at-eol <RESET> <GREEN>+1. still-blank-at-eol <RESET> <GREEN>+2. and a new line <RESET> + <GREEN>+3. and more<RESET> + \ No newline at end of file<RESET> EOF ' test_expect_success 'test --ws-error-highlight option' ' + git config core.whitespace blank-at-eol,incomplete-line && git diff --color --ws-error-highlight=default,old >current.raw && test_decode_color <current.raw >current && @@ -1100,6 +1155,7 @@ test_expect_success 'test --ws-error-highlight option' ' ' test_expect_success 'test diff.wsErrorHighlight config' ' + git config core.whitespace blank-at-eol,incomplete-line && git -c diff.wsErrorHighlight=default,old diff --color >current.raw && test_decode_color <current.raw >current && @@ -1116,6 +1172,7 @@ test_expect_success 'test diff.wsErrorHighlight config' ' ' test_expect_success 'option overrides diff.wsErrorHighlight' ' + git config core.whitespace blank-at-eol,incomplete-line && git -c diff.wsErrorHighlight=none \ diff --color --ws-error-highlight=default,old >current.raw && @@ -1135,6 +1192,8 @@ test_expect_success 'option overrides diff.wsErrorHighlight' ' ' test_expect_success 'detect moved code, complete file' ' + git config core.whitespace blank-at-eol && + git reset --hard && cat <<-\EOF >test.c && #include<stdio.h> diff --git a/t/t4124-apply-ws-rule.sh b/t/t4124-apply-ws-rule.sh index 485c7d2d12..115a0f8579 100755 --- a/t/t4124-apply-ws-rule.sh +++ b/t/t4124-apply-ws-rule.sh @@ -556,4 +556,191 @@ test_expect_success 'whitespace check skipped for excluded paths' ' git apply --include=used --stat --whitespace=error <patch ' +test_expect_success 'check incomplete lines (setup)' ' + rm -f .gitattributes && + git config core.whitespace incomplete-line +' + +test_expect_success 'incomplete context line (not an error)' ' + (test_write_lines 1 2 3 4 5 && printf 6) >sample-i && + (test_write_lines 1 2 3 0 5 && printf 6) >sample2-i && + cat sample-i >target && + git add target && + cat sample2-i >target && + git diff-files -p target >patch && + + cat sample-i >target && + git apply --whitespace=error <patch && + test_cmp sample2-i target && + + cat sample-i >target && + git apply --whitespace=error --check <patch 2>error && + test_cmp sample-i target && + test_must_be_empty error && + + cat sample2-i >target && + git apply --whitespace=error -R <patch && + test_cmp sample-i target && + + cat sample2-i >target && + git apply -R --whitespace=error --check <patch 2>error && + test_cmp sample2-i target && + test_must_be_empty error +' + +test_expect_success 'last line made incomplete (error)' ' + test_write_lines 1 2 3 4 5 6 >sample && + (test_write_lines 1 2 3 4 5 && printf 6) >sample-i && + cat sample >target && + git add target && + cat sample-i >target && + git diff-files -p target >patch && + + cat sample >target && + test_must_fail git apply --whitespace=error <patch 2>error && + test_grep "no newline" error && + + cat sample >target && + test_must_fail git apply --whitespace=error --check <patch 2>actual && + test_cmp sample target && + cat >expect <<-\EOF && + <stdin>:10: no newline at the end of file. + 6 + error: 1 line adds whitespace errors. + EOF + test_cmp expect actual && + + cat sample-i >target && + git apply --whitespace=error -R <patch && + test_cmp sample target && + + cat sample-i >target && + git apply --whitespace=error --check -R <patch 2>error && + test_cmp sample-i target && + test_must_be_empty error && + + cat sample >target && + git apply --whitespace=fix <patch && + test_cmp sample target +' + +test_expect_success 'incomplete line removed at the end (not an error)' ' + (test_write_lines 1 2 3 4 5 && printf 6) >sample-i && + test_write_lines 1 2 3 4 5 6 >sample && + cat sample-i >target && + git add target && + cat sample >target && + git diff-files -p target >patch && + + cat sample-i >target && + git apply --whitespace=error <patch && + test_cmp sample target && + + cat sample-i >target && + git apply --whitespace=error --check <patch 2>error && + test_cmp sample-i target && + test_must_be_empty error && + + cat sample >target && + test_must_fail git apply --whitespace=error -R <patch 2>error && + test_grep "no newline" error && + + cat sample >target && + test_must_fail git apply --whitespace=error --check -R <patch 2>actual && + test_cmp sample target && + cat >expect <<-\EOF && + <stdin>:9: no newline at the end of file. + 6 + error: 1 line adds whitespace errors. + EOF + test_cmp expect actual && + + cat sample >target && + git apply --whitespace=fix -R <patch && + test_cmp sample target +' + +test_expect_success 'incomplete line corrected at the end (not an error)' ' + (test_write_lines 1 2 3 4 5 && printf 6) >sample-i && + test_write_lines 1 2 3 4 5 7 >sample3 && + cat sample-i >target && + git add target && + cat sample3 >target && + git diff-files -p target >patch && + + cat sample-i >target && + git apply --whitespace=error <patch && + test_cmp sample3 target && + + cat sample-i >target && + git apply --whitespace=error --check <patch 2>error && + test_cmp sample-i target && + test_must_be_empty error && + + cat sample3 >target && + test_must_fail git apply --whitespace=error -R <patch 2>error && + test_grep "no newline" error && + + cat sample3 >target && + test_must_fail git apply --whitespace=error -R --check <patch 2>actual && + test_cmp sample3 target && + cat >expect <<-\EOF && + <stdin>:9: no newline at the end of file. + 6 + error: 1 line adds whitespace errors. + EOF + test_cmp expect actual && + + cat sample3 >target && + git apply --whitespace=fix -R <patch && + test_cmp sample target +' + +test_expect_success 'incomplete line modified at the end (error)' ' + (test_write_lines 1 2 3 4 5 && printf 6) >sample-i && + (test_write_lines 1 2 3 4 5 && printf 7) >sample3-i && + test_write_lines 1 2 3 4 5 6 >sample && + test_write_lines 1 2 3 4 5 7 >sample3 && + cat sample-i >target && + git add target && + cat sample3-i >target && + git diff-files -p target >patch && + + cat sample-i >target && + test_must_fail git apply --whitespace=error <patch 2>error && + test_grep "no newline" error && + + cat sample-i >target && + test_must_fail git apply --whitespace=error --check <patch 2>actual && + test_cmp sample-i target && + cat >expect <<-\EOF && + <stdin>:11: no newline at the end of file. + 7 + error: 1 line adds whitespace errors. + EOF + test_cmp expect actual && + + cat sample3-i >target && + test_must_fail git apply --whitespace=error -R <patch 2>error && + test_grep "no newline" error && + + cat sample3-i >target && + test_must_fail git apply --whitespace=error --check -R <patch 2>actual && + test_cmp sample3-i target && + cat >expect <<-\EOF && + <stdin>:9: no newline at the end of file. + 6 + error: 1 line adds whitespace errors. + EOF + test_cmp expect actual && + + cat sample-i >target && + git apply --whitespace=fix <patch && + test_cmp sample3 target && + + cat sample3-i >target && + git apply --whitespace=fix -R <patch && + test_cmp sample target +' + test_done diff --git a/t/t5302-pack-index.sh b/t/t5302-pack-index.sh index 413c99274c..9697448cb2 100755 --- a/t/t5302-pack-index.sh +++ b/t/t5302-pack-index.sh @@ -293,4 +293,20 @@ test_expect_success 'too-large packs report the breach' ' grep "maximum allowed size (20 bytes)" err ' +# git-index-pack(1) uses the default hash algorithm outside of the repository, +# and it has no way to tell it otherwise. So we can only run this test with the +# default hash algorithm, as it would otherwise fail to parse the tree. +test_expect_success DEFAULT_HASH_ALGORITHM 'index-pack --fsck-objects outside of a repo' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + printf "100644 blob $(test_oid 001)\t.gitattributes\n" >tree && + git mktree --missing <tree >tree-oid && + git pack-objects <tree-oid pack && + test_must_fail nongit git index-pack --fsck-objects "$(pwd)"/pack-*.pack 2>err && + test_grep "cannot perform queued object checks outside of a repository" err + ) +' + test_done diff --git a/t/t5564-http-proxy.sh b/t/t5564-http-proxy.sh index c3903faf2d..3bcbdef409 100755 --- a/t/t5564-http-proxy.sh +++ b/t/t5564-http-proxy.sh @@ -40,10 +40,10 @@ test_expect_success 'clone can prompt for proxy password' ' start_socks() { mkfifo socks_output && - { + ( "$PERL_PATH" "$TEST_DIRECTORY/socks4-proxy.pl" "$1" >socks_output & echo $! > "$TRASH_DIRECTORY/socks.pid" - } && + ) && read line <socks_output && test "$line" = ready } diff --git a/t/t5565-push-multiple.sh b/t/t5565-push-multiple.sh new file mode 100755 index 0000000000..7e93668566 --- /dev/null +++ b/t/t5565-push-multiple.sh @@ -0,0 +1,39 @@ +#!/bin/sh + +test_description='push to group' + +. ./test-lib.sh + +test_expect_success setup ' + for i in 1 2 3 + do + git init dest-$i && + git -C dest-$i symbolic-ref HEAD refs/heads/not-a-branch || + return 1 + done && + test_tick && + git commit --allow-empty -m "initial" && + git config set --append remote.them.pushurl "file://$(pwd)/dest-1" && + git config set --append remote.them.pushurl "file://$(pwd)/dest-2" && + git config set --append remote.them.pushurl "file://$(pwd)/dest-3" && + git config set --append remote.them.push "+refs/heads/*:refs/heads/*" +' + +test_expect_success 'push to group' ' + git push them && + j= && + for i in 1 2 3 + do + git -C dest-$i for-each-ref >actual-$i && + if test -n "$j" + then + test_cmp actual-$j actual-$i + else + cat actual-$i + fi && + j=$i || + return 1 + done +' + +test_done diff --git a/t/t6429-merge-sequence-rename-caching.sh b/t/t6429-merge-sequence-rename-caching.sh index 0f39ed0d08..15dd2d94b7 100755 --- a/t/t6429-merge-sequence-rename-caching.sh +++ b/t/t6429-merge-sequence-rename-caching.sh @@ -11,14 +11,13 @@ test_description="remember regular & dir renames in sequence of merges" # sure that we are triggering rename caching rather than rename # bypassing. # -# NOTE 2: this testfile uses 'test-tool fast-rebase' instead of either -# cherry-pick or rebase. sequencer.c is only superficially -# integrated with merge-ort; it calls merge_switch_to_result() -# after EACH merge, which updates the index and working copy AND -# throws away the cached results (because merge_switch_to_result() -# is only supposed to be called at the end of the sequence). -# Integrating them more deeply is a big task, so for now the tests -# use 'test-tool fast-rebase'. +# NOTE 2: this testfile uses replay instead of either cherry-pick or rebase. +# sequencer.c is only superficially integrated with merge-ort; it +# calls merge_switch_to_result() after EACH merge, which updates the +# index and working copy AND throws away the cached results (because +# merge_switch_to_result() is only supposed to be called at the end +# of the sequence). Integrating them more deeply is a big task, so +# for now the tests use 'git replay'. # @@ -769,4 +768,82 @@ test_expect_success 'avoid assuming we detected renames' ' ) ' +# +# In the following testcase: +# Base: olddir/{valuesX_1, valuesY_1, valuesZ_1} +# other/content +# Upstream: rename olddir/valuesX_1 -> newdir/valuesX_2 +# Topic_1: modify olddir/valuesX_1 -> olddir/valuesX_3 +# Topic_2: modify olddir/valuesY, +# modify other/content +# Expected Pick1: olddir/{valuesY, valuesZ}, newdir/valuesX, other/content +# Expected Pick2: olddir/{valuesY, valuesZ}, newdir/valuesX, other/content +# +# This testcase presents no problems for git traditionally, but the fact that +# olddir/valuesX -> newdir/valuesX +# gets cached after the first pick presents a problem for the second commit to +# be replayed, because it appears to be an irrelevant rename, so the trivial +# directory resolution will resolve newdir/ without recursing into it, giving +# us no way to apply the cached rename to anything. +# +test_expect_success 'rename a file, use it on first pick, but irrelevant on second' ' + git init rename_a_file_use_it_once_irrelevant_on_second && + ( + cd rename_a_file_use_it_once_irrelevant_on_second && + + mkdir olddir/ other/ && + test_seq 3 8 >olddir/valuesX && + test_seq 3 8 >olddir/valuesY && + test_seq 3 8 >olddir/valuesZ && + printf "%s\n" A B C D E F G >other/content && + git add olddir other && + git commit -m orig && + + git branch upstream && + git branch topic && + + git switch upstream && + test_seq 1 8 >olddir/valuesX && + git add olddir && + mkdir newdir && + git mv olddir/valuesX newdir && + git commit -m "Renamed (and modified) olddir/valuesX into newdir/" && + + git switch topic && + + test_seq 3 10 >olddir/valuesX && + git add olddir && + git commit -m A && + + test_seq 1 8 >olddir/valuesY && + printf "%s\n" A B C D E F G H I >other/content && + git add olddir/valuesY other && + git commit -m B && + + # + # Actual testing; mostly we want to verify that we do not hit + # git: merge-ort.c:3032: process_renames: Assertion `newinfo && !newinfo->merged.clean` failed. + # + + git switch upstream && + git config merge.directoryRenames true && + + git replay --onto HEAD upstream~1..topic >out && + + # + # ...but we may as well check that the replay gave us a reasonable result + # + + git update-ref --stdin <out && + git checkout topic && + + git ls-files >tracked && + test_line_count = 4 tracked && + test_path_is_file newdir/valuesX && + test_path_is_file olddir/valuesY && + test_path_is_file olddir/valuesZ && + test_path_is_file other/content + ) +' + test_done diff --git a/t/t7004-tag.sh b/t/t7004-tag.sh index 10835631ca..ce2ff2a28a 100755 --- a/t/t7004-tag.sh +++ b/t/t7004-tag.sh @@ -2293,24 +2293,26 @@ test_expect_success '--contains combined with --no-contains' ' # don't recurse down to tags for trees or blobs pointed to by *those* # commits. test_expect_success 'Does --[no-]contains stop at commits? Yes!' ' - cd no-contains && - blob=$(git rev-parse v0.3:v0.3.t) && - tree=$(git rev-parse v0.3^{tree}) && - git tag tag-blob $blob && - git tag tag-tree $tree && - git tag --contains v0.3 >actual && - cat >expected <<-\EOF && - v0.3 - v0.4 - v0.5 - EOF - test_cmp expected actual && - git tag --no-contains v0.3 >actual && - cat >expected <<-\EOF && - v0.1 - v0.2 - EOF - test_cmp expected actual + ( + cd no-contains && + blob=$(git rev-parse v0.3:v0.3.t) && + tree=$(git rev-parse v0.3^{tree}) && + git tag tag-blob $blob && + git tag tag-tree $tree && + git tag --contains v0.3 >actual && + cat >expected <<-\EOF && + v0.3 + v0.4 + v0.5 + EOF + test_cmp expected actual && + git tag --no-contains v0.3 >actual && + cat >expected <<-\EOF && + v0.1 + v0.2 + EOF + test_cmp expected actual + ) ' test_expect_success 'If tag is created then tag message file is unlinked' ' @@ -2332,4 +2334,24 @@ test_expect_success 'If tag cannot be created then tag message file is not unlin test_path_exists .git/TAG_EDITMSG ' +test_expect_success 'annotated tag version sort' ' + git tag -a -m "sample 1.0" vsample-1.0 && + git tag -a -m "sample 2.0" vsample-2.0 && + git tag -a -m "sample 10.0" vsample-10.0 && + cat >expect <<-EOF && + vsample-1.0 + vsample-2.0 + vsample-10.0 + EOF + + git tag --list --sort=version:tag vsample-\* >actual && + test_cmp expect actual && + + # Ensure that we also handle this case alright in the case we have the + # peeled values cached e.g. via the packed-refs file. + git pack-refs --all && + git tag --list --sort=version:tag vsample-\* && + test_cmp expect actual +' + test_done diff --git a/t/t7400-submodule-basic.sh b/t/t7400-submodule-basic.sh index fd3e7e355e..e6b551daad 100755 --- a/t/t7400-submodule-basic.sh +++ b/t/t7400-submodule-basic.sh @@ -407,6 +407,31 @@ test_expect_success 'submodule add in subdirectory with relative path should fai test_grep toplevel output.err ' +test_expect_success 'submodule add of a different algorithm fails' ' + git init --object-format=sha256 sha256 && + ( + cd sha256 && + test_commit abc && + git init --object-format=sha1 submodule && + test_commit -C submodule def && + test_must_fail git submodule add "$submodurl" submodule 2>err && + test_grep "cannot add a submodule of a different hash algorithm" err && + git ls-files --stage >entries && + test_grep ! ^160000 entries + ) && + git init --object-format=sha1 sha1 && + ( + cd sha1 && + test_commit abc && + git init --object-format=sha256 submodule && + test_commit -C submodule def && + test_must_fail git submodule add "$submodurl" submodule 2>err && + test_grep "cannot add a submodule of a different hash algorithm" err && + git ls-files --stage >entries && + test_grep ! ^160000 entries + ) +' + test_expect_success 'setup - add an example entry to .gitmodules' ' git config --file=.gitmodules submodule.example.url git://example.com/init.git ' diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh index 614184a097..6b36f52df7 100755 --- a/t/t7900-maintenance.sh +++ b/t/t7900-maintenance.sh @@ -49,7 +49,9 @@ test_expect_success 'run [--auto|--quiet]' ' git maintenance run --auto 2>/dev/null && GIT_TRACE2_EVENT="$(pwd)/run-no-quiet.txt" \ git maintenance run --no-quiet 2>/dev/null && + git maintenance is-needed && test_subcommand git gc --quiet --no-detach --skip-foreground-tasks <run-no-auto.txt && + ! git maintenance is-needed --auto && test_subcommand ! git gc --auto --quiet --no-detach --skip-foreground-tasks <run-auto.txt && test_subcommand git gc --no-quiet --no-detach --skip-foreground-tasks <run-no-quiet.txt ' @@ -180,6 +182,11 @@ test_expect_success 'commit-graph auto condition' ' test_commit first && + ! git -c maintenance.commit-graph.auto=0 \ + maintenance is-needed --auto --task=commit-graph && + git -c maintenance.commit-graph.auto=1 \ + maintenance is-needed --auto --task=commit-graph && + GIT_TRACE2_EVENT="$(pwd)/cg-zero-means-no.txt" \ git -c maintenance.commit-graph.auto=0 $COMMAND && GIT_TRACE2_EVENT="$(pwd)/cg-one-satisfied.txt" \ @@ -290,16 +297,23 @@ test_expect_success 'maintenance.loose-objects.auto' ' git -c maintenance.loose-objects.auto=1 maintenance \ run --auto --task=loose-objects 2>/dev/null && test_subcommand ! git prune-packed --quiet <trace-lo1.txt && + printf data-A | git hash-object -t blob --stdin -w && + ! git -c maintenance.loose-objects.auto=2 \ + maintenance is-needed --auto --task=loose-objects && GIT_TRACE2_EVENT="$(pwd)/trace-loA" \ git -c maintenance.loose-objects.auto=2 \ maintenance run --auto --task=loose-objects 2>/dev/null && test_subcommand ! git prune-packed --quiet <trace-loA && + printf data-B | git hash-object -t blob --stdin -w && + git -c maintenance.loose-objects.auto=2 \ + maintenance is-needed --auto --task=loose-objects && GIT_TRACE2_EVENT="$(pwd)/trace-loB" \ git -c maintenance.loose-objects.auto=2 \ maintenance run --auto --task=loose-objects 2>/dev/null && test_subcommand git prune-packed --quiet <trace-loB && + GIT_TRACE2_EVENT="$(pwd)/trace-loC" \ git -c maintenance.loose-objects.auto=2 \ maintenance run --auto --task=loose-objects 2>/dev/null && @@ -421,10 +435,13 @@ run_incremental_repack_and_verify () { test_commit A && git repack -adk && git multi-pack-index write && + ! git -c maintenance.incremental-repack.auto=1 \ + maintenance is-needed --auto --task=incremental-repack && GIT_TRACE2_EVENT="$(pwd)/midx-init.txt" git \ -c maintenance.incremental-repack.auto=1 \ maintenance run --auto --task=incremental-repack 2>/dev/null && test_subcommand ! git multi-pack-index write --no-progress <midx-init.txt && + test_commit B && git pack-objects --revs .git/objects/pack/pack <<-\EOF && HEAD @@ -434,11 +451,14 @@ run_incremental_repack_and_verify () { -c maintenance.incremental-repack.auto=2 \ maintenance run --auto --task=incremental-repack 2>/dev/null && test_subcommand ! git multi-pack-index write --no-progress <trace-A && + test_commit C && git pack-objects --revs .git/objects/pack/pack <<-\EOF && HEAD ^HEAD~1 EOF + git -c maintenance.incremental-repack.auto=2 \ + maintenance is-needed --auto --task=incremental-repack && GIT_TRACE2_EVENT=$(pwd)/trace-B git \ -c maintenance.incremental-repack.auto=2 \ maintenance run --auto --task=incremental-repack 2>/dev/null && @@ -655,9 +675,15 @@ test_expect_success 'reflog-expire task --auto only packs when exceeding limits' git reflog expire --all --expire=now && test_commit reflog-one && test_commit reflog-two && + + ! git -c maintenance.reflog-expire.auto=3 \ + maintenance is-needed --auto --task=reflog-expire && GIT_TRACE2_EVENT="$(pwd)/reflog-expire-auto.txt" \ git -c maintenance.reflog-expire.auto=3 maintenance run --auto --task=reflog-expire && test_subcommand ! git reflog expire --all <reflog-expire-auto.txt && + + git -c maintenance.reflog-expire.auto=2 \ + maintenance is-needed --auto --task=reflog-expire && GIT_TRACE2_EVENT="$(pwd)/reflog-expire-auto.txt" \ git -c maintenance.reflog-expire.auto=2 maintenance run --auto --task=reflog-expire && test_subcommand git reflog expire --all <reflog-expire-auto.txt @@ -684,6 +710,7 @@ test_expect_success 'worktree-prune task --auto only prunes with prunable worktr test_expect_worktree_prune ! git maintenance run --auto --task=worktree-prune && mkdir .git/worktrees && : >.git/worktrees/abc && + git maintenance is-needed --auto --task=worktree-prune && test_expect_worktree_prune git maintenance run --auto --task=worktree-prune ' @@ -700,22 +727,7 @@ test_expect_success 'worktree-prune task with --auto honors maintenance.worktree test_expect_worktree_prune ! git -c maintenance.worktree-prune.auto=0 maintenance run --auto --task=worktree-prune && # A positive value should require at least this many prunable worktrees. test_expect_worktree_prune ! git -c maintenance.worktree-prune.auto=4 maintenance run --auto --task=worktree-prune && - test_expect_worktree_prune git -c maintenance.worktree-prune.auto=3 maintenance run --auto --task=worktree-prune -' - -test_expect_success 'worktree-prune task with --auto honors maintenance.worktree-prune.auto' ' - # A negative value should always prune. - test_expect_worktree_prune git -c maintenance.worktree-prune.auto=-1 maintenance run --auto --task=worktree-prune && - - mkdir .git/worktrees && - : >.git/worktrees/first && - : >.git/worktrees/second && - : >.git/worktrees/third && - - # Zero should never prune. - test_expect_worktree_prune ! git -c maintenance.worktree-prune.auto=0 maintenance run --auto --task=worktree-prune && - # A positive value should require at least this many prunable worktrees. - test_expect_worktree_prune ! git -c maintenance.worktree-prune.auto=4 maintenance run --auto --task=worktree-prune && + git -c maintenance.worktree-prune.auto=3 maintenance is-needed --auto --task=worktree-prune && test_expect_worktree_prune git -c maintenance.worktree-prune.auto=3 maintenance run --auto --task=worktree-prune ' @@ -724,11 +736,13 @@ test_expect_success 'worktree-prune task honors gc.worktreePruneExpire' ' rm -rf worktree && rm -f worktree-prune.txt && + ! git -c gc.worktreePruneExpire=1.week.ago maintenance is-needed --auto --task=worktree-prune && GIT_TRACE2_EVENT="$(pwd)/worktree-prune.txt" git -c gc.worktreePruneExpire=1.week.ago maintenance run --auto --task=worktree-prune && test_subcommand ! git worktree prune --expire 1.week.ago <worktree-prune.txt && test_path_is_dir .git/worktrees/worktree && rm -f worktree-prune.txt && + git -c gc.worktreePruneExpire=now maintenance is-needed --auto --task=worktree-prune && GIT_TRACE2_EVENT="$(pwd)/worktree-prune.txt" git -c gc.worktreePruneExpire=now maintenance run --auto --task=worktree-prune && test_subcommand git worktree prune --expire now <worktree-prune.txt && test_path_is_missing .git/worktrees/worktree @@ -753,10 +767,13 @@ test_expect_success 'rerere-gc task without --auto always collects garbage' ' test_expect_success 'rerere-gc task with --auto only prunes with prunable entries' ' test_when_finished "rm -rf .git/rr-cache" && + ! git maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc ! git maintenance run --auto --task=rerere-gc && mkdir .git/rr-cache && + ! git maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc ! git maintenance run --auto --task=rerere-gc && : >.git/rr-cache/entry && + git maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc git maintenance run --auto --task=rerere-gc ' @@ -764,17 +781,22 @@ test_expect_success 'rerere-gc task with --auto honors maintenance.rerere-gc.aut test_when_finished "rm -rf .git/rr-cache" && # A negative value should always prune. + git -c maintenance.rerere-gc.auto=-1 maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc git -c maintenance.rerere-gc.auto=-1 maintenance run --auto --task=rerere-gc && # A positive value prunes when there is at least one entry. + ! git -c maintenance.rerere-gc.auto=9000 maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc && mkdir .git/rr-cache && + ! git -c maintenance.rerere-gc.auto=9000 maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc && : >.git/rr-cache/entry-1 && + git -c maintenance.rerere-gc.auto=9000 maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc && # Zero should never prune. : >.git/rr-cache/entry-1 && + ! git -c maintenance.rerere-gc.auto=0 maintenance is-needed --auto --task=rerere-gc && test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=0 maintenance run --auto --task=rerere-gc ' diff --git a/t/t8015-blame-diff-algorithm.sh b/t/t8015-blame-diff-algorithm.sh new file mode 100755 index 0000000000..cd709536c6 --- /dev/null +++ b/t/t8015-blame-diff-algorithm.sh @@ -0,0 +1,203 @@ +#!/bin/sh + +test_description='git blame with specific diff algorithm' + +. ./test-lib.sh + +test_expect_success setup ' + cat >file.c <<-\EOF && + int f(int x, int y) + { + if (x == 0) + { + return y; + } + return x; + } + + int g(size_t u) + { + while (u < 30) + { + u++; + } + return u; + } + EOF + test_write_lines x x x x >file.txt && + git add file.c file.txt && + GIT_AUTHOR_NAME=Commit_1 git commit -m Commit_1 && + + cat >file.c <<-\EOF && + int g(size_t u) + { + while (u < 30) + { + u++; + } + return u; + } + + int h(int x, int y, int z) + { + if (z == 0) + { + return x; + } + return y; + } + EOF + test_write_lines x x x A B C D x E F G >file.txt && + git add file.c file.txt && + GIT_AUTHOR_NAME=Commit_2 git commit -m Commit_2 +' + +test_expect_success 'blame uses Myers diff algorithm by default' ' + cat >expected <<-\EOF && + Commit_2 int g(size_t u) + Commit_1 { + Commit_2 while (u < 30) + Commit_1 { + Commit_2 u++; + Commit_1 } + Commit_2 return u; + Commit_1 } + Commit_1 + Commit_2 int h(int x, int y, int z) + Commit_1 { + Commit_2 if (z == 0) + Commit_1 { + Commit_2 return x; + Commit_1 } + Commit_2 return y; + Commit_1 } + EOF + + git blame file.c >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" output >without_varying_parts && + sed -e "s/ *$//g" without_varying_parts >actual && + test_cmp expected actual +' + +test_expect_success 'blame honors --diff-algorithm option' ' + cat >expected <<-\EOF && + Commit_1 int g(size_t u) + Commit_1 { + Commit_1 while (u < 30) + Commit_1 { + Commit_1 u++; + Commit_1 } + Commit_1 return u; + Commit_1 } + Commit_2 + Commit_2 int h(int x, int y, int z) + Commit_2 { + Commit_2 if (z == 0) + Commit_2 { + Commit_2 return x; + Commit_2 } + Commit_2 return y; + Commit_2 } + EOF + + git blame file.c --diff-algorithm histogram >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" output >without_varying_parts && + sed -e "s/ *$//g" without_varying_parts >actual && + test_cmp expected actual +' + +test_expect_success 'blame honors diff.algorithm config variable' ' + cat >expected <<-\EOF && + Commit_1 int g(size_t u) + Commit_1 { + Commit_1 while (u < 30) + Commit_1 { + Commit_1 u++; + Commit_1 } + Commit_1 return u; + Commit_1 } + Commit_2 + Commit_2 int h(int x, int y, int z) + Commit_2 { + Commit_2 if (z == 0) + Commit_2 { + Commit_2 return x; + Commit_2 } + Commit_2 return y; + Commit_2 } + EOF + + git -c diff.algorithm=histogram blame file.c >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" \ + -e "s/ *$//g" output >actual && + test_cmp expected actual +' + +test_expect_success 'blame gives priority to --diff-algorithm over diff.algorithm' ' + cat >expected <<-\EOF && + Commit_1 int g(size_t u) + Commit_1 { + Commit_1 while (u < 30) + Commit_1 { + Commit_1 u++; + Commit_1 } + Commit_1 return u; + Commit_1 } + Commit_2 + Commit_2 int h(int x, int y, int z) + Commit_2 { + Commit_2 if (z == 0) + Commit_2 { + Commit_2 return x; + Commit_2 } + Commit_2 return y; + Commit_2 } + EOF + + git -c diff.algorithm=myers blame file.c --diff-algorithm histogram >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" \ + -e "s/ *$//g" output >actual && + test_cmp expected actual +' + +test_expect_success 'blame honors --minimal option' ' + cat >expected <<-\EOF && + Commit_1 x + Commit_1 x + Commit_1 x + Commit_2 A + Commit_2 B + Commit_2 C + Commit_2 D + Commit_1 x + Commit_2 E + Commit_2 F + Commit_2 G + EOF + + git blame file.txt --minimal >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" output >actual && + test_cmp expected actual +' + +test_expect_success 'blame respects the order of diff options' ' + cat >expected <<-\EOF && + Commit_1 x + Commit_1 x + Commit_1 x + Commit_2 A + Commit_2 B + Commit_2 C + Commit_2 D + Commit_2 x + Commit_2 E + Commit_2 F + Commit_2 G + EOF + + git blame file.txt --minimal --diff-algorithm myers >output && + sed -e "s/^[^ ]* (\([^ ]*\) [^)]*)/\1/g" output >actual && + test_cmp expected actual +' + +test_done diff --git a/t/t8020-last-modified.sh b/t/t8020-last-modified.sh index a4c1114ee2..50f4312f71 100755 --- a/t/t8020-last-modified.sh +++ b/t/t8020-last-modified.sh @@ -78,6 +78,14 @@ test_expect_success 'last-modified subdir' ' EOF ' +test_expect_success 'last-modified in sparse checkout' ' + test_when_finished "git sparse-checkout disable" && + git sparse-checkout set b && + check_last_modified -- a <<-\EOF + 3 a + EOF +' + test_expect_success 'last-modified subdir recursive' ' check_last_modified -r a <<-\EOF 3 a/b/file diff --git a/t/t9305-fast-import-signatures.sh b/t/t9305-fast-import-signatures.sh index c2b4271658..022dae02e4 100755 --- a/t/t9305-fast-import-signatures.sh +++ b/t/t9305-fast-import-signatures.sh @@ -79,7 +79,7 @@ test_expect_success GPG 'setup a commit with dual OpenPGP signatures on its SHA- echo B >explicit-sha256/B && git -C explicit-sha256 add B && test_tick && - git -C explicit-sha256 commit -S -m "signed" B && + git -C explicit-sha256 commit -S -m "signed commit" B && SHA256_B=$(git -C explicit-sha256 rev-parse dual-signed) && # Create the corresponding SHA-1 commit @@ -103,4 +103,71 @@ test_expect_success GPG 'strip both OpenPGP signatures with --signed-commits=war test_line_count = 2 out ' +test_expect_success GPG 'import commit with no signature with --signed-commits=strip-if-invalid' ' + git fast-export main >output && + git -C new fast-import --quiet --signed-commits=strip-if-invalid <output >log 2>&1 && + test_must_be_empty log +' + +test_expect_success GPG 'keep valid OpenPGP signature with --signed-commits=strip-if-invalid' ' + rm -rf new && + git init new && + + git fast-export --signed-commits=verbatim openpgp-signing >output && + git -C new fast-import --quiet --signed-commits=strip-if-invalid <output >log 2>&1 && + IMPORTED=$(git -C new rev-parse --verify refs/heads/openpgp-signing) && + test $OPENPGP_SIGNING = $IMPORTED && + git -C new cat-file commit "$IMPORTED" >actual && + test_grep -E "^gpgsig(-sha256)? " actual && + test_must_be_empty log +' + +test_expect_success GPG 'strip signature invalidated by message change with --signed-commits=strip-if-invalid' ' + rm -rf new && + git init new && + + git fast-export --signed-commits=verbatim openpgp-signing >output && + + # Change the commit message, which invalidates the signature. + # The commit message length should not change though, otherwise the + # corresponding `data <length>` command would have to be changed too. + sed "s/OpenPGP signed commit/OpenPGP forged commit/" output >modified && + + git -C new fast-import --quiet --signed-commits=strip-if-invalid <modified >log 2>&1 && + + IMPORTED=$(git -C new rev-parse --verify refs/heads/openpgp-signing) && + test $OPENPGP_SIGNING != $IMPORTED && + git -C new cat-file commit "$IMPORTED" >actual && + test_grep ! -E "^gpgsig" actual && + test_grep "stripping invalid signature" log +' + +test_expect_success GPGSM 'keep valid X.509 signature with --signed-commits=strip-if-invalid' ' + rm -rf new && + git init new && + + git fast-export --signed-commits=verbatim x509-signing >output && + git -C new fast-import --quiet --signed-commits=strip-if-invalid <output >log 2>&1 && + IMPORTED=$(git -C new rev-parse --verify refs/heads/x509-signing) && + test $X509_SIGNING = $IMPORTED && + git -C new cat-file commit "$IMPORTED" >actual && + test_grep -E "^gpgsig(-sha256)? " actual && + test_must_be_empty log +' + +test_expect_success GPGSSH 'keep valid SSH signature with --signed-commits=strip-if-invalid' ' + rm -rf new && + git init new && + + test_config -C new gpg.ssh.allowedSignersFile "${GPGSSH_ALLOWED_SIGNERS}" && + + git fast-export --signed-commits=verbatim ssh-signing >output && + git -C new fast-import --quiet --signed-commits=strip-if-invalid <output >log 2>&1 && + IMPORTED=$(git -C new rev-parse --verify refs/heads/ssh-signing) && + test $SSH_SIGNING = $IMPORTED && + git -C new cat-file commit "$IMPORTED" >actual && + test_grep -E "^gpgsig(-sha256)? " actual && + test_must_be_empty log +' + test_done diff --git a/t/test-lib.sh b/t/test-lib.sh index ef0ab7ec2d..0fb76f7d11 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -77,6 +77,7 @@ prepend_var GIT_SAN_OPTIONS : strip_path_prefix="$GIT_BUILD_DIR/" # want that one to complain to stderr). prepend_var ASAN_OPTIONS : $GIT_SAN_OPTIONS prepend_var ASAN_OPTIONS : detect_leaks=0 +prepend_var ASAN_OPTIONS : strict_string_checks=1 export ASAN_OPTIONS prepend_var LSAN_OPTIONS : $GIT_SAN_OPTIONS diff --git a/t/unit-tests/u-reftable-stack.c b/t/unit-tests/u-reftable-stack.c index a8b91812e8..b8110cdeee 100644 --- a/t/unit-tests/u-reftable-stack.c +++ b/t/unit-tests/u-reftable-stack.c @@ -1067,6 +1067,7 @@ void test_reftable_stack__add_performs_auto_compaction(void) .value_type = REFTABLE_REF_SYMREF, .value.symref = (char *) "master", }; + bool required = false; char buf[128]; /* @@ -1087,10 +1088,17 @@ void test_reftable_stack__add_performs_auto_compaction(void) * auto compaction is disabled. When enabled, we should merge * all tables in the stack. */ - if (i != n) + cl_assert_equal_i(reftable_stack_compaction_required(st, true, &required), 0); + if (i != n) { cl_assert_equal_i(st->merged->tables_len, i + 1); - else + if (i < 1) + cl_assert_equal_b(required, false); + else + cl_assert_equal_b(required, true); + } else { cl_assert_equal_i(st->merged->tables_len, 1); + cl_assert_equal_b(required, false); + } } reftable_stack_destroy(st); diff --git a/t/unit-tests/u-utf8-width.c b/t/unit-tests/u-utf8-width.c new file mode 100644 index 0000000000..86e09c3574 --- /dev/null +++ b/t/unit-tests/u-utf8-width.c @@ -0,0 +1,134 @@ +#include "unit-test.h" +#include "utf8.h" +#include "strbuf.h" + +/* + * Test utf8_strnwidth with various Chinese strings + * Chinese characters typically have a width of 2 columns when displayed + */ +void test_utf8_width__strnwidth_chinese(void) +{ + const char *str; + + /* Test basic ASCII - each character should have width 1 */ + cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 0)); + /* skip_ansi = 1 */ + cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 1)); + + /* Test simple Chinese characters - each should have width 2 */ + /* "你好" is 6 bytes (3 bytes per char in UTF-8), 4 display columns */ + cl_assert_equal_i(4, utf8_strnwidth("你好", 6, 0)); + + /* Test mixed ASCII and Chinese - ASCII = 1 column, Chinese = 2 columns */ + /* "h"(1) + "i"(1) + "你"(2) + "好"(2) = 6 */ + cl_assert_equal_i(6, utf8_strnwidth("Hi你好", 8, 0)); + + /* Test longer Chinese string */ + /* 5 Chinese chars = 10 display columns */ + cl_assert_equal_i(10, utf8_strnwidth("你好世界！", 15, 0)); + + /* Test individual Chinese character width */ + cl_assert_equal_i(2, utf8_strnwidth("中", 3, 0)); + + /* Test empty string */ + cl_assert_equal_i(0, utf8_strnwidth("", 0, 0)); + + /* Test length limiting */ + str = "你好世界"; + /* Only first char "你"(2 columns) within 3 bytes */ + cl_assert_equal_i(2, utf8_strnwidth(str, 3, 0)); + /* First two chars "你好"(4 columns) in 6 bytes */ + cl_assert_equal_i(4, utf8_strnwidth(str, 6, 0)); +} + +/* + * Tests for utf8_strwidth (simpler version without length limit) + */ +void test_utf8_width__strwidth_chinese(void) +{ + /* Test basic ASCII */ + cl_assert_equal_i(5, utf8_strwidth("Hello")); + + /* Test Chinese characters */ + /* 2 Chinese chars = 4 display columns */ + cl_assert_equal_i(4, utf8_strwidth("你好")); + + /* Test longer Chinese string */ + /* 5 Chinese chars = 10 display columns */ + cl_assert_equal_i(10, utf8_strwidth("你好世界！")); + + /* Test mixed ASCII and Chinese */ + /* 5 ASCII (5 cols) + 2 Chinese (4 cols) = 9 */ + cl_assert_equal_i(9, utf8_strwidth("Hello世界")); + /* 2 ASCII (2 cols) + 2 Chinese (4 cols) + 1 ASCII (1 col) = 7 */ + cl_assert_equal_i(7, utf8_strwidth("Hi世界!")); +} + +/* + * Additional tests with other East Asian characters + */ +void test_utf8_width__strnwidth_japanese_korean(void) +{ + /* Japanese characters (should also be 2 columns each) */ + /* 5 Japanese chars x 2 cols each = 10 display columns */ + cl_assert_equal_i(10, utf8_strnwidth("こんにちは", 15, 0)); + + /* Korean characters (should also be 2 columns each) */ + /* 5 Korean chars x 2 cols each = 10 display columns */ + cl_assert_equal_i(10, utf8_strnwidth("안녕하세요", 15, 0)); +} + +/* + * Test utf8_strnwidth with CJK strings and ANSI sequences + */ +void test_utf8_width__strnwidth_cjk_with_ansi(void) +{ + /* Test CJK with ANSI sequences */ + const char *ansi_test = "\033[1m你好\033[0m"; + int width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1); + /* Should skip ANSI sequences and count "你好" as 4 columns */ + cl_assert_equal_i(4, width); + + /* Test mixed ASCII, CJK, and ANSI */ + ansi_test = "Hello\033[32m世界\033[0m!"; + width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1); + /* "Hello"(5) + "世界"(4) + "!"(1) = 10 */ + cl_assert_equal_i(10, width); +} + +/* + * Test the strbuf_utf8_align function with CJK characters + */ +void test_utf8_width__strbuf_utf8_align(void) +{ + struct strbuf buf = STRBUF_INIT; + + /* Test left alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_LEFT, 10, "你好"); + /* Since "你好" is 4 display columns, we need 6 more spaces to reach 10 */ + cl_assert_equal_s("你好 ", buf.buf); + strbuf_reset(&buf); + + /* Test right alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_RIGHT, 8, "世界"); + /* "世界" is 4 display columns, so we need 4 leading spaces */ + cl_assert_equal_s(" 世界", buf.buf); + strbuf_reset(&buf); + + /* Test center alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_MIDDLE, 10, "中"); + /* "中" is 2 display columns, so (10-2)/2 = 4 spaces on left, 4 on right */ + cl_assert_equal_s(" 中 ", buf.buf); + strbuf_reset(&buf); + + strbuf_utf8_align(&buf, ALIGN_MIDDLE, 5, "中"); + /* "中" is 2 display columns, so (5-2)/2 = 1 spaces on left, 2 on right */ + cl_assert_equal_s(" 中 ", buf.buf); + strbuf_reset(&buf); + + /* Test alignment that is smaller than string width */ + strbuf_utf8_align(&buf, ALIGN_LEFT, 2, "你好"); + /* Since "你好" is 4 display columns, it should not be truncated */ + cl_assert_equal_s("你好", buf.buf); + strbuf_release(&buf); +} diff --git a/t/unit-tests/unit-test.c b/t/unit-tests/unit-test.c index 5af645048a..752fb38fb3 100644 --- a/t/unit-tests/unit-test.c +++ b/t/unit-tests/unit-test.c @@ -29,6 +29,7 @@ int cmd_main(int argc, const char **argv) OPT_NOOP_NOARG('d', "debug"), OPT_NOOP_NOARG(0, "github-workflow-markup"), OPT_NOOP_NOARG(0, "no-bin-wrappers"), + OPT_NOOP_ARG(0, "no-chain-lint"), OPT_NOOP_ARG(0, "root"), OPT_NOOP_ARG(0, "stress"), OPT_NOOP_NOARG(0, "tee"), @@ -94,18 +94,6 @@ struct object *deref_tag(struct repository *r, struct object *o, const char *war return o; } -struct object *deref_tag_noverify(struct repository *r, struct object *o) -{ - while (o && o->type == OBJ_TAG) { - o = parse_object(r, &o->oid); - if (o && o->type == OBJ_TAG && ((struct tag *)o)->tagged) - o = ((struct tag *)o)->tagged; - else - o = NULL; - } - return o; -} - struct tag *lookup_tag(struct repository *r, const struct object_id *oid) { struct object *obj = lookup_object(r, oid); @@ -16,7 +16,6 @@ int parse_tag_buffer(struct repository *r, struct tag *item, const void *data, u int parse_tag(struct tag *item); void release_tag_memory(struct tag *t); struct object *deref_tag(struct repository *r, struct object *, const char *, int); -struct object *deref_tag_noverify(struct repository *r, struct object *); int gpg_verify_tag(const struct object_id *oid, const char *name_to_report, unsigned flags); struct object_id *get_tagged_oid(struct tag *tag); diff --git a/upload-pack.c b/upload-pack.c index 1e87ae9559..2d2b70cbf2 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -870,8 +870,8 @@ static void send_unshallow(struct upload_pack_data *data) } } -static int check_ref(const char *refname_full, const char *referent UNUSED, const struct object_id *oid, - int flag, void *cb_data); +static int check_ref(const struct reference *ref, void *cb_data); + static void deepen(struct upload_pack_data *data, int depth) { if (depth == INFINITE_DEPTH && !is_repository_shallow(the_repository)) { @@ -1224,13 +1224,12 @@ static int mark_our_ref(const char *refname, const char *refname_full, return 0; } -static int check_ref(const char *refname_full, const char *referent UNUSED,const struct object_id *oid, - int flag UNUSED, void *cb_data) +static int check_ref(const struct reference *ref, void *cb_data) { - const char *refname = strip_namespace(refname_full); + const char *refname = strip_namespace(ref->name); struct upload_pack_data *data = cb_data; - mark_our_ref(refname, refname_full, oid, &data->hidden_refs); + mark_our_ref(refname, ref->name, ref->oid, &data->hidden_refs); return 0; } @@ -1250,15 +1249,15 @@ static void format_session_id(struct strbuf *buf, struct upload_pack_data *d) { } static void write_v0_ref(struct upload_pack_data *data, - const char *refname, const char *refname_nons, - const struct object_id *oid) + const struct reference *ref, + const char *refname_nons) { static const char *capabilities = "multi_ack thin-pack side-band" " side-band-64k ofs-delta shallow deepen-since deepen-not" " deepen-relative no-progress include-tag multi_ack_detailed"; struct object_id peeled; - if (mark_our_ref(refname_nons, refname, oid, &data->hidden_refs)) + if (mark_our_ref(refname_nons, ref->name, ref->oid, &data->hidden_refs)) return; if (capabilities) { @@ -1268,7 +1267,7 @@ static void write_v0_ref(struct upload_pack_data *data, format_symref_info(&symref_info, &data->symref); format_session_id(&session_id, data); packet_fwrite_fmt(stdout, "%s %s%c%s%s%s%s%s%s%s object-format=%s agent=%s\n", - oid_to_hex(oid), refname_nons, + oid_to_hex(ref->oid), refname_nons, 0, capabilities, (data->allow_uor & ALLOW_TIP_SHA1) ? " allow-tip-sha1-in-want" : "", @@ -1284,35 +1283,33 @@ static void write_v0_ref(struct upload_pack_data *data, strbuf_release(&session_id); data->sent_capabilities = 1; } else { - packet_fwrite_fmt(stdout, "%s %s\n", oid_to_hex(oid), refname_nons); + packet_fwrite_fmt(stdout, "%s %s\n", oid_to_hex(ref->oid), refname_nons); } capabilities = NULL; - if (!peel_iterated_oid(the_repository, oid, &peeled)) + if (!reference_get_peeled_oid(the_repository, ref, &peeled)) packet_fwrite_fmt(stdout, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons); return; } -static int send_ref(const char *refname, const char *referent UNUSED, const struct object_id *oid, - int flag UNUSED, void *cb_data) +static int send_ref(const struct reference *ref, void *cb_data) { - write_v0_ref(cb_data, refname, strip_namespace(refname), oid); + write_v0_ref(cb_data, ref, strip_namespace(ref->name)); return 0; } -static int find_symref(const char *refname, const char *referent UNUSED, - const struct object_id *oid UNUSED, - int flag, void *cb_data) +static int find_symref(const struct reference *ref, void *cb_data) { const char *symref_target; struct string_list_item *item; + int flag; - if ((flag & REF_ISSYMREF) == 0) + if ((ref->flags & REF_ISSYMREF) == 0) return 0; symref_target = refs_resolve_ref_unsafe(get_main_ref_store(the_repository), - refname, 0, NULL, &flag); + ref->name, 0, NULL, &flag); if (!symref_target || (flag & REF_ISSYMREF) == 0) - die("'%s' is a symref but it is not?", refname); - item = string_list_append(cb_data, strip_namespace(refname)); + die("'%s' is a symref but it is not?", ref->name); + item = string_list_append(cb_data, strip_namespace(ref->name)); item->util = xstrdup(strip_namespace(symref_target)); return 0; } @@ -1445,8 +1442,12 @@ void upload_pack(const int advertise_refs, const int stateless_rpc, send_ref, &data); for_each_namespaced_ref_1(send_ref, &data); if (!data.sent_capabilities) { - const char *refname = "capabilities^{}"; - write_v0_ref(&data, refname, refname, null_oid(the_hash_algo)); + struct reference ref = { + .name = "capabilities^{}", + .oid = null_oid(the_hash_algo), + }; + + write_v0_ref(&data, &ref, ref.name); } /* * fflush stdout before calling advertise_shallow_grafts because send_ref @@ -226,14 +226,10 @@ static int interpret_target(struct walker *walker, char *target, struct object_i return -1; } -static int mark_complete(const char *path UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, - void *cb_data UNUSED) +static int mark_complete(const struct reference *ref, void *cb_data UNUSED) { struct commit *commit = lookup_commit_reference_gently(the_repository, - oid, 1); + ref->oid, 1); if (commit) { commit->object.flags |= COMPLETE; diff --git a/worktree.c b/worktree.c index a2a5f51f29..9308389cb6 100644 --- a/worktree.c +++ b/worktree.c @@ -595,8 +595,15 @@ int other_head_refs(each_ref_fn fn, void *cb_data) if (refs_resolve_ref_unsafe(get_main_ref_store(the_repository), refname.buf, RESOLVE_REF_READING, - &oid, &flag)) - ret = fn(refname.buf, NULL, &oid, flag, cb_data); + &oid, &flag)) { + struct reference ref = { + .name = refname.buf, + .oid = &oid, + .flags = flag, + }; + + ret = fn(&ref, cb_data); + } if (ret) break; } @@ -421,24 +421,7 @@ FILE *fopen_or_warn(const char *path, const char *mode) int xmkstemp(char *filename_template) { - int fd; - char origtemplate[PATH_MAX]; - strlcpy(origtemplate, filename_template, sizeof(origtemplate)); - - fd = mkstemp(filename_template); - if (fd < 0) { - int saved_errno = errno; - const char *nonrelative_template; - - if (strlen(filename_template) != strlen(origtemplate)) - filename_template = origtemplate; - - nonrelative_template = absolute_path(filename_template); - errno = saved_errno; - die_errno("Unable to create temporary file '%s'", - nonrelative_template); - } - return fd; + return xmkstemp_mode(filename_template, 0600); } /* Adapted from libiberty's mkstemp.c. */ @@ -446,7 +429,11 @@ int xmkstemp(char *filename_template) #undef TMP_MAX #define TMP_MAX 16384 -int git_mkstemps_mode(char *pattern, int suffix_len, int mode) +/* + * Returns -1 on error, 0 if it created a directory, or an open file + * descriptor to the created regular file. + */ +static int git_mkdstemps_mode(char *pattern, int suffix_len, int mode, bool dir) { static const char letters[] = "abcdefghijklmnopqrstuvwxyz" @@ -488,7 +475,10 @@ int git_mkstemps_mode(char *pattern, int suffix_len, int mode) v /= num_letters; } - fd = open(pattern, O_CREAT | O_EXCL | O_RDWR, mode); + if (dir) + fd = mkdir(pattern, mode); + else + fd = open(pattern, O_CREAT | O_EXCL | O_RDWR, mode); if (fd >= 0) return fd; /* @@ -503,6 +493,16 @@ int git_mkstemps_mode(char *pattern, int suffix_len, int mode) return -1; } +char *git_mkdtemp(char *pattern) +{ + return git_mkdstemps_mode(pattern, 0, 0700, true) ? NULL : pattern; +} + +int git_mkstemps_mode(char *pattern, int suffix_len, int mode) +{ + return git_mkdstemps_mode(pattern, suffix_len, mode, false); +} + int git_mkstemp_mode(char *pattern, int mode) { /* mkstemp is just mkstemps with no suffix */ @@ -37,6 +37,8 @@ int xsnprintf(char *dst, size_t max, const char *fmt, ...); int xgethostname(char *buf, size_t len); +char *git_mkdtemp(char *pattern); + /* set default permissions by passing mode arguments to open(2) */ int git_mkstemps_mode(char *pattern, int suffix_len, int mode); int git_mkstemp_mode(char *pattern, int mode); @@ -26,6 +26,7 @@ static struct whitespace_rule { { "blank-at-eol", WS_BLANK_AT_EOL, 0 }, { "blank-at-eof", WS_BLANK_AT_EOF, 0 }, { "tab-in-indent", WS_TAB_IN_INDENT, 0, 1 }, + { "incomplete-line", WS_INCOMPLETE_LINE, 0, 0 }, }; unsigned parse_whitespace_rule(const char *string) @@ -139,6 +140,11 @@ char *whitespace_error_string(unsigned ws) strbuf_addstr(&err, ", "); strbuf_addstr(&err, "tab in indent"); } + if (ws & WS_INCOMPLETE_LINE) { + if (err.len) + strbuf_addstr(&err, ", "); + strbuf_addstr(&err, "no newline at the end of file"); + } return strbuf_detach(&err, NULL); } @@ -180,6 +186,9 @@ static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule, if (trailing_whitespace == -1) trailing_whitespace = len; + if (!trailing_newline && (ws_rule & WS_INCOMPLETE_LINE)) + result |= WS_INCOMPLETE_LINE; + /* Check indentation */ for (i = 0; i < trailing_whitespace; i++) { if (line[i] == ' ') @@ -292,6 +301,17 @@ void ws_fix_copy(struct strbuf *dst, const char *src, int len, unsigned ws_rule, int need_fix_leading_space = 0; /* + * Remembering that we need to add '\n' at the end + * is sufficient to fix an incomplete line. + */ + if (ws_rule & WS_INCOMPLETE_LINE) { + if (0 < len && src[len - 1] != '\n') { + fixed = 1; + add_nl_to_tail = 1; + } + } + + /* * Strip trailing whitespace */ if (ws_rule & WS_BLANK_AT_EOL) { @@ -7,19 +7,23 @@ struct strbuf; /* * whitespace rules. * used by both diff and apply - * last two digits are tab width + * last two octal-digits are tab width (we support only up to 63). */ -#define WS_BLANK_AT_EOL 0100 -#define WS_SPACE_BEFORE_TAB 0200 -#define WS_INDENT_WITH_NON_TAB 0400 -#define WS_CR_AT_EOL 01000 -#define WS_BLANK_AT_EOF 02000 -#define WS_TAB_IN_INDENT 04000 -#define WS_TRAILING_SPACE (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF) +#define WS_BLANK_AT_EOL (1<<6) +#define WS_SPACE_BEFORE_TAB (1<<7) +#define WS_INDENT_WITH_NON_TAB (1<<8) +#define WS_CR_AT_EOL (1<<9) +#define WS_BLANK_AT_EOF (1<<10) +#define WS_TAB_IN_INDENT (1<<11) +#define WS_INCOMPLETE_LINE (1<<12) + +#define WS_TRAILING_SPACE (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF) #define WS_DEFAULT_RULE (WS_TRAILING_SPACE|WS_SPACE_BEFORE_TAB|8) -#define WS_TAB_WIDTH_MASK 077 -/* All WS_* -- when extended, adapt diff.c emit_symbol */ -#define WS_RULE_MASK 07777 +#define WS_TAB_WIDTH_MASK ((1<<6)-1) + +/* All WS_* -- when extended, adapt constants defined after diff.c:diff_symbol */ +#define WS_RULE_MASK ((1<<16)-1) + extern unsigned whitespace_rule_cfg; unsigned whitespace_rule(struct index_state *, const char *); unsigned parse_whitespace_rule(const char *); diff --git a/xdiff-interface.c b/xdiff-interface.c index 4971f722b3..1a35556380 100644 --- a/xdiff-interface.c +++ b/xdiff-interface.c @@ -300,7 +300,7 @@ void xdiff_clear_find_func(xdemitconf_t *xecfg) unsigned long xdiff_hash_string(const char *s, size_t len, long flags) { - return xdl_hash_record(&s, s + len, flags); + return xdl_hash_record((uint8_t const**)&s, (uint8_t const*)s + len, flags); } int xdiff_compare_lines(const char *l1, long s1, diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h index 2cecde5afe..dc370712e9 100644 --- a/xdiff/xdiff.h +++ b/xdiff/xdiff.h @@ -43,7 +43,7 @@ extern "C" { #define XDF_PATIENCE_DIFF (1 << 14) #define XDF_HISTOGRAM_DIFF (1 << 15) -#define XDF_DIFF_ALGORITHM_MASK (XDF_PATIENCE_DIFF | XDF_HISTOGRAM_DIFF) +#define XDF_DIFF_ALGORITHM_MASK (XDF_PATIENCE_DIFF | XDF_HISTOGRAM_DIFF | XDF_NEED_MINIMAL) #define XDF_DIFF_ALG(x) ((x) & XDF_DIFF_ALGORITHM_MASK) #define XDF_INDENT_HEURISTIC (1 << 23) diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c index 6f3998ee54..4376f943db 100644 --- a/xdiff/xdiffi.c +++ b/xdiff/xdiffi.c @@ -22,9 +22,9 @@ #include "xinclude.h" -static unsigned long get_hash(xdfile_t *xdf, long index) +static size_t get_hash(xdfile_t *xdf, long index) { - return xdf->recs[xdf->rindex[index]].ha; + return xdf->recs[xdf->reference_index[index]].minimal_perfect_hash; } #define XDL_MAX_COST_MIN 256 @@ -278,10 +278,10 @@ int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1, */ if (off1 == lim1) { for (; off2 < lim2; off2++) - xdf2->changed[xdf2->rindex[off2]] = true; + xdf2->changed[xdf2->reference_index[off2]] = true; } else if (off2 == lim2) { for (; off1 < lim1; off1++) - xdf1->changed[xdf1->rindex[off1]] = true; + xdf1->changed[xdf1->reference_index[off1]] = true; } else { xdpsplit_t spl; spl.i1 = spl.i2 = 0; @@ -385,7 +385,7 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, static int recs_match(xrecord_t *rec1, xrecord_t *rec2) { - return (rec1->ha == rec2->ha); + return rec1->minimal_perfect_hash == rec2->minimal_perfect_hash; } /* @@ -403,11 +403,10 @@ static int recs_match(xrecord_t *rec1, xrecord_t *rec2) */ static int get_indent(xrecord_t *rec) { - long i; int ret = 0; - for (i = 0; i < rec->size; i++) { - char c = rec->ptr[i]; + for (size_t i = 0; i < rec->size; i++) { + char c = (char) rec->ptr[i]; if (!XDL_ISSPACE(c)) return ret; @@ -484,7 +483,7 @@ static void measure_split(const xdfile_t *xdf, long split, { long i; - if (split >= xdf->nrec) { + if (split >= (long)xdf->nrec) { m->end_of_file = 1; m->indent = -1; } else { @@ -507,7 +506,7 @@ static void measure_split(const xdfile_t *xdf, long split, m->post_blank = 0; m->post_indent = -1; - for (i = split + 1; i < xdf->nrec; i++) { + for (i = split + 1; i < (long)xdf->nrec; i++) { m->post_indent = get_indent(&xdf->recs[i]); if (m->post_indent != -1) break; @@ -718,7 +717,7 @@ static void group_init(xdfile_t *xdf, struct xdlgroup *g) */ static inline int group_next(xdfile_t *xdf, struct xdlgroup *g) { - if (g->end == xdf->nrec) + if (g->end == (long)xdf->nrec) return -1; g->start = g->end + 1; @@ -751,7 +750,7 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g) */ static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g) { - if (g->end < xdf->nrec && + if (g->end < (long)xdf->nrec && recs_match(&xdf->recs[g->start], &xdf->recs[g->end])) { xdf->changed[g->start++] = false; xdf->changed[g->end++] = true; @@ -993,11 +992,11 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags) rec = &xe->xdf1.recs[xch->i1]; for (i = 0; i < xch->chg1 && ignore; i++) - ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags); + ignore = xdl_blankline((const char *)rec[i].ptr, (long)rec[i].size, flags); rec = &xe->xdf2.recs[xch->i2]; for (i = 0; i < xch->chg2 && ignore; i++) - ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags); + ignore = xdl_blankline((const char *)rec[i].ptr, (long)rec[i].size, flags); xch->ignore = ignore; } @@ -1008,7 +1007,7 @@ static int record_matches_regex(xrecord_t *rec, xpparam_t const *xpp) { size_t i; for (i = 0; i < xpp->ignore_regex_nr; i++) - if (!regexec_buf(xpp->ignore_regex[i], rec->ptr, rec->size, 1, + if (!regexec_buf(xpp->ignore_regex[i], (const char *)rec->ptr, rec->size, 1, ®match, 0)) return 1; diff --git a/xdiff/xemit.c b/xdiff/xemit.c index b2f1f30cd3..04f7e9193b 100644 --- a/xdiff/xemit.c +++ b/xdiff/xemit.c @@ -27,7 +27,7 @@ static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t * { xrecord_t *rec = &xdf->recs[ri]; - if (xdl_emit_diffrec(rec->ptr, rec->size, pre, strlen(pre), ecb) < 0) + if (xdl_emit_diffrec((char const *)rec->ptr, (long)rec->size, pre, strlen(pre), ecb) < 0) return -1; return 0; @@ -113,8 +113,8 @@ static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri, xrecord_t *rec = &xdf->recs[ri]; if (!xecfg->find_func) - return def_ff(rec->ptr, rec->size, buf, sz); - return xecfg->find_func(rec->ptr, rec->size, buf, sz, xecfg->find_func_priv); + return def_ff((const char *)rec->ptr, (long)rec->size, buf, sz); + return xecfg->find_func((const char *)rec->ptr, (long)rec->size, buf, sz, xecfg->find_func_priv); } static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri) @@ -137,7 +137,7 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg, buf = func_line ? func_line->buf : dummy; size = func_line ? sizeof(func_line->buf) : sizeof(dummy); - for (l = start; l != limit && 0 <= l && l < xe->xdf1.nrec; l += step) { + for (l = start; l != limit && 0 <= l && l < (long)xe->xdf1.nrec; l += step) { long len = match_func_rec(&xe->xdf1, xecfg, l, buf, size); if (len >= 0) { if (func_line) @@ -151,7 +151,7 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg, static int is_empty_rec(xdfile_t *xdf, long ri) { xrecord_t *rec = &xdf->recs[ri]; - long i = 0; + size_t i = 0; for (; i < rec->size && XDL_ISSPACE(rec->ptr[i]); i++); @@ -179,14 +179,14 @@ pre_context_calculation: long fs1, i1 = xch->i1; /* Appended chunk? */ - if (i1 >= xe->xdf1.nrec) { + if (i1 >= (long)xe->xdf1.nrec) { long i2 = xch->i2; /* * We don't need additional context if * a whole function was added. */ - while (i2 < xe->xdf2.nrec) { + while (i2 < (long)xe->xdf2.nrec) { if (is_func_rec(&xe->xdf2, xecfg, i2)) goto post_context_calculation; i2++; @@ -196,7 +196,7 @@ pre_context_calculation: * Otherwise get more context from the * pre-image. */ - i1 = xe->xdf1.nrec - 1; + i1 = (long)xe->xdf1.nrec - 1; } fs1 = get_func_line(xe, xecfg, NULL, i1, -1); @@ -228,8 +228,8 @@ pre_context_calculation: post_context_calculation: lctx = xecfg->ctxlen; - lctx = XDL_MIN(lctx, xe->xdf1.nrec - (xche->i1 + xche->chg1)); - lctx = XDL_MIN(lctx, xe->xdf2.nrec - (xche->i2 + xche->chg2)); + lctx = XDL_MIN(lctx, (long)xe->xdf1.nrec - (xche->i1 + xche->chg1)); + lctx = XDL_MIN(lctx, (long)xe->xdf2.nrec - (xche->i2 + xche->chg2)); e1 = xche->i1 + xche->chg1 + lctx; e2 = xche->i2 + xche->chg2 + lctx; @@ -237,13 +237,13 @@ pre_context_calculation: if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) { long fe1 = get_func_line(xe, xecfg, NULL, xche->i1 + xche->chg1, - xe->xdf1.nrec); + (long)xe->xdf1.nrec); while (fe1 > 0 && is_empty_rec(&xe->xdf1, fe1 - 1)) fe1--; if (fe1 < 0) - fe1 = xe->xdf1.nrec; + fe1 = (long)xe->xdf1.nrec; if (fe1 > e1) { - e2 = XDL_MIN(e2 + (fe1 - e1), xe->xdf2.nrec); + e2 = XDL_MIN(e2 + (fe1 - e1), (long)xe->xdf2.nrec); e1 = fe1; } @@ -254,7 +254,7 @@ pre_context_calculation: */ if (xche->next) { long l = XDL_MIN(xche->next->i1, - xe->xdf1.nrec - 1); + (long)xe->xdf1.nrec - 1); if (l - xecfg->ctxlen <= e1 || get_func_line(xe, xecfg, NULL, l, e1) < 0) { xche = xche->next; diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c index 6dc450b1fe..5ae1282c27 100644 --- a/xdiff/xhistogram.c +++ b/xdiff/xhistogram.c @@ -90,7 +90,7 @@ struct region { static int cmp_recs(xrecord_t *r1, xrecord_t *r2) { - return r1->ha == r2->ha; + return r1->minimal_perfect_hash == r2->minimal_perfect_hash; } @@ -98,7 +98,7 @@ static int cmp_recs(xrecord_t *r1, xrecord_t *r2) (cmp_recs(REC(i->env, s1, l1), REC(i->env, s2, l2))) #define TABLE_HASH(index, side, line) \ - XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits) + XDL_HASHLONG((REC(index->env, side, line))->minimal_perfect_hash, index->table_bits) static int scanA(struct histindex *index, int line1, int count1) { diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c index fd600cbb5d..29dad98c49 100644 --- a/xdiff/xmerge.c +++ b/xdiff/xmerge.c @@ -101,8 +101,8 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, xrecord_t *rec2 = xe2->xdf2.recs + i2; for (i = 0; i < line_count; i++) { - int result = xdl_recmatch(rec1[i].ptr, rec1[i].size, - rec2[i].ptr, rec2[i].size, flags); + int result = xdl_recmatch((const char *)rec1[i].ptr, (long)rec1[i].size, + (const char *)rec2[i].ptr, (long)rec2[i].size, flags); if (!result) return -1; } @@ -119,11 +119,11 @@ static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int nee if (count < 1) return 0; - for (i = 0; i < count; size += recs[i++].size) + for (i = 0; i < count; size += (int)recs[i++].size) if (dest) memcpy(dest + size, recs[i].ptr, recs[i].size); if (add_nl) { - i = recs[count - 1].size; + i = (int)recs[count - 1].size; if (i == 0 || recs[count - 1].ptr[i - 1] != '\n') { if (needs_cr) { if (dest) @@ -156,9 +156,9 @@ static int xdl_orig_copy(xdfenv_t *xe, int i, int count, int needs_cr, int add_n */ static int is_eol_crlf(xdfile_t *file, int i) { - long size; + size_t size; - if (i < file->nrec - 1) + if (i < (long)file->nrec - 1) /* All lines before the last *must* end in LF */ return (size = file->recs[i].size) > 1 && file->recs[i].ptr[size - 2] == '\r'; @@ -317,15 +317,15 @@ static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1, continue; i = m->i1 + m->chg1; } - size += xdl_recs_copy(xe1, i, xe1->xdf2.nrec - i, 0, 0, + size += xdl_recs_copy(xe1, i, (int)xe1->xdf2.nrec - i, 0, 0, dest ? dest + size : NULL); return size; } static int recmatch(xrecord_t *rec1, xrecord_t *rec2, unsigned long flags) { - return xdl_recmatch(rec1->ptr, rec1->size, - rec2->ptr, rec2->size, flags); + return xdl_recmatch((const char *)rec1->ptr, (long)rec1->size, + (const char *)rec2->ptr, (long)rec2->size, flags); } /* @@ -382,10 +382,10 @@ static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, * we have a very simple mmfile structure. */ t1.ptr = (char *)xe1->xdf2.recs[m->i1].ptr; - t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1].ptr + t1.size = (char *)xe1->xdf2.recs[m->i1 + m->chg1 - 1].ptr + xe1->xdf2.recs[m->i1 + m->chg1 - 1].size - t1.ptr; t2.ptr = (char *)xe2->xdf2.recs[m->i2].ptr; - t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1].ptr + t2.size = (char *)xe2->xdf2.recs[m->i2 + m->chg2 - 1].ptr + xe2->xdf2.recs[m->i2 + m->chg2 - 1].size - t2.ptr; if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0) return -1; @@ -440,8 +440,8 @@ static int line_contains_alnum(const char *ptr, long size) static int lines_contain_alnum(xdfenv_t *xe, int i, int chg) { for (; chg; chg--, i++) - if (line_contains_alnum(xe->xdf2.recs[i].ptr, - xe->xdf2.recs[i].size)) + if (line_contains_alnum((const char *)xe->xdf2.recs[i].ptr, + (long)xe->xdf2.recs[i].size)) return 1; return 0; } @@ -622,7 +622,7 @@ static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1, changes = c; i0 = xscr1->i1; i1 = xscr1->i2; - i2 = xscr1->i1 + xe2->xdf2.nrec - xe2->xdf1.nrec; + i2 = xscr1->i1 + (long)xe2->xdf2.nrec - (long)xe2->xdf1.nrec; chg0 = xscr1->chg1; chg1 = xscr1->chg2; chg2 = xscr1->chg1; @@ -637,7 +637,7 @@ static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1, if (!changes) changes = c; i0 = xscr2->i1; - i1 = xscr2->i1 + xe1->xdf2.nrec - xe1->xdf1.nrec; + i1 = xscr2->i1 + (long)xe1->xdf2.nrec - (long)xe1->xdf1.nrec; i2 = xscr2->i2; chg0 = xscr2->chg1; chg1 = xscr2->chg1; diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c index 669b653580..9580d18032 100644 --- a/xdiff/xpatience.c +++ b/xdiff/xpatience.c @@ -48,7 +48,7 @@ struct hashmap { int nr, alloc; struct entry { - unsigned long hash; + size_t minimal_perfect_hash; /* * 0 = unused entry, 1 = first line, 2 = second, etc. * line2 is NON_UNIQUE if the line is not unique @@ -101,10 +101,10 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, * So we multiply ha by 2 in the hope that the hashing was * "unique enough". */ - int index = (int)((record->ha << 1) % map->alloc); + int index = (int)((record->minimal_perfect_hash << 1) % map->alloc); while (map->entries[index].line1) { - if (map->entries[index].hash != record->ha) { + if (map->entries[index].minimal_perfect_hash != record->minimal_perfect_hash) { if (++index >= map->alloc) index = 0; continue; @@ -120,8 +120,8 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, if (pass == 2) return; map->entries[index].line1 = line; - map->entries[index].hash = record->ha; - map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1].ptr); + map->entries[index].minimal_perfect_hash = record->minimal_perfect_hash; + map->entries[index].anchor = is_anchor(xpp, (const char *)map->env->xdf1.recs[line - 1].ptr); if (!map->first) map->first = map->entries + index; if (map->last) { @@ -211,7 +211,10 @@ static int find_longest_common_sequence(struct hashmap *map, struct entry **res) for (entry = map->first; entry; entry = entry->next) { if (!entry->line2 || entry->line2 == NON_UNIQUE) continue; - i = binary_search(sequence, longest, entry); + if (longest == 0 || entry->line2 > sequence[longest - 1]->line2) + i = longest - 1; + else + i = binary_search(sequence, longest, entry); entry->previous = i < 0 ? NULL : sequence[i]; ++i; if (i <= anchor_i) @@ -248,7 +251,7 @@ static int match(struct hashmap *map, int line1, int line2) { xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1]; xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1]; - return record1->ha == record2->ha; + return record1->minimal_perfect_hash == record2->minimal_perfect_hash; } static int patience_diff(xpparam_t const *xpp, xdfenv_t *env, @@ -370,5 +373,5 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env, int xdl_do_patience_diff(xpparam_t const *xpp, xdfenv_t *env) { - return patience_diff(xpp, env, 1, env->xdf1.nrec, 1, env->xdf2.nrec); + return patience_diff(xpp, env, 1, (int)env->xdf1.nrec, 1, (int)env->xdf2.nrec); } diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index 192334f1b7..34c82e4f8e 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -93,14 +93,14 @@ static void xdl_free_classifier(xdlclassifier_t *cf) { static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) { - long hi; + size_t hi; xdlclass_t *rcrec; - hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); + hi = XDL_HASHLONG(rec->line_hash, cf->hbits); for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) - if (rcrec->rec.ha == rec->ha && - xdl_recmatch(rcrec->rec.ptr, rcrec->rec.size, - rec->ptr, rec->size, cf->flags)) + if (rcrec->rec.line_hash == rec->line_hash && + xdl_recmatch((const char *)rcrec->rec.ptr, (long)rcrec->rec.size, + (const char *)rec->ptr, (long)rec->size, cf->flags)) break; if (!rcrec) { @@ -120,7 +120,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t (pass == 1) ? rcrec->len1++ : rcrec->len2++; - rec->ha = (unsigned long) rcrec->idx; + rec->minimal_perfect_hash = (size_t)rcrec->idx; return 0; } @@ -128,7 +128,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t static void xdl_free_ctx(xdfile_t *xdf) { - xdl_free(xdf->rindex); + xdl_free(xdf->reference_index); xdl_free(xdf->changed - 1); xdl_free(xdf->recs); } @@ -137,11 +137,11 @@ static void xdl_free_ctx(xdfile_t *xdf) static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf) { long bsize; - unsigned long hav; - char const *blk, *cur, *top, *prev; + uint64_t hav; + uint8_t const *blk, *cur, *top, *prev; xrecord_t *crec; - xdf->rindex = NULL; + xdf->reference_index = NULL; xdf->changed = NULL; xdf->recs = NULL; @@ -153,12 +153,12 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_ for (top = blk + bsize; cur < top; ) { prev = cur; hav = xdl_hash_record(&cur, top, xpp->flags); - if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec)) + if (XDL_ALLOC_GROW(xdf->recs, (long)xdf->nrec + 1, narec)) goto abort; crec = &xdf->recs[xdf->nrec++]; crec->ptr = prev; - crec->size = (long) (cur - prev); - crec->ha = hav; + crec->size = cur - prev; + crec->line_hash = hav; if (xdl_classify_record(pass, cf, crec) < 0) goto abort; } @@ -169,7 +169,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_ if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) { - if (!XDL_ALLOC_ARRAY(xdf->rindex, xdf->nrec + 1)) + if (!XDL_ALLOC_ARRAY(xdf->reference_index, xdf->nrec + 1)) goto abort; } @@ -264,7 +264,7 @@ static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) { * might be potentially discarded if they appear in a run of discardable. */ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { - long i, nm, nreff, mlim; + long i, nm, mlim; xrecord_t *recs; xdlclass_t *rcrec; uint8_t *action1 = NULL, *action2 = NULL; @@ -287,18 +287,18 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd /* * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE. */ - if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT) + if ((mlim = xdl_bogosqrt((long)xdf1->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { - rcrec = cf->rcrecs[recs->ha]; + rcrec = cf->rcrecs[recs->minimal_perfect_hash]; nm = rcrec ? rcrec->len2 : 0; action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; } - if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT) + if ((mlim = xdl_bogosqrt((long)xdf2->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { - rcrec = cf->rcrecs[recs->ha]; + rcrec = cf->rcrecs[recs->minimal_perfect_hash]; nm = rcrec ? rcrec->len1 : 0; action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; } @@ -307,29 +307,29 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd * Use temporary arrays to decide if changed[i] should remain * false, or become true. */ - for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; + xdf1->nreff = 0; + for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { if (action1[i] == KEEP || (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))) { - xdf1->rindex[nreff++] = i; + xdf1->reference_index[xdf1->nreff++] = i; /* changed[i] remains false, i.e. keep */ } else xdf1->changed[i] = true; /* i.e. discard */ } - xdf1->nreff = nreff; - for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; + xdf2->nreff = 0; + for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { if (action2[i] == KEEP || (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))) { - xdf2->rindex[nreff++] = i; + xdf2->reference_index[xdf2->nreff++] = i; /* changed[i] remains false, i.e. keep */ } else xdf2->changed[i] = true; /* i.e. discard */ } - xdf2->nreff = nreff; cleanup: xdl_free(action1); @@ -348,9 +348,9 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { recs1 = xdf1->recs; recs2 = xdf2->recs; - for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim; + for (i = 0, lim = (long)XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim; i++, recs1++, recs2++) - if (recs1->ha != recs2->ha) + if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash) break; xdf1->dstart = xdf2->dstart = i; @@ -358,11 +358,11 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { recs1 = xdf1->recs + xdf1->nrec - 1; recs2 = xdf2->recs + xdf2->nrec - 1; for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--) - if (recs1->ha != recs2->ha) + if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash) break; - xdf1->dend = xdf1->nrec - i - 1; - xdf2->dend = xdf2->nrec - i - 1; + xdf1->dend = (long)xdf1->nrec - i - 1; + xdf2->dend = (long)xdf2->nrec - i - 1; return 0; } diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h index f145abba3e..979586f20a 100644 --- a/xdiff/xtypes.h +++ b/xdiff/xtypes.h @@ -39,18 +39,19 @@ typedef struct s_chastore { } chastore_t; typedef struct s_xrecord { - char const *ptr; - long size; - unsigned long ha; + uint8_t const *ptr; + size_t size; + uint64_t line_hash; + size_t minimal_perfect_hash; } xrecord_t; typedef struct s_xdfile { xrecord_t *recs; - long nrec; - long dstart, dend; + size_t nrec; + ptrdiff_t dstart, dend; bool *changed; - long *rindex; - long nreff; + size_t *reference_index; + size_t nreff; } xdfile_t; typedef struct s_xdfenv { diff --git a/xdiff/xutils.c b/xdiff/xutils.c index 447e66c719..77ee1ad9c8 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -249,11 +249,11 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags) return 1; } -unsigned long xdl_hash_record_with_whitespace(char const **data, - char const *top, long flags) { - unsigned long ha = 5381; - char const *ptr = *data; - int cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL; +uint64_t xdl_hash_record_with_whitespace(uint8_t const **data, + uint8_t const *top, uint64_t flags) { + uint64_t ha = 5381; + uint8_t const *ptr = *data; + bool cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL; for (; ptr < top && *ptr != '\n'; ptr++) { if (cr_at_eol_only) { @@ -263,8 +263,8 @@ unsigned long xdl_hash_record_with_whitespace(char const **data, continue; } else if (XDL_ISSPACE(*ptr)) { - const char *ptr2 = ptr; - int at_eol; + const uint8_t *ptr2 = ptr; + bool at_eol; while (ptr + 1 < top && XDL_ISSPACE(ptr[1]) && ptr[1] != '\n') ptr++; @@ -274,20 +274,20 @@ unsigned long xdl_hash_record_with_whitespace(char const **data, else if (flags & XDF_IGNORE_WHITESPACE_CHANGE && !at_eol) { ha += (ha << 5); - ha ^= (unsigned long) ' '; + ha ^= (uint64_t) ' '; } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL && !at_eol) { while (ptr2 != ptr + 1) { ha += (ha << 5); - ha ^= (unsigned long) *ptr2; + ha ^= (uint64_t) *ptr2; ptr2++; } } continue; } ha += (ha << 5); - ha ^= (unsigned long) *ptr; + ha ^= (uint64_t) *ptr; } *data = ptr < top ? ptr + 1: ptr; @@ -304,9 +304,9 @@ unsigned long xdl_hash_record_with_whitespace(char const **data, #define REASSOC_FENCE(x, y) #endif -unsigned long xdl_hash_record_verbatim(char const **data, char const *top) { - unsigned long ha = 5381, c0, c1; - char const *ptr = *data; +uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top) { + uint64_t ha = 5381, c0, c1; + uint8_t const *ptr = *data; #if 0 /* * The baseline form of the optimized loop below. This is the djb2 @@ -314,7 +314,7 @@ unsigned long xdl_hash_record_verbatim(char const **data, char const *top) { */ for (; ptr < top && *ptr != '\n'; ptr++) { ha += (ha << 5); - ha += (unsigned long) *ptr; + ha += (uint64_t) *ptr; } *data = ptr < top ? ptr + 1: ptr; #else @@ -465,10 +465,10 @@ int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp, xdfenv_t env; subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1].ptr; - subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2].ptr + + subfile1.size = (char *)diff_env->xdf1.recs[line1 + count1 - 2].ptr + diff_env->xdf1.recs[line1 + count1 - 2].size - subfile1.ptr; subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1].ptr; - subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2].ptr + + subfile2.size = (char *)diff_env->xdf2.recs[line2 + count2 - 2].ptr + diff_env->xdf2.recs[line2 + count2 - 2].size - subfile2.ptr; if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0) return -1; diff --git a/xdiff/xutils.h b/xdiff/xutils.h index 13f6831047..615b4a9d35 100644 --- a/xdiff/xutils.h +++ b/xdiff/xutils.h @@ -34,9 +34,9 @@ void *xdl_cha_alloc(chastore_t *cha); long xdl_guess_lines(mmfile_t *mf, long sample); int xdl_blankline(const char *line, long size, long flags); int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags); -unsigned long xdl_hash_record_verbatim(char const **data, char const *top); -unsigned long xdl_hash_record_with_whitespace(char const **data, char const *top, long flags); -static inline unsigned long xdl_hash_record(char const **data, char const *top, long flags) +uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top); +uint64_t xdl_hash_record_with_whitespace(uint8_t const **data, uint8_t const *top, uint64_t flags); +static inline uint64_t xdl_hash_record(uint8_t const **data, uint8_t const *top, uint64_t flags) { if (flags & XDF_WHITESPACE_FLAGS) return xdl_hash_record_with_whitespace(data, top, flags); |