diff options
83 files changed, 3824 insertions, 1608 deletions
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 3622fec742..cc54824c38 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -458,6 +458,21 @@ jobs: - run: ci/install-dependencies.sh - run: ci/run-static-analysis.sh - run: ci/check-directional-formatting.bash + rust-analysis: + needs: ci-config + if: needs.ci-config.outputs.enabled == 'yes' + env: + jobname: RustAnalysis + CI_JOB_IMAGE: ubuntu:rolling + runs-on: ubuntu-latest + container: ubuntu:rolling + concurrency: + group: rust-analysis-${{ github.ref }} + cancel-in-progress: ${{ needs.ci-config.outputs.skip_concurrent == 'yes' }} + steps: + - uses: actions/checkout@v4 + - run: ci/install-dependencies.sh + - run: ci/run-rust-checks.sh sparse: needs: ci-config if: needs.ci-config.outputs.enabled == 'yes' diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index f7d57d1ee9..b419a84e2c 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -161,7 +161,7 @@ test:mingw64: - saas-windows-medium-amd64 before_script: - *windows_before_script - - choco install -y git meson ninja + - choco install -y git meson ninja rust-ms - Import-Module $env:ChocolateyInstall\helpers\chocolateyProfile.psm1 - refreshenv @@ -212,6 +212,17 @@ static-analysis: - ./ci/run-static-analysis.sh - ./ci/check-directional-formatting.bash +rust-analysis: + image: ubuntu:rolling + stage: analyze + needs: [ ] + variables: + jobname: RustAnalysis + before_script: + - ./ci/install-dependencies.sh + script: + - ./ci/run-rust-checks.sh + check-whitespace: image: ubuntu:latest stage: analyze diff --git a/Cargo.toml b/Cargo.toml index 45c9b34981..2f51bf5d5f 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -2,6 +2,7 @@ name = "gitcore" version = "0.1.0" edition = "2018" +rust-version = "1.49.0" [lib] crate-type = ["staticlib"] diff --git a/Documentation/BreakingChanges.adoc b/Documentation/BreakingChanges.adoc index 90b53abcea..f814450d2f 100644 --- a/Documentation/BreakingChanges.adoc +++ b/Documentation/BreakingChanges.adoc @@ -295,6 +295,26 @@ The command will be removed. + cf. <xmqqa59i45wc.fsf@gitster.g> +* Support for `core.preferSymlinkRefs=true` has been deprecated and will be + removed in Git 3.0. Writing symbolic refs as symbolic links will be phased + out in favor of using plain files using the textual representation of + symbolic refs. ++ +Symbolic references were initially always stored as a symbolic link. This was +changed in 9b143c6e15 (Teach update-ref about a symbolic ref stored in a +textfile., 2005-09-25), where a new textual symref format was introduced to +store those symbolic refs in a plain file. In 9f0bb90d16 +(core.prefersymlinkrefs: use symlinks for .git/HEAD, 2006-05-02), the Git +project switched the default to use the textual symrefs in favor of symbolic +links. ++ +The migration away from symbolic links has happened almost 20 years ago by now, +and there is no known reason why one should prefer them nowadays. Furthermore, +symbolic links are not supported on some platforms. ++ +Note that only the writing side for such symbolic links is deprecated. Reading +such symbolic links is still supported for now. + == Superseded features that will not be deprecated Some features have gained newer replacements that aim to improve the design in diff --git a/Documentation/RelNotes/2.52.0.adoc b/Documentation/RelNotes/2.52.0.adoc index 61211dbe82..ba213c0d6c 100644 --- a/Documentation/RelNotes/2.52.0.adoc +++ b/Documentation/RelNotes/2.52.0.adoc @@ -57,6 +57,23 @@ UI, Workflows & Features * Show 'P'ipe command in "git add -p". + * "git sparse-checkout" subcommand learned a new "clean" action to + prune otherwise unused working-tree files that are outside the + areas of interest. + + * "git fast-import" is taught to handle signed tags, just like it + recently learned to handle signed commits, in different ways. + + * A new configuration variable commitGraph.changedPaths allows to + turn "--changed-paths" on by default for "git commit-graph". + + * "Symlink symref" has been added to the list of things that will + disappear at Git 3.0 boundary. + + * "git maintenance" command learns the "geometric" strategy where it + avoids doing maintenance tasks that rebuilds everything from + scratch. + Performance, Internal Implementation, Development Support etc. -------------------------------------------------------------- @@ -137,6 +154,17 @@ Performance, Internal Implementation, Development Support etc. * Build procedure for a few credential helpers (in contrib/) have been updated. + * CI improvements to handle the recent Rust integration better. + + * The code in "git repack" machinery has been cleaned up to prepare + for incremental update of midx files. + + * Two slightly different ways to get at "all the packfiles" in API + has been cleaned up. + + * The code to walk revision graph to compute merge base has been + optimized. + Fixes since v2.51 ----------------- @@ -347,6 +375,28 @@ including security updates, are included in this release. fail doe to overly long pathname in our test environment, which has been worked around by using "ssh-agent -T". + * strbuf_split*() to split a string into multiple strbufs is often a + wrong API to use. A few uses of it have been removed by + simplifying the code. + (merge 2ab72a16d9 ob/gpg-interface-cleanup later to maint). + + * "git shortlog" knows "--committer" and "--author" options, which + the command line completion (in contrib/) did not handle well, + which has been corrected. + (merge c568fa8e1c kf/log-shortlog-completion-fix later to maint). + + * "git bisect" command did not react correctly to "git bisect help" + and "git bisect unknown", which has been corrected. + (merge 2bb3a012f3 rz/bisect-help-unknown later to maint). + + * The 'q'(uit) command in "git add -p" has been improved to quit + without doing any meaningless work before leaving, and giving EOF + (typically control-D) to the prompt is made to behave the same way. + + * The wildmatch code had a corner case bug that mistakenly makes + "foo**/bar" match with "foobar", which has been corrected. + (merge 1940a02dc1 jk/match-pathname-fix later to maint). + * Other code cleanup, docfix, build fix, etc. (merge 529a60a885 ua/t1517-short-help-tests later to maint). (merge 22d421fed9 ac/deglobal-fmt-merge-log-config later to maint). @@ -358,3 +408,4 @@ including security updates, are included in this release. (merge a66fc22bf9 rs/get-oid-with-flags-cleanup later to maint). (merge 15b8abde07 js/mingw-includes-cleanup later to maint). (merge 2cebca0582 tb/cat-file-objectmode-update later to maint). + (merge 8f487db07a kh/doc-patch-id-1 later to maint). diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index d620bd93bd..e270ccbe85 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -446,6 +446,34 @@ highlighted above. Only capitalize the very first letter of the trailer, i.e. favor "Signed-off-by" over "Signed-Off-By" and "Acked-by:" over "Acked-By". +[[ai]] +=== Use of Artificial Intelligence (AI) + +The Developer's Certificate of Origin requires contributors to certify +that they know the origin of their contributions to the project and +that they have the right to submit it under the project's license. +It's not yet clear that this can be legally satisfied when submitting +significant amount of content that has been generated by AI tools. + +Another issue with AI generated content is that AIs still often +hallucinate or just produce bad code, commit messages, documentation +or output, even when you point out their mistakes. + +To avoid these issues, we will reject anything that looks AI +generated, that sounds overly formal or bloated, that looks like AI +slop, that looks good on the surface but makes no sense, or that +senders don’t understand or cannot explain. + +We strongly recommend using AI tools carefully and responsibly. + +Contributors would often benefit more from AI by using it to guide and +help them step by step towards producing a solution by themselves +rather than by asking for a full solution that they would then mostly +copy-paste. They can also use AI to help with debugging, or with +checking for obvious mistakes, things that can be improved, things +that don’t match our style, guidelines or our feedback, before sending +it to us. + [[git-tools]] === Generate your patch using Git tools out of your commits. diff --git a/Documentation/config/commitgraph.adoc b/Documentation/config/commitgraph.adoc index 7f8c9d6638..70a56c53d2 100644 --- a/Documentation/config/commitgraph.adoc +++ b/Documentation/config/commitgraph.adoc @@ -8,6 +8,17 @@ commitGraph.maxNewFilters:: Specifies the default value for the `--max-new-filters` option of `git commit-graph write` (c.f., linkgit:git-commit-graph[1]). +commitGraph.changedPaths:: + If true, then `git commit-graph write` will compute and write + changed-path Bloom filters by default, equivalent to passing + `--changed-paths`. If false or unset, changed-paths Bloom filters will + be written during `git commit-graph write` only if the filters already + exist in the current commit-graph file. This matches the default + behavior of `git commit-graph write` without any `--[no-]changed-paths` + option. To rewrite a commit-graph file without any filters, use the + `--no-changed-paths` option. Command-line option `--[no-]changed-paths` + always takes precedence over this configuration. Defaults to unset. + commitGraph.readChangedPaths:: Deprecated. Equivalent to commitGraph.changedPathsVersion=-1 if true, and commitGraph.changedPathsVersion=0 if false. (If commitGraph.changedPathVersion diff --git a/Documentation/config/core.adoc b/Documentation/config/core.adoc index e2de270c86..11efad189e 100644 --- a/Documentation/config/core.adoc +++ b/Documentation/config/core.adoc @@ -290,6 +290,9 @@ core.preferSymlinkRefs:: and other symbolic reference files, use symbolic links. This is sometimes needed to work with old scripts that expect HEAD to be a symbolic link. ++ +This configuration is deprecated and will be removed in Git 3.0. Symbolic refs +will always be written as textual symrefs. core.alternateRefsCommand:: When advertising tips of available history from an alternate, use the shell to diff --git a/Documentation/config/maintenance.adoc b/Documentation/config/maintenance.adoc index 2f71934218..d0c38f03fa 100644 --- a/Documentation/config/maintenance.adoc +++ b/Documentation/config/maintenance.adoc @@ -16,19 +16,36 @@ detach. maintenance.strategy:: This string config option provides a way to specify one of a few - recommended schedules for background maintenance. This only affects - which tasks are run during `git maintenance run --schedule=X` - commands, provided no `--task=<task>` arguments are provided. - Further, if a `maintenance.<task>.schedule` config value is set, - then that value is used instead of the one provided by - `maintenance.strategy`. The possible strategy strings are: + recommended strategies for repository maintenance. This affects + which tasks are run during `git maintenance run`, provided no + `--task=<task>` arguments are provided. This setting impacts manual + maintenance, auto-maintenance as well as scheduled maintenance. The + tasks that run may be different depending on the maintenance type. + -* `none`: This default setting implies no tasks are run at any schedule. +The maintenance strategy can be further tweaked by setting +`maintenance.<task>.enabled` and `maintenance.<task>.schedule`. If set, these +values are used instead of the defaults provided by `maintenance.strategy`. ++ +The possible strategies are: ++ +* `none`: This strategy implies no tasks are run at all. This is the default + strategy for scheduled maintenance. +* `gc`: This strategy runs the `gc` task. This is the default strategy for + manual maintenance. +* `geometric`: This strategy performs geometric repacking of packfiles and + keeps auxiliary data structures up-to-date. The strategy expires data in the + reflog and removes worktrees that cannot be located anymore. When the + geometric repacking strategy would decide to do an all-into-one repack, then + the strategy generates a cruft pack for all unreachable objects. Objects that + are already part of a cruft pack will be expired. ++ +This repacking strategy is a full replacement for the `gc` strategy and is +recommended for large repositories. * `incremental`: This setting optimizes for performing small maintenance activities that do not delete any data. This does not schedule the `gc` task, but runs the `prefetch` and `commit-graph` tasks hourly, the `loose-objects` and `incremental-repack` tasks daily, and the `pack-refs` - task weekly. + task weekly. Manual repository maintenance uses the `gc` task. maintenance.<task>.enabled:: This boolean config option controls whether the maintenance task @@ -75,6 +92,22 @@ maintenance.incremental-repack.auto:: number of pack-files not in the multi-pack-index is at least the value of `maintenance.incremental-repack.auto`. The default value is 10. +maintenance.geometric-repack.auto:: + This integer config option controls how often the `geometric-repack` + task should be run as part of `git maintenance run --auto`. If zero, + then the `geometric-repack` task will not run with the `--auto` + option. A negative value will force the task to run every time. + Otherwise, a positive value implies the command should run either when + there are packfiles that need to be merged together to retain the + geometric progression, or when there are at least this many loose + objects that would be written into a new packfile. The default value is + 100. + +maintenance.geometric-repack.splitFactor:: + This integer config option controls the factor used for the geometric + sequence. See the `--geometric=` option in linkgit:git-repack[1] for + more details. Defaults to `2`. + maintenance.reflog-expire.auto:: This integer config option controls how often the `reflog-expire` task should be run as part of `git maintenance run --auto`. If zero, then diff --git a/Documentation/git-commit-graph.adoc b/Documentation/git-commit-graph.adoc index e9558173c0..6d19026035 100644 --- a/Documentation/git-commit-graph.adoc +++ b/Documentation/git-commit-graph.adoc @@ -71,7 +71,7 @@ take a while on large repositories. It provides significant performance gains for getting history of a directory or a file with `git log -- <path>`. If this option is given, future commit-graph writes will automatically assume that this option was intended. Use `--no-changed-paths` to stop storing this -data. +data. `--changed-paths` is implied by config `commitGraph.changedPaths=true`. + With the `--max-new-filters=<n>` option, generate at most `n` new Bloom filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is diff --git a/Documentation/git-fast-import.adoc b/Documentation/git-fast-import.adoc index 85ed7a7270..b74179a6c8 100644 --- a/Documentation/git-fast-import.adoc +++ b/Documentation/git-fast-import.adoc @@ -66,6 +66,11 @@ fast-import stream! This option is enabled automatically for remote-helpers that use the `import` capability, as they are already trusted to run their own code. +--signed-tags=(verbatim|warn-verbatim|warn-strip|strip|abort):: + Specify how to handle signed tags. Behaves in the same way + as the same option in linkgit:git-fast-export[1], except that + default is 'verbatim' (instead of 'abort'). + --signed-commits=(verbatim|warn-verbatim|warn-strip|strip|abort):: Specify how to handle signed commits. Behaves in the same way as the same option in linkgit:git-fast-export[1], except that diff --git a/Documentation/git-patch-id.adoc b/Documentation/git-patch-id.adoc index 45da0f27ac..92a1af36a2 100644 --- a/Documentation/git-patch-id.adoc +++ b/Documentation/git-patch-id.adoc @@ -7,8 +7,8 @@ git-patch-id - Compute unique ID for a patch SYNOPSIS -------- -[verse] -'git patch-id' [--stable | --unstable | --verbatim] +[synopsis] +git patch-id [--stable | --unstable | --verbatim] DESCRIPTION ----------- @@ -21,7 +21,7 @@ the same time also reasonably unique, i.e., two patches that have the same The main usecase for this command is to look for likely duplicate commits. -When dealing with 'git diff-tree' output, it takes advantage of +When dealing with `git diff-tree` output, it takes advantage of the fact that the patch is prefixed with the object name of the commit, and outputs two 40-byte hexadecimal strings. The first string is the patch ID, and the second string is the commit ID. @@ -30,35 +30,35 @@ This can be used to make a mapping from patch ID to commit ID. OPTIONS ------- ---verbatim:: +`--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:: +`--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 + 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 + 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 + 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. +This is the default if `patchid.stable` is set to `true`. ---unstable:: +`--unstable`:: Use an "unstable" hash as the patch ID. With this option, the result produced is compatible with the patch-id value produced by git 1.9 and older and whitespace is ignored. Users with pre-existing diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc index 209afd1b61..ce43cb19c8 100644 --- a/Documentation/git-repo.adoc +++ b/Documentation/git-repo.adoc @@ -9,6 +9,7 @@ SYNOPSIS -------- [synopsis] git repo info [--format=(keyvalue|nul)] [-z] [<key>...] +git repo structure [--format=(table|keyvalue|nul)] DESCRIPTION ----------- @@ -43,6 +44,35 @@ supported: + `-z` is an alias for `--format=nul`. +`structure [--format=(table|keyvalue|nul)]`:: + Retrieve statistics about the current repository structure. The + following kinds of information are reported: ++ +* Reference counts categorized by type +* Reachable object counts categorized by type + ++ +The output format can be chosen through the flag `--format`. Three formats are +supported: ++ +`table`::: + Outputs repository stats in a human-friendly table. This format may + change and is not intended for machine parsing. This is the default + format. + +`keyvalue`::: + Each line of output contains a key-value pair for a repository stat. + The '=' character is used to delimit between the key and the value. + Values containing "unusual" characters are quoted as explained for the + configuration variable `core.quotePath` (see linkgit:git-config[1]). + +`nul`::: + Similar to `keyvalue`, but uses a NUL character to delimit between + key-value pairs instead of a newline. Also uses a newline character as + the delimiter between the key and value instead of '='. Unlike the + `keyvalue` format, values containing "unusual" characters are never + quoted. + INFO KEYS --------- In order to obtain a set of values from `git repo info`, you should provide diff --git a/Documentation/git-sparse-checkout.adoc b/Documentation/git-sparse-checkout.adoc index b5fe5da041..0d1618f161 100644 --- a/Documentation/git-sparse-checkout.adoc +++ b/Documentation/git-sparse-checkout.adoc @@ -9,7 +9,7 @@ git-sparse-checkout - Reduce your working tree to a subset of tracked files SYNOPSIS -------- [verse] -'git sparse-checkout' (init | list | set | add | reapply | disable | check-rules) [<options>] +'git sparse-checkout' (init | list | set | add | reapply | disable | check-rules | clean) [<options>] DESCRIPTION @@ -111,6 +111,37 @@ flags, with the same meaning as the flags from the `set` command, in order to change which sparsity mode you are using without needing to also respecify all sparsity paths. +'clean':: + Opportunistically remove files outside of the sparse-checkout + definition. This command requires cone mode to use recursive + directory matches to determine which files should be removed. A + file is considered for removal if it is contained within a tracked + directory that is outside of the sparse-checkout definition. ++ +Some special cases, such as merge conflicts or modified files outside of +the sparse-checkout definition could lead to keeping files that would +otherwise be removed. Resolve conflicts, stage modifications, and use +`git sparse-checkout reapply` in conjunction with `git sparse-checkout +clean` to resolve these cases. ++ +This command can be used to be sure the sparse index works efficiently, +though it does not require enabling the sparse index feature via the +`index.sparse=true` configuration. ++ +To prevent accidental deletion of worktree files, the `clean` subcommand +will not delete any files without the `-f` or `--force` option, unless +the `clean.requireForce` config option is set to `false`. ++ +The `--dry-run` option will list the directories that would be removed +without deleting them. Running in this mode can be helpful to predict the +behavior of the clean comand or to determine which kinds of files are left +in the sparse directories. ++ +The `--verbose` option will list every file within the directories that +are considered for removal. This option is helpful to determine if those +files are actually important or perhaps to explain why the directory is +still present despite the current sparse-checkout. + 'disable':: Disable the `core.sparseCheckout` config setting, and restore the working directory to include all files. diff --git a/Documentation/git-tag.adoc b/Documentation/git-tag.adoc index 0f7badc116..cea3202fdb 100644 --- a/Documentation/git-tag.adoc +++ b/Documentation/git-tag.adoc @@ -3,7 +3,7 @@ git-tag(1) NAME ---- -git-tag - Create, list, delete or verify a tag object signed with GPG +git-tag - Create, list, delete or verify tags SYNOPSIS @@ -38,15 +38,17 @@ and `-a`, `-s`, and `-u <key-id>` are absent, `-a` is implied. Otherwise, a tag reference that points directly at the given object (i.e., a lightweight tag) is created. -A GnuPG signed tag object will be created when `-s` or `-u -<key-id>` is used. When `-u <key-id>` is not used, the -committer identity for the current user is used to find the -GnuPG key for signing. The configuration variable `gpg.program` -is used to specify custom GnuPG binary. +A cryptographically signed tag object will be created when `-s` or +`-u <key-id>` is used. The signing backend (GPG, X.509, SSH, etc.) is +controlled by the `gpg.format` configuration variable, defaulting to +OpenPGP. When `-u <key-id>` is not used, the committer identity for +the current user is used to find the key for signing. The +configuration variable `gpg.program` is used to specify a custom +signing binary. Tag objects (created with `-a`, `-s`, or `-u`) are called "annotated" tags; they contain a creation date, the tagger name and e-mail, a -tagging message, and an optional GnuPG signature. Whereas a +tagging message, and an optional cryptographic signature. Whereas a "lightweight" tag is simply a name for an object (usually a commit object). @@ -64,10 +66,12 @@ OPTIONS `-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]. + Make a cryptographically signed tag, using the default signing + key. The signing backend used depends on the `gpg.format` + configuration variable. The default key is determined by the + backend. For GPG, it's based on the committer's email address, + while for SSH it may be a specific key file or agent + identity. See linkgit:git-config[1]. `--no-sign`:: Override `tag.gpgSign` configuration variable that is @@ -75,7 +79,10 @@ OPTIONS `-u <key-id>`:: `--local-user=<key-id>`:: - Make a GPG-signed tag, using the given key. + Make a cryptographically signed tag using the given key. The + format of the <key-id> and the backend used depend on the + `gpg.format` configuration variable. See + linkgit:git-config[1]. `-f`:: `--force`:: @@ -87,7 +94,7 @@ OPTIONS `-v`:: `--verify`:: - Verify the GPG signature of the given tag names. + Verify the cryptographic signature of the given tags. `-n<num>`:: _<num>_ specifies how many lines from the annotation, if any, @@ -235,12 +242,23 @@ it in the repository configuration as follows: ------------------------------------- [user] - signingKey = <gpg-key-id> + signingKey = <key-id> ------------------------------------- +The signing backend can be chosen via the `gpg.format` configuration +variable, which defaults to `openpgp`. See linkgit:git-config[1] +for a list of other supported formats. + +The path to the program used for each signing backend can be specified +with the `gpg.<format>.program` configuration variable. For the +`openpgp` backend, `gpg.program` can be used as a synonym for +`gpg.openpgp.program`. See linkgit:git-config[1] for details. + `pager.tag` is only respected when listing tags, i.e., when `-l` is used or implied. The default is to use a pager. -See linkgit:git-config[1]. + +See linkgit:git-config[1] for more details and other configuration +variables. DISCUSSION ---------- diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index b16db85e77..c43f33d889 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,6 +1,6 @@ #!/bin/sh -DEF_VER=v2.51.GIT +DEF_VER=v2.52.0-rc0 LF=' ' @@ -927,10 +927,17 @@ export PYTHON_PATH TEST_SHELL_PATH = $(SHELL_PATH) LIB_FILE = libgit.a + ifdef DEBUG -RUST_LIB = target/debug/libgitcore.a +RUST_TARGET_DIR = target/debug else -RUST_LIB = target/release/libgitcore.a +RUST_TARGET_DIR = target/release +endif + +ifeq ($(uname_S),Windows) +RUST_LIB = $(RUST_TARGET_DIR)/gitcore.lib +else +RUST_LIB = $(RUST_TARGET_DIR)/libgitcore.a endif GITLIBS = common-main.o $(LIB_FILE) @@ -1260,6 +1267,12 @@ LIB_OBJS += reftable/table.o LIB_OBJS += reftable/tree.o LIB_OBJS += reftable/writer.o LIB_OBJS += remote.o +LIB_OBJS += repack.o +LIB_OBJS += repack-cruft.o +LIB_OBJS += repack-filtered.o +LIB_OBJS += repack-geometry.o +LIB_OBJS += repack-midx.o +LIB_OBJS += repack-promisor.o LIB_OBJS += replace-object.o LIB_OBJS += repo-settings.o LIB_OBJS += repository.o @@ -1556,6 +1569,9 @@ ALL_LDFLAGS = $(LDFLAGS) $(LDFLAGS_APPEND) ifdef WITH_RUST BASIC_CFLAGS += -DWITH_RUST GITLIBS += $(RUST_LIB) +ifeq ($(uname_S),Windows) +EXTLIBS += -luserenv +endif endif ifdef SANITIZE diff --git a/add-patch.c b/add-patch.c index ae9a20d8f2..173a53241e 100644 --- a/add-patch.c +++ b/add-patch.c @@ -1569,8 +1569,10 @@ static int patch_update_file(struct add_p_state *s, if (*s->s.reset_color_interactive) fputs(s->s.reset_color_interactive, stdout); fflush(stdout); - if (read_single_character(s) == EOF) + if (read_single_character(s) == EOF) { + quit = 1; break; + } if (!s->answer.len) continue; @@ -1601,7 +1603,7 @@ soft_increment: } else if (hunk->use == UNDECIDED_HUNK) { hunk->use = USE_HUNK; } - } else if (ch == 'd' || ch == 'q') { + } else if (ch == 'd') { if (file_diff->hunk_nr) { for (; hunk_index < file_diff->hunk_nr; hunk_index++) { hunk = file_diff->hunk + hunk_index; @@ -1613,10 +1615,9 @@ soft_increment: } else if (hunk->use == UNDECIDED_HUNK) { hunk->use = SKIP_HUNK; } - if (ch == 'q') { - quit = 1; - break; - } + } else if (ch == 'q') { + quit = 1; + break; } else if (s->answer.buf[0] == 'K') { if (permitted & ALLOW_GOTO_PREVIOUS_HUNK) hunk_index = dec_mod(hunk_index, diff --git a/builtin/bisect.c b/builtin/bisect.c index 8b8d870cd1..993caf545d 100644 --- a/builtin/bisect.c +++ b/builtin/bisect.c @@ -1453,9 +1453,13 @@ int cmd_bisect(int argc, if (!argc) usage_msg_opt(_("need a command"), git_bisect_usage, options); + if (!strcmp(argv[0], "help")) + usage_with_options(git_bisect_usage, options); + set_terms(&terms, "bad", "good"); get_terms(&terms); - if (check_and_set_terms(&terms, argv[0])) + if (check_and_set_terms(&terms, argv[0]) || + !one_of(argv[0], terms.term_good, terms.term_bad, NULL)) usage_msg_optf(_("unknown command: '%s'"), git_bisect_usage, options, argv[0]); res = bisect_state(&terms, argc, argv); diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 5ca2ca3852..983ecec837 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -852,10 +852,9 @@ 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 = packfile_store_get_all_packs(packs); pack; pack = pack->next) { + repo_for_each_pack(the_repository, pack) { if (bitmap_index_contains_pack(bitmap, pack) || open_pack_index(pack)) continue; diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index fe3ebaadad..d62005edc0 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -210,6 +210,8 @@ static int git_commit_graph_write_config(const char *var, const char *value, { if (!strcmp(var, "commitgraph.maxnewfilters")) write_opts.max_new_filters = git_config_int(var, value, ctx->kvi); + else if (!strcmp(var, "commitgraph.changedpaths")) + opts.enable_changed_paths = git_config_bool(var, value) ? 1 : -1; /* * No need to fall-back to 'git_default_config', since this was already * called in 'cmd_commit_graph()'. diff --git a/builtin/count-objects.c b/builtin/count-objects.c index f2f407c2a7..18f6e33b6f 100644 --- a/builtin/count-objects.c +++ b/builtin/count-objects.c @@ -122,7 +122,6 @@ 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; @@ -130,7 +129,7 @@ int cmd_count_objects(int argc, struct strbuf pack_buf = STRBUF_INIT; struct strbuf garbage_buf = STRBUF_INIT; - for (p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_local) continue; if (open_pack_index(p)) diff --git a/builtin/fast-export.c b/builtin/fast-export.c index dc2486f9a8..7adbc55f0d 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -931,9 +931,8 @@ static void handle_tag(const char *name, struct tag *tag) /* handle signed tags */ if (message) { - const char *signature = strstr(message, - "\n-----BEGIN PGP SIGNATURE-----\n"); - if (signature) + size_t sig_offset = parse_signed_buffer(message, message_size); + if (sig_offset < message_size) switch (signed_tag_mode) { case SIGN_ABORT: die("encountered signed tag %s; use " @@ -950,7 +949,7 @@ static void handle_tag(const char *name, struct tag *tag) oid_to_hex(&tag->object.oid)); /* fallthru */ case SIGN_STRIP: - message_size = signature + 1 - message; + message_size = sig_offset; break; } } diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 606c6aea82..54d3e592c6 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -188,6 +188,7 @@ static int global_argc; static const char **global_argv; static const char *global_prefix; +static enum sign_mode signed_tag_mode = SIGN_VERBATIM; static enum sign_mode signed_commit_mode = SIGN_VERBATIM; /* Memory pools */ @@ -978,7 +979,7 @@ static int store_object( if (e->idx.offset) { duplicate_count_by_type[type]++; return 1; - } else if (find_oid_pack(&oid, packfile_store_get_all_packs(packs))) { + } else if (find_oid_pack(&oid, packfile_store_get_packs(packs))) { e->type = type; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ @@ -1179,7 +1180,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark) duplicate_count_by_type[OBJ_BLOB]++; truncate_pack(&checkpoint); - } else if (find_oid_pack(&oid, packfile_store_get_all_packs(packs))) { + } else if (find_oid_pack(&oid, packfile_store_get_packs(packs))) { e->type = OBJ_BLOB; e->pack_id = MAX_PACK_ID; e->idx.offset = 1; /* just not zero! */ @@ -2963,6 +2964,43 @@ static void parse_new_commit(const char *arg) b->last_commit = object_count_by_type[OBJ_COMMIT]; } +static void handle_tag_signature(struct strbuf *msg, const char *name) +{ + size_t sig_offset = parse_signed_buffer(msg->buf, msg->len); + + /* If there is no signature, there is nothing to do. */ + if (sig_offset >= msg->len) + return; + + switch (signed_tag_mode) { + + /* First, modes that don't change anything */ + case SIGN_ABORT: + die(_("encountered signed tag; use " + "--signed-tags=<mode> to handle it")); + case SIGN_WARN_VERBATIM: + warning(_("importing a tag signature verbatim for tag '%s'"), name); + /* fallthru */ + case SIGN_VERBATIM: + /* Nothing to do, the signature will be put into the imported tag. */ + break; + + /* Second, modes that remove the signature */ + case SIGN_WARN_STRIP: + warning(_("stripping a tag signature for tag '%s'"), name); + /* fallthru */ + case SIGN_STRIP: + /* Truncate the buffer to remove the signature */ + strbuf_setlen(msg, sig_offset); + break; + + /* Third, BUG */ + default: + BUG("invalid signed_tag_mode value %d from tag '%s'", + signed_tag_mode, name); + } +} + static void parse_new_tag(const char *arg) { static struct strbuf msg = STRBUF_INIT; @@ -3026,6 +3064,8 @@ static void parse_new_tag(const char *arg) /* tag payload/message */ parse_data(&msg, 0, NULL); + handle_tag_signature(&msg, t->name); + /* build the tag object */ strbuf_reset(&new_data); @@ -3546,6 +3586,9 @@ static int parse_one_option(const char *option) } else if (skip_prefix(option, "signed-commits=", &option)) { if (parse_sign_mode(option, &signed_commit_mode)) usagef(_("unknown --signed-commits mode '%s'"), option); + } else if (skip_prefix(option, "signed-tags=", &option)) { + if (parse_sign_mode(option, &signed_tag_mode)) + usagef(_("unknown --signed-tags mode '%s'"), option); } else if (!strcmp(option, "quiet")) { show_stats = 0; quiet = 1; diff --git a/builtin/fsck.c b/builtin/fsck.c index 8ee95e0d67..b1a650c673 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -867,20 +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; + struct packed_git *p; uint32_t pack_count = 0; int res = 0; if (show_progress) { - for (struct packed_git *p = packfile_store_get_all_packs(packs); p; p = p->next) + repo_for_each_pack(r, p) pack_count++; progress = start_delayed_progress(the_repository, "Verifying reverse pack-indexes", pack_count); pack_count = 0; } - for (struct packed_git *p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(r, p) { int load_error = load_pack_revindex_from_disk(p); if (load_error < 0) { @@ -1000,8 +1000,6 @@ 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); @@ -1012,8 +1010,7 @@ int cmd_fsck(int argc, struct progress *progress = NULL; if (show_progress) { - for (p = packfile_store_get_all_packs(packs); p; - p = p->next) { + repo_for_each_pack(the_repository, p) { if (open_pack_index(p)) continue; total += p->num_objects; @@ -1022,8 +1019,8 @@ int cmd_fsck(int argc, progress = start_progress(the_repository, _("Checking objects"), total); } - for (p = packfile_store_get_all_packs(packs); p; - p = p->next) { + + repo_for_each_pack(the_repository, p) { /* verify gives error messages itself */ if (verify_pack(the_repository, p, fsck_obj_buffer, diff --git a/builtin/gc.c b/builtin/gc.c index e19e13d978..d212cbb9b8 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -34,6 +34,7 @@ #include "pack-objects.h" #include "path.h" #include "reflog.h" +#include "repack.h" #include "rerere.h" #include "blob.h" #include "tree.h" @@ -55,7 +56,6 @@ static const char * const builtin_gc_usage[] = { }; static timestamp_t gc_log_expire_time; -static struct strvec repack = STRVEC_INIT; static struct tempfile *pidfile; static struct lock_file log_lock; static struct string_list pack_garbage = STRING_LIST_INIT_DUP; @@ -255,6 +255,7 @@ enum maintenance_task_label { TASK_PREFETCH, TASK_LOOSE_OBJECTS, TASK_INCREMENTAL_REPACK, + TASK_GEOMETRIC_REPACK, TASK_GC, TASK_COMMIT_GRAPH, TASK_PACK_REFS, @@ -448,7 +449,7 @@ out: return should_gc; } -static int too_many_loose_objects(struct gc_config *cfg) +static int too_many_loose_objects(int limit) { /* * Quickly check if a "gc" is needed, by estimating how @@ -470,7 +471,7 @@ static int too_many_loose_objects(struct gc_config *cfg) if (!dir) return 0; - auto_threshold = DIV_ROUND_UP(cfg->gc_auto_threshold, 256); + auto_threshold = DIV_ROUND_UP(limit, 256); while ((ent = readdir(dir)) != NULL) { if (strspn(ent->d_name, "0123456789abcdef") != hexsz_loose || ent->d_name[hexsz_loose] != '\0') @@ -487,10 +488,9 @@ 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 = packfile_store_get_all_packs(packfiles); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_local || p->is_cruft) continue; if (limit) { @@ -509,14 +509,13 @@ 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; + int cnt = 0; if (cfg->gc_auto_pack_limit <= 0) return 0; - for (cnt = 0, p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_local) continue; if (p->pack_keep) @@ -618,48 +617,50 @@ static uint64_t estimate_repack_memory(struct gc_config *cfg, return os_cache + heap; } -static int keep_one_pack(struct string_list_item *item, void *data UNUSED) +static int keep_one_pack(struct string_list_item *item, void *data) { - strvec_pushf(&repack, "--keep-pack=%s", basename(item->string)); + struct strvec *args = data; + strvec_pushf(args, "--keep-pack=%s", basename(item->string)); return 0; } static void add_repack_all_option(struct gc_config *cfg, - struct string_list *keep_pack) + struct string_list *keep_pack, + struct strvec *args) { if (cfg->prune_expire && !strcmp(cfg->prune_expire, "now") && !(cfg->cruft_packs && cfg->repack_expire_to)) - strvec_push(&repack, "-a"); + strvec_push(args, "-a"); else if (cfg->cruft_packs) { - strvec_push(&repack, "--cruft"); + strvec_push(args, "--cruft"); if (cfg->prune_expire) - strvec_pushf(&repack, "--cruft-expiration=%s", cfg->prune_expire); + strvec_pushf(args, "--cruft-expiration=%s", cfg->prune_expire); if (cfg->max_cruft_size) - strvec_pushf(&repack, "--max-cruft-size=%lu", + strvec_pushf(args, "--max-cruft-size=%lu", cfg->max_cruft_size); if (cfg->repack_expire_to) - strvec_pushf(&repack, "--expire-to=%s", cfg->repack_expire_to); + strvec_pushf(args, "--expire-to=%s", cfg->repack_expire_to); } else { - strvec_push(&repack, "-A"); + strvec_push(args, "-A"); if (cfg->prune_expire) - strvec_pushf(&repack, "--unpack-unreachable=%s", cfg->prune_expire); + strvec_pushf(args, "--unpack-unreachable=%s", cfg->prune_expire); } if (keep_pack) - for_each_string_list(keep_pack, keep_one_pack, NULL); + for_each_string_list(keep_pack, keep_one_pack, args); if (cfg->repack_filter && *cfg->repack_filter) - strvec_pushf(&repack, "--filter=%s", cfg->repack_filter); + strvec_pushf(args, "--filter=%s", cfg->repack_filter); if (cfg->repack_filter_to && *cfg->repack_filter_to) - strvec_pushf(&repack, "--filter-to=%s", cfg->repack_filter_to); + strvec_pushf(args, "--filter-to=%s", cfg->repack_filter_to); } -static void add_repack_incremental_option(void) +static void add_repack_incremental_option(struct strvec *args) { - strvec_push(&repack, "--no-write-bitmap-index"); + strvec_push(args, "--no-write-bitmap-index"); } -static int need_to_gc(struct gc_config *cfg) +static int need_to_gc(struct gc_config *cfg, struct strvec *repack_args) { /* * Setting gc.auto to 0 or negative can disable the @@ -700,10 +701,10 @@ static int need_to_gc(struct gc_config *cfg) string_list_clear(&keep_pack, 0); } - add_repack_all_option(cfg, &keep_pack); + add_repack_all_option(cfg, &keep_pack, repack_args); string_list_clear(&keep_pack, 0); - } else if (too_many_loose_objects(cfg)) - add_repack_incremental_option(); + } else if (too_many_loose_objects(cfg->gc_auto_threshold)) + add_repack_incremental_option(repack_args); else return 0; @@ -852,6 +853,7 @@ int cmd_gc(int argc, int keep_largest_pack = -1; int skip_foreground_tasks = 0; timestamp_t dummy; + struct strvec repack_args = STRVEC_INIT; struct maintenance_run_opts opts = MAINTENANCE_RUN_OPTS_INIT; struct gc_config cfg = GC_CONFIG_INIT; const char *prune_expire_sentinel = "sentinel"; @@ -891,7 +893,7 @@ int cmd_gc(int argc, show_usage_with_options_if_asked(argc, argv, builtin_gc_usage, builtin_gc_options); - strvec_pushl(&repack, "repack", "-d", "-l", NULL); + strvec_pushl(&repack_args, "repack", "-d", "-l", NULL); gc_config(&cfg); @@ -914,14 +916,14 @@ int cmd_gc(int argc, die(_("failed to parse prune expiry value %s"), cfg.prune_expire); if (aggressive) { - strvec_push(&repack, "-f"); + strvec_push(&repack_args, "-f"); if (cfg.aggressive_depth > 0) - strvec_pushf(&repack, "--depth=%d", cfg.aggressive_depth); + strvec_pushf(&repack_args, "--depth=%d", cfg.aggressive_depth); if (cfg.aggressive_window > 0) - strvec_pushf(&repack, "--window=%d", cfg.aggressive_window); + strvec_pushf(&repack_args, "--window=%d", cfg.aggressive_window); } if (opts.quiet) - strvec_push(&repack, "-q"); + strvec_push(&repack_args, "-q"); if (opts.auto_flag) { if (cfg.detach_auto && opts.detach < 0) @@ -930,7 +932,7 @@ int cmd_gc(int argc, /* * Auto-gc should be least intrusive as possible. */ - if (!need_to_gc(&cfg)) { + if (!need_to_gc(&cfg, &repack_args)) { ret = 0; goto out; } @@ -952,7 +954,7 @@ int cmd_gc(int argc, find_base_packs(&keep_pack, cfg.big_pack_threshold); } - add_repack_all_option(&cfg, &keep_pack); + add_repack_all_option(&cfg, &keep_pack, &repack_args); string_list_clear(&keep_pack, 0); } @@ -1014,9 +1016,9 @@ int cmd_gc(int argc, repack_cmd.git_cmd = 1; repack_cmd.close_object_store = 1; - strvec_pushv(&repack_cmd.args, repack.v); + strvec_pushv(&repack_cmd.args, repack_args.v); if (run_command(&repack_cmd)) - die(FAILED_RUN, repack.v[0]); + die(FAILED_RUN, repack_args.v[0]); if (cfg.prune_expire) { struct child_process prune_cmd = CHILD_PROCESS_INIT; @@ -1055,7 +1057,7 @@ int cmd_gc(int argc, !opts.quiet && !daemonized ? COMMIT_GRAPH_WRITE_PROGRESS : 0, NULL); - if (opts.auto_flag && too_many_loose_objects(&cfg)) + if (opts.auto_flag && too_many_loose_objects(cfg.gc_auto_threshold)) warning(_("There are too many unreachable loose objects; " "run 'git prune' to remove them.")); @@ -1067,6 +1069,7 @@ int cmd_gc(int argc, out: maintenance_run_opts_release(&opts); + strvec_clear(&repack_args); gc_config_release(&cfg); return 0; } @@ -1269,6 +1272,19 @@ static int maintenance_task_gc_background(struct maintenance_run_opts *opts, return run_command(&child); } +static int gc_condition(struct gc_config *cfg) +{ + /* + * Note that it's fine to drop the repack arguments here, as we execute + * git-gc(1) as a separate child process anyway. So it knows to compute + * these arguments again. + */ + struct strvec repack_args = STRVEC_INIT; + int ret = need_to_gc(cfg, &repack_args); + strvec_clear(&repack_args); + return ret; +} + static int prune_packed(struct maintenance_run_opts *opts) { struct child_process child = CHILD_PROCESS_INIT; @@ -1425,9 +1441,9 @@ static int incremental_repack_auto_condition(struct gc_config *cfg UNUSED) if (incremental_repack_auto_limit < 0) return 1; - for (p = packfile_store_get_packs(the_repository->objects->packfiles); - count < incremental_repack_auto_limit && p; - p = p->next) { + repo_for_each_pack(the_repository, p) { + if (count >= incremental_repack_auto_limit) + break; if (!p->multi_pack_index) count++; } @@ -1494,7 +1510,7 @@ static off_t get_auto_pack_size(void) struct repository *r = the_repository; odb_reprepare(r->objects); - for (p = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { + repo_for_each_pack(r, p) { if (p->pack_size > max_size) { second_largest_size = max_size; max_size = p->pack_size; @@ -1550,6 +1566,108 @@ static int maintenance_task_incremental_repack(struct maintenance_run_opts *opts return 0; } +static int maintenance_task_geometric_repack(struct maintenance_run_opts *opts, + struct gc_config *cfg) +{ + struct pack_geometry geometry = { + .split_factor = 2, + }; + struct pack_objects_args po_args = { + .local = 1, + }; + struct existing_packs existing_packs = EXISTING_PACKS_INIT; + struct string_list kept_packs = STRING_LIST_INIT_DUP; + struct child_process child = CHILD_PROCESS_INIT; + int ret; + + repo_config_get_int(the_repository, "maintenance.geometric-repack.splitFactor", + &geometry.split_factor); + + existing_packs.repo = the_repository; + existing_packs_collect(&existing_packs, &kept_packs); + pack_geometry_init(&geometry, &existing_packs, &po_args); + pack_geometry_split(&geometry); + + child.git_cmd = 1; + + strvec_pushl(&child.args, "repack", "-d", "-l", NULL); + if (geometry.split < geometry.pack_nr) + strvec_pushf(&child.args, "--geometric=%d", + geometry.split_factor); + else + add_repack_all_option(cfg, NULL, &child.args); + if (opts->quiet) + strvec_push(&child.args, "--quiet"); + if (the_repository->settings.core_multi_pack_index) + strvec_push(&child.args, "--write-midx"); + + if (run_command(&child)) { + ret = error(_("failed to perform geometric repack")); + goto out; + } + + ret = 0; + +out: + existing_packs_release(&existing_packs); + pack_geometry_release(&geometry); + return ret; +} + +static int geometric_repack_auto_condition(struct gc_config *cfg UNUSED) +{ + struct pack_geometry geometry = { + .split_factor = 2, + }; + struct pack_objects_args po_args = { + .local = 1, + }; + struct existing_packs existing_packs = EXISTING_PACKS_INIT; + struct string_list kept_packs = STRING_LIST_INIT_DUP; + int auto_value = 100; + int ret; + + repo_config_get_int(the_repository, "maintenance.geometric-repack.auto", + &auto_value); + if (!auto_value) + return 0; + if (auto_value < 0) + return 1; + + repo_config_get_int(the_repository, "maintenance.geometric-repack.splitFactor", + &geometry.split_factor); + + existing_packs.repo = the_repository; + existing_packs_collect(&existing_packs, &kept_packs); + pack_geometry_init(&geometry, &existing_packs, &po_args); + pack_geometry_split(&geometry); + + /* + * When we'd merge at least two packs with one another we always + * perform the repack. + */ + if (geometry.split) { + ret = 1; + goto out; + } + + /* + * Otherwise, we estimate the number of loose objects to determine + * whether we want to create a new packfile or not. + */ + if (too_many_loose_objects(auto_value)) { + ret = 1; + goto out; + } + + ret = 0; + +out: + existing_packs_release(&existing_packs); + pack_geometry_release(&geometry); + return ret; +} + typedef int (*maintenance_task_fn)(struct maintenance_run_opts *opts, struct gc_config *cfg); typedef int (*maintenance_auto_fn)(struct gc_config *cfg); @@ -1592,11 +1710,16 @@ static const struct maintenance_task tasks[] = { .background = maintenance_task_incremental_repack, .auto_condition = incremental_repack_auto_condition, }, + [TASK_GEOMETRIC_REPACK] = { + .name = "geometric-repack", + .background = maintenance_task_geometric_repack, + .auto_condition = geometric_repack_auto_condition, + }, [TASK_GC] = { .name = "gc", .foreground = maintenance_task_gc_foreground, .background = maintenance_task_gc_background, - .auto_condition = need_to_gc, + .auto_condition = gc_condition, }, [TASK_COMMIT_GRAPH] = { .name = "commit-graph", @@ -1702,39 +1825,116 @@ static int maintenance_run_tasks(struct maintenance_run_opts *opts, return result; } +enum maintenance_type { + /* As invoked via `git maintenance run --schedule=`. */ + MAINTENANCE_TYPE_SCHEDULED = (1 << 0), + /* As invoked via `git maintenance run` and with `--auto`. */ + MAINTENANCE_TYPE_MANUAL = (1 << 1), +}; + struct maintenance_strategy { struct { - int enabled; + unsigned type; enum schedule_priority schedule; } tasks[TASK__COUNT]; }; static const struct maintenance_strategy none_strategy = { 0 }; -static const struct maintenance_strategy default_strategy = { + +static const struct maintenance_strategy gc_strategy = { .tasks = { - [TASK_GC].enabled = 1, + [TASK_GC] = { + .type = MAINTENANCE_TYPE_MANUAL | MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_DAILY, + }, }, }; + static const struct maintenance_strategy incremental_strategy = { .tasks = { - [TASK_COMMIT_GRAPH].enabled = 1, - [TASK_COMMIT_GRAPH].schedule = SCHEDULE_HOURLY, - [TASK_PREFETCH].enabled = 1, - [TASK_PREFETCH].schedule = SCHEDULE_HOURLY, - [TASK_INCREMENTAL_REPACK].enabled = 1, - [TASK_INCREMENTAL_REPACK].schedule = SCHEDULE_DAILY, - [TASK_LOOSE_OBJECTS].enabled = 1, - [TASK_LOOSE_OBJECTS].schedule = SCHEDULE_DAILY, - [TASK_PACK_REFS].enabled = 1, - [TASK_PACK_REFS].schedule = SCHEDULE_WEEKLY, + [TASK_COMMIT_GRAPH] = { + .type = MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_HOURLY, + }, + [TASK_PREFETCH] = { + .type = MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_HOURLY, + }, + [TASK_INCREMENTAL_REPACK] = { + .type = MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_DAILY, + }, + [TASK_LOOSE_OBJECTS] = { + .type = MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_DAILY, + }, + [TASK_PACK_REFS] = { + .type = MAINTENANCE_TYPE_SCHEDULED, + .schedule = SCHEDULE_WEEKLY, + }, + /* + * Historically, the "incremental" strategy was only available + * in the context of scheduled maintenance when set up via + * "maintenance.strategy". We have later expanded that config + * to also cover manual maintenance. + * + * To retain backwards compatibility with the previous status + * quo we thus run git-gc(1) in case manual maintenance was + * requested. This is the same as the default strategy, which + * would have been in use beforehand. + */ + [TASK_GC] = { + .type = MAINTENANCE_TYPE_MANUAL, + }, + }, +}; + +static const struct maintenance_strategy geometric_strategy = { + .tasks = { + [TASK_COMMIT_GRAPH] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_HOURLY, + }, + [TASK_GEOMETRIC_REPACK] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_DAILY, + }, + [TASK_PACK_REFS] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_DAILY, + }, + [TASK_RERERE_GC] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_WEEKLY, + }, + [TASK_REFLOG_EXPIRE] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_WEEKLY, + }, + [TASK_WORKTREE_PRUNE] = { + .type = MAINTENANCE_TYPE_SCHEDULED | MAINTENANCE_TYPE_MANUAL, + .schedule = SCHEDULE_WEEKLY, + }, }, }; +static struct maintenance_strategy parse_maintenance_strategy(const char *name) +{ + if (!strcasecmp(name, "incremental")) + return incremental_strategy; + if (!strcasecmp(name, "gc")) + return gc_strategy; + if (!strcasecmp(name, "geometric")) + return geometric_strategy; + die(_("unknown maintenance strategy: '%s'"), name); +} + static void initialize_task_config(struct maintenance_run_opts *opts, const struct string_list *selected_tasks) { struct strbuf config_name = STRBUF_INIT; struct maintenance_strategy strategy; + enum maintenance_type type; const char *config_str; /* @@ -1762,19 +1962,20 @@ static void initialize_task_config(struct maintenance_run_opts *opts, * - Unscheduled maintenance uses our default strategy. * * Both of these are affected by the gitconfig though, which may - * override specific aspects of our strategy. + * override specific aspects of our strategy. Furthermore, both + * strategies can be overridden by setting "maintenance.strategy". */ if (opts->schedule) { strategy = none_strategy; - - if (!repo_config_get_string_tmp(the_repository, "maintenance.strategy", &config_str)) { - if (!strcasecmp(config_str, "incremental")) - strategy = incremental_strategy; - } + type = MAINTENANCE_TYPE_SCHEDULED; } else { - strategy = default_strategy; + strategy = gc_strategy; + type = MAINTENANCE_TYPE_MANUAL; } + if (!repo_config_get_string_tmp(the_repository, "maintenance.strategy", &config_str)) + strategy = parse_maintenance_strategy(config_str); + for (size_t i = 0; i < TASK__COUNT; i++) { int config_value; @@ -1782,8 +1983,8 @@ static void initialize_task_config(struct maintenance_run_opts *opts, strbuf_addf(&config_name, "maintenance.%s.enabled", tasks[i].name); if (!repo_config_get_bool(the_repository, config_name.buf, &config_value)) - strategy.tasks[i].enabled = config_value; - if (!strategy.tasks[i].enabled) + strategy.tasks[i].type = config_value ? type : 0; + if (!(strategy.tasks[i].type & type)) continue; if (opts->schedule) { diff --git a/builtin/grep.c b/builtin/grep.c index 13841fbf00..53cccf2d25 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)packfile_store_get_packs(the_repository->objects->packfiles); + packfile_store_prepare(the_repository->objects->packfiles); start_threads(&opt); } else { diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 5bdc44fb2d..b5454e5df1 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -3831,12 +3831,10 @@ 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; struct string_list_item *item = NULL; - struct packed_git *p; while (strbuf_getline(&buf, stdin) != EOF) { @@ -3856,7 +3854,7 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { const char *pack_name = pack_basename(p); if ((item = string_list_lookup(&include_packs, pack_name))) @@ -4077,7 +4075,6 @@ 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; @@ -4107,7 +4104,7 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) + repo_for_each_pack(the_repository, p) p->pack_keep_in_core = 0; mark_pack_kept_in_core(fresh_packs, 1); @@ -4124,7 +4121,6 @@ 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; @@ -4145,7 +4141,7 @@ static void read_cruft_objects(void) string_list_sort(&discard_packs); string_list_sort(&fresh_packs); - for (p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { const char *pack_name = pack_basename(p); struct string_list_item *item; @@ -4398,7 +4394,7 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) struct packed_git *p; p = (last_found != (void *)1) ? last_found : - packfile_store_get_all_packs(packs); + packfile_store_get_packs(packs); while (p) { if ((!p->pack_local || p->pack_keep || @@ -4408,7 +4404,7 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) return 1; } if (p == last_found) - p = packfile_store_get_all_packs(packs); + p = packfile_store_get_packs(packs); else p = p->next; if (p == last_found) @@ -4440,13 +4436,12 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; @@ -4747,13 +4742,12 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { const char *name = basename(p->pack_name); int i; @@ -5191,10 +5185,9 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) + repo_for_each_pack(the_repository, p) if (p->pack_local && p->pack_keep) break; if (!p) /* no keep-able packs found */ @@ -5206,10 +5199,9 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_local) { have_non_local_packs = 1; break; diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index 80743d8806..e4ecf774ca 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -566,29 +566,23 @@ static struct pack_list * add_pack(struct packed_git *p) static struct pack_list * add_pack_file(const char *filename) { - struct packfile_store *packs = the_repository->objects->packfiles; - struct packed_git *p = packfile_store_get_all_packs(packs); + struct packed_git *p; if (strlen(filename) < 40) die("Bad pack filename: %s", filename); - while (p) { + repo_for_each_pack(the_repository, p) if (strstr(p->pack_name, filename)) return add_pack(p); - p = p->next; - } die("Filename %s not found in packed_git", filename); } static void load_all(void) { - struct packfile_store *packs = the_repository->objects->packfiles; - struct packed_git *p = packfile_store_get_all_packs(packs); + struct packed_git *p; - while (p) { + repo_for_each_pack(the_repository, p) add_pack(p); - p = p->next; - } } int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, struct repository *repo UNUSED) { diff --git a/builtin/repack.c b/builtin/repack.c index e8730808c5..cfdb4c0920 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -3,27 +3,18 @@ #include "builtin.h" #include "config.h" -#include "dir.h" #include "environment.h" -#include "gettext.h" -#include "hex.h" #include "parse-options.h" #include "path.h" #include "run-command.h" #include "server-info.h" -#include "strbuf.h" #include "string-list.h" -#include "strvec.h" #include "midx.h" #include "packfile.h" #include "prune-packed.h" -#include "odb.h" #include "promisor-remote.h" +#include "repack.h" #include "shallow.h" -#include "pack.h" -#include "pack-bitmap.h" -#include "refs.h" -#include "list-objects-filter-options.h" #define ALL_INTO_ONE 1 #define LOOSEN_UNREACHABLE 2 @@ -33,8 +24,6 @@ #define RETAIN_PACK 2 static int pack_everything; -static int delta_base_offset = 1; -static int pack_kept_objects = -1; static int write_bitmaps = -1; static int use_delta_islands; static int run_update_server_info = 1; @@ -53,31 +42,23 @@ static const char incremental_bitmap_conflict_error[] = N_( "--no-write-bitmap-index or disable the pack.writeBitmaps configuration." ); -struct pack_objects_args { - char *window; - char *window_memory; - char *depth; - char *threads; - unsigned long max_pack_size; - int no_reuse_delta; - int no_reuse_object; - int quiet; - int local; - int name_hash_version; - int path_walk; - struct list_objects_filter_options filter_options; +struct repack_config_ctx { + struct pack_objects_args *po_args; + struct pack_objects_args *cruft_po_args; }; static int repack_config(const char *var, const char *value, const struct config_context *ctx, void *cb) { - struct pack_objects_args *cruft_po_args = cb; + struct repack_config_ctx *repack_ctx = cb; + struct pack_objects_args *po_args = repack_ctx->po_args; + struct pack_objects_args *cruft_po_args = repack_ctx->cruft_po_args; if (!strcmp(var, "repack.usedeltabaseoffset")) { - delta_base_offset = git_config_bool(var, value); + po_args->delta_base_offset = git_config_bool(var, value); return 0; } if (!strcmp(var, "repack.packkeptobjects")) { - pack_kept_objects = git_config_bool(var, value); + po_args->pack_kept_objects = git_config_bool(var, value); return 0; } if (!strcmp(var, "repack.writebitmaps") || @@ -116,1138 +97,10 @@ static int repack_config(const char *var, const char *value, return git_default_config(var, value, ctx, cb); } -static void pack_objects_args_release(struct pack_objects_args *args) -{ - free(args->window); - free(args->window_memory); - free(args->depth); - free(args->threads); - list_objects_filter_release(&args->filter_options); -} - -struct existing_packs { - struct string_list kept_packs; - struct string_list non_kept_packs; - struct string_list cruft_packs; -}; - -#define EXISTING_PACKS_INIT { \ - .kept_packs = STRING_LIST_INIT_DUP, \ - .non_kept_packs = STRING_LIST_INIT_DUP, \ - .cruft_packs = STRING_LIST_INIT_DUP, \ -} - -static int has_existing_non_kept_packs(const struct existing_packs *existing) -{ - return existing->non_kept_packs.nr || existing->cruft_packs.nr; -} - -static void pack_mark_for_deletion(struct string_list_item *item) -{ - item->util = (void*)((uintptr_t)item->util | DELETE_PACK); -} - -static void pack_unmark_for_deletion(struct string_list_item *item) -{ - item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK); -} - -static int pack_is_marked_for_deletion(struct string_list_item *item) -{ - return (uintptr_t)item->util & DELETE_PACK; -} - -static void pack_mark_retained(struct string_list_item *item) -{ - item->util = (void*)((uintptr_t)item->util | RETAIN_PACK); -} - -static int pack_is_retained(struct string_list_item *item) -{ - return (uintptr_t)item->util & RETAIN_PACK; -} - -static void mark_packs_for_deletion_1(struct string_list *names, - struct string_list *list) -{ - struct string_list_item *item; - const int hexsz = the_hash_algo->hexsz; - - for_each_string_list_item(item, list) { - char *sha1; - size_t len = strlen(item->string); - if (len < hexsz) - continue; - sha1 = item->string + len - hexsz; - - if (pack_is_retained(item)) { - pack_unmark_for_deletion(item); - } else if (!string_list_has_string(names, sha1)) { - /* - * Mark this pack for deletion, which ensures - * that this pack won't be included in a MIDX - * (if `--write-midx` was given) and that we - * will actually delete this pack (if `-d` was - * given). - */ - pack_mark_for_deletion(item); - } - } -} - -static void retain_cruft_pack(struct existing_packs *existing, - struct packed_git *cruft) -{ - struct strbuf buf = STRBUF_INIT; - struct string_list_item *item; - - strbuf_addstr(&buf, pack_basename(cruft)); - strbuf_strip_suffix(&buf, ".pack"); - - item = string_list_lookup(&existing->cruft_packs, buf.buf); - if (!item) - BUG("could not find cruft pack '%s'", pack_basename(cruft)); - - pack_mark_retained(item); - strbuf_release(&buf); -} - -static void mark_packs_for_deletion(struct existing_packs *existing, - struct string_list *names) - -{ - mark_packs_for_deletion_1(names, &existing->non_kept_packs); - mark_packs_for_deletion_1(names, &existing->cruft_packs); -} - -static void remove_redundant_pack(const char *dir_name, const char *base_name) -{ - struct strbuf buf = STRBUF_INIT; - struct odb_source *source = the_repository->objects->sources; - struct multi_pack_index *m = get_multi_pack_index(source); - strbuf_addf(&buf, "%s.pack", base_name); - if (m && source->local && midx_contains_pack(m, buf.buf)) - clear_midx_file(the_repository); - strbuf_insertf(&buf, 0, "%s/", dir_name); - unlink_pack_path(buf.buf, 1); - strbuf_release(&buf); -} - -static void remove_redundant_packs_1(struct string_list *packs) -{ - struct string_list_item *item; - for_each_string_list_item(item, packs) { - if (!pack_is_marked_for_deletion(item)) - continue; - remove_redundant_pack(packdir, item->string); - } -} - -static void remove_redundant_existing_packs(struct existing_packs *existing) -{ - remove_redundant_packs_1(&existing->non_kept_packs); - remove_redundant_packs_1(&existing->cruft_packs); -} - -static void existing_packs_release(struct existing_packs *existing) -{ - string_list_clear(&existing->kept_packs, 0); - string_list_clear(&existing->non_kept_packs, 0); - string_list_clear(&existing->cruft_packs, 0); -} - -/* - * Adds all packs hex strings (pack-$HASH) to either packs->non_kept - * or packs->kept based on whether each pack has a corresponding - * .keep file or not. Packs without a .keep file are not to be kept - * if we are going to pack everything into one file. - */ -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 = packfile_store_get_all_packs(packs); p; p = p->next) { - int i; - const char *base; - - if (!p->pack_local) - continue; - - base = pack_basename(p); - - for (i = 0; i < extra_keep->nr; i++) - if (!fspathcmp(base, extra_keep->items[i].string)) - break; - - strbuf_reset(&buf); - strbuf_addstr(&buf, base); - strbuf_strip_suffix(&buf, ".pack"); - - if ((extra_keep->nr > 0 && i < extra_keep->nr) || p->pack_keep) - string_list_append(&existing->kept_packs, buf.buf); - else if (p->is_cruft) - string_list_append(&existing->cruft_packs, buf.buf); - else - string_list_append(&existing->non_kept_packs, buf.buf); - } - - string_list_sort(&existing->kept_packs); - string_list_sort(&existing->non_kept_packs); - string_list_sort(&existing->cruft_packs); - strbuf_release(&buf); -} - -static void prepare_pack_objects(struct child_process *cmd, - const struct pack_objects_args *args, - const char *out) -{ - strvec_push(&cmd->args, "pack-objects"); - if (args->window) - strvec_pushf(&cmd->args, "--window=%s", args->window); - if (args->window_memory) - strvec_pushf(&cmd->args, "--window-memory=%s", args->window_memory); - if (args->depth) - strvec_pushf(&cmd->args, "--depth=%s", args->depth); - if (args->threads) - strvec_pushf(&cmd->args, "--threads=%s", args->threads); - if (args->max_pack_size) - strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size); - if (args->no_reuse_delta) - strvec_pushf(&cmd->args, "--no-reuse-delta"); - if (args->no_reuse_object) - strvec_pushf(&cmd->args, "--no-reuse-object"); - if (args->name_hash_version) - strvec_pushf(&cmd->args, "--name-hash-version=%d", args->name_hash_version); - if (args->path_walk) - strvec_pushf(&cmd->args, "--path-walk"); - if (args->local) - strvec_push(&cmd->args, "--local"); - if (args->quiet) - strvec_push(&cmd->args, "--quiet"); - if (delta_base_offset) - strvec_push(&cmd->args, "--delta-base-offset"); - strvec_push(&cmd->args, out); - cmd->git_cmd = 1; - cmd->out = -1; -} - -/* - * Write oid to the given struct child_process's stdin, starting it first if - * necessary. - */ -static int write_oid(const struct object_id *oid, - struct packed_git *pack UNUSED, - uint32_t pos UNUSED, void *data) -{ - struct child_process *cmd = data; - - if (cmd->in == -1) { - if (start_command(cmd)) - die(_("could not start pack-objects to repack promisor objects")); - } - - if (write_in_full(cmd->in, oid_to_hex(oid), the_hash_algo->hexsz) < 0 || - write_in_full(cmd->in, "\n", 1) < 0) - die(_("failed to feed promisor objects to pack-objects")); - return 0; -} - -static struct { - const char *name; - unsigned optional:1; -} exts[] = { - {".pack"}, - {".rev", 1}, - {".mtimes", 1}, - {".bitmap", 1}, - {".promisor", 1}, - {".idx"}, -}; - -struct generated_pack_data { - struct tempfile *tempfiles[ARRAY_SIZE(exts)]; -}; - -static struct generated_pack_data *populate_pack_exts(const char *name) -{ - struct stat statbuf; - struct strbuf path = STRBUF_INIT; - struct generated_pack_data *data = xcalloc(1, sizeof(*data)); - int i; - - for (i = 0; i < ARRAY_SIZE(exts); i++) { - strbuf_reset(&path); - strbuf_addf(&path, "%s-%s%s", packtmp, name, exts[i].name); - - if (stat(path.buf, &statbuf)) - continue; - - data->tempfiles[i] = register_tempfile(path.buf); - } - - strbuf_release(&path); - return data; -} - -static int has_pack_ext(const struct generated_pack_data *data, - const char *ext) -{ - int i; - for (i = 0; i < ARRAY_SIZE(exts); i++) { - if (strcmp(exts[i].name, ext)) - continue; - return !!data->tempfiles[i]; - } - BUG("unknown pack extension: '%s'", ext); -} - -static void repack_promisor_objects(const struct pack_objects_args *args, - struct string_list *names) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - FILE *out; - struct strbuf line = STRBUF_INIT; - - prepare_pack_objects(&cmd, args, packtmp); - cmd.in = -1; - - /* - * NEEDSWORK: Giving pack-objects only the OIDs without any ordering - * hints may result in suboptimal deltas in the resulting pack. See if - * the OIDs can be sent with fake paths such that pack-objects can use a - * {type -> existing pack order} ordering when computing deltas instead - * of a {type -> size} ordering, which may produce better deltas. - */ - for_each_packed_object(the_repository, write_oid, &cmd, - FOR_EACH_OBJECT_PROMISOR_ONLY); - - if (cmd.in == -1) { - /* No packed objects; cmd was never started */ - child_process_clear(&cmd); - return; - } - - close(cmd.in); - - out = xfdopen(cmd.out, "r"); - while (strbuf_getline_lf(&line, out) != EOF) { - struct string_list_item *item; - char *promisor_name; - - if (line.len != the_hash_algo->hexsz) - die(_("repack: Expecting full hex object ID lines only from pack-objects.")); - item = string_list_append(names, line.buf); - - /* - * pack-objects creates the .pack and .idx files, but not the - * .promisor file. Create the .promisor file, which is empty. - * - * NEEDSWORK: fetch-pack sometimes generates non-empty - * .promisor files containing the ref names and associated - * hashes at the point of generation of the corresponding - * packfile, but this would not preserve their contents. Maybe - * concatenate the contents of all .promisor files instead of - * just creating a new empty file. - */ - promisor_name = mkpathdup("%s-%s.promisor", packtmp, - line.buf); - write_promisor_file(promisor_name, NULL, 0); - - item->util = populate_pack_exts(item->string); - - free(promisor_name); - } - - fclose(out); - if (finish_command(&cmd)) - die(_("could not finish pack-objects to repack promisor objects")); - strbuf_release(&line); -} - -struct pack_geometry { - struct packed_git **pack; - uint32_t pack_nr, pack_alloc; - uint32_t split; - - int split_factor; -}; - -static uint32_t geometry_pack_weight(struct packed_git *p) -{ - if (open_pack_index(p)) - die(_("cannot open index for %s"), p->pack_name); - return p->num_objects; -} - -static int geometry_cmp(const void *va, const void *vb) -{ - uint32_t aw = geometry_pack_weight(*(struct packed_git **)va), - bw = geometry_pack_weight(*(struct packed_git **)vb); - - if (aw < bw) - return -1; - if (aw > bw) - return 1; - return 0; -} - -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 = 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 - * over any packfiles that are borrowed from alternate - * object directories. - */ - continue; - - if (!pack_kept_objects) { - /* - * Any pack that has its pack_keep bit set will - * appear in existing->kept_packs below, but - * this saves us from doing a more expensive - * check. - */ - if (p->pack_keep) - continue; - - /* - * The pack may be kept via the --keep-pack - * option; check 'existing->kept_packs' to - * determine whether to ignore it. - */ - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(p)); - strbuf_strip_suffix(&buf, ".pack"); - - if (string_list_has_string(&existing->kept_packs, buf.buf)) - continue; - } - if (p->is_cruft) - continue; - - ALLOC_GROW(geometry->pack, - geometry->pack_nr + 1, - geometry->pack_alloc); - - geometry->pack[geometry->pack_nr] = p; - geometry->pack_nr++; - } - - QSORT(geometry->pack, geometry->pack_nr, geometry_cmp); - strbuf_release(&buf); -} - -static void split_pack_geometry(struct pack_geometry *geometry) -{ - uint32_t i; - uint32_t split; - off_t total_size = 0; - - if (!geometry->pack_nr) { - geometry->split = geometry->pack_nr; - return; - } - - /* - * First, count the number of packs (in descending order of size) which - * already form a geometric progression. - */ - for (i = geometry->pack_nr - 1; i > 0; i--) { - struct packed_git *ours = geometry->pack[i]; - struct packed_git *prev = geometry->pack[i - 1]; - - if (unsigned_mult_overflows(geometry->split_factor, - geometry_pack_weight(prev))) - die(_("pack %s too large to consider in geometric " - "progression"), - prev->pack_name); - - if (geometry_pack_weight(ours) < - geometry->split_factor * geometry_pack_weight(prev)) - break; - } - - split = i; - - if (split) { - /* - * Move the split one to the right, since the top element in the - * last-compared pair can't be in the progression. Only do this - * when we split in the middle of the array (otherwise if we got - * to the end, then the split is in the right place). - */ - split++; - } - - /* - * Then, anything to the left of 'split' must be in a new pack. But, - * creating that new pack may cause packs in the heavy half to no longer - * form a geometric progression. - * - * Compute an expected size of the new pack, and then determine how many - * packs in the heavy half need to be joined into it (if any) to restore - * the geometric progression. - */ - for (i = 0; i < split; i++) { - struct packed_git *p = geometry->pack[i]; - - if (unsigned_add_overflows(total_size, geometry_pack_weight(p))) - die(_("pack %s too large to roll up"), p->pack_name); - total_size += geometry_pack_weight(p); - } - for (i = split; i < geometry->pack_nr; i++) { - struct packed_git *ours = geometry->pack[i]; - - if (unsigned_mult_overflows(geometry->split_factor, - total_size)) - die(_("pack %s too large to roll up"), ours->pack_name); - - if (geometry_pack_weight(ours) < - geometry->split_factor * total_size) { - if (unsigned_add_overflows(total_size, - geometry_pack_weight(ours))) - die(_("pack %s too large to roll up"), - ours->pack_name); - - split++; - total_size += geometry_pack_weight(ours); - } else - break; - } - - geometry->split = split; -} - -static struct packed_git *get_preferred_pack(struct pack_geometry *geometry) -{ - uint32_t i; - - if (!geometry) { - /* - * No geometry means either an all-into-one repack (in which - * case there is only one pack left and it is the largest) or an - * incremental one. - * - * If repacking incrementally, then we could check the size of - * all packs to determine which should be preferred, but leave - * this for later. - */ - return NULL; - } - if (geometry->split == geometry->pack_nr) - return NULL; - - /* - * The preferred pack is the largest pack above the split line. In - * other words, it is the largest pack that does not get rolled up in - * the geometric repack. - */ - for (i = geometry->pack_nr; i > geometry->split; i--) - /* - * A pack that is not local would never be included in a - * multi-pack index. We thus skip over any non-local packs. - */ - if (geometry->pack[i - 1]->pack_local) - return geometry->pack[i - 1]; - - return NULL; -} - -static void geometry_remove_redundant_packs(struct pack_geometry *geometry, - struct string_list *names, - struct existing_packs *existing) -{ - struct strbuf buf = STRBUF_INIT; - uint32_t i; - - for (i = 0; i < geometry->split; i++) { - struct packed_git *p = geometry->pack[i]; - if (string_list_has_string(names, hash_to_hex(p->hash))) - continue; - - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(p)); - strbuf_strip_suffix(&buf, ".pack"); - - if ((p->pack_keep) || - (string_list_has_string(&existing->kept_packs, buf.buf))) - continue; - - remove_redundant_pack(packdir, buf.buf); - } - - strbuf_release(&buf); -} - -static void free_pack_geometry(struct pack_geometry *geometry) -{ - if (!geometry) - return; - - free(geometry->pack); -} - -static int midx_has_unknown_packs(char **midx_pack_names, - size_t midx_pack_names_nr, - struct string_list *include, - struct pack_geometry *geometry, - struct existing_packs *existing) -{ - size_t i; - - string_list_sort(include); - - for (i = 0; i < midx_pack_names_nr; i++) { - const char *pack_name = midx_pack_names[i]; - - /* - * Determine whether or not each MIDX'd pack from the existing - * MIDX (if any) is represented in the new MIDX. For each pack - * in the MIDX, it must either be: - * - * - In the "include" list of packs to be included in the new - * MIDX. Note this function is called before the include - * list is populated with any cruft pack(s). - * - * - Below the geometric split line (if using pack geometry), - * indicating that the pack won't be included in the new - * MIDX, but its contents were rolled up as part of the - * geometric repack. - * - * - In the existing non-kept packs list (if not using pack - * geometry), and marked as non-deleted. - */ - if (string_list_has_string(include, pack_name)) { - continue; - } else if (geometry) { - struct strbuf buf = STRBUF_INIT; - uint32_t j; - - for (j = 0; j < geometry->split; j++) { - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(geometry->pack[j])); - strbuf_strip_suffix(&buf, ".pack"); - strbuf_addstr(&buf, ".idx"); - - if (!strcmp(pack_name, buf.buf)) { - strbuf_release(&buf); - break; - } - } - - strbuf_release(&buf); - - if (j < geometry->split) - continue; - } else { - struct string_list_item *item; - - item = string_list_lookup(&existing->non_kept_packs, - pack_name); - if (item && !pack_is_marked_for_deletion(item)) - continue; - } - - /* - * If we got to this point, the MIDX includes some pack that we - * don't know about. - */ - return 1; - } - - return 0; -} - -struct midx_snapshot_ref_data { - struct tempfile *f; - struct oidset seen; - int preferred; -}; - -static int midx_snapshot_ref_one(const char *refname UNUSED, - const char *referent UNUSED, - const struct object_id *oid, - int flag UNUSED, void *_data) -{ - struct midx_snapshot_ref_data *data = _data; - struct object_id peeled; - - if (!peel_iterated_oid(the_repository, oid, &peeled)) - oid = &peeled; - - if (oidset_insert(&data->seen, oid)) - return 0; /* already seen */ - - if (odb_read_object_info(the_repository->objects, oid, NULL) != OBJ_COMMIT) - return 0; - - fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "", - oid_to_hex(oid)); - - return 0; -} - -static void midx_snapshot_refs(struct tempfile *f) -{ - struct midx_snapshot_ref_data data; - const struct string_list *preferred = bitmap_preferred_tips(the_repository); - - data.f = f; - data.preferred = 0; - oidset_init(&data.seen, 0); - - if (!fdopen_tempfile(f, "w")) - die(_("could not open tempfile %s for writing"), - get_tempfile_path(f)); - - if (preferred) { - struct string_list_item *item; - - data.preferred = 1; - for_each_string_list_item(item, preferred) - refs_for_each_ref_in(get_main_ref_store(the_repository), - item->string, - midx_snapshot_ref_one, &data); - data.preferred = 0; - } - - refs_for_each_ref(get_main_ref_store(the_repository), - midx_snapshot_ref_one, &data); - - if (close_tempfile_gently(f)) { - int save_errno = errno; - delete_tempfile(&f); - errno = save_errno; - die_errno(_("could not close refs snapshot tempfile")); - } - - oidset_clear(&data.seen); -} - -static void midx_included_packs(struct string_list *include, - struct existing_packs *existing, - char **midx_pack_names, - size_t midx_pack_names_nr, - struct string_list *names, - struct pack_geometry *geometry) -{ - struct string_list_item *item; - struct strbuf buf = STRBUF_INIT; - - for_each_string_list_item(item, &existing->kept_packs) { - strbuf_reset(&buf); - strbuf_addf(&buf, "%s.idx", item->string); - string_list_insert(include, buf.buf); - } - - for_each_string_list_item(item, names) { - strbuf_reset(&buf); - strbuf_addf(&buf, "pack-%s.idx", item->string); - string_list_insert(include, buf.buf); - } - - if (geometry->split_factor) { - uint32_t i; - - for (i = geometry->split; i < geometry->pack_nr; i++) { - struct packed_git *p = geometry->pack[i]; - - /* - * The multi-pack index never refers to packfiles part - * of an alternate object database, so we skip these. - * While git-multi-pack-index(1) would silently ignore - * them anyway, this allows us to skip executing the - * command completely when we have only non-local - * packfiles. - */ - if (!p->pack_local) - continue; - - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(p)); - strbuf_strip_suffix(&buf, ".pack"); - strbuf_addstr(&buf, ".idx"); - - string_list_insert(include, buf.buf); - } - } else { - for_each_string_list_item(item, &existing->non_kept_packs) { - if (pack_is_marked_for_deletion(item)) - continue; - - strbuf_reset(&buf); - strbuf_addf(&buf, "%s.idx", item->string); - string_list_insert(include, buf.buf); - } - } - - if (midx_must_contain_cruft || - midx_has_unknown_packs(midx_pack_names, midx_pack_names_nr, - include, geometry, existing)) { - /* - * If there are one or more unknown pack(s) present (see - * midx_has_unknown_packs() for what makes a pack - * "unknown") in the MIDX before the repack, keep them - * as they may be required to form a reachability - * closure if the MIDX is bitmapped. - * - * For example, a cruft pack can be required to form a - * reachability closure if the MIDX is bitmapped and one - * or more of the bitmap's selected commits reaches a - * once-cruft object that was later made reachable. - */ - for_each_string_list_item(item, &existing->cruft_packs) { - /* - * When doing a --geometric repack, there is no - * need to check for deleted packs, since we're - * by definition not doing an ALL_INTO_ONE - * repack (hence no packs will be deleted). - * Otherwise we must check for and exclude any - * packs which are enqueued for deletion. - * - * So we could omit the conditional below in the - * --geometric case, but doing so is unnecessary - * since no packs are marked as pending - * deletion (since we only call - * `mark_packs_for_deletion()` when doing an - * all-into-one repack). - */ - if (pack_is_marked_for_deletion(item)) - continue; - - strbuf_reset(&buf); - strbuf_addf(&buf, "%s.idx", item->string); - string_list_insert(include, buf.buf); - } - } else { - /* - * Modern versions of Git (with the appropriate - * configuration setting) will write new copies of - * once-cruft objects when doing a --geometric repack. - * - * If the MIDX has no cruft pack, new packs written - * during a --geometric repack will not rely on the - * cruft pack to form a reachability closure, so we can - * avoid including them in the MIDX in that case. - */ - ; - } - - strbuf_release(&buf); -} - -static int write_midx_included_packs(struct string_list *include, - struct pack_geometry *geometry, - struct string_list *names, - const char *refs_snapshot, - int show_progress, int write_bitmaps) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - struct string_list_item *item; - struct packed_git *preferred = get_preferred_pack(geometry); - FILE *in; - int ret; - - if (!include->nr) - return 0; - - cmd.in = -1; - cmd.git_cmd = 1; - - strvec_push(&cmd.args, "multi-pack-index"); - strvec_pushl(&cmd.args, "write", "--stdin-packs", NULL); - - if (show_progress) - strvec_push(&cmd.args, "--progress"); - else - strvec_push(&cmd.args, "--no-progress"); - - if (write_bitmaps) - strvec_push(&cmd.args, "--bitmap"); - - if (preferred) - strvec_pushf(&cmd.args, "--preferred-pack=%s", - pack_basename(preferred)); - else if (names->nr) { - /* The largest pack was repacked, meaning that either - * one or two packs exist depending on whether the - * repository has a cruft pack or not. - * - * Select the non-cruft one as preferred to encourage - * pack-reuse among packs containing reachable objects - * over unreachable ones. - * - * (Note we could write multiple packs here if - * `--max-pack-size` was given, but any one of them - * will suffice, so pick the first one.) - */ - for_each_string_list_item(item, names) { - struct generated_pack_data *data = item->util; - if (has_pack_ext(data, ".mtimes")) - continue; - - strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack", - item->string); - break; - } - } else { - /* - * No packs were kept, and no packs were written. The - * only thing remaining are .keep packs (unless - * --pack-kept-objects was given). - * - * Set the `--preferred-pack` arbitrarily here. - */ - ; - } - - if (refs_snapshot) - strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot); - - ret = start_command(&cmd); - if (ret) - return ret; - - in = xfdopen(cmd.in, "w"); - for_each_string_list_item(item, include) - fprintf(in, "%s\n", item->string); - fclose(in); - - return finish_command(&cmd); -} - -static void remove_redundant_bitmaps(struct string_list *include, - const char *packdir) -{ - struct strbuf path = STRBUF_INIT; - struct string_list_item *item; - size_t packdir_len; - - strbuf_addstr(&path, packdir); - strbuf_addch(&path, '/'); - packdir_len = path.len; - - /* - * Remove any pack bitmaps corresponding to packs which are now - * included in the MIDX. - */ - for_each_string_list_item(item, include) { - strbuf_addstr(&path, item->string); - strbuf_strip_suffix(&path, ".idx"); - strbuf_addstr(&path, ".bitmap"); - - if (unlink(path.buf) && errno != ENOENT) - warning_errno(_("could not remove stale bitmap: %s"), - path.buf); - - strbuf_setlen(&path, packdir_len); - } - strbuf_release(&path); -} - -static int finish_pack_objects_cmd(struct child_process *cmd, - struct string_list *names, - int local) -{ - FILE *out; - struct strbuf line = STRBUF_INIT; - - out = xfdopen(cmd->out, "r"); - while (strbuf_getline_lf(&line, out) != EOF) { - struct string_list_item *item; - - if (line.len != the_hash_algo->hexsz) - die(_("repack: Expecting full hex object ID lines only " - "from pack-objects.")); - /* - * Avoid putting packs written outside of the repository in the - * list of names. - */ - if (local) { - item = string_list_append(names, line.buf); - item->util = populate_pack_exts(line.buf); - } - } - fclose(out); - - strbuf_release(&line); - - return finish_command(cmd); -} - -static int write_filtered_pack(const struct pack_objects_args *args, - const char *destination, - const char *pack_prefix, - struct existing_packs *existing, - struct string_list *names) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - struct string_list_item *item; - FILE *in; - int ret; - const char *caret; - const char *scratch; - int local = skip_prefix(destination, packdir, &scratch); - - prepare_pack_objects(&cmd, args, destination); - - strvec_push(&cmd.args, "--stdin-packs"); - - if (!pack_kept_objects) - strvec_push(&cmd.args, "--honor-pack-keep"); - for_each_string_list_item(item, &existing->kept_packs) - strvec_pushf(&cmd.args, "--keep-pack=%s", item->string); - - cmd.in = -1; - - ret = start_command(&cmd); - if (ret) - return ret; - - /* - * Here 'names' contains only the pack(s) that were just - * written, which is exactly the packs we want to keep. Also - * 'existing_kept_packs' already contains the packs in - * 'keep_pack_list'. - */ - in = xfdopen(cmd.in, "w"); - for_each_string_list_item(item, names) - fprintf(in, "^%s-%s.pack\n", pack_prefix, item->string); - for_each_string_list_item(item, &existing->non_kept_packs) - fprintf(in, "%s.pack\n", item->string); - for_each_string_list_item(item, &existing->cruft_packs) - fprintf(in, "%s.pack\n", item->string); - caret = pack_kept_objects ? "" : "^"; - for_each_string_list_item(item, &existing->kept_packs) - fprintf(in, "%s%s.pack\n", caret, item->string); - fclose(in); - - return finish_pack_objects_cmd(&cmd, names, local); -} - -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 = packfile_store_get_all_packs(packs); p; p = p->next) { - if (!(p->is_cruft && p->pack_local)) - continue; - - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(p)); - strbuf_strip_suffix(&buf, ".pack"); - - if (!string_list_has_string(&existing->cruft_packs, buf.buf)) - continue; - - if (p->pack_size < combine_cruft_below_size) { - fprintf(in, "-%s\n", pack_basename(p)); - } else { - retain_cruft_pack(existing, p); - fprintf(in, "%s\n", pack_basename(p)); - } - } - - for (i = 0; i < existing->non_kept_packs.nr; i++) - fprintf(in, "-%s.pack\n", - existing->non_kept_packs.items[i].string); - - strbuf_release(&buf); -} - -static int write_cruft_pack(const struct pack_objects_args *args, - const char *destination, - const char *pack_prefix, - const char *cruft_expiration, - unsigned long combine_cruft_below_size, - struct string_list *names, - struct existing_packs *existing) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - struct string_list_item *item; - FILE *in; - int ret; - const char *scratch; - int local = skip_prefix(destination, packdir, &scratch); - - prepare_pack_objects(&cmd, args, destination); - - strvec_push(&cmd.args, "--cruft"); - if (cruft_expiration) - strvec_pushf(&cmd.args, "--cruft-expiration=%s", - cruft_expiration); - - strvec_push(&cmd.args, "--honor-pack-keep"); - strvec_push(&cmd.args, "--non-empty"); - - cmd.in = -1; - - ret = start_command(&cmd); - if (ret) - return ret; - - /* - * names has a confusing double use: it both provides the list - * of just-written new packs, and accepts the name of the cruft - * pack we are writing. - * - * By the time it is read here, it contains only the pack(s) - * that were just written, which is exactly the set of packs we - * want to consider kept. - * - * If `--expire-to` is given, the double-use served by `names` - * ensures that the pack written to `--expire-to` excludes any - * objects contained in the cruft pack. - */ - in = xfdopen(cmd.in, "w"); - for_each_string_list_item(item, names) - fprintf(in, "%s-%s.pack\n", pack_prefix, item->string); - if (combine_cruft_below_size && !cruft_expiration) { - combine_small_cruft_packs(in, combine_cruft_below_size, - existing); - } else { - for_each_string_list_item(item, &existing->non_kept_packs) - fprintf(in, "-%s.pack\n", item->string); - for_each_string_list_item(item, &existing->cruft_packs) - fprintf(in, "-%s.pack\n", item->string); - } - for_each_string_list_item(item, &existing->kept_packs) - fprintf(in, "%s.pack\n", item->string); - fclose(in); - - return finish_pack_objects_cmd(&cmd, names, local); -} - -static const char *find_pack_prefix(const char *packdir, const char *packtmp) -{ - const char *pack_prefix; - if (!skip_prefix(packtmp, packdir, &pack_prefix)) - die(_("pack prefix %s does not begin with objdir %s"), - packtmp, packdir); - if (*pack_prefix == '/') - pack_prefix++; - return pack_prefix; -} - int cmd_repack(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { struct child_process cmd = CHILD_PROCESS_INIT; struct string_list_item *item; @@ -1255,18 +108,17 @@ int cmd_repack(int argc, struct existing_packs existing = EXISTING_PACKS_INIT; struct pack_geometry geometry = { 0 }; struct tempfile *refs_snapshot = NULL; - int i, ext, ret; + int i, ret; int show_progress; - char **midx_pack_names = NULL; - size_t midx_pack_names_nr = 0; /* variables to be filled by option parsing */ + struct repack_config_ctx config_ctx; int delete_redundant = 0; const char *unpack_unreachable = NULL; int keep_unreachable = 0; struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; - struct pack_objects_args po_args = { 0 }; - struct pack_objects_args cruft_po_args = { 0 }; + struct pack_objects_args po_args = PACK_OBJECTS_ARGS_INIT; + struct pack_objects_args cruft_po_args = PACK_OBJECTS_ARGS_INIT; int write_midx = 0; const char *cruft_expiration = NULL; const char *expire_to = NULL; @@ -1327,7 +179,7 @@ int cmd_repack(int argc, OPT_UNSIGNED(0, "max-pack-size", &po_args.max_pack_size, N_("maximum size of each packfile")), OPT_PARSE_LIST_OBJECTS_FILTER(&po_args.filter_options), - OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects, + OPT_BOOL(0, "pack-kept-objects", &po_args.pack_kept_objects, N_("repack objects in packs marked with .keep")), OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), N_("do not repack this pack")), @@ -1344,7 +196,11 @@ int cmd_repack(int argc, list_objects_filter_init(&po_args.filter_options); - repo_config(the_repository, repack_config, &cruft_po_args); + memset(&config_ctx, 0, sizeof(config_ctx)); + config_ctx.po_args = &po_args; + config_ctx.cruft_po_args = &cruft_po_args; + + repo_config(repo, repack_config, &config_ctx); argc = parse_options(argc, argv, prefix, builtin_repack_options, git_repack_usage, 0); @@ -1354,7 +210,7 @@ int cmd_repack(int argc, po_args.depth = xstrdup_or_null(opt_depth); po_args.threads = xstrdup_or_null(opt_threads); - if (delete_redundant && the_repository->repository_format_precious_objects) + if (delete_redundant && repo->repository_format_precious_objects) die(_("cannot delete packs in a precious-objects repo")); die_for_incompatible_opt3(unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE), "-A", @@ -1369,14 +225,14 @@ int cmd_repack(int argc, (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository())) write_bitmaps = 0; } - if (pack_kept_objects < 0) - pack_kept_objects = write_bitmaps > 0 && !write_midx; + if (po_args.pack_kept_objects < 0) + po_args.pack_kept_objects = write_bitmaps > 0 && !write_midx; if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx) die(_(incremental_bitmap_conflict_error)); if (write_bitmaps && po_args.local && - odb_has_alternates(the_repository->objects)) { + odb_has_alternates(repo->objects)) { /* * When asked to do a local repack, but we have * packfiles that are inherited from an alternate, then @@ -1391,26 +247,28 @@ int cmd_repack(int argc, if (write_midx && write_bitmaps) { struct strbuf path = STRBUF_INIT; - strbuf_addf(&path, "%s/%s_XXXXXX", repo_get_object_directory(the_repository), + strbuf_addf(&path, "%s/%s_XXXXXX", + repo_get_object_directory(repo), "bitmap-ref-tips"); refs_snapshot = xmks_tempfile(path.buf); - midx_snapshot_refs(refs_snapshot); + midx_snapshot_refs(repo, refs_snapshot); strbuf_release(&path); } - packdir = mkpathdup("%s/pack", repo_get_object_directory(the_repository)); + packdir = mkpathdup("%s/pack", repo_get_object_directory(repo)); packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid()); packtmp = mkpathdup("%s/%s", packdir, packtmp_name); - collect_pack_filenames(&existing, &keep_pack_list); + existing.repo = repo; + existing_packs_collect(&existing, &keep_pack_list); if (geometry.split_factor) { if (pack_everything) die(_("options '%s' and '%s' cannot be used together"), "--geometric", "-A/-a"); - init_pack_geometry(&geometry, &existing, &po_args); - split_pack_geometry(&geometry); + pack_geometry_init(&geometry, &existing, &po_args); + pack_geometry_split(&geometry); } prepare_pack_objects(&cmd, &po_args, packtmp); @@ -1418,8 +276,6 @@ int cmd_repack(int argc, show_progress = !po_args.quiet && isatty(2); strvec_push(&cmd.args, "--keep-true-parents"); - if (!pack_kept_objects) - strvec_push(&cmd.args, "--honor-pack-keep"); for (i = 0; i < keep_pack_list.nr; i++) strvec_pushf(&cmd.args, "--keep-pack=%s", keep_pack_list.items[i].string); @@ -1439,7 +295,7 @@ int cmd_repack(int argc, strvec_push(&cmd.args, "--reflog"); strvec_push(&cmd.args, "--indexed-objects"); } - if (repo_has_promisor_remote(the_repository)) + if (repo_has_promisor_remote(repo)) strvec_push(&cmd.args, "--exclude-promisor-objects"); if (!write_midx) { if (write_bitmaps > 0) @@ -1451,9 +307,9 @@ int cmd_repack(int argc, strvec_push(&cmd.args, "--delta-islands"); if (pack_everything & ALL_INTO_ONE) { - repack_promisor_objects(&po_args, &names); + repack_promisor_objects(repo, &po_args, &names, packtmp); - if (has_existing_non_kept_packs(&existing) && + if (existing_packs_has_non_kept(&existing) && delete_redundant && !(pack_everything & PACK_CRUFT)) { for_each_string_list_item(item, &names) { @@ -1515,9 +371,17 @@ int cmd_repack(int argc, fclose(in); } - ret = finish_pack_objects_cmd(&cmd, &names, 1); - if (ret) - goto cleanup; + { + struct write_pack_opts opts = { + .packdir = packdir, + .destination = packdir, + .packtmp = packtmp, + }; + ret = finish_pack_objects_cmd(repo->hash_algo, &opts, &cmd, + &names); + if (ret) + goto cleanup; + } if (!names.nr) { if (!po_args.quiet) @@ -1535,12 +399,17 @@ int cmd_repack(int argc, * midx_has_unknown_packs() will make the decision for * us. */ - if (!get_multi_pack_index(the_repository->objects->sources)) + if (!get_multi_pack_index(repo->objects->sources)) midx_must_contain_cruft = 1; } if (pack_everything & PACK_CRUFT) { - const char *pack_prefix = find_pack_prefix(packdir, packtmp); + struct write_pack_opts opts = { + .po_args = &cruft_po_args, + .destination = packtmp, + .packtmp = packtmp, + .packdir = packdir, + }; if (!cruft_po_args.window) cruft_po_args.window = xstrdup_or_null(po_args.window); @@ -1555,9 +424,10 @@ int cmd_repack(int argc, cruft_po_args.local = po_args.local; cruft_po_args.quiet = po_args.quiet; + cruft_po_args.delta_base_offset = po_args.delta_base_offset; + cruft_po_args.pack_kept_objects = 0; - ret = write_cruft_pack(&cruft_po_args, packtmp, pack_prefix, - cruft_expiration, + ret = write_cruft_pack(&opts, cruft_expiration, combine_cruft_below_size, &names, &existing); if (ret) @@ -1592,11 +462,8 @@ int cmd_repack(int argc, * pack, but rather removing all cruft packs from the * main repository regardless of size. */ - ret = write_cruft_pack(&cruft_po_args, expire_to, - pack_prefix, - NULL, - 0ul, - &names, + opts.destination = expire_to; + ret = write_cruft_pack(&opts, NULL, 0ul, &names, &existing); if (ret) goto cleanup; @@ -1604,99 +471,63 @@ int cmd_repack(int argc, } if (po_args.filter_options.choice) { - if (!filter_to) - filter_to = packtmp; - - ret = write_filtered_pack(&po_args, - filter_to, - find_pack_prefix(packdir, packtmp), - &existing, - &names); + struct write_pack_opts opts = { + .po_args = &po_args, + .destination = filter_to, + .packdir = packdir, + .packtmp = packtmp, + }; + + if (!opts.destination) + opts.destination = packtmp; + + ret = write_filtered_pack(&opts, &existing, &names); if (ret) goto cleanup; } string_list_sort(&names); - if (get_multi_pack_index(the_repository->objects->sources)) { - struct multi_pack_index *m = - get_multi_pack_index(the_repository->objects->sources); - - ALLOC_ARRAY(midx_pack_names, - m->num_packs + m->num_packs_in_base); - - for (; m; m = m->base_midx) - for (uint32_t i = 0; i < m->num_packs; i++) - midx_pack_names[midx_pack_names_nr++] = - xstrdup(m->pack_names[i]); - } - - close_object_store(the_repository->objects); + close_object_store(repo->objects); /* * Ok we have prepared all new packfiles. */ - for_each_string_list_item(item, &names) { - struct generated_pack_data *data = item->util; - - for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { - char *fname; - - fname = mkpathdup("%s/pack-%s%s", - packdir, item->string, exts[ext].name); - - if (data->tempfiles[ext]) { - const char *fname_old = get_tempfile_path(data->tempfiles[ext]); - struct stat statbuffer; - - if (!stat(fname_old, &statbuffer)) { - statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); - chmod(fname_old, statbuffer.st_mode); - } - - if (rename_tempfile(&data->tempfiles[ext], fname)) - die_errno(_("renaming pack to '%s' failed"), fname); - } else if (!exts[ext].optional) - die(_("pack-objects did not write a '%s' file for pack %s-%s"), - exts[ext].name, packtmp, item->string); - else if (unlink(fname) < 0 && errno != ENOENT) - die_errno(_("could not unlink: %s"), fname); - - free(fname); - } - } + for_each_string_list_item(item, &names) + generated_pack_install(item->util, item->string, packdir, + packtmp); /* End of pack replacement. */ if (delete_redundant && pack_everything & ALL_INTO_ONE) - mark_packs_for_deletion(&existing, &names); + existing_packs_mark_for_deletion(&existing, &names); if (write_midx) { - struct string_list include = STRING_LIST_INIT_DUP; - midx_included_packs(&include, &existing, midx_pack_names, - midx_pack_names_nr, &names, &geometry); - - ret = write_midx_included_packs(&include, &geometry, &names, - refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL, - show_progress, write_bitmaps > 0); - - if (!ret && write_bitmaps) - remove_redundant_bitmaps(&include, packdir); - - string_list_clear(&include, 0); + struct repack_write_midx_opts opts = { + .existing = &existing, + .geometry = &geometry, + .names = &names, + .refs_snapshot = refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL, + .packdir = packdir, + .show_progress = show_progress, + .write_bitmaps = write_bitmaps > 0, + .midx_must_contain_cruft = midx_must_contain_cruft + }; + + ret = write_midx_included_packs(&opts); if (ret) goto cleanup; } - odb_reprepare(the_repository->objects); + odb_reprepare(repo->objects); if (delete_redundant) { int opts = 0; - remove_redundant_existing_packs(&existing); + existing_packs_remove_redundant(&existing, packdir); if (geometry.split_factor) - geometry_remove_redundant_packs(&geometry, &names, - &existing); + pack_geometry_remove_redundant(&geometry, &names, + &existing, packdir); if (show_progress) opts |= PRUNE_PACKED_VERBOSE; prune_packed_objects(opts); @@ -1704,18 +535,18 @@ int cmd_repack(int argc, if (!keep_unreachable && (!(pack_everything & LOOSEN_UNREACHABLE) || unpack_unreachable) && - is_repository_shallow(the_repository)) + is_repository_shallow(repo)) prune_shallow(PRUNE_QUICK); } if (run_update_server_info) - update_server_info(the_repository, 0); + update_server_info(repo, 0); if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) { unsigned flags = 0; if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_INCREMENTAL, 0)) flags |= MIDX_WRITE_INCREMENTAL; - write_midx_file(the_repository->objects->sources, + write_midx_file(repo->objects->sources, NULL, NULL, flags); } @@ -1723,10 +554,7 @@ cleanup: string_list_clear(&keep_pack_list, 0); string_list_clear(&names, 1); existing_packs_release(&existing); - free_pack_geometry(&geometry); - for (size_t i = 0; i < midx_pack_names_nr; i++) - free(midx_pack_names[i]); - free(midx_pack_names); + pack_geometry_release(&geometry); pack_objects_args_release(&po_args); pack_objects_args_release(&cruft_po_args); diff --git a/builtin/repo.c b/builtin/repo.c index bbb0966f2d..9d4749f79b 100644 --- a/builtin/repo.c +++ b/builtin/repo.c @@ -3,19 +3,27 @@ #include "builtin.h" #include "environment.h" #include "parse-options.h" +#include "path-walk.h" +#include "progress.h" #include "quote.h" +#include "ref-filter.h" #include "refs.h" +#include "revision.h" #include "strbuf.h" +#include "string-list.h" #include "shallow.h" +#include "utf8.h" static const char *const repo_usage[] = { "git repo info [--format=(keyvalue|nul)] [-z] [<key>...]", + "git repo structure [--format=(table|keyvalue|nul)]", NULL }; typedef int get_value_fn(struct repository *repo, struct strbuf *buf); enum output_format { + FORMAT_TABLE, FORMAT_KEYVALUE, FORMAT_NUL_TERMINATED, }; @@ -130,14 +138,16 @@ static int parse_format_cb(const struct option *opt, *format = FORMAT_NUL_TERMINATED; else if (!strcmp(arg, "keyvalue")) *format = FORMAT_KEYVALUE; + else if (!strcmp(arg, "table")) + *format = FORMAT_TABLE; else die(_("invalid format '%s'"), arg); return 0; } -static int repo_info(int argc, const char **argv, const char *prefix, - struct repository *repo) +static int cmd_repo_info(int argc, const char **argv, const char *prefix, + struct repository *repo) { enum output_format format = FORMAT_KEYVALUE; struct option options[] = { @@ -152,16 +162,380 @@ static int repo_info(int argc, const char **argv, const char *prefix, }; argc = parse_options(argc, argv, prefix, options, repo_usage, 0); + if (format != FORMAT_KEYVALUE && format != FORMAT_NUL_TERMINATED) + die(_("unsupported output format")); return print_fields(argc, argv, repo, format); } +struct ref_stats { + size_t branches; + size_t remotes; + size_t tags; + size_t others; +}; + +struct object_stats { + size_t tags; + size_t commits; + size_t trees; + size_t blobs; +}; + +struct repo_structure { + struct ref_stats refs; + struct object_stats objects; +}; + +struct stats_table { + struct string_list rows; + + int name_col_width; + int value_col_width; +}; + +/* + * Holds column data that gets stored for each row. + */ +struct stats_table_entry { + char *value; +}; + +static void stats_table_vaddf(struct stats_table *table, + struct stats_table_entry *entry, + const char *format, va_list ap) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + char *formatted_name; + int name_width; + + strbuf_vaddf(&buf, format, ap); + formatted_name = strbuf_detach(&buf, NULL); + name_width = utf8_strwidth(formatted_name); + + item = string_list_append_nodup(&table->rows, formatted_name); + item->util = entry; + + if (name_width > table->name_col_width) + table->name_col_width = name_width; + if (entry) { + int value_width = utf8_strwidth(entry->value); + if (value_width > table->value_col_width) + table->value_col_width = value_width; + } +} + +static void stats_table_addf(struct stats_table *table, const char *format, ...) +{ + va_list ap; + + va_start(ap, format); + stats_table_vaddf(table, NULL, format, ap); + va_end(ap); +} + +static void stats_table_count_addf(struct stats_table *table, size_t value, + const char *format, ...) +{ + struct stats_table_entry *entry; + va_list ap; + + CALLOC_ARRAY(entry, 1); + entry->value = xstrfmt("%" PRIuMAX, (uintmax_t)value); + + va_start(ap, format); + stats_table_vaddf(table, entry, format, ap); + va_end(ap); +} + +static inline size_t get_total_reference_count(struct ref_stats *stats) +{ + return stats->branches + stats->remotes + stats->tags + stats->others; +} + +static inline size_t get_total_object_count(struct object_stats *stats) +{ + return stats->tags + stats->commits + stats->trees + stats->blobs; +} + +static void stats_table_setup_structure(struct stats_table *table, + struct repo_structure *stats) +{ + struct object_stats *objects = &stats->objects; + struct ref_stats *refs = &stats->refs; + size_t object_total; + size_t ref_total; + + ref_total = get_total_reference_count(refs); + stats_table_addf(table, "* %s", _("References")); + stats_table_count_addf(table, ref_total, " * %s", _("Count")); + stats_table_count_addf(table, refs->branches, " * %s", _("Branches")); + stats_table_count_addf(table, refs->tags, " * %s", _("Tags")); + stats_table_count_addf(table, refs->remotes, " * %s", _("Remotes")); + stats_table_count_addf(table, refs->others, " * %s", _("Others")); + + object_total = get_total_object_count(objects); + stats_table_addf(table, ""); + stats_table_addf(table, "* %s", _("Reachable objects")); + stats_table_count_addf(table, object_total, " * %s", _("Count")); + stats_table_count_addf(table, objects->commits, " * %s", _("Commits")); + stats_table_count_addf(table, objects->trees, " * %s", _("Trees")); + stats_table_count_addf(table, objects->blobs, " * %s", _("Blobs")); + stats_table_count_addf(table, objects->tags, " * %s", _("Tags")); +} + +static void stats_table_print_structure(const struct stats_table *table) +{ + const char *name_col_title = _("Repository structure"); + const char *value_col_title = _("Value"); + int name_col_width = utf8_strwidth(name_col_title); + int value_col_width = utf8_strwidth(value_col_title); + struct string_list_item *item; + + if (table->name_col_width > name_col_width) + name_col_width = table->name_col_width; + if (table->value_col_width > value_col_width) + value_col_width = table->value_col_width; + + printf("| %-*s | %-*s |\n", name_col_width, name_col_title, + value_col_width, value_col_title); + printf("| "); + for (int i = 0; i < name_col_width; i++) + putchar('-'); + printf(" | "); + for (int i = 0; i < value_col_width; i++) + putchar('-'); + printf(" |\n"); + + for_each_string_list_item(item, &table->rows) { + struct stats_table_entry *entry = item->util; + const char *value = ""; + + if (entry) { + struct stats_table_entry *entry = item->util; + value = entry->value; + } + + printf("| %-*s | %*s |\n", name_col_width, item->string, + value_col_width, value); + } +} + +static void stats_table_clear(struct stats_table *table) +{ + struct stats_table_entry *entry; + struct string_list_item *item; + + for_each_string_list_item(item, &table->rows) { + entry = item->util; + if (entry) + free(entry->value); + } + + string_list_clear(&table->rows, 1); +} + +static void structure_keyvalue_print(struct repo_structure *stats, + char key_delim, char value_delim) +{ + printf("references.branches.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.branches, value_delim); + printf("references.tags.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.tags, value_delim); + printf("references.remotes.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.remotes, value_delim); + printf("references.others.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.others, value_delim); + + printf("objects.commits.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.commits, value_delim); + printf("objects.trees.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.trees, value_delim); + printf("objects.blobs.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.blobs, value_delim); + printf("objects.tags.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.tags, value_delim); + + fflush(stdout); +} + +struct count_references_data { + struct ref_stats *stats; + struct rev_info *revs; + struct progress *progress; +}; + +static int count_references(const char *refname, + const char *referent UNUSED, + const struct object_id *oid, + int flags UNUSED, void *cb_data) +{ + struct count_references_data *data = cb_data; + struct ref_stats *stats = data->stats; + size_t ref_count; + + switch (ref_kind_from_refname(refname)) { + case FILTER_REFS_BRANCHES: + stats->branches++; + break; + case FILTER_REFS_REMOTES: + stats->remotes++; + break; + case FILTER_REFS_TAGS: + stats->tags++; + break; + case FILTER_REFS_OTHERS: + stats->others++; + break; + default: + BUG("unexpected reference type"); + } + + /* + * While iterating through references for counting, also add OIDs in + * preparation for the path walk. + */ + add_pending_oid(data->revs, NULL, oid, 0); + + ref_count = get_total_reference_count(stats); + display_progress(data->progress, ref_count); + + return 0; +} + +static void structure_count_references(struct ref_stats *stats, + struct rev_info *revs, + struct repository *repo, + int show_progress) +{ + struct count_references_data data = { + .stats = stats, + .revs = revs, + }; + + if (show_progress) + data.progress = start_delayed_progress(repo, + _("Counting references"), 0); + + refs_for_each_ref(get_main_ref_store(repo), count_references, &data); + stop_progress(&data.progress); +} + +struct count_objects_data { + struct object_stats *stats; + struct progress *progress; +}; + +static int count_objects(const char *path UNUSED, struct oid_array *oids, + enum object_type type, void *cb_data) +{ + struct count_objects_data *data = cb_data; + struct object_stats *stats = data->stats; + size_t object_count; + + switch (type) { + case OBJ_TAG: + stats->tags += oids->nr; + break; + case OBJ_COMMIT: + stats->commits += oids->nr; + break; + case OBJ_TREE: + stats->trees += oids->nr; + break; + case OBJ_BLOB: + stats->blobs += oids->nr; + break; + default: + BUG("invalid object type"); + } + + object_count = get_total_object_count(stats); + display_progress(data->progress, object_count); + + return 0; +} + +static void structure_count_objects(struct object_stats *stats, + struct rev_info *revs, + struct repository *repo, int show_progress) +{ + struct path_walk_info info = PATH_WALK_INFO_INIT; + struct count_objects_data data = { + .stats = stats, + }; + + info.revs = revs; + info.path_fn = count_objects; + info.path_fn_data = &data; + + if (show_progress) + data.progress = start_delayed_progress(repo, _("Counting objects"), 0); + + walk_objects_by_path(&info); + path_walk_info_clear(&info); + stop_progress(&data.progress); +} + +static int cmd_repo_structure(int argc, const char **argv, const char *prefix, + struct repository *repo) +{ + struct stats_table table = { + .rows = STRING_LIST_INIT_DUP, + }; + enum output_format format = FORMAT_TABLE; + struct repo_structure stats = { 0 }; + struct rev_info revs; + int show_progress = -1; + struct option options[] = { + OPT_CALLBACK_F(0, "format", &format, N_("format"), + N_("output format"), + PARSE_OPT_NONEG, parse_format_cb), + OPT_BOOL(0, "progress", &show_progress, N_("show progress")), + OPT_END() + }; + + argc = parse_options(argc, argv, prefix, options, repo_usage, 0); + if (argc) + usage(_("too many arguments")); + + repo_init_revisions(repo, &revs, prefix); + + if (show_progress < 0) + show_progress = isatty(2); + + structure_count_references(&stats.refs, &revs, repo, show_progress); + structure_count_objects(&stats.objects, &revs, repo, show_progress); + + switch (format) { + case FORMAT_TABLE: + stats_table_setup_structure(&table, &stats); + stats_table_print_structure(&table); + break; + case FORMAT_KEYVALUE: + structure_keyvalue_print(&stats, '=', '\n'); + break; + case FORMAT_NUL_TERMINATED: + structure_keyvalue_print(&stats, '\n', '\0'); + break; + default: + BUG("invalid output format"); + } + + stats_table_clear(&table); + release_revisions(&revs); + + return 0; +} + int cmd_repo(int argc, const char **argv, const char *prefix, struct repository *repo) { parse_opt_subcommand_fn *fn = NULL; struct option options[] = { - OPT_SUBCOMMAND("info", &fn, repo_info), + OPT_SUBCOMMAND("info", &fn, cmd_repo_info), + OPT_SUBCOMMAND("structure", &fn, cmd_repo_structure), OPT_END() }; diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index 8c333b3e2e..15d51e60a8 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -2,6 +2,7 @@ #define DISABLE_SIGN_COMPARE_WARNINGS #include "builtin.h" +#include "abspath.h" #include "config.h" #include "dir.h" #include "environment.h" @@ -23,7 +24,7 @@ static const char *empty_base = ""; static char const * const builtin_sparse_checkout_usage[] = { - N_("git sparse-checkout (init | list | set | add | reapply | disable | check-rules) [<options>]"), + N_("git sparse-checkout (init | list | set | add | reapply | disable | check-rules | clean) [<options>]"), NULL }; @@ -204,12 +205,12 @@ static void clean_tracked_sparse_directories(struct repository *r) ensure_full_index(r->index); } -static int update_working_directory(struct pattern_list *pl) +static int update_working_directory(struct repository *r, + struct pattern_list *pl) { enum update_sparsity_result result; struct unpack_trees_options o; struct lock_file lock_file = LOCK_INIT; - struct repository *r = the_repository; struct pattern_list *old_pl; /* If no branch has been checked out, there are no updates to make. */ @@ -327,7 +328,8 @@ static void write_cone_to_file(FILE *fp, struct pattern_list *pl) string_list_clear(&sl, 0); } -static int write_patterns_and_update(struct pattern_list *pl) +static int write_patterns_and_update(struct repository *repo, + struct pattern_list *pl) { char *sparse_filename; FILE *fp; @@ -336,15 +338,15 @@ static int write_patterns_and_update(struct pattern_list *pl) sparse_filename = get_sparse_checkout_filename(); - if (safe_create_leading_directories(the_repository, sparse_filename)) + if (safe_create_leading_directories(repo, sparse_filename)) die(_("failed to create directory for sparse-checkout file")); hold_lock_file_for_update(&lk, sparse_filename, LOCK_DIE_ON_ERROR); - result = update_working_directory(pl); + result = update_working_directory(repo, pl); if (result) { rollback_lock_file(&lk); - update_working_directory(NULL); + update_working_directory(repo, NULL); goto out; } @@ -372,25 +374,26 @@ enum sparse_checkout_mode { MODE_CONE_PATTERNS = 2, }; -static int set_config(enum sparse_checkout_mode mode) +static int set_config(struct repository *repo, + enum sparse_checkout_mode mode) { /* Update to use worktree config, if not already. */ - if (init_worktree_config(the_repository)) { + if (init_worktree_config(repo)) { error(_("failed to initialize worktree config")); return 1; } - if (repo_config_set_worktree_gently(the_repository, + if (repo_config_set_worktree_gently(repo, "core.sparseCheckout", mode ? "true" : "false") || - repo_config_set_worktree_gently(the_repository, + repo_config_set_worktree_gently(repo, "core.sparseCheckoutCone", mode == MODE_CONE_PATTERNS ? "true" : "false")) return 1; if (mode == MODE_NO_PATTERNS) - return set_sparse_index_config(the_repository, 0); + return set_sparse_index_config(repo, 0); return 0; } @@ -410,7 +413,7 @@ static enum sparse_checkout_mode update_cone_mode(int *cone_mode) { return MODE_ALL_PATTERNS; } -static int update_modes(int *cone_mode, int *sparse_index) +static int update_modes(struct repository *repo, int *cone_mode, int *sparse_index) { int mode, record_mode; @@ -418,20 +421,20 @@ static int update_modes(int *cone_mode, int *sparse_index) record_mode = (*cone_mode != -1) || !core_apply_sparse_checkout; mode = update_cone_mode(cone_mode); - if (record_mode && set_config(mode)) + if (record_mode && set_config(repo, mode)) return 1; /* Set sparse-index/non-sparse-index mode if specified */ if (*sparse_index >= 0) { - if (set_sparse_index_config(the_repository, *sparse_index) < 0) + if (set_sparse_index_config(repo, *sparse_index) < 0) die(_("failed to modify sparse-index config")); /* force an index rewrite */ - repo_read_index(the_repository); - the_repository->index->updated_workdir = 1; + repo_read_index(repo); + repo->index->updated_workdir = 1; if (!*sparse_index) - ensure_full_index(the_repository->index); + ensure_full_index(repo->index); } return 0; @@ -448,7 +451,7 @@ static struct sparse_checkout_init_opts { } init_opts; static int sparse_checkout_init(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { struct pattern_list pl; char *sparse_filename; @@ -464,7 +467,7 @@ static int sparse_checkout_init(int argc, const char **argv, const char *prefix, }; setup_work_tree(); - repo_read_index(the_repository); + repo_read_index(repo); init_opts.cone_mode = -1; init_opts.sparse_index = -1; @@ -473,7 +476,7 @@ static int sparse_checkout_init(int argc, const char **argv, const char *prefix, builtin_sparse_checkout_init_options, builtin_sparse_checkout_init_usage, 0); - if (update_modes(&init_opts.cone_mode, &init_opts.sparse_index)) + if (update_modes(repo, &init_opts.cone_mode, &init_opts.sparse_index)) return 1; memset(&pl, 0, sizeof(pl)); @@ -485,14 +488,14 @@ static int sparse_checkout_init(int argc, const char **argv, const char *prefix, if (res >= 0) { free(sparse_filename); clear_pattern_list(&pl); - return update_working_directory(NULL); + return update_working_directory(repo, NULL); } - if (repo_get_oid(the_repository, "HEAD", &oid)) { + if (repo_get_oid(repo, "HEAD", &oid)) { FILE *fp; /* assume we are in a fresh repo, but update the sparse-checkout file */ - if (safe_create_leading_directories(the_repository, sparse_filename)) + if (safe_create_leading_directories(repo, sparse_filename)) die(_("unable to create leading directories of %s"), sparse_filename); fp = xfopen(sparse_filename, "w"); @@ -511,7 +514,7 @@ static int sparse_checkout_init(int argc, const char **argv, const char *prefix, add_pattern("!/*/", empty_base, 0, &pl, 0); pl.use_cone_patterns = init_opts.cone_mode; - return write_patterns_and_update(&pl); + return write_patterns_and_update(repo, &pl); } static void insert_recursive_pattern(struct pattern_list *pl, struct strbuf *path) @@ -674,7 +677,8 @@ static void add_patterns_literal(int argc, const char **argv, add_patterns_from_input(pl, argc, argv, use_stdin ? stdin : NULL); } -static int modify_pattern_list(struct strvec *args, int use_stdin, +static int modify_pattern_list(struct repository *repo, + struct strvec *args, int use_stdin, enum modify_type m) { int result; @@ -696,22 +700,23 @@ static int modify_pattern_list(struct strvec *args, int use_stdin, } if (!core_apply_sparse_checkout) { - set_config(MODE_ALL_PATTERNS); + set_config(repo, MODE_ALL_PATTERNS); core_apply_sparse_checkout = 1; changed_config = 1; } - result = write_patterns_and_update(pl); + result = write_patterns_and_update(repo, pl); if (result && changed_config) - set_config(MODE_NO_PATTERNS); + set_config(repo, MODE_NO_PATTERNS); clear_pattern_list(pl); free(pl); return result; } -static void sanitize_paths(struct strvec *args, +static void sanitize_paths(struct repository *repo, + struct strvec *args, const char *prefix, int skip_checks) { int i; @@ -752,7 +757,7 @@ static void sanitize_paths(struct strvec *args, for (i = 0; i < args->nr; i++) { struct cache_entry *ce; - struct index_state *index = the_repository->index; + struct index_state *index = repo->index; int pos = index_name_pos(index, args->v[i], strlen(args->v[i])); if (pos < 0) @@ -779,7 +784,7 @@ static struct sparse_checkout_add_opts { } add_opts; static int sparse_checkout_add(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { static struct option builtin_sparse_checkout_add_options[] = { OPT_BOOL_F(0, "skip-checks", &add_opts.skip_checks, @@ -796,7 +801,7 @@ static int sparse_checkout_add(int argc, const char **argv, const char *prefix, if (!core_apply_sparse_checkout) die(_("no sparse-checkout to add to")); - repo_read_index(the_repository); + repo_read_index(repo); argc = parse_options(argc, argv, prefix, builtin_sparse_checkout_add_options, @@ -804,9 +809,9 @@ static int sparse_checkout_add(int argc, const char **argv, const char *prefix, for (int i = 0; i < argc; i++) strvec_push(&patterns, argv[i]); - sanitize_paths(&patterns, prefix, add_opts.skip_checks); + sanitize_paths(repo, &patterns, prefix, add_opts.skip_checks); - ret = modify_pattern_list(&patterns, add_opts.use_stdin, ADD); + ret = modify_pattern_list(repo, &patterns, add_opts.use_stdin, ADD); strvec_clear(&patterns); return ret; @@ -825,7 +830,7 @@ static struct sparse_checkout_set_opts { } set_opts; static int sparse_checkout_set(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { int default_patterns_nr = 2; const char *default_patterns[] = {"/*", "!/*/", NULL}; @@ -847,7 +852,7 @@ static int sparse_checkout_set(int argc, const char **argv, const char *prefix, int ret; setup_work_tree(); - repo_read_index(the_repository); + repo_read_index(repo); set_opts.cone_mode = -1; set_opts.sparse_index = -1; @@ -856,7 +861,7 @@ static int sparse_checkout_set(int argc, const char **argv, const char *prefix, builtin_sparse_checkout_set_options, builtin_sparse_checkout_set_usage, 0); - if (update_modes(&set_opts.cone_mode, &set_opts.sparse_index)) + if (update_modes(repo, &set_opts.cone_mode, &set_opts.sparse_index)) return 1; /* @@ -870,10 +875,10 @@ static int sparse_checkout_set(int argc, const char **argv, const char *prefix, } else { for (int i = 0; i < argc; i++) strvec_push(&patterns, argv[i]); - sanitize_paths(&patterns, prefix, set_opts.skip_checks); + sanitize_paths(repo, &patterns, prefix, set_opts.skip_checks); } - ret = modify_pattern_list(&patterns, set_opts.use_stdin, REPLACE); + ret = modify_pattern_list(repo, &patterns, set_opts.use_stdin, REPLACE); strvec_clear(&patterns); return ret; @@ -891,7 +896,7 @@ static struct sparse_checkout_reapply_opts { static int sparse_checkout_reapply(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { static struct option builtin_sparse_checkout_reapply_options[] = { OPT_BOOL(0, "cone", &reapply_opts.cone_mode, @@ -912,12 +917,107 @@ static int sparse_checkout_reapply(int argc, const char **argv, builtin_sparse_checkout_reapply_options, builtin_sparse_checkout_reapply_usage, 0); - repo_read_index(the_repository); + repo_read_index(repo); - if (update_modes(&reapply_opts.cone_mode, &reapply_opts.sparse_index)) + if (update_modes(repo, &reapply_opts.cone_mode, &reapply_opts.sparse_index)) return 1; - return update_working_directory(NULL); + return update_working_directory(repo, NULL); +} + +static char const * const builtin_sparse_checkout_clean_usage[] = { + "git sparse-checkout clean [-n|--dry-run]", + NULL +}; + +static int list_file_iterator(const char *path, const void *data) +{ + const char *msg = data; + + printf(msg, path); + return 0; +} + +static void list_every_file_in_dir(const char *msg, + const char *directory) +{ + struct strbuf path = STRBUF_INIT; + + strbuf_addstr(&path, directory); + for_each_file_in_dir(&path, list_file_iterator, msg); + strbuf_release(&path); +} + +static const char *msg_remove = N_("Removing %s\n"); +static const char *msg_would_remove = N_("Would remove %s\n"); + +static int sparse_checkout_clean(int argc, const char **argv, + const char *prefix, + struct repository *repo) +{ + struct strbuf full_path = STRBUF_INIT; + const char *msg = msg_remove; + size_t worktree_len; + int force = 0, dry_run = 0, verbose = 0; + int require_force = 1; + + struct option builtin_sparse_checkout_clean_options[] = { + OPT__DRY_RUN(&dry_run, N_("dry run")), + OPT__FORCE(&force, N_("force"), PARSE_OPT_NOCOMPLETE), + OPT__VERBOSE(&verbose, N_("report each affected file, not just directories")), + OPT_END(), + }; + + setup_work_tree(); + if (!core_apply_sparse_checkout) + die(_("must be in a sparse-checkout to clean directories")); + if (!core_sparse_checkout_cone) + die(_("must be in a cone-mode sparse-checkout to clean directories")); + + argc = parse_options(argc, argv, prefix, + builtin_sparse_checkout_clean_options, + builtin_sparse_checkout_clean_usage, 0); + + repo_config_get_bool(repo, "clean.requireforce", &require_force); + if (require_force && !force && !dry_run) + die(_("for safety, refusing to clean without one of --force or --dry-run")); + + if (dry_run) + msg = msg_would_remove; + + if (repo_read_index(repo) < 0) + die(_("failed to read index")); + + if (convert_to_sparse(repo->index, SPARSE_INDEX_MEMORY_ONLY) || + repo->index->sparse_index == INDEX_EXPANDED) + die(_("failed to convert index to a sparse index; resolve merge conflicts and try again")); + + strbuf_addstr(&full_path, repo->worktree); + strbuf_addch(&full_path, '/'); + worktree_len = full_path.len; + + for (size_t i = 0; i < repo->index->cache_nr; i++) { + struct cache_entry *ce = repo->index->cache[i]; + if (!S_ISSPARSEDIR(ce->ce_mode)) + continue; + strbuf_setlen(&full_path, worktree_len); + strbuf_add(&full_path, ce->name, ce->ce_namelen); + + if (!is_directory(full_path.buf)) + continue; + + if (verbose) + list_every_file_in_dir(msg, ce->name); + else + printf(msg, ce->name); + + if (dry_run <= 0 && + remove_dir_recursively(&full_path, 0)) + warning_errno(_("failed to remove '%s'"), ce->name); + } + + strbuf_release(&full_path); + return 0; } static char const * const builtin_sparse_checkout_disable_usage[] = { @@ -927,7 +1027,7 @@ static char const * const builtin_sparse_checkout_disable_usage[] = { static int sparse_checkout_disable(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { static struct option builtin_sparse_checkout_disable_options[] = { OPT_END(), @@ -955,7 +1055,7 @@ static int sparse_checkout_disable(int argc, const char **argv, * are expecting to do that when disabling sparse-checkout. */ give_advice_on_expansion = 0; - repo_read_index(the_repository); + repo_read_index(repo); memset(&pl, 0, sizeof(pl)); hashmap_init(&pl.recursive_hashmap, pl_hashmap_cmp, NULL, 0); @@ -966,13 +1066,13 @@ static int sparse_checkout_disable(int argc, const char **argv, add_pattern("/*", empty_base, 0, &pl, 0); prepare_repo_settings(the_repository); - the_repository->settings.sparse_index = 0; + repo->settings.sparse_index = 0; - if (update_working_directory(&pl)) + if (update_working_directory(repo, &pl)) die(_("error while refreshing working directory")); clear_pattern_list(&pl); - return set_config(MODE_NO_PATTERNS); + return set_config(repo, MODE_NO_PATTERNS); } static char const * const builtin_sparse_checkout_check_rules_usage[] = { @@ -987,14 +1087,17 @@ static struct sparse_checkout_check_rules_opts { char *rules_file; } check_rules_opts; -static int check_rules(struct pattern_list *pl, int null_terminated) { +static int check_rules(struct repository *repo, + struct pattern_list *pl, + int null_terminated) +{ struct strbuf line = STRBUF_INIT; struct strbuf unquoted = STRBUF_INIT; char *path; int line_terminator = null_terminated ? 0 : '\n'; strbuf_getline_fn getline_fn = null_terminated ? strbuf_getline_nul : strbuf_getline; - the_repository->index->sparse_checkout_patterns = pl; + repo->index->sparse_checkout_patterns = pl; while (!getline_fn(&line, stdin)) { path = line.buf; if (!null_terminated && line.buf[0] == '"') { @@ -1006,7 +1109,7 @@ static int check_rules(struct pattern_list *pl, int null_terminated) { path = unquoted.buf; } - if (path_in_sparse_checkout(path, the_repository->index)) + if (path_in_sparse_checkout(path, repo->index)) write_name_quoted(path, stdout, line_terminator); } strbuf_release(&line); @@ -1016,7 +1119,7 @@ static int check_rules(struct pattern_list *pl, int null_terminated) { } static int sparse_checkout_check_rules(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { static struct option builtin_sparse_checkout_check_rules_options[] = { OPT_BOOL('z', NULL, &check_rules_opts.null_termination, @@ -1055,7 +1158,7 @@ static int sparse_checkout_check_rules(int argc, const char **argv, const char * free(sparse_filename); } - ret = check_rules(&pl, check_rules_opts.null_termination); + ret = check_rules(repo, &pl, check_rules_opts.null_termination); clear_pattern_list(&pl); free(check_rules_opts.rules_file); return ret; @@ -1073,6 +1176,7 @@ int cmd_sparse_checkout(int argc, OPT_SUBCOMMAND("set", &fn, sparse_checkout_set), OPT_SUBCOMMAND("add", &fn, sparse_checkout_add), OPT_SUBCOMMAND("reapply", &fn, sparse_checkout_reapply), + OPT_SUBCOMMAND("clean", &fn, sparse_checkout_clean), OPT_SUBCOMMAND("disable", &fn, sparse_checkout_disable), OPT_SUBCOMMAND("check-rules", &fn, sparse_checkout_check_rules), OPT_END(), @@ -1084,8 +1188,8 @@ int cmd_sparse_checkout(int argc, repo_config(the_repository, git_default_config, NULL); - prepare_repo_settings(the_repository); - the_repository->settings.command_requires_full_index = 0; + prepare_repo_settings(repo); + repo->settings.command_requires_full_index = 0; return fn(argc, argv, prefix, repo); } diff --git a/ci/install-dependencies.sh b/ci/install-dependencies.sh index a8dcd9b9bc..50628ee2dd 100755 --- a/ci/install-dependencies.sh +++ b/ci/install-dependencies.sh @@ -10,6 +10,8 @@ begin_group "Install dependencies" P4WHENCE=https://cdist2.perforce.com/perforce/r23.2 LFSWHENCE=https://github.com/github/git-lfs/releases/download/v$LINUX_GIT_LFS_VERSION JGITWHENCE=https://repo1.maven.org/maven2/org/eclipse/jgit/org.eclipse.jgit.pgm/6.8.0.202311291450-r/org.eclipse.jgit.pgm-6.8.0.202311291450-r.sh +CARGO_MSRV_VERSION=0.18.4 +CARGO_MSRV_WHENCE=https://github.com/foresterre/cargo-msrv/releases/download/v$CARGO_MSRV_VERSION/cargo-msrv-x86_64-unknown-linux-musl-v$CARGO_MSRV_VERSION.tgz # Make sudo a no-op and execute the command directly when running as root. # While using sudo would be fine on most platforms when we are root already, @@ -129,21 +131,28 @@ esac case "$jobname" in ClangFormat) - sudo apt-get -q update sudo apt-get -q -y install clang-format ;; StaticAnalysis) - sudo apt-get -q update sudo apt-get -q -y install coccinelle libcurl4-openssl-dev libssl-dev \ libexpat-dev gettext make ;; +RustAnalysis) + sudo apt-get -q -y install rustup + rustup default stable + rustup component add clippy rustfmt + + wget -q "$CARGO_MSRV_WHENCE" -O "cargo-msvc.tgz" + sudo mkdir -p "$CUSTOM_PATH" + sudo tar -xf "cargo-msvc.tgz" --strip-components=1 \ + --directory "$CUSTOM_PATH" --wildcards "*/cargo-msrv" + sudo chmod a+x "$CUSTOM_PATH/cargo-msrv" + ;; sparse) - sudo apt-get -q update -q sudo apt-get -q -y install libssl-dev libcurl4-openssl-dev \ libexpat-dev gettext zlib1g-dev sparse ;; Documentation) - sudo apt-get -q update sudo apt-get -q -y install asciidoc xmlto docbook-xsl-ns make test -n "$ALREADY_HAVE_ASCIIDOCTOR" || diff --git a/ci/run-rust-checks.sh b/ci/run-rust-checks.sh new file mode 100755 index 0000000000..b5ad9e8dc6 --- /dev/null +++ b/ci/run-rust-checks.sh @@ -0,0 +1,22 @@ +#!/bin/sh + +. ${0%/*}/lib.sh + +set +x + +if ! group "Check Rust formatting" cargo fmt --all --check +then + RET=1 +fi + +if ! group "Check for common Rust mistakes" cargo clippy --all-targets --all-features -- -Dwarnings +then + RET=1 +fi + +if ! group "Check for minimum required Rust version" cargo msrv verify +then + RET=1 +fi + +exit $RET diff --git a/commit-reach.c b/commit-reach.c index a339e41aa4..cc18c86d3b 100644 --- a/commit-reach.c +++ b/commit-reach.c @@ -60,6 +60,7 @@ static int paint_down_to_common(struct repository *r, struct prio_queue queue = { compare_commits_by_gen_then_commit_date }; int i; timestamp_t last_gen = GENERATION_NUMBER_INFINITY; + struct commit_list **tail = result; if (!min_generation && !corrected_commit_dates_enabled(r)) queue.compare = compare_commits_by_commit_date; @@ -95,7 +96,7 @@ static int paint_down_to_common(struct repository *r, if (flags == (PARENT1 | PARENT2)) { if (!(commit->object.flags & RESULT)) { commit->object.flags |= RESULT; - commit_list_insert_by_date(commit, result); + tail = commit_list_append(commit, tail); } /* Mark parents of a found merge stale */ flags |= STALE; @@ -128,6 +129,7 @@ static int paint_down_to_common(struct repository *r, } clear_prio_queue(&queue); + commit_list_sort_by_date(result); return 0; } @@ -136,7 +138,7 @@ static int merge_bases_many(struct repository *r, struct commit **twos, struct commit_list **result) { - struct commit_list *list = NULL; + struct commit_list *list = NULL, **tail = result; int i; for (i = 0; i < n; i++) { @@ -171,8 +173,9 @@ static int merge_bases_many(struct repository *r, while (list) { struct commit *commit = pop_commit(&list); if (!(commit->object.flags & STALE)) - commit_list_insert_by_date(commit, result); + tail = commit_list_append(commit, tail); } + commit_list_sort_by_date(result); return 0; } @@ -425,7 +428,7 @@ static int get_merge_bases_many_0(struct repository *r, int cleanup, struct commit_list **result) { - struct commit_list *list; + struct commit_list *list, **tail = result; struct commit **rslt; size_t cnt, i; int ret; @@ -461,7 +464,8 @@ static int get_merge_bases_many_0(struct repository *r, return -1; } for (i = 0; i < cnt; i++) - commit_list_insert_by_date(rslt[i], result); + tail = commit_list_append(rslt[i], tail); + commit_list_sort_by_date(result); free(rslt); return 0; } diff --git a/connected.c b/connected.c index b288a18b17..79403108dd 100644 --- a/connected.c +++ b/connected.c @@ -74,10 +74,9 @@ int check_connected(oid_iterate_fn fn, void *cb_data, */ odb_reprepare(the_repository->objects); do { - struct packfile_store *packs = the_repository->objects->packfiles; struct packed_git *p; - for (p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (!p->pack_promisor) continue; if (find_pack_entry_one(oid, p)) diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index e3d88b0672..73abea31b4 100644 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -2218,7 +2218,7 @@ __git_log_gitk_options=" " # Options that go well for log and shortlog (not gitk) __git_log_shortlog_options=" - --author= --committer= --grep= + --author= --grep= --exclude= --all-match --invert-grep " # Options accepted by log and show @@ -2296,6 +2296,7 @@ __git_complete_log_opts () $__git_log_shortlog_options $__git_log_gitk_options $__git_log_show_options + --committer= --root --topo-order --date-order --reverse --follow --full-diff --abbrev-commit --no-abbrev-commit --abbrev= @@ -3229,7 +3230,7 @@ _git_shortlog () __gitcomp " $__git_log_common_options $__git_log_shortlog_options - --numbered --summary --email + --committer --numbered --summary --email " return ;; diff --git a/contrib/credential/libsecret/Makefile b/contrib/credential/libsecret/Makefile index 7cacc57681..9309cfb78c 100644 --- a/contrib/credential/libsecret/Makefile +++ b/contrib/credential/libsecret/Makefile @@ -10,6 +10,7 @@ gitexecdir ?= $(prefix)/libexec/git-core CC ?= gcc CFLAGS ?= -g -O2 -Wall PKG_CONFIG ?= pkg-config +INSTALL ?= install RM ?= rm -f INCS:=$(shell $(PKG_CONFIG) --cflags libsecret-1 glib-2.0) @@ -21,7 +22,11 @@ LIBS:=$(shell $(PKG_CONFIG) --libs libsecret-1 glib-2.0) git-credential-libsecret: git-credential-libsecret.o $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) $(LIBS) +install: git-credential-libsecret + $(INSTALL) -d -m 755 $(DESTDIR)$(gitexecdir) + $(INSTALL) -m 755 $< $(DESTDIR)$(gitexecdir) + clean: $(RM) git-credential-libsecret git-credential-libsecret.o -.PHONY: all clean +.PHONY: all install clean diff --git a/contrib/credential/osxkeychain/Makefile b/contrib/credential/osxkeychain/Makefile index c7d9121022..9680717abe 100644 --- a/contrib/credential/osxkeychain/Makefile +++ b/contrib/credential/osxkeychain/Makefile @@ -9,6 +9,7 @@ gitexecdir ?= $(prefix)/libexec/git-core CC ?= gcc CFLAGS ?= -g -O2 -Wall +INSTALL ?= install RM ?= rm -f %.o: %.c @@ -18,7 +19,11 @@ git-credential-osxkeychain: git-credential-osxkeychain.o $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) \ -framework Security -framework CoreFoundation +install: git-credential-osxkeychain + $(INSTALL) -d -m 755 $(DESTDIR)$(gitexecdir) + $(INSTALL) -m 755 $< $(DESTDIR)$(gitexecdir) + clean: $(RM) git-credential-osxkeychain git-credential-osxkeychain.o -.PHONY: all clean +.PHONY: all install clean @@ -1351,6 +1351,9 @@ static void emit_diff_symbol_from_struct(struct diff_options *o, int len = eds->len; unsigned flags = eds->flags; + if (!o->file) + return; + switch (s) { case DIFF_SYMBOL_NO_LF_EOF: context = diff_get_color_opt(o, DIFF_CONTEXT); @@ -3762,9 +3765,9 @@ static void builtin_diff(const char *name_a, if (o->word_diff) init_diff_words_data(&ecbdata, o, one, two); - if (o->dry_run) { + if (!o->file) { /* - * Unlike the !dry_run case, we need to ignore the + * Unlike the normal output case, we need to ignore the * return value from xdi_diff_outf() here, because * xdi_diff_outf() takes non-zero return from its * callback function as a sign of error and returns @@ -4420,7 +4423,6 @@ static void run_external_diff(const struct external_diff *pgm, { struct child_process cmd = CHILD_PROCESS_INIT; struct diff_queue_struct *q = &diff_queued_diff; - int quiet = !(o->output_format & DIFF_FORMAT_PATCH); int rc; /* @@ -4429,7 +4431,7 @@ static void run_external_diff(const struct external_diff *pgm, * external diff program lacks the ability to tell us whether * it's empty then we consider it non-empty without even asking. */ - if (!pgm->trust_exit_code && quiet) { + if (!pgm->trust_exit_code && !o->file) { o->found_changes = 1; return; } @@ -4454,7 +4456,10 @@ static void run_external_diff(const struct external_diff *pgm, diff_free_filespec_data(one); diff_free_filespec_data(two); cmd.use_shell = 1; - cmd.no_stdout = quiet; + if (!o->file) + cmd.no_stdout = 1; + else if (o->file != stdout) + cmd.out = xdup(fileno(o->file)); rc = run_command(&cmd); if (!pgm->trust_exit_code && rc == 0) o->found_changes = 1; @@ -4615,7 +4620,8 @@ static void run_diff_cmd(const struct external_diff *pgm, p->status == DIFF_STATUS_RENAMED) o->found_changes = 1; } else { - fprintf(o->file, "* Unmerged path %s\n", name); + if (o->file) + fprintf(o->file, "* Unmerged path %s\n", name); o->found_changes = 1; } } @@ -6192,15 +6198,15 @@ static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o) /* return 1 if any change is found; otherwise, return 0 */ static int diff_flush_patch_quietly(struct diff_filepair *p, struct diff_options *o) { - int saved_dry_run = o->dry_run; + FILE *saved_file = o->file; int saved_found_changes = o->found_changes; int ret; - o->dry_run = 1; + o->file = NULL; o->found_changes = 0; diff_flush_patch(p, o); ret = o->found_changes; - o->dry_run = saved_dry_run; + o->file = saved_file; o->found_changes |= saved_found_changes; return ret; } @@ -6828,38 +6834,18 @@ 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) { - FILE *saved_file = options->file; - int found_changes; + if (options->flags.diff_from_contents && + !diff_flush_patch_quietly(p, options)) + continue; - 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++; } @@ -6910,15 +6896,6 @@ 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)) @@ -408,8 +408,6 @@ struct diff_options { #define COLOR_MOVED_WS_ERROR (1<<0) unsigned color_moved_ws_handling; - bool dry_run; - struct repository *repo; struct strmap *additional_path_headers; @@ -30,6 +30,7 @@ #include "read-cache-ll.h" #include "setup.h" #include "sparse-index.h" +#include "strbuf.h" #include "submodule-config.h" #include "symlinks.h" #include "trace2.h" @@ -87,6 +88,33 @@ struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp) return e; } +int for_each_file_in_dir(struct strbuf *path, file_iterator fn, const void *data) +{ + struct dirent *e; + int res = 0; + size_t baselen = path->len; + DIR *dir = opendir(path->buf); + + if (!dir) + return 0; + + while (!res && (e = readdir_skip_dot_and_dotdot(dir)) != NULL) { + unsigned char dtype = get_dtype(e, path, 0); + strbuf_setlen(path, baselen); + strbuf_addstr(path, e->d_name); + + if (dtype == DT_REG) { + res = fn(path->buf, data); + } else if (dtype == DT_DIR) { + strbuf_addch(path, '/'); + res = for_each_file_in_dir(path, fn, data); + } + } + + closedir(dir); + return res; +} + int count_slashes(const char *s) { int cnt = 0; @@ -1360,18 +1388,25 @@ int match_pathname(const char *pathname, int pathlen, if (fspathncmp(pattern, name, prefix)) return 0; - pattern += prefix; - patternlen -= prefix; - name += prefix; - namelen -= prefix; /* * If the whole pattern did not have a wildcard, * then our prefix match is all we need; we * do not need to call fnmatch at all. */ - if (!patternlen && !namelen) + if (patternlen == prefix && namelen == prefix) return 1; + + /* + * Retain one character of the prefix to + * pass to fnmatch, which lets it distinguish + * the start of a directory component correctly. + */ + prefix--; + pattern += prefix; + patternlen -= prefix; + name += prefix; + namelen -= prefix; } return fnmatch_icase_mem(pattern, patternlen, @@ -537,6 +537,20 @@ int get_sparse_checkout_patterns(struct pattern_list *pl); int remove_dir_recursively(struct strbuf *path, int flag); /* + * This function pointer type is called on each file discovered in + * for_each_file_in_dir. The iteration stops if this method returns + * non-zero. + */ +typedef int (*file_iterator)(const char *path, const void *data); + +struct strbuf; +/* + * Given a directory path, recursively visit each file within, including + * within subdirectories. + */ +int for_each_file_in_dir(struct strbuf *path, file_iterator fn, const void *data); + +/* * Tries to remove the path, along with leading empty directories so long as * those empty directories are not startup_info->original_cwd. Ignores * ENOENT. diff --git a/gpg-interface.c b/gpg-interface.c index 2f4f0e32cb..d1e88da8c1 100644 --- a/gpg-interface.c +++ b/gpg-interface.c @@ -821,8 +821,7 @@ static char *get_ssh_key_fingerprint(const char *signing_key) struct child_process ssh_keygen = CHILD_PROCESS_INIT; int ret = -1; struct strbuf fingerprint_stdout = STRBUF_INIT; - struct strbuf **fingerprint; - char *fingerprint_ret; + char *fingerprint_ret, *begin, *delim; const char *literal_key = NULL; /* @@ -845,13 +844,17 @@ static char *get_ssh_key_fingerprint(const char *signing_key) die_errno(_("failed to get the ssh fingerprint for key '%s'"), signing_key); - fingerprint = strbuf_split_max(&fingerprint_stdout, ' ', 3); - if (!fingerprint[1]) - die_errno(_("failed to get the ssh fingerprint for key '%s'"), + begin = fingerprint_stdout.buf; + delim = strchr(begin, ' '); + if (!delim) + die(_("failed to get the ssh fingerprint for key %s"), signing_key); - - fingerprint_ret = strbuf_detach(fingerprint[1], NULL); - strbuf_list_free(fingerprint); + begin = delim + 1; + delim = strchr(begin, ' '); + if (!delim) + die(_("failed to get the ssh fingerprint for key %s"), + signing_key); + fingerprint_ret = xmemdupz(begin, delim - begin); strbuf_release(&fingerprint_stdout); return fingerprint_ret; } @@ -862,12 +865,12 @@ static char *get_default_ssh_signing_key(void) struct child_process ssh_default_key = CHILD_PROCESS_INIT; int ret = -1; struct strbuf key_stdout = STRBUF_INIT, key_stderr = STRBUF_INIT; - struct strbuf **keys; char *key_command = NULL; const char **argv; int n; char *default_key = NULL; const char *literal_key = NULL; + char *begin, *new_line, *first_line; if (!ssh_default_key_command) die(_("either user.signingkey or gpg.ssh.defaultKeyCommand needs to be configured")); @@ -884,19 +887,24 @@ static char *get_default_ssh_signing_key(void) &key_stderr, 0); if (!ret) { - keys = strbuf_split_max(&key_stdout, '\n', 2); - if (keys[0] && is_literal_ssh_key(keys[0]->buf, &literal_key)) { + begin = key_stdout.buf; + new_line = strchr(begin, '\n'); + if (new_line) + first_line = xmemdupz(begin, new_line - begin); + else + first_line = xstrdup(begin); + if (is_literal_ssh_key(first_line, &literal_key)) { /* * We only use `is_literal_ssh_key` here to check validity * The prefix will be stripped when the key is used. */ - default_key = strbuf_detach(keys[0], NULL); + default_key = first_line; } else { + free(first_line); warning(_("gpg.ssh.defaultKeyCommand succeeded but returned no keys: %s %s"), key_stderr.buf, key_stdout.buf); } - strbuf_list_free(keys); } else { warning(_("gpg.ssh.defaultKeyCommand failed: %s %s"), key_stderr.buf, key_stdout.buf); diff --git a/http-backend.c b/http-backend.c index 9084058f1e..52f0483dd3 100644 --- a/http-backend.c +++ b/http-backend.c @@ -603,19 +603,18 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (p->pack_local) cnt++; } strbuf_grow(&buf, cnt * 53 + 2); - for (p = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (p->pack_local) strbuf_addf(&buf, "P %s\n", p->pack_name + objdirlen + 6); } @@ -2416,7 +2416,6 @@ 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; @@ -2425,7 +2424,7 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(the_repository, p) { if (hasheq(p->hash, sha1, the_repository->hash_algo)) return 0; } diff --git a/meson.build b/meson.build index cee9424475..2b763f7c53 100644 --- a/meson.build +++ b/meson.build @@ -463,6 +463,12 @@ libgit_sources = [ 'reftable/tree.c', 'reftable/writer.c', 'remote.c', + 'repack.c', + 'repack-cruft.c', + 'repack-filtered.c', + 'repack-geometry.c', + 'repack-midx.c', + 'repack-promisor.c', 'replace-object.c', 'repo-settings.c', 'repository.c', @@ -1708,6 +1714,10 @@ rust_option = get_option('rust').disable_auto_if(not cargo.found()) if rust_option.allowed() subdir('src') libgit_c_args += '-DWITH_RUST' + + if host_machine.system() == 'windows' + libgit_dependencies += compiler.find_library('userenv') + endif else libgit_sources += [ 'varint.c', diff --git a/object-name.c b/object-name.c index f6902e140d..766c757042 100644 --- a/object-name.c +++ b/object-name.c @@ -213,9 +213,11 @@ static void find_short_packed_object(struct disambiguate_state *ds) unique_in_midx(m, ds); } - for (p = packfile_store_get_packs(ds->repo->objects->packfiles); p && !ds->ambiguous; - p = p->next) + repo_for_each_pack(ds->repo, p) { + if (ds->ambiguous) + break; unique_in_pack(p, ds); + } } static int finish_object_disambiguation(struct disambiguate_state *ds, @@ -805,7 +807,7 @@ static void find_abbrev_len_packed(struct min_abbrev_data *mad) find_abbrev_len_for_midx(m, mad); } - for (p = packfile_store_get_packs(mad->repo->objects->packfiles); p; p = p->next) + repo_for_each_pack(mad->repo, p) find_abbrev_len_for_pack(p, mad); } diff --git a/pack-bitmap.c b/pack-bitmap.c index ac71035d77..291e1a9cf4 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 = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { + repo_for_each_pack(r, p) { if (open_pack_bitmap_1(bitmap_git, p) == 0) { ret = 0; /* @@ -3347,6 +3347,7 @@ static int verify_bitmap_file(const struct git_hash_algo *algop, int verify_bitmap_files(struct repository *r) { struct odb_source *source; + struct packed_git *p; int res = 0; odb_prepare_alternates(r->objects); @@ -3362,8 +3363,7 @@ int verify_bitmap_files(struct repository *r) free(midx_bitmap_name); } - for (struct packed_git *p = packfile_store_get_all_packs(r->objects->packfiles); - p; p = p->next) { + repo_for_each_pack(r, p) { char *pack_bitmap_name = pack_bitmap_filename(p); res |= verify_bitmap_file(r->hash_algo, pack_bitmap_name); free(pack_bitmap_name); diff --git a/pack-objects.c b/pack-objects.c index 9d6ee72569..48510dd343 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -87,7 +87,6 @@ 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; @@ -97,13 +96,13 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next, cnt++) { + repo_for_each_pack(pdata->repo, p) { if (cnt == nr) { free(mapping); return; } p->index = cnt; - mapping[cnt] = p; + mapping[cnt++] = p; } pdata->in_pack_by_idx = mapping; } diff --git a/packfile.c b/packfile.c index 5a7caec292..1ae2b2fe1e 100644 --- a/packfile.c +++ b/packfile.c @@ -1030,12 +1030,6 @@ void packfile_store_reprepare(struct packfile_store *store) struct packed_git *packfile_store_get_packs(struct packfile_store *store) { packfile_store_prepare(store); - return store->packs; -} - -struct packed_git *packfile_store_get_all_packs(struct packfile_store *store) -{ - packfile_store_prepare(store); for (struct odb_source *source = store->odb->sources; source; source = source->next) { struct multi_pack_index *m = source->midx; @@ -2105,7 +2099,7 @@ 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 = packfile_store_get_all_packs(r->objects->packfiles); p; p = p->next) { + repo_for_each_pack(r, p) { 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); @@ -2202,7 +2196,7 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, int r = 0; int pack_errors = 0; - for (p = packfile_store_get_all_packs(repo->objects->packfiles); p; p = p->next) { + repo_for_each_pack(repo, p) { if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) continue; if ((flags & FOR_EACH_OBJECT_PROMISOR_ONLY) && diff --git a/packfile.h b/packfile.h index e7a5792b6c..c9d0b93446 100644 --- a/packfile.h +++ b/packfile.h @@ -137,16 +137,18 @@ 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. + * Load and iterate through all packs of the given repository. This helper + * function will yield packfiles from all object sources connected to the + * repository. */ -struct packed_git *packfile_store_get_packs(struct packfile_store *store); +#define repo_for_each_pack(repo, p) \ + for (p = packfile_store_get_packs(repo->objects->packfiles); p; p = p->next) /* * 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); +struct packed_git *packfile_store_get_packs(struct packfile_store *store); /* * Get all packs in most-recently-used order. diff --git a/ref-filter.c b/ref-filter.c index 520d2539c9..30cc488d8a 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -2664,7 +2664,7 @@ static int match_name_as_path(const char **pattern, const char *refname, /* Return 1 if the refname matches one of the patterns, otherwise 0. */ static int filter_pattern_match(struct ref_filter *filter, const char *refname) { - if (!*filter->name_patterns) + if (!filter->name_patterns || !*filter->name_patterns) return 1; /* No pattern always matches */ if (filter->match_as_path) return match_name_as_path(filter->name_patterns, refname, @@ -2751,7 +2751,7 @@ static int for_each_fullref_in_pattern(struct ref_filter *filter, return for_each_fullref_with_seek(filter, cb, cb_data, 0); } - if (!filter->name_patterns[0]) { + if (!filter->name_patterns || !filter->name_patterns[0]) { /* no patterns; we have to look at everything */ return for_each_fullref_with_seek(filter, cb, cb_data, 0); } @@ -2833,7 +2833,7 @@ struct ref_array_item *ref_array_push(struct ref_array *array, return ref; } -static int ref_kind_from_refname(const char *refname) +int ref_kind_from_refname(const char *refname) { unsigned int i; diff --git a/ref-filter.h b/ref-filter.h index 81f2c229a9..235c60f79c 100644 --- a/ref-filter.h +++ b/ref-filter.h @@ -135,6 +135,8 @@ struct ref_format { OPT_STRVEC(0, "exclude", &(var)->exclude, \ N_("pattern"), N_("exclude refs which match pattern")) +/* Get the reference kind from the provided reference name. */ +int ref_kind_from_refname(const char *refname); /* * API for filtering a set of refs. Based on the type of refs the user * has requested, we iterate through those refs and apply filters diff --git a/refs/files-backend.c b/refs/files-backend.c index 8d7007f4aa..054cf42f4e 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -2113,20 +2113,35 @@ static int commit_ref_update(struct files_ref_store *refs, return 0; } -#ifdef NO_SYMLINK_HEAD +#if defined(NO_SYMLINK_HEAD) || defined(WITH_BREAKING_CHANGES) #define create_ref_symlink(a, b) (-1) #else static int create_ref_symlink(struct ref_lock *lock, const char *target) { + static int warn_once = 1; + char *ref_path; int ret = -1; - char *ref_path = get_locked_file_path(&lock->lk); + ref_path = get_locked_file_path(&lock->lk); unlink(ref_path); ret = symlink(target, ref_path); free(ref_path); if (ret) fprintf(stderr, "no symlink - falling back to symbolic ref\n"); + + if (warn_once) + warning(_("'core.preferSymlinkRefs=true' is nominated for removal.\n" + "hint: The use of symbolic links for symbolic refs is deprecated\n" + "hint: and will be removed in Git 3.0. The configuration that\n" + "hint: tells Git to use them is thus going away. You can unset\n" + "hint: it with:\n" + "hint:\n" + "hint:\tgit config unset core.preferSymlinkRefs\n" + "hint:\n" + "hint: Git will then use the textual symref format instead.")); + warn_once = 0; + return ret; } #endif diff --git a/repack-cruft.c b/repack-cruft.c new file mode 100644 index 0000000000..0653e88792 --- /dev/null +++ b/repack-cruft.c @@ -0,0 +1,98 @@ +#include "git-compat-util.h" +#include "repack.h" +#include "packfile.h" +#include "repository.h" +#include "run-command.h" + +static void combine_small_cruft_packs(FILE *in, off_t combine_cruft_below_size, + struct existing_packs *existing) +{ + struct packed_git *p; + struct strbuf buf = STRBUF_INIT; + size_t i; + + repo_for_each_pack(existing->repo, p) { + if (!(p->is_cruft && p->pack_local)) + continue; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if (!string_list_has_string(&existing->cruft_packs, buf.buf)) + continue; + + if (p->pack_size < combine_cruft_below_size) { + fprintf(in, "-%s\n", pack_basename(p)); + } else { + existing_packs_retain_cruft(existing, p); + fprintf(in, "%s\n", pack_basename(p)); + } + } + + for (i = 0; i < existing->non_kept_packs.nr; i++) + fprintf(in, "-%s.pack\n", + existing->non_kept_packs.items[i].string); + + strbuf_release(&buf); +} + +int write_cruft_pack(const struct write_pack_opts *opts, + const char *cruft_expiration, + unsigned long combine_cruft_below_size, + struct string_list *names, + struct existing_packs *existing) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct string_list_item *item; + FILE *in; + int ret; + const char *pack_prefix = write_pack_opts_pack_prefix(opts); + + prepare_pack_objects(&cmd, opts->po_args, opts->destination); + + strvec_push(&cmd.args, "--cruft"); + if (cruft_expiration) + strvec_pushf(&cmd.args, "--cruft-expiration=%s", + cruft_expiration); + + strvec_push(&cmd.args, "--non-empty"); + + cmd.in = -1; + + ret = start_command(&cmd); + if (ret) + return ret; + + /* + * names has a confusing double use: it both provides the list + * of just-written new packs, and accepts the name of the cruft + * pack we are writing. + * + * By the time it is read here, it contains only the pack(s) + * that were just written, which is exactly the set of packs we + * want to consider kept. + * + * If `--expire-to` is given, the double-use served by `names` + * ensures that the pack written to `--expire-to` excludes any + * objects contained in the cruft pack. + */ + in = xfdopen(cmd.in, "w"); + for_each_string_list_item(item, names) + fprintf(in, "%s-%s.pack\n", pack_prefix, item->string); + if (combine_cruft_below_size && !cruft_expiration) { + combine_small_cruft_packs(in, combine_cruft_below_size, + existing); + } else { + for_each_string_list_item(item, &existing->non_kept_packs) + fprintf(in, "-%s.pack\n", item->string); + for_each_string_list_item(item, &existing->cruft_packs) + fprintf(in, "-%s.pack\n", item->string); + } + for_each_string_list_item(item, &existing->kept_packs) + fprintf(in, "%s.pack\n", item->string); + fclose(in); + + return finish_pack_objects_cmd(existing->repo->hash_algo, opts, &cmd, + names); +} diff --git a/repack-filtered.c b/repack-filtered.c new file mode 100644 index 0000000000..edcf7667c5 --- /dev/null +++ b/repack-filtered.c @@ -0,0 +1,51 @@ +#include "git-compat-util.h" +#include "repack.h" +#include "repository.h" +#include "run-command.h" +#include "string-list.h" + +int write_filtered_pack(const struct write_pack_opts *opts, + struct existing_packs *existing, + struct string_list *names) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct string_list_item *item; + FILE *in; + int ret; + const char *caret; + const char *pack_prefix = write_pack_opts_pack_prefix(opts); + + prepare_pack_objects(&cmd, opts->po_args, opts->destination); + + strvec_push(&cmd.args, "--stdin-packs"); + + for_each_string_list_item(item, &existing->kept_packs) + strvec_pushf(&cmd.args, "--keep-pack=%s", item->string); + + cmd.in = -1; + + ret = start_command(&cmd); + if (ret) + return ret; + + /* + * Here 'names' contains only the pack(s) that were just + * written, which is exactly the packs we want to keep. Also + * 'existing_kept_packs' already contains the packs in + * 'keep_pack_list'. + */ + in = xfdopen(cmd.in, "w"); + for_each_string_list_item(item, names) + fprintf(in, "^%s-%s.pack\n", pack_prefix, item->string); + for_each_string_list_item(item, &existing->non_kept_packs) + fprintf(in, "%s.pack\n", item->string); + for_each_string_list_item(item, &existing->cruft_packs) + fprintf(in, "%s.pack\n", item->string); + caret = opts->po_args->pack_kept_objects ? "" : "^"; + for_each_string_list_item(item, &existing->kept_packs) + fprintf(in, "%s%s.pack\n", caret, item->string); + fclose(in); + + return finish_pack_objects_cmd(existing->repo->hash_algo, opts, &cmd, + names); +} diff --git a/repack-geometry.c b/repack-geometry.c new file mode 100644 index 0000000000..b3e32cd07e --- /dev/null +++ b/repack-geometry.c @@ -0,0 +1,232 @@ +#define DISABLE_SIGN_COMPARE_WARNINGS + +#include "git-compat-util.h" +#include "repack.h" +#include "repository.h" +#include "hex.h" +#include "packfile.h" + +static uint32_t pack_geometry_weight(struct packed_git *p) +{ + if (open_pack_index(p)) + die(_("cannot open index for %s"), p->pack_name); + return p->num_objects; +} + +static int pack_geometry_cmp(const void *va, const void *vb) +{ + uint32_t aw = pack_geometry_weight(*(struct packed_git **)va), + bw = pack_geometry_weight(*(struct packed_git **)vb); + + if (aw < bw) + return -1; + if (aw > bw) + return 1; + return 0; +} + +void pack_geometry_init(struct pack_geometry *geometry, + struct existing_packs *existing, + const struct pack_objects_args *args) +{ + struct packed_git *p; + struct strbuf buf = STRBUF_INIT; + + repo_for_each_pack(existing->repo, p) { + if (args->local && !p->pack_local) + /* + * When asked to only repack local packfiles we skip + * over any packfiles that are borrowed from alternate + * object directories. + */ + continue; + + if (!args->pack_kept_objects) { + /* + * Any pack that has its pack_keep bit set will + * appear in existing->kept_packs below, but + * this saves us from doing a more expensive + * check. + */ + if (p->pack_keep) + continue; + + /* + * The pack may be kept via the --keep-pack + * option; check 'existing->kept_packs' to + * determine whether to ignore it. + */ + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if (string_list_has_string(&existing->kept_packs, buf.buf)) + continue; + } + if (p->is_cruft) + continue; + + ALLOC_GROW(geometry->pack, + geometry->pack_nr + 1, + geometry->pack_alloc); + + geometry->pack[geometry->pack_nr] = p; + geometry->pack_nr++; + } + + QSORT(geometry->pack, geometry->pack_nr, pack_geometry_cmp); + strbuf_release(&buf); +} + +void pack_geometry_split(struct pack_geometry *geometry) +{ + uint32_t i; + uint32_t split; + off_t total_size = 0; + + if (!geometry->pack_nr) { + geometry->split = geometry->pack_nr; + return; + } + + /* + * First, count the number of packs (in descending order of size) which + * already form a geometric progression. + */ + for (i = geometry->pack_nr - 1; i > 0; i--) { + struct packed_git *ours = geometry->pack[i]; + struct packed_git *prev = geometry->pack[i - 1]; + + if (unsigned_mult_overflows(geometry->split_factor, + pack_geometry_weight(prev))) + die(_("pack %s too large to consider in geometric " + "progression"), + prev->pack_name); + + if (pack_geometry_weight(ours) < + geometry->split_factor * pack_geometry_weight(prev)) + break; + } + + split = i; + + if (split) { + /* + * Move the split one to the right, since the top element in the + * last-compared pair can't be in the progression. Only do this + * when we split in the middle of the array (otherwise if we got + * to the end, then the split is in the right place). + */ + split++; + } + + /* + * Then, anything to the left of 'split' must be in a new pack. But, + * creating that new pack may cause packs in the heavy half to no longer + * form a geometric progression. + * + * Compute an expected size of the new pack, and then determine how many + * packs in the heavy half need to be joined into it (if any) to restore + * the geometric progression. + */ + for (i = 0; i < split; i++) { + struct packed_git *p = geometry->pack[i]; + + if (unsigned_add_overflows(total_size, pack_geometry_weight(p))) + die(_("pack %s too large to roll up"), p->pack_name); + total_size += pack_geometry_weight(p); + } + for (i = split; i < geometry->pack_nr; i++) { + struct packed_git *ours = geometry->pack[i]; + + if (unsigned_mult_overflows(geometry->split_factor, + total_size)) + die(_("pack %s too large to roll up"), ours->pack_name); + + if (pack_geometry_weight(ours) < + geometry->split_factor * total_size) { + if (unsigned_add_overflows(total_size, + pack_geometry_weight(ours))) + die(_("pack %s too large to roll up"), + ours->pack_name); + + split++; + total_size += pack_geometry_weight(ours); + } else + break; + } + + geometry->split = split; +} + +struct packed_git *pack_geometry_preferred_pack(struct pack_geometry *geometry) +{ + uint32_t i; + + if (!geometry) { + /* + * No geometry means either an all-into-one repack (in which + * case there is only one pack left and it is the largest) or an + * incremental one. + * + * If repacking incrementally, then we could check the size of + * all packs to determine which should be preferred, but leave + * this for later. + */ + return NULL; + } + if (geometry->split == geometry->pack_nr) + return NULL; + + /* + * The preferred pack is the largest pack above the split line. In + * other words, it is the largest pack that does not get rolled up in + * the geometric repack. + */ + for (i = geometry->pack_nr; i > geometry->split; i--) + /* + * A pack that is not local would never be included in a + * multi-pack index. We thus skip over any non-local packs. + */ + if (geometry->pack[i - 1]->pack_local) + return geometry->pack[i - 1]; + + return NULL; +} + +void pack_geometry_remove_redundant(struct pack_geometry *geometry, + struct string_list *names, + struct existing_packs *existing, + const char *packdir) +{ + const struct git_hash_algo *algop = existing->repo->hash_algo; + struct strbuf buf = STRBUF_INIT; + uint32_t i; + + for (i = 0; i < geometry->split; i++) { + struct packed_git *p = geometry->pack[i]; + if (string_list_has_string(names, hash_to_hex_algop(p->hash, + algop))) + continue; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if ((p->pack_keep) || + (string_list_has_string(&existing->kept_packs, buf.buf))) + continue; + + repack_remove_redundant_pack(existing->repo, packdir, buf.buf); + } + + strbuf_release(&buf); +} + +void pack_geometry_release(struct pack_geometry *geometry) +{ + if (!geometry) + return; + + free(geometry->pack); +} diff --git a/repack-midx.c b/repack-midx.c new file mode 100644 index 0000000000..6f6202c5bc --- /dev/null +++ b/repack-midx.c @@ -0,0 +1,372 @@ +#include "git-compat-util.h" +#include "repack.h" +#include "hash.h" +#include "hex.h" +#include "odb.h" +#include "oidset.h" +#include "pack-bitmap.h" +#include "refs.h" +#include "run-command.h" +#include "tempfile.h" + +struct midx_snapshot_ref_data { + struct repository *repo; + struct tempfile *f; + struct oidset seen; + int preferred; +}; + +static int midx_snapshot_ref_one(const char *refname UNUSED, + const char *referent UNUSED, + const struct object_id *oid, + int flag UNUSED, void *_data) +{ + struct midx_snapshot_ref_data *data = _data; + struct object_id peeled; + + if (!peel_iterated_oid(data->repo, oid, &peeled)) + oid = &peeled; + + if (oidset_insert(&data->seen, oid)) + return 0; /* already seen */ + + if (odb_read_object_info(data->repo->objects, oid, NULL) != OBJ_COMMIT) + return 0; + + fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "", + oid_to_hex(oid)); + + return 0; +} + +void midx_snapshot_refs(struct repository *repo, struct tempfile *f) +{ + struct midx_snapshot_ref_data data; + const struct string_list *preferred = bitmap_preferred_tips(repo); + + data.repo = repo; + data.f = f; + data.preferred = 0; + oidset_init(&data.seen, 0); + + if (!fdopen_tempfile(f, "w")) + die(_("could not open tempfile %s for writing"), + get_tempfile_path(f)); + + if (preferred) { + struct string_list_item *item; + + data.preferred = 1; + for_each_string_list_item(item, preferred) + refs_for_each_ref_in(get_main_ref_store(repo), + item->string, + midx_snapshot_ref_one, &data); + data.preferred = 0; + } + + refs_for_each_ref(get_main_ref_store(repo), + midx_snapshot_ref_one, &data); + + if (close_tempfile_gently(f)) { + int save_errno = errno; + delete_tempfile(&f); + errno = save_errno; + die_errno(_("could not close refs snapshot tempfile")); + } + + oidset_clear(&data.seen); +} + +static int midx_has_unknown_packs(struct string_list *include, + struct pack_geometry *geometry, + struct existing_packs *existing) +{ + struct string_list_item *item; + + string_list_sort(include); + + for_each_string_list_item(item, &existing->midx_packs) { + const char *pack_name = item->string; + + /* + * Determine whether or not each MIDX'd pack from the existing + * MIDX (if any) is represented in the new MIDX. For each pack + * in the MIDX, it must either be: + * + * - In the "include" list of packs to be included in the new + * MIDX. Note this function is called before the include + * list is populated with any cruft pack(s). + * + * - Below the geometric split line (if using pack geometry), + * indicating that the pack won't be included in the new + * MIDX, but its contents were rolled up as part of the + * geometric repack. + * + * - In the existing non-kept packs list (if not using pack + * geometry), and marked as non-deleted. + */ + if (string_list_has_string(include, pack_name)) { + continue; + } else if (geometry) { + struct strbuf buf = STRBUF_INIT; + uint32_t j; + + for (j = 0; j < geometry->split; j++) { + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(geometry->pack[j])); + strbuf_strip_suffix(&buf, ".pack"); + strbuf_addstr(&buf, ".idx"); + + if (!strcmp(pack_name, buf.buf)) { + strbuf_release(&buf); + break; + } + } + + strbuf_release(&buf); + + if (j < geometry->split) + continue; + } else { + struct string_list_item *item; + + item = string_list_lookup(&existing->non_kept_packs, + pack_name); + if (item && !existing_pack_is_marked_for_deletion(item)) + continue; + } + + /* + * If we got to this point, the MIDX includes some pack that we + * don't know about. + */ + return 1; + } + + return 0; +} + +static void midx_included_packs(struct string_list *include, + struct repack_write_midx_opts *opts) +{ + struct existing_packs *existing = opts->existing; + struct pack_geometry *geometry = opts->geometry; + struct string_list *names = opts->names; + struct string_list_item *item; + struct strbuf buf = STRBUF_INIT; + + for_each_string_list_item(item, &existing->kept_packs) { + strbuf_reset(&buf); + strbuf_addf(&buf, "%s.idx", item->string); + string_list_insert(include, buf.buf); + } + + for_each_string_list_item(item, names) { + strbuf_reset(&buf); + strbuf_addf(&buf, "pack-%s.idx", item->string); + string_list_insert(include, buf.buf); + } + + if (geometry->split_factor) { + uint32_t i; + + for (i = geometry->split; i < geometry->pack_nr; i++) { + struct packed_git *p = geometry->pack[i]; + + /* + * The multi-pack index never refers to packfiles part + * of an alternate object database, so we skip these. + * While git-multi-pack-index(1) would silently ignore + * them anyway, this allows us to skip executing the + * command completely when we have only non-local + * packfiles. + */ + if (!p->pack_local) + continue; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + strbuf_addstr(&buf, ".idx"); + + string_list_insert(include, buf.buf); + } + } else { + for_each_string_list_item(item, &existing->non_kept_packs) { + if (existing_pack_is_marked_for_deletion(item)) + continue; + + strbuf_reset(&buf); + strbuf_addf(&buf, "%s.idx", item->string); + string_list_insert(include, buf.buf); + } + } + + if (opts->midx_must_contain_cruft || + midx_has_unknown_packs(include, geometry, existing)) { + /* + * If there are one or more unknown pack(s) present (see + * midx_has_unknown_packs() for what makes a pack + * "unknown") in the MIDX before the repack, keep them + * as they may be required to form a reachability + * closure if the MIDX is bitmapped. + * + * For example, a cruft pack can be required to form a + * reachability closure if the MIDX is bitmapped and one + * or more of the bitmap's selected commits reaches a + * once-cruft object that was later made reachable. + */ + for_each_string_list_item(item, &existing->cruft_packs) { + /* + * When doing a --geometric repack, there is no + * need to check for deleted packs, since we're + * by definition not doing an ALL_INTO_ONE + * repack (hence no packs will be deleted). + * Otherwise we must check for and exclude any + * packs which are enqueued for deletion. + * + * So we could omit the conditional below in the + * --geometric case, but doing so is unnecessary + * since no packs are marked as pending + * deletion (since we only call + * `existing_packs_mark_for_deletion()` when + * doing an all-into-one repack). + */ + if (existing_pack_is_marked_for_deletion(item)) + continue; + + strbuf_reset(&buf); + strbuf_addf(&buf, "%s.idx", item->string); + string_list_insert(include, buf.buf); + } + } else { + /* + * Modern versions of Git (with the appropriate + * configuration setting) will write new copies of + * once-cruft objects when doing a --geometric repack. + * + * If the MIDX has no cruft pack, new packs written + * during a --geometric repack will not rely on the + * cruft pack to form a reachability closure, so we can + * avoid including them in the MIDX in that case. + */ + ; + } + + strbuf_release(&buf); +} + +static void remove_redundant_bitmaps(struct string_list *include, + const char *packdir) +{ + struct strbuf path = STRBUF_INIT; + struct string_list_item *item; + size_t packdir_len; + + strbuf_addstr(&path, packdir); + strbuf_addch(&path, '/'); + packdir_len = path.len; + + /* + * Remove any pack bitmaps corresponding to packs which are now + * included in the MIDX. + */ + for_each_string_list_item(item, include) { + strbuf_addstr(&path, item->string); + strbuf_strip_suffix(&path, ".idx"); + strbuf_addstr(&path, ".bitmap"); + + if (unlink(path.buf) && errno != ENOENT) + warning_errno(_("could not remove stale bitmap: %s"), + path.buf); + + strbuf_setlen(&path, packdir_len); + } + strbuf_release(&path); +} + +int write_midx_included_packs(struct repack_write_midx_opts *opts) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct string_list include = STRING_LIST_INIT_DUP; + struct string_list_item *item; + struct packed_git *preferred = pack_geometry_preferred_pack(opts->geometry); + FILE *in; + int ret = 0; + + midx_included_packs(&include, opts); + if (!include.nr) + goto done; + + cmd.in = -1; + cmd.git_cmd = 1; + + strvec_push(&cmd.args, "multi-pack-index"); + strvec_pushl(&cmd.args, "write", "--stdin-packs", NULL); + + if (opts->show_progress) + strvec_push(&cmd.args, "--progress"); + else + strvec_push(&cmd.args, "--no-progress"); + + if (opts->write_bitmaps) + strvec_push(&cmd.args, "--bitmap"); + + if (preferred) + strvec_pushf(&cmd.args, "--preferred-pack=%s", + pack_basename(preferred)); + else if (opts->names->nr) { + /* The largest pack was repacked, meaning that either + * one or two packs exist depending on whether the + * repository has a cruft pack or not. + * + * Select the non-cruft one as preferred to encourage + * pack-reuse among packs containing reachable objects + * over unreachable ones. + * + * (Note we could write multiple packs here if + * `--max-pack-size` was given, but any one of them + * will suffice, so pick the first one.) + */ + for_each_string_list_item(item, opts->names) { + struct generated_pack *pack = item->util; + if (generated_pack_has_ext(pack, ".mtimes")) + continue; + + strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack", + item->string); + break; + } + } else { + /* + * No packs were kept, and no packs were written. The + * only thing remaining are .keep packs (unless + * --pack-kept-objects was given). + * + * Set the `--preferred-pack` arbitrarily here. + */ + ; + } + + if (opts->refs_snapshot) + strvec_pushf(&cmd.args, "--refs-snapshot=%s", + opts->refs_snapshot); + + ret = start_command(&cmd); + if (ret) + goto done; + + in = xfdopen(cmd.in, "w"); + for_each_string_list_item(item, &include) + fprintf(in, "%s\n", item->string); + fclose(in); + + ret = finish_command(&cmd); +done: + if (!ret && opts->write_bitmaps) + remove_redundant_bitmaps(&include, opts->packdir); + + string_list_clear(&include, 0); + + return ret; +} diff --git a/repack-promisor.c b/repack-promisor.c new file mode 100644 index 0000000000..ee6e0669f6 --- /dev/null +++ b/repack-promisor.c @@ -0,0 +1,102 @@ +#include "git-compat-util.h" +#include "repack.h" +#include "hex.h" +#include "pack.h" +#include "packfile.h" +#include "path.h" +#include "repository.h" +#include "run-command.h" + +struct write_oid_context { + struct child_process *cmd; + const struct git_hash_algo *algop; +}; + +/* + * Write oid to the given struct child_process's stdin, starting it first if + * necessary. + */ +static int write_oid(const struct object_id *oid, + struct packed_git *pack UNUSED, + uint32_t pos UNUSED, void *data) +{ + struct write_oid_context *ctx = data; + struct child_process *cmd = ctx->cmd; + + if (cmd->in == -1) { + if (start_command(cmd)) + die(_("could not start pack-objects to repack promisor objects")); + } + + if (write_in_full(cmd->in, oid_to_hex(oid), ctx->algop->hexsz) < 0 || + write_in_full(cmd->in, "\n", 1) < 0) + die(_("failed to feed promisor objects to pack-objects")); + return 0; +} + +void repack_promisor_objects(struct repository *repo, + const struct pack_objects_args *args, + struct string_list *names, const char *packtmp) +{ + struct write_oid_context ctx; + struct child_process cmd = CHILD_PROCESS_INIT; + FILE *out; + struct strbuf line = STRBUF_INIT; + + prepare_pack_objects(&cmd, args, packtmp); + cmd.in = -1; + + /* + * NEEDSWORK: Giving pack-objects only the OIDs without any ordering + * hints may result in suboptimal deltas in the resulting pack. See if + * the OIDs can be sent with fake paths such that pack-objects can use a + * {type -> existing pack order} ordering when computing deltas instead + * of a {type -> size} ordering, which may produce better deltas. + */ + ctx.cmd = &cmd; + ctx.algop = repo->hash_algo; + for_each_packed_object(repo, write_oid, &ctx, + FOR_EACH_OBJECT_PROMISOR_ONLY); + + if (cmd.in == -1) { + /* No packed objects; cmd was never started */ + child_process_clear(&cmd); + return; + } + + close(cmd.in); + + out = xfdopen(cmd.out, "r"); + while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + char *promisor_name; + + if (line.len != repo->hash_algo->hexsz) + die(_("repack: Expecting full hex object ID lines only from pack-objects.")); + item = string_list_append(names, line.buf); + + /* + * pack-objects creates the .pack and .idx files, but not the + * .promisor file. Create the .promisor file, which is empty. + * + * NEEDSWORK: fetch-pack sometimes generates non-empty + * .promisor files containing the ref names and associated + * hashes at the point of generation of the corresponding + * packfile, but this would not preserve their contents. Maybe + * concatenate the contents of all .promisor files instead of + * just creating a new empty file. + */ + promisor_name = mkpathdup("%s-%s.promisor", packtmp, + line.buf); + write_promisor_file(promisor_name, NULL, 0); + + item->util = generated_pack_populate(item->string, packtmp); + + free(promisor_name); + } + + fclose(out); + if (finish_command(&cmd)) + die(_("could not finish pack-objects to repack promisor objects")); + strbuf_release(&line); +} diff --git a/repack.c b/repack.c new file mode 100644 index 0000000000..596841027a --- /dev/null +++ b/repack.c @@ -0,0 +1,359 @@ +#include "git-compat-util.h" +#include "dir.h" +#include "midx.h" +#include "odb.h" +#include "packfile.h" +#include "path.h" +#include "repack.h" +#include "repository.h" +#include "run-command.h" +#include "tempfile.h" + +void prepare_pack_objects(struct child_process *cmd, + const struct pack_objects_args *args, + const char *out) +{ + strvec_push(&cmd->args, "pack-objects"); + if (args->window) + strvec_pushf(&cmd->args, "--window=%s", args->window); + if (args->window_memory) + strvec_pushf(&cmd->args, "--window-memory=%s", args->window_memory); + if (args->depth) + strvec_pushf(&cmd->args, "--depth=%s", args->depth); + if (args->threads) + strvec_pushf(&cmd->args, "--threads=%s", args->threads); + if (args->max_pack_size) + strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size); + if (args->no_reuse_delta) + strvec_pushf(&cmd->args, "--no-reuse-delta"); + if (args->no_reuse_object) + strvec_pushf(&cmd->args, "--no-reuse-object"); + if (args->name_hash_version) + strvec_pushf(&cmd->args, "--name-hash-version=%d", args->name_hash_version); + if (args->path_walk) + strvec_pushf(&cmd->args, "--path-walk"); + if (args->local) + strvec_push(&cmd->args, "--local"); + if (args->quiet) + strvec_push(&cmd->args, "--quiet"); + if (args->delta_base_offset) + strvec_push(&cmd->args, "--delta-base-offset"); + if (!args->pack_kept_objects) + strvec_push(&cmd->args, "--honor-pack-keep"); + strvec_push(&cmd->args, out); + cmd->git_cmd = 1; + cmd->out = -1; +} + +void pack_objects_args_release(struct pack_objects_args *args) +{ + free(args->window); + free(args->window_memory); + free(args->depth); + free(args->threads); + list_objects_filter_release(&args->filter_options); +} + +void repack_remove_redundant_pack(struct repository *repo, const char *dir_name, + const char *base_name) +{ + struct strbuf buf = STRBUF_INIT; + struct odb_source *source = repo->objects->sources; + struct multi_pack_index *m = get_multi_pack_index(source); + strbuf_addf(&buf, "%s.pack", base_name); + if (m && source->local && midx_contains_pack(m, buf.buf)) + clear_midx_file(repo); + strbuf_insertf(&buf, 0, "%s/", dir_name); + unlink_pack_path(buf.buf, 1); + strbuf_release(&buf); +} + +const char *write_pack_opts_pack_prefix(const struct write_pack_opts *opts) +{ + const char *pack_prefix; + if (!skip_prefix(opts->packtmp, opts->packdir, &pack_prefix)) + die(_("pack prefix %s does not begin with objdir %s"), + opts->packtmp, opts->packdir); + if (*pack_prefix == '/') + pack_prefix++; + return pack_prefix; +} + +bool write_pack_opts_is_local(const struct write_pack_opts *opts) +{ + return starts_with(opts->destination, opts->packdir); +} + +int finish_pack_objects_cmd(const struct git_hash_algo *algop, + const struct write_pack_opts *opts, + struct child_process *cmd, + struct string_list *names) +{ + FILE *out; + bool local = write_pack_opts_is_local(opts); + struct strbuf line = STRBUF_INIT; + + out = xfdopen(cmd->out, "r"); + while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + + if (line.len != algop->hexsz) + die(_("repack: Expecting full hex object ID lines only " + "from pack-objects.")); + /* + * Avoid putting packs written outside of the repository in the + * list of names. + */ + if (local) { + item = string_list_append(names, line.buf); + item->util = generated_pack_populate(line.buf, + opts->packtmp); + } + } + fclose(out); + + strbuf_release(&line); + + return finish_command(cmd); +} + +#define DELETE_PACK 1 +#define RETAIN_PACK 2 + +void existing_packs_collect(struct existing_packs *existing, + const struct string_list *extra_keep) +{ + struct packed_git *p; + struct strbuf buf = STRBUF_INIT; + + repo_for_each_pack(existing->repo, p) { + size_t i; + const char *base; + + if (p->multi_pack_index) + string_list_append(&existing->midx_packs, + pack_basename(p)); + if (!p->pack_local) + continue; + + base = pack_basename(p); + + for (i = 0; i < extra_keep->nr; i++) + if (!fspathcmp(base, extra_keep->items[i].string)) + break; + + strbuf_reset(&buf); + strbuf_addstr(&buf, base); + strbuf_strip_suffix(&buf, ".pack"); + + if ((extra_keep->nr > 0 && i < extra_keep->nr) || p->pack_keep) + string_list_append(&existing->kept_packs, buf.buf); + else if (p->is_cruft) + string_list_append(&existing->cruft_packs, buf.buf); + else + string_list_append(&existing->non_kept_packs, buf.buf); + } + + string_list_sort(&existing->kept_packs); + string_list_sort(&existing->non_kept_packs); + string_list_sort(&existing->cruft_packs); + string_list_sort(&existing->midx_packs); + strbuf_release(&buf); +} + +int existing_packs_has_non_kept(const struct existing_packs *existing) +{ + return existing->non_kept_packs.nr || existing->cruft_packs.nr; +} + +static void existing_pack_mark_for_deletion(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util | DELETE_PACK); +} + +static void existing_pack_unmark_for_deletion(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK); +} + +int existing_pack_is_marked_for_deletion(struct string_list_item *item) +{ + return (uintptr_t)item->util & DELETE_PACK; +} + +static void existing_packs_mark_retained(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util | RETAIN_PACK); +} + +static int existing_pack_is_retained(struct string_list_item *item) +{ + return (uintptr_t)item->util & RETAIN_PACK; +} + +static void existing_packs_mark_for_deletion_1(const struct git_hash_algo *algop, + struct string_list *names, + struct string_list *list) +{ + struct string_list_item *item; + const size_t hexsz = algop->hexsz; + + for_each_string_list_item(item, list) { + char *sha1; + size_t len = strlen(item->string); + if (len < hexsz) + continue; + sha1 = item->string + len - hexsz; + + if (existing_pack_is_retained(item)) { + existing_pack_unmark_for_deletion(item); + } else if (!string_list_has_string(names, sha1)) { + /* + * Mark this pack for deletion, which ensures + * that this pack won't be included in a MIDX + * (if `--write-midx` was given) and that we + * will actually delete this pack (if `-d` was + * given). + */ + existing_pack_mark_for_deletion(item); + } + } +} + +void existing_packs_retain_cruft(struct existing_packs *existing, + struct packed_git *cruft) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + + strbuf_addstr(&buf, pack_basename(cruft)); + strbuf_strip_suffix(&buf, ".pack"); + + item = string_list_lookup(&existing->cruft_packs, buf.buf); + if (!item) + BUG("could not find cruft pack '%s'", pack_basename(cruft)); + + existing_packs_mark_retained(item); + strbuf_release(&buf); +} + +void existing_packs_mark_for_deletion(struct existing_packs *existing, + struct string_list *names) + +{ + const struct git_hash_algo *algop = existing->repo->hash_algo; + existing_packs_mark_for_deletion_1(algop, names, + &existing->non_kept_packs); + existing_packs_mark_for_deletion_1(algop, names, + &existing->cruft_packs); +} + +static void remove_redundant_packs_1(struct repository *repo, + struct string_list *packs, + const char *packdir) +{ + struct string_list_item *item; + for_each_string_list_item(item, packs) { + if (!existing_pack_is_marked_for_deletion(item)) + continue; + repack_remove_redundant_pack(repo, packdir, item->string); + } +} + +void existing_packs_remove_redundant(struct existing_packs *existing, + const char *packdir) +{ + remove_redundant_packs_1(existing->repo, &existing->non_kept_packs, + packdir); + remove_redundant_packs_1(existing->repo, &existing->cruft_packs, + packdir); +} + +void existing_packs_release(struct existing_packs *existing) +{ + string_list_clear(&existing->kept_packs, 0); + string_list_clear(&existing->non_kept_packs, 0); + string_list_clear(&existing->cruft_packs, 0); + string_list_clear(&existing->midx_packs, 0); +} + +static struct { + const char *name; + unsigned optional:1; +} exts[] = { + {".pack"}, + {".rev", 1}, + {".mtimes", 1}, + {".bitmap", 1}, + {".promisor", 1}, + {".idx"}, +}; + +struct generated_pack { + struct tempfile *tempfiles[ARRAY_SIZE(exts)]; +}; + +struct generated_pack *generated_pack_populate(const char *name, + const char *packtmp) +{ + struct stat statbuf; + struct strbuf path = STRBUF_INIT; + struct generated_pack *pack = xcalloc(1, sizeof(*pack)); + size_t i; + + for (i = 0; i < ARRAY_SIZE(exts); i++) { + strbuf_reset(&path); + strbuf_addf(&path, "%s-%s%s", packtmp, name, exts[i].name); + + if (stat(path.buf, &statbuf)) + continue; + + pack->tempfiles[i] = register_tempfile(path.buf); + } + + strbuf_release(&path); + return pack; +} + +int generated_pack_has_ext(const struct generated_pack *pack, const char *ext) +{ + size_t i; + for (i = 0; i < ARRAY_SIZE(exts); i++) { + if (strcmp(exts[i].name, ext)) + continue; + return !!pack->tempfiles[i]; + } + BUG("unknown pack extension: '%s'", ext); +} + +void generated_pack_install(struct generated_pack *pack, const char *name, + const char *packdir, const char *packtmp) +{ + size_t ext; + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { + char *fname; + + fname = mkpathdup("%s/pack-%s%s", packdir, name, + exts[ext].name); + + if (pack->tempfiles[ext]) { + const char *fname_old = get_tempfile_path(pack->tempfiles[ext]); + struct stat statbuffer; + + if (!stat(fname_old, &statbuffer)) { + statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); + chmod(fname_old, statbuffer.st_mode); + } + + if (rename_tempfile(&pack->tempfiles[ext], fname)) + die_errno(_("renaming pack to '%s' failed"), + fname); + } else if (!exts[ext].optional) + die(_("pack-objects did not write a '%s' file for pack %s-%s"), + exts[ext].name, packtmp, name); + else if (unlink(fname) < 0 && errno != ENOENT) + die_errno(_("could not unlink: %s"), fname); + + free(fname); + } +} diff --git a/repack.h b/repack.h new file mode 100644 index 0000000000..3a688a12ee --- /dev/null +++ b/repack.h @@ -0,0 +1,146 @@ +#ifndef REPACK_H +#define REPACK_H + +#include "list-objects-filter-options.h" +#include "string-list.h" + +struct pack_objects_args { + char *window; + char *window_memory; + char *depth; + char *threads; + unsigned long max_pack_size; + int no_reuse_delta; + int no_reuse_object; + int quiet; + int local; + int name_hash_version; + int path_walk; + int delta_base_offset; + int pack_kept_objects; + struct list_objects_filter_options filter_options; +}; + +#define PACK_OBJECTS_ARGS_INIT { \ + .delta_base_offset = 1, \ + .pack_kept_objects = -1, \ +} + +struct child_process; + +void prepare_pack_objects(struct child_process *cmd, + const struct pack_objects_args *args, + const char *out); +void pack_objects_args_release(struct pack_objects_args *args); + +void repack_remove_redundant_pack(struct repository *repo, const char *dir_name, + const char *base_name); + +struct write_pack_opts { + struct pack_objects_args *po_args; + const char *destination; + const char *packdir; + const char *packtmp; +}; + +const char *write_pack_opts_pack_prefix(const struct write_pack_opts *opts); +bool write_pack_opts_is_local(const struct write_pack_opts *opts); + +int finish_pack_objects_cmd(const struct git_hash_algo *algop, + const struct write_pack_opts *opts, + struct child_process *cmd, + struct string_list *names); + +struct repository; +struct packed_git; + +struct existing_packs { + struct repository *repo; + struct string_list kept_packs; + struct string_list non_kept_packs; + struct string_list cruft_packs; + struct string_list midx_packs; +}; + +#define EXISTING_PACKS_INIT { \ + .kept_packs = STRING_LIST_INIT_DUP, \ + .non_kept_packs = STRING_LIST_INIT_DUP, \ + .cruft_packs = STRING_LIST_INIT_DUP, \ +} + +/* + * Adds all packs hex strings (pack-$HASH) to either packs->non_kept + * or packs->kept based on whether each pack has a corresponding + * .keep file or not. Packs without a .keep file are not to be kept + * if we are going to pack everything into one file. + */ +void existing_packs_collect(struct existing_packs *existing, + const struct string_list *extra_keep); +int existing_packs_has_non_kept(const struct existing_packs *existing); +int existing_pack_is_marked_for_deletion(struct string_list_item *item); +void existing_packs_retain_cruft(struct existing_packs *existing, + struct packed_git *cruft); +void existing_packs_mark_for_deletion(struct existing_packs *existing, + struct string_list *names); +void existing_packs_remove_redundant(struct existing_packs *existing, + const char *packdir); +void existing_packs_release(struct existing_packs *existing); + +struct generated_pack; + +struct generated_pack *generated_pack_populate(const char *name, + const char *packtmp); +int generated_pack_has_ext(const struct generated_pack *pack, const char *ext); +void generated_pack_install(struct generated_pack *pack, const char *name, + const char *packdir, const char *packtmp); + +void repack_promisor_objects(struct repository *repo, + const struct pack_objects_args *args, + struct string_list *names, const char *packtmp); + +struct pack_geometry { + struct packed_git **pack; + uint32_t pack_nr, pack_alloc; + uint32_t split; + + int split_factor; +}; + +void pack_geometry_init(struct pack_geometry *geometry, + struct existing_packs *existing, + const struct pack_objects_args *args); +void pack_geometry_split(struct pack_geometry *geometry); +struct packed_git *pack_geometry_preferred_pack(struct pack_geometry *geometry); +void pack_geometry_remove_redundant(struct pack_geometry *geometry, + struct string_list *names, + struct existing_packs *existing, + const char *packdir); +void pack_geometry_release(struct pack_geometry *geometry); + +struct tempfile; + +struct repack_write_midx_opts { + struct existing_packs *existing; + struct pack_geometry *geometry; + struct string_list *names; + const char *refs_snapshot; + const char *packdir; + int show_progress; + int write_bitmaps; + int midx_must_contain_cruft; +}; + +void midx_snapshot_refs(struct repository *repo, struct tempfile *f); +int write_midx_included_packs(struct repack_write_midx_opts *opts); + +int write_filtered_pack(const struct write_pack_opts *opts, + struct existing_packs *existing, + struct string_list *names); + +int write_cruft_pack(const struct write_pack_opts *opts, + const char *cruft_expiration, + unsigned long combine_cruft_below_size, + struct string_list *names, + struct existing_packs *existing); + +#endif /* REPACK_H */ @@ -166,6 +166,7 @@ static int set_recommended_config(int reconfigure) #endif /* Optional */ { "status.aheadBehind", "false" }, + { "commitGraph.changedPaths", "true" }, { "commitGraph.generationVersion", "1" }, { "core.autoCRLF", "false" }, { "core.safeCRLF", "false" }, diff --git a/server-info.c b/server-info.c index 1d33de821e..b9a710544a 100644 --- a/server-info.c +++ b/server-info.c @@ -287,13 +287,12 @@ 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 = packfile_store_get_all_packs(packs); p; p = p->next) { + repo_for_each_pack(r, p) { /* we ignore things on alternate path since they are * not available to the pullers in general. */ diff --git a/sparse-index.c b/sparse-index.c index 5634abafaa..76f90da5f5 100644 --- a/sparse-index.c +++ b/sparse-index.c @@ -32,7 +32,9 @@ int give_advice_on_expansion = 1; "Your working directory likely has contents that are outside of\n" \ "your sparse-checkout patterns. Use 'git sparse-checkout list' to\n" \ "see your sparse-checkout definition and compare it to your working\n" \ - "directory contents. Running 'git clean' may assist in this cleanup." + "directory contents. Cleaning up any merge conflicts or staged\n" \ + "changes before running 'git sparse-checkout clean' or 'git\n" \ + "sparse-checkout reapply' may assist in this cleanup." struct modify_index_context { struct index_state *write; diff --git a/src/cargo-meson.sh b/src/cargo-meson.sh index 99400986d9..3998db0435 100755 --- a/src/cargo-meson.sh +++ b/src/cargo-meson.sh @@ -26,7 +26,14 @@ then exit $RET fi -if ! cmp "$BUILD_DIR/$BUILD_TYPE/libgitcore.a" "$BUILD_DIR/libgitcore.a" >/dev/null 2>&1 +case "$(cargo -vV | sed -s 's/^host: \(.*\)$/\1/')" in + *-windows-*) + LIBNAME=gitcore.lib;; + *) + LIBNAME=libgitcore.a;; +esac + +if ! cmp "$BUILD_DIR/$BUILD_TYPE/$LIBNAME" "$BUILD_DIR/libgitcore.a" >/dev/null 2>&1 then - cp "$BUILD_DIR/$BUILD_TYPE/libgitcore.a" "$BUILD_DIR/libgitcore.a" + cp "$BUILD_DIR/$BUILD_TYPE/$LIBNAME" "$BUILD_DIR/libgitcore.a" fi diff --git a/src/varint.rs b/src/varint.rs index 6e610bdd8e..06492dfc5e 100644 --- a/src/varint.rs +++ b/src/varint.rs @@ -1,3 +1,10 @@ +/// Decode the variable-length integer stored in `bufp` and return the decoded value. +/// +/// Returns 0 in case the decoded integer would overflow u64::MAX. +/// +/// # Safety +/// +/// The buffer must be NUL-terminated to ensure safety. #[no_mangle] pub unsafe extern "C" fn decode_varint(bufp: *mut *const u8) -> u64 { let mut buf = *bufp; @@ -22,6 +29,14 @@ pub unsafe extern "C" fn decode_varint(bufp: *mut *const u8) -> u64 { val } +/// Encode `value` into `buf` as a variable-length integer unless `buf` is null. +/// +/// Returns the number of bytes written, or, if `buf` is null, the number of bytes that would be +/// written to encode the integer. +/// +/// # Safety +/// +/// `buf` must either be null or point to at least 16 bytes of memory. #[no_mangle] pub unsafe extern "C" fn encode_varint(value: u64, buf: *mut u8) -> u8 { let mut varint: [u8; 16] = [0; 16]; diff --git a/t/helper/test-find-pack.c b/t/helper/test-find-pack.c index e001dc3066..fc4b8a77b3 100644 --- a/t/helper/test-find-pack.c +++ b/t/helper/test-find-pack.c @@ -39,11 +39,12 @@ 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 = packfile_store_get_all_packs(the_repository->objects->packfiles); p; p = p->next) + repo_for_each_pack(the_repository, p) { if (find_pack_entry_one(&oid, p)) { printf("%s\n", p->pack_name); actual_count++; } + } if (count > -1 && count != actual_count) die("bad packfile count %d instead of %d", actual_count, count); diff --git a/t/helper/test-pack-mtimes.c b/t/helper/test-pack-mtimes.c index 7c428c1601..7a8ee1de24 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 = packfile_store_get_all_packs(the_repository->objects->packfiles); p; p = p->next) { + repo_for_each_pack(the_repository, p) { strbuf_addstr(&buf, basename(p->pack_name)); strbuf_strip_suffix(&buf, ".pack"); strbuf_addstr(&buf, ".mtimes"); diff --git a/t/lib-gpg.sh b/t/lib-gpg.sh index 937b876bd0..97268ae07c 100644 --- a/t/lib-gpg.sh +++ b/t/lib-gpg.sh @@ -9,6 +9,16 @@ GNUPGHOME="$(pwd)/gpghome" export GNUPGHOME +# All the "test_lazy_prereq GPG*" below should use +# `prepare_gnupghome()` either directly or through a call to +# `test_have_prereq GPG*`. That's because `gpg` and `gpgsm` +# only create the directory specified using "$GNUPGHOME" or +# `--homedir` if it's the default (usually "~/.gnupg"). +prepare_gnupghome() { + mkdir -p "$GNUPGHOME" && + chmod 0700 "$GNUPGHOME" +} + test_lazy_prereq GPG ' gpg_version=$(gpg --version 2>&1) test $? != 127 || exit 1 @@ -38,8 +48,7 @@ test_lazy_prereq GPG ' # To export ownertrust: # gpg --homedir /tmp/gpghome --export-ownertrust \ # > lib-gpg/ownertrust - mkdir "$GNUPGHOME" && - chmod 0700 "$GNUPGHOME" && + prepare_gnupghome && (gpgconf --kill all || : ) && gpg --homedir "${GNUPGHOME}" --import \ "$TEST_DIRECTORY"/lib-gpg/keyring.gpg && @@ -62,7 +71,16 @@ test_lazy_prereq GPG2 ' exit 1 ;; *) + prepare_gnupghome && (gpgconf --kill all || : ) && + + # NEEDSWORK: prepare_gnupghome() should definitely be + # called here, but it looks like it exposes a + # pre-existing, hidden bug by allowing some tests in + # t1016-compatObjectFormat.sh to run instead of being + # skipped. See: + # https://lore.kernel.org/git/ZoV8b2RvYxLOotSJ@teonanacatl.net/ + gpg --homedir "${GNUPGHOME}" --import \ "$TEST_DIRECTORY"/lib-gpg/keyring.gpg && gpg --homedir "${GNUPGHOME}" --import-ownertrust \ @@ -132,8 +150,7 @@ test_lazy_prereq GPGSSH ' test $? = 0 || exit 1; # Setup some keys and an allowed signers file - mkdir -p "${GNUPGHOME}" && - chmod 0700 "${GNUPGHOME}" && + prepare_gnupghome && (setfacl -k "${GNUPGHOME}" 2>/dev/null || true) && ssh-keygen -t ed25519 -N "" -C "git ed25519 key" -f "${GPGSSH_KEY_PRIMARY}" >/dev/null && ssh-keygen -t rsa -b 2048 -N "" -C "git rsa2048 key" -f "${GPGSSH_KEY_SECONDARY}" >/dev/null && diff --git a/t/meson.build b/t/meson.build index 401b24e50e..a5531df415 100644 --- a/t/meson.build +++ b/t/meson.build @@ -238,6 +238,7 @@ integration_tests = [ 't1701-racy-split-index.sh', 't1800-hook.sh', 't1900-repo.sh', + 't1901-repo-structure.sh', 't2000-conflict-when-checking-files-out.sh', 't2002-checkout-cache-u.sh', 't2003-checkout-cache-mkdir.sh', @@ -1037,6 +1038,7 @@ integration_tests = [ 't9303-fast-import-compression.sh', 't9304-fast-import-marks.sh', 't9305-fast-import-signatures.sh', + 't9306-fast-import-signed-tags.sh', 't9350-fast-export.sh', 't9351-fast-export-anonymize.sh', 't9400-git-cvsserver-server.sh', diff --git a/t/perf/p6010-merge-base.sh b/t/perf/p6010-merge-base.sh new file mode 100755 index 0000000000..54f52fa23e --- /dev/null +++ b/t/perf/p6010-merge-base.sh @@ -0,0 +1,101 @@ +#!/bin/sh + +test_description='Test git merge-base' + +. ./perf-lib.sh + +test_perf_fresh_repo + +# +# Creates lots of merges to make history traversal costly. In +# particular it creates 2^($max_level-1)-1 2-way merges on top of +# 2^($max_level-1) root commits. E.g., the commit history looks like +# this for a $max_level of 3: +# +# _1_ +# / \ +# 2 3 +# / \ / \ +# 4 5 6 7 +# +# The numbers are the fast-import marks, which also are the commit +# messages. 1 is the HEAD commit and a merge, 2 and 3 are also merges, +# 4-7 are the root commits. +# +build_history () { + local max_level="$1" && + local level="${2:-1}" && + local mark="${3:-1}" && + if test $level -eq $max_level + then + echo "reset refs/heads/master" && + echo "from $ZERO_OID" && + echo "commit refs/heads/master" && + echo "mark :$mark" && + echo "committer C <c@example.com> 1234567890 +0000" && + echo "data <<EOF" && + echo "$mark" && + echo "EOF" + else + local level1=$((level+1)) && + local mark1=$((2*mark)) && + local mark2=$((2*mark+1)) && + build_history $max_level $level1 $mark1 && + build_history $max_level $level1 $mark2 && + echo "commit refs/heads/master" && + echo "mark :$mark" && + echo "committer C <c@example.com> 1234567890 +0000" && + echo "data <<EOF" && + echo "$mark" && + echo "EOF" && + echo "from :$mark1" && + echo "merge :$mark2" + fi +} + +# +# Creates a new merge history in the same shape as build_history does, +# while reusing the same root commits. This way the two top commits +# have 2^($max_level-1) merge bases between them. +# +build_history2 () { + local max_level="$1" && + local level="${2:-1}" && + local mark="${3:-1}" && + if test $level -lt $max_level + then + local level1=$((level+1)) && + local mark1=$((2*mark)) && + local mark2=$((2*mark+1)) && + build_history2 $max_level $level1 $mark1 && + build_history2 $max_level $level1 $mark2 && + echo "commit refs/heads/master" && + echo "mark :$mark" && + echo "committer C <c@example.com> 1234567890 +0000" && + echo "data <<EOF" && + echo "$mark II" && + echo "EOF" && + echo "from :$mark1" && + echo "merge :$mark2" + fi +} + +test_expect_success 'setup' ' + max_level=15 && + build_history $max_level | git fast-import --export-marks=marks && + git tag one && + build_history2 $max_level | git fast-import --import-marks=marks --force && + git tag two && + git gc && + git log --format=%H --no-merges >expect +' + +test_perf 'git merge-base' ' + git merge-base --all one two >actual +' + +test_expect_success 'verify result' ' + test_cmp expect actual +' + +test_done diff --git a/t/t0008-ignores.sh b/t/t0008-ignores.sh index 273d71411f..db8bde280e 100755 --- a/t/t0008-ignores.sh +++ b/t/t0008-ignores.sh @@ -847,6 +847,17 @@ test_expect_success 'directories and ** matches' ' test_cmp expect actual ' +test_expect_success '** not confused by matching leading prefix' ' + cat >.gitignore <<-\EOF && + foo**/bar + EOF + git check-ignore foobar foo/bar >actual && + cat >expect <<-\EOF && + foo/bar + EOF + test_cmp expect actual +' + ############################################################################ # # test whitespace handling diff --git a/t/t0600-reffiles-backend.sh b/t/t0600-reffiles-backend.sh index 1e62c791d9..b11126ed47 100755 --- a/t/t0600-reffiles-backend.sh +++ b/t/t0600-reffiles-backend.sh @@ -477,9 +477,29 @@ test_expect_success SYMLINKS 'symref transaction supports symlinks' ' prepare commit EOF - git update-ref --no-deref --stdin <stdin && - test_path_is_symlink .git/TEST_SYMREF_HEAD && - test "$(test_readlink .git/TEST_SYMREF_HEAD)" = refs/heads/new + git update-ref --no-deref --stdin <stdin 2>err && + if test_have_prereq WITH_BREAKING_CHANGES + then + test_path_is_file .git/TEST_SYMREF_HEAD && + echo "ref: refs/heads/new" >expect && + test_cmp expect .git/TEST_SYMREF_HEAD && + test_must_be_empty err + else + test_path_is_symlink .git/TEST_SYMREF_HEAD && + test "$(test_readlink .git/TEST_SYMREF_HEAD)" = refs/heads/new && + cat >expect <<-EOF && + warning: ${SQ}core.preferSymlinkRefs=true${SQ} is nominated for removal. + hint: The use of symbolic links for symbolic refs is deprecated + hint: and will be removed in Git 3.0. The configuration that + hint: tells Git to use them is thus going away. You can unset + hint: it with: + hint: + hint: git config unset core.preferSymlinkRefs + hint: + hint: Git will then use the textual symref format instead. + EOF + test_cmp expect err + fi ' test_expect_success 'symref transaction supports false symlink config' ' diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh index ab3a105fff..b2da4feaef 100755 --- a/t/t1091-sparse-checkout-builtin.sh +++ b/t/t1091-sparse-checkout-builtin.sh @@ -1050,5 +1050,180 @@ test_expect_success 'check-rules null termination' ' test_cmp expect actual ' +test_expect_success 'clean' ' + git -C repo sparse-checkout set --cone deep/deeper1 && + git -C repo sparse-checkout reapply && + mkdir -p repo/deep/deeper2 repo/folder1/extra/inside && + + # Add untracked files + touch repo/deep/deeper2/file && + touch repo/folder1/extra/inside/file && + + test_must_fail git -C repo sparse-checkout clean 2>err && + grep "refusing to clean" err && + + git -C repo config clean.requireForce true && + test_must_fail git -C repo sparse-checkout clean 2>err && + grep "refusing to clean" err && + + cat >expect <<-\EOF && + Would remove deep/deeper2/ + Would remove folder1/ + EOF + + git -C repo sparse-checkout clean --dry-run >out && + test_cmp expect out && + test_path_exists repo/deep/deeper2 && + test_path_exists repo/folder1/extra/inside/file && + + cat >expect <<-\EOF && + Would remove deep/deeper2/file + Would remove folder1/extra/inside/file + EOF + + git -C repo sparse-checkout clean --dry-run --verbose >out && + test_cmp expect out && + + cat >expect <<-\EOF && + Removing deep/deeper2/ + Removing folder1/ + EOF + + git -C repo sparse-checkout clean -f >out && + test_cmp expect out && + + test_path_is_missing repo/deep/deeper2 && + test_path_is_missing repo/folder1 +' + +test_expect_success 'clean with sparse file states' ' + test_when_finished git reset --hard && + git -C repo sparse-checkout set --cone deep/deeper1 && + mkdir repo/folder2 && + + # The previous test case checked the -f option, so + # test the config option in this one. + git -C repo config clean.requireForce false && + + # create an untracked file and a modified file + touch repo/folder2/file && + echo dirty >repo/folder2/a && + + # First clean/reapply pass will do nothing. + git -C repo sparse-checkout clean >out && + test_must_be_empty out && + test_path_exists repo/folder2/a && + test_path_exists repo/folder2/file && + + git -C repo sparse-checkout reapply 2>err && + test_grep folder2 err && + test_path_exists repo/folder2/a && + test_path_exists repo/folder2/file && + + # Now, stage the change to the tracked file. + git -C repo add --sparse folder2/a && + + # Clean will continue not doing anything. + git -C repo sparse-checkout clean >out && + test_line_count = 0 out && + test_path_exists repo/folder2/a && + test_path_exists repo/folder2/file && + + # But we can reapply to remove the staged change. + git -C repo sparse-checkout reapply 2>err && + test_grep folder2 err && + test_path_is_missing repo/folder2/a && + test_path_exists repo/folder2/file && + + # We can clean now. + cat >expect <<-\EOF && + Removing folder2/ + EOF + git -C repo sparse-checkout clean >out && + test_cmp expect out && + test_path_is_missing repo/folder2 && + + # At the moment, the file is staged. + cat >expect <<-\EOF && + M folder2/a + EOF + + git -C repo status -s >out && + test_cmp expect out && + + # Reapply persists the modified state. + git -C repo sparse-checkout reapply && + cat >expect <<-\EOF && + M folder2/a + EOF + git -C repo status -s >out && + test_cmp expect out && + + # Committing the change leads to resolved status. + git -C repo commit -m "modified" && + git -C repo status -s >out && + test_must_be_empty out && + + # Repeat, but this time commit before reapplying. + mkdir repo/folder2/ && + echo dirtier >repo/folder2/a && + git -C repo add --sparse folder2/a && + git -C repo sparse-checkout clean >out && + test_must_be_empty out && + test_path_exists repo/folder2/a && + + # Committing without reapplying makes it look like a deletion + # due to no skip-worktree bit. + git -C repo commit -m "dirtier" && + git -C repo status -s >out && + test_must_be_empty out && + + git -C repo sparse-checkout reapply && + git -C repo status -s >out && + test_must_be_empty out +' + +test_expect_success 'sparse-checkout operations with merge conflicts' ' + git clone repo merge && + + ( + cd merge && + mkdir -p folder1/even/more/dirs && + echo base >folder1/even/more/dirs/file && + git add folder1 && + git commit -m "base" && + + git checkout -b right&& + echo right >folder1/even/more/dirs/file && + git commit -a -m "right" && + + git checkout -b left HEAD~1 && + echo left >folder1/even/more/dirs/file && + git commit -a -m "left" && + + git checkout -b merge && + git sparse-checkout set deep/deeper1 && + + test_must_fail git merge -m "will-conflict" right && + + test_must_fail git sparse-checkout clean -f 2>err && + grep "failed to convert index to a sparse index" err && + + echo merged >folder1/even/more/dirs/file && + git add --sparse folder1 && + git merge --continue && + + test_path_exists folder1/even/more/dirs/file && + + # clean does not remove the file, because the + # SKIP_WORKTREE bit was not cleared by the merge command. + git sparse-checkout clean -f >out && + test_line_count = 0 out && + test_path_exists folder1/even/more/dirs/file && + + git sparse-checkout reapply && + test_path_is_missing folder1 + ) +' test_done diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh new file mode 100755 index 0000000000..36a71a144e --- /dev/null +++ b/t/t1901-repo-structure.sh @@ -0,0 +1,129 @@ +#!/bin/sh + +test_description='test git repo structure' + +. ./test-lib.sh + +test_expect_success 'empty repository' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + cat >expect <<-\EOF && + | Repository structure | Value | + | -------------------- | ----- | + | * References | | + | * Count | 0 | + | * Branches | 0 | + | * Tags | 0 | + | * Remotes | 0 | + | * Others | 0 | + | | | + | * Reachable objects | | + | * Count | 0 | + | * Commits | 0 | + | * Trees | 0 | + | * Blobs | 0 | + | * Tags | 0 | + EOF + + git repo structure >out 2>err && + + test_cmp expect out && + test_line_count = 0 err + ) +' + +test_expect_success 'repository with references and objects' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit_bulk 42 && + git tag -a foo -m bar && + + oid="$(git rev-parse HEAD)" && + git update-ref refs/remotes/origin/foo "$oid" && + + # Also creates a commit, tree, and blob. + git notes add -m foo && + + cat >expect <<-\EOF && + | Repository structure | Value | + | -------------------- | ----- | + | * References | | + | * Count | 4 | + | * Branches | 1 | + | * Tags | 1 | + | * Remotes | 1 | + | * Others | 1 | + | | | + | * Reachable objects | | + | * Count | 130 | + | * Commits | 43 | + | * Trees | 43 | + | * Blobs | 43 | + | * Tags | 1 | + EOF + + git repo structure >out 2>err && + + test_cmp expect out && + test_line_count = 0 err + ) +' + +test_expect_success 'keyvalue and nul format' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit_bulk 42 && + git tag -a foo -m bar && + + cat >expect <<-\EOF && + references.branches.count=1 + references.tags.count=1 + references.remotes.count=0 + references.others.count=0 + objects.commits.count=42 + objects.trees.count=42 + objects.blobs.count=42 + objects.tags.count=1 + EOF + + git repo structure --format=keyvalue >out 2>err && + + test_cmp expect out && + test_line_count = 0 err && + + # Replace key and value delimiters for nul format. + tr "\n=" "\0\n" <expect >expect_nul && + git repo structure --format=nul >out 2>err && + + test_cmp expect_nul out && + test_line_count = 0 err + ) +' + +test_expect_success 'progress meter option' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit foo && + + GIT_PROGRESS_DELAY=0 git repo structure --progress >out 2>err && + + test_file_not_empty out && + test_grep "Counting references: 2, done." err && + test_grep "Counting objects: 3, done." err && + + GIT_PROGRESS_DELAY=0 git repo structure --no-progress >out 2>err && + + test_file_not_empty out && + test_line_count = 0 err + ) +' + +test_done diff --git a/t/t3701-add-interactive.sh b/t/t3701-add-interactive.sh index 851ca6dd91..4285314f35 100755 --- a/t/t3701-add-interactive.sh +++ b/t/t3701-add-interactive.sh @@ -1431,4 +1431,15 @@ test_expect_success 'invalid option s is rejected' ' test_cmp expect actual ' +test_expect_success 'EOF quits' ' + echo a >file && + echo a >file2 && + git add file file2 && + echo X >file && + echo X >file2 && + git add -p </dev/null >out && + test_grep file out && + test_grep ! file2 out +' + test_done diff --git a/t/t4013-diff-various.sh b/t/t4013-diff-various.sh index 55a06eadb3..d35695f5b0 100755 --- a/t/t4013-diff-various.sh +++ b/t/t4013-diff-various.sh @@ -661,6 +661,43 @@ test_expect_success 'diff -I<regex>: ignore matching file' ' test_grep ! "file1" actual ' +test_expect_success 'diff -I<regex>: ignore all content changes' ' + test_when_finished "git rm -f file1 file2 file3" && + : >file1 && + git add file1 && + : >file2 && + git add file2 && + : >file3 && + git add file3 && + + rm -f file1 file2 && + mkdir file2 && + echo "A" >file3 && + A_hash=$(git hash-object -w file3) && + echo "B" >file3 && + B_hash=$(git hash-object -w file3) && + cat <<-EOF | git update-index --index-info && + 100644 $A_hash 1 file3 + 100644 $B_hash 2 file3 + EOF + + test_diff_no_content_changes () { + git diff $1 --ignore-blank-lines -I".*" >actual && + test_line_count = 3 actual && + test_grep "file1" actual && + test_grep "file2" actual && + test_grep "file3" actual && + test_grep ! "diff --git" actual + } && + test_diff_no_content_changes "--raw" && + test_diff_no_content_changes "--name-only" && + test_diff_no_content_changes "--name-status" && + + : >actual && + test_must_fail git diff --quiet -I".*" >actual && + test_must_be_empty actual +' + # check_prefix <patch> <src> <dst> # check only lines with paths to avoid dependency on exact oid/contents check_prefix () { diff --git a/t/t4020-diff-external.sh b/t/t4020-diff-external.sh index c8a23d5148..7ec5854f74 100755 --- a/t/t4020-diff-external.sh +++ b/t/t4020-diff-external.sh @@ -44,6 +44,16 @@ test_expect_success 'GIT_EXTERNAL_DIFF environment and --no-ext-diff' ' ' +test_expect_success 'GIT_EXTERNAL_DIFF and --output' ' + cat >expect <<-EOF && + file $(git rev-parse --verify HEAD:file) 100644 file $(test_oid zero) 100644 + EOF + GIT_EXTERNAL_DIFF=echo git diff --output=out >stdout && + cut -d" " -f1,3- <out >actual && + test_must_be_empty stdout && + test_cmp expect actual +' + test_expect_success SYMLINKS 'typechange diff' ' rm -f file && ln -s elif file && diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 0b3404f58f..98c6910963 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -946,4 +946,48 @@ test_expect_success 'stale commit cannot be parsed when traversing graph' ' ) ' +test_expect_success 'config commitGraph.changedPaths acts like --changed-paths' ' + git init config-changed-paths && + ( + cd config-changed-paths && + + # commitGraph.changedPaths is not set and it should not write Bloom filters + test_commit first && + GIT_PROGRESS_DELAY=0 git commit-graph write --reachable --progress 2>error && + test_grep ! "Bloom filters" error && + + # Set commitGraph.changedPaths to true and it should write Bloom filters + test_commit second && + git config commitGraph.changedPaths true && + GIT_PROGRESS_DELAY=0 git commit-graph write --reachable --progress 2>error && + test_grep "Bloom filters" error && + + # Add one more config commitGraph.changedPaths as false to disable the previous true config value + # It should still write Bloom filters due to existing filters + test_commit third && + git config --add commitGraph.changedPaths false && + GIT_PROGRESS_DELAY=0 git commit-graph write --reachable --progress 2>error && + test_grep "Bloom filters" error && + + # commitGraph.changedPaths is still false and command line options should take precedence + test_commit fourth && + GIT_PROGRESS_DELAY=0 git commit-graph write --no-changed-paths --reachable --progress 2>error && + test_grep ! "Bloom filters" error && + GIT_PROGRESS_DELAY=0 git commit-graph write --reachable --progress 2>error && + test_grep ! "Bloom filters" error && + + # commitGraph.changedPaths is all cleared and then set to false again, command line options should take precedence + test_commit fifth && + git config --unset-all commitGraph.changedPaths && + git config commitGraph.changedPaths false && + GIT_PROGRESS_DELAY=0 git commit-graph write --changed-paths --reachable --progress 2>error && + test_grep "Bloom filters" error && + + # commitGraph.changedPaths is still false and it should write Bloom filters due to existing filters + test_commit sixth && + GIT_PROGRESS_DELAY=0 git commit-graph write --reachable --progress 2>error && + test_grep "Bloom filters" error + ) +' + test_done diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh index ddd273d8dc..614184a097 100755 --- a/t/t7900-maintenance.sh +++ b/t/t7900-maintenance.sh @@ -465,6 +465,176 @@ test_expect_success 'maintenance.incremental-repack.auto (when config is unset)' ) ' +run_and_verify_geometric_pack () { + EXPECTED_PACKS="$1" && + + # Verify that we perform a geometric repack. + rm -f "trace2.txt" && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git maintenance run --task=geometric-repack 2>/dev/null && + test_subcommand git repack -d -l --geometric=2 \ + --quiet --write-midx <trace2.txt && + + # Verify that the number of packfiles matches our expectation. + ls -l .git/objects/pack/*.pack >packfiles && + test_line_count = "$EXPECTED_PACKS" packfiles && + + # And verify that there are no loose objects anymore. + git count-objects -v >count && + test_grep '^count: 0$' count +} + +test_expect_success 'geometric repacking task' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + git config set maintenance.auto false && + test_commit initial && + + # The initial repack causes an all-into-one repack. + GIT_TRACE2_EVENT="$(pwd)/initial-repack.txt" \ + git maintenance run --task=geometric-repack 2>/dev/null && + test_subcommand git repack -d -l --cruft --cruft-expiration=2.weeks.ago \ + --quiet --write-midx <initial-repack.txt && + + # Repacking should now cause a no-op geometric repack because + # no packfiles need to be combined. + ls -l .git/objects/pack/*.pack >before && + run_and_verify_geometric_pack 1 && + ls -l .git/objects/pack/*.pack >after && + test_cmp before after && + + # This incremental change creates a new packfile that only + # soaks up loose objects. The packfiles are not getting merged + # at this point. + test_commit loose && + run_and_verify_geometric_pack 2 && + + # Both packfiles have 3 objects, so the next run would cause us + # to merge all packfiles together. This should be turned into + # an all-into-one-repack. + GIT_TRACE2_EVENT="$(pwd)/all-into-one-repack.txt" \ + git maintenance run --task=geometric-repack 2>/dev/null && + test_subcommand git repack -d -l --cruft --cruft-expiration=2.weeks.ago \ + --quiet --write-midx <all-into-one-repack.txt && + + # The geometric repack soaks up unreachable objects. + echo blob-1 | git hash-object -w --stdin -t blob && + run_and_verify_geometric_pack 2 && + + # A second unreachable object should be written into another packfile. + echo blob-2 | git hash-object -w --stdin -t blob && + run_and_verify_geometric_pack 3 && + + # And these two small packs should now be merged via the + # geometric repack. The large packfile should remain intact. + run_and_verify_geometric_pack 2 && + + # If we now add two more objects and repack twice we should + # then see another all-into-one repack. This time around + # though, as we have unreachable objects, we should also see a + # cruft pack. + echo blob-3 | git hash-object -w --stdin -t blob && + echo blob-4 | git hash-object -w --stdin -t blob && + run_and_verify_geometric_pack 3 && + GIT_TRACE2_EVENT="$(pwd)/cruft-repack.txt" \ + git maintenance run --task=geometric-repack 2>/dev/null && + test_subcommand git repack -d -l --cruft --cruft-expiration=2.weeks.ago \ + --quiet --write-midx <cruft-repack.txt && + ls .git/objects/pack/*.pack >packs && + test_line_count = 2 packs && + ls .git/objects/pack/*.mtimes >cruft && + test_line_count = 1 cruft + ) +' + +test_geometric_repack_needed () { + NEEDED="$1" + GEOMETRIC_CONFIG="$2" && + rm -f trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git ${GEOMETRIC_CONFIG:+-c maintenance.geometric-repack.$GEOMETRIC_CONFIG} \ + maintenance run --auto --task=geometric-repack 2>/dev/null && + case "$NEEDED" in + true) + test_grep "\[\"git\",\"repack\"," trace2.txt;; + false) + ! test_grep "\[\"git\",\"repack\"," trace2.txt;; + *) + BUG "invalid parameter: $NEEDED";; + esac +} + +test_expect_success 'geometric repacking with --auto' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + + # An empty repository does not need repacking, except when + # explicitly told to do it. + test_geometric_repack_needed false && + test_geometric_repack_needed false auto=0 && + test_geometric_repack_needed false auto=1 && + test_geometric_repack_needed true auto=-1 && + + test_oid_init && + + # Loose objects cause a repack when crossing the limit. Note + # that the number of objects gets extrapolated by having a look + # at the "objects/17/" shard. + test_commit "$(test_oid blob17_1)" && + test_geometric_repack_needed false && + test_commit "$(test_oid blob17_2)" && + test_geometric_repack_needed false auto=257 && + test_geometric_repack_needed true auto=256 && + + # Force another repack. + test_commit first && + test_commit second && + test_geometric_repack_needed true auto=-1 && + + # We now have two packfiles that would be merged together. As + # such, the repack should always happen unless the user has + # disabled the auto task. + test_geometric_repack_needed false auto=0 && + test_geometric_repack_needed true auto=9000 + ) +' + +test_expect_success 'geometric repacking honors configured split factor' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + git config set maintenance.auto false && + + # Create three different packs with 9, 2 and 1 object, respectively. + # This is done so that only a subset of packs would be merged + # together so that we can verify that `git repack` receives the + # correct geometric factor. + for i in $(test_seq 9) + do + echo first-$i | git hash-object -w --stdin -t blob || return 1 + done && + git repack --geometric=2 -d && + + for i in $(test_seq 2) + do + echo second-$i | git hash-object -w --stdin -t blob || return 1 + done && + git repack --geometric=2 -d && + + echo third | git hash-object -w --stdin -t blob && + git repack --geometric=2 -d && + + test_geometric_repack_needed false splitFactor=2 && + test_geometric_repack_needed true splitFactor=3 && + test_subcommand git repack -d -l --geometric=3 --quiet --write-midx <trace2.txt + ) +' + test_expect_success 'pack-refs task' ' for n in $(test_seq 1 5) do @@ -716,6 +886,76 @@ test_expect_success 'maintenance.strategy inheritance' ' <modified-daily.txt ' +test_strategy () { + STRATEGY="$1" + shift + + cat >expect && + rm -f trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -c maintenance.strategy=$STRATEGY maintenance run --quiet "$@" && + sed -n 's/{"event":"child_start","sid":"[^/"]*",.*,"argv":\["\(.*\)\"]}/\1/p' <trace2.txt | + sed 's/","/ /g' >actual + test_cmp expect actual +} + +test_expect_success 'maintenance.strategy is respected' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + + test_must_fail git -c maintenance.strategy=unknown maintenance run 2>err && + test_grep "unknown maintenance strategy: .unknown." err && + + test_strategy incremental <<-\EOF && + git pack-refs --all --prune + git reflog expire --all + git gc --quiet --no-detach --skip-foreground-tasks + EOF + + test_strategy incremental --schedule=weekly <<-\EOF && + git pack-refs --all --prune + git prune-packed --quiet + git multi-pack-index write --no-progress + git multi-pack-index expire --no-progress + git multi-pack-index repack --no-progress --batch-size=1 + git commit-graph write --split --reachable --no-progress + EOF + + test_strategy gc <<-\EOF && + git pack-refs --all --prune + git reflog expire --all + git gc --quiet --no-detach --skip-foreground-tasks + EOF + + test_strategy gc --schedule=weekly <<-\EOF && + git pack-refs --all --prune + git reflog expire --all + git gc --quiet --no-detach --skip-foreground-tasks + EOF + + test_strategy geometric <<-\EOF && + git pack-refs --all --prune + git reflog expire --all + git repack -d -l --geometric=2 --quiet --write-midx + git commit-graph write --split --reachable --no-progress + git worktree prune --expire 3.months.ago + git rerere gc + EOF + + test_strategy geometric --schedule=weekly <<-\EOF + git pack-refs --all --prune + git reflog expire --all + git repack -d -l --geometric=2 --quiet --write-midx + git commit-graph write --split --reachable --no-progress + git worktree prune --expire 3.months.ago + git rerere gc + EOF + ) +' + test_expect_success 'register and unregister' ' test_when_finished git config --global --unset-all maintenance.repo && @@ -1093,6 +1333,11 @@ test_expect_success 'fails when running outside of a repository' ' nongit test_must_fail git maintenance unregister ' +test_expect_success 'fails when configured to use an invalid strategy' ' + test_must_fail git -c maintenance.strategy=invalid maintenance run --schedule=hourly 2>err && + test_grep "unknown maintenance strategy: .invalid." err +' + test_expect_success 'register and unregister bare repo' ' test_when_finished "git config --global --unset-all maintenance.repo || :" && test_might_fail git config --global --unset-all maintenance.repo && diff --git a/t/t9306-fast-import-signed-tags.sh b/t/t9306-fast-import-signed-tags.sh new file mode 100755 index 0000000000..363619e7d1 --- /dev/null +++ b/t/t9306-fast-import-signed-tags.sh @@ -0,0 +1,80 @@ +#!/bin/sh + +test_description='git fast-import --signed-tags=<mode>' + +GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main + +. ./test-lib.sh +. "$TEST_DIRECTORY/lib-gpg.sh" + +test_expect_success 'set up unsigned initial commit and import repo' ' + test_commit first && + git init new +' + +test_expect_success 'import no signed tag with --signed-tags=abort' ' + git fast-export --signed-tags=verbatim >output && + git -C new fast-import --quiet --signed-tags=abort <output +' + +test_expect_success GPG 'set up OpenPGP signed tag' ' + git tag -s -m "OpenPGP signed tag" openpgp-signed first && + OPENPGP_SIGNED=$(git rev-parse --verify refs/tags/openpgp-signed) && + git fast-export --signed-tags=verbatim openpgp-signed >output +' + +test_expect_success GPG 'import OpenPGP signed tag with --signed-tags=abort' ' + test_must_fail git -C new fast-import --quiet --signed-tags=abort <output +' + +test_expect_success GPG 'import OpenPGP signed tag with --signed-tags=verbatim' ' + git -C new fast-import --quiet --signed-tags=verbatim <output >log 2>&1 && + IMPORTED=$(git -C new rev-parse --verify refs/tags/openpgp-signed) && + test $OPENPGP_SIGNED = $IMPORTED && + test_must_be_empty log +' + +test_expect_success GPGSM 'setup X.509 signed tag' ' + test_config gpg.format x509 && + test_config user.signingkey $GIT_COMMITTER_EMAIL && + + git tag -s -m "X.509 signed tag" x509-signed first && + X509_SIGNED=$(git rev-parse --verify refs/tags/x509-signed) && + git fast-export --signed-tags=verbatim x509-signed >output +' + +test_expect_success GPGSM 'import X.509 signed tag with --signed-tags=warn-strip' ' + git -C new fast-import --quiet --signed-tags=warn-strip <output >log 2>&1 && + test_grep "stripping a tag signature for tag '\''x509-signed'\''" log && + IMPORTED=$(git -C new rev-parse --verify refs/tags/x509-signed) && + test $X509_SIGNED != $IMPORTED && + git -C new cat-file -p x509-signed >out && + test_grep ! "SIGNED MESSAGE" out +' + +test_expect_success GPGSSH 'setup SSH signed tag' ' + test_config gpg.format ssh && + test_config user.signingkey "${GPGSSH_KEY_PRIMARY}" && + + git tag -s -m "SSH signed tag" ssh-signed first && + SSH_SIGNED=$(git rev-parse --verify refs/tags/ssh-signed) && + git fast-export --signed-tags=verbatim ssh-signed >output +' + +test_expect_success GPGSSH 'import SSH signed tag with --signed-tags=warn-verbatim' ' + git -C new fast-import --quiet --signed-tags=warn-verbatim <output >log 2>&1 && + test_grep "importing a tag signature verbatim for tag '\''ssh-signed'\''" log && + IMPORTED=$(git -C new rev-parse --verify refs/tags/ssh-signed) && + test $SSH_SIGNED = $IMPORTED +' + +test_expect_success GPGSSH 'import SSH signed tag with --signed-tags=strip' ' + git -C new fast-import --quiet --signed-tags=strip <output >log 2>&1 && + test_must_be_empty log && + IMPORTED=$(git -C new rev-parse --verify refs/tags/ssh-signed) && + test $SSH_SIGNED != $IMPORTED && + git -C new cat-file -p ssh-signed >out && + test_grep ! "SSH SIGNATURE" out +' + +test_done diff --git a/t/t9350-fast-export.sh b/t/t9350-fast-export.sh index 8f85c69d62..3d153a4805 100755 --- a/t/t9350-fast-export.sh +++ b/t/t9350-fast-export.sh @@ -35,6 +35,7 @@ test_expect_success 'setup' ' git commit -m sitzt file2 && test_tick && git tag -a -m valentin muss && + ANNOTATED_TAG_COUNT=1 && git merge -s ours main ' @@ -229,7 +230,8 @@ EOF test_expect_success 'set up faked signed tag' ' - git fast-import <signed-tag-import + git fast-import <signed-tag-import && + ANNOTATED_TAG_COUNT=$((ANNOTATED_TAG_COUNT + 1)) ' @@ -277,6 +279,42 @@ test_expect_success 'signed-tags=warn-strip' ' test -s err ' +test_expect_success GPGSM 'setup X.509 signed tag' ' + test_config gpg.format x509 && + test_config user.signingkey $GIT_COMMITTER_EMAIL && + + git tag -s -m "X.509 signed tag" x509-signed $(git rev-parse HEAD) && + ANNOTATED_TAG_COUNT=$((ANNOTATED_TAG_COUNT + 1)) +' + +test_expect_success GPGSM 'signed-tags=verbatim with X.509' ' + git fast-export --signed-tags=verbatim x509-signed > output && + test_grep "SIGNED MESSAGE" output +' + +test_expect_success GPGSM 'signed-tags=strip with X.509' ' + git fast-export --signed-tags=strip x509-signed > output && + test_grep ! "SIGNED MESSAGE" output +' + +test_expect_success GPGSSH 'setup SSH signed tag' ' + test_config gpg.format ssh && + test_config user.signingkey "${GPGSSH_KEY_PRIMARY}" && + + git tag -s -m "SSH signed tag" ssh-signed $(git rev-parse HEAD) && + ANNOTATED_TAG_COUNT=$((ANNOTATED_TAG_COUNT + 1)) +' + +test_expect_success GPGSSH 'signed-tags=verbatim with SSH' ' + git fast-export --signed-tags=verbatim ssh-signed > output && + test_grep "SSH SIGNATURE" output +' + +test_expect_success GPGSSH 'signed-tags=strip with SSH' ' + git fast-export --signed-tags=strip ssh-signed > output && + test_grep ! "SSH SIGNATURE" output +' + test_expect_success GPG 'set up signed commit' ' # Generate a commit with both "gpgsig" and "encoding" set, so @@ -491,8 +529,9 @@ test_expect_success 'fast-export -C -C | fast-import' ' test_expect_success 'fast-export | fast-import when main is tagged' ' git tag -m msg last && + ANNOTATED_TAG_COUNT=$((ANNOTATED_TAG_COUNT + 1)) && git fast-export -C -C --signed-tags=strip --all > output && - test $(grep -c "^tag " output) = 3 + test $(grep -c "^tag " output) = $ANNOTATED_TAG_COUNT ' @@ -506,12 +545,13 @@ test_expect_success 'cope with tagger-less tags' ' TAG=$(git hash-object --literally -t tag -w tag-content) && git update-ref refs/tags/sonnenschein $TAG && + ANNOTATED_TAG_COUNT=$((ANNOTATED_TAG_COUNT + 1)) && git fast-export -C -C --signed-tags=strip --all > output && - test $(grep -c "^tag " output) = 4 && + test $(grep -c "^tag " output) = $ANNOTATED_TAG_COUNT && ! grep "Unspecified Tagger" output && git fast-export -C -C --signed-tags=strip --all \ --fake-missing-tagger > output && - test $(grep -c "^tag " output) = 4 && + test $(grep -c "^tag " output) = $ANNOTATED_TAG_COUNT && grep "Unspecified Tagger" output ' |