diff options
168 files changed, 3872 insertions, 2302 deletions
diff --git a/.clang-format b/.clang-format index dcfd0aad60..86b4fe33e5 100644 --- a/.clang-format +++ b/.clang-format @@ -149,7 +149,7 @@ SpaceBeforeCaseColon: false # f(); # } # } -SpaceBeforeParens: ControlStatements +SpaceBeforeParens: ControlStatementsExceptControlMacros # Don't insert spaces inside empty '()' SpaceInEmptyParentheses: false diff --git a/.github/workflows/check-style.yml b/.github/workflows/check-style.yml index c052a5df23..19a145d4ad 100644 --- a/.github/workflows/check-style.yml +++ b/.github/workflows/check-style.yml @@ -20,7 +20,7 @@ jobs: jobname: ClangFormat runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 with: fetch-depth: 0 diff --git a/.github/workflows/check-whitespace.yml b/.github/workflows/check-whitespace.yml index d0a78fc426..928fd4cfe2 100644 --- a/.github/workflows/check-whitespace.yml +++ b/.github/workflows/check-whitespace.yml @@ -19,7 +19,7 @@ jobs: check-whitespace: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 with: fetch-depth: 0 diff --git a/.github/workflows/coverity.yml b/.github/workflows/coverity.yml index 01a0437b2f..cfa17d394a 100644 --- a/.github/workflows/coverity.yml +++ b/.github/workflows/coverity.yml @@ -38,7 +38,7 @@ jobs: COVERITY_LANGUAGE: cxx COVERITY_PLATFORM: overridden-below steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - name: install minimal Git for Windows SDK if: contains(matrix.os, 'windows') uses: git-for-windows/setup-git-for-windows-sdk@v1 diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index d122e79415..3622fec742 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -63,7 +63,7 @@ jobs: echo "skip_concurrent=$skip_concurrent" >>$GITHUB_OUTPUT - name: skip if the commit or tree was already tested id: skip-if-redundant - uses: actions/github-script@v7 + uses: actions/github-script@v8 if: steps.check-ref.outputs.enabled == 'yes' with: github-token: ${{secrets.GITHUB_TOKEN}} @@ -112,7 +112,7 @@ jobs: group: windows-build-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - uses: git-for-windows/setup-git-for-windows-sdk@v1 - name: build shell: bash @@ -140,7 +140,7 @@ jobs: cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - name: download tracked files and build artifacts - uses: actions/download-artifact@v4 + uses: actions/download-artifact@v5 with: name: windows-artifacts path: ${{github.workspace}} @@ -173,10 +173,10 @@ jobs: group: vs-build-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - uses: git-for-windows/setup-git-for-windows-sdk@v1 - name: initialize vcpkg - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: repository: 'microsoft/vcpkg' path: 'compat/vcbuild/vcpkg' @@ -226,7 +226,7 @@ jobs: steps: - uses: git-for-windows/setup-git-for-windows-sdk@v1 - name: download tracked files and build artifacts - uses: actions/download-artifact@v4 + uses: actions/download-artifact@v5 with: name: vs-artifacts path: ${{github.workspace}} @@ -258,8 +258,8 @@ jobs: group: windows-meson-build-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 - - uses: actions/setup-python@v5 + - uses: actions/checkout@v5 + - uses: actions/setup-python@v6 - name: Set up dependencies shell: pwsh run: pip install meson ninja @@ -286,13 +286,13 @@ jobs: group: windows-meson-test-${{ matrix.nr }}-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 - - uses: actions/setup-python@v5 + - uses: actions/checkout@v5 + - uses: actions/setup-python@v6 - name: Set up dependencies shell: pwsh run: pip install meson ninja - name: Download build artifacts - uses: actions/download-artifact@v4 + uses: actions/download-artifact@v5 with: name: windows-meson-artifacts path: build @@ -331,7 +331,7 @@ jobs: TEST_OUTPUT_DIRECTORY: ${{github.workspace}}/t runs-on: ${{matrix.vector.pool}} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - run: ci/install-dependencies.sh - run: ci/run-build-and-tests.sh - name: print test failures @@ -352,7 +352,7 @@ jobs: CI_JOB_IMAGE: ubuntu-latest runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - run: ci/install-dependencies.sh - run: ci/run-build-and-minimal-fuzzers.sh dockerized: @@ -379,6 +379,8 @@ jobs: - jobname: linux-breaking-changes cc: gcc image: ubuntu:rolling + - jobname: fedora-breaking-changes-meson + image: fedora:latest - jobname: linux-leaks image: ubuntu:rolling cc: gcc @@ -396,8 +398,6 @@ jobs: # Supported until 2025-04-02. - jobname: linux32 image: i386/ubuntu:focal - - jobname: pedantic - image: fedora:latest # A RHEL 8 compatible distro. Supported until 2029-05-31. - jobname: almalinux-8 image: almalinux:8 @@ -429,7 +429,7 @@ jobs: else apt-get -q update && apt-get -q -y install git fi - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - run: ci/install-dependencies.sh - run: useradd builder --create-home - run: chown -R builder . @@ -454,7 +454,7 @@ jobs: group: static-analysis-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - run: ci/install-dependencies.sh - run: ci/run-static-analysis.sh - run: ci/check-directional-formatting.bash @@ -469,7 +469,7 @@ jobs: group: sparse-${{ github.ref }} cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - name: Install other dependencies run: ci/install-dependencies.sh - run: make sparse @@ -485,6 +485,6 @@ jobs: CI_JOB_IMAGE: ubuntu-latest runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v5 - run: ci/install-dependencies.sh - run: ci/test-documentation.sh diff --git a/.gitignore b/.gitignore index 802ce70e48..78a45cb5be 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,6 @@ /fuzz_corpora +/target/ +/Cargo.lock /GIT-BUILD-DIR /GIT-BUILD-OPTIONS /GIT-CFLAGS diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index cf122e706f..f7d57d1ee9 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -45,6 +45,8 @@ test:linux: - jobname: linux-breaking-changes image: ubuntu:20.04 CC: gcc + - jobname: fedora-breaking-changes-meson + image: fedora:latest - jobname: linux-TEST-vars image: ubuntu:20.04 CC: gcc @@ -58,8 +60,6 @@ test:linux: - jobname: linux-asan-ubsan image: ubuntu:rolling CC: clang - - jobname: pedantic - image: fedora:latest - jobname: linux-musl-meson image: alpine:latest - jobname: linux32 @@ -70,6 +70,8 @@ test:linux: artifacts: paths: - t/failed-test-artifacts + reports: + junit: build/meson-logs/testlog.junit.xml when: on_failure test:osx: @@ -110,8 +112,16 @@ test:osx: artifacts: paths: - t/failed-test-artifacts + reports: + junit: build/meson-logs/testlog.junit.xml when: on_failure +.windows_before_script: &windows_before_script + # Disabling realtime monitoring fails on some of the runners, but it + # significantly speeds up test execution in the case where it works. We thus + # try our luck, but ignore any failures. + - Set-MpPreference -DisableRealtimeMonitoring $true; $true + build:mingw64: stage: build tags: @@ -119,7 +129,7 @@ build:mingw64: variables: NO_PERL: 1 before_script: - - Set-MpPreference -DisableRealtimeMonitoring $true + - *windows_before_script - ./ci/install-sdk.ps1 -directory "git-sdk" script: - git-sdk/usr/bin/bash.exe -l -c 'ci/make-test-artifacts.sh artifacts' @@ -136,7 +146,7 @@ test:mingw64: - job: "build:mingw64" artifacts: true before_script: - - Set-MpPreference -DisableRealtimeMonitoring $true + - *windows_before_script - git-sdk/usr/bin/bash.exe -l -c 'tar xf artifacts/artifacts.tar.gz' - New-Item -Path .git/info -ItemType Directory - New-Item .git/info/exclude -ItemType File -Value "/git-sdk" @@ -150,18 +160,10 @@ test:mingw64: tags: - saas-windows-medium-amd64 before_script: - - Set-MpPreference -DisableRealtimeMonitoring $true - - choco install -y git meson ninja openssl + - *windows_before_script + - choco install -y git meson ninja - Import-Module $env:ChocolateyInstall\helpers\chocolateyProfile.psm1 - refreshenv - # The certificate store for Python on Windows is broken and fails to fetch - # certificates, see https://bugs.python.org/issue36011. This seems to - # mostly be an issue with how the GitLab image is set up as it is a - # non-issue on GitHub Actions. Work around the issue by importing - # cetrificates manually. - - Invoke-WebRequest https://curl.haxx.se/ca/cacert.pem -OutFile cacert.pem - - openssl pkcs12 -export -nokeys -in cacert.pem -out certs.pfx -passout "pass:" - - Import-PfxCertificate -CertStoreLocation Cert:\LocalMachine\Root -FilePath certs.pfx build:msvc-meson: extends: .msvc-meson @@ -183,6 +185,9 @@ test:msvc-meson: script: - meson test -C build --no-rebuild --print-errorlogs --slice $Env:CI_NODE_INDEX/$Env:CI_NODE_TOTAL parallel: 10 + artifacts: + reports: + junit: build/meson-logs/testlog.junit.xml test:fuzz-smoke-tests: image: ubuntu:latest @@ -126,6 +126,7 @@ Jon Loeliger <jdl@jdl.com> <jdl@freescale.org> Jon Seymour <jon.seymour@gmail.com> <jon@blackcubes.dyndns.org> Jonathan Nieder <jrnieder@gmail.com> <jrnieder@uchicago.edu> Jonathan del Strother <jon.delStrother@bestbefore.tv> <maillist@steelskies.com> +Jonathan Tan <jonathantanmy@fastmail.com> <jonathantanmy@google.com> Josh Triplett <josh@joshtriplett.org> <josh@freedesktop.org> Josh Triplett <josh@joshtriplett.org> <josht@us.ibm.com> Julian Phillips <julian@quantumfyre.co.uk> <jp3@quantumfyre.co.uk> diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000000..45c9b34981 --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,9 @@ +[package] +name = "gitcore" +version = "0.1.0" +edition = "2018" + +[lib] +crate-type = ["staticlib"] + +[dependencies] diff --git a/Documentation/BreakingChanges.adoc b/Documentation/BreakingChanges.adoc index a67ad4eea1..90b53abcea 100644 --- a/Documentation/BreakingChanges.adoc +++ b/Documentation/BreakingChanges.adoc @@ -171,6 +171,51 @@ JGit, libgit2 and Gitoxide need to support it. matches the default branch name used in new repositories by many of the big Git forges. +* Git will require Rust as a mandatory part of the build process. While Git + already started to adopt Rust in Git 2.49, all parts written in Rust are + optional for the time being. This includes: ++ + ** The Rust wrapper around libgit.a that is part of "contrib/" and which has + been introduced in Git 2.49. + ** Subsystems that have an alternative implementation in Rust to test + interoperability between our C and Rust codebase. + ** Newly written features that are not mission critical for a fully functional + Git client. ++ +These changes are meant as test balloons to allow distributors of Git to prepare +for Rust becoming a mandatory part of the build process. There will be multiple +milestones for the introduction of Rust: ++ +-- +1. Initially, with Git 2.52, support for Rust will be auto-detected by Meson and + disabled in our Makefile so that the project can sort out the initial + infrastructure. +2. In Git 2.53, both build systems will default-enable support for Rust. + Consequently, builds will break by default if Rust is not available on the + build host. The use of Rust can still be explicitly disabled via build + flags. +3. In Git 3.0, the build options will be removed and support for Rust is + mandatory. +-- ++ +You can explicitly ask both Meson and our Makefile-based system to enable Rust +by saying `meson configure -Drust=enabled` and `make WITH_RUST=YesPlease`, +respectively. ++ +The Git project will declare the last version before Git 3.0 to be a long-term +support release. This long-term release will receive important bug fixes for at +least four release cycles and security fixes for six release cycles. The Git +project will hand over maintainership of the long-term release to distributors +in case they need to extend the life of that long-term release even further. +Details of how this long-term release will be handed over to the community will +be discussed once the Git project decides to stop officially supporting it. ++ +We will evaluate the impact on downstream distributions before making Rust +mandatory in Git 3.0. If we see that the impact on downstream distributions +would be significant, we may decide to defer this change to a subsequent minor +release. This evaluation will also take into account our own experience with +how painful it is to keep Rust an optional component. + === Removals * Support for grafting commits has long been superseded by git-replace(1). diff --git a/Documentation/Makefile b/Documentation/Makefile index 6fb83d0c6e..04e9e10b27 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -34,6 +34,7 @@ MAN5_TXT += gitformat-bundle.adoc MAN5_TXT += gitformat-chunk.adoc MAN5_TXT += gitformat-commit-graph.adoc MAN5_TXT += gitformat-index.adoc +MAN5_TXT += gitformat-loose.adoc MAN5_TXT += gitformat-pack.adoc MAN5_TXT += gitformat-signature.adoc MAN5_TXT += githooks.adoc @@ -119,18 +120,27 @@ TECH_DOCS += ToolsForGit TECH_DOCS += technical/bitmap-format TECH_DOCS += technical/build-systems TECH_DOCS += technical/bundle-uri +TECH_DOCS += technical/commit-graph +TECH_DOCS += technical/directory-rename-detection TECH_DOCS += technical/hash-function-transition +TECH_DOCS += technical/large-object-promisors TECH_DOCS += technical/long-running-process-protocol TECH_DOCS += technical/multi-pack-index +TECH_DOCS += technical/packfile-uri TECH_DOCS += technical/pack-heuristics TECH_DOCS += technical/parallel-checkout TECH_DOCS += technical/partial-clone TECH_DOCS += technical/platform-support TECH_DOCS += technical/racy-git TECH_DOCS += technical/reftable +TECH_DOCS += technical/remembering-renames +TECH_DOCS += technical/repository-version +TECH_DOCS += technical/rerere TECH_DOCS += technical/scalar TECH_DOCS += technical/send-pack-pipeline TECH_DOCS += technical/shallow +TECH_DOCS += technical/sparse-checkout +TECH_DOCS += technical/sparse-index TECH_DOCS += technical/trivial-merge TECH_DOCS += technical/unit-tests SP_ARTICLES += $(TECH_DOCS) diff --git a/Documentation/RelNotes/2.51.1.adoc b/Documentation/RelNotes/2.51.1.adoc new file mode 100644 index 0000000000..b8bd49c876 --- /dev/null +++ b/Documentation/RelNotes/2.51.1.adoc @@ -0,0 +1,99 @@ +Git 2.51.1 Release Notes +======================== + +There shouldn't be anything exciting to see here. This is primarily +to flush the "do you still use it?" improvements that has landed on +the master front, together with a handful of low-hanging, low-impact +fixes that should be safe. + + +Fixes since Git 2.51.0 +---------------------- + + * The "do you still use it?" message given by a command that is + deeply deprecated and allow us to suggest alternatives has been + updated. + + * The compatObjectFormat extension is used to hide an incomplete + feature that is not yet usable for any purpose other than + developing the feature further. Document it as such to discourage + its use by mere mortals. + + * Manual page for "gitk" is updated with the current maintainer's + name. + + * Update the instructions for using GGG in the MyFirstContribution + document to say that a GitHub PR could be made against `git/git` + instead of `gitgitgadget/git`. + + * Clang-format update to let our control macros be formatted the way we + had them traditionally, e.g., "for_each_string_list_item()" without + space before the parentheses. + + * A few places where a size_t value was cast to curl_off_t without + checking has been updated to use the existing helper function. + + * The start_delayed_progress() function in the progress eye-candy API + did not clear its internal state, making an initial delay value + larger than 1 second ineffective, which has been corrected. + + * Makefile tried to run multiple "cargo build" which would not work + very well; serialize their execution to work around this problem. + + * Adjust to the way newer versions of cURL selectively enable tracing + options, so that our tests can continue to work. + + * During interactive rebase, using 'drop' on a merge commit led to + an error, which has been corrected. + + * "git refs migrate" to migrate the reflog entries from a refs + backend to another had a handful of bugs squashed. + + * "git push" had a code path that led to BUG() but it should have + been a die(), as it is a response to a usual but invalid end-user + action to attempt pushing an object that does not exist. + + * Various bugs about rename handling in "ort" merge strategy have + been fixed. + + * "git diff --no-index" run inside a subdirectory under control of a + Git repository operated at the top of the working tree and stripped + the prefix from the output, and oddballs like "-" (stdin) did not + work correctly because of it. Correct the set-up by undoing what + the set-up sequence did to cwd and prefix. + + * Various options to "git diff" that make comparison ignore certain + aspects of the differences (like "space changes are ignored", + "differences in lines that match these regular expressions are + ignored") did not work well with "--name-only" and friends. + + * Under a race against another process that is repacking the + repository, especially a partially cloned one, "git fetch" may + mistakenly think some objects we do have are missing, which has + been corrected. + + * "git repack --path-walk" lost objects in some corner cases, which + has been corrected. + cf. <CABPp-BHFxxGrqKc0m==TjQNjDGdO=H5Rf6EFsf2nfE1=TuraOQ@mail.gmail.com> + + * Fixes multiple crashes around midx write-out codepaths. + + * A broken or malicious "git fetch" can say that it has the same + object for many many times, and the upload-pack serving it can + exhaust memory storing them redundantly, which has been corrected. + + * A corner case bug in "git log -L..." has been corrected. + + * Some among "git add -p" and friends ignored color.diff and/or + color.ui configuration variables, which is an old regression, which + has been corrected. + + * "git rebase -i" failed to clean-up the commit log message when the + command commits the final one in a chain of "fixup" commands, which + has been corrected. + + * Deal more gracefully with directory / file conflicts when the files + backend is used for ref storage, by failing only the ones that are + involved in the conflict while allowing others. + +Also contains various documentation updates, code cleanups and minor fixups. diff --git a/Documentation/RelNotes/2.52.0.adoc b/Documentation/RelNotes/2.52.0.adoc index b106483f42..55ee816d58 100644 --- a/Documentation/RelNotes/2.52.0.adoc +++ b/Documentation/RelNotes/2.52.0.adoc @@ -47,6 +47,14 @@ UI, Workflows & Features * "git fast-import" learned that "--signed-commits=<how>" option that corresponds to that of "git fast-export". + * Marking a hunk 'selected' in "git add -p" and then splitting made + all the split pieces 'selected'; this has been changed to make them + all 'undecided', which gives better end-user experience. + + * Configuration variables that take a pathname as a value + (e.g. blame.ignorerevsfile) can be marked as optional by prefixing + ":(optoinal)" before its value. + Performance, Internal Implementation, Development Support etc. -------------------------------------------------------------- @@ -92,7 +100,7 @@ Performance, Internal Implementation, Development Support etc. * CodingGuidelines now spells out how bitfields are to be written. - * Adjust to the way newer versions of cURL selectivel enables tracing + * Adjust to the way newer versions of cURL selectively enable tracing options, so that our tests can continue to work. (merge 1b5a6bfff3 jk/curl-global-trace-components later to maint). @@ -113,6 +121,18 @@ Performance, Internal Implementation, Development Support etc. documentation, similar to "make doc". (merge ff4ec8ded0 ps/meson-build-docs later to maint). + * Dip our toes a bit to (optionally) use Rust implemented helper + called from our C code. + + * Documentation for "git log --pretty" options has been updated + to make it easier to translate. + + * Instead of three library archives (one for git, one for reftable, + and one for xdiff), roll everything into a single libgit.a archive. + This would help later effort to FFI into Rust. + + * The beginning of SHA1-SHA256 interoperability work. + Fixes since v2.51 ----------------- @@ -162,6 +182,10 @@ including security updates, are included in this release. ignored") did not work well with "--name-only" and friends. (merge b55e6d36eb ly/diff-name-only-with-diff-from-content later to maint). + * The above caused regressions, which has been corrected. + (merge 623f7af2 jk/diff-from-contents-fix later to maint). + (merge 3da4413d jc/diff-from-contents-fix later to maint). + * Documentation for "git rebase" has been updated. (merge 3f7f2b0359 je/doc-rebase later to maint). @@ -198,13 +222,13 @@ including security updates, are included in this release. name. (merge bcb20dda83 js/doc-gitk-history later to maint). - * Update the instruction to use of GGG in the MyFirstContribution + * Update the instructions for using GGG in the MyFirstContribution document to say that a GitHub PR could be made against `git/git` instead of `gitgitgadget/git`. (merge 37001cdbc4 ds/doc-ggg-pr-fork-clarify later to maint). * Makefile tried to run multiple "cargo build" which would not work - very well; serialize their execution to work it around. + very well; serialize their execution to work around this problem. (merge 0eeacde50e da/cargo-serialize later to maint). * "git repack --path-walk" lost objects in some corner cases, which @@ -280,6 +304,54 @@ including security updates, are included in this release. updated. (merge 54a60e5b38 kh/you-still-use-whatchanged-fix later to maint). + * Clang-format update to let our control macros be formatted the way we + had them traditionally, e.g., "for_each_string_list_item()" without + space before the parentheses. + (merge 3721541d35 jt/clang-format-foreach-wo-space-before-parenthesis later to maint). + + * A few places where a size_t value was cast to curl_off_t without + checking has been updated to use the existing helper function. + (merge ecc5749578 js/curl-off-t-fixes later to maint). + + * "git reflog write" did not honor the configured user.name/email + which has been corrected. + + * Handling of an empty subdirectory of .git/refs/ in the ref-files + backend has been corrected. + + * Our CI script requires "sudo" that can be told to preserve + environment, but Ubuntu replaced with "sudo" with an implementation + that lacks the feature. Work this around by reinstalling the + original version. + (merge fddb484255 ps/ci-avoid-broken-sudo-on-ubuntu later to maint). + + * The reftable backend learned to sanity check its on-disk data more + carefully. + (merge 466a3a1afd kn/reftable-consistency-checks later to maint). + + * A lot of code clean-up of xdiff. + Split out of a larger topic. + (merge 8b9c5d2e3a en/xdiff-cleanup later to maint). + + * "git format-patch --range-diff=... --notes=..." did not drive the + underlying range-diff with correct --notes parameter, ending up + comparing with different set of notes from its main patch output + you would get from "git format-patch --notes=..." for a singleton + patch. + + * The code in "git add -p" and friends to iterate over hunks was + riddled with bugs, which has been corrected. + + * A few more things that patch authors can do to help maintainer to + keep track of their topics better. + (merge 1a41698841 tb/doc-submitting-patches later to maint). + + * An earlier addition to "git diff --no-index A B" to limit the + output with pathspec after the two directories misbehaved when + these directories were given with a trailing slash, which has been + corrected. + (merge c0bec06cfe jk/diff-no-index-with-pathspec-fix later to maint). + * Other code cleanup, docfix, build fix, etc. (merge 823d537fa7 kh/doc-git-log-markup-fix later to maint). (merge cf7efa4f33 rj/t6137-cygwin-fix later to maint). @@ -305,3 +377,14 @@ including security updates, are included in this release. (merge ac7096723b jc/doc-includeif-hasconfig-remote-url-fix later to maint). (merge fafc9b08b8 ag/doc-sendmail-gmail-example-update later to maint). (merge a66fc22bf9 rs/get-oid-with-flags-cleanup later to maint). + (merge e1d062e8ba ps/odb-clean-stale-wrappers later to maint). + (merge fdd21ba116 mh/doc-credential-url-prefix later to maint). + (merge 1c573a3451 en/doc-merge-tree-describe-merge-base later to maint). + (merge 84a6bf7965 ja/doc-markup-attached-paragraph-fix later to maint). + (merge 399694384b kh/doc-patch-id-markup-fix later to maint). + (merge 15b8abde07 js/mingw-includes-cleanup later to maint). + (merge 3860985105 js/unreachable-workaround-for-no-symlink-head later to maint). + (merge b3ac6e737d kh/doc-continued-paragraph-fix later to maint). + (merge 2cebca0582 tb/cat-file-objectmode-update later to maint). + (merge 96978d7545 js/ci-github-actions-update later to maint). + (merge 0c4f1346ca so/t2401-use-test-path-helpers later to maint). diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 86ca7f6a78..d620bd93bd 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -579,14 +579,27 @@ line via `git format-patch --notes`. [[the-topic-summary]] *This is EXPERIMENTAL*. -When sending a topic, you can propose a one-paragraph summary that -should appear in the "What's cooking" report when it is picked up to -explain the topic. If you choose to do so, please write a 2-5 line -paragraph that will fit well in our release notes (see many bulleted -entries in the Documentation/RelNotes/* files for examples), and make -it the first paragraph of the cover letter. For a single-patch -series, use the space between the three-dash line and the diffstat, as -described earlier. +When sending a topic, you can optionally propose a topic name and/or a +one-paragraph summary that should appear in the "What's cooking" +report when it is picked up to explain the topic. If you choose to do +so, please write a 2-5 line paragraph that will fit well in our +release notes (see many bulleted entries in the +Documentation/RelNotes/* files for examples), and make it the first +(or second, if including a suggested topic name) paragraph of the +cover letter. If suggesting a topic name, use the format +"XX/your-topic-name", where "XX" is a stand-in for the primary +author's initials, and "your-topic-name" is a brief, dash-delimited +description of what your topic does. For a single-patch series, use +the space between the three-dash line and the diffstat, as described +earlier. + +[[multi-series-efforts]] +If your patch series is part of a larger effort spanning multiple +patch series, briefly describe the broader goal, and state where the +current series fits into that goal. If you are suggesting a topic +name as in <<the-topic-summary, section above>>, consider +"XX/the-broader-goal-part-one", "XX/the-broader-goal-part-two", and so +on. [[attachment]] Do not attach the patch as a MIME attachment, compressed or not. diff --git a/Documentation/config.adoc b/Documentation/config.adoc index 05f1ca7293..62eebe7c54 100644 --- a/Documentation/config.adoc +++ b/Documentation/config.adoc @@ -357,7 +357,9 @@ compiled without runtime prefix support, the compiled-in prefix will be substituted instead. In the unlikely event that a literal path needs to be specified that should _not_ be expanded, it needs to be prefixed by `./`, like so: `./%(prefix)/bin`. - ++ +If prefixed with `:(optional)`, the configuration variable is treated +as if it does not exist, if the named path does not exist. Variables ~~~~~~~~~ diff --git a/Documentation/config/core.adoc b/Documentation/config/core.adoc index 08739bb9d4..e2de270c86 100644 --- a/Documentation/config/core.adoc +++ b/Documentation/config/core.adoc @@ -75,8 +75,8 @@ The built-in file system monitor is currently available only on a limited set of supported platforms. Currently, this includes Windows and MacOS. + - Otherwise, this variable contains the pathname of the "fsmonitor" - hook command. +Otherwise, this variable contains the pathname of the "fsmonitor" +hook command. + This hook command is used to identify all files that may have changed since the requested date/time. This information is used to speed up diff --git a/Documentation/config/extensions.adoc b/Documentation/config/extensions.adoc index 829f2523fc..532456644b 100644 --- a/Documentation/config/extensions.adoc +++ b/Documentation/config/extensions.adoc @@ -3,8 +3,7 @@ extensions.*:: `core.repositoryFormatVersion` is not `1`. See linkgit:gitrepository-layout[5]. + --- -compatObjectFormat:: +compatObjectFormat::: Specify a compatibility hash algorithm to use. The acceptable values are `sha1` and `sha256`. The value specified must be different from the value of `extensions.objectFormat`. This allows client level @@ -19,18 +18,18 @@ Note that the functionality enabled by this extension is incomplete and subject to change. It currently exists only to allow development and testing of the underlying feature and is not designed to be enabled by end users. -noop:: +noop::: This extension does not change git's behavior at all. It is useful only for testing format-1 compatibility. + For historical reasons, this extension is respected regardless of the `core.repositoryFormatVersion` setting. -noop-v1:: +noop-v1::: This extension does not change git's behavior at all. It is useful only for testing format-1 compatibility. -objectFormat:: +objectFormat::: Specify the hash algorithm to use. The acceptable values are `sha1` and `sha256`. If not specified, `sha1` is assumed. + @@ -38,7 +37,7 @@ Note that this setting should only be set by linkgit:git-init[1] or linkgit:git-clone[1]. Trying to change it after initialization will not work and will produce hard-to-diagnose issues. -partialClone:: +partialClone::: When enabled, indicates that the repo was created with a partial clone (or later performed a partial fetch) and that the remote may have omitted sending certain unwanted objects. Such a remote is called a @@ -50,30 +49,31 @@ The value of this key is the name of the promisor remote. For historical reasons, this extension is respected regardless of the `core.repositoryFormatVersion` setting. -preciousObjects:: +preciousObjects::: If enabled, indicates that objects in the repository MUST NOT be deleted (e.g., by `git-prune` or `git repack -d`). + For historical reasons, this extension is respected regardless of the `core.repositoryFormatVersion` setting. -refStorage:: +refStorage::: Specify the ref storage format to use. The acceptable values are: + +-- include::../ref-storage-format.adoc[] - +-- + Note that this setting should only be set by linkgit:git-init[1] or linkgit:git-clone[1]. Trying to change it after initialization will not work and will produce hard-to-diagnose issues. -relativeWorktrees:: +relativeWorktrees::: If enabled, indicates at least one worktree has been linked with relative paths. Automatically set if a worktree has been created or repaired with either the `--relative-paths` option or with the `worktree.useRelativePaths` config set to `true`. -worktreeConfig:: +worktreeConfig::: If enabled, then worktrees will load config settings from the `$GIT_DIR/config.worktree` file in addition to the `$GIT_COMMON_DIR/config` file. Note that `$GIT_COMMON_DIR` and @@ -87,11 +87,12 @@ When enabling this extension, you must be careful to move certain values from the common config file to the main working tree's `config.worktree` file, if present: + +-- * `core.worktree` must be moved from `$GIT_COMMON_DIR/config` to `$GIT_COMMON_DIR/config.worktree`. * If `core.bare` is true, then it must be moved from `$GIT_COMMON_DIR/config` to `$GIT_COMMON_DIR/config.worktree`. - +-- + It may also be beneficial to adjust the locations of `core.sparseCheckout` and `core.sparseCheckoutCone` depending on your desire for customizable @@ -104,4 +105,3 @@ details. + For historical reasons, this extension is respected regardless of the `core.repositoryFormatVersion` setting. --- diff --git a/Documentation/config/stash.adoc b/Documentation/config/stash.adoc index e556105a15..a1197ffd7d 100644 --- a/Documentation/config/stash.adoc +++ b/Documentation/config/stash.adoc @@ -1,19 +1,32 @@ -stash.index:: +ifndef::git-stash[] +:see-show: See the description of the 'show' command in linkgit:git-stash[1]. +endif::git-stash[] + +ifdef::git-stash[] +:see-show: +endif::git-stash[] + +`stash.index`:: If this is set to true, `git stash apply` and `git stash pop` will - behave as if `--index` was supplied. Defaults to false. See the - descriptions in linkgit:git-stash[1]. + behave as if `--index` was supplied. Defaults to false. +ifndef::git-stash[] +See the descriptions in linkgit:git-stash[1]. ++ +This also affects invocations of linkgit:git-stash[1] via `--autostash` from +commands like linkgit:git-merge[1], linkgit:git-rebase[1], and +linkgit:git-pull[1]. +endif::git-stash[] -stash.showIncludeUntracked:: +`stash.showIncludeUntracked`:: If this is set to true, the `git stash show` command will show - the untracked files of a stash entry. Defaults to false. See - the description of the 'show' command in linkgit:git-stash[1]. + the untracked files of a stash entry. Defaults to false. {see-show} -stash.showPatch:: +`stash.showPatch`:: If this is set to true, the `git stash show` command without an option will show the stash entry in patch form. Defaults to false. - See the description of the 'show' command in linkgit:git-stash[1]. + {see-show} -stash.showStat:: +`stash.showStat`:: If this is set to true, the `git stash show` command without an option will show a diffstat of the stash entry. Defaults to true. - See the description of the 'show' command in linkgit:git-stash[1]. + {see-show} diff --git a/Documentation/config/tag.adoc b/Documentation/config/tag.adoc index 5062a057ff..d878da98d4 100644 --- a/Documentation/config/tag.adoc +++ b/Documentation/config/tag.adoc @@ -1,17 +1,23 @@ -tag.forceSignAnnotated:: +`tag.forceSignAnnotated`:: A boolean to specify whether annotated tags created should be GPG signed. If `--annotate` is specified on the command line, it takes precedence over this option. -tag.sort:: - This variable controls the sort ordering of tags when displayed by - linkgit:git-tag[1]. Without the "--sort=<value>" option provided, the - value of this variable will be used as the default. +`tag.sort`:: +ifdef::git-tag[] +This variable controls the sort ordering of tags when displayed by `git-tag`. +endif::git-tag[] +ifndef::git-tag[] +This variable controls the sort ordering of tags when displayed by +linkgit:git-tag[1]. +endif::git-tag[] +Without the `--sort=<value>` option provided, the value of this variable will +be used as the default. -tag.gpgSign:: +`tag.gpgSign`:: A boolean to specify whether all tags should be GPG signed. Use of this option when running in an automated script can result in a large number of tags being signed. It is therefore - convenient to use an agent to avoid typing your gpg passphrase + convenient to use an agent to avoid typing your GPG passphrase several times. Note that this option doesn't affect tag signing - behavior enabled by "-u <keyid>" or "--local-user=<keyid>" options. + behavior enabled by `-u <keyid>` or `--local-user=<keyid>` options. diff --git a/Documentation/config/worktree.adoc b/Documentation/config/worktree.adoc index 9e3f84f748..a248076ea5 100644 --- a/Documentation/config/worktree.adoc +++ b/Documentation/config/worktree.adoc @@ -1,4 +1,4 @@ -worktree.guessRemote:: +`worktree.guessRemote`:: If no branch is specified and neither `-b` nor `-B` nor `--detach` is used, then `git worktree add` defaults to creating a new branch from HEAD. If `worktree.guessRemote` is @@ -6,14 +6,14 @@ worktree.guessRemote:: branch whose name uniquely matches the new branch name. If such a branch exists, it is checked out and set as "upstream" for the new branch. If no such match can be found, it falls - back to creating a new branch from the current HEAD. + back to creating a new branch from the current `HEAD`. -worktree.useRelativePaths:: - Link worktrees using relative paths (when "true") or absolute - paths (when "false"). This is particularly useful for setups +`worktree.useRelativePaths`:: + Link worktrees using relative paths (when "`true`") or absolute + paths (when "`false`"). This is particularly useful for setups where the repository and worktrees may be moved between - different locations or environments. Defaults to "false". + different locations or environments. Defaults to "`false`". + -Note that setting `worktree.useRelativePaths` to "true" implies enabling the +Note that setting `worktree.useRelativePaths` to "`true`" implies enabling the `extensions.relativeWorktrees` config (see linkgit:git-config[1]), thus making it incompatible with older versions of Git. diff --git a/Documentation/fsck-msgids.adoc b/Documentation/fsck-msgids.adoc index 0ba4f9a27e..acac9683af 100644 --- a/Documentation/fsck-msgids.adoc +++ b/Documentation/fsck-msgids.adoc @@ -10,6 +10,12 @@ `badFilemode`:: (INFO) A tree contains a bad filemode entry. +`badGpgsig`:: + (ERROR) A tag contains a bad (truncated) signature (e.g., `gpgsig`) header. + +`badHeaderContinuation`:: + (ERROR) A continuation header (such as for `gpgsig`) is unexpectedly truncated. + `badName`:: (ERROR) An author/committer name is empty. @@ -38,6 +44,9 @@ `badReferentName`:: (ERROR) The referent name of a symref is invalid. +`badReftableTableName`:: + (WARN) A reftable table has an invalid name. + `badTagName`:: (INFO) A tag has an invalid format. @@ -104,9 +113,6 @@ `gitmodulesParse`:: (INFO) Could not parse `.gitmodules` blob. -`gitmodulesLarge`; - (ERROR) `.gitmodules` blob is too large to parse. - `gitmodulesPath`:: (ERROR) `.gitmodules` path is invalid. diff --git a/Documentation/git-config.adoc b/Documentation/git-config.adoc index 36d2845152..cc054fa7e1 100644 --- a/Documentation/git-config.adoc +++ b/Documentation/git-config.adoc @@ -117,15 +117,15 @@ OPTIONS --comment <message>:: Append a comment at the end of new or modified lines. - - If _<message>_ begins with one or more whitespaces followed - by "#", it is used as-is. If it begins with "#", a space is - prepended before it is used. Otherwise, a string " # " (a - space followed by a hash followed by a space) is prepended - to it. And the resulting string is placed immediately after - the value defined for the variable. The _<message>_ must - not contain linefeed characters (no multi-line comments are - permitted). ++ +If _<message>_ begins with one or more whitespaces followed +by "#", it is used as-is. If it begins with "#", a space is +prepended before it is used. Otherwise, a string " # " (a +space followed by a hash followed by a space) is prepended +to it. And the resulting string is placed immediately after +the value defined for the variable. The _<message>_ must +not contain linefeed characters (no multi-line comments are +permitted). --all:: With `get`, return all values for a multi-valued key. diff --git a/Documentation/git-merge-tree.adoc b/Documentation/git-merge-tree.adoc index 271ab220e8..4391bbee47 100644 --- a/Documentation/git-merge-tree.adoc +++ b/Documentation/git-merge-tree.adoc @@ -79,11 +79,17 @@ OPTIONS --merge-base=<tree-ish>:: Instead of finding the merge-bases for <branch1> and <branch2>, - specify a merge-base for the merge, and specifying multiple bases is - currently not supported. This option is incompatible with `--stdin`. + specify a merge-base for the merge. This option is incompatible with + `--stdin`. + -As the merge-base is provided directly, <branch1> and <branch2> do not need -to specify commits; trees are enough. +Specifying multiple bases is currently not supported, which means that when +merging two branches with more than one merge-base, using this option may +cause merge results to differ from what `git merge` would compute. This +can include potentially losing some changes made on one side of the history +in the resulting merge. ++ +With this option, since the merge-base is provided directly, <branch1> and +<branch2> do not need to specify commits; trees are enough. -X<option>:: --strategy-option=<option>:: diff --git a/Documentation/git-patch-id.adoc b/Documentation/git-patch-id.adoc index 1d15fa45d5..45da0f27ac 100644 --- a/Documentation/git-patch-id.adoc +++ b/Documentation/git-patch-id.adoc @@ -33,27 +33,30 @@ OPTIONS --verbatim:: Calculate the patch-id of the input as it is given, do not strip any whitespace. - - This is the default if patchid.verbatim is true. ++ +This is the default if patchid.verbatim is true. --stable:: Use a "stable" sum of hashes as the patch ID. With this option: - - Reordering file diffs that make up a patch does not affect the ID. - In particular, two patches produced by comparing the same two trees - with two different settings for "-O<orderfile>" result in the same - patch ID signature, thereby allowing the computed result to be used - as a key to index some meta-information about the change between - the two trees; - - - Result is different from the value produced by git 1.9 and older - or produced when an "unstable" hash (see --unstable below) is - configured - even when used on a diff output taken without any use - of "-O<orderfile>", thereby making existing databases storing such - "unstable" or historical patch-ids unusable. - - - All whitespace within the patch is ignored and does not affect the id. - - This is the default if patchid.stable is set to true. ++ +-- +- Reordering file diffs that make up a patch does not affect the ID. + In particular, two patches produced by comparing the same two trees + with two different settings for "-O<orderfile>" result in the same + patch ID signature, thereby allowing the computed result to be used + as a key to index some meta-information about the change between + the two trees; + +- Result is different from the value produced by git 1.9 and older + or produced when an "unstable" hash (see --unstable below) is + configured - even when used on a diff output taken without any use + of "-O<orderfile>", thereby making existing databases storing such + "unstable" or historical patch-ids unusable. + +- All whitespace within the patch is ignored and does not affect the id. +-- ++ +This is the default if patchid.stable is set to true. --unstable:: Use an "unstable" hash as the patch ID. With this option, @@ -61,8 +64,8 @@ OPTIONS by git 1.9 and older and whitespace is ignored. Users with pre-existing databases storing patch-ids produced by git 1.9 and older (who do not deal with reordered patches) may want to use this option. - - This is the default. ++ +This is the default. GIT --- diff --git a/Documentation/git-pull.adoc b/Documentation/git-pull.adoc index 48e924a10a..cd3bbc90e3 100644 --- a/Documentation/git-pull.adoc +++ b/Documentation/git-pull.adoc @@ -15,68 +15,54 @@ SYNOPSIS DESCRIPTION ----------- -Incorporates changes from a remote repository into the current branch. -If the current branch is behind the remote, then by default it will -fast-forward the current branch to match the remote. If the current -branch and the remote have diverged, the user needs to specify how to -reconcile the divergent branches with `--rebase` or `--no-rebase` (or -the corresponding configuration option in `pull.rebase`). - -More precisely, `git pull` runs `git fetch` with the given parameters -and then depending on configuration options or command line flags, -will call either `git rebase` or `git merge` to reconcile diverging -branches. - -<repository> should be the name of a remote repository as -passed to linkgit:git-fetch[1]. <refspec> can name an -arbitrary remote ref (for example, the name of a tag) or even -a collection of refs with corresponding remote-tracking branches -(e.g., refs/heads/{asterisk}:refs/remotes/origin/{asterisk}), -but usually it is the name of a branch in the remote repository. - -Default values for <repository> and <branch> are read from the -"remote" and "merge" configuration for the current branch -as set by linkgit:git-branch[1] `--track`. - -Assume the following history exists and the current branch is -"`master`": +Integrate changes from a remote repository into the current branch. ------------- - A---B---C master on origin - / - D---E---F---G master - ^ - origin/master in your repository ------------- +First, `git pull` runs `git fetch` with the same arguments +(excluding merge options) to fetch remote branch(es). +Then it decides which remote branch to integrate: if you run `git pull` +with no arguments this defaults to the <<UPSTREAM-BRANCHES,upstream>> +for the current branch. +Then it integrates that branch into the current branch. -Then "`git pull`" will fetch and replay the changes from the remote -`master` branch since it diverged from the local `master` (i.e., `E`) -until its current commit (`C`) on top of `master` and record the -result in a new commit along with the names of the two parent commits -and a log message from the user describing the changes. - ------------- - A---B---C origin/master - / \ - D---E---F---G---H master ------------- +There are 4 main options for integrating the remote branch: -See linkgit:git-merge[1] for details, including how conflicts -are presented and handled. +1. `git pull --ff-only` will only do "fast-forward" updates: it + fails if your local branch has diverged from the remote branch. + This is the default. +2. `git pull --rebase` runs `git rebase` +3. `git pull --no-rebase` runs `git merge`. +4. `git pull --squash` runs `git merge --squash` -In Git 1.7.0 or later, to cancel a conflicting merge, use -`git reset --merge`. *Warning*: In older versions of Git, running 'git pull' -with uncommitted changes is discouraged: while possible, it leaves you -in a state that may be hard to back out of in the case of a conflict. +You can also set the configuration options `pull.rebase`, `pull.squash`, +or `pull.ff` with your preferred behaviour. -If any of the remote changes overlap with local uncommitted changes, -the merge will be automatically canceled and the work tree untouched. -It is generally best to get any local changes in working order before -pulling or stash them away with linkgit:git-stash[1]. +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`. OPTIONS ------- +<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). ++ +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>:: + 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" +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:: This is passed to both underlying git-fetch to squelch reporting of @@ -145,6 +131,7 @@ include::urls-remotes.adoc[] include::merge-strategies.adoc[] +[[DEFAULT-BEHAVIOUR]] DEFAULT BEHAVIOUR ----------------- diff --git a/Documentation/git-push.adoc b/Documentation/git-push.adoc index 5f5408e2c0..864b0d0467 100644 --- a/Documentation/git-push.adoc +++ b/Documentation/git-push.adoc @@ -19,30 +19,35 @@ SYNOPSIS DESCRIPTION ----------- -Updates remote refs using local refs, while sending objects -necessary to complete the given refs. +Updates one or more branches, tags, or other references in a remote +repository from your local repository, and sends all necessary data +that isn't already on the remote. -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]. +The simplest way to push is `git push <remote> <branch>`. +`git push origin main` will push the local `main` branch to the `main` +branch on the remote named `origin`. -When the command line does not specify where to push with the -`<repository>` argument, `branch.*.remote` configuration for the -current branch is consulted to determine where to push. If the -configuration is missing, it defaults to 'origin'. +The `<repository>` argument defaults to the upstream for the current branch, +or `origin` if there's no configured upstream. -When the command line does not specify what to push with `<refspec>...` -arguments or `--all`, `--mirror`, `--tags` options, the command finds -the default `<refspec>` by consulting `remote.*.push` configuration, -and if it is not found, honors `push.default` configuration to decide -what to push (See linkgit:git-config[1] for the meaning of `push.default`). +To decide which branches, tags, or other refs to push, Git uses +(in order of precedence): -When neither the command-line nor the configuration specifies what to -push, the default behavior is used, which corresponds to the `simple` -value for `push.default`: the current branch is pushed to the -corresponding upstream branch, but as a safety measure, the push is -aborted if the upstream branch does not have the same name as the -local one. +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 +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`. + +`git push` may fail if you haven't set an upstream for the current branch, +depending on what `push.default` is set to. +See the <<UPSTREAM-BRANCHES,UPSTREAM BRANCHES>> section below for more +on how to set and use upstreams. + +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]] @@ -55,96 +60,66 @@ OPTIONS[[OPTIONS]] <refspec>...:: Specify what destination ref to update with what source object. - The format of a <refspec> parameter is an optional plus - `+`, followed by the source object <src>, followed - by a colon `:`, followed by the destination ref <dst>. -+ -The <src> is often the name of the branch you would want to push, but -it can be any arbitrary "SHA-1 expression", such as `master~4` or -`HEAD` (see linkgit:gitrevisions[7]). -+ -The <dst> tells which ref on the remote side is updated with this -push. Arbitrary expressions cannot be used here, an actual ref must -be named. -If `git push [<repository>]` without any `<refspec>` argument is set to -update some ref at the destination with `<src>` with -`remote.<repository>.push` configuration variable, `:<dst>` part can -be omitted--such a push will update a ref that `<src>` normally updates -without any `<refspec>` on the command line. Otherwise, missing -`:<dst>` means to update the same ref as the `<src>`. -+ -If <dst> doesn't start with `refs/` (e.g. `refs/heads/master`) we will -try to infer where in `refs/*` on the destination <repository> it -belongs based on the type of <src> being pushed and whether <dst> -is ambiguous. + --- -* If <dst> unambiguously refers to a ref on the <repository> remote, - then push to that ref. - -* If <src> resolves to a ref starting with refs/heads/ or refs/tags/, - then prepend that to <dst>. - -* Other ambiguity resolutions might be added in the future, but for - now any other cases will error out with an error indicating what we - tried, and depending on the `advice.pushUnqualifiedRefname` - configuration (see linkgit:git-config[1]) suggest what refs/ - namespace you may have wanted to push to. - --- -+ -The object referenced by <src> is used to update the <dst> reference -on the remote side. Whether this is allowed depends on where in -`refs/*` the <dst> reference lives as described in detail below, in -those sections "update" means any modifications except deletes, which -as noted after the next few sections are treated differently. -+ -The `refs/heads/*` namespace will only accept commit objects, and -updates only if they can be fast-forwarded. -+ -The `refs/tags/*` namespace will accept any kind of object (as -commits, trees and blobs can be tagged), and any updates to them will -be rejected. -+ -It's possible to push any type of object to any namespace outside of -`refs/{tags,heads}/*`. In the case of tags and commits, these will be -treated as if they were the commits inside `refs/heads/*` for the -purposes of whether the update is allowed. -+ -I.e. a fast-forward of commits and tags outside `refs/{tags,heads}/*` -is allowed, even in cases where what's being fast-forwarded is not a -commit, but a tag object which happens to point to a new commit which -is a fast-forward of the commit the last tag (or commit) it's -replacing. Replacing a tag with an entirely different tag is also -allowed, if it points to the same commit, as well as pushing a peeled -tag, i.e. pushing the commit that existing tag object points to, or a -new tag object which an existing commit points to. -+ -Tree and blob objects outside of `refs/{tags,heads}/*` will be treated -the same way as if they were inside `refs/tags/*`, any update of them -will be rejected. -+ -All of the rules described above about what's not allowed as an update -can be overridden by adding an the optional leading `+` to a refspec -(or using `--force` command line option). The only exception to this -is that no amount of forcing will make the `refs/heads/*` namespace -accept a non-commit object. Hooks and configuration can also override -or amend these rules, see e.g. `receive.denyNonFastForwards` in -linkgit:git-config[1] and `pre-receive` and `update` in -linkgit:githooks[5]. -+ -Pushing an empty <src> allows you to delete the <dst> ref from the -remote repository. Deletions are always accepted without a leading `+` -in the refspec (or `--force`), except when forbidden by configuration -or hooks. See `receive.denyDeletes` in linkgit:git-config[1] and -`pre-receive` and `update` in linkgit:githooks[5]. -+ -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. -+ -`tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`. +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 +any arbitrary "SHA-1 expression" (see linkgit:gitrevisions[7]). ++ +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`. ++ +You can write a refspec using the fully expanded form (for +example `refs/heads/main:refs/heads/main`) which specifies the exact source +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 + `main` expands to `main:refs/heads/main`. + * 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/`, + 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. + This works like a glob that matches any ref matching the pattern. + 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. + * A refspec starting with `^` is a negative refspec. + 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>`. + 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 + repository. For example, `git push origin :dev` will + delete the `dev` branch. + * `tag <tag>` expands to `refs/tags/<tag>:refs/tags/<tag>`. + This is technically a special syntax for `git push` and not a refspec, + since in `git push origin tag v1.0` the arguments `tag` and `v1.0` + are separate. + * If the refspec can't be expanded unambiguously, error out + with an error indicating what was tried, and depending + on the `advice.pushUnqualifiedRefname` configuration (see + linkgit:git-config[1]) suggest what refs/ namespace you may have + wanted to push to. + +Not all updates are allowed: see PUSH RULES below for the details. --all:: --branches:: @@ -335,14 +310,12 @@ allowing a forced update. -f:: --force:: - Usually, the command refuses to update a remote ref that is - not an ancestor of the local ref used to overwrite it. - Also, when `--force-with-lease` option is used, the command refuses - to update a remote ref whose current value does not match - what is expected. + Usually, `git push` will refuse to update a branch that is not an + ancestor of the commit being pushed. + -This flag disables these checks, and can cause the remote repository -to lose commits; use it with care. +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 +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 @@ -514,6 +487,45 @@ reason:: refs, no explanation is needed. For a failed ref, the reason for failure is described. +PUSH RULES +---------- + +As a safety feature, the `git push` command only allows certain kinds of +updates to prevent you from accidentally losing data on the remote. + +Because branches and tags are intended to be used differently, the +safety rules for pushing to a branch are different from the rules +for pushing to a tag. In the following rules "update" means any +modifications except deletions and creations. Deletions and creations +are always allowed, except when forbidden by configuration or hooks. + +1. If the push destination is a **branch** (`refs/heads/*`): only + fast-forward updates are allowed, which means the destination must be + an ancestor of the source commit. The source must be a commit. +2. If the push destination is a **tag** (`refs/tags/*`): all updates will + be rejected. The source can be any object. +3. If the push destination is not a branch or tag: + * If the source is a tree or blob object, any updates will be rejected + * If the source is a tag or commit object, any fast-forward update + is allowed, even in cases where what's being fast-forwarded is not a + commit, but a tag object which happens to point to a new commit which + is a fast-forward of the commit the last tag (or commit) it's + replacing. Replacing a tag with an entirely different tag is also + allowed, if it points to the same commit, as well as pushing a peeled + tag, i.e. pushing the commit that existing tag object points to, or a + new tag object which an existing commit points to. + +You can override these rules by passing `--force` or by adding the +optional leading `+` to a refspec. The only exceptions are that no +amount of forcing will make a branch accept a non-commit object, +and forcing won't make the remote repository accept a push that it's +configured to deny. + +Hooks and configuration can also override or amend these rules, +see e.g. `receive.denyNonFastForwards` and `receive.denyDeletes` +in linkgit:git-config[1] and `pre-receive` and `update` in +linkgit:githooks[5]. + NOTE ABOUT FAST-FORWARDS ------------------------ @@ -703,6 +715,7 @@ a `git gc` command on the origin repository. include::transfer-data-leaks.adoc[] +[[CONFIGURATION]] CONFIGURATION ------------- diff --git a/Documentation/git-rev-parse.adoc b/Documentation/git-rev-parse.adoc index cc32b4b4f0..5398691f3f 100644 --- a/Documentation/git-rev-parse.adoc +++ b/Documentation/git-rev-parse.adoc @@ -174,13 +174,13 @@ for another option. Allow oids to be input from any object format that the current repository supports. - - Specifying "sha1" translates if necessary and returns a sha1 oid. - - Specifying "sha256" translates if necessary and returns a sha256 oid. - - Specifying "storage" translates if necessary and returns an oid in - encoded in the storage hash algorithm. ++ +Specifying "sha1" translates if necessary and returns a sha1 oid. ++ +Specifying "sha256" translates if necessary and returns a sha256 oid. ++ +Specifying "storage" translates if necessary and returns an oid in +encoded in the storage hash algorithm. Options for Objects ~~~~~~~~~~~~~~~~~~~ @@ -324,11 +324,12 @@ The following options are unaffected by `--path-format`: path of the current directory relative to the top-level directory. ---show-object-format[=(storage|input|output)]:: - Show the object format (hash algorithm) used for the repository - for storage inside the `.git` directory, input, or output. For - input, multiple algorithms may be printed, space-separated. - If not specified, the default is "storage". +--show-object-format[=(storage|input|output|compat)]:: + Show the object format (hash algorithm) used for the repository for storage + inside the `.git` directory, input, output, or compatibility. For input, + multiple algorithms may be printed, space-separated. If `compat` is + requested and no compatibility algorithm is enabled, prints an empty line. If + not specified, the default is "storage". --show-ref-format:: Show the reference storage format used for the repository. diff --git a/Documentation/git-shortlog.adoc b/Documentation/git-shortlog.adoc index d8ab38dcc1..aa92800c69 100644 --- a/Documentation/git-shortlog.adoc +++ b/Documentation/git-shortlog.adoc @@ -44,8 +44,8 @@ OPTIONS describe each commit. '<format>' can be any string accepted by the `--format` option of 'git log', such as '* [%h] %s'. (See the "PRETTY FORMATS" section of linkgit:git-log[1].) - - Each pretty-printed commit will be rewrapped before it is shown. ++ +Each pretty-printed commit will be rewrapped before it is shown. --date=<format>:: Show dates formatted according to the given date string. (See diff --git a/Documentation/git-sparse-checkout.adoc b/Documentation/git-sparse-checkout.adoc index 529a8edd9c..b5fe5da041 100644 --- a/Documentation/git-sparse-checkout.adoc +++ b/Documentation/git-sparse-checkout.adoc @@ -264,34 +264,50 @@ patterns in non-cone mode has a number of shortcomings: inconsistent. * It has edge cases where the "right" behavior is unclear. Two examples: - - First, two users are in a subdirectory, and the first runs - git sparse-checkout set '/toplevel-dir/*.c' - while the second runs - git sparse-checkout set relative-dir - Should those arguments be transliterated into - current/subdirectory/toplevel-dir/*.c - and - current/subdirectory/relative-dir - before inserting into the sparse-checkout file? The user who typed - the first command is probably aware that arguments to set/add are - supposed to be patterns in non-cone mode, and probably would not be - happy with such a transliteration. However, many gitignore-style - patterns are just paths, which might be what the user who typed the - second command was thinking, and they'd be upset if their argument - wasn't transliterated. - - Second, what should bash-completion complete on for set/add commands - for non-cone users? If it suggests paths, is it exacerbating the - problem above? Also, if it suggests paths, what if the user has a - file or directory that begins with either a '!' or '#' or has a '*', - '\', '?', '[', or ']' in its name? And if it suggests paths, will - it complete "/pro" to "/proc" (in the root filesystem) rather than to - "/progress.txt" in the current directory? (Note that users are - likely to want to start paths with a leading '/' in non-cone mode, - for the same reason that .gitignore files often have one.) - Completing on files or directories might give nasty surprises in - all these cases. ++ +First, two users are in a subdirectory, and the first runs ++ +---- +git sparse-checkout set '/toplevel-dir/*.c' +---- ++ +while the second runs ++ +---- +git sparse-checkout set relative-dir +---- ++ +Should those arguments be transliterated into ++ +---- +current/subdirectory/toplevel-dir/*.c +---- ++ +and ++ +---- +current/subdirectory/relative-dir +---- ++ +before inserting into the sparse-checkout file? The user who typed +the first command is probably aware that arguments to set/add are +supposed to be patterns in non-cone mode, and probably would not be +happy with such a transliteration. However, many gitignore-style +patterns are just paths, which might be what the user who typed the +second command was thinking, and they'd be upset if their argument +wasn't transliterated. ++ +Second, what should bash-completion complete on for set/add commands +for non-cone users? If it suggests paths, is it exacerbating the +problem above? Also, if it suggests paths, what if the user has a +file or directory that begins with either a '!' or '#' or has a '*', +'\', '?', '[', or ']' in its name? And if it suggests paths, will +it complete "/pro" to "/proc" (in the root filesystem) rather than to +"/progress.txt" in the current directory? (Note that users are +likely to want to start paths with a leading '/' in non-cone mode, +for the same reason that .gitignore files often have one.) +Completing on files or directories might give nasty surprises in +all these cases. * The excessive flexibility made other extensions essentially impractical. `--sparse-index` is likely impossible in non-cone diff --git a/Documentation/git-stash.adoc b/Documentation/git-stash.adoc index e2300a19a2..235d57ddd8 100644 --- a/Documentation/git-stash.adoc +++ b/Documentation/git-stash.adoc @@ -7,24 +7,24 @@ git-stash - Stash the changes in a dirty working directory away SYNOPSIS -------- -[verse] -'git stash' list [<log-options>] -'git stash' show [-u | --include-untracked | --only-untracked] [<diff-options>] [<stash>] -'git stash' drop [-q | --quiet] [<stash>] -'git stash' pop [--index] [-q | --quiet] [<stash>] -'git stash' apply [--index] [-q | --quiet] [<stash>] -'git stash' branch <branchname> [<stash>] -'git stash' [push [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-q | --quiet] +[synopsis] +git stash list [<log-options>] +git stash show [-u | --include-untracked | --only-untracked] [<diff-options>] [<stash>] +git stash drop [-q | --quiet] [<stash>] +git stash pop [--index] [-q | --quiet] [<stash>] +git stash apply [--index] [-q | --quiet] [<stash>] +git stash branch <branchname> [<stash>] +git stash [push [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-q | --quiet] [-u | --include-untracked] [-a | --all] [(-m | --message) <message>] [--pathspec-from-file=<file> [--pathspec-file-nul]] [--] [<pathspec>...]] -'git stash' save [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-q | --quiet] - [-u | --include-untracked] [-a | --all] [<message>] -'git stash' clear -'git stash' create [<message>] -'git stash' store [(-m | --message) <message>] [-q | --quiet] <commit> -'git stash' export (--print | --to-ref <ref>) [<stash>...] -'git stash' import <commit> +git stash save [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-q | --quiet] + [-u | --include-untracked] [-a | --all] [<message>] +git stash clear +git stash create [<message>] +git stash store [(-m | --message) <message>] [-q | --quiet] <commit> +git stash export (--print | --to-ref <ref>) [<stash>...] +git stash import <commit> DESCRIPTION ----------- @@ -38,7 +38,7 @@ The modifications stashed away by this command can be listed with `git stash list`, inspected with `git stash show`, and restored (potentially on top of a different commit) with `git stash apply`. Calling `git stash` without any arguments is equivalent to `git stash push`. -A stash is by default listed as "WIP on 'branchname' ...", but +A stash is by default listed as "WIP on '<branchname>' ...", but you can give a more descriptive message on the command line when you create one. @@ -47,16 +47,16 @@ stashes are found in the reflog of this reference and can be named using the usual reflog syntax (e.g. `stash@{0}` is the most recently created stash, `stash@{1}` is the one before it, `stash@{2.hours.ago}` is also possible). Stashes may also be referenced by specifying just the -stash index (e.g. the integer `n` is equivalent to `stash@{n}`). +stash index (e.g. the integer `<n>` is equivalent to `stash@{<n>}`). COMMANDS -------- -push [-p|--patch] [-S|--staged] [-k|--[no-]keep-index] [-u|--include-untracked] [-a|--all] [-q|--quiet] [(-m|--message) <message>] [--pathspec-from-file=<file> [--pathspec-file-nul]] [--] [<pathspec>...]:: +`push [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-u | --include-untracked] [ -a | --all] [-q | --quiet] [(-m|--message) <message>] [--pathspec-from-file=<file> [--pathspec-file-nul]] [--] [<pathspec>...]`:: Save your local modifications to a new 'stash entry' and roll them - back to HEAD (in the working tree and in the index). - The <message> part is optional and gives + back to `HEAD` (in the working tree and in the index). + The _<message>_ part is optional and gives the description along with the stashed state. + For quickly making a snapshot, you can omit "push". In this mode, @@ -65,14 +65,14 @@ subcommand from making an unwanted stash entry. The two exceptions to this are `stash -p` which acts as alias for `stash push -p` and pathspec elements, which are allowed after a double hyphen `--` for disambiguation. -save [-p|--patch] [-S|--staged] [-k|--[no-]keep-index] [-u|--include-untracked] [-a|--all] [-q|--quiet] [<message>]:: +`save [-p | --patch] [-S | --staged] [-k | --[no-]keep-index] [-u | --include-untracked] [-a | --all] [-q | --quiet] [<message>]`:: This option is deprecated in favour of 'git stash push'. It differs from "stash push" in that it cannot take pathspec. Instead, all non-option arguments are concatenated to form the stash message. -list [<log-options>]:: +`list [<log-options>]`:: List the stash entries that you currently have. Each 'stash entry' is listed with its name (e.g. `stash@{0}` is the latest entry, `stash@{1}` is @@ -88,7 +88,7 @@ stash@{1}: On master: 9cc0589... Add git-stash The command takes options applicable to the 'git log' command to control what is shown and how. See linkgit:git-log[1]. -show [-u|--include-untracked|--only-untracked] [<diff-options>] [<stash>]:: +`show [-u | --include-untracked | --only-untracked] [<diff-options>] [<stash>]`:: Show the changes recorded in the stash entry as a diff between the stashed contents and the commit back when the stash entry was first @@ -96,12 +96,12 @@ show [-u|--include-untracked|--only-untracked] [<diff-options>] [<stash>]:: By default, the command shows the diffstat, but it will accept any format known to 'git diff' (e.g., `git stash show -p stash@{1}` to view the second most recent entry in patch form). - If no `<diff-option>` is provided, the default behavior will be given + If no _<diff-option>_ is provided, the default behavior will be given by the `stash.showStat`, and `stash.showPatch` config variables. You can also use `stash.showIncludeUntracked` to set whether `--include-untracked` is enabled by default. -pop [--index] [-q|--quiet] [<stash>]:: +`pop [--index] [-q | --quiet] [<stash>]`:: Remove a single stashed state from the stash list and apply it on top of the current working tree state, i.e., do the inverse @@ -112,19 +112,19 @@ Applying the state can fail with conflicts; in this case, it is not removed from the stash list. You need to resolve the conflicts by hand and call `git stash drop` manually afterwards. -apply [--index] [-q|--quiet] [<stash>]:: +`apply [--index] [-q | --quiet] [<stash>]`:: Like `pop`, but do not remove the state from the stash list. Unlike `pop`, `<stash>` may be any commit that looks like a commit created by `stash push` or `stash create`. -branch <branchname> [<stash>]:: +`branch <branchname> [<stash>]`:: - Creates and checks out a new branch named `<branchname>` starting from - the commit at which the `<stash>` was originally created, applies the - changes recorded in `<stash>` to the new working tree and index. - If that succeeds, and `<stash>` is a reference of the form - `stash@{<revision>}`, it then drops the `<stash>`. + Creates and checks out a new branch named _<branchname>_ starting from + the commit at which the _<stash>_ was originally created, applies the + changes recorded in _<stash>_ to the new working tree and index. + If that succeeds, and _<stash>_ is a reference of the form + `stash@{<revision>}`, it then drops the _<stash>_. + This is useful if the branch on which you ran `git stash push` has changed enough that `git stash apply` fails due to conflicts. Since @@ -132,54 +132,51 @@ the stash entry is applied on top of the commit that was HEAD at the time `git stash` was run, it restores the originally stashed state with no conflicts. -clear:: +`clear`:: Remove all the stash entries. Note that those entries will then be subject to pruning, and may be impossible to recover (see - 'Examples' below for a possible strategy). - -drop [-q|--quiet] [<stash>]:: + 'EXAMPLES' below for a possible strategy). +`drop [-q | --quiet] [<stash>]`:: Remove a single stash entry from the list of stash entries. -create:: - +`create`:: Create a stash entry (which is a regular commit object) and return its object name, without storing it anywhere in the ref namespace. This is intended to be useful for scripts. It is probably not the command you want to use; see "push" above. -store:: +`store`:: Store a given stash created via 'git stash create' (which is a dangling merge commit) in the stash ref, updating the stash reflog. This is intended to be useful for scripts. It is probably not the command you want to use; see "push" above. -export ( --print | --to-ref <ref> ) [<stash>...]:: +`export ( --print | --to-ref <ref> ) [<stash>...]`:: Export the specified stashes, or all of them if none are specified, to a chain of commits which can be transferred using the normal fetch and push mechanisms, then imported using the `import` subcommand. -import <commit>:: - +`import <commit>`:: Import the specified stashes from the specified commit, which must have been created by `export`, and add them to the list of stashes. To replace the existing stashes, use `clear` first. OPTIONS ------- --a:: ---all:: +`-a`:: +`--all`:: This option is only valid for `push` and `save` commands. + All ignored and untracked files are also stashed and then cleaned up with `git clean`. --u:: ---include-untracked:: ---no-include-untracked:: +`-u`:: +`--include-untracked`:: +`--no-include-untracked`:: When used with the `push` and `save` commands, all untracked files are also stashed and then cleaned up with `git clean`. @@ -187,12 +184,12 @@ up with `git clean`. When used with the `show` command, show the untracked files in the stash entry as part of the diff. ---only-untracked:: +`--only-untracked`:: This option is only valid for the `show` command. + Show only the untracked files in the stash entry as part of the diff. ---index:: +`--index`:: This option is only valid for `pop` and `apply` commands. + Tries to reinstate not only the working tree's changes, but also @@ -200,15 +197,15 @@ the index's ones. However, this can fail, when you have conflicts (which are stored in the index, where you therefore can no longer apply the changes as they were originally). --k:: ---keep-index:: ---no-keep-index:: +`-k`:: +`--keep-index`:: +`--no-keep-index`:: This option is only valid for `push` and `save` commands. + All changes already added to the index are left intact. --p:: ---patch:: +`-p`:: +`--patch`:: This option is only valid for `push` and `save` commands. + Interactively select hunks from the diff between HEAD and the @@ -224,8 +221,8 @@ The `--patch` option implies `--keep-index`. You can use include::diff-context-options.adoc[] --S:: ---staged:: +`-S`:: +`--staged`:: This option is only valid for `push` and `save` commands. + Stash only the changes that are currently staged. This is similar to @@ -234,49 +231,49 @@ of current branch. + The `--patch` option has priority over this one. ---pathspec-from-file=<file>:: +`--pathspec-from-file=<file>`:: This option is only valid for `push` command. + -Pathspec is passed in `<file>` instead of commandline args. If -`<file>` is exactly `-` then standard input is used. Pathspec +Pathspec is passed in _<file>_ instead of commandline args. If +_<file>_ is exactly `-` then standard input is used. Pathspec elements are separated by LF or CR/LF. Pathspec elements can be quoted as explained for the configuration variable `core.quotePath` (see linkgit:git-config[1]). See also `--pathspec-file-nul` and global `--literal-pathspecs`. ---pathspec-file-nul:: +`--pathspec-file-nul`:: This option is only valid for `push` command. + Only meaningful with `--pathspec-from-file`. Pathspec elements are separated with NUL character and all other characters are taken literally (including newlines and quotes). --q:: ---quiet:: +`-q`:: +`--quiet`:: This option is only valid for `apply`, `drop`, `pop`, `push`, `save`, `store` commands. + Quiet, suppress feedback messages. ---print:: +`--print`:: This option is only valid for the `export` command. + Create the chain of commits representing the exported stashes without storing it anywhere in the ref namespace and print the object ID to standard output. This is designed for scripts. ---to-ref:: +`--to-ref`:: This option is only valid for the `export` command. + Create the chain of commits representing the exported stashes and store it to the specified ref. -\--:: +`--`:: This option is only valid for `push` command. + Separates pathspec from options for disambiguation purposes. -<pathspec>...:: +`<pathspec>...`:: This option is only valid for `push` command. + The new stash entry records the modified states only for the files @@ -286,11 +283,11 @@ too, leaving files that do not match the pathspec intact. + For more details, see the 'pathspec' entry in linkgit:gitglossary[7]. -<stash>:: +_<stash>_:: This option is only valid for `apply`, `branch`, `drop`, `pop`, `show`, and `export` commands. + -A reference of the form `stash@{<revision>}`. When no `<stash>` is +A reference of the form `stash@{<revision>}`. When no _<stash>_ is given, the latest stash is assumed (that is, `stash@{0}`). DISCUSSION @@ -419,6 +416,7 @@ CONFIGURATION include::includes/cmd-config-section-all.adoc[] +:git-stash: 1 include::config/stash.adoc[] diff --git a/Documentation/git-tag.adoc b/Documentation/git-tag.adoc index a4b1c0ec05..0f7badc116 100644 --- a/Documentation/git-tag.adoc +++ b/Documentation/git-tag.adoc @@ -8,21 +8,21 @@ git-tag - Create, list, delete or verify a tag object signed with GPG SYNOPSIS -------- -[verse] -'git tag' [-a | -s | -u <key-id>] [-f] [-m <msg> | -F <file>] [-e] +[synopsis] +git tag [-a | -s | -u <key-id>] [-f] [-m <msg> | -F <file>] [-e] [(--trailer <token>[(=|:)<value>])...] <tagname> [<commit> | <object>] -'git tag' -d <tagname>... -'git tag' [-n[<num>]] -l [--contains <commit>] [--no-contains <commit>] +git tag -d <tagname>... +git tag [-n[<num>]] -l [--contains <commit>] [--no-contains <commit>] [--points-at <object>] [--column[=<options>] | --no-column] [--create-reflog] [--sort=<key>] [--format=<format>] [--merged <commit>] [--no-merged <commit>] [<pattern>...] -'git tag' -v [--format=<format>] <tagname>... +git tag -v [--format=<format>] <tagname>... DESCRIPTION ----------- -Add a tag reference in `refs/tags/`, unless `-d/-l/-v` is given +Add a tag reference in `refs/tags/`, unless `-d`/`-l`/`-v` is given to delete, list or verify tags. Unless `-f` is given, the named tag must not yet exist. @@ -58,129 +58,129 @@ lightweight tags by default. OPTIONS ------- --a:: ---annotate:: +`-a`:: +`--annotate`:: Make an unsigned, annotated tag object --s:: ---sign:: +`-s`:: +`--sign`:: Make a GPG-signed tag, using the default e-mail address's key. The default behavior of tag GPG-signing is controlled by `tag.gpgSign` configuration variable if it exists, or disabled otherwise. See linkgit:git-config[1]. ---no-sign:: +`--no-sign`:: Override `tag.gpgSign` configuration variable that is set to force each and every tag to be signed. --u <key-id>:: ---local-user=<key-id>:: +`-u <key-id>`:: +`--local-user=<key-id>`:: Make a GPG-signed tag, using the given key. --f:: ---force:: +`-f`:: +`--force`:: Replace an existing tag with the given name (instead of failing) --d:: ---delete:: +`-d`:: +`--delete`:: Delete existing tags with the given names. --v:: ---verify:: +`-v`:: +`--verify`:: Verify the GPG signature of the given tag names. --n<num>:: - <num> specifies how many lines from the annotation, if any, - are printed when using -l. Implies `--list`. +`-n<num>`:: + _<num>_ specifies how many lines from the annotation, if any, + are printed when using `-l`. Implies `--list`. + The default is not to print any annotation lines. If no number is given to `-n`, only the first line is printed. If the tag is not annotated, the commit message is displayed instead. --l:: ---list:: +`-l`:: +`--list`:: List tags. With optional `<pattern>...`, e.g. `git tag --list 'v-*'`, list only the tags that match the pattern(s). + -Running "git tag" without arguments also lists all tags. The pattern -is a shell wildcard (i.e., matched using fnmatch(3)). Multiple +Running `git tag` without arguments also lists all tags. The pattern +is a shell wildcard (i.e., matched using `fnmatch`(3)). Multiple patterns may be given; if any of them matches, the tag is shown. + This option is implicitly supplied if any other list-like option such as `--contains` is provided. See the documentation for each of those options for details. ---sort=<key>:: +`--sort=<key>`:: Sort based on the key given. Prefix `-` to sort in - descending order of the value. You may use the --sort=<key> option - multiple times, in which case the last key becomes the primary - key. Also supports "version:refname" or "v:refname" (tag - names are treated as versions). The "version:refname" sort - order can also be affected by the "versionsort.suffix" + descending order of the value. You may use the `--sort=<key>` option + multiple times, in which case the last _<key>_ becomes the primary + key. Also supports "`version:refname`" or "`v:refname`" (tag + names are treated as versions). The "`version:refname`" sort + order can also be affected by the "`versionsort.suffix`" configuration variable. The keys supported are the same as those in `git for-each-ref`. Sort order defaults to the value configured for the `tag.sort` variable if it exists, or lexicographic order otherwise. See linkgit:git-config[1]. ---color[=<when>]:: +`--color[=<when>]`:: Respect any colors specified in the `--format` option. The - `<when>` field must be one of `always`, `never`, or `auto` (if - `<when>` is absent, behave as if `always` was given). + _<when>_ field must be one of `always`, `never`, or `auto` (if + _<when>_ is absent, behave as if `always` was given). --i:: ---ignore-case:: +`-i`:: +`--ignore-case`:: Sorting and filtering tags are case insensitive. ---omit-empty:: +`--omit-empty`:: Do not print a newline after formatted refs where the format expands to the empty string. ---column[=<options>]:: ---no-column:: +`--column[=<options>]`:: +`--no-column`:: Display tag listing in columns. See configuration variable `column.tag` for option syntax. `--column` and `--no-column` - without options are equivalent to 'always' and 'never' respectively. + without options are equivalent to `always` and `never` respectively. + This option is only applicable when listing tags without annotation lines. ---contains [<commit>]:: - Only list tags which contain the specified commit (HEAD if not +`--contains [<commit>]`:: + Only list tags which contain _<commit>_ (`HEAD` if not specified). Implies `--list`. ---no-contains [<commit>]:: - Only list tags which don't contain the specified commit (HEAD if +`--no-contains [<commit>]`:: + Only list tags which don't contain _<commit>_ (`HEAD` if not specified). Implies `--list`. ---merged [<commit>]:: - Only list tags whose commits are reachable from the specified - commit (`HEAD` if not specified). +`--merged [<commit>]`:: + Only list tags whose commits are reachable from + _<commit>_ (`HEAD` if not specified). ---no-merged [<commit>]:: - Only list tags whose commits are not reachable from the specified - commit (`HEAD` if not specified). +`--no-merged [<commit>]`:: + Only list tags whose commits are not reachable from + _<commit>_ (`HEAD` if not specified). ---points-at <object>:: - Only list tags of the given object (HEAD if not +`--points-at [<object>]`:: + Only list tags of _<object>_ (`HEAD` if not specified). Implies `--list`. --m <msg>:: ---message=<msg>:: - Use the given tag message (instead of prompting). +`-m <msg>`:: +`--message=<msg>`:: + Use _<msg>_ (instead of prompting). If multiple `-m` options are given, their values are concatenated as separate paragraphs. Implies `-a` if none of `-a`, `-s`, or `-u <key-id>` is given. --F <file>:: ---file=<file>:: - Take the tag message from the given file. Use '-' to +`-F <file>`:: +`--file=<file>`:: + Take the tag message from _<file>_. Use `-` to read the message from the standard input. Implies `-a` if none of `-a`, `-s`, or `-u <key-id>` is given. ---trailer <token>[(=|:)<value>]:: - Specify a (<token>, <value>) pair that should be applied as a +`--trailer <token>[(=|:)<value>]`:: + Specify a (_<token>_, _<value>_) pair that should be applied as a trailer. (e.g. `git tag --trailer "Custom-Key: value"` will add a "Custom-Key" trailer to the tag message.) The `trailer.*` configuration variables @@ -190,46 +190,45 @@ This option is only applicable when listing tags without annotation lines. The trailers can be extracted in `git tag --list`, using `--format="%(trailers)"` placeholder. --e:: ---edit:: - The message taken from file with `-F` and command line with - `-m` are usually used as the tag message unmodified. - This option lets you further edit the message taken from these sources. +`-e`:: +`--edit`:: + Let further edit the message taken from file with `-F` and command line with + `-m`. ---cleanup=<mode>:: - This option sets how the tag message is cleaned up. - The '<mode>' can be one of 'verbatim', 'whitespace' and 'strip'. The - 'strip' mode is default. The 'verbatim' mode does not change message at - all, 'whitespace' removes just leading/trailing whitespace lines and - 'strip' removes both whitespace and commentary. +`--cleanup=<mode>`:: + Set how the tag message is cleaned up. + The _<mode>_ can be one of `verbatim`, `whitespace` and `strip`. The + `strip` mode is default. The `verbatim` mode does not change message at + all, `whitespace` removes just leading/trailing whitespace lines and + `strip` removes both whitespace and commentary. ---create-reflog:: +`--create-reflog`:: Create a reflog for the tag. To globally enable reflogs for tags, see `core.logAllRefUpdates` in linkgit:git-config[1]. The negated form `--no-create-reflog` only overrides an earlier `--create-reflog`, but currently does not negate the setting of `core.logAllRefUpdates`. ---format=<format>:: +`--format=<format>`:: A string that interpolates `%(fieldname)` from a tag ref being shown and the object it points at. The format is the same as that of linkgit:git-for-each-ref[1]. When unspecified, defaults to `%(refname:strip=2)`. -<tagname>:: +_<tagname>_:: The name of the tag to create, delete, or describe. The new tag name must pass all checks defined by linkgit:git-check-ref-format[1]. Some of these checks may restrict the characters allowed in a tag name. -<commit>:: -<object>:: +_<commit>_:: +_<object>_:: The object that the new tag will refer to, usually a commit. - Defaults to HEAD. + Defaults to `HEAD`. CONFIGURATION ------------- -By default, 'git tag' in sign-with-default mode (-s) will use your +By default, `git tag` in sign-with-default mode (`-s`) will use your committer identity (of the form `Your Name <your@email.address>`) to find a key. If you want to use a different default key, you can specify it in the repository configuration as follows: @@ -252,7 +251,7 @@ On Re-tagging What should you do when you tag a wrong commit and you would want to re-tag? -If you never pushed anything out, just re-tag it. Use "-f" to +If you never pushed anything out, just re-tag it. Use `-f` to replace the old one. And you're done. But if you have pushed things out (or others could just read @@ -268,12 +267,12 @@ the old tag. In that case you can do one of two things: . The insane thing. You really want to call the new version "X" too, 'even though' - others have already seen the old one. So just use 'git tag -f' + others have already seen the old one. So just use `git tag -f` again, as if you hadn't already published the old one. However, Git does *not* (and it should not) change tags behind users back. So if somebody already got the old tag, doing a -'git pull' on your tree shouldn't just make them overwrite the old +`git pull` on your tree shouldn't just make them overwrite the old one. If somebody got a release tag from you, you cannot just change @@ -325,7 +324,7 @@ private anchor point tags from the other person. Often, "please pull" messages on the mailing list just provide two pieces of information: a repo URL and a branch name; this -is designed to be easily cut&pasted at the end of a 'git fetch' +is designed to be easily cut&pasted at the end of a `git fetch` command line: ------------ @@ -403,6 +402,14 @@ FILES user in an editor session will be available in this file, but may be overwritten by the next invocation of `git tag`. +CONFIGURATION +------------- + +include::includes/cmd-config-section-all.adoc[] + +:git-tag: 1 +include::config/tag.adoc[] + NOTES ----- diff --git a/Documentation/git-worktree.adoc b/Documentation/git-worktree.adoc index 389e669ac0..f272f79783 100644 --- a/Documentation/git-worktree.adoc +++ b/Documentation/git-worktree.adoc @@ -8,16 +8,16 @@ git-worktree - Manage multiple working trees SYNOPSIS -------- -[verse] -'git worktree add' [-f] [--detach] [--checkout] [--lock [--reason <string>]] - [--orphan] [(-b | -B) <new-branch>] <path> [<commit-ish>] -'git worktree list' [-v | --porcelain [-z]] -'git worktree lock' [--reason <string>] <worktree> -'git worktree move' <worktree> <new-path> -'git worktree prune' [-n] [-v] [--expire <expire>] -'git worktree remove' [-f] <worktree> -'git worktree repair' [<path>...] -'git worktree unlock' <worktree> +[synopsis] +git worktree add [-f] [--detach] [--checkout] [--lock [--reason <string>]] + [--orphan] [(-b | -B) <new-branch>] <path> [<commit-ish>] +git worktree list [-v | --porcelain [-z]] +git worktree lock [--reason <string>] <worktree> +git worktree move <worktree> <new-path> +git worktree prune [-n] [-v] [--expire <expire>] +git worktree remove [-f] <worktree> +git worktree repair [<path>...] +git worktree unlock <worktree> DESCRIPTION ----------- @@ -37,7 +37,7 @@ zero or more linked worktrees. When you are done with a linked worktree, remove it with `git worktree remove`. In its simplest form, `git worktree add <path>` automatically creates a -new branch whose name is the final component of `<path>`, which is +new branch whose name is the final component of _<path>_, which is convenient if you plan to work on a new topic. For instance, `git worktree add ../hotfix` creates new branch `hotfix` and checks it out at path `../hotfix`. To instead work on an existing branch in a new worktree, @@ -63,16 +63,16 @@ locked. COMMANDS -------- -add <path> [<commit-ish>]:: +`add <path> [<commit-ish>]`:: -Create a worktree at `<path>` and checkout `<commit-ish>` into it. The new worktree +Create a worktree at _<path>_ and checkout _<commit-ish>_ into it. The new worktree is linked to the current repository, sharing everything except per-worktree -files such as `HEAD`, `index`, etc. As a convenience, `<commit-ish>` may +files such as `HEAD`, `index`, etc. As a convenience, _<commit-ish>_ may be a bare "`-`", which is synonymous with `@{-1}`. + -If `<commit-ish>` is a branch name (call it `<branch>`) and is not found, +If _<commit-ish>_ is a branch name (call it _<branch>_) and is not found, and neither `-b` nor `-B` nor `--detach` are used, but there does -exist a tracking branch in exactly one remote (call it `<remote>`) +exist a tracking branch in exactly one remote (call it _<remote>_) with a matching name, treat as equivalent to: + ------------ @@ -81,32 +81,32 @@ $ git worktree add --track -b <branch> <path> <remote>/<branch> + If the branch exists in multiple remotes and one of them is named by the `checkout.defaultRemote` configuration variable, we'll use that -one for the purposes of disambiguation, even if the `<branch>` isn't +one for the purposes of disambiguation, even if the _<branch>_ isn't unique across all remotes. Set it to e.g. `checkout.defaultRemote=origin` to always checkout remote -branches from there if `<branch>` is ambiguous but exists on the +branches from there if _<branch>_ is ambiguous but exists on the `origin` remote. See also `checkout.defaultRemote` in linkgit:git-config[1]. + -If `<commit-ish>` is omitted and neither `-b` nor `-B` nor `--detach` used, +If _<commit-ish>_ is omitted and neither `-b` nor `-B` nor `--detach` used, then, as a convenience, the new worktree is associated with a branch (call -it `<branch>`) named after `$(basename <path>)`. If `<branch>` doesn't +it _<branch>_) named after `$(basename <path>)`. If _<branch>_ doesn't exist, a new branch based on `HEAD` is automatically created as if -`-b <branch>` was given. If `<branch>` does exist, it will be checked out +`-b <branch>` was given. If _<branch>_ does exist, it will be checked out in the new worktree, if it's not checked out anywhere else, otherwise the command will refuse to create the worktree (unless `--force` is used). + -If `<commit-ish>` is omitted, neither `--detach`, or `--orphan` is +If _<commit-ish>_ is omitted, neither `--detach`, or `--orphan` is used, and there are no valid local branches (or remote branches if `--guess-remote` is specified) then, as a convenience, the new worktree is -associated with a new unborn branch named `<branch>` (after +associated with a new unborn branch named _<branch>_ (after `$(basename <path>)` if neither `-b` or `-B` is used) as if `--orphan` was passed to the command. In the event the repository has a remote and `--guess-remote` is used, but no remote or local branches exist, then the command fails with a warning reminding the user to fetch from their remote first (or override by using `-f/--force`). -list:: +`list`:: List details of each worktree. The main worktree is listed first, followed by each of the linked worktrees. The output details include @@ -115,32 +115,32 @@ branch currently checked out (or "detached HEAD" if none), "locked" if the worktree is locked, "prunable" if the worktree can be pruned by the `prune` command. -lock:: +`lock`:: If a worktree is on a portable device or network share which is not always mounted, lock it to prevent its administrative files from being pruned automatically. This also prevents it from being moved or deleted. Optionally, specify a reason for the lock with `--reason`. -move:: +`move`:: Move a worktree to a new location. Note that the main worktree or linked worktrees containing submodules cannot be moved with this command. (The `git worktree repair` command, however, can reestablish the connection with linked worktrees if you move the main worktree manually.) -prune:: +`prune`:: Prune worktree information in `$GIT_DIR/worktrees`. -remove:: +`remove`:: Remove a worktree. Only clean worktrees (no untracked files and no modification in tracked files) can be removed. Unclean worktrees or ones with submodules can be removed with `--force`. The main worktree cannot be removed. -repair [<path>...]:: +`repair [<path>...]`:: Repair worktree administrative files, if possible, if they have become corrupted or outdated due to external factors. @@ -154,72 +154,72 @@ Similarly, if the working tree for a linked worktree is moved without using `git worktree move`, the main worktree (or bare repository) will be unable to locate it. Running `repair` within the recently-moved worktree will reestablish the connection. If multiple linked worktrees are moved, -running `repair` from any worktree with each tree's new `<path>` as an +running `repair` from any worktree with each tree's new _<path>_ as an argument, will reestablish the connection to all the specified paths. + If both the main worktree and linked worktrees have been moved or copied manually, -then running `repair` in the main worktree and specifying the new `<path>` +then running `repair` in the main worktree and specifying the new _<path>_ of each linked worktree will reestablish all connections in both directions. -unlock:: +`unlock`:: Unlock a worktree, allowing it to be pruned, moved or deleted. OPTIONS ------- --f:: ---force:: +`-f`:: +`--force`:: By default, `add` refuses to create a new worktree when - `<commit-ish>` is a branch name and is already checked out by - another worktree, or if `<path>` is already assigned to some - worktree but is missing (for instance, if `<path>` was deleted + _<commit-ish>_ is a branch name and is already checked out by + another worktree, or if _<path>_ is already assigned to some + worktree but is missing (for instance, if _<path>_ was deleted manually). This option overrides these safeguards. To add a missing but locked worktree path, specify `--force` twice. + `move` refuses to move a locked worktree unless `--force` is specified twice. If the destination is already assigned to some other worktree but is -missing (for instance, if `<new-path>` was deleted manually), then `--force` +missing (for instance, if _<new-path>_ was deleted manually), then `--force` allows the move to proceed; use `--force` twice if the destination is locked. + `remove` refuses to remove an unclean worktree unless `--force` is used. To remove a locked worktree, specify `--force` twice. --b <new-branch>:: --B <new-branch>:: - With `add`, create a new branch named `<new-branch>` starting at - `<commit-ish>`, and check out `<new-branch>` into the new worktree. - If `<commit-ish>` is omitted, it defaults to `HEAD`. +`-b <new-branch>`:: +`-B <new-branch>`:: + With `add`, create a new branch named _<new-branch>_ starting at + _<commit-ish>_, and check out _<new-branch>_ into the new worktree. + If _<commit-ish>_ is omitted, it defaults to `HEAD`. By default, `-b` refuses to create a new branch if it already - exists. `-B` overrides this safeguard, resetting `<new-branch>` to - `<commit-ish>`. + exists. `-B` overrides this safeguard, resetting _<new-branch>_ to + _<commit-ish>_. --d:: ---detach:: +`-d`:: +`--detach`:: With `add`, detach `HEAD` in the new worktree. See "DETACHED HEAD" in linkgit:git-checkout[1]. ---checkout:: ---no-checkout:: - By default, `add` checks out `<commit-ish>`, however, `--no-checkout` can +`--checkout`:: +`--no-checkout`:: + By default, `add` checks out _<commit-ish>_, however, `--no-checkout` can be used to suppress checkout in order to make customizations, such as configuring sparse-checkout. See "Sparse checkout" in linkgit:git-read-tree[1]. ---guess-remote:: ---no-guess-remote:: - With `worktree add <path>`, without `<commit-ish>`, instead +`--guess-remote`:: +`--no-guess-remote`:: + With `worktree add <path>`, without _<commit-ish>_, instead of creating a new branch from `HEAD`, if there exists a tracking - branch in exactly one remote matching the basename of `<path>`, + branch in exactly one remote matching the basename of _<path>_, base the new branch on the remote-tracking branch, and mark the remote-tracking branch as "upstream" from the new branch. + This can also be set up as the default behaviour by using the `worktree.guessRemote` config option. ---relative-paths:: ---no-relative-paths:: +`--relative-paths`:: +`--no-relative-paths`:: Link worktrees using relative paths or absolute paths (default). Overrides the `worktree.useRelativePaths` config option, see linkgit:git-config[1]. @@ -227,60 +227,60 @@ This can also be set up as the default behaviour by using the With `repair`, the linking files will be updated if there's an absolute/relative mismatch, even if the links are correct. ---track:: ---no-track:: - When creating a new branch, if `<commit-ish>` is a branch, +`--track`:: +`--no-track`:: + When creating a new branch, if _<commit-ish>_ is a branch, mark it as "upstream" from the new branch. This is the - default if `<commit-ish>` is a remote-tracking branch. See + default if _<commit-ish>_ is a remote-tracking branch. See `--track` in linkgit:git-branch[1] for details. ---lock:: +`--lock`:: Keep the worktree locked after creation. This is the equivalent of `git worktree lock` after `git worktree add`, but without a race condition. --n:: ---dry-run:: +`-n`:: +`--dry-run`:: With `prune`, do not remove anything; just report what it would remove. ---orphan:: +`--orphan`:: With `add`, make the new worktree and index empty, associating - the worktree with a new unborn branch named `<new-branch>`. + the worktree with a new unborn branch named _<new-branch>_. ---porcelain:: +`--porcelain`:: With `list`, output in an easy-to-parse format for scripts. This format will remain stable across Git versions and regardless of user configuration. It is recommended to combine this with `-z`. See below for details. --z:: - Terminate each line with a NUL rather than a newline when +`-z`:: + Terminate each line with a _NUL_ rather than a newline when `--porcelain` is specified with `list`. This makes it possible to parse the output when a worktree path contains a newline character. --q:: ---quiet:: +`-q`:: +`--quiet`:: With `add`, suppress feedback messages. --v:: ---verbose:: +`-v`:: +`--verbose`:: With `prune`, report all removals. + With `list`, output additional information about worktrees (see below). ---expire <time>:: - With `prune`, only expire unused worktrees older than `<time>`. +`--expire <time>`:: + With `prune`, only expire unused worktrees older than _<time>_. + With `list`, annotate missing worktrees as prunable if they are older than -`<time>`. +_<time>_. ---reason <string>:: +`--reason <string>`:: With `lock` or with `add --lock`, an explanation why the worktree is locked. -<worktree>:: +_<worktree>_:: Worktrees can be identified by path, either relative or absolute. + If the last path components in the worktree's path is unique among @@ -522,6 +522,13 @@ $ popd $ git worktree remove ../temp ------------ +CONFIGURATION +------------- + +include::includes/cmd-config-section-all.adoc[] + +include::config/worktree.adoc[] + BUGS ---- Multiple checkout in general is still experimental, and the support diff --git a/Documentation/gitcli.adoc b/Documentation/gitcli.adoc index 1ea681b59d..ef2a0a399d 100644 --- a/Documentation/gitcli.adoc +++ b/Documentation/gitcli.adoc @@ -216,6 +216,20 @@ $ git describe --abbrev=10 HEAD # correct $ git describe --abbrev 10 HEAD # NOT WHAT YOU MEANT ---------------------------- + +Magic filename options +~~~~~~~~~~~~~~~~~~~~~~ +Options that take a filename allow a prefix `:(optional)`. For example: + +---------------------------- +git commit -F :(optional)COMMIT_EDITMSG +# if COMMIT_EDITMSG does not exist, equivalent to +git commit +---------------------------- + +Like with configuration values, if the named file is missing Git behaves as if +the option was not given at all. See "Values" in linkgit:git-config[1]. + NOTES ON FREQUENTLY CONFUSED OPTIONS ------------------------------------ diff --git a/Documentation/gitcredentials.adoc b/Documentation/gitcredentials.adoc index 3337bb475d..60c2cc4ade 100644 --- a/Documentation/gitcredentials.adoc +++ b/Documentation/gitcredentials.adoc @@ -150,9 +150,8 @@ pattern in the config file. For example, if you have this in your config file: username = foo -------------------------------------- -then we will match: both protocols are the same, both hosts are the same, and -the "pattern" URL does not care about the path component at all. However, this -context would not match: +then we will match: both protocols are the same and both hosts are the same. +However, this context would not match: -------------------------------------- [credential "https://kernel.org"] @@ -166,11 +165,11 @@ match: Git compares the protocols exactly. However, you may use wildcards in the domain name and other pattern matching techniques as with the `http.<URL>.*` options. -If the "pattern" URL does include a path component, then this too must match -exactly: the context `https://example.com/bar/baz.git` will match a config -entry for `https://example.com/bar/baz.git` (in addition to matching the config -entry for `https://example.com`) but will not match a config entry for -`https://example.com/bar`. +If the "pattern" URL does include a path component, then this must match +as a prefix path: the context `https://example.com/bar` will match a config +entry for `https://example.com/bar/baz.git` but will not match a config entry for +`https://example.com/other/repo.git` or `https://example.com/barry/repo.git` +(even though it is a string prefix). CONFIGURATION OPTIONS diff --git a/Documentation/gitformat-loose.adoc b/Documentation/gitformat-loose.adoc new file mode 100644 index 0000000000..947993663e --- /dev/null +++ b/Documentation/gitformat-loose.adoc @@ -0,0 +1,53 @@ +gitformat-loose(5) +================== + +NAME +---- +gitformat-loose - Git loose object format + + +SYNOPSIS +-------- +[verse] +$GIT_DIR/objects/[0-9a-f][0-9a-f]/* + +DESCRIPTION +----------- + +Loose objects are how Git stores individual objects, where every object is +written as a separate file. + +Over the lifetime of a repository, objects are usually written as loose objects +initially. Eventually, these loose objects will be compacted into packfiles +via repository maintenance to improve disk space usage and speed up the lookup +of these objects. + +== Loose objects + +Each loose object contains a prefix, followed immediately by the data of the +object. The prefix contains `<type> <size>\0`. `<type>` is one of `blob`, +`tree`, `commit`, or `tag` and `size` is the size of the data (without the +prefix) as a decimal integer expressed in ASCII. + +The entire contents, prefix and data concatenated, is then compressed with zlib +and the compressed data is stored in the file. The object ID of the object is +the SHA-1 or SHA-256 (as appropriate) hash of the uncompressed data. + +The file for the loose object is stored under the `objects` directory, with the +first two hex characters of the object ID being the directory and the remaining +characters being the file name. This is done to shard the data and avoid too +many files being in one directory, since some file systems perform poorly with +many items in a directory. + +As an example, the empty tree contains the data (when uncompressed) `tree 0\0` +and, in a SHA-256 repository, would have the object ID +`6ef19b41225c5369f1c104d45d8d85efa9b057b53b14b4b9b939dd74decc5321` and would be +stored under +`$GIT_DIR/objects/6e/f19b41225c5369f1c104d45d8d85efa9b057b53b14b4b9b939dd74decc5321`. + +Similarly, a blob containing the contents `abc` would have the uncompressed +data of `blob 3\0abc`. + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/Documentation/gitformat-pack.adoc b/Documentation/gitformat-pack.adoc index d6ae229be5..1b4db4aa61 100644 --- a/Documentation/gitformat-pack.adoc +++ b/Documentation/gitformat-pack.adoc @@ -32,6 +32,10 @@ In a repository using the traditional SHA-1, pack checksums, index checksums, and object IDs (object names) mentioned below are all computed using SHA-1. Similarly, in SHA-256 repositories, these values are computed using SHA-256. +CRC32 checksums are always computed over the entire packed object, including +the header (n-byte type and length); the base object name or offset, if any; +and the entire compressed object. The CRC32 algorithm used is that of zlib. + == pack-*.pack files have the following format: - A header appears at the beginning and consists of the following: @@ -80,6 +84,16 @@ Valid object types are: Type 5 is reserved for future expansion. Type 0 is invalid. +=== Object encoding + +Unlike loose objects, packed objects do not have a prefix containing the type, +size, and a NUL byte. These are not necessary because they can be determined by +the n-byte type and length that prefixes the data and so they are omitted from +the compressed and deltified data. + +The computation of the object ID still uses this prefix by reconstructing it +from the type and length as needed. + === Size encoding This document uses the following "size encoding" of non-negative @@ -92,6 +106,11 @@ values are more significant. This size encoding should not be confused with the "offset encoding", which is also used in this document. +When encoding the size of an undeltified object in a pack, the size is that of +the uncompressed raw object. For deltified objects, it is the size of the +uncompressed delta. The base object name or offset is not included in the size +computation. + === Deltified representation Conceptually there are only four object types: commit, tree, tag and diff --git a/Documentation/meson.build b/Documentation/meson.build index 44f94cdb7b..9d24f2da54 100644 --- a/Documentation/meson.build +++ b/Documentation/meson.build @@ -173,6 +173,7 @@ manpages = { 'gitformat-chunk.adoc' : 5, 'gitformat-commit-graph.adoc' : 5, 'gitformat-index.adoc' : 5, + 'gitformat-loose.adoc' : 5, 'gitformat-pack.adoc' : 5, 'gitformat-signature.adoc' : 5, 'githooks.adoc' : 5, diff --git a/Documentation/pretty-formats.adoc b/Documentation/pretty-formats.adoc index 618ddc4a0c..2121e8e1df 100644 --- a/Documentation/pretty-formats.adoc +++ b/Documentation/pretty-formats.adoc @@ -232,7 +232,7 @@ ref names with custom decorations. The `decorate` string may be followed by a colon and zero or more comma-separated options. Option values may contain literal formatting codes. These must be used for commas (`%x2C`) and closing parentheses (`%x29`), due to their role in the option syntax. -+ + ** `prefix=<value>`: Shown before the list of ref names. Defaults to "{nbsp}++(++". ** `suffix=<value>`: Shown after the list of ref names. Defaults to "+)+". ** `separator=<value>`: Shown between ref names. Defaults to "+,+{nbsp}". @@ -241,10 +241,12 @@ parentheses (`%x29`), due to their role in the option syntax. ** `tag=<value>`: Shown before tag names. Defaults to "`tag:`{nbsp}". + +-- For example, to produce decorations with no wrapping or tag annotations, and spaces as separators: -+ + ++%(decorate:prefix=,suffix=,tag=,separator= )++ +-- ++%(describe++`[:<option>,...]`++)++:: human-readable name, like linkgit:git-describe[1]; empty string for diff --git a/Documentation/pretty-options.adoc b/Documentation/pretty-options.adoc index 8aac51dbe7..658e462b25 100644 --- a/Documentation/pretty-options.adoc +++ b/Documentation/pretty-options.adoc @@ -61,15 +61,16 @@ and `fuller`). ifndef::git-rev-list[] `--notes[=<ref>]`:: Show the notes (see linkgit:git-notes[1]) that annotate the - commit, when showing the commit log message. This is the default + commit, when showing the commit log message. ifndef::with-breaking-changes[] - for `git log`, `git show` and `git whatchanged` commands when +This is the default for `git log`, `git show` and `git whatchanged` +commands when there is no `--pretty`, `--format`, or `--oneline` option given +on the command line. endif::with-breaking-changes[] ifdef::with-breaking-changes[] - for `git log` and `git show` commands when +This is the default for `git log` and `git show` commands when there is no +`--pretty`, `--format`, or `--oneline` option given on the command line. endif::with-breaking-changes[] - there is no `--pretty`, `--format`, or `--oneline` option given - on the command line. + By default, the notes shown are from the notes refs listed in the `core.notesRef` and `notes.displayRef` variables (or corresponding diff --git a/Documentation/pull-fetch-param.adoc b/Documentation/pull-fetch-param.adoc index d79d2f6065..bb2cf6a462 100644 --- a/Documentation/pull-fetch-param.adoc +++ b/Documentation/pull-fetch-param.adoc @@ -11,6 +11,7 @@ ifndef::git-pull[] (See linkgit:git-config[1]). endif::git-pull[] +[[fetch-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 diff --git a/Documentation/technical/commit-graph.adoc b/Documentation/technical/commit-graph.adoc index 2c26e95e51..a259d1567b 100644 --- a/Documentation/technical/commit-graph.adoc +++ b/Documentation/technical/commit-graph.adoc @@ -39,6 +39,7 @@ A consumer may load the following info for a commit from the graph: Values 1-4 satisfy the requirements of parse_commit_gently(). There are two definitions of generation number: + 1. Corrected committer dates (generation number v2) 2. Topological levels (generation number v1) @@ -158,7 +159,8 @@ number of commits in the full history. By creating a "chain" of commit-graphs, we enable fast writes of new commit data without rewriting the entire commit history -- at least, most of the time. -## File Layout +File Layout +~~~~~~~~~~~ A commit-graph chain uses multiple files, and we use a fixed naming convention to organize these files. Each commit-graph file has a name @@ -170,11 +172,11 @@ hashes for the files in order from "lowest" to "highest". For example, if the `commit-graph-chain` file contains the lines -``` +---- {hash0} {hash1} {hash2} -``` +---- then the commit-graph chain looks like the following diagram: @@ -213,7 +215,8 @@ specifying the hashes of all files in the lower layers. In the above example, `graph-{hash1}.graph` contains `{hash0}` while `graph-{hash2}.graph` contains `{hash0}` and `{hash1}`. -## Merging commit-graph files +Merging commit-graph files +~~~~~~~~~~~~~~~~~~~~~~~~~~ If we only added a new commit-graph file on every write, we would run into a linear search problem through many commit-graph files. Instead, we use a merge @@ -225,6 +228,7 @@ is determined by the merge strategy that the files should collapse to the commits in `graph-{hash1}` should be combined into a new `graph-{hash3}` file. +.... +---------------------+ | | | (new commits) | @@ -250,6 +254,7 @@ file. | | | | +-----------------------+ +.... During this process, the commits to write are combined, sorted and we write the contents to a temporary file, all while holding a `commit-graph-chain.lock` @@ -257,14 +262,15 @@ lock-file. When the file is flushed, we rename it to `graph-{hash3}` according to the computed `{hash3}`. Finally, we write the new chain data to `commit-graph-chain.lock`: -``` +---- {hash3} {hash0} -``` +---- We then close the lock-file. -## Merge Strategy +Merge Strategy +~~~~~~~~~~~~~~ When writing a set of commits that do not exist in the commit-graph stack of height N, we default to creating a new file at level N + 1. We then decide to @@ -289,7 +295,8 @@ The merge strategy values (2 for the size multiple, 64,000 for the maximum number of commits) could be extracted into config settings for full flexibility. -## Handling Mixed Generation Number Chains +Handling Mixed Generation Number Chains +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ With the introduction of generation number v2 and generation data chunk, the following scenario is possible: @@ -318,7 +325,8 @@ have corrected commit dates when written by compatible versions of Git. Thus, rewriting split commit-graph as a single file (`--split=replace`) creates a single layer with corrected commit dates. -## Deleting graph-{hash} files +Deleting graph-\{hash\} files +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ After a new tip file is written, some `graph-{hash}` files may no longer be part of a chain. It is important to remove these files from disk, eventually. @@ -333,7 +341,8 @@ files whose modified times are older than a given expiry window. This window defaults to zero, but can be changed using command-line arguments or a config setting. -## Chains across multiple object directories +Chains across multiple object directories +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In a repo with alternates, we look for the `commit-graph-chain` file starting in the local object directory and then in each alternate. The first file that diff --git a/Documentation/technical/hash-function-transition.adoc b/Documentation/technical/hash-function-transition.adoc index f047fd80ca..2359d7d106 100644 --- a/Documentation/technical/hash-function-transition.adoc +++ b/Documentation/technical/hash-function-transition.adoc @@ -227,9 +227,9 @@ network byte order): ** 4-byte length in bytes of shortened object names. This is the shortest possible length needed to make names in the shortened object name table unambiguous. - ** 4-byte integer, recording where tables relating to this format + ** 8-byte integer, recording where tables relating to this format are stored in this index file, as an offset from the beginning. - * 4-byte offset to the trailer from the beginning of this file. + * 8-byte offset to the trailer from the beginning of this file. * Zero or more additional key/value pairs (4-byte key, 4-byte value). Only one key is supported: 'PSRC'. See the "Loose objects and unreachable objects" section for supported values and how this @@ -260,12 +260,10 @@ network byte order): compressed data to be copied directly from pack to pack during repacking without undetected data corruption. - * A table of 4-byte offset values. For an object in the table of - sorted shortened object names, the value at the corresponding - index in this table indicates where that object can be found in - the pack file. These are usually 31-bit pack file offsets, but - large offsets are encoded as an index into the next table with the - most significant bit set. + * A table of 4-byte offset values. The index of this table in pack order + indicates where that object can be found in the pack file. These are + usually 31-bit pack file offsets, but large offsets are encoded as + an index into the next table with the most significant bit set. * A table of 8-byte offset entries (empty for pack files less than 2 GiB). Pack files are organized with heavily used objects toward @@ -276,10 +274,14 @@ network byte order): up to and not including the table of CRC32 values. - Zero or more NUL bytes. - The trailer consists of the following: - * A copy of the 20-byte SHA-256 checksum at the end of the + * A copy of the full main hash checksum at the end of the corresponding packfile. - * 20-byte SHA-256 checksum of all of the above. + * Full main hash checksum of all of the above. + +The "full main hash" is a full-length hash of the main (not compatibility) +algorithm in the repository. Thus, if the main algorithm is SHA-256, this is +a 32-byte SHA-256 hash and for SHA-1, it's a 20-byte SHA-1 hash. Loose object index ~~~~~~~~~~~~~~~~~~ @@ -427,17 +429,19 @@ ordinary unsigned commit. Signed Tags ~~~~~~~~~~~ -We add a new field "gpgsig-sha256" to the tag object format to allow -signing tags without relying on SHA-1. Its signed payload is the -SHA-256 content of the tag with its gpgsig-sha256 field and "-----BEGIN PGP -SIGNATURE-----" delimited in-body signature removed. - -This means tags can be signed - -1. using SHA-1 only, as in existing signed tag objects -2. using both SHA-1 and SHA-256, by using gpgsig-sha256 and an in-body - signature. -3. using only SHA-256, by only using the gpgsig-sha256 field. +We add new fields "gpgsig" and "gpgsig-sha256" to the tag object format to +allow signing tags in both formats. The in-body signature is used for the +signature in the current hash algorithm and the header is used for the +signature in the other algorithm. Thus, a dual-signature tag will contain both +an in-body signature and a gpgsig-sha256 header for the SHA-1 format of an +object or both an in-body signature and a gpgsig header for the SHA-256 format +of and object. + +The signed payload of the tag is the content of the tag in the current +algorithm with both its gpgsig and gpgsig-sha256 fields and +"-----BEGIN PGP SIGNATURE-----" delimited in-body signature removed. + +This means tags can be signed using one or both algorithms. Mergetag embedding ~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/technical/large-object-promisors.adoc b/Documentation/technical/large-object-promisors.adoc index dea8dafa66..2aa815e023 100644 --- a/Documentation/technical/large-object-promisors.adoc +++ b/Documentation/technical/large-object-promisors.adoc @@ -34,8 +34,8 @@ a new object representation for large blobs as discussed in: https://lore.kernel.org/git/xmqqbkdometi.fsf@gitster.g/ -0) Non goals ------------- +Non goals +--------- - We will not discuss those client side improvements here, as they would require changes in different parts of Git than this effort. @@ -90,8 +90,8 @@ later in this document: even more to host content with larger blobs or more large blobs than currently. -I) Issues with the current situation ------------------------------------- +I Issues with the current situation +----------------------------------- - Some statistics made on GitLab repos have shown that more than 75% of the disk space is used by blobs that are larger than 1MB and @@ -138,8 +138,8 @@ I) Issues with the current situation complaining that these tools require significant effort to set up, learn and use correctly. -II) Main features of the "Large Object Promisors" solution ----------------------------------------------------------- +II Main features of the "Large Object Promisors" solution +--------------------------------------------------------- The main features below should give a rough overview of how the solution may work. Details about needed elements can be found in @@ -166,7 +166,7 @@ format. They should be used along with main remotes that contain the other objects. Note 1 -++++++ +^^^^^^ To clarify, a LOP is a normal promisor remote, except that: @@ -178,7 +178,7 @@ To clarify, a LOP is a normal promisor remote, except that: itself. Note 2 -++++++ +^^^^^^ Git already makes it possible for a main remote to also be a promisor remote storing both regular objects and large blobs for a client that @@ -186,13 +186,13 @@ clones from it with a filter on blob size. But here we explicitly want to avoid that. Rationale -+++++++++ +^^^^^^^^^ LOPs aim to be good at handling large blobs while main remotes are already good at handling other objects. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ Git already has support for multiple promisor remotes, see link:partial-clone.html#using-many-promisor-remotes[the partial clone documentation]. @@ -213,19 +213,19 @@ remote helper (see linkgit:gitremote-helpers[7]) which makes the underlying object storage appear like a remote to Git. Note -++++ +^^^^ A LOP can be a promisor remote accessed using a remote helper by both some clients and the main remote. Rationale -+++++++++ +^^^^^^^^^ This looks like the simplest way to create LOPs that can cheaply handle many large blobs. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ Remote helpers are quite easy to write as shell scripts, but it might be more efficient and maintainable to write them using other languages @@ -247,7 +247,7 @@ The underlying object storage that a LOP uses could also serve as storage for large files handled by Git LFS. Rationale -+++++++++ +^^^^^^^^^ This would simplify the server side if it wants to both use a LOP and act as a Git LFS server. @@ -259,7 +259,7 @@ On the server side, a main remote should have a way to offload to a LOP all its blobs with a size over a configurable threshold. Rationale -+++++++++ +^^^^^^^^^ This makes it easy to set things up and to clean things up. For example, an admin could use this to manually convert a repo not using @@ -268,7 +268,7 @@ some users would sometimes push large blobs, a cron job could use this to regularly make sure the large blobs are moved to the LOP. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ Using something based on `git repack --filter=...` to separate the blobs we want to offload from the other Git objects could be a good @@ -284,13 +284,13 @@ should have ways to prevent oversize blobs to be fetched, and also perhaps pushed, into it. Rationale -+++++++++ +^^^^^^^^^ A main remote containing many oversize blobs would defeat the purpose of LOPs. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ The way to offload to a LOP discussed in 4) above can be used to regularly offload oversize blobs. About preventing oversize blobs from @@ -326,18 +326,18 @@ large blobs directly from the LOP and the server would not need to fetch those blobs from the LOP to be able to serve the client. Note -++++ +^^^^ For fetches instead of clones, a protocol negotiation might not always happen, see the "What about fetches?" FAQ entry below for details. Rationale -+++++++++ +^^^^^^^^^ Security, configurability and efficiency of setting things up. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ A "promisor-remote" protocol v2 capability looks like a good way to implement this. The way the client and server use this capability @@ -356,7 +356,7 @@ the client should be able to offload some large blobs it has fetched, but might not need anymore, to the LOP. Note -++++ +^^^^ It might depend on the context if it should be OK or not for clients to offload large blobs they have created, instead of fetched, directly @@ -367,13 +367,13 @@ This should be discussed and refined when we get closer to implementing this feature. Rationale -+++++++++ +^^^^^^^^^ On the client, the easiest way to deal with unneeded large blobs is to offload them. Implementation -++++++++++++++ +^^^^^^^^^^^^^^ This is very similar to what 4) above is about, except on the client side instead of the server side. So a good solution to 4) could likely @@ -385,8 +385,8 @@ when cloning (see 6) above). Also if the large blobs were fetched from a LOP, it is likely, and can easily be confirmed, that the LOP still has them, so that they can just be removed from the client. -III) Benefits of using LOPs ---------------------------- +III Benefits of using LOPs +-------------------------- Many benefits are related to the issues discussed in "I) Issues with the current situation" above: @@ -406,8 +406,8 @@ the current situation" above: - Reduced storage needs on the client side. -IV) FAQ -------- +IV FAQ +------ What about using multiple LOPs on the server and client side? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -533,7 +533,7 @@ some objects it already knows about but doesn't have because they are on a promisor remote. Regular fetch -+++++++++++++ +^^^^^^^^^^^^^ In a regular fetch, the client will contact the main remote and a protocol negotiation will happen between them. It's a good thing that @@ -551,7 +551,7 @@ new fetch will happen in the same way as the previous clone or fetch, using, or not using, the same LOP(s) as last time. "Backfill" or "lazy" fetch -++++++++++++++++++++++++++ +^^^^^^^^^^^^^^^^^^^^^^^^^^ When there is a backfill fetch, the client doesn't necessarily contact the main remote first. It will try to fetch from its promisor remotes @@ -576,8 +576,8 @@ from the client when it fetches from them. The client could get the token when performing a protocol negotiation with the main remote (see section II.6 above). -V) Future improvements ----------------------- +V Future improvements +--------------------- It is expected that at the beginning using LOPs will be mostly worth it either in a corporate context where the Git version that clients diff --git a/Documentation/technical/meson.build b/Documentation/technical/meson.build index 858af811a7..be698ef22a 100644 --- a/Documentation/technical/meson.build +++ b/Documentation/technical/meson.build @@ -13,6 +13,7 @@ articles = [ 'commit-graph.adoc', 'directory-rename-detection.adoc', 'hash-function-transition.adoc', + 'large-object-promisors.adoc', 'long-running-process-protocol.adoc', 'multi-pack-index.adoc', 'packfile-uri.adoc', diff --git a/Documentation/technical/remembering-renames.adoc b/Documentation/technical/remembering-renames.adoc index 73f41761e2..6155f36c72 100644 --- a/Documentation/technical/remembering-renames.adoc +++ b/Documentation/technical/remembering-renames.adoc @@ -10,32 +10,32 @@ history as an optimization, assuming all merges are automatic and clean Outline: - 0. Assumptions + 1. Assumptions - 1. How rebasing and cherry-picking work + 2. How rebasing and cherry-picking work - 2. Why the renames on MERGE_SIDE1 in any given pick are *always* a + 3. Why the renames on MERGE_SIDE1 in any given pick are *always* a superset of the renames on MERGE_SIDE1 for the next pick. - 3. Why any rename on MERGE_SIDE1 in any given pick is _almost_ always also + 4. Why any rename on MERGE_SIDE1 in any given pick is _almost_ always also a rename on MERGE_SIDE1 for the next pick - 4. A detailed description of the counter-examples to #3. + 5. A detailed description of the counter-examples to #4. - 5. Why the special cases in #4 are still fully reasonable to use to pair + 6. Why the special cases in #5 are still fully reasonable to use to pair up files for three-way content merging in the merge machinery, and why they do not affect the correctness of the merge. - 6. Interaction with skipping of "irrelevant" renames + 7. Interaction with skipping of "irrelevant" renames - 7. Additional items that need to be cached + 8. Additional items that need to be cached - 8. How directory rename detection interacts with the above and why this + 9. How directory rename detection interacts with the above and why this optimization is still safe even if merge.directoryRenames is set to "true". -=== 0. Assumptions === +== 1. Assumptions == There are two assumptions that will hold throughout this document: @@ -44,8 +44,8 @@ There are two assumptions that will hold throughout this document: * All merges are fully automatic -and a third that will hold in sections 2-5 for simplicity, that I'll later -address in section 8: +and a third that will hold in sections 3-6 for simplicity, that I'll later +address in section 9: * No directory renames occur @@ -77,9 +77,9 @@ conflicts that the user needs to resolve), the cache of renames is not stored on disk, and thus is thrown away as soon as the rebase or cherry pick stops for the user to resolve the operation. -The third assumption makes sections 2-5 simpler, and allows people to +The third assumption makes sections 3-6 simpler, and allows people to understand the basics of why this optimization is safe and effective, and -then I can go back and address the specifics in section 8. It is probably +then I can go back and address the specifics in section 9. It is probably also worth noting that if directory renames do occur, then the default of merge.directoryRenames being set to "conflict" means that the operation will stop for users to resolve the conflicts and the cache will be thrown @@ -88,22 +88,26 @@ reason we need to address directory renames specifically, is that some users will have set merge.directoryRenames to "true" to allow the merges to continue to proceed automatically. The optimization is still safe with this config setting, but we have to discuss a few more cases to show why; -this discussion is deferred until section 8. +this discussion is deferred until section 9. -=== 1. How rebasing and cherry-picking work === +== 2. How rebasing and cherry-picking work == Consider the following setup (from the git-rebase manpage): +------------ A---B---C topic / D---E---F---G main +------------ After rebasing or cherry-picking topic onto main, this will appear as: +------------ A'--B'--C' topic / D---E---F---G main +------------ The way the commits A', B', and C' are created is through a series of merges, where rebase or cherry-pick sequentially uses each of the three @@ -111,6 +115,7 @@ A-B-C commits in a special merge operation. Let's label the three commits in the merge operation as MERGE_BASE, MERGE_SIDE1, and MERGE_SIDE2. For this picture, the three commits for each of the three merges would be: +.... To create A': MERGE_BASE: E MERGE_SIDE1: G @@ -125,6 +130,7 @@ To create C': MERGE_BASE: B MERGE_SIDE1: B' MERGE_SIDE2: C +.... Sometimes, folks are surprised that these three-way merges are done. It can be useful in understanding these three-way merges to view them in a @@ -138,8 +144,7 @@ Conceptually the two statements above are the same as a three-way merge of B, B', and C, at least the parts before you decide to record a commit. -=== 2. Why the renames on MERGE_SIDE1 in any given pick are always a === -=== superset of the renames on MERGE_SIDE1 for the next pick. === +== 3. Why the renames on MERGE_SIDE1 in any given pick are always a superset of the renames on MERGE_SIDE1 for the next pick. == The merge machinery uses the filenames it is fed from MERGE_BASE, MERGE_SIDE1, and MERGE_SIDE2. It will only move content to a different @@ -156,6 +161,7 @@ filename under one of three conditions: First, let's remember what commits are involved in the first and second picks of the cherry-pick or rebase sequence: +.... To create A': MERGE_BASE: E MERGE_SIDE1: G @@ -165,6 +171,7 @@ To create B': MERGE_BASE: A MERGE_SIDE1: A' MERGE_SIDE2: B +.... So, in particular, we need to show that the renames between E and G are a superset of those between A and A'. @@ -181,11 +188,11 @@ are a subset of those between E and G. Equivalently, all renames between E and G are a superset of those between A and A'. -=== 3. Why any rename on MERGE_SIDE1 in any given pick is _almost_ === -=== always also a rename on MERGE_SIDE1 for the next pick. === +== 4. Why any rename on MERGE_SIDE1 in any given pick is _almost_ always also a rename on MERGE_SIDE1 for the next pick. == Let's again look at the first two picks: +.... To create A': MERGE_BASE: E MERGE_SIDE1: G @@ -195,17 +202,25 @@ To create B': MERGE_BASE: A MERGE_SIDE1: A' MERGE_SIDE2: B +.... Now let's look at any given rename from MERGE_SIDE1 of the first pick, i.e. any given rename from E to G. Let's use the filenames 'oldfile' and 'newfile' for demonstration purposes. That first pick will function as follows; when the rename is detected, the merge machinery will do a three-way content merge of the following: + +.... E:oldfile G:newfile A:oldfile +.... + and produce a new result: + +.... A':newfile +.... Note above that I've assumed that E->A did not rename oldfile. If that side did rename, then we most likely have a rename/rename(1to2) conflict @@ -254,19 +269,21 @@ were detected as renames, A:oldfile and A':newfile should also be detectable as renames almost always. -=== 4. A detailed description of the counter-examples to #3. === +== 5. A detailed description of the counter-examples to #4. == -We already noted in section 3 that rename/rename(1to1) (i.e. both sides +We already noted in section 4 that rename/rename(1to1) (i.e. both sides renaming a file the same way) was one counter-example. The more interesting bit, though, is why did we need to use the "almost" qualifier when stating that A:oldfile and A':newfile are "almost" always detectable as renames? -Let's repeat an earlier point that section 3 made: +Let's repeat an earlier point that section 4 made: +.... A':newfile was created by applying the changes between E:oldfile and G:newfile to A:oldfile. The changes between E:oldfile and G:newfile were <50% of the size of E:oldfile. +.... If those changes that were <50% of the size of E:oldfile are also <50% of the size of A:oldfile, then A:oldfile and A':newfile will be detectable as @@ -276,18 +293,21 @@ still somehow merge cleanly), then traditional rename detection would not detect A:oldfile and A':newfile as renames. Here's an example where that can happen: + * E:oldfile had 20 lines * G:newfile added 10 new lines at the beginning of the file * A:oldfile kept the first 3 lines of the file, and deleted all the rest + then + +.... => A':newfile would have 13 lines, 3 of which matches those in A:oldfile. -E:oldfile -> G:newfile would be detected as a rename, but A:oldfile and -A':newfile would not be. + E:oldfile -> G:newfile would be detected as a rename, but A:oldfile and + A':newfile would not be. +.... -=== 5. Why the special cases in #4 are still fully reasonable to use to === -=== pair up files for three-way content merging in the merge machinery, === -=== and why they do not affect the correctness of the merge. === +== 6. Why the special cases in #5 are still fully reasonable to use to pair up files for three-way content merging in the merge machinery, and why they do not affect the correctness of the merge. == In the rename/rename(1to1) case, A:newfile and A':newfile are not renames since they use the *same* filename. However, files with the same filename @@ -295,14 +315,14 @@ are obviously fine to pair up for three-way content merging (the merge machinery has never employed break detection). The interesting counter-example case is thus not the rename/rename(1to1) case, but the case where A did not rename oldfile. That was the case that we spent most of -the time discussing in sections 3 and 4. The remainder of this section +the time discussing in sections 4 and 5. The remainder of this section will be devoted to that case as well. So, even if A:oldfile and A':newfile aren't detectable as renames, why is it still reasonable to pair them up for three-way content merging in the merge machinery? There are multiple reasons: - * As noted in sections 3 and 4, the diff between A:oldfile and A':newfile + * As noted in sections 4 and 5, the diff between A:oldfile and A':newfile is *exactly* the same as the diff between E:oldfile and G:newfile. The latter pair were detected as renames, so it seems unlikely to surprise users for us to treat A:oldfile and A':newfile as renames. @@ -394,7 +414,7 @@ cases 1 and 3 seem to provide as good or better behavior with the optimization than without. -=== 6. Interaction with skipping of "irrelevant" renames === +== 7. Interaction with skipping of "irrelevant" renames == Previous optimizations involved skipping rename detection for paths considered to be "irrelevant". See for example the following commits: @@ -421,24 +441,27 @@ detection -- though we can limit it to the paths for which we have not already detected renames. -=== 7. Additional items that need to be cached === +== 8. Additional items that need to be cached == It turns out we have to cache more than just renames; we also cache: +.... A) non-renames (i.e. unpaired deletes) B) counts of renames within directories C) sources that were marked as RELEVANT_LOCATION, but which were downgraded to RELEVANT_NO_MORE D) the toplevel trees involved in the merge +.... These are all stored in struct rename_info, and respectively appear in + * cached_pairs (along side actual renames, just with a value of NULL) * dir_rename_counts * cached_irrelevant * merge_trees -The reason for (A) comes from the irrelevant renames skipping -optimization discussed in section 6. The fact that irrelevant renames +The reason for `(A)` comes from the irrelevant renames skipping +optimization discussed in section 7. The fact that irrelevant renames are skipped means we only get a subset of the potential renames detected and subsequent commits may need to run rename detection on the upstream side on a subset of the remaining renames (to get the @@ -447,23 +470,24 @@ deletes are involved in rename detection too, we don't want to repeatedly check that those paths remain unpaired on the upstream side with every commit we are transplanting. -The reason for (B) is that diffcore_rename_extended() is what +The reason for `(B)` is that diffcore_rename_extended() is what generates the counts of renames by directory which is needed in directory rename detection, and if we don't run diffcore_rename_extended() again then we need to have the output from it, including dir_rename_counts, from the previous run. -The reason for (C) is that merge-ort's tree traversal will again think +The reason for `(C)` is that merge-ort's tree traversal will again think those paths are relevant (marking them as RELEVANT_LOCATION), but the fact that they were downgraded to RELEVANT_NO_MORE means that dir_rename_counts already has the information we need for directory rename detection. (A path which becomes RELEVANT_CONTENT in a subsequent commit will be removed from cached_irrelevant.) -The reason for (D) is that is how we determine whether the remember +The reason for `(D)` is that is how we determine whether the remember renames optimization can be used. In particular, remembering that our sequence of merges looks like: +.... Merge 1: MERGE_BASE: E MERGE_SIDE1: G @@ -475,6 +499,7 @@ sequence of merges looks like: MERGE_SIDE1: A' MERGE_SIDE2: B => Creates B' +.... It is the fact that the trees A and A' appear both in Merge 1 and in Merge 2, with A as a parent of A' that allows this optimization. So @@ -482,12 +507,11 @@ we store the trees to compare with what we are asked to merge next time. -=== 8. How directory rename detection interacts with the above and === -=== why this optimization is still safe even if === -=== merge.directoryRenames is set to "true". === +== 9. How directory rename detection interacts with the above and why this optimization is still safe even if merge.directoryRenames is set to "true". == As noted in the assumptions section: +.... """ ...if directory renames do occur, then the default of merge.directoryRenames being set to "conflict" means that the operation @@ -497,11 +521,13 @@ As noted in the assumptions section: is that some users will have set merge.directoryRenames to "true" to allow the merges to continue to proceed automatically. """ +.... Let's remember that we need to look at how any given pick affects the next one. So let's again use the first two picks from the diagram in section one: +.... First pick does this three-way merge: MERGE_BASE: E MERGE_SIDE1: G @@ -513,6 +539,7 @@ one: MERGE_SIDE1: A' MERGE_SIDE2: B => creates B' +.... Now, directory rename detection exists so that if one side of history renames a directory, and the other side adds a new file to the old @@ -545,7 +572,7 @@ while considering all of these cases: concerned; see the assumptions section). Two interesting sub-notes about these counts: - * If we need to perform rename-detection again on the given side (e.g. + ** If we need to perform rename-detection again on the given side (e.g. some paths are relevant for rename detection that weren't before), then we clear dir_rename_counts and recompute it, making use of cached_pairs. The reason it is important to do this is optimizations @@ -556,7 +583,7 @@ while considering all of these cases: easiest way to "fix up" dir_rename_counts in such cases is to just recompute it. - * If we prune rename/rename(1to1) entries from the cache, then we also + ** If we prune rename/rename(1to1) entries from the cache, then we also need to update dir_rename_counts to decrement the counts for the involved directory and any relevant parent directories (to undo what update_dir_rename_counts() in diffcore-rename.c incremented when the @@ -578,6 +605,7 @@ in order: Case 1: MERGE_SIDE1 renames old dir, MERGE_SIDE2 adds new file to old dir +.... This case looks like this: MERGE_BASE: E, Has olddir/ @@ -595,10 +623,13 @@ Case 1: MERGE_SIDE1 renames old dir, MERGE_SIDE2 adds new file to old dir * MERGE_SIDE1 has cached olddir/newfile -> newdir/newfile Given the cached rename noted above, the second merge can proceed as expected without needing to perform rename detection from A -> A'. +.... Case 2: MERGE_SIDE1 renames old dir, MERGE_SIDE2 renames file into old dir +.... This case looks like this: + MERGE_BASE: E oldfile, olddir/ MERGE_SIDE1: G oldfile, olddir/ -> newdir/ MERGE_SIDE2: A oldfile -> olddir/newfile @@ -617,9 +648,11 @@ Case 2: MERGE_SIDE1 renames old dir, MERGE_SIDE2 renames file into old dir Given the cached rename noted above, the second merge can proceed as expected without needing to perform rename detection from A -> A'. +.... Case 3: MERGE_SIDE1 adds new file to old dir, MERGE_SIDE2 renames old dir +.... This case looks like this: MERGE_BASE: E, Has olddir/ @@ -635,9 +668,11 @@ Case 3: MERGE_SIDE1 adds new file to old dir, MERGE_SIDE2 renames old dir In this case, with the optimization, note that after the first commit there were no renames on MERGE_SIDE1, and any renames on MERGE_SIDE2 are tossed. But the second merge didn't need any renames so this is fine. +.... Case 4: MERGE_SIDE1 renames file into old dir, MERGE_SIDE2 renames old dir +.... This case looks like this: MERGE_BASE: E, Has olddir/ @@ -658,6 +693,7 @@ Case 4: MERGE_SIDE1 renames file into old dir, MERGE_SIDE2 renames old dir Given the cached rename noted above, the second merge can proceed as expected without needing to perform rename detection from A -> A'. +.... Finally, I'll just note here that interactions with the skip-irrelevant-renames optimization means we sometimes don't detect diff --git a/Documentation/technical/sparse-checkout.adoc b/Documentation/technical/sparse-checkout.adoc index 0f750ef3e3..3fa8e53655 100644 --- a/Documentation/technical/sparse-checkout.adoc +++ b/Documentation/technical/sparse-checkout.adoc @@ -14,37 +14,41 @@ Table of contents: * Reference Emails -=== Terminology === +== Terminology == -cone mode: one of two modes for specifying the desired subset of files +*`cone mode`*:: + one of two modes for specifying the desired subset of files in a sparse-checkout. In cone-mode, the user specifies directories (getting both everything under that directory as well as everything in leading directories), while in non-cone mode, the user specifies gitignore-style patterns. Controlled by the --[no-]cone option to sparse-checkout init|set. -SKIP_WORKTREE: When tracked files do not match the sparse specification and +*`SKIP_WORKTREE`*:: + When tracked files do not match the sparse specification and are removed from the working tree, the file in the index is marked with a SKIP_WORKTREE bit. Note that if a tracked file has the SKIP_WORKTREE bit set but the file is later written by the user to the working tree anyway, the SKIP_WORKTREE bit will be cleared at the beginning of any subsequent Git operation. - - Most sparse checkout users are unaware of this implementation - detail, and the term should generally be avoided in user-facing - descriptions and command flags. Unfortunately, prior to the - `sparse-checkout` subcommand this low-level detail was exposed, - and as of time of writing, is still exposed in various places. - -sparse-checkout: a subcommand in git used to reduce the files present in ++ +Most sparse checkout users are unaware of this implementation +detail, and the term should generally be avoided in user-facing +descriptions and command flags. Unfortunately, prior to the +`sparse-checkout` subcommand this low-level detail was exposed, +and as of time of writing, is still exposed in various places. + +*`sparse-checkout`*:: + a subcommand in git used to reduce the files present in the working tree to a subset of all tracked files. Also, the name of the file in the $GIT_DIR/info directory used to track the sparsity patterns corresponding to the user's desired subset. -sparse cone: see cone mode +*`sparse cone`*:: see cone mode -sparse directory: An entry in the index corresponding to a directory, which +*`sparse directory`*:: + An entry in the index corresponding to a directory, which appears in the index instead of all the files under that directory that would normally appear. See also sparse-index. Something that can cause confusion is that the "sparse directory" does NOT match @@ -52,7 +56,8 @@ sparse directory: An entry in the index corresponding to a directory, which working tree. May be renamed in the future (e.g. to "skipped directory"). -sparse index: A special mode for sparse-checkout that also makes the +*`sparse index`*:: + A special mode for sparse-checkout that also makes the index sparse by recording a directory entry in lieu of all the files underneath that directory (thus making that a "skipped directory" which unfortunately has also been called a "sparse @@ -60,7 +65,8 @@ sparse index: A special mode for sparse-checkout that also makes the directories. Controlled by the --[no-]sparse-index option to init|set|reapply. -sparsity patterns: patterns from $GIT_DIR/info/sparse-checkout used to +*`sparsity patterns`*:: + patterns from $GIT_DIR/info/sparse-checkout used to define the set of files of interest. A warning: It is easy to over-use this term (or the shortened "patterns" term), for two reasons: (1) users in cone mode specify directories rather than @@ -70,7 +76,8 @@ sparsity patterns: patterns from $GIT_DIR/info/sparse-checkout used to transiently differ in the working tree or index from the sparsity patterns (see "Sparse specification vs. sparsity patterns"). -sparse specification: The set of paths in the user's area of focus. This +*`sparse specification`*:: + The set of paths in the user's area of focus. This is typically just the tracked files that match the sparsity patterns, but the sparse specification can temporarily differ and include additional files. (See also "Sparse specification @@ -87,12 +94,13 @@ sparse specification: The set of paths in the user's area of focus. This * If working with the index and the working copy, the sparse specification is the union of the paths from above. -vivifying: When a command restores a tracked file to the working tree (and +*`vivifying`*:: + When a command restores a tracked file to the working tree (and hopefully also clears the SKIP_WORKTREE bit in the index for that file), this is referred to as "vivifying" the file. -=== Purpose of sparse-checkouts === +== Purpose of sparse-checkouts == sparse-checkouts exist to allow users to work with a subset of their files. @@ -120,14 +128,12 @@ those usecases, sparse-checkouts can modify different subcommands in over a half dozen different ways. Let's start by considering the high level usecases: - A) Users are _only_ interested in the sparse portion of the repo - - A*) Users are _only_ interested in the sparse portion of the repo - that they have downloaded so far - - B) Users want a sparse working tree, but are working in a larger whole - - C) sparse-checkout is a behind-the-scenes implementation detail allowing +[horizontal] +A):: Users are _only_ interested in the sparse portion of the repo +A*):: Users are _only_ interested in the sparse portion of the repo + that they have downloaded so far +B):: Users want a sparse working tree, but are working in a larger whole +C):: sparse-checkout is a behind-the-scenes implementation detail allowing Git to work with a specially crafted in-house virtual file system; users are actually working with a "full" working tree that is lazily populated, and sparse-checkout helps with the lazy population @@ -136,7 +142,7 @@ usecases: It may be worth explaining each of these in a bit more detail: - (Behavior A) Users are _only_ interested in the sparse portion of the repo +=== (Behavior A) Users are _only_ interested in the sparse portion of the repo These folks might know there are other things in the repository, but don't care. They are uninterested in other parts of the repository, and @@ -163,8 +169,7 @@ side-effects of various other commands (such as the printed diffstat after a merge or pull) can lead to worries about local repository size growing unnecessarily[10]. - (Behavior A*) Users are _only_ interested in the sparse portion of the repo - that they have downloaded so far (a variant on the first usecase) +=== (Behavior A*) Users are _only_ interested in the sparse portion of the repo that they have downloaded so far (a variant on the first usecase) This variant is driven by folks who using partial clones together with sparse checkouts and do disconnected development (so far sounding like a @@ -173,15 +178,14 @@ reason for yet another variant is that downloading even just the blobs through history within their sparse specification may be too much, so they only download some. They would still like operations to succeed without network connectivity, though, so things like `git log -S${SEARCH_TERM} -p` -or `git grep ${SEARCH_TERM} OLDREV ` would need to be prepared to provide +or `git grep ${SEARCH_TERM} OLDREV` would need to be prepared to provide partial results that depend on what happens to have been downloaded. This variant could be viewed as Behavior A with the sparse specification for history querying operations modified from "sparsity patterns" to "sparsity patterns limited to the blobs we have already downloaded". - (Behavior B) Users want a sparse working tree, but are working in a - larger whole +=== (Behavior B) Users want a sparse working tree, but are working in a larger whole Stolee described this usecase this way[11]: @@ -229,8 +233,7 @@ those expensive checks when interacting with the working copy, and may prefer getting "unrelated" results from their history queries over having slow commands. - (Behavior C) sparse-checkout is an implementational detail supporting a - special VFS. +=== (Behavior C) sparse-checkout is an implementational detail supporting a special VFS. This usecase goes slightly against the traditional definition of sparse-checkout in that it actually tries to present a full or dense @@ -255,13 +258,13 @@ will perceive the checkout as dense, and commands should thus behave as if all files are present. -=== Usecases of primary concern === +== Usecases of primary concern == Most of the rest of this document will focus on Behavior A and Behavior B. Some notes about the other two cases and why we are not focusing on them: - (Behavior A*) +=== (Behavior A*) Supporting this usecase is estimated to be difficult and a lot of work. There are no plans to implement it currently, but it may be a potential @@ -275,7 +278,7 @@ valid for this usecase, with the only exception being that it redefines the sparse specification to restrict it to already-downloaded blobs. The hard part is in making commands capable of respecting that modified definition. - (Behavior C) +=== (Behavior C) This usecase violates some of the early sparse-checkout documented assumptions (since files marked as SKIP_WORKTREE will be displayed to users @@ -300,20 +303,20 @@ Behavior C do not assume they are part of the Behavior B camp and propose patches that break things for the real Behavior B folks. -=== Oversimplified mental models === +== Oversimplified mental models == An oversimplification of the differences in the above behaviors is: - Behavior A: Restrict worktree and history operations to sparse specification - Behavior B: Restrict worktree operations to sparse specification; have any - history operations work across all files - Behavior C: Do not restrict either worktree or history operations to the - sparse specification...with the exception of branch checkouts or - switches which avoid writing files that will match the index so - they can later lazily be populated instead. +(Behavior A):: Restrict worktree and history operations to sparse specification +(Behavior B):: Restrict worktree operations to sparse specification; have any + history operations work across all files +(Behavior C):: Do not restrict either worktree or history operations to the + sparse specification...with the exception of branch checkouts or + switches which avoid writing files that will match the index so + they can later lazily be populated instead. -=== Desired behavior === +== Desired behavior == As noted previously, despite the simple idea of just working with a subset of files, there are a range of different behavioral changes that need to be @@ -326,37 +329,38 @@ understanding these differences can be beneficial. * Commands behaving the same regardless of high-level use-case - * commands that only look at files within the sparsity specification + ** commands that only look at files within the sparsity specification - * diff (without --cached or REVISION arguments) - * grep (without --cached or REVISION arguments) - * diff-files + *** diff (without --cached or REVISION arguments) + *** grep (without --cached or REVISION arguments) + *** diff-files - * commands that restore files to the working tree that match sparsity + ** commands that restore files to the working tree that match sparsity patterns, and remove unmodified files that don't match those patterns: - * switch - * checkout (the switch-like half) - * read-tree - * reset --hard + *** switch + *** checkout (the switch-like half) + *** read-tree + *** reset --hard - * commands that write conflicted files to the working tree, but otherwise + ** commands that write conflicted files to the working tree, but otherwise will omit writing files to the working tree that do not match the sparsity patterns: - * merge - * rebase - * cherry-pick - * revert + *** merge + *** rebase + *** cherry-pick + *** revert - * `am` and `apply --cached` should probably be in this section but + *** `am` and `apply --cached` should probably be in this section but are buggy (see the "Known bugs" section below) The behavior for these commands somewhat depends upon the merge strategy being used: - * `ort` behaves as described above - * `octopus` and `resolve` will always vivify any file changed in the merge + + *** `ort` behaves as described above + *** `octopus` and `resolve` will always vivify any file changed in the merge relative to the first parent, which is rather suboptimal. It is also important to note that these commands WILL update the index @@ -372,21 +376,21 @@ understanding these differences can be beneficial. specification and the sparsity patterns (much like the commands in the previous section). - * commands that always ignore sparsity since commits must be full-tree + ** commands that always ignore sparsity since commits must be full-tree - * archive - * bundle - * commit - * format-patch - * fast-export - * fast-import - * commit-tree + *** archive + *** bundle + *** commit + *** format-patch + *** fast-export + *** fast-import + *** commit-tree - * commands that write any modified file to the working tree (conflicted + ** commands that write any modified file to the working tree (conflicted or not, and whether those paths match sparsity patterns or not): - * stash - * apply (without `--index` or `--cached`) + *** stash + *** apply (without `--index` or `--cached`) * Commands that may slightly differ for behavior A vs. behavior B: @@ -394,19 +398,20 @@ understanding these differences can be beneficial. behaviors, but may differ in verbosity and types of warning and error messages. - * commands that make modifications to which files are tracked: - * add - * rm - * mv - * update-index + ** commands that make modifications to which files are tracked: + + *** add + *** rm + *** mv + *** update-index The fact that files can move between the 'tracked' and 'untracked' categories means some commands will have to treat untracked files differently. But if we have to treat untracked files differently, then additional commands may also need changes: - * status - * clean + *** status + *** clean In particular, `status` may need to report any untracked files outside the sparsity specification as an erroneous condition (especially to @@ -420,9 +425,10 @@ understanding these differences can be beneficial. may need to ignore the sparse specification by its nature. Also, its current --[no-]ignore-skip-worktree-entries default is totally bogus. - * commands for manually tweaking paths in both the index and the working tree - * `restore` - * the restore-like half of `checkout` + ** commands for manually tweaking paths in both the index and the working tree + + *** `restore` + *** the restore-like half of `checkout` These commands should be similar to add/rm/mv in that they should only operate on the sparse specification by default, and require a @@ -433,18 +439,19 @@ understanding these differences can be beneficial. * Commands that significantly differ for behavior A vs. behavior B: - * commands that query history - * diff (with --cached or REVISION arguments) - * grep (with --cached or REVISION arguments) - * show (when given commit arguments) - * blame (only matters when one or more -C flags are passed) - * and annotate - * log - * whatchanged (may not exist anymore) - * ls-files - * diff-index - * diff-tree - * ls-tree + ** commands that query history + + *** diff (with --cached or REVISION arguments) + *** grep (with --cached or REVISION arguments) + *** show (when given commit arguments) + *** blame (only matters when one or more -C flags are passed) + **** and annotate + *** log + *** whatchanged (may not exist anymore) + *** ls-files + *** diff-index + *** diff-tree + *** ls-tree Note: for log and whatchanged, revision walking logic is unaffected but displaying of patches is affected by scoping the command to the @@ -458,91 +465,91 @@ understanding these differences can be beneficial. * Commands I don't know how to classify - * range-diff + ** range-diff Is this like `log` or `format-patch`? - * cherry + ** cherry See range-diff * Commands unaffected by sparse-checkouts - * shortlog - * show-branch - * rev-list - * bisect - - * branch - * describe - * fetch - * gc - * init - * maintenance - * notes - * pull (merge & rebase have the necessary changes) - * push - * submodule - * tag - - * config - * filter-branch (works in separate checkout without sparse-checkout setup) - * pack-refs - * prune - * remote - * repack - * replace - - * bugreport - * count-objects - * fsck - * gitweb - * help - * instaweb - * merge-tree (doesn't touch worktree or index, and merges always compute full-tree) - * rerere - * verify-commit - * verify-tag - - * commit-graph - * hash-object - * index-pack - * mktag - * mktree - * multi-pack-index - * pack-objects - * prune-packed - * symbolic-ref - * unpack-objects - * update-ref - * write-tree (operates on index, possibly optimized to use sparse dir entries) - - * for-each-ref - * get-tar-commit-id - * ls-remote - * merge-base (merges are computed full tree, so merge base should be too) - * name-rev - * pack-redundant - * rev-parse - * show-index - * show-ref - * unpack-file - * var - * verify-pack - - * <Everything under 'Interacting with Others' in 'git help --all'> - * <Everything under 'Low-level...Syncing' in 'git help --all'> - * <Everything under 'Low-level...Internal Helpers' in 'git help --all'> - * <Everything under 'External commands' in 'git help --all'> + ** shortlog + ** show-branch + ** rev-list + ** bisect + + ** branch + ** describe + ** fetch + ** gc + ** init + ** maintenance + ** notes + ** pull (merge & rebase have the necessary changes) + ** push + ** submodule + ** tag + + ** config + ** filter-branch (works in separate checkout without sparse-checkout setup) + ** pack-refs + ** prune + ** remote + ** repack + ** replace + + ** bugreport + ** count-objects + ** fsck + ** gitweb + ** help + ** instaweb + ** merge-tree (doesn't touch worktree or index, and merges always compute full-tree) + ** rerere + ** verify-commit + ** verify-tag + + ** commit-graph + ** hash-object + ** index-pack + ** mktag + ** mktree + ** multi-pack-index + ** pack-objects + ** prune-packed + ** symbolic-ref + ** unpack-objects + ** update-ref + ** write-tree (operates on index, possibly optimized to use sparse dir entries) + + ** for-each-ref + ** get-tar-commit-id + ** ls-remote + ** merge-base (merges are computed full tree, so merge base should be too) + ** name-rev + ** pack-redundant + ** rev-parse + ** show-index + ** show-ref + ** unpack-file + ** var + ** verify-pack + + ** <Everything under 'Interacting with Others' in 'git help --all'> + ** <Everything under 'Low-level...Syncing' in 'git help --all'> + ** <Everything under 'Low-level...Internal Helpers' in 'git help --all'> + ** <Everything under 'External commands' in 'git help --all'> * Commands that might be affected, but who cares? - * merge-file - * merge-index - * gitk? + ** merge-file + ** merge-index + ** gitk? -=== Behavior classes === +== Behavior classes == From the above there are a few classes of behavior: @@ -573,18 +580,19 @@ From the above there are a few classes of behavior: Commands in this class generally behave like the "restrict" class, except that: - (1) they will ignore the sparse specification and write files with - conflicts to the working tree (thus temporarily expanding the - sparse specification to include such files.) - (2) they are grouped with commands which move to a new commit, since - they often create a commit and then move to it, even though we - know there are many exceptions to moving to the new commit. (For - example, the user may rebase a commit that becomes empty, or have - a cherry-pick which conflicts, or a user could run `merge - --no-commit`, and we also view `apply --index` kind of like `am - --no-commit`.) As such, these commands can make changes to index - files outside the sparse specification, though they'll mark such - files with SKIP_WORKTREE. + + (1) they will ignore the sparse specification and write files with + conflicts to the working tree (thus temporarily expanding the + sparse specification to include such files.) + (2) they are grouped with commands which move to a new commit, since + they often create a commit and then move to it, even though we + know there are many exceptions to moving to the new commit. (For + example, the user may rebase a commit that becomes empty, or have + a cherry-pick which conflicts, or a user could run `merge + --no-commit`, and we also view `apply --index` kind of like `am + --no-commit`.) As such, these commands can make changes to index + files outside the sparse specification, though they'll mark such + files with SKIP_WORKTREE. * "restrict also specially applied to untracked files" @@ -609,37 +617,39 @@ From the above there are a few classes of behavior: specification. -=== Subcommand-dependent defaults === +== Subcommand-dependent defaults == Note that we have different defaults depending on the command for the desired behavior : * Commands defaulting to "restrict": - * diff-files - * diff (without --cached or REVISION arguments) - * grep (without --cached or REVISION arguments) - * switch - * checkout (the switch-like half) - * reset (<commit>) - - * restore - * checkout (the restore-like half) - * checkout-index - * reset (with pathspec) + + ** diff-files + ** diff (without --cached or REVISION arguments) + ** grep (without --cached or REVISION arguments) + ** switch + ** checkout (the switch-like half) + ** reset (<commit>) + + ** restore + ** checkout (the restore-like half) + ** checkout-index + ** reset (with pathspec) This behavior makes sense; these interact with the working tree. * Commands defaulting to "restrict modulo conflicts": - * merge - * rebase - * cherry-pick - * revert - * am - * apply --index (which is kind of like an `am --no-commit`) + ** merge + ** rebase + ** cherry-pick + ** revert + + ** am + ** apply --index (which is kind of like an `am --no-commit`) - * read-tree (especially with -m or -u; is kind of like a --no-commit merge) - * reset (<tree-ish>, due to similarity to read-tree) + ** read-tree (especially with -m or -u; is kind of like a --no-commit merge) + ** reset (<tree-ish>, due to similarity to read-tree) These also interact with the working tree, but require slightly different behavior either so that (a) conflicts can be resolved or (b) @@ -648,16 +658,17 @@ desired behavior : (See also the "Known bugs" section below regarding `am` and `apply`) * Commands defaulting to "no restrict": - * archive - * bundle - * commit - * format-patch - * fast-export - * fast-import - * commit-tree - * stash - * apply (without `--index`) + ** archive + ** bundle + ** commit + ** format-patch + ** fast-export + ** fast-import + ** commit-tree + + ** stash + ** apply (without `--index`) These have completely different defaults and perhaps deserve the most detailed explanation: @@ -679,53 +690,59 @@ desired behavior : sparse specification then we'll lose changes from the user. * Commands defaulting to "restrict also specially applied to untracked files": - * add - * rm - * mv - * update-index - * status - * clean (?) - - Our original implementation for the first three of these commands was - "no restrict", but it had some severe usability issues: - * `git add <somefile>` if honored and outside the sparse - specification, can result in the file randomly disappearing later - when some subsequent command is run (since various commands - automatically clean up unmodified files outside the sparse - specification). - * `git rm '*.jpg'` could very negatively surprise users if it deletes - files outside the range of the user's interest. - * `git mv` has similar surprises when moving into or out of the cone, - so best to restrict by default - - So, we switched `add` and `rm` to default to "restrict", which made - usability problems much less severe and less frequent, but we still got - complaints because commands like: - git add <file-outside-sparse-specification> - git rm <file-outside-sparse-specification> - would silently do nothing. We should instead print an error in those - cases to get usability right. - - update-index needs to be updated to match, and status and maybe clean - also need to be updated to specially handle untracked paths. - - There may be a difference in here between behavior A and behavior B in - terms of verboseness of errors or additional warnings. + + ** add + ** rm + ** mv + ** update-index + ** status + ** clean (?) + +.... + Our original implementation for the first three of these commands was + "no restrict", but it had some severe usability issues: + + * `git add <somefile>` if honored and outside the sparse + specification, can result in the file randomly disappearing later + when some subsequent command is run (since various commands + automatically clean up unmodified files outside the sparse + specification). + * `git rm '*.jpg'` could very negatively surprise users if it deletes + files outside the range of the user's interest. + * `git mv` has similar surprises when moving into or out of the cone, + so best to restrict by default + + So, we switched `add` and `rm` to default to "restrict", which made + usability problems much less severe and less frequent, but we still got + complaints because commands like: + + git add <file-outside-sparse-specification> + git rm <file-outside-sparse-specification> + + would silently do nothing. We should instead print an error in those + cases to get usability right. + + update-index needs to be updated to match, and status and maybe clean + also need to be updated to specially handle untracked paths. + + There may be a difference in here between behavior A and behavior B in + terms of verboseness of errors or additional warnings. +.... * Commands falling under "restrict or no restrict dependent upon behavior A vs. behavior B" - * diff (with --cached or REVISION arguments) - * grep (with --cached or REVISION arguments) - * show (when given commit arguments) - * blame (only matters when one or more -C flags passed) - * and annotate - * log - * and variants: shortlog, gitk, show-branch, whatchanged, rev-list - * ls-files - * diff-index - * diff-tree - * ls-tree + ** diff (with --cached or REVISION arguments) + ** grep (with --cached or REVISION arguments) + ** show (when given commit arguments) + ** blame (only matters when one or more -C flags passed) + *** and annotate + ** log + *** and variants: shortlog, gitk, show-branch, whatchanged, rev-list + ** ls-files + ** diff-index + ** diff-tree + ** ls-tree For now, we default to behavior B for these, which want a default of "no restrict". @@ -749,7 +766,7 @@ desired behavior : implemented. -=== Sparse specification vs. sparsity patterns === +== Sparse specification vs. sparsity patterns == In a well-behaved situation, the sparse specification is given directly by the $GIT_DIR/info/sparse-checkout file. However, it can transiently @@ -821,45 +838,48 @@ under behavior B index operations are lumped with history and tend to operate full-tree. -=== Implementation Questions === - - * Do the options --scope={sparse,all} sound good to others? Are there better - options? - * Names in use, or appearing in patches, or previously suggested: - * --sparse/--dense - * --ignore-skip-worktree-bits - * --ignore-skip-worktree-entries - * --ignore-sparsity - * --[no-]restrict-to-sparse-paths - * --full-tree/--sparse-tree - * --[no-]restrict - * --scope={sparse,all} - * --focus/--unfocus - * --limit/--unlimited - * Rationale making me lean slightly towards --scope={sparse,all}: - * We want a name that works for many commands, so we need a name that +== Implementation Questions == + + * Do the options --scope={sparse,all} sound good to others? Are there better options? + + ** Names in use, or appearing in patches, or previously suggested: + + *** --sparse/--dense + *** --ignore-skip-worktree-bits + *** --ignore-skip-worktree-entries + *** --ignore-sparsity + *** --[no-]restrict-to-sparse-paths + *** --full-tree/--sparse-tree + *** --[no-]restrict + *** --scope={sparse,all} + *** --focus/--unfocus + *** --limit/--unlimited + + ** Rationale making me lean slightly towards --scope={sparse,all}: + + *** We want a name that works for many commands, so we need a name that does not conflict - * We know that we have more than two possible usecases, so it is best + *** We know that we have more than two possible usecases, so it is best to avoid a flag that appears to be binary. - * --scope={sparse,all} isn't overly long and seems relatively + *** --scope={sparse,all} isn't overly long and seems relatively explanatory - * `--sparse`, as used in add/rm/mv, is totally backwards for + *** `--sparse`, as used in add/rm/mv, is totally backwards for grep/log/etc. Changing the meaning of `--sparse` for these commands would fix the backwardness, but possibly break existing scripts. Using a new name pairing would allow us to treat `--sparse` in these commands as a deprecated alias. - * There is a different `--sparse`/`--dense` pair for commands using + *** There is a different `--sparse`/`--dense` pair for commands using revision machinery, so using that naming might cause confusion - * There is also a `--sparse` in both pack-objects and show-branch, which + *** There is also a `--sparse` in both pack-objects and show-branch, which don't conflict but do suggest that `--sparse` is overloaded - * The name --ignore-skip-worktree-bits is a double negative, is + *** The name --ignore-skip-worktree-bits is a double negative, is quite a mouthful, refers to an implementation detail that many users may not be familiar with, and we'd need a negation for it which would probably be even more ridiculously long. (But we can make --ignore-skip-worktree-bits a deprecated alias for --no-restrict.) - * If a config option is added (sparse.scope?) what should the values and + ** If a config option is added (sparse.scope?) what should the values and description be? "sparse" (behavior A), "worktree-sparse-history-dense" (behavior B), "dense" (behavior C)? There's a risk of confusion, because even for Behaviors A and B we want some commands to be @@ -868,19 +888,20 @@ operate full-tree. the primary difference we are focusing is just the history-querying commands (log/diff/grep). Previous config suggestion here: [13] - * Is `--no-expand` a good alias for ls-files's `--sparse` option? + ** Is `--no-expand` a good alias for ls-files's `--sparse` option? (`--sparse` does not map to either `--scope=sparse` or `--scope=all`, because in non-cone mode it does nothing and in cone-mode it shows the sparse directory entries which are technically outside the sparse specification) - * Under Behavior A: - * Does ls-files' `--no-expand` override the default `--scope=all`, or + ** Under Behavior A: + + *** Does ls-files' `--no-expand` override the default `--scope=all`, or does it need an extra flag? - * Does ls-files' `-t` option imply `--scope=all`? - * Does update-index's `--[no-]skip-worktree` option imply `--scope=all`? + *** Does ls-files' `-t` option imply `--scope=all`? + *** Does update-index's `--[no-]skip-worktree` option imply `--scope=all`? - * sparse-checkout: once behavior A is fully implemented, should we take + ** sparse-checkout: once behavior A is fully implemented, should we take an interim measure to ease people into switching the default? Namely, if folks are not already in a sparse checkout, then require `sparse-checkout init/set` to take a @@ -892,7 +913,7 @@ operate full-tree. is seamless for them. -=== Implementation Goals/Plans === +== Implementation Goals/Plans == * Get buy-in on this document in general. @@ -910,25 +931,26 @@ operate full-tree. request that they not trigger this bug." flag * Flags & Config - * Make `--sparse` in add/rm/mv a deprecated alias for `--scope=all` - * Make `--ignore-skip-worktree-bits` in checkout-index/checkout/restore + + ** Make `--sparse` in add/rm/mv a deprecated alias for `--scope=all` + ** Make `--ignore-skip-worktree-bits` in checkout-index/checkout/restore a deprecated aliases for `--scope=all` - * Create config option (sparse.scope?), tie it to the "Cliff notes" + ** Create config option (sparse.scope?), tie it to the "Cliff notes" overview - * Add --scope=sparse (and --scope=all) flag to each of the history querying + ** Add --scope=sparse (and --scope=all) flag to each of the history querying commands. IMPORTANT: make sure diff machinery changes don't mess with format-patch, fast-export, etc. -=== Known bugs === +== Known bugs == This list used to be a lot longer (see e.g. [1,2,3,4,5,6,7,8,9]), but we've been working on it. -0. Behavior A is not well supported in Git. (Behavior B didn't used to +1. Behavior A is not well supported in Git. (Behavior B didn't used to be either, but was the easier of the two to implement.) -1. am and apply: +2. am and apply: apply, without `--index` or `--cached`, relies on files being present in the working copy, and also writes to them unconditionally. As @@ -948,7 +970,7 @@ been working on it. files and then complain that those vivified files would be overwritten by merge. -2. reset --hard: +3. reset --hard: reset --hard provides confusing error message (works correctly, but misleads the user into believing it didn't): @@ -971,13 +993,13 @@ been working on it. `git reset --hard` DID remove addme from the index and the working tree, contrary to the error message, but in line with how reset --hard should behave. -3. read-tree +4. read-tree `read-tree` doesn't apply the 'SKIP_WORKTREE' bit to *any* of the entries it reads into the index, resulting in all your files suddenly appearing to be "deleted". -4. Checkout, restore: +5. Checkout, restore: These command do not handle path & revision arguments appropriately: @@ -1030,7 +1052,7 @@ been working on it. S tracked H tracked-but-maybe-skipped -5. checkout and restore --staged, continued: +6. checkout and restore --staged, continued: These commands do not correctly scope operations to the sparse specification, and make it worse by not setting important SKIP_WORKTREE @@ -1046,56 +1068,82 @@ been working on it. the sparse specification, but then it will be important to set the SKIP_WORKTREE bits appropriately. -6. Performance issues; see: - https://lore.kernel.org/git/CABPp-BEkJQoKZsQGCYioyga_uoDQ6iBeW+FKr8JhyuuTMK1RDw@mail.gmail.com/ +7. Performance issues; see: + + https://lore.kernel.org/git/CABPp-BEkJQoKZsQGCYioyga_uoDQ6iBeW+FKr8JhyuuTMK1RDw@mail.gmail.com/ -=== Reference Emails === +== Reference Emails == Emails that detail various bugs we've had in sparse-checkout: -[1] (Original descriptions of behavior A & behavior B) - https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/ -[2] (Fix stash applications in sparse checkouts; bugs from behavioral differences) - https://lore.kernel.org/git/ccfedc7140dbf63ba26a15f93bd3885180b26517.1606861519.git.gitgitgadget@gmail.com/ -[3] (Present-despite-skipped entries) - https://lore.kernel.org/git/11d46a399d26c913787b704d2b7169cafc28d639.1642175983.git.gitgitgadget@gmail.com/ -[4] (Clone --no-checkout interaction) - https://lore.kernel.org/git/pull.801.v2.git.git.1591324899170.gitgitgadget@gmail.com/ (clone --no-checkout) -[5] (The need for update_sparsity() and avoiding `read-tree -mu HEAD`) - https://lore.kernel.org/git/3a1f084641eb47515b5a41ed4409a36128913309.1585270142.git.gitgitgadget@gmail.com/ -[6] (SKIP_WORKTREE is advisory, not mandatory) - https://lore.kernel.org/git/844306c3e86ef67591cc086decb2b760e7d710a3.1585270142.git.gitgitgadget@gmail.com/ -[7] (`worktree add` should copy sparsity settings from current worktree) - https://lore.kernel.org/git/c51cb3714e7b1d2f8c9370fe87eca9984ff4859f.1644269584.git.gitgitgadget@gmail.com/ -[8] (Avoid negative surprises in add, rm, and mv) - https://lore.kernel.org/git/cover.1617914011.git.matheus.bernardino@usp.br/ - https://lore.kernel.org/git/pull.1018.v4.git.1632497954.gitgitgadget@gmail.com/ -[9] (Move from out-of-cone to in-cone) - https://lore.kernel.org/git/20220630023737.473690-6-shaoxuan.yuan02@gmail.com/ - https://lore.kernel.org/git/20220630023737.473690-4-shaoxuan.yuan02@gmail.com/ -[10] (Unnecessarily downloading objects outside sparse specification) - https://lore.kernel.org/git/CAOLTT8QfwOi9yx_qZZgyGa8iL8kHWutEED7ok_jxwTcYT_hf9Q@mail.gmail.com/ - -[11] (Stolee's comments on high-level usecases) - https://lore.kernel.org/git/1a1e33f6-3514-9afc-0a28-5a6b85bd8014@gmail.com/ +[1] (Original descriptions of behavior A & behavior B): + +https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/ + +[2] (Fix stash applications in sparse checkouts; bugs from behavioral differences): + +https://lore.kernel.org/git/ccfedc7140dbf63ba26a15f93bd3885180b26517.1606861519.git.gitgitgadget@gmail.com/ + +[3] (Present-despite-skipped entries): + +https://lore.kernel.org/git/11d46a399d26c913787b704d2b7169cafc28d639.1642175983.git.gitgitgadget@gmail.com/ + +[4] (Clone --no-checkout interaction): + +https://lore.kernel.org/git/pull.801.v2.git.git.1591324899170.gitgitgadget@gmail.com/ (clone --no-checkout) + +[5] (The need for update_sparsity() and avoiding `read-tree -mu HEAD`): + +https://lore.kernel.org/git/3a1f084641eb47515b5a41ed4409a36128913309.1585270142.git.gitgitgadget@gmail.com/ + +[6] (SKIP_WORKTREE is advisory, not mandatory): + +https://lore.kernel.org/git/844306c3e86ef67591cc086decb2b760e7d710a3.1585270142.git.gitgitgadget@gmail.com/ + +[7] (`worktree add` should copy sparsity settings from current worktree): + +https://lore.kernel.org/git/c51cb3714e7b1d2f8c9370fe87eca9984ff4859f.1644269584.git.gitgitgadget@gmail.com/ + +[8] (Avoid negative surprises in add, rm, and mv): + + * https://lore.kernel.org/git/cover.1617914011.git.matheus.bernardino@usp.br/ + * https://lore.kernel.org/git/pull.1018.v4.git.1632497954.gitgitgadget@gmail.com/ + +[9] (Move from out-of-cone to in-cone): + + * https://lore.kernel.org/git/20220630023737.473690-6-shaoxuan.yuan02@gmail.com/ + * https://lore.kernel.org/git/20220630023737.473690-4-shaoxuan.yuan02@gmail.com/ + +[10] (Unnecessarily downloading objects outside sparse specification): + +https://lore.kernel.org/git/CAOLTT8QfwOi9yx_qZZgyGa8iL8kHWutEED7ok_jxwTcYT_hf9Q@mail.gmail.com/ + +[11] (Stolee's comments on high-level usecases): + +https://lore.kernel.org/git/1a1e33f6-3514-9afc-0a28-5a6b85bd8014@gmail.com/ [12] Others commenting on eventually switching default to behavior A: + * https://lore.kernel.org/git/xmqqh719pcoo.fsf@gitster.g/ * https://lore.kernel.org/git/xmqqzgeqw0sy.fsf@gitster.g/ * https://lore.kernel.org/git/a86af661-cf58-a4e5-0214-a67d3a794d7e@github.com/ -[13] Previous config name suggestion and description - * https://lore.kernel.org/git/CABPp-BE6zW0nJSStcVU=_DoDBnPgLqOR8pkTXK3dW11=T01OhA@mail.gmail.com/ +[13] Previous config name suggestion and description: + + https://lore.kernel.org/git/CABPp-BE6zW0nJSStcVU=_DoDBnPgLqOR8pkTXK3dW11=T01OhA@mail.gmail.com/ [14] Tangential issue: switch to cone mode as default sparse specification mechanism: - https://lore.kernel.org/git/a1b68fd6126eb341ef3637bb93fedad4309b36d0.1650594746.git.gitgitgadget@gmail.com/ + +https://lore.kernel.org/git/a1b68fd6126eb341ef3637bb93fedad4309b36d0.1650594746.git.gitgitgadget@gmail.com/ [15] Lengthy email on grep behavior, covering what should be searched: - * https://lore.kernel.org/git/CABPp-BGVO3QdbfE84uF_3QDF0-y2iHHh6G5FAFzNRfeRitkuHw@mail.gmail.com/ + +https://lore.kernel.org/git/CABPp-BGVO3QdbfE84uF_3QDF0-y2iHHh6G5FAFzNRfeRitkuHw@mail.gmail.com/ [16] Email explaining sparsity patterns vs. SKIP_WORKTREE and history operations, search for the parenthetical comment starting "We do not check". - https://lore.kernel.org/git/CABPp-BFsCPPNOZ92JQRJeGyNd0e-TCW-LcLyr0i_+VSQJP+GCg@mail.gmail.com/ + +https://lore.kernel.org/git/CABPp-BFsCPPNOZ92JQRJeGyNd0e-TCW-LcLyr0i_+VSQJP+GCg@mail.gmail.com/ [17] https://lore.kernel.org/git/20220207190320.2960362-1-jonathantanmy@google.com/ diff --git a/Documentation/urls-remotes.adoc b/Documentation/urls-remotes.adoc index 9b10151198..57b1646d3e 100644 --- a/Documentation/urls-remotes.adoc +++ b/Documentation/urls-remotes.adoc @@ -92,5 +92,47 @@ git push uses: ------------ +[[UPSTREAM-BRANCHES]] +UPSTREAM BRANCHES +----------------- + +Branches in Git can optionally have an upstream remote branch. +Git defaults to using the upstream branch for remote operations, for example: + +* It's the default for `git pull` or `git fetch` with no arguments. +* It's the default for `git push` with no arguments, with some exceptions. + For example, you can use the `branch.<name>.pushRemote` option to push + to a different remote than you pull from, and by default with + `push.default=simple` the upstream branch you configure must have + the same name. +* Various commands, including `git checkout` and `git status`, will + show you how many commits have been added to your current branch and + the upstream since you forked from it, for example "Your branch and + '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" +fields. For example, if `main`'s upstream is `origin/main`: +------------ +[branch "main"] + remote = origin + merge = refs/heads/main +------------ +You can set an upstream branch explicitly with +`git push --set-upstream <remote> <branch>` +but Git will often automatically set the upstream for you, for example: + +* When you clone a repository, Git will automatically set the upstream + for the default branch. +* If you have the `push.autoSetupRemote` configuration option set, + `git push` will automatically set the upstream the first time you push + a branch. +* Checking out a remote-tracking branch with `git checkout <branch>` + will automatically create a local branch with that name and set + the upstream to the remote branch. + +[NOTE] +Upstream branches are sometimes referred to as "tracking information", +as in "set the branch's tracking information". @@ -483,6 +483,14 @@ include shared.mak # Define LIBPCREDIR=/foo/bar if your PCRE header and library files are # in /foo/bar/include and /foo/bar/lib directories. # +# == Optional Rust support == +# +# Define WITH_RUST if you want to include features and subsystems written in +# Rust into Git. For now, Rust is still an optional feature of the build +# process. With Git 3.0 though, Rust will always be enabled. +# +# Building Rust code requires Cargo. +# # == SHA-1 and SHA-256 defines == # # === SHA-1 backend === @@ -683,6 +691,7 @@ OBJECTS = OTHER_PROGRAMS = PROGRAM_OBJS = PROGRAMS = +RUST_SOURCES = EXCLUDED_PROGRAMS = SCRIPT_PERL = SCRIPT_PYTHON = @@ -918,8 +927,107 @@ export PYTHON_PATH TEST_SHELL_PATH = $(SHELL_PATH) LIB_FILE = libgit.a -XDIFF_LIB = xdiff/lib.a -REFTABLE_LIB = reftable/libreftable.a +ifdef DEBUG +RUST_LIB = target/debug/libgitcore.a +else +RUST_LIB = target/release/libgitcore.a +endif + +GITLIBS = common-main.o $(LIB_FILE) +EXTLIBS = + +GIT_USER_AGENT = git/$(GIT_VERSION) + +ifeq ($(wildcard sha1collisiondetection/lib/sha1.h),sha1collisiondetection/lib/sha1.h) +DC_SHA1_SUBMODULE = auto +endif + +# Set CFLAGS, LDFLAGS and other *FLAGS variables. These might be +# tweaked by config.* below as well as the command-line, both of +# which'll override these defaults. +# Older versions of GCC may require adding "-std=gnu99" at the end. +CFLAGS = -g -O2 -Wall +LDFLAGS = +CC_LD_DYNPATH = -Wl,-rpath, +BASIC_CFLAGS = -I. +BASIC_LDFLAGS = + +# library flags +ARFLAGS = rcs +PTHREAD_CFLAGS = + +# Rust flags +CARGO_ARGS = +ifndef V +CARGO_ARGS += --quiet +endif +ifndef DEBUG +CARGO_ARGS += --release +endif + +# For the 'sparse' target +SPARSE_FLAGS ?= -std=gnu99 -D__STDC_NO_VLA__ +SP_EXTRA_FLAGS = + +# For informing GIT-BUILD-OPTIONS of the SANITIZE=leak,address targets +SANITIZE_LEAK = +SANITIZE_ADDRESS = + +# For the 'coccicheck' target +SPATCH_INCLUDE_FLAGS = --all-includes +SPATCH_FLAGS = +SPATCH_TEST_FLAGS = + +# If *.o files are present, have "coccicheck" depend on them, with +# COMPUTE_HEADER_DEPENDENCIES this will speed up the common-case of +# only needing to re-generate coccicheck results for the users of a +# given API if it's changed, and not all files in the project. If +# COMPUTE_HEADER_DEPENDENCIES=no this will be unset too. +SPATCH_USE_O_DEPENDENCIES = YesPlease + +# Set SPATCH_CONCAT_COCCI to concatenate the contrib/cocci/*.cocci +# files into a single contrib/cocci/ALL.cocci before running +# "coccicheck". +# +# Pros: +# +# - Speeds up a one-shot run of "make coccicheck", as we won't have to +# parse *.[ch] files N times for the N *.cocci rules +# +# Cons: +# +# - Will make incremental development of *.cocci slower, as +# e.g. changing strbuf.cocci will re-run all *.cocci. +# +# - Makes error and performance analysis harder, as rules will be +# applied from a monolithic ALL.cocci, rather than +# e.g. strbuf.cocci. To work around this either undefine this, or +# generate a specific patch, e.g. this will always use strbuf.cocci, +# not ALL.cocci: +# +# make contrib/coccinelle/strbuf.cocci.patch +SPATCH_CONCAT_COCCI = YesPlease + +# Rebuild 'coccicheck' if $(SPATCH), its flags etc. change +TRACK_SPATCH_DEFINES = +TRACK_SPATCH_DEFINES += $(SPATCH) +TRACK_SPATCH_DEFINES += $(SPATCH_INCLUDE_FLAGS) +TRACK_SPATCH_DEFINES += $(SPATCH_FLAGS) +TRACK_SPATCH_DEFINES += $(SPATCH_TEST_FLAGS) +GIT-SPATCH-DEFINES: FORCE + @FLAGS='$(TRACK_SPATCH_DEFINES)'; \ + if test x"$$FLAGS" != x"`cat GIT-SPATCH-DEFINES 2>/dev/null`" ; then \ + echo >&2 " * new spatch flags"; \ + echo "$$FLAGS" >GIT-SPATCH-DEFINES; \ + fi + +include config.mak.uname +-include config.mak.autogen +-include config.mak + +ifdef DEVELOPER +include config.mak.dev +endif GENERATED_H += command-list.h GENERATED_H += config-list.h @@ -1137,6 +1245,20 @@ LIB_OBJS += refs/iterator.o LIB_OBJS += refs/packed-backend.o LIB_OBJS += refs/ref-cache.o LIB_OBJS += refspec.o +LIB_OBJS += reftable/basics.o +LIB_OBJS += reftable/block.o +LIB_OBJS += reftable/blocksource.o +LIB_OBJS += reftable/error.o +LIB_OBJS += reftable/fsck.o +LIB_OBJS += reftable/iter.o +LIB_OBJS += reftable/merged.o +LIB_OBJS += reftable/pq.o +LIB_OBJS += reftable/record.o +LIB_OBJS += reftable/stack.o +LIB_OBJS += reftable/system.o +LIB_OBJS += reftable/table.o +LIB_OBJS += reftable/tree.o +LIB_OBJS += reftable/writer.o LIB_OBJS += remote.o LIB_OBJS += replace-object.o LIB_OBJS += repo-settings.o @@ -1198,7 +1320,9 @@ LIB_OBJS += urlmatch.o LIB_OBJS += usage.o LIB_OBJS += userdiff.o LIB_OBJS += utf8.o +ifndef WITH_RUST LIB_OBJS += varint.o +endif LIB_OBJS += version.o LIB_OBJS += versioncmp.o LIB_OBJS += walker.o @@ -1209,6 +1333,13 @@ LIB_OBJS += write-or-die.o LIB_OBJS += ws.o LIB_OBJS += wt-status.o LIB_OBJS += xdiff-interface.o +LIB_OBJS += xdiff/xdiffi.o +LIB_OBJS += xdiff/xemit.o +LIB_OBJS += xdiff/xhistogram.o +LIB_OBJS += xdiff/xmerge.o +LIB_OBJS += xdiff/xpatience.o +LIB_OBJS += xdiff/xprepare.o +LIB_OBJS += xdiff/xutils.o BUILTIN_OBJS += builtin/add.o BUILTIN_OBJS += builtin/am.o @@ -1390,93 +1521,8 @@ CLAR_TEST_OBJS += $(UNIT_TEST_DIR)/unit-test.o UNIT_TEST_OBJS += $(UNIT_TEST_DIR)/test-lib.o -# xdiff and reftable libs may in turn depend on what is in libgit.a -GITLIBS = common-main.o $(LIB_FILE) $(XDIFF_LIB) $(REFTABLE_LIB) $(LIB_FILE) -EXTLIBS = - -GIT_USER_AGENT = git/$(GIT_VERSION) - -ifeq ($(wildcard sha1collisiondetection/lib/sha1.h),sha1collisiondetection/lib/sha1.h) -DC_SHA1_SUBMODULE = auto -endif - -# Set CFLAGS, LDFLAGS and other *FLAGS variables. These might be -# tweaked by config.* below as well as the command-line, both of -# which'll override these defaults. -# Older versions of GCC may require adding "-std=gnu99" at the end. -CFLAGS = -g -O2 -Wall -LDFLAGS = -CC_LD_DYNPATH = -Wl,-rpath, -BASIC_CFLAGS = -I. -BASIC_LDFLAGS = - -# library flags -ARFLAGS = rcs -PTHREAD_CFLAGS = - -# For the 'sparse' target -SPARSE_FLAGS ?= -std=gnu99 -D__STDC_NO_VLA__ -SP_EXTRA_FLAGS = - -# For informing GIT-BUILD-OPTIONS of the SANITIZE=leak,address targets -SANITIZE_LEAK = -SANITIZE_ADDRESS = - -# For the 'coccicheck' target -SPATCH_INCLUDE_FLAGS = --all-includes -SPATCH_FLAGS = -SPATCH_TEST_FLAGS = - -# If *.o files are present, have "coccicheck" depend on them, with -# COMPUTE_HEADER_DEPENDENCIES this will speed up the common-case of -# only needing to re-generate coccicheck results for the users of a -# given API if it's changed, and not all files in the project. If -# COMPUTE_HEADER_DEPENDENCIES=no this will be unset too. -SPATCH_USE_O_DEPENDENCIES = YesPlease - -# Set SPATCH_CONCAT_COCCI to concatenate the contrib/cocci/*.cocci -# files into a single contrib/cocci/ALL.cocci before running -# "coccicheck". -# -# Pros: -# -# - Speeds up a one-shot run of "make coccicheck", as we won't have to -# parse *.[ch] files N times for the N *.cocci rules -# -# Cons: -# -# - Will make incremental development of *.cocci slower, as -# e.g. changing strbuf.cocci will re-run all *.cocci. -# -# - Makes error and performance analysis harder, as rules will be -# applied from a monolithic ALL.cocci, rather than -# e.g. strbuf.cocci. To work around this either undefine this, or -# generate a specific patch, e.g. this will always use strbuf.cocci, -# not ALL.cocci: -# -# make contrib/coccinelle/strbuf.cocci.patch -SPATCH_CONCAT_COCCI = YesPlease - -# Rebuild 'coccicheck' if $(SPATCH), its flags etc. change -TRACK_SPATCH_DEFINES = -TRACK_SPATCH_DEFINES += $(SPATCH) -TRACK_SPATCH_DEFINES += $(SPATCH_INCLUDE_FLAGS) -TRACK_SPATCH_DEFINES += $(SPATCH_FLAGS) -TRACK_SPATCH_DEFINES += $(SPATCH_TEST_FLAGS) -GIT-SPATCH-DEFINES: FORCE - @FLAGS='$(TRACK_SPATCH_DEFINES)'; \ - if test x"$$FLAGS" != x"`cat GIT-SPATCH-DEFINES 2>/dev/null`" ; then \ - echo >&2 " * new spatch flags"; \ - echo "$$FLAGS" >GIT-SPATCH-DEFINES; \ - fi - -include config.mak.uname --include config.mak.autogen --include config.mak - -ifdef DEVELOPER -include config.mak.dev -endif +RUST_SOURCES += src/lib.rs +RUST_SOURCES += src/varint.rs GIT-VERSION-FILE: FORCE @OLD=$$(cat $@ 2>/dev/null || :) && \ @@ -1507,6 +1553,11 @@ endif ALL_CFLAGS = $(DEVELOPER_CFLAGS) $(CPPFLAGS) $(CFLAGS) $(CFLAGS_APPEND) ALL_LDFLAGS = $(LDFLAGS) $(LDFLAGS_APPEND) +ifdef WITH_RUST +BASIC_CFLAGS += -DWITH_RUST +GITLIBS += $(RUST_LIB) +endif + ifdef SANITIZE SANITIZERS := $(foreach flag,$(subst $(comma),$(space),$(SANITIZE)),$(flag)) BASIC_CFLAGS += -fsanitize=$(SANITIZE) -fno-sanitize-recover=$(SANITIZE) @@ -2723,30 +2774,6 @@ reconfigure config.mak.autogen: config.status .PHONY: reconfigure # This is a convenience target. endif -XDIFF_OBJS += xdiff/xdiffi.o -XDIFF_OBJS += xdiff/xemit.o -XDIFF_OBJS += xdiff/xhistogram.o -XDIFF_OBJS += xdiff/xmerge.o -XDIFF_OBJS += xdiff/xpatience.o -XDIFF_OBJS += xdiff/xprepare.o -XDIFF_OBJS += xdiff/xutils.o -.PHONY: xdiff-objs -xdiff-objs: $(XDIFF_OBJS) - -REFTABLE_OBJS += reftable/basics.o -REFTABLE_OBJS += reftable/error.o -REFTABLE_OBJS += reftable/block.o -REFTABLE_OBJS += reftable/blocksource.o -REFTABLE_OBJS += reftable/iter.o -REFTABLE_OBJS += reftable/merged.o -REFTABLE_OBJS += reftable/pq.o -REFTABLE_OBJS += reftable/record.o -REFTABLE_OBJS += reftable/stack.o -REFTABLE_OBJS += reftable/system.o -REFTABLE_OBJS += reftable/table.o -REFTABLE_OBJS += reftable/tree.o -REFTABLE_OBJS += reftable/writer.o - TEST_OBJS := $(patsubst %$X,%.o,$(TEST_PROGRAMS)) $(patsubst %,t/helper/%,$(TEST_BUILTINS_OBJS)) .PHONY: test-objs @@ -2767,9 +2794,8 @@ OBJECTS += $(GIT_OBJS) OBJECTS += $(SCALAR_OBJS) OBJECTS += $(PROGRAM_OBJS) OBJECTS += $(TEST_OBJS) -OBJECTS += $(XDIFF_OBJS) OBJECTS += $(FUZZ_OBJS) -OBJECTS += $(REFTABLE_OBJS) $(REFTABLE_TEST_OBJS) +OBJECTS += $(REFTABLE_TEST_OBJS) OBJECTS += $(UNIT_TEST_OBJS) OBJECTS += $(CLAR_TEST_OBJS) OBJECTS += $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(UNIT_TEST_PROGRAMS)) @@ -2921,11 +2947,11 @@ scalar$X: scalar.o GIT-LDFLAGS $(GITLIBS) $(LIB_FILE): $(LIB_OBJS) $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ -$(XDIFF_LIB): $(XDIFF_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ +$(RUST_LIB): Cargo.toml $(RUST_SOURCES) + $(QUIET_CARGO)cargo build $(CARGO_ARGS) -$(REFTABLE_LIB): $(REFTABLE_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ +.PHONY: rust +rust: $(RUST_LIB) export DEFAULT_EDITOR DEFAULT_PAGER @@ -3765,12 +3791,13 @@ clean: profile-clean coverage-clean cocciclean $(RM) git.rc git.res $(RM) $(OBJECTS) $(RM) headless-git.o - $(RM) $(LIB_FILE) $(XDIFF_LIB) $(REFTABLE_LIB) + $(RM) $(LIB_FILE) $(RM) $(ALL_PROGRAMS) $(SCRIPT_LIB) $(BUILT_INS) $(OTHER_PROGRAMS) $(RM) $(TEST_PROGRAMS) $(RM) $(FUZZ_PROGRAMS) $(RM) $(SP_OBJ) $(RM) $(HCC) + $(RM) -r Cargo.lock target/ $(RM) version-def.h $(RM) -r $(dep_dirs) $(compdb_dir) compile_commands.json $(RM) $(test_bindir_programs) @@ -3958,8 +3985,6 @@ endif LIBGIT_PUB_OBJS += contrib/libgit-sys/public_symbol_export.o LIBGIT_PUB_OBJS += libgit.a -LIBGIT_PUB_OBJS += reftable/libreftable.a -LIBGIT_PUB_OBJS += xdiff/lib.a LIBGIT_PARTIAL_EXPORT = contrib/libgit-sys/partial_symbol_export.o diff --git a/add-interactive.c b/add-interactive.c index 6ffe64c38d..68fc09547d 100644 --- a/add-interactive.c +++ b/add-interactive.c @@ -244,7 +244,8 @@ static void find_unique_prefixes(struct prefix_item_list *list) static ssize_t find_unique(const char *string, struct prefix_item_list *list) { - int index = string_list_find_insert_index(&list->sorted, string, 1); + bool exact_match; + size_t index = string_list_find_insert_index(&list->sorted, string, &exact_match); struct string_list_item *item; if (list->items.nr != list->sorted.nr) @@ -252,8 +253,8 @@ static ssize_t find_unique(const char *string, struct prefix_item_list *list) " vs %"PRIuMAX")", (uintmax_t)list->items.nr, (uintmax_t)list->sorted.nr); - if (index < 0) - item = list->sorted.items[-1 - index].util; + if (exact_match) + item = list->sorted.items[index].util; else if (index > 0 && starts_with(list->sorted.items[index - 1].string, string)) return -1; diff --git a/add-patch.c b/add-patch.c index 737fafdefc..ae9a20d8f2 100644 --- a/add-patch.c +++ b/add-patch.c @@ -956,6 +956,7 @@ static int split_hunk(struct add_p_state *s, struct file_diff *file_diff, * sizeof(*hunk)); hunk = file_diff->hunk + hunk_index; hunk->splittable_into = 1; + hunk->use = UNDECIDED_HUNK; memset(hunk + 1, 0, (splittable_into - 1) * sizeof(*hunk)); header = &hunk->header; @@ -1057,7 +1058,7 @@ next_hunk_line: hunk++; hunk->splittable_into = 1; - hunk->use = hunk[-1].use; + hunk->use = UNDECIDED_HUNK; header = &hunk->header; header->old_count = header->new_count = context_line_count; @@ -1184,19 +1185,29 @@ static ssize_t recount_edited_hunk(struct add_p_state *s, struct hunk *hunk, { struct hunk_header *header = &hunk->header; size_t i; + char ch, marker = ' '; + hunk->splittable_into = 0; header->old_count = header->new_count = 0; for (i = hunk->start; i < hunk->end; ) { - switch(normalize_marker(&s->plain.buf[i])) { + ch = normalize_marker(&s->plain.buf[i]); + switch (ch) { case '-': header->old_count++; + if (marker == ' ') + hunk->splittable_into++; + marker = ch; break; case '+': header->new_count++; + if (marker == ' ') + hunk->splittable_into++; + marker = ch; break; case ' ': header->old_count++; header->new_count++; + marker = ch; break; } @@ -2909,9 +2909,6 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb) struct blame_bloom_data *bd; struct bloom_filter_settings *bs; - if (!sb->repo->objects->commit_graph) - return; - bs = get_bloom_filter_settings(sb->repo); if (!bs) return; @@ -452,10 +452,12 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, filter = bloom_filter_slab_at(&bloom_filters, c); if (!filter->data) { + struct commit_graph *g; uint32_t graph_pos; - if (repo_find_commit_pos_in_graph(r, c, &graph_pos)) - load_bloom_filter_from_graph(r->objects->commit_graph, - filter, graph_pos); + + g = repo_find_commit_pos_in_graph(r, c, &graph_pos); + if (g) + load_bloom_filter_from_graph(g, filter, graph_pos); } if (filter->data && filter->len) { diff --git a/builtin/backfill.c b/builtin/backfill.c index 80056abe47..e80fc1b694 100644 --- a/builtin/backfill.c +++ b/builtin/backfill.c @@ -53,7 +53,7 @@ static void download_batch(struct backfill_context *ctx) * We likely have a new packfile. Add it to the packed list to * avoid possible duplicate downloads of the same objects. */ - reprepare_packed_git(ctx->repo); + odb_reprepare(ctx->repo->objects); } static int fill_missing_blobs(const char *path UNUSED, diff --git a/builtin/cat-file.c b/builtin/cat-file.c index fce0b06451..5ca2ca3852 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -495,7 +495,7 @@ static void batch_object_write(const char *obj_name, OBJECT_INFO_LOOKUP_REPLACE); if (ret < 0) { if (data->mode == S_IFGITLINK) - report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "submodule"); + report_object_status(opt, NULL, &data->oid, "submodule"); else report_object_status(opt, obj_name, &data->oid, "missing"); return; @@ -852,9 +852,10 @@ static void batch_each_object(struct batch_options *opt, if (bitmap && !for_each_bitmapped_object(bitmap, &opt->objects_filter, batch_one_object_bitmapped, &payload)) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *pack; - for (pack = get_all_packs(the_repository); pack; pack = pack->next) { + for (pack = packfile_store_get_all_packs(packs); pack; pack = pack->next) { if (bitmap_index_contains_pack(bitmap, pack) || open_pack_index(pack)) continue; diff --git a/builtin/count-objects.c b/builtin/count-objects.c index a61d3b46aa..f2f407c2a7 100644 --- a/builtin/count-objects.c +++ b/builtin/count-objects.c @@ -122,6 +122,7 @@ int cmd_count_objects(int argc, count_loose, count_cruft, NULL, NULL); if (verbose) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; unsigned long num_pack = 0; off_t size_pack = 0; @@ -129,7 +130,7 @@ int cmd_count_objects(int argc, struct strbuf pack_buf = STRBUF_INIT; struct strbuf garbage_buf = STRBUF_INIT; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!p->pack_local) continue; if (open_pack_index(p)) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 2010e78475..606c6aea82 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -899,11 +899,11 @@ static void end_packfile(void) idx_name = keep_pack(create_index()); /* Register the packfile with core git's machinery. */ - new_p = add_packed_git(pack_data->repo, idx_name, strlen(idx_name), 1); + new_p = packfile_store_load_pack(pack_data->repo->objects->packfiles, + idx_name, 1); if (!new_p) die("core git rejected index %s", idx_name); all_packs[pack_id] = new_p; - install_packed_git(the_repository, new_p); free(idx_name); /* Print the boundary */ @@ -954,6 +954,7 @@ static int store_object( struct object_id *oidout, uintmax_t mark) { + struct packfile_store *packs = the_repository->objects->packfiles; void *out, *delta; struct object_entry *e; unsigned char hdr[96]; @@ -977,7 +978,7 @@ static int store_object( if (e->idx.offset) { duplicate_count_by_type[type]++; return 1; - } else if (find_oid_pack(&oid, get_all_packs(the_repository))) { + } else if (find_oid_pack(&oid, packfile_store_get_all_packs(packs))) { e->type = type; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ @@ -1094,6 +1095,7 @@ static void truncate_pack(struct hashfile_checkpoint *checkpoint) static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark) { + struct packfile_store *packs = the_repository->objects->packfiles; size_t in_sz = 64 * 1024, out_sz = 64 * 1024; unsigned char *in_buf = xmalloc(in_sz); unsigned char *out_buf = xmalloc(out_sz); @@ -1177,7 +1179,7 @@ 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, get_all_packs(the_repository))) { + } else if (find_oid_pack(&oid, packfile_store_get_all_packs(packs))) { e->type = OBJ_BLOB; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ diff --git a/builtin/fsck.c b/builtin/fsck.c index d2eb9d4fbe..8ee95e0d67 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -867,19 +867,20 @@ static int mark_packed_for_connectivity(const struct object_id *oid, static int check_pack_rev_indexes(struct repository *r, int show_progress) { + struct packfile_store *packs = r->objects->packfiles; struct progress *progress = NULL; uint32_t pack_count = 0; int res = 0; if (show_progress) { - for (struct packed_git *p = get_all_packs(r); p; p = p->next) + for (struct packed_git *p = packfile_store_get_all_packs(packs); p; p = p->next) pack_count++; progress = start_delayed_progress(the_repository, "Verifying reverse pack-indexes", pack_count); pack_count = 0; } - for (struct packed_git *p = get_all_packs(r); p; p = p->next) { + for (struct packed_git *p = packfile_store_get_all_packs(packs); p; p = p->next) { int load_error = load_pack_revindex_from_disk(p); if (load_error < 0) { @@ -999,6 +1000,8 @@ int cmd_fsck(int argc, for_each_packed_object(the_repository, mark_packed_for_connectivity, NULL, 0); } else { + struct packfile_store *packs = the_repository->objects->packfiles; + odb_prepare_alternates(the_repository->objects); for (source = the_repository->objects->sources; source; source = source->next) fsck_source(source); @@ -1009,7 +1012,7 @@ int cmd_fsck(int argc, struct progress *progress = NULL; if (show_progress) { - for (p = get_all_packs(the_repository); p; + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (open_pack_index(p)) continue; @@ -1019,7 +1022,7 @@ int cmd_fsck(int argc, progress = start_progress(the_repository, _("Checking objects"), total); } - for (p = get_all_packs(the_repository); p; + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { /* verify gives error messages itself */ if (verify_pack(the_repository, diff --git a/builtin/gc.c b/builtin/gc.c index 03ae4926b2..e19e13d978 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -487,9 +487,10 @@ static int too_many_loose_objects(struct gc_config *cfg) static struct packed_git *find_base_packs(struct string_list *packs, unsigned long limit) { + struct packfile_store *packfiles = the_repository->objects->packfiles; struct packed_git *p, *base = NULL; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packfiles); p; p = p->next) { if (!p->pack_local || p->is_cruft) continue; if (limit) { @@ -508,13 +509,14 @@ static struct packed_git *find_base_packs(struct string_list *packs, static int too_many_packs(struct gc_config *cfg) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; int cnt; if (cfg->gc_auto_pack_limit <= 0) return 0; - for (cnt = 0, p = get_all_packs(the_repository); p; p = p->next) { + for (cnt = 0, p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!p->pack_local) continue; if (p->pack_keep) @@ -1042,7 +1044,7 @@ int cmd_gc(int argc, die(FAILED_RUN, "rerere"); report_garbage = report_pack_garbage; - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); if (pack_garbage.nr > 0) { close_object_store(the_repository->objects); clean_pack_garbage(); @@ -1423,7 +1425,7 @@ static int incremental_repack_auto_condition(struct gc_config *cfg UNUSED) if (incremental_repack_auto_limit < 0) return 1; - for (p = get_packed_git(the_repository); + for (p = packfile_store_get_packs(the_repository->objects->packfiles); count < incremental_repack_auto_limit && p; p = p->next) { if (!p->multi_pack_index) @@ -1491,8 +1493,8 @@ static off_t get_auto_pack_size(void) struct packed_git *p; struct repository *r = the_repository; - reprepare_packed_git(r); - for (p = get_all_packs(r); p; p = p->next) { + odb_reprepare(r->objects); + for (p = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { if (p->pack_size > max_size) { second_largest_size = max_size; max_size = p->pack_size; diff --git a/builtin/grep.c b/builtin/grep.c index 1d97eb2a2a..13841fbf00 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -1214,7 +1214,7 @@ int cmd_grep(int argc, if (recurse_submodules) repo_read_gitmodules(the_repository, 1); if (startup_info->have_repository) - (void)get_packed_git(the_repository); + (void)packfile_store_get_packs(the_repository->objects->packfiles); start_threads(&opt); } else { diff --git a/builtin/index-pack.c b/builtin/index-pack.c index f91c301bba..2b78ba7fe4 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1640,13 +1640,9 @@ 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) { - struct packed_git *p; - p = add_packed_git(the_repository, final_index_name, - strlen(final_index_name), 0); - if (p) - install_packed_git(the_repository, p); - } + if (do_fsck_object) + packfile_store_load_pack(the_repository->objects->packfiles, + final_index_name, 0); if (!from_stdin) { printf("%s\n", hash_to_hex(hash)); diff --git a/builtin/log.c b/builtin/log.c index 8aa1777940..c8319b8af3 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -1406,13 +1406,12 @@ static void make_cover_letter(struct rev_info *rev, int use_separate_file, * can be added later if deemed desirable. */ struct diff_options opts; - struct strvec other_arg = STRVEC_INIT; struct range_diff_options range_diff_opts = { .creation_factor = rev->creation_factor, .dual_color = 1, .max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT, .diffopt = &opts, - .other_arg = &other_arg + .log_arg = &rev->rdiff_log_arg }; repo_diff_setup(the_repository, &opts); @@ -1420,9 +1419,7 @@ static void make_cover_letter(struct rev_info *rev, int use_separate_file, opts.use_color = rev->diffopt.use_color; diff_setup_done(&opts); fprintf_ln(rev->diffopt.file, "%s", rev->rdiff_title); - get_notes_args(&other_arg, rev); show_range_diff(rev->rdiff1, rev->rdiff2, &range_diff_opts); - strvec_clear(&other_arg); } } @@ -2334,6 +2331,7 @@ int cmd_format_patch(int argc, rev.rdiff_title = diff_title(&rdiff_title, reroll_count, _("Range-diff:"), _("Range-diff against v%d:")); + get_notes_args(&(rev.rdiff_log_arg), &rev); } /* @@ -2493,6 +2491,7 @@ done: rev.diffopt.no_free = 0; release_revisions(&rev); format_config_release(&cfg); + strvec_clear(&rev.rdiff_log_arg); return 0; } diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 5856b5f6bf..5bdc44fb2d 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1748,12 +1748,12 @@ static int want_object_in_pack_mtime(const struct object_id *oid, } } - list_for_each(pos, get_packed_git_mru(the_repository)) { + list_for_each(pos, packfile_store_get_packs_mru(the_repository->objects->packfiles)) { struct packed_git *p = list_entry(pos, struct packed_git, mru); want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset, found_mtime); if (!exclude && want > 0) list_move(&p->mru, - get_packed_git_mru(the_repository)); + packfile_store_get_packs_mru(the_repository->objects->packfiles)); if (want != -1) return want; } @@ -3774,7 +3774,7 @@ static void show_object_pack_hint(struct object *object, const char *name, enum stdin_packs_mode mode = *(enum stdin_packs_mode *)data; if (mode == STDIN_PACKS_MODE_FOLLOW) { if (object->type == OBJ_BLOB && - !has_object(the_repository, &object->oid, 0)) + !odb_has_object(the_repository->objects, &object->oid, 0)) return; add_object_entry(&object->oid, object->type, name, 0); } else { @@ -3831,6 +3831,7 @@ static int pack_mtime_cmp(const void *_a, const void *_b) static void read_packs_list_from_stdin(struct rev_info *revs) { + struct packfile_store *packs = the_repository->objects->packfiles; struct strbuf buf = STRBUF_INIT; struct string_list include_packs = STRING_LIST_INIT_DUP; struct string_list exclude_packs = STRING_LIST_INIT_DUP; @@ -3855,7 +3856,7 @@ static void read_packs_list_from_stdin(struct rev_info *revs) string_list_sort(&exclude_packs); string_list_remove_duplicates(&exclude_packs, 0); - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { const char *pack_name = pack_basename(p); if ((item = string_list_lookup(&include_packs, pack_name))) @@ -4076,6 +4077,7 @@ static void enumerate_cruft_objects(void) static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; struct rev_info revs; int ret; @@ -4105,7 +4107,7 @@ static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs * Re-mark only the fresh packs as kept so that objects in * unknown packs do not halt the reachability traversal early. */ - for (p = get_all_packs(the_repository); p; p = p->next) + for (p = packfile_store_get_all_packs(packs); p; p = p->next) p->pack_keep_in_core = 0; mark_pack_kept_in_core(fresh_packs, 1); @@ -4122,6 +4124,7 @@ static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs static void read_cruft_objects(void) { + struct packfile_store *packs = the_repository->objects->packfiles; struct strbuf buf = STRBUF_INIT; struct string_list discard_packs = STRING_LIST_INIT_DUP; struct string_list fresh_packs = STRING_LIST_INIT_DUP; @@ -4142,7 +4145,7 @@ static void read_cruft_objects(void) string_list_sort(&discard_packs); string_list_sort(&fresh_packs); - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { const char *pack_name = pack_basename(p); struct string_list_item *item; @@ -4390,11 +4393,12 @@ 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; struct packed_git *p; p = (last_found != (void *)1) ? last_found : - get_all_packs(the_repository); + packfile_store_get_all_packs(packs); while (p) { if ((!p->pack_local || p->pack_keep || @@ -4404,7 +4408,7 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) return 1; } if (p == last_found) - p = get_all_packs(the_repository); + p = packfile_store_get_all_packs(packs); else p = p->next; if (p == last_found) @@ -4436,12 +4440,13 @@ static int loosened_object_can_be_discarded(const struct object_id *oid, static void loosen_unused_packed_objects(void) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; uint32_t i; uint32_t loosened_objects_nr = 0; struct object_id oid; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; @@ -4591,8 +4596,8 @@ static int add_objects_by_path(const char *path, /* Skip objects that do not exist locally. */ if ((exclude_promisor_objects || arg_missing_action != MA_ERROR) && - oid_object_info_extended(the_repository, oid, &oi, - OBJECT_INFO_FOR_PREFETCH) < 0) + odb_read_object_info_extended(the_repository->objects, oid, &oi, + OBJECT_INFO_FOR_PREFETCH) < 0) continue; exclude = is_oid_uninteresting(the_repository, oid); @@ -4742,12 +4747,13 @@ static void get_object_list(struct rev_info *revs, struct strvec *argv) static void add_extra_kept_packs(const struct string_list *names) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; if (!names->nr) return; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { const char *name = basename(p->pack_name); int i; @@ -5185,8 +5191,10 @@ int cmd_pack_objects(int argc, add_extra_kept_packs(&keep_pack_list); if (ignore_packed_keep_on_disk) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; - for (p = get_all_packs(the_repository); p; p = p->next) + + for (p = packfile_store_get_all_packs(packs); p; p = p->next) if (p->pack_local && p->pack_keep) break; if (!p) /* no keep-able packs found */ @@ -5198,8 +5206,10 @@ int cmd_pack_objects(int argc, * want to unset "local" based on looking at packs, as * it also covers non-local objects */ + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; - for (p = get_all_packs(the_repository); p; p = p->next) { + + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!p->pack_local) { have_non_local_packs = 1; break; diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index 5d5ae4afa2..80743d8806 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -566,7 +566,8 @@ static struct pack_list * add_pack(struct packed_git *p) static struct pack_list * add_pack_file(const char *filename) { - struct packed_git *p = get_all_packs(the_repository); + struct packfile_store *packs = the_repository->objects->packfiles; + struct packed_git *p = packfile_store_get_all_packs(packs); if (strlen(filename) < 40) die("Bad pack filename: %s", filename); @@ -581,7 +582,8 @@ static struct pack_list * add_pack_file(const char *filename) static void load_all(void) { - struct packed_git *p = get_all_packs(the_repository); + struct packfile_store *packs = the_repository->objects->packfiles; + struct packed_git *p = packfile_store_get_all_packs(packs); while (p) { add_pack(p); diff --git a/builtin/range-diff.c b/builtin/range-diff.c index 1bc082a869..e54c0f7fe1 100644 --- a/builtin/range-diff.c +++ b/builtin/range-diff.c @@ -38,13 +38,13 @@ int cmd_range_diff(int argc, struct repository *repo UNUSED) { struct diff_options diffopt = { NULL }; - struct strvec other_arg = STRVEC_INIT; + struct strvec log_arg = STRVEC_INIT; struct strvec diff_merges_arg = STRVEC_INIT; struct range_diff_options range_diff_opts = { .creation_factor = RANGE_DIFF_CREATION_FACTOR_DEFAULT, .max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT, .diffopt = &diffopt, - .other_arg = &other_arg + .log_arg = &log_arg }; int simple_color = -1, left_only = 0, right_only = 0; struct option range_diff_options[] = { @@ -53,7 +53,7 @@ int cmd_range_diff(int argc, N_("percentage by which creation is weighted")), OPT_BOOL(0, "no-dual-color", &simple_color, N_("use simple diff colors")), - OPT_PASSTHRU_ARGV(0, "notes", &other_arg, + OPT_PASSTHRU_ARGV(0, "notes", &log_arg, N_("notes"), N_("passed to 'git log'"), PARSE_OPT_OPTARG), OPT_PASSTHRU_ARGV(0, "diff-merges", &diff_merges_arg, @@ -93,7 +93,7 @@ int cmd_range_diff(int argc, /* If `--diff-merges` was specified, imply `--merges` */ if (diff_merges_arg.nr) { range_diff_opts.include_merges = 1; - strvec_pushv(&other_arg, diff_merges_arg.v); + strvec_pushv(&log_arg, diff_merges_arg.v); } for (i = 0; i < argc; i++) @@ -125,7 +125,7 @@ int cmd_range_diff(int argc, strbuf_addf(&range1, "%s..%s", argv[0], argv[1]); strbuf_addf(&range2, "%s..%s", argv[0], argv[2]); - strvec_pushv(&other_arg, argv + + strvec_pushv(&log_arg, argv + (dash_dash < 0 ? 3 : dash_dash)); } else if (dash_dash == 2 || (dash_dash < 0 && argc > 1 && @@ -145,7 +145,7 @@ int cmd_range_diff(int argc, strbuf_addstr(&range1, argv[0]); strbuf_addstr(&range2, argv[1]); - strvec_pushv(&other_arg, argv + + strvec_pushv(&log_arg, argv + (dash_dash < 0 ? 2 : dash_dash)); } else if (dash_dash == 1 || (dash_dash < 0 && argc > 0 && @@ -176,7 +176,7 @@ int cmd_range_diff(int argc, strbuf_addf(&range1, "%s..%.*s", b, a_len, a); strbuf_addf(&range2, "%.*s..%s", a_len, a, b); - strvec_pushv(&other_arg, argv + + strvec_pushv(&log_arg, argv + (dash_dash < 0 ? 1 : dash_dash)); } else usage_msg_opt(_("need two commit ranges"), @@ -188,7 +188,7 @@ int cmd_range_diff(int argc, range_diff_opts.right_only = right_only; res = show_range_diff(range1.buf, range2.buf, &range_diff_opts); - strvec_clear(&other_arg); + strvec_clear(&log_arg); strvec_clear(&diff_merges_arg); strbuf_release(&range1); strbuf_release(&range2); diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 1113137a6f..c9288a9c7e 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -2389,7 +2389,7 @@ static const char *unpack(int err_fd, struct shallow_info *si) status = finish_command(&child); if (status) return "index-pack abnormal exit"; - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); } return NULL; } diff --git a/builtin/reflog.c b/builtin/reflog.c index c8f6b93d60..dcbfe89339 100644 --- a/builtin/reflog.c +++ b/builtin/reflog.c @@ -418,6 +418,8 @@ static int cmd_reflog_write(int argc, const char **argv, const char *prefix, const char *ref, *message; int ret; + repo_config(repo, git_ident_config, NULL); + argc = parse_options(argc, argv, prefix, options, reflog_write_usage, 0); if (argc != 4) usage_with_options(reflog_write_usage, options); diff --git a/builtin/repack.c b/builtin/repack.c index c490a51e91..e8730808c5 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -265,10 +265,11 @@ static void existing_packs_release(struct existing_packs *existing) static void collect_pack_filenames(struct existing_packs *existing, const struct string_list *extra_keep) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; struct strbuf buf = STRBUF_INIT; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { int i; const char *base; @@ -497,10 +498,11 @@ static void init_pack_geometry(struct pack_geometry *geometry, struct existing_packs *existing, const struct pack_objects_args *args) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; struct strbuf buf = STRBUF_INIT; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (args->local && !p->pack_local) /* * When asked to only repack local packfiles we skip @@ -1137,11 +1139,12 @@ static int write_filtered_pack(const struct pack_objects_args *args, static void combine_small_cruft_packs(FILE *in, size_t combine_cruft_below_size, struct existing_packs *existing) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; struct strbuf buf = STRBUF_INIT; size_t i; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!(p->is_cruft && p->pack_local)) continue; @@ -1685,7 +1688,7 @@ int cmd_repack(int argc, goto cleanup; } - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); if (delete_redundant) { int opts = 0; diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index 9da92b990d..7b3711cf34 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -1107,11 +1107,20 @@ int cmd_rev_parse(int argc, const char *val = arg ? arg : "storage"; if (strcmp(val, "storage") && + strcmp(val, "compat") && strcmp(val, "input") && strcmp(val, "output")) die(_("unknown mode for --show-object-format: %s"), arg); - puts(the_hash_algo->name); + + if (!strcmp(val, "compat")) { + if (the_repository->compat_hash_algo) + puts(the_repository->compat_hash_algo->name); + else + putchar('\n'); + } else { + puts(the_hash_algo->name); + } continue; } if (!strcmp(arg, "--show-ref-format")) { diff --git a/ci/install-dependencies.sh b/ci/install-dependencies.sh index d061a47293..a8dcd9b9bc 100755 --- a/ci/install-dependencies.sh +++ b/ci/install-dependencies.sh @@ -30,8 +30,12 @@ alpine-*) bash cvs gnupg perl-cgi perl-dbd-sqlite perl-io-tty >/dev/null ;; fedora-*|almalinux-*) + case "$jobname" in + *-meson) + MESON_DEPS="meson ninja";; + esac dnf -yq update >/dev/null && - dnf -yq install shadow-utils sudo make gcc findutils diffutils perl python3 gawk gettext zlib-devel expat-devel openssl-devel curl-devel pcre2-devel >/dev/null + dnf -yq install shadow-utils sudo make pkg-config gcc findutils diffutils perl python3 gawk gettext zlib-devel expat-devel openssl-devel curl-devel pcre2-devel $MESON_DEPS cargo >/dev/null ;; ubuntu-*|i386/ubuntu-*|debian-*) # Required so that apt doesn't wait for user input on certain packages. @@ -58,9 +62,18 @@ ubuntu-*|i386/ubuntu-*|debian-*) make libssl-dev libcurl4-openssl-dev libexpat-dev wget sudo default-jre \ tcl tk gettext zlib1g-dev perl-modules liberror-perl libauthen-sasl-perl \ libemail-valid-perl libio-pty-perl libio-socket-ssl-perl libnet-smtp-ssl-perl libdbd-sqlite3-perl libcgi-pm-perl \ - libsecret-1-dev libpcre2-dev meson ninja-build pkg-config \ + libsecret-1-dev libpcre2-dev meson ninja-build pkg-config cargo \ ${CC_PACKAGE:-${CC:-gcc}} $PYTHON_PACKAGE + # Starting with Ubuntu 25.10, sudo can now be provided via either + # sudo(1) or sudo-rs(1), with the latter being the default. The problem + # is that it does not support `--preserve-env` though, which we rely on + # in our CI. We thus revert back to the C implementation. + if test -f /etc/alternatives/sudo + then + sudo update-alternatives --set sudo /usr/bin/sudo.ws + fi + case "$distro" in ubuntu-*) mkdir --parents "$CUSTOM_PATH" diff --git a/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh index a21834043f..8bda62b921 100755 --- a/ci/run-build-and-tests.sh +++ b/ci/run-build-and-tests.sh @@ -5,11 +5,12 @@ . ${0%/*}/lib.sh -run_tests=t - case "$jobname" in -linux-breaking-changes) +fedora-breaking-changes-musl|linux-breaking-changes) export WITH_BREAKING_CHANGES=YesPlease + export WITH_RUST=YesPlease + MESONFLAGS="$MESONFLAGS -Dbreaking_changes=true" + MESONFLAGS="$MESONFLAGS -Drust=enabled" ;; linux-TEST-vars) export OPENSSL_SHA1_UNSAFE=YesPlease @@ -35,12 +36,6 @@ linux-sha256) linux-reftable|linux-reftable-leaks|osx-reftable) export GIT_TEST_DEFAULT_REF_FORMAT=reftable ;; -pedantic) - # Don't run the tests; we only care about whether Git can be - # built. - export DEVOPTS=pedantic - run_tests= - ;; esac case "$jobname" in @@ -53,21 +48,15 @@ case "$jobname" in -Dtest_output_directory="${TEST_OUTPUT_DIRECTORY:-$(pwd)/t}" \ $MESONFLAGS group "Build" meson compile -C build -- - if test -n "$run_tests" - then - group "Run tests" meson test -C build --print-errorlogs --test-args="$GIT_TEST_OPTS" || ( - ./t/aggregate-results.sh "${TEST_OUTPUT_DIRECTORY:-t}/test-results" - handle_failed_tests - ) - fi + group "Run tests" meson test -C build --print-errorlogs --test-args="$GIT_TEST_OPTS" || ( + ./t/aggregate-results.sh "${TEST_OUTPUT_DIRECTORY:-t}/test-results" + handle_failed_tests + ) ;; *) group Build make - if test -n "$run_tests" - then - group "Run tests" make test || - handle_failed_tests - fi + group "Run tests" make test || + handle_failed_tests ;; esac diff --git a/commit-graph.c b/commit-graph.c index 2f20f66cfd..474454db73 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -735,7 +735,7 @@ struct commit_graph *read_commit_graph_one(struct odb_source *source) * On the first invocation, this function attempts to load the commit * graph if the repository is configured to have one. */ -static int prepare_commit_graph(struct repository *r) +static struct commit_graph *prepare_commit_graph(struct repository *r) { struct odb_source *source; @@ -747,10 +747,10 @@ static int prepare_commit_graph(struct repository *r) * we want to disable even an already-loaded graph file. */ if (!r->gitdir || r->commit_graph_disabled) - return 0; + return NULL; if (r->objects->commit_graph_attempted) - return !!r->objects->commit_graph; + return r->objects->commit_graph; r->objects->commit_graph_attempted = 1; prepare_repo_settings(r); @@ -763,10 +763,10 @@ static int prepare_commit_graph(struct repository *r) * so that commit graph loading is not attempted again for this * repository.) */ - return 0; + return NULL; if (!commit_graph_compatible(r)) - return 0; + return NULL; odb_prepare_alternates(r->objects); for (source = r->objects->sources; source; source = source->next) { @@ -775,20 +775,17 @@ static int prepare_commit_graph(struct repository *r) break; } - return !!r->objects->commit_graph; + return r->objects->commit_graph; } int generation_numbers_enabled(struct repository *r) { uint32_t first_generation; struct commit_graph *g; - if (!prepare_commit_graph(r)) - return 0; - - g = r->objects->commit_graph; - if (!g->num_commits) - return 0; + g = prepare_commit_graph(r); + if (!g || !g->num_commits) + return 0; first_generation = get_be32(g->chunk_commit_data + g->hash_algo->rawsz + 8) >> 2; @@ -799,12 +796,9 @@ int generation_numbers_enabled(struct repository *r) int corrected_commit_dates_enabled(struct repository *r) { struct commit_graph *g; - if (!prepare_commit_graph(r)) - return 0; - - g = r->objects->commit_graph; - if (!g->num_commits) + g = prepare_commit_graph(r); + if (!g || !g->num_commits) return 0; return g->read_generation_data; @@ -1014,26 +1008,32 @@ static int find_commit_pos_in_graph(struct commit *item, struct commit_graph *g, } } -int repo_find_commit_pos_in_graph(struct repository *r, struct commit *c, - uint32_t *pos) +struct commit_graph *repo_find_commit_pos_in_graph(struct repository *r, + struct commit *c, + uint32_t *pos) { - if (!prepare_commit_graph(r)) - return 0; - return find_commit_pos_in_graph(c, r->objects->commit_graph, pos); + struct commit_graph *g = prepare_commit_graph(r); + if (!g) + return NULL; + if (!find_commit_pos_in_graph(c, g, pos)) + return NULL; + return g; } struct commit *lookup_commit_in_graph(struct repository *repo, const struct object_id *id) { static int commit_graph_paranoia = -1; + struct commit_graph *g; struct commit *commit; uint32_t pos; if (commit_graph_paranoia == -1) commit_graph_paranoia = git_env_bool(GIT_COMMIT_GRAPH_PARANOIA, 0); - if (!prepare_commit_graph(repo)) + g = prepare_commit_graph(repo); + if (!g) return NULL; - if (!search_commit_pos_in_graph(id, repo->objects->commit_graph, &pos)) + if (!search_commit_pos_in_graph(id, g, &pos)) return NULL; if (commit_graph_paranoia && !odb_has_object(repo->objects, id, 0)) return NULL; @@ -1044,7 +1044,7 @@ struct commit *lookup_commit_in_graph(struct repository *repo, const struct obje if (commit->object.parsed) return commit; - if (!fill_commit_in_graph(commit, repo->objects->commit_graph, pos)) + if (!fill_commit_in_graph(commit, g, pos)) return NULL; return commit; @@ -1067,6 +1067,7 @@ static int parse_commit_in_graph_one(struct commit_graph *g, int parse_commit_in_graph(struct repository *r, struct commit *item) { static int checked_env = 0; + struct commit_graph *g; if (!checked_env && git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE, 0)) @@ -1074,16 +1075,20 @@ int parse_commit_in_graph(struct repository *r, struct commit *item) GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE); checked_env = 1; - if (!prepare_commit_graph(r)) + g = prepare_commit_graph(r); + if (!g) return 0; - return parse_commit_in_graph_one(r->objects->commit_graph, item); + return parse_commit_in_graph_one(g, item); } void load_commit_graph_info(struct repository *r, struct commit *item) { + struct commit_graph *g; uint32_t pos; - if (repo_find_commit_pos_in_graph(r, item, &pos)) - fill_commit_graph_info(item, r->objects->commit_graph, pos); + + g = repo_find_commit_pos_in_graph(r, item, &pos); + if (g) + fill_commit_graph_info(item, g, pos); } static struct tree *load_tree_for_commit(struct commit_graph *g, @@ -2226,7 +2231,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) return 0; } -static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) +static void split_graph_merge_strategy(struct write_commit_graph_context *ctx, + struct commit_graph *graph_to_merge) { struct commit_graph *g; uint32_t num_commits; @@ -2245,7 +2251,7 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) flags = ctx->opts->split_flags; } - g = ctx->r->objects->commit_graph; + g = graph_to_merge; num_commits = ctx->commits.nr; if (flags == COMMIT_GRAPH_SPLIT_REPLACE) ctx->num_commit_graphs_after = 1; @@ -2297,7 +2303,7 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) ctx->commit_graph_filenames_after[i] = xstrdup(ctx->commit_graph_filenames_before[i]); i = ctx->num_commit_graphs_before - 1; - g = ctx->r->objects->commit_graph; + g = graph_to_merge; while (g) { if (i < ctx->num_commit_graphs_after) @@ -2395,9 +2401,9 @@ static void sort_and_scan_merged_commits(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } -static void merge_commit_graphs(struct write_commit_graph_context *ctx) +static void merge_commit_graphs(struct write_commit_graph_context *ctx, + struct commit_graph *g) { - struct commit_graph *g = ctx->r->objects->commit_graph; uint32_t current_graph_number = ctx->num_commit_graphs_before; while (g && current_graph_number >= ctx->num_commit_graphs_after) { @@ -2524,6 +2530,7 @@ int write_commit_graph(struct odb_source *source, int replace = 0; struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; struct topo_level_slab topo_levels; + struct commit_graph *g; prepare_repo_settings(r); if (!r->settings.core_commit_graph) { @@ -2552,23 +2559,13 @@ int write_commit_graph(struct odb_source *source, init_topo_level_slab(&topo_levels); ctx.topo_levels = &topo_levels; - prepare_commit_graph(ctx.r); - if (ctx.r->objects->commit_graph) { - struct commit_graph *g = ctx.r->objects->commit_graph; - - while (g) { - g->topo_levels = &topo_levels; - g = g->base_graph; - } - } + g = prepare_commit_graph(ctx.r); + for (struct commit_graph *chain = g; chain; chain = chain->base_graph) + g->topo_levels = &topo_levels; if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS) ctx.changed_paths = 1; if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) { - struct commit_graph *g; - - g = ctx.r->objects->commit_graph; - /* We have changed-paths already. Keep them in the next graph */ if (g && g->bloom_filter_settings) { ctx.changed_paths = 1; @@ -2585,22 +2582,15 @@ int write_commit_graph(struct odb_source *source, bloom_settings.hash_version = bloom_settings.hash_version == 2 ? 2 : 1; if (ctx.split) { - struct commit_graph *g = ctx.r->objects->commit_graph; - - while (g) { + for (struct commit_graph *chain = g; chain; chain = chain->base_graph) ctx.num_commit_graphs_before++; - g = g->base_graph; - } if (ctx.num_commit_graphs_before) { ALLOC_ARRAY(ctx.commit_graph_filenames_before, ctx.num_commit_graphs_before); i = ctx.num_commit_graphs_before; - g = ctx.r->objects->commit_graph; - while (g) { - ctx.commit_graph_filenames_before[--i] = xstrdup(g->filename); - g = g->base_graph; - } + for (struct commit_graph *chain = g; chain; chain = chain->base_graph) + ctx.commit_graph_filenames_before[--i] = xstrdup(chain->filename); } if (ctx.opts) @@ -2609,8 +2599,7 @@ int write_commit_graph(struct odb_source *source, ctx.approx_nr_objects = repo_approximate_object_count(r); - if (ctx.append && ctx.r->objects->commit_graph) { - struct commit_graph *g = ctx.r->objects->commit_graph; + if (ctx.append && g) { for (i = 0; i < g->num_commits; i++) { struct object_id oid; oidread(&oid, g->chunk_oid_lookup + st_mult(g->hash_algo->rawsz, i), @@ -2649,14 +2638,15 @@ int write_commit_graph(struct odb_source *source, goto cleanup; if (ctx.split) { - split_graph_merge_strategy(&ctx); + split_graph_merge_strategy(&ctx, g); if (!replace) - merge_commit_graphs(&ctx); - } else + merge_commit_graphs(&ctx, g); + } else { ctx.num_commit_graphs_after = 1; + } - ctx.trust_generation_numbers = validate_mixed_generation_chain(ctx.r->objects->commit_graph); + ctx.trust_generation_numbers = validate_mixed_generation_chain(g); compute_topological_levels(&ctx); if (ctx.write_generation_data) diff --git a/commit-graph.h b/commit-graph.h index 4899b54ef8..f6a5433641 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -48,10 +48,9 @@ int open_commit_graph_chain(const char *chain_file, int *fd, struct stat *st, int parse_commit_in_graph(struct repository *r, struct commit *item); /* - * Fills `*pos` with the graph position of `c`, and returns 1 if `c` is - * found in the commit-graph belonging to `r`, or 0 otherwise. - * Initializes the commit-graph belonging to `r` if it hasn't been - * already. + * Fills `*pos` with the graph position of `c`, and returns the graph `c` is + * found in, or NULL otherwise. Initializes the commit-graphs belonging to + * `r` if it hasn't been already. * * Note: this is a low-level helper that does not alter any slab data * associated with `c`. Useful in circumstances where the slab data is @@ -59,8 +58,9 @@ int parse_commit_in_graph(struct repository *r, struct commit *item); * * In most cases, callers should use `parse_commit_in_graph()` instead. */ -int repo_find_commit_pos_in_graph(struct repository *r, struct commit *c, - uint32_t *pos); +struct commit_graph *repo_find_commit_pos_in_graph(struct repository *r, + struct commit *c, + uint32_t *pos); /* * Look up the given commit ID in the commit-graph. This will only return a diff --git a/compat/mingw.c b/compat/mingw.c index 8538e3d172..736a07a028 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -1,26 +1,26 @@ #define USE_THE_REPOSITORY_VARIABLE #define DISABLE_SIGN_COMPARE_WARNINGS -#include "../git-compat-util.h" +#include "git-compat-util.h" +#include "abspath.h" +#include "alloc.h" +#include "config.h" +#include "dir.h" +#include "environment.h" +#include "gettext.h" +#include "run-command.h" +#include "strbuf.h" +#include "symlinks.h" +#include "trace2.h" #include "win32.h" +#include "win32/lazyload.h" +#include "wrapper.h" #include <aclapi.h> -#include <sddl.h> #include <conio.h> -#include <wchar.h> -#include "../strbuf.h" -#include "../run-command.h" -#include "../abspath.h" -#include "../alloc.h" -#include "win32/lazyload.h" -#include "../config.h" -#include "../environment.h" -#include "../trace2.h" -#include "../symlinks.h" -#include "../wrapper.h" -#include "dir.h" -#include "gettext.h" +#include <sddl.h> #define SECURITY_WIN32 #include <sspi.h> +#include <wchar.h> #include <winternl.h> #define STATUS_DELETE_PENDING ((NTSTATUS) 0xC0000056) @@ -1278,11 +1278,23 @@ int git_config_string(char **dest, const char *var, const char *value) int git_config_pathname(char **dest, const char *var, const char *value) { + int is_optional; + char *path; + if (!value) return config_error_nonbool(var); - *dest = interpolate_path(value, 0); - if (!*dest) + + is_optional = skip_prefix(value, ":(optional)", &value); + path = interpolate_path(value, 0); + if (!path) die(_("failed to expand user dir in: '%s'"), value); + + if (is_optional && is_missing_file(path)) { + free(path); + return 0; + } + + *dest = path; return 0; } diff --git a/connected.c b/connected.c index 18c13245d8..b288a18b17 100644 --- a/connected.c +++ b/connected.c @@ -72,11 +72,12 @@ int check_connected(oid_iterate_fn fn, void *cb_data, * Before checking for promisor packs, be sure we have the * latest pack-files loaded into memory. */ - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); do { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (!p->pack_promisor) continue; if (find_pack_entry_one(oid, p)) diff --git a/contrib/credential/libsecret/Makefile b/contrib/credential/libsecret/Makefile index 97ce9c92fb..7cacc57681 100644 --- a/contrib/credential/libsecret/Makefile +++ b/contrib/credential/libsecret/Makefile @@ -1,28 +1,27 @@ # The default target of this Makefile is... -all:: - -MAIN:=git-credential-libsecret -all:: $(MAIN) - -CC = gcc -RM = rm -f -CFLAGS = -g -O2 -Wall -PKG_CONFIG = pkg-config +all:: git-credential-libsecret -include ../../../config.mak.autogen -include ../../../config.mak +prefix ?= /usr/local +gitexecdir ?= $(prefix)/libexec/git-core + +CC ?= gcc +CFLAGS ?= -g -O2 -Wall +PKG_CONFIG ?= pkg-config +RM ?= rm -f + INCS:=$(shell $(PKG_CONFIG) --cflags libsecret-1 glib-2.0) LIBS:=$(shell $(PKG_CONFIG) --libs libsecret-1 glib-2.0) -SRCS:=$(MAIN).c -OBJS:=$(SRCS:.c=.o) - %.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) $(INCS) -o $@ -c $< -$(MAIN): $(OBJS) - $(CC) -o $@ $(LDFLAGS) $^ $(LIBS) +git-credential-libsecret: git-credential-libsecret.o + $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) $(LIBS) clean: - @$(RM) $(MAIN) $(OBJS) + $(RM) git-credential-libsecret git-credential-libsecret.o + +.PHONY: all clean diff --git a/contrib/credential/osxkeychain/Makefile b/contrib/credential/osxkeychain/Makefile index 0948297e20..c7d9121022 100644 --- a/contrib/credential/osxkeychain/Makefile +++ b/contrib/credential/osxkeychain/Makefile @@ -1,19 +1,24 @@ # The default target of this Makefile is... all:: git-credential-osxkeychain -CC = gcc -RM = rm -f -CFLAGS = -g -O2 -Wall - -include ../../../config.mak.autogen -include ../../../config.mak +prefix ?= /usr/local +gitexecdir ?= $(prefix)/libexec/git-core + +CC ?= gcc +CFLAGS ?= -g -O2 -Wall +RM ?= rm -f + +%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) -o $@ -c $< + git-credential-osxkeychain: git-credential-osxkeychain.o - $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) \ + $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) \ -framework Security -framework CoreFoundation -git-credential-osxkeychain.o: git-credential-osxkeychain.c - $(CC) -c $(CFLAGS) $< - clean: $(RM) git-credential-osxkeychain git-credential-osxkeychain.o + +.PHONY: all clean diff --git a/diff-no-index.c b/diff-no-index.c index 88ae4cee56..f320424f05 100644 --- a/diff-no-index.c +++ b/diff-no-index.c @@ -21,30 +21,21 @@ static int read_directory_contents(const char *path, struct string_list *list, const struct pathspec *pathspec, - int skip) + struct strbuf *match) { - struct strbuf match = STRBUF_INIT; - int len; + int len = match->len; DIR *dir; struct dirent *e; if (!(dir = opendir(path))) return error("Could not open directory %s", path); - if (pathspec) { - strbuf_addstr(&match, path); - strbuf_complete(&match, '/'); - strbuf_remove(&match, 0, skip); - - len = match.len; - } - while ((e = readdir_skip_dot_and_dotdot(dir))) { if (pathspec) { int is_dir = 0; - strbuf_setlen(&match, len); - strbuf_addstr(&match, e->d_name); + strbuf_setlen(match, len); + strbuf_addstr(match, e->d_name); if (NOT_CONSTANT(DTYPE(e)) != DT_UNKNOWN) { is_dir = (DTYPE(e) == DT_DIR); } else { @@ -57,7 +48,7 @@ static int read_directory_contents(const char *path, struct string_list *list, } if (!match_leading_pathspec(NULL, pathspec, - match.buf, match.len, + match->buf, match->len, 0, NULL, is_dir)) continue; } @@ -65,7 +56,7 @@ static int read_directory_contents(const char *path, struct string_list *list, string_list_insert(list, e->d_name); } - strbuf_release(&match); + strbuf_setlen(match, len); closedir(dir); return 0; } @@ -169,7 +160,8 @@ static struct diff_filespec *noindex_filespec(const struct git_hash_algo *algop, static int queue_diff(struct diff_options *o, const struct git_hash_algo *algop, const char *name1, const char *name2, int recursing, - const struct pathspec *ps, int skip1, int skip2) + const struct pathspec *ps, + struct strbuf *ps_match1, struct strbuf *ps_match2) { int mode1 = 0, mode2 = 0; enum special special1 = SPECIAL_NONE, special2 = SPECIAL_NONE; @@ -208,10 +200,12 @@ static int queue_diff(struct diff_options *o, const struct git_hash_algo *algop, struct string_list p2 = STRING_LIST_INIT_DUP; int i1, i2, ret = 0; size_t len1 = 0, len2 = 0; + size_t match1_len = ps_match1->len; + size_t match2_len = ps_match2->len; - if (name1 && read_directory_contents(name1, &p1, ps, skip1)) + if (name1 && read_directory_contents(name1, &p1, ps, ps_match1)) return -1; - if (name2 && read_directory_contents(name2, &p2, ps, skip2)) { + if (name2 && read_directory_contents(name2, &p2, ps, ps_match2)) { string_list_clear(&p1, 0); return -1; } @@ -235,6 +229,11 @@ static int queue_diff(struct diff_options *o, const struct git_hash_algo *algop, strbuf_setlen(&buffer1, len1); strbuf_setlen(&buffer2, len2); + if (ps) { + strbuf_setlen(ps_match1, match1_len); + strbuf_setlen(ps_match2, match2_len); + } + if (i1 == p1.nr) comp = 1; else if (i2 == p2.nr) @@ -245,18 +244,28 @@ static int queue_diff(struct diff_options *o, const struct git_hash_algo *algop, if (comp > 0) n1 = NULL; else { - strbuf_addstr(&buffer1, p1.items[i1++].string); + strbuf_addstr(&buffer1, p1.items[i1].string); + if (ps) { + strbuf_addstr(ps_match1, p1.items[i1].string); + strbuf_complete(ps_match1, '/'); + } n1 = buffer1.buf; + i1++; } if (comp < 0) n2 = NULL; else { - strbuf_addstr(&buffer2, p2.items[i2++].string); + strbuf_addstr(&buffer2, p2.items[i2].string); + if (ps) { + strbuf_addstr(ps_match2, p2.items[i2].string); + strbuf_complete(ps_match2, '/'); + } n2 = buffer2.buf; + i2++; } - ret = queue_diff(o, algop, n1, n2, 1, ps, skip1, skip2); + ret = queue_diff(o, algop, n1, n2, 1, ps, ps_match1, ps_match2); } string_list_clear(&p1, 0); string_list_clear(&p2, 0); @@ -346,7 +355,8 @@ int diff_no_index(struct rev_info *revs, const struct git_hash_algo *algop, int implicit_no_index, int argc, const char **argv) { struct pathspec pathspec, *ps = NULL; - int i, no_index, skip1 = 0, skip2 = 0; + struct strbuf ps_match1 = STRBUF_INIT, ps_match2 = STRBUF_INIT; + int i, no_index; int ret = 1; const char *paths[2]; char *to_free[ARRAY_SIZE(paths)] = { 0 }; @@ -387,11 +397,6 @@ int diff_no_index(struct rev_info *revs, const struct git_hash_algo *algop, NULL, &argv[2]); if (pathspec.nr) ps = &pathspec; - - skip1 = strlen(paths[0]); - skip1 += paths[0][skip1] == '/' ? 0 : 1; - skip2 = strlen(paths[1]); - skip2 += paths[1][skip2] == '/' ? 0 : 1; } else if (argc > 2) { warning(_("Limiting comparison with pathspecs is only " "supported if both paths are directories.")); @@ -415,7 +420,7 @@ int diff_no_index(struct rev_info *revs, const struct git_hash_algo *algop, revs->diffopt.flags.exit_with_status = 1; if (queue_diff(&revs->diffopt, algop, paths[0], paths[1], 0, ps, - skip1, skip2)) + &ps_match1, &ps_match2)) goto out; diff_set_mnemonic_prefix(&revs->diffopt, "1/", "2/"); diffcore_std(&revs->diffopt); @@ -431,6 +436,8 @@ out: for (i = 0; i < ARRAY_SIZE(to_free); i++) free(to_free[i]); strbuf_release(&replacement); + strbuf_release(&ps_match1); + strbuf_release(&ps_match2); if (ps) clear_pathspec(ps); return ret; @@ -6828,18 +6828,38 @@ void diff_flush(struct diff_options *options) DIFF_FORMAT_NAME | DIFF_FORMAT_NAME_STATUS | DIFF_FORMAT_CHECKDIFF)) { + /* + * make sure diff_Flush_patch_quietly() to be silent. + */ + FILE *dev_null = NULL; + int saved_color_moved = options->color_moved; + + if (options->flags.diff_from_contents) { + dev_null = xfopen("/dev/null", "w"); + options->color_moved = 0; + } for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; if (!check_pair_status(p)) continue; - if (options->flags.diff_from_contents && - !diff_flush_patch_quietly(p, options)) - continue; + if (options->flags.diff_from_contents) { + FILE *saved_file = options->file; + int found_changes; + options->file = dev_null; + found_changes = diff_flush_patch_quietly(p, options); + options->file = saved_file; + if (!found_changes) + continue; + } flush_one_pair(p, options); } + if (options->flags.diff_from_contents) { + fclose(dev_null); + options->color_moved = saved_color_moved; + } separator++; } @@ -6890,6 +6910,15 @@ void diff_flush(struct diff_options *options) if (output_format & DIFF_FORMAT_NO_OUTPUT && options->flags.exit_with_status && options->flags.diff_from_contents) { + /* + * run diff_flush_patch for the exit status. setting + * options->file to /dev/null should be safe, because we + * aren't supposed to produce any output anyway. + */ + diff_free_file(options); + options->file = xfopen("/dev/null", "w"); + options->close_file = 1; + options->color_moved = 0; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; if (check_pair_status(p)) @@ -3579,7 +3579,8 @@ static void write_one_dir(struct untracked_cache_dir *untracked, struct stat_data stat_data; struct strbuf *out = &wd->out; unsigned char intbuf[16]; - unsigned int intlen, value; + unsigned int value; + uint8_t intlen; int i = wd->index++; /* @@ -3632,7 +3633,7 @@ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untra struct ondisk_untracked_cache *ouc; struct write_data wd; unsigned char varbuf[16]; - int varint_len; + uint8_t varint_len; const unsigned hashsz = the_hash_algo->rawsz; CALLOC_ARRAY(ouc, 1); @@ -3738,7 +3739,7 @@ static int read_one_dir(struct untracked_cache_dir **untracked_, struct untracked_cache_dir ud, *untracked; const unsigned char *data = rd->data, *end = rd->end; const unsigned char *eos; - unsigned int value; + uint64_t value; int i; memset(&ud, 0, sizeof(ud)); @@ -3830,7 +3831,8 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long struct read_data rd; const unsigned char *next = data, *end = (const unsigned char *)data + sz; const char *ident; - int ident_len; + uint64_t ident_len; + uint64_t varint_len; ssize_t len; const char *exclude_per_dir; const unsigned hashsz = the_hash_algo->rawsz; @@ -3867,8 +3869,8 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long if (next >= end) goto done2; - len = decode_varint(&next); - if (next > end || len == 0) + varint_len = decode_varint(&next); + if (next > end || varint_len == 0) goto done2; rd.valid = ewah_new(); @@ -3877,9 +3879,9 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long rd.data = next; rd.end = end; rd.index = 0; - ALLOC_ARRAY(rd.ucd, len); + ALLOC_ARRAY(rd.ucd, varint_len); - if (read_one_dir(&uc->root, &rd) || rd.index != len) + if (read_one_dir(&uc->root, &rd) || rd.index != varint_len) goto done; next = rd.data; diff --git a/fetch-pack.c b/fetch-pack.c index 6ed5662951..fe7a84bf2f 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1983,7 +1983,7 @@ static void update_shallow(struct fetch_pack_args *args, * remote is shallow, but this is a clone, there are * no objects in repo to worry about. Accept any * shallow points that exist in the pack (iow in repo - * after get_pack() and reprepare_packed_git()) + * after get_pack() and odb_reprepare()) */ struct oid_array extra = OID_ARRAY_INIT; struct object_id *oid = si->shallow->oid; @@ -2108,7 +2108,7 @@ struct ref *fetch_pack(struct fetch_pack_args *args, ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought, &si, pack_lockfiles); } - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); if (!args->cloning && args->deepen) { struct check_connected_options opt = CHECK_CONNECTED_INIT; @@ -1067,6 +1067,24 @@ int fsck_tag_standalone(const struct object_id *oid, const char *buffer, else ret = fsck_ident(&buffer, 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); + if (!eol) { + ret = report(options, oid, OBJ_TAG, FSCK_MSG_BAD_GPGSIG, "invalid format - unexpected end after 'gpgsig' or 'gpgsig-sha256' line"); + goto done; + } + buffer = eol + 1; + + while (buffer < buffer_end && starts_with(buffer, " ")) { + eol = memchr(buffer, '\n', buffer_end - buffer); + if (!eol) { + ret = report(options, oid, OBJ_TAG, FSCK_MSG_BAD_HEADER_CONTINUATION, "invalid format - unexpected end in 'gpgsig' or 'gpgsig-sha256' continuation line"); + goto done; + } + buffer = eol + 1; + } + } + if (buffer < buffer_end && !starts_with(buffer, "\n")) { /* * The verify_headers() check will allow @@ -25,23 +25,37 @@ enum fsck_msg_type { FUNC(NUL_IN_HEADER, FATAL) \ FUNC(UNTERMINATED_HEADER, FATAL) \ /* errors */ \ + FUNC(BAD_HEADER_CONTINUATION, ERROR) \ FUNC(BAD_DATE, ERROR) \ FUNC(BAD_DATE_OVERFLOW, ERROR) \ FUNC(BAD_EMAIL, ERROR) \ + FUNC(BAD_GPGSIG, ERROR) \ FUNC(BAD_NAME, ERROR) \ FUNC(BAD_OBJECT_SHA1, ERROR) \ FUNC(BAD_PACKED_REF_ENTRY, ERROR) \ FUNC(BAD_PACKED_REF_HEADER, ERROR) \ FUNC(BAD_PARENT_SHA1, ERROR) \ + FUNC(BAD_REFERENT_NAME, ERROR) \ FUNC(BAD_REF_CONTENT, ERROR) \ FUNC(BAD_REF_FILETYPE, ERROR) \ FUNC(BAD_REF_NAME, ERROR) \ - FUNC(BAD_REFERENT_NAME, ERROR) \ FUNC(BAD_TIMEZONE, ERROR) \ FUNC(BAD_TREE, ERROR) \ FUNC(BAD_TREE_SHA1, ERROR) \ FUNC(BAD_TYPE, ERROR) \ FUNC(DUPLICATE_ENTRIES, ERROR) \ + FUNC(GITATTRIBUTES_BLOB, ERROR) \ + FUNC(GITATTRIBUTES_LARGE, ERROR) \ + FUNC(GITATTRIBUTES_LINE_LENGTH, ERROR) \ + FUNC(GITATTRIBUTES_MISSING, ERROR) \ + FUNC(GITMODULES_BLOB, ERROR) \ + FUNC(GITMODULES_LARGE, ERROR) \ + FUNC(GITMODULES_MISSING, ERROR) \ + FUNC(GITMODULES_NAME, ERROR) \ + FUNC(GITMODULES_PATH, ERROR) \ + FUNC(GITMODULES_SYMLINK, ERROR) \ + FUNC(GITMODULES_UPDATE, ERROR) \ + FUNC(GITMODULES_URL, ERROR) \ FUNC(MISSING_AUTHOR, ERROR) \ FUNC(MISSING_COMMITTER, ERROR) \ FUNC(MISSING_EMAIL, ERROR) \ @@ -60,39 +74,28 @@ enum fsck_msg_type { FUNC(TREE_NOT_SORTED, ERROR) \ FUNC(UNKNOWN_TYPE, ERROR) \ FUNC(ZERO_PADDED_DATE, ERROR) \ - FUNC(GITMODULES_MISSING, ERROR) \ - FUNC(GITMODULES_BLOB, ERROR) \ - FUNC(GITMODULES_LARGE, ERROR) \ - FUNC(GITMODULES_NAME, ERROR) \ - FUNC(GITMODULES_SYMLINK, ERROR) \ - FUNC(GITMODULES_URL, ERROR) \ - FUNC(GITMODULES_PATH, ERROR) \ - FUNC(GITMODULES_UPDATE, ERROR) \ - FUNC(GITATTRIBUTES_MISSING, ERROR) \ - FUNC(GITATTRIBUTES_LARGE, ERROR) \ - FUNC(GITATTRIBUTES_LINE_LENGTH, ERROR) \ - FUNC(GITATTRIBUTES_BLOB, ERROR) \ /* warnings */ \ + FUNC(BAD_REFTABLE_TABLE_NAME, WARN) \ FUNC(EMPTY_NAME, WARN) \ FUNC(FULL_PATHNAME, WARN) \ FUNC(HAS_DOT, WARN) \ FUNC(HAS_DOTDOT, WARN) \ FUNC(HAS_DOTGIT, WARN) \ + FUNC(LARGE_PATHNAME, WARN) \ FUNC(NULL_SHA1, WARN) \ - FUNC(ZERO_PADDED_FILEMODE, WARN) \ FUNC(NUL_IN_COMMIT, WARN) \ - FUNC(LARGE_PATHNAME, WARN) \ + FUNC(ZERO_PADDED_FILEMODE, WARN) \ /* infos (reported as warnings, but ignored by default) */ \ FUNC(BAD_FILEMODE, INFO) \ + FUNC(BAD_TAG_NAME, INFO) \ FUNC(EMPTY_PACKED_REFS_FILE, INFO) \ - FUNC(GITMODULES_PARSE, INFO) \ - FUNC(GITIGNORE_SYMLINK, INFO) \ FUNC(GITATTRIBUTES_SYMLINK, INFO) \ + FUNC(GITIGNORE_SYMLINK, INFO) \ + FUNC(GITMODULES_PARSE, INFO) \ FUNC(MAILMAP_SYMLINK, INFO) \ - FUNC(BAD_TAG_NAME, INFO) \ FUNC(MISSING_TAGGER_ENTRY, INFO) \ - FUNC(SYMLINK_REF, INFO) \ FUNC(REF_MISSING_NEWLINE, INFO) \ + FUNC(SYMLINK_REF, INFO) \ FUNC(SYMREF_TARGET_IS_NOT_A_REF, INFO) \ FUNC(TRAILING_REF_CONTENT, INFO) \ /* ignored (elevated when requested) */ \ diff --git a/gitk-git/gitk b/gitk-git/gitk index 6e4d71d585..c02db0194d 100755 --- a/gitk-git/gitk +++ b/gitk-git/gitk @@ -2215,6 +2215,7 @@ proc setoptions {} { } proc setttkstyle {} { + global theme eval font configure TkDefaultFont [fontflags mainfont] eval font configure TkTextFont [fontflags textfont] eval font configure TkHeadingFont [fontflags mainfont] @@ -2224,6 +2225,10 @@ proc setttkstyle {} { eval font configure TkIconFont [fontflags uifont] eval font configure TkMenuFont [fontflags uifont] eval font configure TkSmallCaptionFont [fontflags uifont] + + if {[catch {ttk::style theme use $theme} err]} { + set theme [ttk::style theme use] + } } # Make a menu and submenus. @@ -2376,7 +2381,6 @@ proc makewindow {} { global highlight_files gdttype global searchstring sstring global bgcolor fgcolor bglist fglist diffcolors diffbgcolors selectbgcolor - global uifgcolor uifgdisabledcolor global filesepbgcolor filesepfgcolor global mergecolors foundbgcolor currentsearchhitbgcolor global headctxmenu progresscanv progressitem progresscoords statusw @@ -2495,40 +2499,18 @@ proc makewindow {} { set sha1entry .tf.bar.sha1 set entries $sha1entry set sha1but .tf.bar.sha1label - button $sha1but -text "[mc "Commit ID:"] " -state disabled -relief flat \ + ttk::button $sha1but -text "[mc "Commit ID:"] " -state disabled \ -command gotocommit -width 8 - $sha1but conf -disabledforeground [$sha1but cget -foreground] pack .tf.bar.sha1label -side left ttk::entry $sha1entry -width $hashlength -font textfont -textvariable sha1string trace add variable sha1string write sha1change pack $sha1entry -side left -pady 2 - set bm_left_data { - #define left_width 16 - #define left_height 16 - static unsigned char left_bits[] = { - 0x00, 0x00, 0xc0, 0x01, 0xe0, 0x00, 0x70, 0x00, 0x38, 0x00, 0x1c, 0x00, - 0x0e, 0x00, 0xff, 0x7f, 0xff, 0x7f, 0xff, 0x7f, 0x0e, 0x00, 0x1c, 0x00, - 0x38, 0x00, 0x70, 0x00, 0xe0, 0x00, 0xc0, 0x01}; - } - set bm_right_data { - #define right_width 16 - #define right_height 16 - static unsigned char right_bits[] = { - 0x00, 0x00, 0xc0, 0x01, 0x80, 0x03, 0x00, 0x07, 0x00, 0x0e, 0x00, 0x1c, - 0x00, 0x38, 0xff, 0x7f, 0xff, 0x7f, 0xff, 0x7f, 0x00, 0x38, 0x00, 0x1c, - 0x00, 0x0e, 0x00, 0x07, 0x80, 0x03, 0xc0, 0x01}; - } - image create bitmap bm-left -data $bm_left_data -foreground $uifgcolor - image create bitmap bm-left-gray -data $bm_left_data -foreground $uifgdisabledcolor - image create bitmap bm-right -data $bm_right_data -foreground $uifgcolor - image create bitmap bm-right-gray -data $bm_right_data -foreground $uifgdisabledcolor - - ttk::button .tf.bar.leftbut -command goback -state disabled -width 26 - .tf.bar.leftbut configure -image [list bm-left disabled bm-left-gray] + ttk::button .tf.bar.leftbut -command goback -state disabled + .tf.bar.leftbut configure -text \u2190 -width 3 pack .tf.bar.leftbut -side left -fill y - ttk::button .tf.bar.rightbut -command goforw -state disabled -width 26 - .tf.bar.rightbut configure -image [list bm-right disabled bm-right-gray] + ttk::button .tf.bar.rightbut -command goforw -state disabled + .tf.bar.rightbut configure -text \u2192 -width 3 pack .tf.bar.rightbut -side left -fill y ttk::label .tf.bar.rowlabel -text [mc "Row"] @@ -2559,31 +2541,8 @@ proc makewindow {} { # build up the bottom bar of upper window ttk::label .tf.lbar.flabel -text "[mc "Find"] " - set bm_down_data { - #define down_width 16 - #define down_height 16 - static unsigned char down_bits[] = { - 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, - 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, - 0x87, 0xe1, 0x8e, 0x71, 0x9c, 0x39, 0xb8, 0x1d, - 0xf0, 0x0f, 0xe0, 0x07, 0xc0, 0x03, 0x80, 0x01}; - } - image create bitmap bm-down -data $bm_down_data -foreground $uifgcolor - ttk::button .tf.lbar.fnext -width 26 -command {dofind 1 1} - .tf.lbar.fnext configure -image bm-down - - set bm_up_data { - #define up_width 16 - #define up_height 16 - static unsigned char up_bits[] = { - 0x80, 0x01, 0xc0, 0x03, 0xe0, 0x07, 0xf0, 0x0f, - 0xb8, 0x1d, 0x9c, 0x39, 0x8e, 0x71, 0x87, 0xe1, - 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, - 0x80, 0x01, 0x80, 0x01, 0x80, 0x01, 0x80, 0x01}; - } - image create bitmap bm-up -data $bm_up_data -foreground $uifgcolor - ttk::button .tf.lbar.fprev -width 26 -command {dofind -1 1} - .tf.lbar.fprev configure -image bm-up + ttk::button .tf.lbar.fnext -command {dofind 1 1} -text \u2193 -width 3 + ttk::button .tf.lbar.fprev -command {dofind -1 1} -text \u2191 -width 3 ttk::label .tf.lbar.flab2 -text " [mc "commit"] " @@ -2656,7 +2615,7 @@ proc makewindow {} { ttk::label .bleft.mid.labeldiffcontext -text " [mc "Lines of context"]: " pack .bleft.mid.diff .bleft.mid.old .bleft.mid.new -side left -ipadx $wgap - spinbox .bleft.mid.diffcontext -width 5 \ + ttk::spinbox .bleft.mid.diffcontext -width 5 \ -from 0 -increment 1 -to 10000000 \ -validate all -validatecommand "diffcontextvalidate %P" \ -textvariable diffcontextstring @@ -8910,9 +8869,9 @@ proc sha1change {n1 n2 op} { } if {[$sha1but cget -state] == $state} return if {$state == "normal"} { - $sha1but conf -state normal -relief raised -text "[mc "Goto:"] " + $sha1but conf -state normal -text "[mc "Goto:"] " } else { - $sha1but conf -state disabled -relief flat -text "[mc "Commit ID:"] " + $sha1but conf -state disabled -text "[mc "Commit ID:"] " } } @@ -10294,7 +10253,9 @@ proc refill_reflist {} { if {![string match "remotes/*" $n] && [string match $reflistfilter $n]} { if {[commitinview $headids($n) $curview]} { lappend localrefs [list $n H] - if {[info exists upstreamofref($n)] && [commitinview $headids($upstreamofref($n)) $curview]} { + if {[info exists upstreamofref($n)] && \ + [info exists headids($upstreamofref($n))] && \ + [commitinview $headids($upstreamofref($n)) $curview]} { lappend trackedremoterefs [list $upstreamofref($n) R] } } else { @@ -11608,9 +11569,10 @@ proc mkfontdisp {font top which} { set fontpref($font) [set $font] ttk::button $top.${font}but -text $which \ -command [list choosefont $font $which] - ttk::label $top.$font -relief flat -font $font \ - -text $fontattr($font,family) -justify left + ttk::label $top.$font -font $font \ + -text $fontattr($font,family) grid x $top.${font}but $top.$font -sticky w + grid configure $top.$font -sticky ew } proc centertext {w} { @@ -11690,48 +11652,52 @@ proc prefspage_general {notebook} { ttk::label $page.ldisp -text [mc "Commit list display options"] -font mainfontbold grid $page.ldisp - -sticky w -pady 10 + ttk::label $page.spacer -text " " ttk::label $page.maxwidthl -text [mc "Maximum graph width (lines)"] - spinbox $page.maxwidth -from 0 -to 100 -width 4 -textvariable maxwidth + ttk::spinbox $page.maxwidth -from 0 -to 100 -width 4 -textvariable maxwidth grid $page.spacer $page.maxwidthl $page.maxwidth -sticky w #xgettext:no-tcl-format ttk::label $page.maxpctl -text [mc "Maximum graph width (% of pane)"] - spinbox $page.maxpct -from 1 -to 100 -width 4 -textvariable maxgraphpct + ttk::spinbox $page.maxpct -from 1 -to 100 -width 4 -textvariable maxgraphpct grid x $page.maxpctl $page.maxpct -sticky w + ttk::checkbutton $page.showlocal -text [mc "Show local changes"] \ -variable showlocalchanges grid x $page.showlocal -sticky w + ttk::checkbutton $page.hideremotes -text [mc "Hide remote refs"] \ -variable hideremotes grid x $page.hideremotes -sticky w ttk::entry $page.refstohide -textvariable refstohide - ttk::frame $page.refstohidef - ttk::label $page.refstohidef.l -text [mc "Refs to hide (space-separated globs)" ] - pack $page.refstohidef.l -side left - pack configure $page.refstohidef.l -padx 10 - grid x $page.refstohidef $page.refstohide -sticky ew + ttk::label $page.refstohidel -text [mc "Refs to hide (space-separated globs)"] + grid x $page.refstohidel $page.refstohide -sticky ew + grid configure $page.refstohide -padx {0 5} ttk::checkbutton $page.autocopy -text [mc "Copy commit ID to clipboard"] \ -variable autocopy grid x $page.autocopy -sticky w + if {[haveselectionclipboard]} { ttk::checkbutton $page.autoselect -text [mc "Copy commit ID to X11 selection"] \ -variable autoselect grid x $page.autoselect -sticky w } - spinbox $page.autosellen -from 1 -to $hashlength -width 4 -textvariable autosellen + ttk::spinbox $page.autosellen -from 1 -to $hashlength -width 4 -textvariable autosellen ttk::label $page.autosellenl -text [mc "Length of commit ID to copy"] grid x $page.autosellenl $page.autosellen -sticky w + ttk::label $page.kscroll1 -text [mc "Wheel scrolling multiplier"] - spinbox $page.kscroll -from 1 -to 20 -width 4 -textvariable kscroll + ttk::spinbox $page.kscroll -from 1 -to 20 -width 4 -textvariable kscroll grid x $page.kscroll1 $page.kscroll -sticky w ttk::label $page.ddisp -text [mc "Diff display options"] -font mainfontbold grid $page.ddisp - -sticky w -pady 10 + ttk::label $page.tabstopl -text [mc "Tab spacing"] - spinbox $page.tabstop -from 1 -to 20 -width 4 -textvariable tabstop + ttk::spinbox $page.tabstop -from 1 -to 20 -width 4 -textvariable tabstop grid x $page.tabstopl $page.tabstop -sticky w ttk::label $page.wrapcommentl -text [mc "Wrap comment text"] @@ -11745,12 +11711,15 @@ proc prefspage_general {notebook} { ttk::checkbutton $page.ntag -text [mc "Display nearby tags/heads"] \ -variable showneartags grid x $page.ntag -sticky w + ttk::label $page.maxrefsl -text [mc "Maximum # tags/heads to show"] - spinbox $page.maxrefs -from 1 -to 1000 -width 4 -textvariable maxrefs + ttk::spinbox $page.maxrefs -from 1 -to 1000 -width 4 -textvariable maxrefs grid x $page.maxrefsl $page.maxrefs -sticky w + ttk::checkbutton $page.ldiff -text [mc "Limit diffs to listed paths"] \ -variable limitdiffs grid x $page.ldiff -sticky w + ttk::checkbutton $page.lattr -text [mc "Support per-file encodings"] \ -variable perfile_attrs grid x $page.lattr -sticky w @@ -11759,76 +11728,109 @@ proc prefspage_general {notebook} { ttk::frame $page.extdifff ttk::label $page.extdifff.l -text [mc "External diff tool" ] ttk::button $page.extdifff.b -text [mc "Choose..."] -command choose_extdiff - pack $page.extdifff.l $page.extdifff.b -side left - pack configure $page.extdifff.l -padx 10 + pack $page.extdifff.l -side left + pack $page.extdifff.b -side right -padx {0 5} grid x $page.extdifff $page.extdifft -sticky ew + grid configure $page.extdifft -padx {0 5} ttk::entry $page.webbrowser -textvariable web_browser - ttk::frame $page.webbrowserf - ttk::label $page.webbrowserf.l -text [mc "Web browser" ] - pack $page.webbrowserf.l -side left - pack configure $page.webbrowserf.l -padx 10 - grid x $page.webbrowserf $page.webbrowser -sticky ew + ttk::label $page.webbrowserl -text [mc "Web browser" ] + grid x $page.webbrowserl $page.webbrowser -sticky ew + grid configure $page.webbrowser -padx {0 5} + + grid columnconfigure $page 2 -weight 1 return $page } proc prefspage_colors {notebook} { - global uicolor bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor + global bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor global diffbgcolors + global themeloader set page [create_prefs_page $notebook.colors] + ttk::label $page.themesel -font mainfontbold \ + -text [mc "Themes - change requires restart"] + grid $page.themesel - -sticky w -pady 10 + + ttk::label $page.themelabel -text [mc "Theme to use after restart"] + makedroplist $page.theme theme {*}[lsort [ttk::style theme names]] + grid x $page.themelabel $page.theme -sticky w + + ttk::entry $page.tloadvar -textvariable themeloader + ttk::frame $page.tloadframe + ttk::label $page.tloadframe.l -text [mc "Theme definition file"] + ttk::button $page.tloadframe.b -text [mc "Choose..."] \ + -command [list choose_themeloader $page] + pack $page.tloadframe.l -side left + pack $page.tloadframe.b -side right -padx {0 5} + pack configure $page.tloadframe.l -padx 0 + grid x $page.tloadframe $page.tloadvar -sticky ew + grid configure $page.tloadvar -padx {0 5} + + ttk::label $page.themelabel2 -text \ + [mc "The theme definition file may affect all themes."] + ttk::button $page.themebut2 -text [mc "Apply theme"] \ + -command [list updatetheme $page] + grid x $page.themebut2 $page.themelabel2 -sticky w + ttk::label $page.cdisp -text [mc "Colors: press to choose"] -font mainfontbold grid $page.cdisp - -sticky w -pady 10 - label $page.ui -padx 40 -relief sunk -background $uicolor - ttk::button $page.uibut -text [mc "Interface"] \ - -command [list choosecolor uicolor {} $page [mc "interface"]] - grid x $page.uibut $page.ui -sticky w label $page.bg -padx 40 -relief sunk -background $bgcolor ttk::button $page.bgbut -text [mc "Background"] \ -command [list choosecolor bgcolor {} $page [mc "background"]] grid x $page.bgbut $page.bg -sticky w + label $page.fg -padx 40 -relief sunk -background $fgcolor ttk::button $page.fgbut -text [mc "Foreground"] \ -command [list choosecolor fgcolor {} $page [mc "foreground"]] grid x $page.fgbut $page.fg -sticky w + label $page.diffold -padx 40 -relief sunk -background [lindex $diffcolors 0] ttk::button $page.diffoldbut -text [mc "Diff: old lines"] \ -command [list choosecolor diffcolors 0 $page [mc "diff old lines"]] grid x $page.diffoldbut $page.diffold -sticky w + label $page.diffoldbg -padx 40 -relief sunk -background [lindex $diffbgcolors 0] ttk::button $page.diffoldbgbut -text [mc "Diff: old lines bg"] \ -command [list choosecolor diffbgcolors 0 $page [mc "diff old lines bg"]] grid x $page.diffoldbgbut $page.diffoldbg -sticky w + label $page.diffnew -padx 40 -relief sunk -background [lindex $diffcolors 1] ttk::button $page.diffnewbut -text [mc "Diff: new lines"] \ -command [list choosecolor diffcolors 1 $page [mc "diff new lines"]] grid x $page.diffnewbut $page.diffnew -sticky w + label $page.diffnewbg -padx 40 -relief sunk -background [lindex $diffbgcolors 1] ttk::button $page.diffnewbgbut -text [mc "Diff: new lines bg"] \ -command [list choosecolor diffbgcolors 1 $page [mc "diff new lines bg"]] grid x $page.diffnewbgbut $page.diffnewbg -sticky w + label $page.hunksep -padx 40 -relief sunk -background [lindex $diffcolors 2] ttk::button $page.hunksepbut -text [mc "Diff: hunk header"] \ -command [list choosecolor diffcolors 2 $page [mc "diff hunk header"]] grid x $page.hunksepbut $page.hunksep -sticky w + label $page.markbgsep -padx 40 -relief sunk -background $markbgcolor ttk::button $page.markbgbut -text [mc "Marked line bg"] \ -command [list choosecolor markbgcolor {} $page [mc "marked line background"]] grid x $page.markbgbut $page.markbgsep -sticky w + label $page.selbgsep -padx 40 -relief sunk -background $selectbgcolor ttk::button $page.selbgbut -text [mc "Select bg"] \ -command [list choosecolor selectbgcolor {} $page [mc "background"]] grid x $page.selbgbut $page.selbgsep -sticky w + + grid columnconfigure $page 2 -weight 1 + return $page } proc prefspage_set_colorswatches {page} { - global uicolor bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor + global bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor global diffbgcolors - $page.ui configure -background $uicolor $page.bg configure -background $bgcolor $page.fg configure -background $fgcolor $page.diffold configure -background [lindex $diffcolors 0] @@ -11847,6 +11849,7 @@ proc prefspage_fonts {notebook} { mkfontdisp mainfont $page [mc "Main font"] mkfontdisp textfont $page [mc "Diff display font"] mkfontdisp uifont $page [mc "User interface font"] + grid columnconfigure $page 2 -weight 1 return $page } @@ -11881,7 +11884,7 @@ proc doprefs {} { grid rowconfigure $notebook 1 -weight 1 raise [lindex $pages 0] - grid $notebook -sticky news -padx 2 -pady 2 + grid $notebook -sticky news -padx 3 -pady 3 grid rowconfigure $top 0 -weight 1 grid columnconfigure $top 0 -weight 1 @@ -11890,12 +11893,13 @@ proc doprefs {} { ttk::button $top.buts.can -text [mc "Cancel"] -command prefscan -default normal bind $top <Key-Return> prefsok bind $top <Key-Escape> prefscan - grid $top.buts.ok $top.buts.can - grid columnconfigure $top.buts 0 -weight 1 -uniform a - grid columnconfigure $top.buts 1 -weight 1 -uniform a - grid $top.buts - - -pady 10 -sticky ew - grid columnconfigure $top 2 -weight 1 + grid $top.buts.ok $top.buts.can -padx 20 + grid $top.buts -sticky w -pady 10 bind $top <Visibility> [list focus $top.buts.ok] + + # let geometry manager determine run, set minimum size + update idletasks + wm minsize $top [winfo reqwidth $top] [winfo reqheight $top] } proc choose_extdiff {} { @@ -11907,6 +11911,51 @@ proc choose_extdiff {} { } } +proc run_themeloader {f} { + if {![info exists ::_themefiles_seen]} { + set ::_themefiles_seen [dict create] + } + + set fn [file normalize $f] + if {![dict exists $::_themefiles_seen $fn]} { + if {[catch {source $fn} err]} { + error_popup "could not interpret: $fn\n$err" + dict set ::_themefiles_seen $fn 0 + } else { + dict set ::_themefiles_seen $fn 1 + } + } + return [dict get $::_themefiles_seen $fn] +} + +proc updatetheme {prefspage {dotheme 1}} { + global theme + global themeloader + if {$themeloader ne {}} { + if {![run_themeloader $themeloader]} { + set themeloader {} + return + } else { + $prefspage.theme configure -values \ + [lsort [ttk::style theme names]] + } + } + if {$dotheme} { + ttk::style theme use $theme + set_gui_colors + prefspage_set_colorswatches $prefspage + } +} + +proc choose_themeloader {prefspage} { + global themeloader + set tfile [tk_getOpenFile -title [mc "Gitk: select theme definition"] -multiple false] + if {$tfile ne {}} { + set themeloader $tfile + updatetheme $prefspage 0 + } +} + proc choosecolor {v vi prefspage x} { global $v @@ -11930,21 +11979,6 @@ proc setselbg {c} { allcanvs itemconf secsel -fill $c } -# This sets the background color and the color scheme for the whole UI. -# For some reason, tk_setPalette chooses a nasty dark red for selectColor -# if we don't specify one ourselves, which makes the checkbuttons and -# radiobuttons look bad. This chooses white for selectColor if the -# background color is light, or black if it is dark. -proc setui {c} { - if {[tk windowingsystem] eq "win32"} { return } - set bg [winfo rgb . $c] - set selc black - if {[lindex $bg 0] + 1.5 * [lindex $bg 1] + 0.5 * [lindex $bg 2] > 100000} { - set selc white - } - tk_setPalette background $c selectColor $selc -} - proc setbg {c} { global bglist @@ -11969,10 +12003,9 @@ proc setfg {c} { } proc set_gui_colors {} { - global uicolor bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor + global bgcolor fgcolor ctext diffcolors selectbgcolor markbgcolor global diffbgcolors - setui $uicolor setbg $bgcolor setfg $fgcolor $ctext tag conf d0 -foreground [lindex $diffcolors 0] @@ -11994,6 +12027,7 @@ proc prefscan {} { catch {destroy $prefstop} unset prefstop fontcan + setttkstyle set_gui_colors } @@ -12460,11 +12494,13 @@ namespace import ::msgcat::mc # on OSX bring the current Wish process window to front if {[tk windowingsystem] eq "aqua"} { - safe_exec [list osascript -e [format { - tell application "System Events" - set frontmost of processes whose unix id is %d to true - end tell - } [pid] ]] + catch { + safe_exec [list osascript -e [format { + tell application "System Events" + set frontmost of processes whose unix id is %d to true + end tell + } [pid] ]] + } } # Unset GIT_TRACE var if set @@ -12569,17 +12605,11 @@ if {[tk windowingsystem] eq "aqua"} { set colors {"#00ff00" red blue magenta darkgrey brown orange} if {[tk windowingsystem] eq "win32"} { - set uicolor SystemButtonFace - set uifgcolor SystemButtonText - set uifgdisabledcolor SystemDisabledText set bgcolor SystemWindow set fgcolor SystemWindowText set selectbgcolor SystemHighlight set web_browser "cmd /c start" } else { - set uicolor grey85 - set uifgcolor black - set uifgdisabledcolor "#999" set bgcolor white set fgcolor black set selectbgcolor gray85 @@ -12619,6 +12649,12 @@ set circleoutlinecolor $fgcolor set foundbgcolor yellow set currentsearchhitbgcolor orange +set theme [ttk::style theme use] +set themeloader {} +set uicolor {} +set uifgcolor {} +set uifgdisabledcolor {} + # button for popping up context menus if {[tk windowingsystem] eq "aqua" && [package vcompare $::tcl_version 8.7] < 0} { set ctxbut <Button-2> @@ -12702,6 +12738,8 @@ set config_variables { tagfgcolor tagoutlinecolor textfont + theme + themeloader uicolor uifgcolor uifgdisabledcolor @@ -12801,7 +12839,13 @@ set nullid "0000000000000000000000000000000000000000" set nullid2 "0000000000000000000000000000000000000001" set nullfile "/dev/null" -setttkstyle +if {[file exists $themeloader]} { + if {![run_themeloader $themeloader]} { + puts stderr "Could not interpret themeloader: $themeloader" + exit 1 + } +} + set appname "gitk" set runq {} @@ -12917,6 +12961,7 @@ if {[tk windowingsystem] eq "win32"} { focus -force . } +setttkstyle set_gui_colors getcommits {} @@ -791,6 +791,12 @@ void get_version_info(struct strbuf *buf, int show_build_options) strbuf_addf(buf, "shell-path: %s\n", SHELL_PATH); /* NEEDSWORK: also save and output GIT-BUILD_OPTIONS? */ +#if defined WITH_RUST + strbuf_addstr(buf, "rust: enabled\n"); +#else + strbuf_addstr(buf, "rust: disabled\n"); +#endif + if (fsmonitor_ipc__is_supported()) strbuf_addstr(buf, "feature: fsmonitor--daemon\n"); #if defined LIBCURL_VERSION diff --git a/http-backend.c b/http-backend.c index d5dfe762bb..9084058f1e 100644 --- a/http-backend.c +++ b/http-backend.c @@ -603,18 +603,19 @@ static void get_head(struct strbuf *hdr, char *arg UNUSED) static void get_info_packs(struct strbuf *hdr, char *arg UNUSED) { size_t objdirlen = strlen(repo_get_object_directory(the_repository)); + struct packfile_store *packs = the_repository->objects->packfiles; struct strbuf buf = STRBUF_INIT; struct packed_git *p; size_t cnt = 0; select_getanyfile(hdr); - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (p->pack_local) cnt++; } strbuf_grow(&buf, cnt * 53 + 2); - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (p->pack_local) strbuf_addf(&buf, "P %s\n", p->pack_name + objdirlen + 6); } diff --git a/http-push.c b/http-push.c index 4c43ba3bc7..a1c01e3b9b 100644 --- a/http-push.c +++ b/http-push.c @@ -208,7 +208,8 @@ static void curl_setup_http(CURL *curl, const char *url, curl_easy_setopt(curl, CURLOPT_UPLOAD, 1L); curl_easy_setopt(curl, CURLOPT_URL, url); curl_easy_setopt(curl, CURLOPT_INFILE, buffer); - curl_easy_setopt(curl, CURLOPT_INFILESIZE, buffer->buf.len); + curl_easy_setopt(curl, CURLOPT_INFILESIZE_LARGE, + cast_size_t_to_curl_off_t(buffer->buf.len)); curl_easy_setopt(curl, CURLOPT_READFUNCTION, fread_buffer); curl_easy_setopt(curl, CURLOPT_SEEKFUNCTION, seek_buffer); curl_easy_setopt(curl, CURLOPT_SEEKDATA, buffer); @@ -2416,6 +2416,7 @@ static char *fetch_pack_index(unsigned char *hash, const char *base_url) static int fetch_and_setup_pack_index(struct packed_git **packs_head, unsigned char *sha1, const char *base_url) { + struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *new_pack, *p; char *tmp_idx = NULL; int ret; @@ -2424,7 +2425,7 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head, * If we already have the pack locally, no need to fetch its index or * even add it to list; we already have all of its objects. */ - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { if (hasheq(p->hash, sha1, the_repository->hash_algo)) return 0; } @@ -2549,7 +2550,7 @@ void http_install_packfile(struct packed_git *p, lst = &((*lst)->next); *lst = (*lst)->next; - install_packed_git(the_repository, p); + packfile_store_add_pack(the_repository->objects->packfiles, p); } struct http_pack_request *new_http_pack_request( @@ -8,6 +8,7 @@ struct packed_git; #include <curl/curl.h> #include <curl/easy.h> +#include "gettext.h" #include "strbuf.h" #include "remote.h" @@ -95,6 +96,15 @@ static inline int missing__target(int code, int result) #define missing_target(a) missing__target((a)->http_code, (a)->curl_result) +static inline curl_off_t cast_size_t_to_curl_off_t(size_t a) +{ + uintmax_t size = a; + if (size > maximum_signed_value_of_type(curl_off_t)) + die(_("number too large to represent as curl_off_t " + "on this platform: %"PRIuMAX), (uintmax_t)a); + return (curl_off_t)a; +} + /* * Normalize curl results to handle CURL_FAILONERROR (or lack thereof). Failing * http codes have their "result" converted to CURLE_HTTP_RETURNED_ERROR, and @@ -210,7 +220,7 @@ int finish_http_pack_request(struct http_pack_request *preq); void release_http_pack_request(struct http_pack_request *preq); /* - * Remove p from the given list, and invoke install_packed_git() on it. + * Remove p from the given list, and invoke packfile_store_add_pack() on it. * * This is a convenience function for users that have obtained a list of packs * from http_get_info_packs() and have chosen a specific pack to fetch. diff --git a/imap-send.c b/imap-send.c index 4bd5b8aa0d..26dda7f328 100644 --- a/imap-send.c +++ b/imap-send.c @@ -1721,7 +1721,7 @@ static int curl_append_msgs_to_imap(struct imap_server_conf *server, lf_to_crlf(&msgbuf.buf); curl_easy_setopt(curl, CURLOPT_INFILESIZE_LARGE, - (curl_off_t)(msgbuf.buf.len-prev_len)); + cast_size_t_to_curl_off_t(msgbuf.buf.len-prev_len)); res = curl_easy_perform(curl); diff --git a/log-tree.c b/log-tree.c index 67d9ace596..7d917f2a83 100644 --- a/log-tree.c +++ b/log-tree.c @@ -718,7 +718,8 @@ static void show_diff_of_diff(struct rev_info *opt) .creation_factor = opt->creation_factor, .dual_color = 1, .max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT, - .diffopt = &opts + .diffopt = &opts, + .log_arg = &opt->rdiff_log_arg }; memcpy(&dq, &diff_queued_diff, sizeof(diff_queued_diff)); @@ -1,5 +1,4 @@ #define USE_THE_REPOSITORY_VARIABLE -#define DISABLE_SIGN_COMPARE_WARNINGS #include "git-compat-util.h" #include "environment.h" @@ -243,10 +242,9 @@ void clear_mailmap(struct string_list *map) static struct string_list_item *lookup_prefix(struct string_list *map, const char *string, size_t len) { - int i = string_list_find_insert_index(map, string, 1); - if (i < 0) { - /* exact match */ - i = -1 - i; + bool exact_match; + size_t i = string_list_find_insert_index(map, string, &exact_match); + if (exact_match) { if (!string[len]) return &map->items[i]; /* @@ -267,7 +265,7 @@ static struct string_list_item *lookup_prefix(struct string_list *map, * overlong key would be inserted, which must come after the * real location of the key if one exists. */ - while (0 <= --i && i < map->nr) { + while (i-- && i < map->nr) { int cmp = strncasecmp(map->items[i].string, string, len); if (cmp < 0) /* diff --git a/meson.build b/meson.build index db1710e229..cee9424475 100644 --- a/meson.build +++ b/meson.build @@ -220,7 +220,7 @@ project('git', 'c', # learned to define __STDC_VERSION__ with C11 and later. We thus require # GNU C99 and fall back to C11. Meson only learned to handle the fallback # with version 1.3.0, so on older versions we use GNU C99 unconditionally. - default_options: meson.version().version_compare('>=1.3.0') ? ['c_std=gnu99,c11'] : ['c_std=gnu99'], + default_options: meson.version().version_compare('>=1.3.0') ? ['rust_std=2018', 'c_std=gnu99,c11'] : ['rust_std=2018', 'c_std=gnu99'], ) fs = import('fs') @@ -452,6 +452,7 @@ libgit_sources = [ 'reftable/error.c', 'reftable/block.c', 'reftable/blocksource.c', + 'reftable/fsck.c', 'reftable/iter.c', 'reftable/merged.c', 'reftable/pq.c', @@ -522,7 +523,6 @@ libgit_sources = [ 'usage.c', 'userdiff.c', 'utf8.c', - 'varint.c', 'version.c', 'versioncmp.c', 'walker.c', @@ -1703,6 +1703,17 @@ version_def_h = custom_target( ) libgit_sources += version_def_h +cargo = find_program('cargo', dirs: program_path, native: true, required: get_option('rust')) +rust_option = get_option('rust').disable_auto_if(not cargo.found()) +if rust_option.allowed() + subdir('src') + libgit_c_args += '-DWITH_RUST' +else + libgit_sources += [ + 'varint.c', + ] +endif + libgit = declare_dependency( link_with: static_library('git', sources: libgit_sources, @@ -2249,6 +2260,7 @@ summary({ 'pcre2': pcre2, 'perl': perl_features_enabled, 'python': target_python.found(), + 'rust': rust_option.allowed(), }, section: 'Auto-detected features', bool_yn: true) summary({ diff --git a/meson_options.txt b/meson_options.txt index 1668f260a1..143dee9237 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -71,6 +71,8 @@ option('zlib_backend', type: 'combo', choices: ['auto', 'zlib', 'zlib-ng'], valu # Build tweaks. option('breaking_changes', type: 'boolean', value: false, description: 'Enable upcoming breaking changes.') +option('rust', type: 'feature', value: 'auto', + description: 'Enable building with Rust.') option('macos_use_homebrew_gettext', type: 'boolean', value: true, description: 'Use gettext from Homebrew instead of the slightly-broken system-provided one.') @@ -93,6 +93,12 @@ static int midx_read_object_offsets(const unsigned char *chunk_start, return 0; } +struct multi_pack_index *get_multi_pack_index(struct odb_source *source) +{ + packfile_store_prepare(source->odb->packfiles); + return source->midx; +} + static struct multi_pack_index *load_multi_pack_index_one(struct odb_source *source, const char *midx_name) { @@ -443,7 +449,6 @@ int prepare_midx_pack(struct multi_pack_index *m, { struct repository *r = m->source->odb->repo; struct strbuf pack_name = STRBUF_INIT; - struct strbuf key = STRBUF_INIT; struct packed_git *p; pack_int_id = midx_for_pack(&m, pack_int_id); @@ -455,25 +460,11 @@ int prepare_midx_pack(struct multi_pack_index *m, strbuf_addf(&pack_name, "%s/pack/%s", m->source->path, m->pack_names[pack_int_id]); - - /* pack_map holds the ".pack" name, but we have the .idx */ - strbuf_addbuf(&key, &pack_name); - strbuf_strip_suffix(&key, ".idx"); - strbuf_addstr(&key, ".pack"); - p = hashmap_get_entry_from_hash(&r->objects->pack_map, - strhash(key.buf), key.buf, - struct packed_git, packmap_ent); - if (!p) { - p = add_packed_git(r, pack_name.buf, pack_name.len, - m->source->local); - if (p) { - install_packed_git(r, p); - list_add_tail(&p->mru, &r->objects->packed_git_mru); - } - } - + 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); - strbuf_release(&key); if (!p) { m->packs[pack_int_id] = MIDX_PACK_ERROR; @@ -94,6 +94,7 @@ void get_midx_chain_filename(struct odb_source *source, struct strbuf *out); void get_split_midx_filename_ext(struct odb_source *source, struct strbuf *buf, const unsigned char *hash, const char *ext); +struct multi_pack_index *get_multi_pack_index(struct odb_source *source); struct multi_pack_index *load_multi_pack_index(struct odb_source *source); int prepare_midx_pack(struct multi_pack_index *m, uint32_t pack_int_id); struct packed_git *nth_midxed_pack(struct multi_pack_index *m, diff --git a/object-file.c b/object-file.c index 17a236d2fe..4675c8ed6b 100644 --- a/object-file.c +++ b/object-file.c @@ -1504,7 +1504,7 @@ clear_exit: strbuf_release(&packname); /* Make objects we just wrote available to ourselves */ - reprepare_packed_git(repo); + odb_reprepare(repo->objects); } /* diff --git a/object-name.c b/object-name.c index 7774991d28..f6902e140d 100644 --- a/object-name.c +++ b/object-name.c @@ -213,7 +213,7 @@ static void find_short_packed_object(struct disambiguate_state *ds) unique_in_midx(m, ds); } - for (p = get_packed_git(ds->repo); p && !ds->ambiguous; + for (p = packfile_store_get_packs(ds->repo->objects->packfiles); p && !ds->ambiguous; p = p->next) unique_in_pack(p, ds); } @@ -596,7 +596,7 @@ static enum get_oid_result get_short_oid(struct repository *r, * or migrated from loose to packed. */ if (status == MISSING_OBJECT) { - reprepare_packed_git(r); + odb_reprepare(r->objects); find_short_object_filename(&ds); find_short_packed_object(&ds); status = finish_object_disambiguation(&ds, oid); @@ -805,7 +805,7 @@ static void find_abbrev_len_packed(struct min_abbrev_data *mad) find_abbrev_len_for_midx(m, mad); } - for (p = get_packed_git(mad->repo); p; p = p->next) + for (p = packfile_store_get_packs(mad->repo->objects->packfiles); p; p = p->next) find_abbrev_len_for_pack(p, mad); } @@ -694,7 +694,7 @@ static int do_oid_object_info_extended(struct object_database *odb, /* Not a loose object; someone else may have just packed it. */ if (!(flags & OBJECT_INFO_QUICK)) { - reprepare_packed_git(odb->repo); + odb_reprepare(odb->repo->objects); if (find_pack_entry(odb->repo, real, &e)) break; } @@ -996,8 +996,7 @@ struct object_database *odb_new(struct repository *repo) memset(o, 0, sizeof(*o)); o->repo = repo; - INIT_LIST_HEAD(&o->packed_git_mru); - hashmap_init(&o->pack_map, pack_map_entry_cmp, NULL, 0); + o->packfiles = packfile_store_new(o); pthread_mutex_init(&o->replace_mutex, NULL); string_list_init_dup(&o->submodule_source_paths); return o; @@ -1035,21 +1034,36 @@ void odb_clear(struct object_database *o) free((char *) o->cached_objects[i].value.buf); FREE_AND_NULL(o->cached_objects); - INIT_LIST_HEAD(&o->packed_git_mru); close_object_store(o); + packfile_store_free(o->packfiles); + o->packfiles = NULL; + + string_list_clear(&o->submodule_source_paths, 0); +} + +void odb_reprepare(struct object_database *o) +{ + struct odb_source *source; + + obj_read_lock(); /* - * `close_object_store()` only closes the packfiles, but doesn't free - * them. We thus have to do this manually. + * Reprepare alt odbs, in case the alternates file was modified + * during the course of this process. This only _adds_ odbs to + * the linked list, so existing odbs will continue to exist for + * the lifetime of the process. */ - for (struct packed_git *p = o->packed_git, *next; p; p = next) { - next = p->next; - free(p); - } - o->packed_git = NULL; + o->loaded_alternates = 0; + odb_prepare_alternates(o); - hashmap_clear(&o->pack_map); - string_list_clear(&o->submodule_source_paths, 0); + for (source = o->sources; source; source = source->next) + odb_clear_loose_cache(source); + + o->approximate_object_count_valid = 0; + + packfile_store_reprepare(o->packfiles); + + obj_read_unlock(); } struct odb_transaction *odb_transaction_begin(struct object_database *odb) @@ -3,7 +3,6 @@ #include "hashmap.h" #include "object.h" -#include "list.h" #include "oidset.h" #include "oidmap.h" #include "string-list.h" @@ -91,6 +90,7 @@ struct odb_source { }; struct packed_git; +struct packfile_store; struct cached_object_entry; struct odb_transaction; @@ -139,20 +139,8 @@ struct object_database { struct commit_graph *commit_graph; unsigned commit_graph_attempted : 1; /* if loading has been attempted */ - /* - * private data - * - * should only be accessed directly by packfile.c - */ - - struct packed_git *packed_git; - /* A most-recently-used ordered version of the packed_git list. */ - struct list_head packed_git_mru; - - struct { - struct packed_git **packs; - unsigned flags; - } kept_pack_cache; + /* Should only be accessed directly by packfile.c and midx.c. */ + struct packfile_store *packfiles; /* * This is meant to hold a *small* number of objects that you would @@ -164,12 +152,6 @@ struct object_database { size_t cached_object_nr, cached_object_alloc; /* - * A map of packfiles to packed_git structs for tracking which - * packs have been loaded already. - */ - struct hashmap pack_map; - - /* * A fast, rough count of the number of objects in the repository. * These two fields are not meant for direct access. Use * repo_approximate_object_count() instead. @@ -178,12 +160,6 @@ struct object_database { unsigned approximate_object_count_valid : 1; /* - * Whether packed_git has already been populated with this repository's - * packs. - */ - unsigned packed_git_initialized : 1; - - /* * Submodule source paths that will be added as additional sources to * allow lookup of submodule objects via the main object database. */ @@ -194,6 +170,12 @@ struct object_database *odb_new(struct repository *repo); void odb_clear(struct object_database *o); /* + * Clear caches, reload alternates and then reload object sources so that new + * objects may become accessible. + */ +void odb_reprepare(struct object_database *o); + +/* * Starts an ODB transaction. Subsequent objects are written to the transaction * and not committed until odb_transaction_commit() is invoked on the * transaction. If the ODB already has a pending transaction, NULL is returned. @@ -507,37 +489,4 @@ static inline int odb_write_object(struct object_database *odb, return odb_write_object_ext(odb, buf, len, type, oid, NULL, 0); } -/* Compatibility wrappers, to be removed once Git 2.51 has been released. */ -#include "repository.h" - -static inline int oid_object_info_extended(struct repository *r, - const struct object_id *oid, - struct object_info *oi, - unsigned flags) -{ - return odb_read_object_info_extended(r->objects, oid, oi, flags); -} - -static inline int oid_object_info(struct repository *r, - const struct object_id *oid, - unsigned long *sizep) -{ - return odb_read_object_info(r->objects, oid, sizep); -} - -static inline void *repo_read_object_file(struct repository *r, - const struct object_id *oid, - enum object_type *type, - unsigned long *size) -{ - return odb_read_object(r->objects, oid, type, size); -} - -static inline int has_object(struct repository *r, - const struct object_id *oid, - unsigned flags) -{ - return odb_has_object(r->objects, oid, flags); -} - #endif /* ODB_H */ diff --git a/pack-bitmap.c b/pack-bitmap.c index 058bdb5d7d..ac71035d77 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -664,7 +664,7 @@ static int open_pack_bitmap(struct repository *r, struct packed_git *p; int ret = -1; - for (p = get_all_packs(r); p; p = p->next) { + for (p = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { if (open_pack_bitmap_1(bitmap_git, p) == 0) { ret = 0; /* @@ -3362,7 +3362,7 @@ int verify_bitmap_files(struct repository *r) free(midx_bitmap_name); } - for (struct packed_git *p = get_all_packs(r); + for (struct packed_git *p = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { char *pack_bitmap_name = pack_bitmap_filename(p); res |= verify_bitmap_file(r->hash_algo, pack_bitmap_name); diff --git a/pack-objects.c b/pack-objects.c index a9d9855063..9d6ee72569 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -4,6 +4,7 @@ #include "pack-objects.h" #include "packfile.h" #include "parse.h" +#include "repository.h" static uint32_t locate_object_entry_hash(struct packing_data *pdata, const struct object_id *oid, @@ -86,6 +87,7 @@ struct object_entry *packlist_find(struct packing_data *pdata, static void prepare_in_pack_by_idx(struct packing_data *pdata) { + struct packfile_store *packs = pdata->repo->objects->packfiles; struct packed_git **mapping, *p; int cnt = 0, nr = 1U << OE_IN_PACK_BITS; @@ -95,7 +97,7 @@ static void prepare_in_pack_by_idx(struct packing_data *pdata) * (i.e. in_pack_idx also zero) should return NULL. */ mapping[cnt++] = NULL; - for (p = get_all_packs(pdata->repo); p; p = p->next, cnt++) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next, cnt++) { if (cnt == nr) { free(mapping); return; diff --git a/packfile.c b/packfile.c index acb680966d..5a7caec292 100644 --- a/packfile.c +++ b/packfile.c @@ -278,7 +278,7 @@ static int unuse_one_window(struct packed_git *current) if (current) scan_windows(current, &lru_p, &lru_w, &lru_l); - for (p = current->repo->objects->packed_git; p; p = p->next) + for (p = current->repo->objects->packfiles->packs; p; p = p->next) scan_windows(p, &lru_p, &lru_w, &lru_l); if (lru_p) { munmap(lru_w->base, lru_w->len); @@ -362,13 +362,8 @@ void close_pack(struct packed_git *p) void close_object_store(struct object_database *o) { struct odb_source *source; - struct packed_git *p; - for (p = o->packed_git; p; p = p->next) - if (p->do_not_close) - BUG("want to close pack marked 'do-not-close'"); - else - close_pack(p); + packfile_store_close(o->packfiles); for (source = o->sources; source; source = source->next) { if (source->midx) @@ -468,7 +463,7 @@ static int close_one_pack(struct repository *r) struct pack_window *mru_w = NULL; int accept_windows_inuse = 1; - for (p = r->objects->packed_git; p; p = p->next) { + for (p = r->objects->packfiles->packs; p; p = p->next) { if (p->pack_fd == -1) continue; find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); @@ -784,16 +779,44 @@ struct packed_git *add_packed_git(struct repository *r, const char *path, return p; } -void install_packed_git(struct repository *r, struct packed_git *pack) +void packfile_store_add_pack(struct packfile_store *store, + struct packed_git *pack) { if (pack->pack_fd != -1) pack_open_fds++; - pack->next = r->objects->packed_git; - r->objects->packed_git = pack; + pack->next = store->packs; + store->packs = pack; hashmap_entry_init(&pack->packmap_ent, strhash(pack->pack_name)); - hashmap_add(&r->objects->pack_map, &pack->packmap_ent); + hashmap_add(&store->map, &pack->packmap_ent); +} + +struct packed_git *packfile_store_load_pack(struct packfile_store *store, + const char *idx_path, int local) +{ + struct strbuf key = STRBUF_INIT; + struct packed_git *p; + + /* + * We're being called with the path to the index file, but `pack_map` + * holds the path to the packfile itself. + */ + strbuf_addstr(&key, idx_path); + 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); + if (!p) { + p = add_packed_git(store->odb->repo, idx_path, + strlen(idx_path), local); + if (p) + packfile_store_add_pack(store, p); + } + + strbuf_release(&key); + return p; } void (*report_garbage)(unsigned seen_bits, const char *path); @@ -895,23 +918,14 @@ static void prepare_pack(const char *full_name, size_t full_name_len, const char *file_name, void *_data) { struct prepare_pack_data *data = (struct prepare_pack_data *)_data; - struct packed_git *p; size_t base_len = full_name_len; if (strip_suffix_mem(full_name, &base_len, ".idx") && !(data->m && midx_contains_pack(data->m, file_name))) { - struct hashmap_entry hent; - char *pack_name = xstrfmt("%.*s.pack", (int)base_len, full_name); - unsigned int hash = strhash(pack_name); - hashmap_entry_init(&hent, hash); - - /* Don't reopen a pack we already have. */ - if (!hashmap_get(&data->r->objects->pack_map, &hent, pack_name)) { - p = add_packed_git(data->r, full_name, full_name_len, data->local); - if (p) - install_packed_git(data->r, p); - } - free(pack_name); + char *trimmed_path = xstrndup(full_name, full_name_len); + packfile_store_load_pack(data->r->objects->packfiles, + trimmed_path, data->local); + free(trimmed_path); } if (!report_garbage) @@ -951,40 +965,6 @@ static void prepare_packed_git_one(struct odb_source *source) string_list_clear(data.garbage, 0); } -static void prepare_packed_git(struct repository *r); -/* - * Give a fast, rough count of the number of objects in the repository. This - * ignores loose objects completely. If you have a lot of them, then either - * you should repack because your performance will be awful, or they are - * all unreachable objects about to be pruned, in which case they're not really - * interesting as a measure of repo size in the first place. - */ -unsigned long repo_approximate_object_count(struct repository *r) -{ - if (!r->objects->approximate_object_count_valid) { - struct odb_source *source; - unsigned long count = 0; - struct packed_git *p; - - prepare_packed_git(r); - - 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; - } - - for (p = r->objects->packed_git; p; p = p->next) { - if (open_pack_index(p)) - continue; - count += p->num_objects; - } - r->objects->approximate_object_count = count; - r->objects->approximate_object_count_valid = 1; - } - return r->objects->approximate_object_count; -} - DEFINE_LIST_SORT(static, sort_packs, struct packed_git, next); static int sort_pack(const struct packed_git *a, const struct packed_git *b) @@ -1013,80 +993,51 @@ static int sort_pack(const struct packed_git *a, const struct packed_git *b) return -1; } -static void rearrange_packed_git(struct repository *r) -{ - sort_packs(&r->objects->packed_git, sort_pack); -} - -static void prepare_packed_git_mru(struct repository *r) +static void packfile_store_prepare_mru(struct packfile_store *store) { struct packed_git *p; - INIT_LIST_HEAD(&r->objects->packed_git_mru); + INIT_LIST_HEAD(&store->mru); - for (p = r->objects->packed_git; p; p = p->next) - list_add_tail(&p->mru, &r->objects->packed_git_mru); + for (p = store->packs; p; p = p->next) + list_add_tail(&p->mru, &store->mru); } -static void prepare_packed_git(struct repository *r) +void packfile_store_prepare(struct packfile_store *store) { struct odb_source *source; - if (r->objects->packed_git_initialized) + if (store->initialized) return; - odb_prepare_alternates(r->objects); - for (source = r->objects->sources; source; source = source->next) { + odb_prepare_alternates(store->odb); + for (source = store->odb->sources; source; source = source->next) { prepare_multi_pack_index_one(source); prepare_packed_git_one(source); } - rearrange_packed_git(r); - - prepare_packed_git_mru(r); - r->objects->packed_git_initialized = 1; -} - -void reprepare_packed_git(struct repository *r) -{ - struct odb_source *source; + sort_packs(&store->packs, sort_pack); - obj_read_lock(); - - /* - * Reprepare alt odbs, in case the alternates file was modified - * during the course of this process. This only _adds_ odbs to - * the linked list, so existing odbs will continue to exist for - * the lifetime of the process. - */ - r->objects->loaded_alternates = 0; - odb_prepare_alternates(r->objects); - - for (source = r->objects->sources; source; source = source->next) - odb_clear_loose_cache(source); - - r->objects->approximate_object_count_valid = 0; - r->objects->packed_git_initialized = 0; - prepare_packed_git(r); - obj_read_unlock(); + packfile_store_prepare_mru(store); + store->initialized = true; } -struct packed_git *get_packed_git(struct repository *r) +void packfile_store_reprepare(struct packfile_store *store) { - prepare_packed_git(r); - return r->objects->packed_git; + store->initialized = false; + packfile_store_prepare(store); } -struct multi_pack_index *get_multi_pack_index(struct odb_source *source) +struct packed_git *packfile_store_get_packs(struct packfile_store *store) { - prepare_packed_git(source->odb->repo); - return source->midx; + packfile_store_prepare(store); + return store->packs; } -struct packed_git *get_all_packs(struct repository *r) +struct packed_git *packfile_store_get_all_packs(struct packfile_store *store) { - prepare_packed_git(r); + packfile_store_prepare(store); - for (struct odb_source *source = r->objects->sources; source; source = source->next) { + for (struct odb_source *source = store->odb->sources; source; source = source->next) { struct multi_pack_index *m = source->midx; if (!m) continue; @@ -1094,13 +1045,46 @@ struct packed_git *get_all_packs(struct repository *r) prepare_midx_pack(m, i); } - return r->objects->packed_git; + return store->packs; } -struct list_head *get_packed_git_mru(struct repository *r) +struct list_head *packfile_store_get_packs_mru(struct packfile_store *store) { - prepare_packed_git(r); - return &r->objects->packed_git_mru; + packfile_store_prepare(store); + return &store->mru; +} + +/* + * Give a fast, rough count of the number of objects in the repository. This + * ignores loose objects completely. If you have a lot of them, then either + * you should repack because your performance will be awful, or they are + * all unreachable objects about to be pruned, in which case they're not really + * interesting as a measure of repo size in the first place. + */ +unsigned long repo_approximate_object_count(struct repository *r) +{ + if (!r->objects->approximate_object_count_valid) { + struct odb_source *source; + unsigned long count = 0; + struct packed_git *p; + + packfile_store_prepare(r->objects->packfiles); + + 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; + } + + for (p = r->objects->packfiles->packs; p; p = p->next) { + if (open_pack_index(p)) + continue; + count += p->num_objects; + } + r->objects->approximate_object_count = count; + r->objects->approximate_object_count_valid = 1; + } + return r->objects->approximate_object_count; } unsigned long unpack_object_header_buffer(const unsigned char *buf, @@ -1155,7 +1139,7 @@ unsigned long get_size_from_delta(struct packed_git *p, * * Other worrying sections could be the call to close_pack_fd(), * which can close packs even with in-use windows, and to - * reprepare_packed_git(). Regarding the former, mmap doc says: + * odb_reprepare(). Regarding the former, mmap doc says: * "closing the file descriptor does not unmap the region". And * for the latter, it won't re-open already available packs. */ @@ -1219,7 +1203,7 @@ const struct packed_git *has_packed_and_bad(struct repository *r, { struct packed_git *p; - for (p = r->objects->packed_git; p; p = p->next) + for (p = r->objects->packfiles->packs; p; p = p->next) if (oidset_contains(&p->bad_objects, oid)) return p; return NULL; @@ -2074,19 +2058,19 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa { struct list_head *pos; - prepare_packed_git(r); + packfile_store_prepare(r->objects->packfiles); for (struct odb_source *source = r->objects->sources; source; source = source->next) if (source->midx && fill_midx_entry(source->midx, oid, e)) return 1; - if (!r->objects->packed_git) + if (!r->objects->packfiles->packs) return 0; - list_for_each(pos, &r->objects->packed_git_mru) { + list_for_each(pos, &r->objects->packfiles->mru) { struct packed_git *p = list_entry(pos, struct packed_git, mru); if (!p->multi_pack_index && fill_pack_entry(oid, e, p)) { - list_move(&p->mru, &r->objects->packed_git_mru); + list_move(&p->mru, &r->objects->packfiles->mru); return 1; } } @@ -2096,19 +2080,19 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa static void maybe_invalidate_kept_pack_cache(struct repository *r, unsigned flags) { - if (!r->objects->kept_pack_cache.packs) + if (!r->objects->packfiles->kept_cache.packs) return; - if (r->objects->kept_pack_cache.flags == flags) + if (r->objects->packfiles->kept_cache.flags == flags) return; - FREE_AND_NULL(r->objects->kept_pack_cache.packs); - r->objects->kept_pack_cache.flags = 0; + FREE_AND_NULL(r->objects->packfiles->kept_cache.packs); + r->objects->packfiles->kept_cache.flags = 0; } struct packed_git **kept_pack_cache(struct repository *r, unsigned flags) { maybe_invalidate_kept_pack_cache(r, flags); - if (!r->objects->kept_pack_cache.packs) { + if (!r->objects->packfiles->kept_cache.packs) { struct packed_git **packs = NULL; size_t nr = 0, alloc = 0; struct packed_git *p; @@ -2121,7 +2105,7 @@ struct packed_git **kept_pack_cache(struct repository *r, unsigned flags) * covers, one kept and one not kept, but the midx returns only * the non-kept version. */ - for (p = get_all_packs(r); p; p = p->next) { + for (p = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { if ((p->pack_keep && (flags & ON_DISK_KEEP_PACKS)) || (p->pack_keep_in_core && (flags & IN_CORE_KEEP_PACKS))) { ALLOC_GROW(packs, nr + 1, alloc); @@ -2131,11 +2115,11 @@ struct packed_git **kept_pack_cache(struct repository *r, unsigned flags) ALLOC_GROW(packs, nr + 1, alloc); packs[nr] = NULL; - r->objects->kept_pack_cache.packs = packs; - r->objects->kept_pack_cache.flags = flags; + r->objects->packfiles->kept_cache.packs = packs; + r->objects->packfiles->kept_cache.flags = flags; } - return r->objects->kept_pack_cache.packs; + return r->objects->packfiles->kept_cache.packs; } int find_kept_pack_entry(struct repository *r, @@ -2218,7 +2202,7 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, int r = 0; int pack_errors = 0; - for (p = get_all_packs(repo); p; p = p->next) { + for (p = packfile_store_get_all_packs(repo->objects->packfiles); p; p = p->next) { if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) continue; if ((flags & FOR_EACH_OBJECT_PROMISOR_ONLY) && @@ -2332,3 +2316,46 @@ int parse_pack_header_option(const char *in, unsigned char *out, unsigned int *l *len = hdr - out; 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); + 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); + 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) + BUG("want to close pack marked 'do-not-close'"); + close_pack(p); + } +} diff --git a/packfile.h b/packfile.h index f16753f2a9..e7a5792b6c 100644 --- a/packfile.h +++ b/packfile.h @@ -52,19 +52,114 @@ struct packed_git { char pack_name[FLEX_ARRAY]; /* more */ }; -static inline 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; +/* + * A store that manages packfiles for a given object database. + */ +struct packfile_store { + struct object_database *odb; - pg1 = container_of(entry, const struct packed_git, packmap_ent); - pg2 = container_of(entry2, const struct packed_git, packmap_ent); + /* + * The list of packfiles in the order in which they are being added to + * the store. + */ + struct packed_git *packs; - return strcmp(pg1->pack_name, key ? key : pg2->pack_name); -} + /* + * Cache of packfiles which are marked as "kept", either because there + * is an on-disk ".keep" file or because they are marked as "kept" in + * memory. + * + * Should not be accessed directly, but via `kept_pack_cache()`. The + * list of packs gets invalidated when the stored flags and the flags + * passed to `kept_pack_cache()` mismatch. + */ + struct { + struct packed_git **packs; + 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; + + /* + * Whether packfiles have already been populated with this store's + * packs. + */ + bool initialized; +}; + +/* + * Allocate and initialize a new empty packfile store for the given object + * database. + */ +struct packfile_store *packfile_store_new(struct object_database *odb); + +/* + * Free the packfile store and all its associated state. All packfiles + * tracked by the store will be closed. + */ +void packfile_store_free(struct packfile_store *store); + +/* + * Close all packfiles associated with this store. The packfiles won't be + * free'd, so they can be re-opened at a later point in time. + */ +void packfile_store_close(struct packfile_store *store); + +/* + * Prepare the packfile store by loading packfiles and multi-pack indices for + * all alternates. This becomes a no-op if the store is already prepared. + * + * It shouldn't typically be necessary to call this function directly, as + * functions that access the store know to prepare it. + */ +void packfile_store_prepare(struct packfile_store *store); + +/* + * Clear the packfile caches and try to look up any new packfiles that have + * appeared since last preparing the packfiles store. + * + * This function must be called under the `odb_read_lock()`. + */ +void packfile_store_reprepare(struct packfile_store *store); + +/* + * Add the pack to the store so that contained objects become accessible via + * the store. This moves ownership into the store. + */ +void packfile_store_add_pack(struct packfile_store *store, + struct packed_git *pack); + +/* + * Get packs managed by the given store. Does not load the MIDX or any packs + * referenced by it. + */ +struct packed_git *packfile_store_get_packs(struct packfile_store *store); + +/* + * Get all packs managed by the given store, including packfiles that are + * referenced by multi-pack indices. + */ +struct packed_git *packfile_store_get_all_packs(struct packfile_store *store); + +/* + * Get all packs in most-recently-used order. + */ +struct list_head *packfile_store_get_packs_mru(struct packfile_store *store); + +/* + * Open the packfile and add it to the store if it isn't yet known. Returns + * either the newly opened packfile or the preexisting packfile. Returns a + * `NULL` pointer in case the packfile could not be opened. + */ +struct packed_git *packfile_store_load_pack(struct packfile_store *store, + const char *idx_path, int local); struct pack_window { struct pack_window *next; @@ -142,14 +237,6 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, #define PACKDIR_FILE_GARBAGE 4 extern void (*report_garbage)(unsigned seen_bits, const char *path); -void reprepare_packed_git(struct repository *r); -void install_packed_git(struct repository *r, struct packed_git *pack); - -struct packed_git *get_packed_git(struct repository *r); -struct list_head *get_packed_git_mru(struct repository *r); -struct multi_pack_index *get_multi_pack_index(struct odb_source *source); -struct packed_git *get_all_packs(struct repository *r); - /* * Give a rough count of objects in the repository. This sacrifices accuracy * for speed. diff --git a/parse-options.c b/parse-options.c index 992ec9631f..5933468c19 100644 --- a/parse-options.c +++ b/parse-options.c @@ -133,7 +133,6 @@ static enum parse_opt_result do_get_value(struct parse_opt_ctx_t *p, { const char *arg; const int unset = flags & OPT_UNSET; - int err; if (unset && p->opt) return error(_("%s takes no value"), optname(opt, flags)); @@ -209,21 +208,31 @@ static enum parse_opt_result do_get_value(struct parse_opt_ctx_t *p, case OPTION_FILENAME: { const char *value; - - FREE_AND_NULL(*(char **)opt->value); - - err = 0; + int is_optional; if (unset) value = NULL; else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) - value = (const char *) opt->defval; - else - err = get_arg(p, opt, flags, &value); + value = (char *)opt->defval; + else { + int err = get_arg(p, opt, flags, &value); + if (err) + return err; + } + if (!value) + return 0; - if (!err) - *(char **)opt->value = fix_filename(p->prefix, value); - return err; + is_optional = skip_prefix(value, ":(optional)", &value); + if (!value) + is_optional = 0; + value = fix_filename(p->prefix, value); + if (is_optional && is_empty_or_missing_file(value)) { + free((char *)value); + } else { + FREE_AND_NULL(*(char **)opt->value); + *(const char **)opt->value = value; + } + return 0; } case OPTION_CALLBACK: { diff --git a/range-diff.c b/range-diff.c index ca449a0769..57edff40a8 100644 --- a/range-diff.c +++ b/range-diff.c @@ -39,7 +39,7 @@ struct patch_util { * as struct object_id (will need to be free()d). */ static int read_patches(const char *range, struct string_list *list, - const struct strvec *other_arg, + const struct strvec *log_arg, unsigned int include_merges) { struct child_process cp = CHILD_PROCESS_INIT; @@ -69,8 +69,8 @@ static int read_patches(const char *range, struct string_list *list, if (!include_merges) strvec_push(&cp.args, "--no-merges"); strvec_push(&cp.args, range); - if (other_arg) - strvec_pushv(&cp.args, other_arg->v); + if (log_arg) + strvec_pushv(&cp.args, log_arg->v); cp.out = -1; cp.no_stdin = 1; cp.git_cmd = 1; @@ -594,9 +594,9 @@ int show_range_diff(const char *range1, const char *range2, if (range_diff_opts->left_only && range_diff_opts->right_only) res = error(_("options '%s' and '%s' cannot be used together"), "--left-only", "--right-only"); - if (!res && read_patches(range1, &branch1, range_diff_opts->other_arg, include_merges)) + if (!res && read_patches(range1, &branch1, range_diff_opts->log_arg, include_merges)) res = error(_("could not parse log for '%s'"), range1); - if (!res && read_patches(range2, &branch2, range_diff_opts->other_arg, include_merges)) + if (!res && read_patches(range2, &branch2, range_diff_opts->log_arg, include_merges)) res = error(_("could not parse log for '%s'"), range2); if (!res) { diff --git a/range-diff.h b/range-diff.h index 9d39818e34..9b70a80009 100644 --- a/range-diff.h +++ b/range-diff.h @@ -23,7 +23,7 @@ struct range_diff_options { unsigned include_merges:1; size_t max_memory; const struct diff_options *diffopt; /* may be NULL */ - const struct strvec *other_arg; /* may be NULL */ + const struct strvec *log_arg; /* may be NULL */ }; /* diff --git a/read-cache.c b/read-cache.c index 94098a3861..032480d0c7 100644 --- a/read-cache.c +++ b/read-cache.c @@ -1806,7 +1806,7 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool, if (expand_name_field) { const unsigned char *cp = (const unsigned char *)name; - size_t strip_len, previous_len; + uint64_t strip_len, previous_len; /* If we're at the beginning of a block, ignore the previous name */ strip_len = decode_varint(&cp); @@ -2654,8 +2654,10 @@ static int ce_write_entry(struct hashfile *f, struct cache_entry *ce, hashwrite(f, ce->name, len); hashwrite(f, padding, align_padding_size(size, len)); } else { - int common, to_remove, prefix_size; + int common, to_remove; + uint8_t prefix_size; unsigned char to_remove_vi[16]; + for (common = 0; (common < previous_name->len && ce->name[common] && @@ -3,7 +3,6 @@ */ #define USE_THE_REPOSITORY_VARIABLE -#define DISABLE_SIGN_COMPARE_WARNINGS #include "git-compat-util.h" #include "advice.h" @@ -32,6 +31,7 @@ #include "commit.h" #include "wildmatch.h" #include "ident.h" +#include "fsck.h" /* * List of all available backends @@ -323,6 +323,9 @@ int check_refname_format(const char *refname, int flags) int refs_fsck(struct ref_store *refs, struct fsck_options *o, struct worktree *wt) { + if (o->verbose) + fprintf_ln(stderr, _("Checking references consistency")); + return refs->be->fsck(refs, o, wt); } @@ -1710,8 +1713,6 @@ const char *find_descendant_ref(const char *dirname, const struct string_list *extras, const struct string_list *skip) { - int pos; - if (!extras) return NULL; @@ -1721,7 +1722,7 @@ const char *find_descendant_ref(const char *dirname, * with dirname (remember, dirname includes the trailing * slash) and is not in skip, then we have a conflict. */ - for (pos = string_list_find_insert_index(extras, dirname, 0); + for (size_t pos = string_list_find_insert_index(extras, dirname, NULL); pos < extras->nr; pos++) { const char *extra_refname = extras->items[pos].string; @@ -2410,7 +2411,7 @@ static int run_transaction_hook(struct ref_transaction *transaction, struct child_process proc = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; const char *hook; - int ret = 0, i; + int ret = 0; hook = find_hook(transaction->ref_store->repo, "reference-transaction"); if (!hook) @@ -2427,7 +2428,7 @@ static int run_transaction_hook(struct ref_transaction *transaction, sigchain_push(SIGPIPE, SIG_IGN); - for (i = 0; i < transaction->nr; i++) { + for (size_t i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; if (update->flags & REF_LOG_ONLY) @@ -2820,9 +2821,7 @@ void ref_transaction_for_each_queued_update(struct ref_transaction *transaction, ref_transaction_for_each_queued_update_fn cb, void *cb_data) { - int i; - - for (i = 0; i < transaction->nr; i++) { + for (size_t i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; cb(update->refname, diff --git a/refs/debug.c b/refs/debug.c index 1cb955961e..697adbd0dc 100644 --- a/refs/debug.c +++ b/refs/debug.c @@ -1,7 +1,6 @@ #include "git-compat-util.h" #include "hex.h" #include "refs-internal.h" -#include "string-list.h" #include "trace.h" static struct trace_key trace_refs = TRACE_KEY_INIT(REFS); diff --git a/refs/files-backend.c b/refs/files-backend.c index bb2bec3807..8d7007f4aa 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -20,7 +20,6 @@ #include "../dir-iterator.h" #include "../lockfile.h" #include "../object.h" -#include "../object-file.h" #include "../path.h" #include "../dir.h" #include "../chdir-notify.h" @@ -3328,7 +3327,13 @@ static int files_transaction_finish(struct ref_store *ref_store, * next update. If not, we try and create a regular symref. */ if (update->new_target && refs->prefer_symlink_refs) - if (!create_ref_symlink(lock, update->new_target)) + /* + * By using the `NOT_CONSTANT()` trick, we can avoid + * errors by `clang`'s `-Wunreachable` logic that would + * report that the `continue` statement is not reachable + * when `NO_SYMLINK_HEAD` is `#define`d. + */ + if (NOT_CONSTANT(!create_ref_symlink(lock, update->new_target))) continue; if (update->flags & REF_NEEDS_COMMIT) { @@ -3970,8 +3975,6 @@ static int files_fsck_refs(struct ref_store *ref_store, NULL, }; - if (o->verbose) - fprintf_ln(stderr, _("Checking references consistency")); return files_fsck_refs_dir(ref_store, o, "refs", wt, fsck_refs_fn); } diff --git a/refs/ref-cache.c b/refs/ref-cache.c index c180e0aad7..e5e5df16d8 100644 --- a/refs/ref-cache.c +++ b/refs/ref-cache.c @@ -539,7 +539,7 @@ static int cache_ref_iterator_seek(struct ref_iterator *ref_iterator, */ break; } - } while (slash); + } while (slash && dir->nr); } return 0; diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 9884b876c1..d4b7928620 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -6,20 +6,21 @@ #include "../config.h" #include "../dir.h" #include "../environment.h" +#include "../fsck.h" #include "../gettext.h" #include "../hash.h" #include "../hex.h" #include "../iterator.h" #include "../ident.h" -#include "../lockfile.h" #include "../object.h" #include "../path.h" #include "../refs.h" #include "../reftable/reftable-basics.h" -#include "../reftable/reftable-stack.h" -#include "../reftable/reftable-record.h" #include "../reftable/reftable-error.h" +#include "../reftable/reftable-fsck.h" #include "../reftable/reftable-iterator.h" +#include "../reftable/reftable-record.h" +#include "../reftable/reftable-stack.h" #include "../repo-settings.h" #include "../setup.h" #include "../strmap.h" @@ -2714,11 +2715,56 @@ done: return ret; } -static int reftable_be_fsck(struct ref_store *ref_store UNUSED, - struct fsck_options *o UNUSED, +static void reftable_fsck_verbose_handler(const char *msg, void *cb_data) +{ + struct fsck_options *o = cb_data; + + if (o->verbose) + fprintf_ln(stderr, "%s", msg); +} + +static const enum fsck_msg_id fsck_msg_id_map[] = { + [REFTABLE_FSCK_ERROR_TABLE_NAME] = FSCK_MSG_BAD_REFTABLE_TABLE_NAME, +}; + +static int reftable_fsck_error_handler(struct reftable_fsck_info *info, + void *cb_data) +{ + struct fsck_ref_report report = { .path = info->path }; + struct fsck_options *o = cb_data; + enum fsck_msg_id msg_id; + + if (info->error < 0 || info->error >= REFTABLE_FSCK_MAX_VALUE) + BUG("unknown fsck error: %d", (int)info->error); + + msg_id = fsck_msg_id_map[info->error]; + + if (!msg_id) + BUG("fsck_msg_id value missing for reftable error: %d", (int)info->error); + + return fsck_report_ref(o, &report, msg_id, "%s", info->msg); +} + +static int reftable_be_fsck(struct ref_store *ref_store, struct fsck_options *o, struct worktree *wt UNUSED) { - return 0; + struct reftable_ref_store *refs; + struct strmap_entry *entry; + struct hashmap_iter iter; + int ret = 0; + + refs = reftable_be_downcast(ref_store, REF_STORE_READ, "fsck"); + + ret |= reftable_fsck_check(refs->main_backend.stack, reftable_fsck_error_handler, + reftable_fsck_verbose_handler, o); + + strmap_for_each_entry(&refs->worktree_backends, &iter, entry) { + struct reftable_backend *b = (struct reftable_backend *)entry->value; + ret |= reftable_fsck_check(b->stack, reftable_fsck_error_handler, + reftable_fsck_verbose_handler, o); + } + + return ret; } struct ref_storage_be refs_be_reftable = { diff --git a/reftable/basics.c b/reftable/basics.c index 9988ebd635..e969927b61 100644 --- a/reftable/basics.c +++ b/reftable/basics.c @@ -195,44 +195,55 @@ size_t names_length(const char **names) return p - names; } -char **parse_names(char *buf, int size) +int parse_names(char *buf, int size, char ***out) { char **names = NULL; size_t names_cap = 0; size_t names_len = 0; char *p = buf; char *end = buf + size; + int err = 0; while (p < end) { char *next = strchr(p, '\n'); - if (next && next < end) { - *next = 0; + if (!next) { + err = REFTABLE_FORMAT_ERROR; + goto done; + } else if (next < end) { + *next = '\0'; } else { next = end; } + if (p < next) { if (REFTABLE_ALLOC_GROW(names, names_len + 1, - names_cap)) - goto err; + names_cap)) { + err = REFTABLE_OUT_OF_MEMORY_ERROR; + goto done; + } names[names_len] = reftable_strdup(p); - if (!names[names_len++]) - goto err; + if (!names[names_len++]) { + err = REFTABLE_OUT_OF_MEMORY_ERROR; + goto done; + } } p = next + 1; } - if (REFTABLE_ALLOC_GROW(names, names_len + 1, names_cap)) - goto err; + if (REFTABLE_ALLOC_GROW(names, names_len + 1, names_cap)) { + err = REFTABLE_OUT_OF_MEMORY_ERROR; + goto done; + } names[names_len] = NULL; - return names; - -err: + *out = names; + return 0; +done: for (size_t i = 0; i < names_len; i++) reftable_free(names[i]); reftable_free(names); - return NULL; + return err; } int names_equal(const char **a, const char **b) diff --git a/reftable/basics.h b/reftable/basics.h index 7d22f96261..e4b83b2b03 100644 --- a/reftable/basics.h +++ b/reftable/basics.h @@ -167,10 +167,11 @@ void free_names(char **a); /* * Parse a newline separated list of names. `size` is the length of the buffer, - * without terminating '\0'. Empty names are discarded. Returns a `NULL` - * pointer when allocations fail. + * without terminating '\0'. Empty names are discarded. + * + * Returns 0 on success, a reftable error code on error. */ -char **parse_names(char *buf, int size); +int parse_names(char *buf, int size, char ***out); /* compares two NULL-terminated arrays of strings. */ int names_equal(const char **a, const char **b); diff --git a/reftable/fsck.c b/reftable/fsck.c new file mode 100644 index 0000000000..26b9115b14 --- /dev/null +++ b/reftable/fsck.c @@ -0,0 +1,100 @@ +#include "basics.h" +#include "reftable-fsck.h" +#include "reftable-table.h" +#include "stack.h" + +static bool table_has_valid_name(const char *name) +{ + const char *ptr = name; + char *endptr; + + /* strtoull doesn't set errno on success */ + errno = 0; + + strtoull(ptr, &endptr, 16); + if (errno) + return false; + ptr = endptr; + + if (*ptr != '-') + return false; + ptr++; + + strtoull(ptr, &endptr, 16); + if (errno) + return false; + ptr = endptr; + + if (*ptr != '-') + return false; + ptr++; + + strtoul(ptr, &endptr, 16); + if (errno) + return false; + ptr = endptr; + + if (strcmp(ptr, ".ref") && strcmp(ptr, ".log")) + return false; + + return true; +} + +typedef int (*table_check_fn)(struct reftable_table *table, + reftable_fsck_report_fn report_fn, + void *cb_data); + +static int table_check_name(struct reftable_table *table, + reftable_fsck_report_fn report_fn, + void *cb_data) +{ + if (!table_has_valid_name(table->name)) { + struct reftable_fsck_info info; + + info.error = REFTABLE_FSCK_ERROR_TABLE_NAME; + info.msg = "invalid reftable table name"; + info.path = table->name; + + return report_fn(&info, cb_data); + } + + return 0; +} + +static int table_checks(struct reftable_table *table, + reftable_fsck_report_fn report_fn, + reftable_fsck_verbose_fn verbose_fn UNUSED, + void *cb_data) +{ + table_check_fn table_check_fns[] = { + table_check_name, + NULL, + }; + int err = 0; + + for (size_t i = 0; table_check_fns[i]; i++) + err |= table_check_fns[i](table, report_fn, cb_data); + + return err; +} + +int reftable_fsck_check(struct reftable_stack *stack, + reftable_fsck_report_fn report_fn, + reftable_fsck_verbose_fn verbose_fn, + void *cb_data) +{ + struct reftable_buf msg = REFTABLE_BUF_INIT; + int err = 0; + + for (size_t i = 0; i < stack->tables_len; i++) { + reftable_buf_reset(&msg); + reftable_buf_addstr(&msg, "Checking table: "); + reftable_buf_addstr(&msg, stack->tables[i]->name); + verbose_fn(msg.buf, cb_data); + + err |= table_checks(stack->tables[i], report_fn, verbose_fn, cb_data); + } + + reftable_buf_release(&msg); + return err; +} diff --git a/reftable/reftable-fsck.h b/reftable/reftable-fsck.h new file mode 100644 index 0000000000..007a392cf9 --- /dev/null +++ b/reftable/reftable-fsck.h @@ -0,0 +1,40 @@ +#ifndef REFTABLE_FSCK_H +#define REFTABLE_FSCK_H + +#include "reftable-stack.h" + +enum reftable_fsck_error { + /* Invalid table name */ + REFTABLE_FSCK_ERROR_TABLE_NAME = 0, + /* Used for bounds checking, must be last */ + REFTABLE_FSCK_MAX_VALUE, +}; + +/* Represents an individual error encountered during the FSCK checks. */ +struct reftable_fsck_info { + enum reftable_fsck_error error; + const char *msg; + const char *path; +}; + +typedef int reftable_fsck_report_fn(struct reftable_fsck_info *info, + void *cb_data); +typedef void reftable_fsck_verbose_fn(const char *msg, void *cb_data); + +/* + * Given a reftable stack, perform consistency checks on the stack. + * + * If an issue is encountered, the issue is reported to the callee via the + * provided 'report_fn'. If the issue is non-recoverable the flow will not + * continue. If it is recoverable, the flow will continue and further issues + * will be reported as identified. + * + * The 'verbose_fn' will be invoked to provide verbose information about + * the progress and state of the consistency checks. + */ +int reftable_fsck_check(struct reftable_stack *stack, + reftable_fsck_report_fn report_fn, + reftable_fsck_verbose_fn verbose_fn, + void *cb_data); + +#endif /* REFTABLE_FSCK_H */ diff --git a/reftable/stack.c b/reftable/stack.c index f91ce50bcd..65d89820bd 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -109,12 +109,7 @@ static int fd_read_lines(int fd, char ***namesp) } buf[size] = 0; - *namesp = parse_names(buf, size); - if (!*namesp) { - err = REFTABLE_OUT_OF_MEMORY_ERROR; - goto done; - } - + err = parse_names(buf, size, namesp); done: reftable_free(buf); return err; diff --git a/remote-curl.c b/remote-curl.c index 84f4694780..69f919454a 100644 --- a/remote-curl.c +++ b/remote-curl.c @@ -894,14 +894,6 @@ static int probe_rpc(struct rpc_state *rpc, struct slot_results *results) return err; } -static curl_off_t xcurl_off_t(size_t len) -{ - uintmax_t size = len; - if (size > maximum_signed_value_of_type(curl_off_t)) - die(_("cannot handle pushes this big")); - return (curl_off_t)size; -} - /* * If flush_received is true, do not attempt to read any more; just use what's * in rpc->buf. @@ -999,7 +991,7 @@ retry: * and we just need to send it. */ curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, gzip_body); - curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, xcurl_off_t(gzip_size)); + curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, cast_size_t_to_curl_off_t(gzip_size)); } else if (use_gzip && 1024 < rpc->len) { /* The client backend isn't giving us compressed data so @@ -1030,7 +1022,7 @@ retry: headers = curl_slist_append(headers, "Content-Encoding: gzip"); curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, gzip_body); - curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, xcurl_off_t(gzip_size)); + curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, cast_size_t_to_curl_off_t(gzip_size)); if (options.verbosity > 1) { fprintf(stderr, "POST %s (gzip %lu to %lu bytes)\n", @@ -1043,7 +1035,7 @@ retry: * more normal Content-Length approach. */ curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, rpc->buf); - curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, xcurl_off_t(rpc->len)); + curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDSIZE_LARGE, cast_size_t_to_curl_off_t(rpc->len)); if (options.verbosity > 1) { fprintf(stderr, "POST %s (%lu bytes)\n", rpc->service_name, (unsigned long)rpc->len); diff --git a/revision.c b/revision.c index 806a1c4c24..cf5e6c1ec9 100644 --- a/revision.c +++ b/revision.c @@ -774,9 +774,6 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs, struct bloom_filter *filter; int result = 0; - if (!revs->repo->objects->commit_graph) - return -1; - if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY) return -1; diff --git a/revision.h b/revision.h index a28e349044..b36acfc2d9 100644 --- a/revision.h +++ b/revision.h @@ -334,6 +334,7 @@ struct rev_info { /* range-diff */ const char *rdiff1; const char *rdiff2; + struct strvec rdiff_log_arg; int creation_factor; const char *rdiff_title; @@ -410,6 +411,7 @@ struct rev_info { .expand_tabs_in_log = -1, \ .commit_format = CMIT_FMT_DEFAULT, \ .expand_tabs_in_log_default = 8, \ + .rdiff_log_arg = STRVEC_INIT, \ } /** diff --git a/server-info.c b/server-info.c index 9bb30d9ab7..1d33de821e 100644 --- a/server-info.c +++ b/server-info.c @@ -287,12 +287,13 @@ static int compare_info(const void *a_, const void *b_) static void init_pack_info(struct repository *r, const char *infofile, int force) { + struct packfile_store *packs = r->objects->packfiles; struct packed_git *p; int stale; int i; size_t alloc = 0; - for (p = get_all_packs(r); p; p = p->next) { + for (p = packfile_store_get_all_packs(packs); p; p = p->next) { /* we ignore things on alternate path since they are * not available to the pullers in general. */ diff --git a/shared.mak b/shared.mak index 5c7bc94785..0e7492076e 100644 --- a/shared.mak +++ b/shared.mak @@ -56,6 +56,7 @@ ifndef V QUIET_MKDIR_P_PARENT = @echo ' ' MKDIR -p $(@D); ## Used in "Makefile" + QUIET_CARGO = @echo ' ' CARGO $@; QUIET_CC = @echo ' ' CC $@; QUIET_AR = @echo ' ' AR $@; QUIET_LINK = @echo ' ' LINK $@; diff --git a/src/cargo-meson.sh b/src/cargo-meson.sh new file mode 100755 index 0000000000..99400986d9 --- /dev/null +++ b/src/cargo-meson.sh @@ -0,0 +1,32 @@ +#!/bin/sh + +if test "$#" -lt 2 +then + exit 1 +fi + +SOURCE_DIR="$1" +BUILD_DIR="$2" +BUILD_TYPE=debug + +shift 2 + +for arg +do + case "$arg" in + --release) + BUILD_TYPE=release;; + esac +done + +cargo build --lib --quiet --manifest-path="$SOURCE_DIR/Cargo.toml" --target-dir="$BUILD_DIR" "$@" +RET=$? +if test $RET -ne 0 +then + exit $RET +fi + +if ! cmp "$BUILD_DIR/$BUILD_TYPE/libgitcore.a" "$BUILD_DIR/libgitcore.a" >/dev/null 2>&1 +then + cp "$BUILD_DIR/$BUILD_TYPE/libgitcore.a" "$BUILD_DIR/libgitcore.a" +fi diff --git a/src/lib.rs b/src/lib.rs new file mode 100644 index 0000000000..9da70d8b57 --- /dev/null +++ b/src/lib.rs @@ -0,0 +1 @@ +pub mod varint; diff --git a/src/meson.build b/src/meson.build new file mode 100644 index 0000000000..25b9ad5a14 --- /dev/null +++ b/src/meson.build @@ -0,0 +1,41 @@ +libgit_rs_sources = [ + 'lib.rs', + 'varint.rs', +] + +# Unfortunately we must use a wrapper command to move the output file into the +# current build directory. This can fixed once `cargo build --artifact-dir` +# stabilizes. See https://github.com/rust-lang/cargo/issues/6790 for that +# effort. +cargo_command = [ + shell, + meson.current_source_dir() / 'cargo-meson.sh', + meson.project_source_root(), + meson.current_build_dir(), +] +if get_option('buildtype') == 'release' + cargo_command += '--release' +endif + +libgit_rs = custom_target('git_rs', + input: libgit_rs_sources + [ + meson.project_source_root() / 'Cargo.toml', + ], + output: 'libgitcore.a', + command: cargo_command, +) +libgit_dependencies += declare_dependency(link_with: libgit_rs) + +if get_option('tests') + test('rust', cargo, + args: [ + 'test', + '--manifest-path', + meson.project_source_root() / 'Cargo.toml', + '--target-dir', + meson.current_build_dir() / 'target', + ], + timeout: 0, + protocol: 'rust', + ) +endif diff --git a/src/varint.rs b/src/varint.rs new file mode 100644 index 0000000000..6e610bdd8e --- /dev/null +++ b/src/varint.rs @@ -0,0 +1,92 @@ +#[no_mangle] +pub unsafe extern "C" fn decode_varint(bufp: *mut *const u8) -> u64 { + let mut buf = *bufp; + let mut c = *buf; + let mut val = u64::from(c & 127); + + buf = buf.add(1); + + while (c & 128) != 0 { + val = val.wrapping_add(1); + if val == 0 || val.leading_zeros() < 7 { + return 0; // overflow + } + + c = *buf; + buf = buf.add(1); + + val = (val << 7) + u64::from(c & 127); + } + + *bufp = buf; + val +} + +#[no_mangle] +pub unsafe extern "C" fn encode_varint(value: u64, buf: *mut u8) -> u8 { + let mut varint: [u8; 16] = [0; 16]; + let mut pos = varint.len() - 1; + + varint[pos] = (value & 127) as u8; + + let mut value = value >> 7; + while value != 0 { + pos -= 1; + value -= 1; + varint[pos] = 128 | (value & 127) as u8; + value >>= 7; + } + + if !buf.is_null() { + std::ptr::copy_nonoverlapping(varint.as_ptr().add(pos), buf, varint.len() - pos); + } + + (varint.len() - pos) as u8 +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn test_decode_varint() { + unsafe { + assert_eq!(decode_varint(&mut [0x00].as_slice().as_ptr()), 0); + assert_eq!(decode_varint(&mut [0x01].as_slice().as_ptr()), 1); + assert_eq!(decode_varint(&mut [0x7f].as_slice().as_ptr()), 127); + assert_eq!(decode_varint(&mut [0x80, 0x00].as_slice().as_ptr()), 128); + assert_eq!(decode_varint(&mut [0x80, 0x01].as_slice().as_ptr()), 129); + assert_eq!(decode_varint(&mut [0x80, 0x7f].as_slice().as_ptr()), 255); + + // Overflows are expected to return 0. + assert_eq!(decode_varint(&mut [0x88; 16].as_slice().as_ptr()), 0); + } + } + + #[test] + fn test_encode_varint() { + unsafe { + let mut varint: [u8; 16] = [0; 16]; + + assert_eq!(encode_varint(0, std::ptr::null_mut()), 1); + + assert_eq!(encode_varint(0, varint.as_mut_slice().as_mut_ptr()), 1); + assert_eq!(varint, [0; 16]); + + assert_eq!(encode_varint(10, varint.as_mut_slice().as_mut_ptr()), 1); + assert_eq!(varint, [10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + + assert_eq!(encode_varint(127, varint.as_mut_slice().as_mut_ptr()), 1); + assert_eq!(varint, [127, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + + assert_eq!(encode_varint(128, varint.as_mut_slice().as_mut_ptr()), 2); + assert_eq!(varint, [128, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + + assert_eq!(encode_varint(129, varint.as_mut_slice().as_mut_ptr()), 2); + assert_eq!(varint, [128, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + + assert_eq!(encode_varint(255, varint.as_mut_slice().as_mut_ptr()), 2); + assert_eq!(varint, [128, 127, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + } + } +} diff --git a/string-list.c b/string-list.c index 343cf1ca90..08dc00984c 100644 --- a/string-list.c +++ b/string-list.c @@ -16,7 +16,7 @@ void string_list_init_dup(struct string_list *list) /* if there is no exact match, point to the index where the entry could be * inserted */ static size_t get_entry_index(const struct string_list *list, const char *string, - int *exact_match) + bool *exact_match) { size_t left = 0, right = list->nr; compare_strings_fn cmp = list->cmp ? list->cmp : strcmp; @@ -29,18 +29,20 @@ static size_t get_entry_index(const struct string_list *list, const char *string else if (compare > 0) left = middle + 1; else { - *exact_match = 1; + if (exact_match) + *exact_match = true; return middle; } } - *exact_match = 0; + if (exact_match) + *exact_match = false; return right; } static size_t add_entry(struct string_list *list, const char *string) { - int exact_match = 0; + bool exact_match; size_t index = get_entry_index(list, string, &exact_match); if (exact_match) @@ -68,7 +70,7 @@ struct string_list_item *string_list_insert(struct string_list *list, const char void string_list_remove(struct string_list *list, const char *string, int free_util) { - int exact_match; + bool exact_match; int i = get_entry_index(list, string, &exact_match); if (exact_match) { @@ -82,26 +84,23 @@ void string_list_remove(struct string_list *list, const char *string, } } -int string_list_has_string(const struct string_list *list, const char *string) +bool string_list_has_string(const struct string_list *list, const char *string) { - int exact_match; + bool exact_match; get_entry_index(list, string, &exact_match); return exact_match; } -int string_list_find_insert_index(const struct string_list *list, const char *string, - int negative_existing_index) +size_t string_list_find_insert_index(const struct string_list *list, const char *string, + bool *exact_match) { - int exact_match; - int index = get_entry_index(list, string, &exact_match); - if (exact_match) - index = -1 - (negative_existing_index ? index : 0); - return index; + return get_entry_index(list, string, exact_match); } struct string_list_item *string_list_lookup(struct string_list *list, const char *string) { - int exact_match, i = get_entry_index(list, string, &exact_match); + bool exact_match; + size_t i = get_entry_index(list, string, &exact_match); if (!exact_match) return NULL; return list->items + i; diff --git a/string-list.h b/string-list.h index 2b438c7733..fa6ba07853 100644 --- a/string-list.h +++ b/string-list.h @@ -172,9 +172,15 @@ void string_list_remove_empty_items(struct string_list *list, int free_util); /* Use these functions only on sorted lists: */ /** Determine if the string_list has a given string or not. */ -int string_list_has_string(const struct string_list *list, const char *string); -int string_list_find_insert_index(const struct string_list *list, const char *string, - int negative_existing_index); +bool string_list_has_string(const struct string_list *list, const char *string); + +/** + * Find the index at which a new element should be inserted into the + * string_list to maintain sorted order. If exact_match is not NULL, + * it will be set to true if the string already exists in the list. + */ +size_t string_list_find_insert_index(const struct string_list *list, const char *string, + bool *exact_match); /** * Insert a new element to the string_list. The returned pointer can diff --git a/t/helper/test-find-pack.c b/t/helper/test-find-pack.c index 611a13a326..e001dc3066 100644 --- a/t/helper/test-find-pack.c +++ b/t/helper/test-find-pack.c @@ -39,7 +39,7 @@ int cmd__find_pack(int argc, const char **argv) if (repo_get_oid(the_repository, argv[0], &oid)) die("cannot parse %s as an object name", argv[0]); - for (p = get_all_packs(the_repository); p; p = p->next) + for (p = packfile_store_get_all_packs(the_repository->objects->packfiles); p; p = p->next) if (find_pack_entry_one(&oid, p)) { printf("%s\n", p->pack_name); actual_count++; diff --git a/t/helper/test-pack-deltas.c b/t/helper/test-pack-deltas.c index 4caa024b1e..4981401eaa 100644 --- a/t/helper/test-pack-deltas.c +++ b/t/helper/test-pack-deltas.c @@ -51,16 +51,14 @@ static void write_ref_delta(struct hashfile *f, unsigned long size, base_size, delta_size, compressed_size, hdrlen; enum object_type type; void *base_buf, *delta_buf; - void *buf = repo_read_object_file(the_repository, - oid, &type, - &size); + void *buf = odb_read_object(the_repository->objects, + oid, &type, &size); if (!buf) die("unable to read %s", oid_to_hex(oid)); - base_buf = repo_read_object_file(the_repository, - base, &type, - &base_size); + base_buf = odb_read_object(the_repository->objects, + base, &type, &base_size); if (!base_buf) die("unable to read %s", oid_to_hex(base)); diff --git a/t/helper/test-pack-mtimes.c b/t/helper/test-pack-mtimes.c index d51aaa3dc4..7c428c1601 100644 --- a/t/helper/test-pack-mtimes.c +++ b/t/helper/test-pack-mtimes.c @@ -37,7 +37,7 @@ int cmd__pack_mtimes(int argc, const char **argv) if (argc != 2) usage(pack_mtimes_usage); - for (p = get_all_packs(the_repository); p; p = p->next) { + for (p = packfile_store_get_all_packs(the_repository->objects->packfiles); p; p = p->next) { strbuf_addstr(&buf, basename(p->pack_name)); strbuf_strip_suffix(&buf, ".pack"); strbuf_addstr(&buf, ".mtimes"); diff --git a/t/meson.build b/t/meson.build index 11376b9e25..401b24e50e 100644 --- a/t/meson.build +++ b/t/meson.build @@ -146,6 +146,7 @@ integration_tests = [ 't0611-reftable-httpd.sh', 't0612-reftable-jgit-compatibility.sh', 't0613-reftable-write-options.sh', + 't0614-reftable-fsck.sh', 't1000-read-tree-m-3way.sh', 't1001-read-tree-m-2way.sh', 't1002-read-tree-m-u-2way.sh', diff --git a/t/t0300-credentials.sh b/t/t0300-credentials.sh index cb3a85c7ff..07aa834d33 100755 --- a/t/t0300-credentials.sh +++ b/t/t0300-credentials.sh @@ -991,18 +991,24 @@ test_expect_success 'url parser not confused by encoded markers' ' test_expect_success 'credential config with partial URLs' ' echo "echo password=yep" | write_script git-credential-yep && - test_write_lines url=https://user@example.com/repo.git >stdin && + test_write_lines url=https://user@example.com/org/repo.git >stdin && for partial in \ example.com \ + example.com/org/repo.git \ user@example.com \ + user@example.com/org/repo.git \ https:// \ https://example.com \ https://example.com/ \ + https://example.com/org \ + https://example.com/org/ \ + https://example.com/org/repo.git \ https://user@example.com \ https://user@example.com/ \ - https://example.com/repo.git \ - https://user@example.com/repo.git \ - /repo.git + https://user@example.com/org \ + https://user@example.com/org/ \ + https://user@example.com/org/repo.git \ + /org/repo.git do git -c credential.$partial.helper=yep \ credential fill <stdin >stdout && @@ -1012,7 +1018,12 @@ test_expect_success 'credential config with partial URLs' ' for partial in \ dont.use.this \ + example.com/o \ + user@example.com/o \ http:// \ + https://example.com/o \ + https://user@example.com/o \ + /o \ /repo do git -c credential.$partial.helper=yep \ diff --git a/t/t0614-reftable-fsck.sh b/t/t0614-reftable-fsck.sh new file mode 100755 index 0000000000..85cc47d67e --- /dev/null +++ b/t/t0614-reftable-fsck.sh @@ -0,0 +1,58 @@ +#!/bin/sh + +test_description='Test reftable backend consistency check' + +GIT_TEST_DEFAULT_REF_FORMAT=reftable +export GIT_TEST_DEFAULT_REF_FORMAT + +. ./test-lib.sh + +test_expect_success "no errors reported on a well formed repository" ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + git commit --allow-empty -m initial && + + for i in $(test_seq 20) + do + git update-ref refs/heads/branch-$i HEAD || return 1 + done && + + # The repository should end up with multiple tables. + test_line_count ">" 1 .git/reftable/tables.list && + + git refs verify 2>err && + test_must_be_empty err + ) +' + +for TABLE_NAME in "foo-bar-e4d12d59.ref" \ + "0x00000000zzzz-0x00000000zzzz-e4d12d59.ref" \ + "0x000000000001-0x000000000002-e4d12d59.abc" \ + "0x000000000001-0x000000000002-e4d12d59.refabc"; do + test_expect_success "table name $TABLE_NAME should be checked" ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + git commit --allow-empty -m initial && + + git refs verify 2>err && + test_must_be_empty err && + + EXISTING_TABLE=$(head -n1 .git/reftable/tables.list) && + mv ".git/reftable/$EXISTING_TABLE" ".git/reftable/$TABLE_NAME" && + sed "s/${EXISTING_TABLE}/${TABLE_NAME}/g" .git/reftable/tables.list > tables.list && + mv tables.list .git/reftable/tables.list && + + git refs verify 2>err && + cat >expect <<-EOF && + warning: ${TABLE_NAME}: badReftableTableName: invalid reftable table name + EOF + test_cmp expect err + ) + ' +done + +test_done diff --git a/t/t1010-mktree.sh b/t/t1010-mktree.sh index e9973f7494..312fe6717a 100755 --- a/t/t1010-mktree.sh +++ b/t/t1010-mktree.sh @@ -11,10 +11,13 @@ test_expect_success setup ' git add "$d" || return 1 done && echo zero >one && - git update-index --add --info-only one && - git write-tree --missing-ok >tree.missing && - git ls-tree $(cat tree.missing) >top.missing && - git ls-tree -r $(cat tree.missing) >all.missing && + if test_have_prereq BROKEN_OBJECTS + then + git update-index --add --info-only one && + git write-tree --missing-ok >tree.missing && + git ls-tree $(cat tree.missing) >top.missing && + git ls-tree -r $(cat tree.missing) >all.missing + fi && echo one >one && git add one && git write-tree >tree && @@ -53,7 +56,7 @@ test_expect_success 'ls-tree output in wrong order given to mktree (2)' ' test_cmp tree.withsub actual ' -test_expect_success 'allow missing object with --missing' ' +test_expect_success BROKEN_OBJECTS 'allow missing object with --missing' ' git mktree --missing <top.missing >actual && test_cmp tree.missing actual ' diff --git a/t/t1016-compatObjectFormat.sh b/t/t1016-compatObjectFormat.sh index e88362fbe4..a9af8b2396 100755 --- a/t/t1016-compatObjectFormat.sh +++ b/t/t1016-compatObjectFormat.sh @@ -114,7 +114,7 @@ do git config core.repositoryformatversion 1 && git config extensions.objectformat $hash && git config extensions.compatobjectformat $(compat_hash $hash) && - test_config gpg.program $TEST_DIRECTORY/t1016/gpg && + git config gpg.program $TEST_DIRECTORY/t1016/gpg && echo "Hello World!" >hello && eval hello_${hash}_oid=$(git hash-object hello) && git update-index --add hello && diff --git a/t/t1421-reflog-write.sh b/t/t1421-reflog-write.sh index 46df64c176..603ec3f6ed 100755 --- a/t/t1421-reflog-write.sh +++ b/t/t1421-reflog-write.sh @@ -108,6 +108,42 @@ test_expect_success 'simple writes' ' ) ' +test_expect_success 'uses user.name and user.email config' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + COMMIT_OID=$(git rev-parse HEAD) && + + sane_unset GIT_COMMITTER_NAME && + sane_unset GIT_COMMITTER_EMAIL && + git config --local user.name "Author" && + git config --local user.email "a@uth.or" && + git reflog write refs/heads/something $ZERO_OID $COMMIT_OID first && + test_reflog_matches . refs/heads/something <<-EOF + $ZERO_OID $COMMIT_OID Author <a@uth.or> $GIT_COMMITTER_DATE first + EOF + ) +' + +test_expect_success 'environment variables take precedence over config' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + COMMIT_OID=$(git rev-parse HEAD) && + + git config --local user.name "Author" && + git config --local user.email "a@uth.or" && + git reflog write refs/heads/something $ZERO_OID $COMMIT_OID first && + test_reflog_matches . refs/heads/something <<-EOF + $ZERO_OID $COMMIT_OID $SIGNATURE first + EOF + ) +' + test_expect_success 'can write to root ref' ' test_when_finished "rm -rf repo" && git init repo && diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh index 5ae86c42be..c4b651c2dc 100755 --- a/t/t1450-fsck.sh +++ b/t/t1450-fsck.sh @@ -454,6 +454,60 @@ test_expect_success 'tag with NUL in header' ' test_grep "error in tag $tag.*unterminated header: NUL at offset" out ' +test_expect_success 'tag accepts gpgsig header even if not validly signed' ' + test_oid_cache <<-\EOF && + header sha1:gpgsig-sha256 + header sha256:gpgsig + EOF + header=$(test_oid header) && + sha=$(git rev-parse HEAD) && + cat >good-tag <<-EOF && + object $sha + type commit + tag good + tagger T A Gger <tagger@example.com> 1234567890 -0000 + $header -----BEGIN PGP SIGNATURE----- + Not a valid signature + -----END PGP SIGNATURE----- + + This is a good tag. + EOF + + tag=$(git hash-object --literally -t tag -w --stdin <good-tag) && + test_when_finished "remove_object $tag" && + git update-ref refs/tags/good $tag && + test_when_finished "git update-ref -d refs/tags/good" && + git -c fsck.extraHeaderEntry=error fsck --tags +' + +test_expect_success 'tag rejects invalid headers' ' + test_oid_cache <<-\EOF && + header sha1:gpgsig-sha256 + header sha256:gpgsig + EOF + header=$(test_oid header) && + sha=$(git rev-parse HEAD) && + cat >bad-tag <<-EOF && + object $sha + type commit + tag good + tagger T A Gger <tagger@example.com> 1234567890 -0000 + $header -----BEGIN PGP SIGNATURE----- + Not a valid signature + -----END PGP SIGNATURE----- + junk + + This is a bad tag with junk at the end of the headers. + EOF + + tag=$(git hash-object --literally -t tag -w --stdin <bad-tag) && + test_when_finished "remove_object $tag" && + git update-ref refs/tags/bad $tag && + test_when_finished "git update-ref -d refs/tags/bad" && + test_must_fail git -c fsck.extraHeaderEntry=error fsck --tags 2>out && + test_grep "error in tag $tag.*invalid format - extra header" out +' + test_expect_success 'cleaned up' ' git fsck >actual 2>&1 && test_must_be_empty actual diff --git a/t/t1500-rev-parse.sh b/t/t1500-rev-parse.sh index 58a4583088..7739ab611b 100755 --- a/t/t1500-rev-parse.sh +++ b/t/t1500-rev-parse.sh @@ -207,6 +207,40 @@ test_expect_success 'rev-parse --show-object-format in repo' ' grep "unknown mode for --show-object-format: squeamish-ossifrage" err ' + +test_expect_success 'rev-parse --show-object-format in repo with compat mode' ' + mkdir repo && + ( + sane_unset GIT_DEFAULT_HASH && + cd repo && + git init --object-format=sha256 && + git config extensions.compatobjectformat sha1 && + echo sha256 >expect && + git rev-parse --show-object-format >actual && + test_cmp expect actual && + git rev-parse --show-object-format=storage >actual && + test_cmp expect actual && + git rev-parse --show-object-format=input >actual && + test_cmp expect actual && + git rev-parse --show-object-format=output >actual && + test_cmp expect actual && + echo sha1 >expect && + git rev-parse --show-object-format=compat >actual && + test_cmp expect actual && + test_must_fail git rev-parse --show-object-format=squeamish-ossifrage 2>err && + grep "unknown mode for --show-object-format: squeamish-ossifrage" err + ) && + mkdir repo2 && + ( + sane_unset GIT_DEFAULT_HASH && + cd repo2 && + git init --object-format=sha256 && + echo >expect && + git rev-parse --show-object-format=compat >actual && + test_cmp expect actual + ) +' + test_expect_success 'rev-parse --show-ref-format' ' test_detect_ref_format >expect && git rev-parse --show-ref-format >actual && diff --git a/t/t2401-worktree-prune.sh b/t/t2401-worktree-prune.sh index fe671d4197..f8f28c76ee 100755 --- a/t/t2401-worktree-prune.sh +++ b/t/t2401-worktree-prune.sh @@ -24,8 +24,8 @@ test_expect_success 'prune files inside $GIT_DIR/worktrees' ' Removing worktrees/abc: not a valid directory EOF test_cmp expect actual && - ! test -f .git/worktrees/abc && - ! test -d .git/worktrees + test_path_is_missing .git/worktrees/abc && + test_path_is_missing .git/worktrees ' test_expect_success 'prune directories without gitdir' ' @@ -36,8 +36,8 @@ Removing worktrees/def: gitdir file does not exist EOF git worktree prune --verbose 2>actual && test_cmp expect actual && - ! test -d .git/worktrees/def && - ! test -d .git/worktrees + test_path_is_missing .git/worktrees/def && + test_path_is_missing .git/worktrees ' test_expect_success SANITY 'prune directories with unreadable gitdir' ' @@ -47,8 +47,8 @@ test_expect_success SANITY 'prune directories with unreadable gitdir' ' chmod u-r .git/worktrees/def/gitdir && git worktree prune --verbose 2>actual && test_grep "Removing worktrees/def: unable to read gitdir file" actual && - ! test -d .git/worktrees/def && - ! test -d .git/worktrees + test_path_is_missing .git/worktrees/def && + test_path_is_missing .git/worktrees ' test_expect_success 'prune directories with invalid gitdir' ' @@ -57,8 +57,8 @@ test_expect_success 'prune directories with invalid gitdir' ' : >.git/worktrees/def/gitdir && git worktree prune --verbose 2>actual && test_grep "Removing worktrees/def: invalid gitdir file" actual && - ! test -d .git/worktrees/def && - ! test -d .git/worktrees + test_path_is_missing .git/worktrees/def && + test_path_is_missing .git/worktrees ' test_expect_success 'prune directories with gitdir pointing to nowhere' ' @@ -67,8 +67,8 @@ test_expect_success 'prune directories with gitdir pointing to nowhere' ' echo "$(pwd)"/nowhere >.git/worktrees/def/gitdir && git worktree prune --verbose 2>actual && test_grep "Removing worktrees/def: gitdir file points to non-existent location" actual && - ! test -d .git/worktrees/def && - ! test -d .git/worktrees + test_path_is_missing .git/worktrees/def && + test_path_is_missing .git/worktrees ' test_expect_success 'not prune locked checkout' ' @@ -76,23 +76,23 @@ test_expect_success 'not prune locked checkout' ' mkdir -p .git/worktrees/ghi && : >.git/worktrees/ghi/locked && git worktree prune && - test -d .git/worktrees/ghi + test_path_is_dir .git/worktrees/ghi ' test_expect_success 'not prune recent checkouts' ' test_when_finished rm -r .git/worktrees && git worktree add jlm HEAD && - test -d .git/worktrees/jlm && + test_path_is_dir .git/worktrees/jlm && rm -rf jlm && git worktree prune --verbose --expire=2.days.ago && - test -d .git/worktrees/jlm + test_path_is_dir .git/worktrees/jlm ' test_expect_success 'not prune proper checkouts' ' test_when_finished rm -r .git/worktrees && git worktree add --detach "$PWD/nop" main && git worktree prune && - test -d .git/worktrees/nop + test_path_is_dir .git/worktrees/nop ' test_expect_success 'prune duplicate (linked/linked)' ' @@ -103,8 +103,8 @@ test_expect_success 'prune duplicate (linked/linked)' ' mv .git/worktrees/w2/gitdir.new .git/worktrees/w2/gitdir && git worktree prune --verbose 2>actual && test_grep "duplicate entry" actual && - test -d .git/worktrees/w1 && - ! test -d .git/worktrees/w2 + test_path_is_dir .git/worktrees/w1 && + test_path_is_missing .git/worktrees/w2 ' test_expect_success 'prune duplicate (main/linked)' ' @@ -116,7 +116,7 @@ test_expect_success 'prune duplicate (main/linked)' ' mv repo wt && git -C wt worktree prune --verbose 2>actual && test_grep "duplicate entry" actual && - ! test -d .git/worktrees/wt + test_path_is_missing .git/worktrees/wt ' test_expect_success 'not prune proper worktrees inside linked worktree with relative paths' ' diff --git a/t/t3206-range-diff.sh b/t/t3206-range-diff.sh index e091df6d01..1e812df806 100755 --- a/t/t3206-range-diff.sh +++ b/t/t3206-range-diff.sh @@ -707,7 +707,7 @@ test_expect_success 'format-patch --range-diff does not compare notes by default ! grep "note" 0000-* ' -test_expect_success 'format-patch --notes=custom --range-diff only compares custom notes' ' +test_expect_success 'format-patch --notes=custom --range-diff --cover-letter only compares custom notes' ' test_when_finished "git notes remove topic unmodified || :" && git notes add -m "topic note" topic && git notes add -m "unmodified note" unmodified && @@ -721,6 +721,20 @@ test_expect_success 'format-patch --notes=custom --range-diff only compares cust ! grep "## Notes ##" 0000-* ' +# --range-diff on a single commit requires --no-cover-letter +test_expect_success 'format-patch --notes=custom --range-diff on single commit only compares custom notes' ' + test_when_finished "git notes remove HEAD unmodified || :" && + git notes add -m "topic note" HEAD && + test_when_finished "git notes --ref=custom remove HEAD unmodified || :" && + git notes add -m "unmodified note" unmodified && + git notes --ref=custom add -m "topic note (custom)" HEAD && + git notes --ref=custom add -m "unmodified note (custom)" unmodified && + git format-patch --notes=custom --range-diff=$prev \ + -1 --stdout >actual && + test_grep "## Notes (custom) ##" actual && + test_grep ! "## Notes ##" actual +' + test_expect_success 'format-patch --range-diff with --no-notes' ' test_when_finished "git notes remove topic unmodified || :" && git notes add -m "topic note" topic && diff --git a/t/t3701-add-interactive.sh b/t/t3701-add-interactive.sh index 19aacc8270..851ca6dd91 100755 --- a/t/t3701-add-interactive.sh +++ b/t/t3701-add-interactive.sh @@ -1354,6 +1354,37 @@ do ' done +test_expect_success 'splitting previous hunk marks split hunks as undecided' ' + test_write_lines a " " b c d e f g h i j k >file && + git add file && + test_write_lines x " " b y d e f g h i j x >file && + test_write_lines n K s n y q | git add -p file && + git cat-file blob :file >actual && + test_write_lines a " " b y d e f g h i j k >expect && + test_cmp expect actual +' + +test_expect_success 'splitting edited hunk' ' + # Before the first hunk is edited it can be split into two + # hunks, after editing it can be split into three hunks. + + write_script fake-editor.sh <<-\EOF && + sed "s/^ c/-c/" "$1" >"$1.tmp" && + mv "$1.tmp" "$1" + EOF + + test_write_lines a b c d e f g h i j k l m n >file && + git add file && + test_write_lines A b c d E f g h i j k l M n >file && + ( + test_set_editor "$(pwd)/fake-editor.sh" && + test_write_lines e K s j y n y q | git add -p file + ) && + git cat-file blob :file >actual && + test_write_lines a b d e f g h i j k l M n >expect && + test_cmp expect actual +' + test_expect_success 'options J, K roll over' ' test_write_lines a b c d e f g h i >file && git add file && diff --git a/t/t4035-diff-quiet.sh b/t/t4035-diff-quiet.sh index 0352bf81a9..35eaf0855f 100755 --- a/t/t4035-diff-quiet.sh +++ b/t/t4035-diff-quiet.sh @@ -50,6 +50,10 @@ test_expect_success 'git diff-tree HEAD HEAD' ' test_expect_code 0 git diff-tree --quiet HEAD HEAD >cnt && test_line_count = 0 cnt ' +test_expect_success 'git diff-tree -w HEAD^ HEAD' ' + test_expect_code 1 git diff-tree --quiet -w HEAD^ HEAD >cnt && + test_line_count = 0 cnt +' test_expect_success 'git diff-files' ' test_expect_code 0 git diff-files --quiet >cnt && test_line_count = 0 cnt diff --git a/t/t4053-diff-no-index.sh b/t/t4053-diff-no-index.sh index 44b4b13f5d..69599279e9 100755 --- a/t/t4053-diff-no-index.sh +++ b/t/t4053-diff-no-index.sh @@ -339,6 +339,22 @@ test_expect_success 'diff --no-index with pathspec' ' test_cmp expect actual ' +test_expect_success 'diff --no-index first path ending in slash with pathspec' ' + test_expect_code 1 git diff --name-status --no-index a/ b 1 >actual && + cat >expect <<-EOF && + D a/1 + EOF + test_cmp expect actual +' + +test_expect_success 'diff --no-index second path ending in slash with pathspec' ' + test_expect_code 1 git diff --name-status --no-index a b/ 1 >actual && + cat >expect <<-EOF && + D a/1 + EOF + test_cmp expect actual +' + test_expect_success 'diff --no-index with pathspec no matches' ' test_expect_code 0 git diff --name-status --no-index a b missing ' diff --git a/t/t6302-for-each-ref-filter.sh b/t/t6302-for-each-ref-filter.sh index 9b80ea1e3b..7f060d97bf 100755 --- a/t/t6302-for-each-ref-filter.sh +++ b/t/t6302-for-each-ref-filter.sh @@ -754,4 +754,69 @@ test_expect_success 'start after used with custom sort order' ' test_cmp expect actual ' +test_expect_success 'start after with packed refs' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit default && + + git update-ref --stdin <<-\EOF && + create refs/heads/branch @ + create refs/heads/side @ + create refs/odd/spot @ + create refs/tags/one @ + create refs/tags/two @ + commit + EOF + + cat >expect <<-\EOF && + refs/tags/default + refs/tags/one + refs/tags/two + EOF + + git pack-refs --all && + git for-each-ref --format="%(refname)" --start-after=refs/odd/spot >actual && + test_cmp expect actual + ) +' + +test_expect_success 'start after with packed refs and some loose refs' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit default && + + git update-ref --stdin <<-\EOF && + create refs/heads/branch @ + create refs/heads/side @ + create refs/odd/spot @ + create refs/tags/one @ + create refs/tags/two @ + commit + EOF + + git pack-refs --all && + + git update-ref --stdin <<-\EOF && + create refs/heads/foo @ + create refs/odd/tee @ + commit + EOF + + cat >expect <<-\EOF && + refs/odd/tee + refs/tags/default + refs/tags/one + refs/tags/two + EOF + + + git for-each-ref --format="%(refname)" --start-after=refs/odd/spot >actual && + test_cmp expect actual + ) +' + test_done diff --git a/t/t7500-commit-template-squash-signoff.sh b/t/t7500-commit-template-squash-signoff.sh index 4dca8d97a7..66aff8e097 100755 --- a/t/t7500-commit-template-squash-signoff.sh +++ b/t/t7500-commit-template-squash-signoff.sh @@ -31,56 +31,83 @@ test_expect_success 'nonexistent template file should return error' ' echo changes >> foo && git add foo && ( + GIT_EDITOR="echo hello >" && + export GIT_EDITOR && + test_must_fail git commit --template "$(pwd)"/notexist + ) +' + +test_expect_success 'nonexistent optional template file on command line' ' + echo changes >> foo && + git add foo && + ( GIT_EDITOR="echo hello >\"\$1\"" && export GIT_EDITOR && - test_must_fail git commit --template "$PWD"/notexist + git commit --template ":(optional)$(pwd)/notexist" ) ' test_expect_success 'nonexistent template file in config should return error' ' - test_config commit.template "$PWD"/notexist && + test_config commit.template "$(pwd)"/notexist && ( - GIT_EDITOR="echo hello >\"\$1\"" && + GIT_EDITOR="echo hello >" && export GIT_EDITOR && - test_must_fail git commit + test_must_fail git commit --allow-empty ) ' +test_expect_success 'nonexistent optional template file in config' ' + test_config commit.template ":(optional)$(pwd)"/notexist && + GIT_EDITOR="echo hello >" git commit --allow-empty && + git cat-file commit HEAD | sed -e "1,/^$/d" >actual && + echo hello >expect && + test_cmp expect actual +' + # From now on we'll use a template file that exists. -TEMPLATE="$PWD"/template +TEMPLATE="$(pwd)"/template test_expect_success 'unedited template should not commit' ' - echo "template line" > "$TEMPLATE" && - test_must_fail git commit --template "$TEMPLATE" + echo "template line" >"$TEMPLATE" && + test_must_fail git commit --allow-empty --template "$TEMPLATE" ' test_expect_success 'unedited template with comments should not commit' ' - echo "# comment in template" >> "$TEMPLATE" && - test_must_fail git commit --template "$TEMPLATE" + echo "# comment in template" >>"$TEMPLATE" && + test_must_fail git commit --allow-empty --template "$TEMPLATE" ' test_expect_success 'a Signed-off-by line by itself should not commit' ' ( test_set_editor "$TEST_DIRECTORY"/t7500/add-signed-off && - test_must_fail git commit --template "$TEMPLATE" + test_must_fail git commit --allow-empty --template "$TEMPLATE" ) ' test_expect_success 'adding comments to a template should not commit' ' ( test_set_editor "$TEST_DIRECTORY"/t7500/add-comments && - test_must_fail git commit --template "$TEMPLATE" + test_must_fail git commit --allow-empty --template "$TEMPLATE" ) ' test_expect_success 'adding real content to a template should commit' ' ( test_set_editor "$TEST_DIRECTORY"/t7500/add-content && - git commit --template "$TEMPLATE" + git commit --allow-empty --template "$TEMPLATE" ) && commit_msg_is "template linecommit message" ' +test_expect_success 'existent template marked optional should commit' ' + echo "existent template" >"$TEMPLATE" && + ( + test_set_editor "$TEST_DIRECTORY"/t7500/add-content && + git commit --allow-empty --template ":(optional)$TEMPLATE" + ) && + commit_msg_is "existent templatecommit message" +' + test_expect_success '-t option should be short for --template' ' echo "short template" > "$TEMPLATE" && echo "new content" >> foo && diff --git a/t/t7508-status.sh b/t/t7508-status.sh index cdc1d6fcc7..abad229e9d 100755 --- a/t/t7508-status.sh +++ b/t/t7508-status.sh @@ -717,6 +717,17 @@ test_expect_success TTY 'status -s with color.status' ' ' +test_expect_success TTY 'status -s keeps colors with -z' ' + test_when_finished "rm -f output.*" && + test_terminal git status -s -z >output.raw && + # convert back to newlines to avoid portability issues with + # test_decode_color and test_cmp, and to let us use the same expected + # output as earlier tests + tr "\0" "\n" <output.raw >output.nl && + test_decode_color <output.nl >output && + test_cmp expect output +' + cat >expect <<\EOF ## <YELLOW>main<RESET>...<CYAN>upstream<RESET> [ahead <YELLOW>1<RESET>, behind <CYAN>2<RESET>] <RED>M<RESET> dir1/modified diff --git a/t/t8020-last-modified.sh b/t/t8020-last-modified.sh index e13aad1439..61f00bc15c 100755 --- a/t/t8020-last-modified.sh +++ b/t/t8020-last-modified.sh @@ -33,7 +33,6 @@ check_last_modified() { done && cat >expect && - test_when_finished "rm -f tmp.*" && git ${indir:+-C "$indir"} last-modified "$@" >tmp.1 && git name-rev --annotate-stdin --name-only --tags \ <tmp.1 >tmp.2 && @@ -128,20 +127,25 @@ test_expect_success 'only last-modified files in the current tree' ' EOF ' -test_expect_success 'last-modified with subdir and criss-cross merge' ' - git checkout -b branch-k1 1 && - mkdir -p a k && - test_commit k1 a/file2 && - git checkout -b branch-k2 && - test_commit k2 k/file2 && - git checkout branch-k1 && - test_merge km2 branch-k2 && - test_merge km3 3 && - check_last_modified <<-\EOF - km3 a - k2 k - 1 file - EOF +test_expect_success 'subdirectory modified via merge' ' + test_when_finished rm -rf repo && + git init repo && + ( + cd repo && + test_commit base && + git switch --create left && + mkdir subdir && + test_commit left subdir/left && + git switch --create right base && + mkdir subdir && + test_commit right subdir/right && + git switch - && + test_merge merge right && + check_last_modified <<-\EOF + merge subdir + base base.t + EOF + ) ' test_expect_success 'cross merge boundaries in blaming' ' diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index a28de7b19b..52d7759bf5 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -1708,11 +1708,16 @@ test_set_hash () { # Detect the hash algorithm in use. test_detect_hash () { case "${GIT_TEST_DEFAULT_HASH:-$GIT_TEST_BUILTIN_HASH}" in - "sha256") + *:*) + test_hash_algo="${GIT_TEST_DEFAULT_HASH%%:*}" + test_compat_hash_algo="${GIT_TEST_DEFAULT_HASH##*:}" + test_repo_compat_hash_algo="$test_compat_hash_algo" + ;; + sha256) test_hash_algo=sha256 test_compat_hash_algo=sha1 ;; - *) + sha1) test_hash_algo=sha1 test_compat_hash_algo=sha256 ;; diff --git a/t/test-lib.sh b/t/test-lib.sh index 562f950fb0..ef0ab7ec2d 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -1924,6 +1924,19 @@ test_lazy_prereq DEFAULT_HASH_ALGORITHM ' test_lazy_prereq DEFAULT_REPO_FORMAT ' test_have_prereq SHA1,REFFILES ' +# BROKEN_OBJECTS is a test whether we can write deliberately broken objects and +# expect them to work. When running using SHA-256 mode with SHA-1 +# compatibility, we cannot write such objects because there's no SHA-1 +# compatibility value for a nonexistent object. +test_lazy_prereq BROKEN_OBJECTS ' + ! test_have_prereq COMPAT_HASH +' + +# COMPAT_HASH is a test if we're operating in a repository with SHA-256 with +# SHA-1 compatibility. +test_lazy_prereq COMPAT_HASH ' + test -n "$test_repo_compat_hash_algo" +' # Ensure that no test accidentally triggers a Git command # that runs the actual maintenance scheduler, affecting a user's diff --git a/t/unit-tests/u-reftable-basics.c b/t/unit-tests/u-reftable-basics.c index a0471083e7..73566ed0eb 100644 --- a/t/unit-tests/u-reftable-basics.c +++ b/t/unit-tests/u-reftable-basics.c @@ -9,6 +9,7 @@ https://developers.google.com/open-source/licenses/bsd #include "unit-test.h" #include "lib-reftable.h" #include "reftable/basics.h" +#include "reftable/reftable-error.h" struct integer_needle_lesseq_args { int needle; @@ -79,14 +80,18 @@ void test_reftable_basics__names_equal(void) void test_reftable_basics__parse_names(void) { char in1[] = "line\n"; - char in2[] = "a\nb\nc"; - char **out = parse_names(in1, strlen(in1)); + char in2[] = "a\nb\nc\n"; + char **out = NULL; + int err = parse_names(in1, strlen(in1), &out); + cl_assert(err == 0); cl_assert(out != NULL); cl_assert_equal_s(out[0], "line"); cl_assert(!out[1]); free_names(out); - out = parse_names(in2, strlen(in2)); + out = NULL; + err = parse_names(in2, strlen(in2), &out); + cl_assert(err == 0); cl_assert(out != NULL); cl_assert_equal_s(out[0], "a"); cl_assert_equal_s(out[1], "b"); @@ -95,10 +100,21 @@ void test_reftable_basics__parse_names(void) free_names(out); } +void test_reftable_basics__parse_names_missing_newline(void) +{ + char in1[] = "line\nline2"; + char **out = NULL; + int err = parse_names(in1, strlen(in1), &out); + cl_assert(err == REFTABLE_FORMAT_ERROR); + cl_assert(out == NULL); +} + void test_reftable_basics__parse_names_drop_empty_string(void) { char in[] = "a\n\nb\n"; - char **out = parse_names(in, strlen(in)); + char **out = NULL; + int err = parse_names(in, strlen(in), &out); + cl_assert(err == 0); cl_assert(out != NULL); cl_assert_equal_s(out[0], "a"); /* simply '\n' should be dropped as empty string */ diff --git a/transport-helper.c b/transport-helper.c index 0789e5bca5..4d95d84f9e 100644 --- a/transport-helper.c +++ b/transport-helper.c @@ -450,7 +450,7 @@ static int fetch_with_fetch(struct transport *transport, } strbuf_release(&buf); - reprepare_packed_git(the_repository); + odb_reprepare(the_repository->objects); return 0; } diff --git a/unicode-width.h b/unicode-width.h index 3ffee123a0..b701129515 100644 --- a/unicode-width.h +++ b/unicode-width.h @@ -143,7 +143,8 @@ static const struct interval zero_width[] = { { 0x1A65, 0x1A6C }, { 0x1A73, 0x1A7C }, { 0x1A7F, 0x1A7F }, -{ 0x1AB0, 0x1ACE }, +{ 0x1AB0, 0x1ADD }, +{ 0x1AE0, 0x1AEB }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A }, @@ -229,7 +230,7 @@ static const struct interval zero_width[] = { { 0x10D24, 0x10D27 }, { 0x10D69, 0x10D6D }, { 0x10EAB, 0x10EAC }, -{ 0x10EFC, 0x10EFF }, +{ 0x10EFA, 0x10EFF }, { 0x10F46, 0x10F50 }, { 0x10F82, 0x10F85 }, { 0x11001, 0x11001 }, @@ -306,6 +307,9 @@ static const struct interval zero_width[] = { { 0x11A59, 0x11A5B }, { 0x11A8A, 0x11A96 }, { 0x11A98, 0x11A99 }, +{ 0x11B60, 0x11B60 }, +{ 0x11B62, 0x11B64 }, +{ 0x11B66, 0x11B66 }, { 0x11C30, 0x11C36 }, { 0x11C38, 0x11C3D }, { 0x11C3F, 0x11C3F }, @@ -362,6 +366,10 @@ static const struct interval zero_width[] = { { 0x1E2EC, 0x1E2EF }, { 0x1E4EC, 0x1E4EF }, { 0x1E5EE, 0x1E5EF }, +{ 0x1E6E3, 0x1E6E3 }, +{ 0x1E6E6, 0x1E6E6 }, +{ 0x1E6EE, 0x1E6EF }, +{ 0x1E6F5, 0x1E6F5 }, { 0x1E8D0, 0x1E8D6 }, { 0x1E944, 0x1E94A }, { 0xE0001, 0xE0001 }, @@ -429,10 +437,10 @@ static const struct interval double_width[] = { { 0xFF01, 0xFF60 }, { 0xFFE0, 0xFFE6 }, { 0x16FE0, 0x16FE4 }, -{ 0x16FF0, 0x16FF1 }, -{ 0x17000, 0x187F7 }, -{ 0x18800, 0x18CD5 }, -{ 0x18CFF, 0x18D08 }, +{ 0x16FF0, 0x16FF6 }, +{ 0x17000, 0x18CD5 }, +{ 0x18CFF, 0x18D1E }, +{ 0x18D80, 0x18DF2 }, { 0x1AFF0, 0x1AFF3 }, { 0x1AFF5, 0x1AFFB }, { 0x1AFFD, 0x1AFFE }, @@ -474,7 +482,7 @@ static const struct interval double_width[] = { { 0x1F680, 0x1F6C5 }, { 0x1F6CC, 0x1F6CC }, { 0x1F6D0, 0x1F6D2 }, -{ 0x1F6D5, 0x1F6D7 }, +{ 0x1F6D5, 0x1F6D8 }, { 0x1F6DC, 0x1F6DF }, { 0x1F6EB, 0x1F6EC }, { 0x1F6F4, 0x1F6FC }, @@ -484,11 +492,12 @@ static const struct interval double_width[] = { { 0x1F93C, 0x1F945 }, { 0x1F947, 0x1F9FF }, { 0x1FA70, 0x1FA7C }, -{ 0x1FA80, 0x1FA89 }, -{ 0x1FA8F, 0x1FAC6 }, -{ 0x1FACE, 0x1FADC }, -{ 0x1FADF, 0x1FAE9 }, -{ 0x1FAF0, 0x1FAF8 }, +{ 0x1FA80, 0x1FA8A }, +{ 0x1FA8E, 0x1FAC6 }, +{ 0x1FAC8, 0x1FAC8 }, +{ 0x1FACD, 0x1FADC }, +{ 0x1FADF, 0x1FAEA }, +{ 0x1FAEF, 0x1FAF8 }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD } }; @@ -1,11 +1,11 @@ #include "git-compat-util.h" #include "varint.h" -uintmax_t decode_varint(const unsigned char **bufp) +uint64_t decode_varint(const unsigned char **bufp) { const unsigned char *buf = *bufp; unsigned char c = *buf++; - uintmax_t val = c & 127; + uint64_t val = c & 127; while (c & 128) { val += 1; if (!val || MSB(val, 7)) @@ -17,7 +17,7 @@ uintmax_t decode_varint(const unsigned char **bufp) return val; } -int encode_varint(uintmax_t value, unsigned char *buf) +uint8_t encode_varint(uint64_t value, unsigned char *buf) { unsigned char varint[16]; unsigned pos = sizeof(varint) - 1; @@ -1,7 +1,7 @@ #ifndef VARINT_H #define VARINT_H -int encode_varint(uintmax_t, unsigned char *); -uintmax_t decode_varint(const unsigned char **); +uint8_t encode_varint(uint64_t, unsigned char *); +uint64_t decode_varint(const unsigned char **); #endif /* VARINT_H */ @@ -721,6 +721,19 @@ int xgethostname(char *buf, size_t len) return ret; } +int is_missing_file(const char *filename) +{ + struct stat st; + + if (stat(filename, &st) < 0) { + if (errno == ENOENT) + return 1; + die_errno(_("could not stat %s"), filename); + } + + return 0; +} + int is_empty_or_missing_file(const char *filename) { struct stat st; @@ -66,7 +66,9 @@ void write_file_buf(const char *path, const char *buf, size_t len); __attribute__((format (printf, 2, 3))) void write_file(const char *path, const char *fmt, ...); -/* Return 1 if the file is empty or does not exists, 0 otherwise. */ +/* Return 1 if the file does not exist, 0 otherwise. */ +int is_missing_file(const char *filename); +/* Return 1 if the file is empty or does not exist, 0 otherwise. */ int is_empty_or_missing_file(const char *filename); enum fsync_action { diff --git a/wt-status.c b/wt-status.c index 8ffe6d3988..e12adb26b9 100644 --- a/wt-status.c +++ b/wt-status.c @@ -2042,13 +2042,13 @@ static void wt_shortstatus_status(struct string_list_item *it, static void wt_shortstatus_other(struct string_list_item *it, struct wt_status *s, const char *sign) { + color_fprintf(s->fp, color(WT_STATUS_UNTRACKED, s), "%s", sign); if (s->null_termination) { - fprintf(s->fp, "%s %s%c", sign, it->string, 0); + fprintf(s->fp, " %s%c", it->string, 0); } else { struct strbuf onebuf = STRBUF_INIT; const char *one; one = quote_path(it->string, s->prefix, &onebuf, QUOTE_PATH_QUOTE_SP); - color_fprintf(s->fp, color(WT_STATUS_UNTRACKED, s), "%s", sign); fprintf(s->fp, " %s\n", one); strbuf_release(&onebuf); } diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c index 5a96e36dfb..6f3998ee54 100644 --- a/xdiff/xdiffi.c +++ b/xdiff/xdiffi.c @@ -22,6 +22,11 @@ #include "xinclude.h" +static unsigned long get_hash(xdfile_t *xdf, long index) +{ + return xdf->recs[xdf->rindex[index]].ha; +} + #define XDL_MAX_COST_MIN 256 #define XDL_HEUR_MIN_COST 256 #define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1) @@ -42,8 +47,8 @@ typedef struct s_xdpsplit { * using this algorithm, so a little bit of heuristic is needed to cut the * search and to return a suboptimal point. */ -static long xdl_split(unsigned long const *ha1, long off1, long lim1, - unsigned long const *ha2, long off2, long lim2, +static long xdl_split(xdfile_t *xdf1, long off1, long lim1, + xdfile_t *xdf2, long off2, long lim2, long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, xdalgoenv_t *xenv) { long dmin = off1 - lim2, dmax = lim1 - off2; @@ -87,7 +92,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, i1 = kvdf[d + 1]; prev1 = i1; i2 = i1 - d; - for (; i1 < lim1 && i2 < lim2 && ha1[i1] == ha2[i2]; i1++, i2++); + for (; i1 < lim1 && i2 < lim2 && get_hash(xdf1, i1) == get_hash(xdf2, i2); i1++, i2++); if (i1 - prev1 > xenv->snake_cnt) got_snake = 1; kvdf[d] = i1; @@ -124,7 +129,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, i1 = kvdb[d + 1] - 1; prev1 = i1; i2 = i1 - d; - for (; i1 > off1 && i2 > off2 && ha1[i1 - 1] == ha2[i2 - 1]; i1--, i2--); + for (; i1 > off1 && i2 > off2 && get_hash(xdf1, i1 - 1) == get_hash(xdf2, i2 - 1); i1--, i2--); if (prev1 - i1 > xenv->snake_cnt) got_snake = 1; kvdb[d] = i1; @@ -159,7 +164,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, if (v > XDL_K_HEUR * ec && v > best && off1 + xenv->snake_cnt <= i1 && i1 < lim1 && off2 + xenv->snake_cnt <= i2 && i2 < lim2) { - for (k = 1; ha1[i1 - k] == ha2[i2 - k]; k++) + for (k = 1; get_hash(xdf1, i1 - k) == get_hash(xdf2, i2 - k); k++) if (k == xenv->snake_cnt) { best = v; spl->i1 = i1; @@ -183,7 +188,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, if (v > XDL_K_HEUR * ec && v > best && off1 < i1 && i1 <= lim1 - xenv->snake_cnt && off2 < i2 && i2 <= lim2 - xenv->snake_cnt) { - for (k = 0; ha1[i1 + k] == ha2[i2 + k]; k++) + for (k = 0; get_hash(xdf1, i1 + k) == get_hash(xdf2, i2 + k); k++) if (k == xenv->snake_cnt - 1) { best = v; spl->i1 = i1; @@ -257,33 +262,26 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1, * sub-boxes by calling the box splitting function. Note that the real job * (marking changed lines) is done in the two boundary reaching checks. */ -int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, - diffdata_t *dd2, long off2, long lim2, +int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1, + xdfile_t *xdf2, long off2, long lim2, long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) { - unsigned long const *ha1 = dd1->ha, *ha2 = dd2->ha; /* * Shrink the box by walking through each diagonal snake (SW and NE). */ - for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++); - for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--); + for (; off1 < lim1 && off2 < lim2 && get_hash(xdf1, off1) == get_hash(xdf2, off2); off1++, off2++); + for (; off1 < lim1 && off2 < lim2 && get_hash(xdf1, lim1 - 1) == get_hash(xdf2, lim2 - 1); lim1--, lim2--); /* * If one dimension is empty, then all records on the other one must * be obviously changed. */ if (off1 == lim1) { - char *rchg2 = dd2->rchg; - long *rindex2 = dd2->rindex; - for (; off2 < lim2; off2++) - rchg2[rindex2[off2]] = 1; + xdf2->changed[xdf2->rindex[off2]] = true; } else if (off2 == lim2) { - char *rchg1 = dd1->rchg; - long *rindex1 = dd1->rindex; - for (; off1 < lim1; off1++) - rchg1[rindex1[off1]] = 1; + xdf1->changed[xdf1->rindex[off1]] = true; } else { xdpsplit_t spl; spl.i1 = spl.i2 = 0; @@ -291,7 +289,7 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, /* * Divide ... */ - if (xdl_split(ha1, off1, lim1, ha2, off2, lim2, kvdf, kvdb, + if (xdl_split(xdf1, off1, lim1, xdf2, off2, lim2, kvdf, kvdb, need_min, &spl, xenv) < 0) { return -1; @@ -300,9 +298,9 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, /* * ... et Impera. */ - if (xdl_recs_cmp(dd1, off1, spl.i1, dd2, off2, spl.i2, + if (xdl_recs_cmp(xdf1, off1, spl.i1, xdf2, off2, spl.i2, kvdf, kvdb, spl.min_lo, xenv) < 0 || - xdl_recs_cmp(dd1, spl.i1, lim1, dd2, spl.i2, lim2, + xdl_recs_cmp(xdf1, spl.i1, lim1, xdf2, spl.i2, lim2, kvdf, kvdb, spl.min_hi, xenv) < 0) { return -1; @@ -318,7 +316,6 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, long ndiags; long *kvd, *kvdf, *kvdb; xdalgoenv_t xenv; - diffdata_t dd1, dd2; int res; if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) @@ -357,16 +354,7 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xenv.snake_cnt = XDL_SNAKE_CNT; xenv.heur_min = XDL_HEUR_MIN_COST; - dd1.nrec = xe->xdf1.nreff; - dd1.ha = xe->xdf1.ha; - dd1.rchg = xe->xdf1.rchg; - dd1.rindex = xe->xdf1.rindex; - dd2.nrec = xe->xdf2.nreff; - dd2.ha = xe->xdf2.ha; - dd2.rchg = xe->xdf2.rchg; - dd2.rindex = xe->xdf2.rindex; - - res = xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec, + res = xdl_recs_cmp(&xe->xdf1, 0, xe->xdf1.nreff, &xe->xdf2, 0, xe->xdf2.nreff, kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, &xenv); xdl_free(kvd); @@ -501,13 +489,13 @@ static void measure_split(const xdfile_t *xdf, long split, m->indent = -1; } else { m->end_of_file = 0; - m->indent = get_indent(xdf->recs[split]); + m->indent = get_indent(&xdf->recs[split]); } m->pre_blank = 0; m->pre_indent = -1; for (i = split - 1; i >= 0; i--) { - m->pre_indent = get_indent(xdf->recs[i]); + m->pre_indent = get_indent(&xdf->recs[i]); if (m->pre_indent != -1) break; m->pre_blank += 1; @@ -520,7 +508,7 @@ 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++) { - m->post_indent = get_indent(xdf->recs[i]); + m->post_indent = get_indent(&xdf->recs[i]); if (m->post_indent != -1) break; m->post_blank += 1; @@ -720,7 +708,7 @@ struct xdlgroup { static void group_init(xdfile_t *xdf, struct xdlgroup *g) { g->start = g->end = 0; - while (xdf->rchg[g->end]) + while (xdf->changed[g->end]) g->end++; } @@ -734,7 +722,7 @@ static inline int group_next(xdfile_t *xdf, struct xdlgroup *g) return -1; g->start = g->end + 1; - for (g->end = g->start; xdf->rchg[g->end]; g->end++) + for (g->end = g->start; xdf->changed[g->end]; g->end++) ; return 0; @@ -750,7 +738,7 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g) return -1; g->end = g->start - 1; - for (g->start = g->end; xdf->rchg[g->start - 1]; g->start--) + for (g->start = g->end; xdf->changed[g->start - 1]; g->start--) ; return 0; @@ -764,11 +752,11 @@ 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 && - recs_match(xdf->recs[g->start], xdf->recs[g->end])) { - xdf->rchg[g->start++] = 0; - xdf->rchg[g->end++] = 1; + recs_match(&xdf->recs[g->start], &xdf->recs[g->end])) { + xdf->changed[g->start++] = false; + xdf->changed[g->end++] = true; - while (xdf->rchg[g->end]) + while (xdf->changed[g->end]) g->end++; return 0; @@ -785,11 +773,11 @@ static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g) static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g) { if (g->start > 0 && - recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1])) { - xdf->rchg[--g->start] = 1; - xdf->rchg[--g->end] = 0; + recs_match(&xdf->recs[g->start - 1], &xdf->recs[g->end - 1])) { + xdf->changed[--g->start] = true; + xdf->changed[--g->end] = false; - while (xdf->rchg[g->start - 1]) + while (xdf->changed[g->start - 1]) g->start--; return 0; @@ -944,16 +932,16 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) { int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) { xdchange_t *cscr = NULL, *xch; - char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg; + bool *changed1 = xe->xdf1.changed, *changed2 = xe->xdf2.changed; long i1, i2, l1, l2; /* * Trivial. Collects "groups" of changes and creates an edit script. */ for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--) - if (rchg1[i1 - 1] || rchg2[i2 - 1]) { - for (l1 = i1; rchg1[i1 - 1]; i1--); - for (l2 = i2; rchg2[i2 - 1]; i2--); + if (changed1[i1 - 1] || changed2[i2 - 1]) { + for (l1 = i1; changed1[i1 - 1]; i1--); + for (l2 = i2; changed2[i2 - 1]; i2--); if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) { xdl_free_script(cscr); @@ -1000,16 +988,16 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags) for (xch = xscr; xch; xch = xch->next) { int ignore = 1; - xrecord_t **rec; + xrecord_t *rec; long i; 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(rec[i].ptr, 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(rec[i].ptr, rec[i].size, flags); xch->ignore = ignore; } @@ -1033,7 +1021,7 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe, xdchange_t *xch; for (xch = xscr; xch; xch = xch->next) { - xrecord_t **rec; + xrecord_t *rec; int ignore = 1; long i; @@ -1045,11 +1033,11 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe, rec = &xe->xdf1.recs[xch->i1]; for (i = 0; i < xch->chg1 && ignore; i++) - ignore = record_matches_regex(rec[i], xpp); + ignore = record_matches_regex(&rec[i], xpp); rec = &xe->xdf2.recs[xch->i2]; for (i = 0; i < xch->chg2 && ignore; i++) - ignore = record_matches_regex(rec[i], xpp); + ignore = record_matches_regex(&rec[i], xpp); xch->ignore = ignore; } diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h index 126c9d8ff4..49e52c67f9 100644 --- a/xdiff/xdiffi.h +++ b/xdiff/xdiffi.h @@ -24,13 +24,6 @@ #define XDIFFI_H -typedef struct s_diffdata { - long nrec; - unsigned long const *ha; - long *rindex; - char *rchg; -} diffdata_t; - typedef struct s_xdalgoenv { long mxcost; long snake_cnt; @@ -46,8 +39,8 @@ typedef struct s_xdchange { -int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, - diffdata_t *dd2, long off2, long lim2, +int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1, + xdfile_t *xdf2, long off2, long lim2, long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv); int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdfenv_t *xe); diff --git a/xdiff/xemit.c b/xdiff/xemit.c index 1d40c9cb40..b2f1f30cd3 100644 --- a/xdiff/xemit.c +++ b/xdiff/xemit.c @@ -22,23 +22,13 @@ #include "xinclude.h" -static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) { - *rec = xdf->recs[ri]->ptr; - - return xdf->recs[ri]->size; -} - - -static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) { - long size, psize = strlen(pre); - char const *rec; - - size = xdl_get_rec(xdf, ri, &rec); - if (xdl_emit_diffrec(rec, size, pre, psize, ecb) < 0) { +static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) +{ + xrecord_t *rec = &xdf->recs[ri]; + if (xdl_emit_diffrec(rec->ptr, rec->size, pre, strlen(pre), ecb) < 0) return -1; - } return 0; } @@ -120,11 +110,11 @@ static long def_ff(const char *rec, long len, char *buf, long sz) static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri, char *buf, long sz) { - const char *rec; - long len = xdl_get_rec(xdf, ri, &rec); + xrecord_t *rec = &xdf->recs[ri]; + if (!xecfg->find_func) - return def_ff(rec, len, buf, sz); - return xecfg->find_func(rec, len, buf, sz, xecfg->find_func_priv); + return def_ff(rec->ptr, rec->size, buf, sz); + return xecfg->find_func(rec->ptr, rec->size, buf, sz, xecfg->find_func_priv); } static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri) @@ -160,14 +150,12 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg, static int is_empty_rec(xdfile_t *xdf, long ri) { - const char *rec; - long len = xdl_get_rec(xdf, ri, &rec); + xrecord_t *rec = &xdf->recs[ri]; + long i = 0; - while (len > 0 && XDL_ISSPACE(*rec)) { - rec++; - len--; - } - return !len; + for (; i < rec->size && XDL_ISSPACE(rec->ptr[i]); i++); + + return i == rec->size; } int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c index 040d81e0bc..6dc450b1fe 100644 --- a/xdiff/xhistogram.c +++ b/xdiff/xhistogram.c @@ -86,7 +86,7 @@ struct region { ((LINE_MAP(index, ptr))->cnt) #define REC(env, s, l) \ - (env->xdf##s.recs[l - 1]) + (&env->xdf##s.recs[l - 1]) static int cmp_recs(xrecord_t *r1, xrecord_t *r2) { @@ -318,11 +318,11 @@ redo: if (!count1) { while(count2--) - env->xdf2.rchg[line2++ - 1] = 1; + env->xdf2.changed[line2++ - 1] = true; return 0; } else if (!count2) { while(count1--) - env->xdf1.rchg[line1++ - 1] = 1; + env->xdf1.changed[line1++ - 1] = true; return 0; } @@ -335,9 +335,9 @@ redo: else { if (lcs.begin1 == 0 && lcs.begin2 == 0) { while (count1--) - env->xdf1.rchg[line1++ - 1] = 1; + env->xdf1.changed[line1++ - 1] = true; while (count2--) - env->xdf2.rchg[line2++ - 1] = 1; + env->xdf2.changed[line2++ - 1] = true; result = 0; } else { result = histogram_diff(xpp, env, diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c index af40c88a5b..fd600cbb5d 100644 --- a/xdiff/xmerge.c +++ b/xdiff/xmerge.c @@ -97,12 +97,12 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, int line_count, long flags) { int i; - xrecord_t **rec1 = xe1->xdf2.recs + i1; - xrecord_t **rec2 = xe2->xdf2.recs + i2; + xrecord_t *rec1 = xe1->xdf2.recs + i1; + 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(rec1[i].ptr, rec1[i].size, + rec2[i].ptr, rec2[i].size, flags); if (!result) return -1; } @@ -111,7 +111,7 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2, static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest) { - xrecord_t **recs; + xrecord_t *recs; int size = 0; recs = (use_orig ? xe->xdf1.recs : xe->xdf2.recs) + i; @@ -119,12 +119,12 @@ 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 += recs[i++].size) if (dest) - memcpy(dest + size, recs[i]->ptr, recs[i]->size); + memcpy(dest + size, recs[i].ptr, recs[i].size); if (add_nl) { - i = recs[count - 1]->size; - if (i == 0 || recs[count - 1]->ptr[i - 1] != '\n') { + i = recs[count - 1].size; + if (i == 0 || recs[count - 1].ptr[i - 1] != '\n') { if (needs_cr) { if (dest) dest[size] = '\r'; @@ -160,22 +160,22 @@ static int is_eol_crlf(xdfile_t *file, int i) if (i < 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'; + return (size = file->recs[i].size) > 1 && + file->recs[i].ptr[size - 2] == '\r'; if (!file->nrec) /* Cannot determine eol style from empty file */ return -1; - if ((size = file->recs[i]->size) && - file->recs[i]->ptr[size - 1] == '\n') + if ((size = file->recs[i].size) && + file->recs[i].ptr[size - 1] == '\n') /* Last line; ends in LF; Is it CR/LF? */ return size > 1 && - file->recs[i]->ptr[size - 2] == '\r'; + file->recs[i].ptr[size - 2] == '\r'; if (!i) /* The only line has no eol */ return -1; /* Determine eol from second-to-last line */ - return (size = file->recs[i - 1]->size) > 1 && - file->recs[i - 1]->ptr[size - 2] == '\r'; + return (size = file->recs[i - 1].size) > 1 && + file->recs[i - 1].ptr[size - 2] == '\r'; } static int is_cr_needed(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m) @@ -334,22 +334,22 @@ static int recmatch(xrecord_t *rec1, xrecord_t *rec2, unsigned long flags) static void xdl_refine_zdiff3_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, xpparam_t const *xpp) { - xrecord_t **rec1 = xe1->xdf2.recs, **rec2 = xe2->xdf2.recs; + xrecord_t *rec1 = xe1->xdf2.recs, *rec2 = xe2->xdf2.recs; for (; m; m = m->next) { /* let's handle just the conflicts */ if (m->mode) continue; while(m->chg1 && m->chg2 && - recmatch(rec1[m->i1], rec2[m->i2], xpp->flags)) { + recmatch(&rec1[m->i1], &rec2[m->i2], xpp->flags)) { m->chg1--; m->chg2--; m->i1++; m->i2++; } while (m->chg1 && m->chg2 && - recmatch(rec1[m->i1 + m->chg1 - 1], - rec2[m->i2 + m->chg2 - 1], xpp->flags)) { + recmatch(&rec1[m->i1 + m->chg1 - 1], + &rec2[m->i2 + m->chg2 - 1], xpp->flags)) { m->chg1--; m->chg2--; } @@ -381,12 +381,12 @@ static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, * This probably does not work outside git, since * 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 - + 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 - + xe2->xdf2.recs[m->i2 + m->chg2 - 1]->size - t2.ptr; + t1.ptr = (char *)xe1->xdf2.recs[m->i1].ptr; + t1.size = 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 + + xe2->xdf2.recs[m->i2 + m->chg2 - 1].size - t2.ptr; if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0) return -1; if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 || @@ -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(xe->xdf2.recs[i].ptr, + xe->xdf2.recs[i].size)) return 1; return 0; } diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c index 77dc411d19..669b653580 100644 --- a/xdiff/xpatience.c +++ b/xdiff/xpatience.c @@ -88,9 +88,9 @@ static int is_anchor(xpparam_t const *xpp, const char *line) static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, int pass) { - xrecord_t **records = pass == 1 ? + xrecord_t *records = pass == 1 ? map->env->xdf1.recs : map->env->xdf2.recs; - xrecord_t *record = records[line - 1]; + xrecord_t *record = &records[line - 1]; /* * After xdl_prepare_env() (or more precisely, due to * xdl_classify_record()), the "ha" member of the records (AKA lines) @@ -121,7 +121,7 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, 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].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1].ptr); if (!map->first) map->first = map->entries + index; if (map->last) { @@ -246,8 +246,8 @@ static int find_longest_common_sequence(struct hashmap *map, struct entry **res) 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]; + xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1]; + xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1]; return record1->ha == record2->ha; } @@ -331,11 +331,11 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env, /* trivial case: one side is empty */ if (!count1) { while(count2--) - env->xdf2.rchg[line2++ - 1] = 1; + env->xdf2.changed[line2++ - 1] = true; return 0; } else if (!count2) { while(count1--) - env->xdf1.rchg[line1++ - 1] = 1; + env->xdf1.changed[line1++ - 1] = true; return 0; } @@ -347,9 +347,9 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env, /* are there any matching lines at all? */ if (!map.has_matches) { while(count1--) - env->xdf1.rchg[line1++ - 1] = 1; + env->xdf1.changed[line1++ - 1] = true; while(count2--) - env->xdf2.rchg[line2++ - 1] = 1; + env->xdf2.changed[line2++ - 1] = true; xdl_free(map.entries); return 0; } diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index e1d4017b2d..192334f1b7 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -29,12 +29,13 @@ #define XDL_GUESS_NLINES1 256 #define XDL_GUESS_NLINES2 20 +#define DISCARD 0 +#define KEEP 1 +#define INVESTIGATE 2 typedef struct s_xdlclass { struct s_xdlclass *next; - unsigned long ha; - char const *line; - long size; + xrecord_t rec; long idx; long len1, len2; } xdlclass_t; @@ -53,21 +54,6 @@ typedef struct s_xdlclassifier { -static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags); -static void xdl_free_classifier(xdlclassifier_t *cf); -static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, - unsigned int hbits, xrecord_t *rec); -static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, - xdlclassifier_t *cf, xdfile_t *xdf); -static void xdl_free_ctx(xdfile_t *xdf); -static int xdl_clean_mmatch(char const *dis, long i, long s, long e); -static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); -static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2); -static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); - - - - static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { cf->flags = flags; @@ -106,17 +92,14 @@ static void xdl_free_classifier(xdlclassifier_t *cf) { } -static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, - unsigned int hbits, xrecord_t *rec) { +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) { long hi; - char const *line; xdlclass_t *rcrec; - line = rec->ptr; hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) - if (rcrec->ha == rec->ha && - xdl_recmatch(rcrec->line, rcrec->size, + if (rcrec->rec.ha == rec->ha && + xdl_recmatch(rcrec->rec.ptr, rcrec->rec.size, rec->ptr, rec->size, cf->flags)) break; @@ -129,9 +112,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t if (XDL_ALLOC_GROW(cf->rcrecs, cf->count, cf->alloc)) return -1; cf->rcrecs[rcrec->idx] = rcrec; - rcrec->line = line; - rcrec->size = rec->size; - rcrec->ha = rec->ha; + rcrec->rec = *rec; rcrec->len1 = rcrec->len2 = 0; rcrec->next = cf->rchash[hi]; cf->rchash[hi] = rcrec; @@ -141,158 +122,70 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t rec->ha = (unsigned long) rcrec->idx; - hi = (long) XDL_HASHLONG(rec->ha, hbits); - rec->next = rhash[hi]; - rhash[hi] = rec; - return 0; } +static void xdl_free_ctx(xdfile_t *xdf) +{ + xdl_free(xdf->rindex); + xdl_free(xdf->changed - 1); + xdl_free(xdf->recs); +} + + static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf) { - unsigned int hbits; - long nrec, hsize, bsize; + long bsize; unsigned long hav; char const *blk, *cur, *top, *prev; xrecord_t *crec; - xrecord_t **recs; - xrecord_t **rhash; - unsigned long *ha; - char *rchg; - long *rindex; - - ha = NULL; - rindex = NULL; - rchg = NULL; - rhash = NULL; - recs = NULL; - - if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) - goto abort; - if (!XDL_ALLOC_ARRAY(recs, narec)) - goto abort; - hbits = xdl_hashbits((unsigned int) narec); - hsize = 1 << hbits; - if (!XDL_CALLOC_ARRAY(rhash, hsize)) + xdf->rindex = NULL; + xdf->changed = NULL; + xdf->recs = NULL; + + if (!XDL_ALLOC_ARRAY(xdf->recs, narec)) goto abort; - nrec = 0; + xdf->nrec = 0; if ((cur = blk = xdl_mmfile_first(mf, &bsize))) { for (top = blk + bsize; cur < top; ) { prev = cur; hav = xdl_hash_record(&cur, top, xpp->flags); - if (XDL_ALLOC_GROW(recs, nrec + 1, narec)) - goto abort; - if (!(crec = xdl_cha_alloc(&xdf->rcha))) + if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec)) goto abort; + crec = &xdf->recs[xdf->nrec++]; crec->ptr = prev; crec->size = (long) (cur - prev); crec->ha = hav; - recs[nrec++] = crec; - if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0) + if (xdl_classify_record(pass, cf, crec) < 0) goto abort; } } - if (!XDL_CALLOC_ARRAY(rchg, nrec + 2)) + if (!XDL_CALLOC_ARRAY(xdf->changed, xdf->nrec + 2)) goto abort; if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) { - if (!XDL_ALLOC_ARRAY(rindex, nrec + 1)) - goto abort; - if (!XDL_ALLOC_ARRAY(ha, nrec + 1)) + if (!XDL_ALLOC_ARRAY(xdf->rindex, xdf->nrec + 1)) goto abort; } - xdf->nrec = nrec; - xdf->recs = recs; - xdf->hbits = hbits; - xdf->rhash = rhash; - xdf->rchg = rchg + 1; - xdf->rindex = rindex; + xdf->changed += 1; xdf->nreff = 0; - xdf->ha = ha; xdf->dstart = 0; - xdf->dend = nrec - 1; + xdf->dend = xdf->nrec - 1; return 0; abort: - xdl_free(ha); - xdl_free(rindex); - xdl_free(rchg); - xdl_free(rhash); - xdl_free(recs); - xdl_cha_free(&xdf->rcha); + xdl_free_ctx(xdf); return -1; } -static void xdl_free_ctx(xdfile_t *xdf) { - - xdl_free(xdf->rhash); - xdl_free(xdf->rindex); - xdl_free(xdf->rchg - 1); - xdl_free(xdf->ha); - xdl_free(xdf->recs); - xdl_cha_free(&xdf->rcha); -} - - -int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, - xdfenv_t *xe) { - long enl1, enl2, sample; - xdlclassifier_t cf; - - memset(&cf, 0, sizeof(cf)); - - /* - * For histogram diff, we can afford a smaller sample size and - * thus a poorer estimate of the number of lines, as the hash - * table (rhash) won't be filled up/grown. The number of lines - * (nrecs) will be updated correctly anyway by - * xdl_prepare_ctx(). - */ - sample = (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF - ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1); - - enl1 = xdl_guess_lines(mf1, sample) + 1; - enl2 = xdl_guess_lines(mf2, sample) + 1; - - if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) - return -1; - - if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { - - xdl_free_classifier(&cf); - return -1; - } - if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { - - xdl_free_ctx(&xe->xdf1); - xdl_free_classifier(&cf); - return -1; - } - - if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && - (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) && - xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) { - - xdl_free_ctx(&xe->xdf2); - xdl_free_ctx(&xe->xdf1); - xdl_free_classifier(&cf); - return -1; - } - - xdl_free_classifier(&cf); - - return 0; -} - - void xdl_free_env(xdfenv_t *xe) { xdl_free_ctx(&xe->xdf2); @@ -300,15 +193,15 @@ void xdl_free_env(xdfenv_t *xe) { } -static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { +static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) { long r, rdis0, rpdis0, rdis1, rpdis1; /* - * Limits the window the is examined during the similar-lines - * scan. The loops below stops when dis[i - r] == 1 (line that - * has no match), but there are corner cases where the loop - * proceed all the way to the extremities by causing huge - * performance penalties in case of big files. + * Limits the window that is examined during the similar-lines + * scan. The loops below stops when action[i - r] == KEEP + * (line that has no match), but there are corner cases where + * the loop proceed all the way to the extremities by causing + * huge performance penalties in case of big files. */ if (i - s > XDL_SIMSCAN_WINDOW) s = i - XDL_SIMSCAN_WINDOW; @@ -317,40 +210,47 @@ static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { /* * Scans the lines before 'i' to find a run of lines that either - * have no match (dis[j] == 0) or have multiple matches (dis[j] > 1). - * Note that we always call this function with dis[i] > 1, so the - * current line (i) is already a multimatch line. + * have no match (action[j] == DISCARD) or have multiple matches + * (action[j] == INVESTIGATE). Note that we always call this + * function with action[i] == INVESTIGATE, so the current line + * (i) is already a multimatch line. */ for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) { - if (!dis[i - r]) + if (action[i - r] == DISCARD) rdis0++; - else if (dis[i - r] == 2) + else if (action[i - r] == INVESTIGATE) rpdis0++; - else + else if (action[i - r] == KEEP) break; + else + BUG("Illegal value for action[i - r]"); } /* - * If the run before the line 'i' found only multimatch lines, we - * return 0 and hence we don't make the current line (i) discarded. - * We want to discard multimatch lines only when they appear in the - * middle of runs with nomatch lines (dis[j] == 0). + * If the run before the line 'i' found only multimatch lines, + * we return false and hence we don't make the current line (i) + * discarded. We want to discard multimatch lines only when + * they appear in the middle of runs with nomatch lines + * (action[j] == DISCARD). */ if (rdis0 == 0) return 0; for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) { - if (!dis[i + r]) + if (action[i + r] == DISCARD) rdis1++; - else if (dis[i + r] == 2) + else if (action[i + r] == INVESTIGATE) rpdis1++; - else + else if (action[i + r] == KEEP) break; + else + BUG("Illegal value for action[i + r]"); } /* - * If the run after the line 'i' found only multimatch lines, we - * return 0 and hence we don't make the current line (i) discarded. + * If the run after the line 'i' found only multimatch lines, + * we return false and hence we don't make the current line (i) + * discarded. */ if (rdis1 == 0) - return 0; + return false; rdis1 += rdis0; rpdis1 += rpdis0; @@ -361,63 +261,81 @@ static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { /* * Try to reduce the problem complexity, discard records that have no * matches on the other file. Also, lines that have multiple matches - * might be potentially discarded if they happear in a run of discardable. + * 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; - xrecord_t **recs; + xrecord_t *recs; xdlclass_t *rcrec; - char *dis, *dis1, *dis2; - int need_min = !!(cf->flags & XDF_NEED_MINIMAL); + uint8_t *action1 = NULL, *action2 = NULL; + bool need_min = !!(cf->flags & XDF_NEED_MINIMAL); + int ret = 0; - if (!XDL_CALLOC_ARRAY(dis, xdf1->nrec + xdf2->nrec + 2)) - return -1; - dis1 = dis; - dis2 = dis1 + xdf1->nrec + 1; + /* + * Create temporary arrays that will help us decide if + * changed[i] should remain false, or become true. + */ + if (!XDL_CALLOC_ARRAY(action1, xdf1->nrec + 1)) { + ret = -1; + goto cleanup; + } + if (!XDL_CALLOC_ARRAY(action2, xdf2->nrec + 1)) { + ret = -1; + goto cleanup; + } + /* + * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE. + */ if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { - rcrec = cf->rcrecs[(*recs)->ha]; + rcrec = cf->rcrecs[recs->ha]; nm = rcrec ? rcrec->len2 : 0; - dis1[i] = (nm == 0) ? 0: (nm >= mlim && !need_min) ? 2: 1; + action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; } if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT) mlim = XDL_MAX_EQLIMIT; for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { - rcrec = cf->rcrecs[(*recs)->ha]; + rcrec = cf->rcrecs[recs->ha]; nm = rcrec ? rcrec->len1 : 0; - dis2[i] = (nm == 0) ? 0: (nm >= mlim && !need_min) ? 2: 1; + action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; } + /* + * 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]; i <= xdf1->dend; i++, recs++) { - if (dis1[i] == 1 || - (dis1[i] == 2 && !xdl_clean_mmatch(dis1, i, xdf1->dstart, xdf1->dend))) { - xdf1->rindex[nreff] = i; - xdf1->ha[nreff] = (*recs)->ha; - nreff++; + if (action1[i] == KEEP || + (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))) { + xdf1->rindex[nreff++] = i; + /* changed[i] remains false, i.e. keep */ } else - xdf1->rchg[i] = 1; + xdf1->changed[i] = true; + /* i.e. discard */ } xdf1->nreff = nreff; for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { - if (dis2[i] == 1 || - (dis2[i] == 2 && !xdl_clean_mmatch(dis2, i, xdf2->dstart, xdf2->dend))) { - xdf2->rindex[nreff] = i; - xdf2->ha[nreff] = (*recs)->ha; - nreff++; + if (action2[i] == KEEP || + (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))) { + xdf2->rindex[nreff++] = i; + /* changed[i] remains false, i.e. keep */ } else - xdf2->rchg[i] = 1; + xdf2->changed[i] = true; + /* i.e. discard */ } xdf2->nreff = nreff; - xdl_free(dis); +cleanup: + xdl_free(action1); + xdl_free(action2); - return 0; + return ret; } @@ -426,13 +344,13 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd */ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { long i, lim; - xrecord_t **recs1, **recs2; + xrecord_t *recs1, *recs2; recs1 = xdf1->recs; recs2 = xdf2->recs; for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim; i++, recs1++, recs2++) - if ((*recs1)->ha != (*recs2)->ha) + if (recs1->ha != recs2->ha) break; xdf1->dstart = xdf2->dstart = i; @@ -440,7 +358,7 @@ 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->ha != recs2->ha) break; xdf1->dend = xdf1->nrec - i - 1; @@ -460,3 +378,53 @@ static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2 return 0; } + +int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, + xdfenv_t *xe) { + long enl1, enl2, sample; + xdlclassifier_t cf; + + memset(&cf, 0, sizeof(cf)); + + /* + * For histogram diff, we can afford a smaller sample size and + * thus a poorer estimate of the number of lines, as the hash + * table (rhash) won't be filled up/grown. The number of lines + * (nrecs) will be updated correctly anyway by + * xdl_prepare_ctx(). + */ + sample = (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF + ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1); + + enl1 = xdl_guess_lines(mf1, sample) + 1; + enl2 = xdl_guess_lines(mf2, sample) + 1; + + if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) + return -1; + + if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { + + xdl_free_classifier(&cf); + return -1; + } + if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { + + xdl_free_ctx(&xe->xdf1); + xdl_free_classifier(&cf); + return -1; + } + + if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && + (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) && + xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) { + + xdl_free_ctx(&xe->xdf2); + xdl_free_ctx(&xe->xdf1); + xdl_free_classifier(&cf); + return -1; + } + + xdl_free_classifier(&cf); + + return 0; +} diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h index 8442bd436e..f145abba3e 100644 --- a/xdiff/xtypes.h +++ b/xdiff/xtypes.h @@ -39,23 +39,18 @@ typedef struct s_chastore { } chastore_t; typedef struct s_xrecord { - struct s_xrecord *next; char const *ptr; long size; unsigned long ha; } xrecord_t; typedef struct s_xdfile { - chastore_t rcha; + xrecord_t *recs; long nrec; - unsigned int hbits; - xrecord_t **rhash; long dstart, dend; - xrecord_t **recs; - char *rchg; + bool *changed; long *rindex; long nreff; - unsigned long *ha; } xdfile_t; typedef struct s_xdfenv { diff --git a/xdiff/xutils.c b/xdiff/xutils.c index 78d1cf74b1..447e66c719 100644 --- a/xdiff/xutils.c +++ b/xdiff/xutils.c @@ -464,17 +464,17 @@ int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp, mmfile_t subfile1, subfile2; xdfenv_t env; - subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr; - subfile1.size = 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 + - diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr; + subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1].ptr; + subfile1.size = 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 + + diff_env->xdf2.recs[line2 + count2 - 2].size - subfile2.ptr; if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0) return -1; - memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1); - memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2); + memcpy(diff_env->xdf1.changed + line1 - 1, env.xdf1.changed, count1); + memcpy(diff_env->xdf2.changed + line2 - 1, env.xdf2.changed, count2); xdl_free_env(&env); |